diff options
Diffstat (limited to 'parser/html/javasrc')
| -rw-r--r-- | parser/html/javasrc/AttributeName.java | 2278 | ||||
| -rw-r--r-- | parser/html/javasrc/ElementName.java | 1896 | ||||
| -rw-r--r-- | parser/html/javasrc/Portability.java | 159 | ||||
| -rw-r--r-- | parser/html/javasrc/README.txt | 6 | ||||
| -rw-r--r-- | parser/html/javasrc/StackNode.java | 364 | ||||
| -rw-r--r-- | parser/html/javasrc/StateSnapshot.java | 205 | ||||
| -rw-r--r-- | parser/html/javasrc/Tokenizer.java | 7636 | ||||
| -rw-r--r-- | parser/html/javasrc/TreeBuilder.java | 6550 | ||||
| -rw-r--r-- | parser/html/javasrc/UTF16Buffer.java | 151 |
9 files changed, 19245 insertions, 0 deletions
diff --git a/parser/html/javasrc/AttributeName.java b/parser/html/javasrc/AttributeName.java new file mode 100644 index 0000000000..8014cd8043 --- /dev/null +++ b/parser/html/javasrc/AttributeName.java @@ -0,0 +1,2278 @@ +/* + * Copyright (c) 2008-2017 Mozilla Foundation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + */ + +package nu.validator.htmlparser.impl; + +import java.util.Arrays; +import java.util.Collections; +import java.util.LinkedList; +import java.util.List; + +import nu.validator.htmlparser.annotation.Inline; +import nu.validator.htmlparser.annotation.Local; +import nu.validator.htmlparser.annotation.NoLength; +import nu.validator.htmlparser.annotation.NsUri; +import nu.validator.htmlparser.annotation.Prefix; +import nu.validator.htmlparser.annotation.QName; +import nu.validator.htmlparser.annotation.Unsigned; +import nu.validator.htmlparser.common.Interner; + +public final class AttributeName +// Uncomment to regenerate +// implements Comparable<AttributeName> +{ + // [NOCPP[ + + public static final int NCNAME_HTML = 1; + + public static final int NCNAME_FOREIGN = (1 << 1) | (1 << 2); + + public static final int NCNAME_LANG = (1 << 3); + + public static final int IS_XMLNS = (1 << 4); + + public static final int CASE_FOLDED = (1 << 5); + + public static final int BOOLEAN = (1 << 6); + + // ]NOCPP] + + /** + * An array representing no namespace regardless of namespace mode (HTML, + * SVG, MathML, lang-mapping HTML) used. + */ + static final @NoLength @NsUri String[] ALL_NO_NS = { "", "", "", + // [NOCPP[ + "" + // ]NOCPP] + }; + + /** + * An array that has no namespace for the HTML mode but the XMLNS namespace + * for the SVG and MathML modes. + */ + private static final @NoLength @NsUri String[] XMLNS_NS = { "", + "http://www.w3.org/2000/xmlns/", "http://www.w3.org/2000/xmlns/", + // [NOCPP[ + "" + // ]NOCPP] + }; + + /** + * An array that has no namespace for the HTML mode but the XML namespace + * for the SVG and MathML modes. + */ + private static final @NoLength @NsUri String[] XML_NS = { "", + "http://www.w3.org/XML/1998/namespace", + "http://www.w3.org/XML/1998/namespace", + // [NOCPP[ + "" + // ]NOCPP] + }; + + /** + * An array that has no namespace for the HTML mode but the XLink namespace + * for the SVG and MathML modes. + */ + private static final @NoLength @NsUri String[] XLINK_NS = { "", + "http://www.w3.org/1999/xlink", "http://www.w3.org/1999/xlink", + // [NOCPP[ + "" + // ]NOCPP] + }; + + // [NOCPP[ + /** + * An array that has no namespace for the HTML, SVG and MathML modes but has + * the XML namespace for the lang-mapping HTML mode. + */ + private static final @NoLength @NsUri String[] LANG_NS = { "", "", "", + "http://www.w3.org/XML/1998/namespace" }; + + // ]NOCPP] + + /** + * An array for no prefixes in any mode. + */ + static final @NoLength @Prefix String[] ALL_NO_PREFIX = { null, null, null, + // [NOCPP[ + null + // ]NOCPP] + }; + + /** + * An array for no prefixe in the HTML mode and the <code>xmlns</code> + * prefix in the SVG and MathML modes. + */ + private static final @NoLength @Prefix String[] XMLNS_PREFIX = { null, + "xmlns", "xmlns", + // [NOCPP[ + null + // ]NOCPP] + }; + + /** + * An array for no prefixe in the HTML mode and the <code>xlink</code> + * prefix in the SVG and MathML modes. + */ + private static final @NoLength @Prefix String[] XLINK_PREFIX = { null, + "xlink", "xlink", + // [NOCPP[ + null + // ]NOCPP] + }; + + /** + * An array for no prefixe in the HTML mode and the <code>xml</code> prefix + * in the SVG and MathML modes. + */ + private static final @NoLength @Prefix String[] XML_PREFIX = { null, "xml", + "xml", + // [NOCPP[ + null + // ]NOCPP] + }; + + // [NOCPP[ + + private static final @NoLength @Prefix String[] LANG_PREFIX = { null, null, + null, "xml" }; + + private static @QName String[] COMPUTE_QNAME(String[] local, String[] prefix) { + @QName String[] arr = new String[4]; + for (int i = 0; i < arr.length; i++) { + if (prefix[i] == null) { + arr[i] = local[i]; + } else { + arr[i] = (prefix[i] + ':' + local[i]).intern(); + } + } + return arr; + } + + // ]NOCPP] + + /** + * An initialization helper for having a one name in the SVG mode and + * another name in the other modes. + * + * @param name + * the name for the non-SVG modes + * @param camel + * the name for the SVG mode + * @return the initialized name array + */ + private static @NoLength @Local String[] SVG_DIFFERENT(@Local String name, + @Local String camel) { + @NoLength @Local String[] arr = new String[4]; + arr[0] = name; + arr[1] = name; + arr[2] = camel; + // [NOCPP[ + arr[3] = name; + // ]NOCPP] + return arr; + } + + /** + * An initialization helper for having a one name in the MathML mode and + * another name in the other modes. + * + * @param name + * the name for the non-MathML modes + * @param camel + * the name for the MathML mode + * @return the initialized name array + */ + private static @NoLength @Local String[] MATH_DIFFERENT(@Local String name, + @Local String camel) { + @NoLength @Local String[] arr = new String[4]; + arr[0] = name; + arr[1] = camel; + arr[2] = name; + // [NOCPP[ + arr[3] = name; + // ]NOCPP] + return arr; + } + + /** + * An initialization helper for having a different local name in the HTML + * mode and the SVG and MathML modes. + * + * @param name + * the name for the HTML mode + * @param suffix + * the name for the SVG and MathML modes + * @return the initialized name array + */ + private static @NoLength @Local String[] COLONIFIED_LOCAL( + @Local String name, @Local String suffix) { + @NoLength @Local String[] arr = new String[4]; + arr[0] = name; + arr[1] = suffix; + arr[2] = suffix; + // [NOCPP[ + arr[3] = name; + // ]NOCPP] + return arr; + } + + /** + * An initialization helper for having the same local name in all modes. + * + * @param name + * the name + * @return the initialized name array + */ + static @NoLength @Local String[] SAME_LOCAL(@Local String name) { + @NoLength @Local String[] arr = new String[4]; + arr[0] = name; + arr[1] = name; + arr[2] = name; + // [NOCPP[ + arr[3] = name; + // ]NOCPP] + return arr; + } + + @Inline static int levelOrderBinarySearch(int[] data, int key) { + int n = data.length; + int i = 0; + + while (i < n) { + int val = data[i]; + if (val < key) { + i = 2 * i + 2; + } else if (val > key) { + i = 2 * i + 1; + } else { + return i; + } + } + + return -1; + } + + /** + * Returns an attribute name by buffer. + * + * <p> + * C++ ownership: The return value is either released by the caller if the + * attribute is a duplicate or the ownership is transferred to + * HtmlAttributes and released upon clearing or destroying that object. + * + * @param buf + * the buffer + * @param offset + * ignored + * @param length + * length of data + * @param checkNcName + * whether to check ncnameness + * @return an <code>AttributeName</code> corresponding to the argument data + */ + @Inline static AttributeName nameByBuffer(@NoLength char[] buf, + int length, Interner interner) { + // XXX deal with offset + @Unsigned int hash = AttributeName.bufToHash(buf, length); + int[] hashes; + hashes = AttributeName.ATTRIBUTE_HASHES; + int index = levelOrderBinarySearch(hashes, hash); + if (index < 0) { + return null; + } + AttributeName attributeName = AttributeName.ATTRIBUTE_NAMES[index]; + @Local String name = attributeName.getLocal(0); + if (!Portability.localEqualsBuffer(name, buf, length)) { + return null; + } + return attributeName; + } + + /** + * This method has to return a unique positive integer for each well-known + * lower-cased attribute name. + * + * @param buf + * @param len + * @return + */ + @Inline private static @Unsigned int bufToHash(@NoLength char[] buf, int length) { + @Unsigned int len = length; + @Unsigned int first = buf[0]; + first <<= 19; + @Unsigned int second = 1 << 23; + @Unsigned int third = 0; + @Unsigned int fourth = 0; + @Unsigned int fifth = 0; + @Unsigned int sixth = 0; + if (length >= 4) { + second = buf[length - 4]; + second <<= 4; + third = buf[1]; + third <<= 9; + fourth = buf[length - 2]; + fourth <<= 14; + fifth = buf[3]; + fifth <<= 24; + sixth = buf[length - 1]; + sixth <<= 11; + } else if (length == 3) { + second = buf[1]; + second <<= 4; + third = buf[2]; + third <<= 9; + } else if (length == 2) { + second = buf[1]; + second <<= 24; + } + return len + first + second + third + fourth + fifth + sixth; + } + + /** + * The mode value for HTML. + */ + public static final int HTML = 0; + + /** + * The mode value for MathML. + */ + public static final int MATHML = 1; + + /** + * The mode value for SVG. + */ + public static final int SVG = 2; + + // [NOCPP[ + + /** + * The mode value for lang-mapping HTML. + */ + public static final int HTML_LANG = 3; + + // ]NOCPP] + + /** + * The namespaces indexable by mode. + */ + private final @NsUri @NoLength String[] uri; + + /** + * The local names indexable by mode. + */ + private final @Local @NoLength String[] local; + + /** + * The prefixes indexably by mode. + */ + private final @Prefix @NoLength String[] prefix; + + // CPPONLY: private final boolean custom; + + // [NOCPP[ + + private final int flags; + + /** + * The qnames indexable by mode. + */ + private final @QName @NoLength String[] qName; + + // ]NOCPP] + + /** + * The startup-time constructor. + * + * @param uri + * the namespace + * @param local + * the local name + * @param prefix + * the prefix + * @param ncname + * the ncnameness + * @param xmlns + * whether this is an xmlns attribute + */ + private AttributeName(@NsUri @NoLength String[] uri, + @Local @NoLength String[] local, @Prefix @NoLength String[] prefix + // [NOCPP[ + , int flags + // ]NOCPP] + ) { + this.uri = uri; + this.local = local; + this.prefix = prefix; + // [NOCPP[ + this.qName = COMPUTE_QNAME(local, prefix); + this.flags = flags; + // ]NOCPP] + // CPPONLY: this.custom = false; + } + + // CPPONLY: public AttributeName() { + // CPPONLY: this.uri = AttributeName.ALL_NO_NS; + // CPPONLY: this.local = AttributeName.SAME_LOCAL(null); + // CPPONLY: this.prefix = ALL_NO_PREFIX; + // CPPONLY: this.custom = true; + // CPPONLY: } + // CPPONLY: + // CPPONLY: @Inline public boolean isInterned() { + // CPPONLY: return !custom; + // CPPONLY: } + // CPPONLY: + // CPPONLY: @Inline public void setNameForNonInterned(@Local String name) { + // CPPONLY: assert custom; + // CPPONLY: local[0] = name; + // CPPONLY: local[1] = name; + // CPPONLY: local[2] = name; + // CPPONLY: } + + /** + * Creates an <code>AttributeName</code> for a local name. + * + * @param name + * the name + * @param checkNcName + * whether to check ncnameness + * @return an <code>AttributeName</code> + */ + static AttributeName createAttributeName(@Local String name + // [NOCPP[ + , boolean checkNcName + // ]NOCPP] + ) { + // [NOCPP[ + int flags = NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG; + if (name.startsWith("xmlns:")) { + flags = IS_XMLNS; + } else if (checkNcName && !NCName.isNCName(name)) { + flags = 0; + } + // ]NOCPP] + return new AttributeName(AttributeName.ALL_NO_NS, + AttributeName.SAME_LOCAL(name), ALL_NO_PREFIX, flags); + } + + /** + * The C++ destructor. + */ + @SuppressWarnings("unused") private void destructor() { + Portability.deleteArray(local); + } + + // [NOCPP[ + /** + * Creator for use when the XML violation policy requires an attribute name + * to be changed. + * + * @param name + * the name of the attribute to create + */ + static AttributeName create(@Local String name) { + return new AttributeName(AttributeName.ALL_NO_NS, + AttributeName.SAME_LOCAL(name), ALL_NO_PREFIX, + NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + } + + /** + * Queries whether this name is an XML 1.0 4th ed. NCName. + * + * @param mode + * the SVG/MathML/HTML mode + * @return <code>true</code> if this is an NCName in the given mode + */ + public boolean isNcName(int mode) { + return (flags & (1 << mode)) != 0; + } + + /** + * Queries whether this is an <code>xmlns</code> attribute. + * + * @return <code>true</code> if this is an <code>xmlns</code> attribute + */ + public boolean isXmlns() { + return (flags & IS_XMLNS) != 0; + } + + /** + * Queries whether this attribute has a case-folded value in the HTML4 mode + * of the parser. + * + * @return <code>true</code> if the value is case-folded + */ + boolean isCaseFolded() { + return (flags & CASE_FOLDED) != 0; + } + + boolean isBoolean() { + return (flags & BOOLEAN) != 0; + } + + public @QName String getQName(int mode) { + return qName[mode]; + } + + // ]NOCPP] + + public @NsUri String getUri(int mode) { + return uri[mode]; + } + + public @Local String getLocal(int mode) { + return local[mode]; + } + + public @Prefix String getPrefix(int mode) { + return prefix[mode]; + } + + boolean equalsAnother(AttributeName another) { + return this.getLocal(AttributeName.HTML) == another.getLocal(AttributeName.HTML); + } + + // START CODE ONLY USED FOR GENERATING CODE uncomment to regenerate + +// /** +// * @see java.lang.Object#toString() +// */ +// @Override public String toString() { +// return "(" + formatNs() + ", " + formatLocal() + ", " + formatPrefix() +// + ", " + formatFlags() + ")"; +// } +// +// private String formatFlags() { +// StringBuilder builder = new StringBuilder(); +// if ((flags & NCNAME_HTML) != 0) { +// if (builder.length() != 0) { +// builder.append(" | "); +// } +// builder.append("NCNAME_HTML"); +// } +// if ((flags & NCNAME_FOREIGN) != 0) { +// if (builder.length() != 0) { +// builder.append(" | "); +// } +// builder.append("NCNAME_FOREIGN"); +// } +// if ((flags & NCNAME_LANG) != 0) { +// if (builder.length() != 0) { +// builder.append(" | "); +// } +// builder.append("NCNAME_LANG"); +// } +// if (isXmlns()) { +// if (builder.length() != 0) { +// builder.append(" | "); +// } +// builder.append("IS_XMLNS"); +// } +// if (isCaseFolded()) { +// if (builder.length() != 0) { +// builder.append(" | "); +// } +// builder.append("CASE_FOLDED"); +// } +// if (isBoolean()) { +// if (builder.length() != 0) { +// builder.append(" | "); +// } +// builder.append("BOOLEAN"); +// } +// if (builder.length() == 0) { +// return "0"; +// } +// return builder.toString(); +// } +// +// public int compareTo(AttributeName other) { +// int thisHash = this.hash(); +// int otherHash = other.hash(); +// if (thisHash < otherHash) { +// return -1; +// } else if (thisHash == otherHash) { +// return 0; +// } else { +// return 1; +// } +// } +// +// private String formatPrefix() { +// if (prefix[0] == null && prefix[1] == null && prefix[2] == null +// && prefix[3] == null) { +// return "ALL_NO_PREFIX"; +// } else if (prefix[0] == null && prefix[1] == prefix[2] +// && prefix[3] == null) { +// if ("xmlns".equals(prefix[1])) { +// return "XMLNS_PREFIX"; +// } else if ("xml".equals(prefix[1])) { +// return "XML_PREFIX"; +// } else if ("xlink".equals(prefix[1])) { +// return "XLINK_PREFIX"; +// } else { +// throw new IllegalStateException(); +// } +// } else if (prefix[0] == null && prefix[1] == null && prefix[2] == null +// && prefix[3] == "xml") { +// return "LANG_PREFIX"; +// } else { +// throw new IllegalStateException(); +// } +// } +// +// private String formatLocal() { +// if (local[0] == local[1] && local[0] == local[3] +// && local[0] != local[2]) { +// return "SVG_DIFFERENT(\"" + local[0] + "\", \"" + local[2] + "\")"; +// } +// if (local[0] == local[2] && local[0] == local[3] +// && local[0] != local[1]) { +// return "MATH_DIFFERENT(\"" + local[0] + "\", \"" + local[1] + "\")"; +// } +// if (local[0] == local[3] && local[1] == local[2] +// && local[0] != local[1]) { +// return "COLONIFIED_LOCAL(\"" + local[0] + "\", \"" + local[1] +// + "\")"; +// } +// for (int i = 1; i < local.length; i++) { +// if (local[0] != local[i]) { +// throw new IllegalStateException(); +// } +// } +// return "SAME_LOCAL(\"" + local[0] + "\")"; +// } +// +// private String formatNs() { +// if (uri[0] == "" && uri[1] == "" && uri[2] == "" && uri[3] == "") { +// return "ALL_NO_NS"; +// } else if (uri[0] == "" && uri[1] == uri[2] && uri[3] == "") { +// if ("http://www.w3.org/2000/xmlns/".equals(uri[1])) { +// return "XMLNS_NS"; +// } else if ("http://www.w3.org/XML/1998/namespace".equals(uri[1])) { +// return "XML_NS"; +// } else if ("http://www.w3.org/1999/xlink".equals(uri[1])) { +// return "XLINK_NS"; +// } else { +// throw new IllegalStateException(); +// } +// } else if (uri[0] == "" && uri[1] == "" && uri[2] == "" +// && uri[3] == "http://www.w3.org/XML/1998/namespace") { +// return "LANG_NS"; +// } else { +// throw new IllegalStateException(); +// } +// } +// +// private String constName() { +// String name = getLocal(HTML); +// char[] buf = new char[name.length()]; +// for (int i = 0; i < name.length(); i++) { +// char c = name.charAt(i); +// if (c == '-' || c == ':') { +// buf[i] = '_'; +// } else if (c >= 'a' && c <= 'z') { +// buf[i] = (char) (c - 0x20); +// } else { +// buf[i] = c; +// } +// } +// return new String(buf); +// } +// +// private int hash() { +// String name = getLocal(HTML); +// return bufToHash(name.toCharArray(), name.length()); +// } +// +// private static void fillLevelOrderArray(List<AttributeName> sorted, int depth, +// int rootIdx, AttributeName[] levelOrder) { +// if (rootIdx >= levelOrder.length) { +// return; +// } +// +// if (depth > 0) { +// fillLevelOrderArray(sorted, depth - 1, rootIdx * 2 + 1, levelOrder); +// } +// +// if (!sorted.isEmpty()) { +// levelOrder[rootIdx] = sorted.remove(0); +// } +// +// if (depth > 0) { +// fillLevelOrderArray(sorted, depth - 1, rootIdx * 2 + 2, levelOrder); +// } +// } +// +// /** +// * Regenerate self +// * +// * @param args +// */ +// public static void main(String[] args) { +// Arrays.sort(ATTRIBUTE_NAMES); +// for (int i = 0; i < ATTRIBUTE_NAMES.length; i++) { +// int hash = ATTRIBUTE_NAMES[i].hash(); +// if (hash < 0) { +// System.err.println("Negative hash: " + ATTRIBUTE_NAMES[i].local[0]); +// return; +// } +// for (int j = i + 1; j < ATTRIBUTE_NAMES.length; j++) { +// if (hash == ATTRIBUTE_NAMES[j].hash()) { +// System.err.println( +// "Hash collision: " + ATTRIBUTE_NAMES[i].local[0] + ", " +// + ATTRIBUTE_NAMES[j].local[0]); +// return; +// } +// } +// } +// for (int i = 0; i < ATTRIBUTE_NAMES.length; i++) { +// AttributeName att = ATTRIBUTE_NAMES[i]; +// System.out.println("public static final AttributeName " +// + att.constName() + " = new AttributeName" + att.toString() +// + ";"); +// } +// +// LinkedList<AttributeName> sortedNames = new LinkedList<AttributeName>(); +// Collections.addAll(sortedNames, ATTRIBUTE_NAMES); +// AttributeName[] levelOrder = new AttributeName[ATTRIBUTE_NAMES.length]; +// int bstDepth = (int) Math.ceil(Math.log(ATTRIBUTE_NAMES.length) / Math.log(2)); +// fillLevelOrderArray(sortedNames, bstDepth, 0, levelOrder); +// +// System.out.println("private final static @NoLength AttributeName[] ATTRIBUTE_NAMES = {"); +// for (int i = 0; i < levelOrder.length; i++) { +// AttributeName att = levelOrder[i]; +// System.out.println(att.constName() + ","); +// } +// System.out.println("};"); +// System.out.println("private final static int[] ATTRIBUTE_HASHES = {"); +// for (int i = 0; i < levelOrder.length; i++) { +// AttributeName att = levelOrder[i]; +// System.out.println(Integer.toString(att.hash()) + ","); +// } +// System.out.println("};"); +// } + + // START GENERATED CODE + public static final AttributeName ALT = new AttributeName(ALL_NO_NS, SAME_LOCAL("alt"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName DIR = new AttributeName(ALL_NO_NS, SAME_LOCAL("dir"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED); + public static final AttributeName DUR = new AttributeName(ALL_NO_NS, SAME_LOCAL("dur"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName END = new AttributeName(ALL_NO_NS, SAME_LOCAL("end"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName FOR = new AttributeName(ALL_NO_NS, SAME_LOCAL("for"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName IN2 = new AttributeName(ALL_NO_NS, SAME_LOCAL("in2"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName LOW = new AttributeName(ALL_NO_NS, SAME_LOCAL("low"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName MIN = new AttributeName(ALL_NO_NS, SAME_LOCAL("min"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName MAX = new AttributeName(ALL_NO_NS, SAME_LOCAL("max"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName REL = new AttributeName(ALL_NO_NS, SAME_LOCAL("rel"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName REV = new AttributeName(ALL_NO_NS, SAME_LOCAL("rev"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName SRC = new AttributeName(ALL_NO_NS, SAME_LOCAL("src"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName D = new AttributeName(ALL_NO_NS, SAME_LOCAL("d"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName R = new AttributeName(ALL_NO_NS, SAME_LOCAL("r"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName X = new AttributeName(ALL_NO_NS, SAME_LOCAL("x"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName Y = new AttributeName(ALL_NO_NS, SAME_LOCAL("y"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName Z = new AttributeName(ALL_NO_NS, SAME_LOCAL("z"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName K1 = new AttributeName(ALL_NO_NS, SAME_LOCAL("k1"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName X1 = new AttributeName(ALL_NO_NS, SAME_LOCAL("x1"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName Y1 = new AttributeName(ALL_NO_NS, SAME_LOCAL("y1"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName K2 = new AttributeName(ALL_NO_NS, SAME_LOCAL("k2"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName X2 = new AttributeName(ALL_NO_NS, SAME_LOCAL("x2"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName Y2 = new AttributeName(ALL_NO_NS, SAME_LOCAL("y2"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName K3 = new AttributeName(ALL_NO_NS, SAME_LOCAL("k3"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName K4 = new AttributeName(ALL_NO_NS, SAME_LOCAL("k4"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName XML_SPACE = new AttributeName(XML_NS, COLONIFIED_LOCAL("xml:space", "space"), XML_PREFIX, NCNAME_FOREIGN); + public static final AttributeName XML_LANG = new AttributeName(XML_NS, COLONIFIED_LOCAL("xml:lang", "lang"), XML_PREFIX, NCNAME_FOREIGN); + public static final AttributeName ARIA_GRAB = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-grab"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_VALUEMAX = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-valuemax"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_LABELLEDBY = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-labelledby"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_DESCRIBEDBY = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-describedby"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_DISABLED = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-disabled"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_CHECKED = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-checked"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_SELECTED = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-selected"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_DROPEFFECT = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-dropeffect"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_REQUIRED = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-required"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_EXPANDED = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-expanded"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_PRESSED = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-pressed"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_LEVEL = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-level"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_CHANNEL = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-channel"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_HIDDEN = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-hidden"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_SECRET = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-secret"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_POSINSET = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-posinset"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_ATOMIC = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-atomic"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_INVALID = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-invalid"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_TEMPLATEID = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-templateid"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_VALUEMIN = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-valuemin"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_MULTISELECTABLE = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-multiselectable"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_CONTROLS = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-controls"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_MULTILINE = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-multiline"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_READONLY = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-readonly"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_OWNS = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-owns"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_ACTIVEDESCENDANT = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-activedescendant"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_RELEVANT = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-relevant"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_DATATYPE = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-datatype"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_VALUENOW = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-valuenow"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_SORT = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-sort"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_AUTOCOMPLETE = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-autocomplete"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_FLOWTO = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-flowto"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_BUSY = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-busy"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_LIVE = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-live"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_HASPOPUP = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-haspopup"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARIA_SETSIZE = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-setsize"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName CLEAR = new AttributeName(ALL_NO_NS, SAME_LOCAL("clear"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED); + public static final AttributeName DISABLED = new AttributeName(ALL_NO_NS, SAME_LOCAL("disabled"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN); + public static final AttributeName DEFAULT = new AttributeName(ALL_NO_NS, SAME_LOCAL("default"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN); + public static final AttributeName DATA = new AttributeName(ALL_NO_NS, SAME_LOCAL("data"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName EQUALCOLUMNS = new AttributeName(ALL_NO_NS, SAME_LOCAL("equalcolumns"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName EQUALROWS = new AttributeName(ALL_NO_NS, SAME_LOCAL("equalrows"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName HSPACE = new AttributeName(ALL_NO_NS, SAME_LOCAL("hspace"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ISMAP = new AttributeName(ALL_NO_NS, SAME_LOCAL("ismap"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN); + public static final AttributeName LOCAL = new AttributeName(ALL_NO_NS, SAME_LOCAL("local"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName LSPACE = new AttributeName(ALL_NO_NS, SAME_LOCAL("lspace"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName MOVABLELIMITS = new AttributeName(ALL_NO_NS, SAME_LOCAL("movablelimits"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName NOTATION = new AttributeName(ALL_NO_NS, SAME_LOCAL("notation"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONDATAAVAILABLE = new AttributeName(ALL_NO_NS, SAME_LOCAL("ondataavailable"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONPASTE = new AttributeName(ALL_NO_NS, SAME_LOCAL("onpaste"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName RSPACE = new AttributeName(ALL_NO_NS, SAME_LOCAL("rspace"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ROWALIGN = new AttributeName(ALL_NO_NS, SAME_LOCAL("rowalign"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ROTATE = new AttributeName(ALL_NO_NS, SAME_LOCAL("rotate"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName SEPARATOR = new AttributeName(ALL_NO_NS, SAME_LOCAL("separator"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName SEPARATORS = new AttributeName(ALL_NO_NS, SAME_LOCAL("separators"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName VSPACE = new AttributeName(ALL_NO_NS, SAME_LOCAL("vspace"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName XCHANNELSELECTOR = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("xchannelselector", "xChannelSelector"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName YCHANNELSELECTOR = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("ychannelselector", "yChannelSelector"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ENABLE_BACKGROUND = new AttributeName(ALL_NO_NS, SAME_LOCAL("enable-background"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONDBLCLICK = new AttributeName(ALL_NO_NS, SAME_LOCAL("ondblclick"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONABORT = new AttributeName(ALL_NO_NS, SAME_LOCAL("onabort"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName CALCMODE = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("calcmode", "calcMode"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName CHECKED = new AttributeName(ALL_NO_NS, SAME_LOCAL("checked"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN); + public static final AttributeName FENCE = new AttributeName(ALL_NO_NS, SAME_LOCAL("fence"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONSCROLL = new AttributeName(ALL_NO_NS, SAME_LOCAL("onscroll"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONACTIVATE = new AttributeName(ALL_NO_NS, SAME_LOCAL("onactivate"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName OPACITY = new AttributeName(ALL_NO_NS, SAME_LOCAL("opacity"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName SPACING = new AttributeName(ALL_NO_NS, SAME_LOCAL("spacing"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName SPECULAREXPONENT = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("specularexponent", "specularExponent"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName SPECULARCONSTANT = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("specularconstant", "specularConstant"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName BORDER = new AttributeName(ALL_NO_NS, SAME_LOCAL("border"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ID = new AttributeName(ALL_NO_NS, SAME_LOCAL("id"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName GRADIENTTRANSFORM = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("gradienttransform", "gradientTransform"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName GRADIENTUNITS = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("gradientunits", "gradientUnits"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName HIDDEN = new AttributeName(ALL_NO_NS, SAME_LOCAL("hidden"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName HEADERS = new AttributeName(ALL_NO_NS, SAME_LOCAL("headers"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName LOADING = new AttributeName(ALL_NO_NS, SAME_LOCAL("loading"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName READONLY = new AttributeName(ALL_NO_NS, SAME_LOCAL("readonly"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN); + public static final AttributeName RENDERING_INTENT = new AttributeName(ALL_NO_NS, SAME_LOCAL("rendering-intent"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName SEED = new AttributeName(ALL_NO_NS, SAME_LOCAL("seed"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName SRCDOC = new AttributeName(ALL_NO_NS, SAME_LOCAL("srcdoc"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName STDDEVIATION = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("stddeviation", "stdDeviation"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName SANDBOX = new AttributeName(ALL_NO_NS, SAME_LOCAL("sandbox"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName WORD_SPACING = new AttributeName(ALL_NO_NS, SAME_LOCAL("word-spacing"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ACCENTUNDER = new AttributeName(ALL_NO_NS, SAME_LOCAL("accentunder"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ACCEPT_CHARSET = new AttributeName(ALL_NO_NS, SAME_LOCAL("accept-charset"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ACCESSKEY = new AttributeName(ALL_NO_NS, SAME_LOCAL("accesskey"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ACCENT = new AttributeName(ALL_NO_NS, SAME_LOCAL("accent"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ACCEPT = new AttributeName(ALL_NO_NS, SAME_LOCAL("accept"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName BEVELLED = new AttributeName(ALL_NO_NS, SAME_LOCAL("bevelled"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName BASEFREQUENCY = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("basefrequency", "baseFrequency"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName BASELINE_SHIFT = new AttributeName(ALL_NO_NS, SAME_LOCAL("baseline-shift"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName BASEPROFILE = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("baseprofile", "baseProfile"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName BASELINE = new AttributeName(ALL_NO_NS, SAME_LOCAL("baseline"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName BASE = new AttributeName(ALL_NO_NS, SAME_LOCAL("base"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName CODE = new AttributeName(ALL_NO_NS, SAME_LOCAL("code"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName CODETYPE = new AttributeName(ALL_NO_NS, SAME_LOCAL("codetype"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName CODEBASE = new AttributeName(ALL_NO_NS, SAME_LOCAL("codebase"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName CITE = new AttributeName(ALL_NO_NS, SAME_LOCAL("cite"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName DEFER = new AttributeName(ALL_NO_NS, SAME_LOCAL("defer"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN); + public static final AttributeName DATETIME = new AttributeName(ALL_NO_NS, SAME_LOCAL("datetime"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName DIRECTION = new AttributeName(ALL_NO_NS, SAME_LOCAL("direction"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName EDGEMODE = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("edgemode", "edgeMode"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName EDGE = new AttributeName(ALL_NO_NS, SAME_LOCAL("edge"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ENTERKEYHINT = new AttributeName(ALL_NO_NS, SAME_LOCAL("enterkeyhint"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName FACE = new AttributeName(ALL_NO_NS, SAME_LOCAL("face"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName INDEX = new AttributeName(ALL_NO_NS, SAME_LOCAL("index"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName INTERCEPT = new AttributeName(ALL_NO_NS, SAME_LOCAL("intercept"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName INTEGRITY = new AttributeName(ALL_NO_NS, SAME_LOCAL("integrity"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName LINEBREAK = new AttributeName(ALL_NO_NS, SAME_LOCAL("linebreak"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName LABEL = new AttributeName(ALL_NO_NS, SAME_LOCAL("label"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName LINETHICKNESS = new AttributeName(ALL_NO_NS, SAME_LOCAL("linethickness"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName MODE = new AttributeName(ALL_NO_NS, SAME_LOCAL("mode"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName NAME = new AttributeName(ALL_NO_NS, SAME_LOCAL("name"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName NORESIZE = new AttributeName(ALL_NO_NS, SAME_LOCAL("noresize"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN); + public static final AttributeName ONBEFOREUNLOAD = new AttributeName(ALL_NO_NS, SAME_LOCAL("onbeforeunload"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONREPEAT = new AttributeName(ALL_NO_NS, SAME_LOCAL("onrepeat"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName OBJECT = new AttributeName(ALL_NO_NS, SAME_LOCAL("object"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONSELECT = new AttributeName(ALL_NO_NS, SAME_LOCAL("onselect"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ORDER = new AttributeName(ALL_NO_NS, SAME_LOCAL("order"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName OTHER = new AttributeName(ALL_NO_NS, SAME_LOCAL("other"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONRESET = new AttributeName(ALL_NO_NS, SAME_LOCAL("onreset"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONREADYSTATECHANGE = new AttributeName(ALL_NO_NS, SAME_LOCAL("onreadystatechange"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONMESSAGE = new AttributeName(ALL_NO_NS, SAME_LOCAL("onmessage"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONBEGIN = new AttributeName(ALL_NO_NS, SAME_LOCAL("onbegin"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONBEFOREPRINT = new AttributeName(ALL_NO_NS, SAME_LOCAL("onbeforeprint"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ORIENT = new AttributeName(ALL_NO_NS, SAME_LOCAL("orient"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ORIENTATION = new AttributeName(ALL_NO_NS, SAME_LOCAL("orientation"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONBEFORECOPY = new AttributeName(ALL_NO_NS, SAME_LOCAL("onbeforecopy"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONSELECTSTART = new AttributeName(ALL_NO_NS, SAME_LOCAL("onselectstart"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONBEFOREPASTE = new AttributeName(ALL_NO_NS, SAME_LOCAL("onbeforepaste"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONKEYPRESS = new AttributeName(ALL_NO_NS, SAME_LOCAL("onkeypress"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONKEYUP = new AttributeName(ALL_NO_NS, SAME_LOCAL("onkeyup"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONBEFORECUT = new AttributeName(ALL_NO_NS, SAME_LOCAL("onbeforecut"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONKEYDOWN = new AttributeName(ALL_NO_NS, SAME_LOCAL("onkeydown"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONRESIZE = new AttributeName(ALL_NO_NS, SAME_LOCAL("onresize"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName REPEAT = new AttributeName(ALL_NO_NS, SAME_LOCAL("repeat"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName REFERRERPOLICY = new AttributeName(ALL_NO_NS, SAME_LOCAL("referrerpolicy"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName RULES = new AttributeName(ALL_NO_NS, SAME_LOCAL("rules"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED); + public static final AttributeName ROLE = new AttributeName(ALL_NO_NS, SAME_LOCAL("role"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName REPEATCOUNT = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("repeatcount", "repeatCount"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName REPEATDUR = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("repeatdur", "repeatDur"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName SELECTED = new AttributeName(ALL_NO_NS, SAME_LOCAL("selected"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN); + public static final AttributeName SIZES = new AttributeName(ALL_NO_NS, SAME_LOCAL("sizes"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName SUPERSCRIPTSHIFT = new AttributeName(ALL_NO_NS, SAME_LOCAL("superscriptshift"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName STRETCHY = new AttributeName(ALL_NO_NS, SAME_LOCAL("stretchy"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName SCHEME = new AttributeName(ALL_NO_NS, SAME_LOCAL("scheme"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName SPREADMETHOD = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("spreadmethod", "spreadMethod"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName SELECTION = new AttributeName(ALL_NO_NS, SAME_LOCAL("selection"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName SIZE = new AttributeName(ALL_NO_NS, SAME_LOCAL("size"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName TYPE = new AttributeName(ALL_NO_NS, SAME_LOCAL("type"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED); + public static final AttributeName DIFFUSECONSTANT = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("diffuseconstant", "diffuseConstant"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName HREF = new AttributeName(ALL_NO_NS, SAME_LOCAL("href"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName HREFLANG = new AttributeName(ALL_NO_NS, SAME_LOCAL("hreflang"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONAFTERPRINT = new AttributeName(ALL_NO_NS, SAME_LOCAL("onafterprint"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName PROFILE = new AttributeName(ALL_NO_NS, SAME_LOCAL("profile"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName SURFACESCALE = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("surfacescale", "surfaceScale"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName XREF = new AttributeName(ALL_NO_NS, SAME_LOCAL("xref"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ALIGN = new AttributeName(ALL_NO_NS, SAME_LOCAL("align"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED); + public static final AttributeName ALIGNMENT_BASELINE = new AttributeName(ALL_NO_NS, SAME_LOCAL("alignment-baseline"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ALIGNMENTSCOPE = new AttributeName(ALL_NO_NS, SAME_LOCAL("alignmentscope"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName DRAGGABLE = new AttributeName(ALL_NO_NS, SAME_LOCAL("draggable"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName HEIGHT = new AttributeName(ALL_NO_NS, SAME_LOCAL("height"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName IMAGESIZES = new AttributeName(ALL_NO_NS, SAME_LOCAL("imagesizes"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName IMAGESRCSET = new AttributeName(ALL_NO_NS, SAME_LOCAL("imagesrcset"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName IMAGE_RENDERING = new AttributeName(ALL_NO_NS, SAME_LOCAL("image-rendering"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName LANGUAGE = new AttributeName(ALL_NO_NS, SAME_LOCAL("language"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName LANG = new AttributeName(LANG_NS, SAME_LOCAL("lang"), LANG_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName LARGEOP = new AttributeName(ALL_NO_NS, SAME_LOCAL("largeop"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName LONGDESC = new AttributeName(ALL_NO_NS, SAME_LOCAL("longdesc"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName LENGTHADJUST = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("lengthadjust", "lengthAdjust"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName MARGINHEIGHT = new AttributeName(ALL_NO_NS, SAME_LOCAL("marginheight"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName MARGINWIDTH = new AttributeName(ALL_NO_NS, SAME_LOCAL("marginwidth"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ORIGIN = new AttributeName(ALL_NO_NS, SAME_LOCAL("origin"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName PING = new AttributeName(ALL_NO_NS, SAME_LOCAL("ping"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName TARGET = new AttributeName(ALL_NO_NS, SAME_LOCAL("target"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName TARGETX = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("targetx", "targetX"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName TARGETY = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("targety", "targetY"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ARCHIVE = new AttributeName(ALL_NO_NS, SAME_LOCAL("archive"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName HIGH = new AttributeName(ALL_NO_NS, SAME_LOCAL("high"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName LIGHTING_COLOR = new AttributeName(ALL_NO_NS, SAME_LOCAL("lighting-color"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName MATHBACKGROUND = new AttributeName(ALL_NO_NS, SAME_LOCAL("mathbackground"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName METHOD = new AttributeName(ALL_NO_NS, SAME_LOCAL("method"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED); + public static final AttributeName MATHVARIANT = new AttributeName(ALL_NO_NS, SAME_LOCAL("mathvariant"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName MATHCOLOR = new AttributeName(ALL_NO_NS, SAME_LOCAL("mathcolor"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName MATHSIZE = new AttributeName(ALL_NO_NS, SAME_LOCAL("mathsize"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName NOSHADE = new AttributeName(ALL_NO_NS, SAME_LOCAL("noshade"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN); + public static final AttributeName ONCHANGE = new AttributeName(ALL_NO_NS, SAME_LOCAL("onchange"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName PATHLENGTH = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("pathlength", "pathLength"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName PATH = new AttributeName(ALL_NO_NS, SAME_LOCAL("path"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ALTIMG = new AttributeName(ALL_NO_NS, SAME_LOCAL("altimg"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ACTIONTYPE = new AttributeName(ALL_NO_NS, SAME_LOCAL("actiontype"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ACTION = new AttributeName(ALL_NO_NS, SAME_LOCAL("action"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ACTIVE = new AttributeName(ALL_NO_NS, SAME_LOCAL("active"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN); + public static final AttributeName ADDITIVE = new AttributeName(ALL_NO_NS, SAME_LOCAL("additive"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName BEGIN = new AttributeName(ALL_NO_NS, SAME_LOCAL("begin"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName DOMINANT_BASELINE = new AttributeName(ALL_NO_NS, SAME_LOCAL("dominant-baseline"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName DIVISOR = new AttributeName(ALL_NO_NS, SAME_LOCAL("divisor"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName DEFINITIONURL = new AttributeName(ALL_NO_NS, MATH_DIFFERENT("definitionurl", "definitionURL"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName LIMITINGCONEANGLE = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("limitingconeangle", "limitingConeAngle"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName MEDIA = new AttributeName(ALL_NO_NS, SAME_LOCAL("media"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName MANIFEST = new AttributeName(ALL_NO_NS, SAME_LOCAL("manifest"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONFINISH = new AttributeName(ALL_NO_NS, SAME_LOCAL("onfinish"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName OPTIMUM = new AttributeName(ALL_NO_NS, SAME_LOCAL("optimum"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName RADIOGROUP = new AttributeName(ALL_NO_NS, SAME_LOCAL("radiogroup"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName RADIUS = new AttributeName(ALL_NO_NS, SAME_LOCAL("radius"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName SCRIPTLEVEL = new AttributeName(ALL_NO_NS, SAME_LOCAL("scriptlevel"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName SCRIPTSIZEMULTIPLIER = new AttributeName(ALL_NO_NS, SAME_LOCAL("scriptsizemultiplier"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName SCRIPTMINSIZE = new AttributeName(ALL_NO_NS, SAME_LOCAL("scriptminsize"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName TABINDEX = new AttributeName(ALL_NO_NS, SAME_LOCAL("tabindex"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName VALIGN = new AttributeName(ALL_NO_NS, SAME_LOCAL("valign"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED); + public static final AttributeName VISIBILITY = new AttributeName(ALL_NO_NS, SAME_LOCAL("visibility"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName BACKGROUND = new AttributeName(ALL_NO_NS, SAME_LOCAL("background"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName LINK = new AttributeName(ALL_NO_NS, SAME_LOCAL("link"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName MARKER_MID = new AttributeName(ALL_NO_NS, SAME_LOCAL("marker-mid"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName MARKERHEIGHT = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("markerheight", "markerHeight"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName MARKER_END = new AttributeName(ALL_NO_NS, SAME_LOCAL("marker-end"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName MASK = new AttributeName(ALL_NO_NS, SAME_LOCAL("mask"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName MARKER_START = new AttributeName(ALL_NO_NS, SAME_LOCAL("marker-start"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName MARKERWIDTH = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("markerwidth", "markerWidth"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName MASKUNITS = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("maskunits", "maskUnits"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName MARKERUNITS = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("markerunits", "markerUnits"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName MASKCONTENTUNITS = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("maskcontentunits", "maskContentUnits"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName AMPLITUDE = new AttributeName(ALL_NO_NS, SAME_LOCAL("amplitude"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName CELLSPACING = new AttributeName(ALL_NO_NS, SAME_LOCAL("cellspacing"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName CELLPADDING = new AttributeName(ALL_NO_NS, SAME_LOCAL("cellpadding"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName DECLARE = new AttributeName(ALL_NO_NS, SAME_LOCAL("declare"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN); + public static final AttributeName FILL_RULE = new AttributeName(ALL_NO_NS, SAME_LOCAL("fill-rule"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName FILL = new AttributeName(ALL_NO_NS, SAME_LOCAL("fill"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName FILL_OPACITY = new AttributeName(ALL_NO_NS, SAME_LOCAL("fill-opacity"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName MAXLENGTH = new AttributeName(ALL_NO_NS, SAME_LOCAL("maxlength"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONCLICK = new AttributeName(ALL_NO_NS, SAME_LOCAL("onclick"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONBLUR = new AttributeName(ALL_NO_NS, SAME_LOCAL("onblur"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName REPLACE = new AttributeName(ALL_NO_NS, SAME_LOCAL("replace"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED); + public static final AttributeName ROWLINES = new AttributeName(ALL_NO_NS, SAME_LOCAL("rowlines"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName SCALE = new AttributeName(ALL_NO_NS, SAME_LOCAL("scale"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName STYLE = new AttributeName(ALL_NO_NS, SAME_LOCAL("style"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName TABLEVALUES = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("tablevalues", "tableValues"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName TITLE = new AttributeName(ALL_NO_NS, SAME_LOCAL("title"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName AZIMUTH = new AttributeName(ALL_NO_NS, SAME_LOCAL("azimuth"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName FORMAT = new AttributeName(ALL_NO_NS, SAME_LOCAL("format"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName FRAMEBORDER = new AttributeName(ALL_NO_NS, SAME_LOCAL("frameborder"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName FRAME = new AttributeName(ALL_NO_NS, SAME_LOCAL("frame"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED); + public static final AttributeName FRAMESPACING = new AttributeName(ALL_NO_NS, SAME_LOCAL("framespacing"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName FROM = new AttributeName(ALL_NO_NS, SAME_LOCAL("from"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName FORM = new AttributeName(ALL_NO_NS, SAME_LOCAL("form"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName PROMPT = new AttributeName(ALL_NO_NS, SAME_LOCAL("prompt"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName PRIMITIVEUNITS = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("primitiveunits", "primitiveUnits"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName SYMMETRIC = new AttributeName(ALL_NO_NS, SAME_LOCAL("symmetric"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName SUMMARY = new AttributeName(ALL_NO_NS, SAME_LOCAL("summary"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName USEMAP = new AttributeName(ALL_NO_NS, SAME_LOCAL("usemap"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ZOOMANDPAN = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("zoomandpan", "zoomAndPan"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ASYNC = new AttributeName(ALL_NO_NS, SAME_LOCAL("async"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN); + public static final AttributeName ALINK = new AttributeName(ALL_NO_NS, SAME_LOCAL("alink"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName IN = new AttributeName(ALL_NO_NS, SAME_LOCAL("in"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ICON = new AttributeName(ALL_NO_NS, SAME_LOCAL("icon"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName KERNELMATRIX = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("kernelmatrix", "kernelMatrix"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName KERNING = new AttributeName(ALL_NO_NS, SAME_LOCAL("kerning"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName KERNELUNITLENGTH = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("kernelunitlength", "kernelUnitLength"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONUNLOAD = new AttributeName(ALL_NO_NS, SAME_LOCAL("onunload"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName OPEN = new AttributeName(ALL_NO_NS, SAME_LOCAL("open"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONINVALID = new AttributeName(ALL_NO_NS, SAME_LOCAL("oninvalid"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONEND = new AttributeName(ALL_NO_NS, SAME_LOCAL("onend"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONINPUT = new AttributeName(ALL_NO_NS, SAME_LOCAL("oninput"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName POINTER_EVENTS = new AttributeName(ALL_NO_NS, SAME_LOCAL("pointer-events"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName POINTS = new AttributeName(ALL_NO_NS, SAME_LOCAL("points"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName POINTSATX = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("pointsatx", "pointsAtX"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName POINTSATY = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("pointsaty", "pointsAtY"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName POINTSATZ = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("pointsatz", "pointsAtZ"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName SPAN = new AttributeName(ALL_NO_NS, SAME_LOCAL("span"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName STANDBY = new AttributeName(ALL_NO_NS, SAME_LOCAL("standby"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName TRANSFORM_ORIGIN = new AttributeName(ALL_NO_NS, SAME_LOCAL("transform-origin"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName TRANSFORM = new AttributeName(ALL_NO_NS, SAME_LOCAL("transform"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName VLINK = new AttributeName(ALL_NO_NS, SAME_LOCAL("vlink"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName WHEN = new AttributeName(ALL_NO_NS, SAME_LOCAL("when"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName XLINK_HREF = new AttributeName(XLINK_NS, COLONIFIED_LOCAL("xlink:href", "href"), XLINK_PREFIX, NCNAME_FOREIGN); + public static final AttributeName XLINK_TITLE = new AttributeName(XLINK_NS, COLONIFIED_LOCAL("xlink:title", "title"), XLINK_PREFIX, NCNAME_FOREIGN); + public static final AttributeName XLINK_ROLE = new AttributeName(XLINK_NS, COLONIFIED_LOCAL("xlink:role", "role"), XLINK_PREFIX, NCNAME_FOREIGN); + public static final AttributeName XLINK_ARCROLE = new AttributeName(XLINK_NS, COLONIFIED_LOCAL("xlink:arcrole", "arcrole"), XLINK_PREFIX, NCNAME_FOREIGN); + public static final AttributeName XMLNS_XLINK = new AttributeName(XMLNS_NS, COLONIFIED_LOCAL("xmlns:xlink", "xlink"), XMLNS_PREFIX, IS_XMLNS); + public static final AttributeName XMLNS = new AttributeName(XMLNS_NS, SAME_LOCAL("xmlns"), ALL_NO_PREFIX, IS_XMLNS); + public static final AttributeName XLINK_TYPE = new AttributeName(XLINK_NS, COLONIFIED_LOCAL("xlink:type", "type"), XLINK_PREFIX, NCNAME_FOREIGN); + public static final AttributeName XLINK_SHOW = new AttributeName(XLINK_NS, COLONIFIED_LOCAL("xlink:show", "show"), XLINK_PREFIX, NCNAME_FOREIGN); + public static final AttributeName XLINK_ACTUATE = new AttributeName(XLINK_NS, COLONIFIED_LOCAL("xlink:actuate", "actuate"), XLINK_PREFIX, NCNAME_FOREIGN); + public static final AttributeName AUTOPLAY = new AttributeName(ALL_NO_NS, SAME_LOCAL("autoplay"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName AUTOCOMPLETE = new AttributeName(ALL_NO_NS, SAME_LOCAL("autocomplete"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED); + public static final AttributeName AUTOFOCUS = new AttributeName(ALL_NO_NS, SAME_LOCAL("autofocus"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN); + public static final AttributeName AUTOCAPITALIZE = new AttributeName(ALL_NO_NS, SAME_LOCAL("autocapitalize"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName BGCOLOR = new AttributeName(ALL_NO_NS, SAME_LOCAL("bgcolor"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName COLOR_PROFILE = new AttributeName(ALL_NO_NS, SAME_LOCAL("color-profile"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName COLOR_RENDERING = new AttributeName(ALL_NO_NS, SAME_LOCAL("color-rendering"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName COLOR_INTERPOLATION = new AttributeName(ALL_NO_NS, SAME_LOCAL("color-interpolation"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName COLOR = new AttributeName(ALL_NO_NS, SAME_LOCAL("color"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName COLOR_INTERPOLATION_FILTERS = new AttributeName(ALL_NO_NS, SAME_LOCAL("color-interpolation-filters"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ENCODING = new AttributeName(ALL_NO_NS, SAME_LOCAL("encoding"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName EXPONENT = new AttributeName(ALL_NO_NS, SAME_LOCAL("exponent"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName FLOOD_COLOR = new AttributeName(ALL_NO_NS, SAME_LOCAL("flood-color"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName FLOOD_OPACITY = new AttributeName(ALL_NO_NS, SAME_LOCAL("flood-opacity"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName LQUOTE = new AttributeName(ALL_NO_NS, SAME_LOCAL("lquote"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName NUMOCTAVES = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("numoctaves", "numOctaves"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName NOMODULE = new AttributeName(ALL_NO_NS, SAME_LOCAL("nomodule"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN); + public static final AttributeName ONLOAD = new AttributeName(ALL_NO_NS, SAME_LOCAL("onload"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONMOUSEWHEEL = new AttributeName(ALL_NO_NS, SAME_LOCAL("onmousewheel"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONMOUSEENTER = new AttributeName(ALL_NO_NS, SAME_LOCAL("onmouseenter"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONMOUSEOVER = new AttributeName(ALL_NO_NS, SAME_LOCAL("onmouseover"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONFOCUSIN = new AttributeName(ALL_NO_NS, SAME_LOCAL("onfocusin"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONCONTEXTMENU = new AttributeName(ALL_NO_NS, SAME_LOCAL("oncontextmenu"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONZOOM = new AttributeName(ALL_NO_NS, SAME_LOCAL("onzoom"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONCOPY = new AttributeName(ALL_NO_NS, SAME_LOCAL("oncopy"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONMOUSELEAVE = new AttributeName(ALL_NO_NS, SAME_LOCAL("onmouseleave"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONMOUSEMOVE = new AttributeName(ALL_NO_NS, SAME_LOCAL("onmousemove"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONMOUSEUP = new AttributeName(ALL_NO_NS, SAME_LOCAL("onmouseup"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONFOCUS = new AttributeName(ALL_NO_NS, SAME_LOCAL("onfocus"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONMOUSEOUT = new AttributeName(ALL_NO_NS, SAME_LOCAL("onmouseout"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONFOCUSOUT = new AttributeName(ALL_NO_NS, SAME_LOCAL("onfocusout"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONMOUSEDOWN = new AttributeName(ALL_NO_NS, SAME_LOCAL("onmousedown"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName TO = new AttributeName(ALL_NO_NS, SAME_LOCAL("to"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName RQUOTE = new AttributeName(ALL_NO_NS, SAME_LOCAL("rquote"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName STROKE_LINECAP = new AttributeName(ALL_NO_NS, SAME_LOCAL("stroke-linecap"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName STROKE_DASHARRAY = new AttributeName(ALL_NO_NS, SAME_LOCAL("stroke-dasharray"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName STROKE_DASHOFFSET = new AttributeName(ALL_NO_NS, SAME_LOCAL("stroke-dashoffset"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName STROKE_LINEJOIN = new AttributeName(ALL_NO_NS, SAME_LOCAL("stroke-linejoin"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName STROKE_MITERLIMIT = new AttributeName(ALL_NO_NS, SAME_LOCAL("stroke-miterlimit"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName STROKE = new AttributeName(ALL_NO_NS, SAME_LOCAL("stroke"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName SCROLLING = new AttributeName(ALL_NO_NS, SAME_LOCAL("scrolling"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED); + public static final AttributeName STROKE_WIDTH = new AttributeName(ALL_NO_NS, SAME_LOCAL("stroke-width"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName STROKE_OPACITY = new AttributeName(ALL_NO_NS, SAME_LOCAL("stroke-opacity"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName COMPACT = new AttributeName(ALL_NO_NS, SAME_LOCAL("compact"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN); + public static final AttributeName CLIP = new AttributeName(ALL_NO_NS, SAME_LOCAL("clip"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName CLIP_RULE = new AttributeName(ALL_NO_NS, SAME_LOCAL("clip-rule"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName CLIP_PATH = new AttributeName(ALL_NO_NS, SAME_LOCAL("clip-path"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName CLIPPATHUNITS = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("clippathunits", "clipPathUnits"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName DISPLAY = new AttributeName(ALL_NO_NS, SAME_LOCAL("display"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName DISPLAYSTYLE = new AttributeName(ALL_NO_NS, SAME_LOCAL("displaystyle"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName GLYPH_ORIENTATION_VERTICAL = new AttributeName(ALL_NO_NS, SAME_LOCAL("glyph-orientation-vertical"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName GLYPH_ORIENTATION_HORIZONTAL = new AttributeName(ALL_NO_NS, SAME_LOCAL("glyph-orientation-horizontal"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName GLYPHREF = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("glyphref", "glyphRef"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName HTTP_EQUIV = new AttributeName(ALL_NO_NS, SAME_LOCAL("http-equiv"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName KEYPOINTS = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("keypoints", "keyPoints"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName LOOP = new AttributeName(ALL_NO_NS, SAME_LOCAL("loop"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName PROPERTY = new AttributeName(ALL_NO_NS, SAME_LOCAL("property"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName SCOPED = new AttributeName(ALL_NO_NS, SAME_LOCAL("scoped"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName STEP = new AttributeName(ALL_NO_NS, SAME_LOCAL("step"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED); + public static final AttributeName SHAPE_RENDERING = new AttributeName(ALL_NO_NS, SAME_LOCAL("shape-rendering"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName SCOPE = new AttributeName(ALL_NO_NS, SAME_LOCAL("scope"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED); + public static final AttributeName SHAPE = new AttributeName(ALL_NO_NS, SAME_LOCAL("shape"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED); + public static final AttributeName SLOPE = new AttributeName(ALL_NO_NS, SAME_LOCAL("slope"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName STOP_COLOR = new AttributeName(ALL_NO_NS, SAME_LOCAL("stop-color"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName STOP_OPACITY = new AttributeName(ALL_NO_NS, SAME_LOCAL("stop-opacity"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName TEMPLATE = new AttributeName(ALL_NO_NS, SAME_LOCAL("template"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName WRAP = new AttributeName(ALL_NO_NS, SAME_LOCAL("wrap"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ABBR = new AttributeName(ALL_NO_NS, SAME_LOCAL("abbr"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ATTRIBUTENAME = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("attributename", "attributeName"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ATTRIBUTETYPE = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("attributetype", "attributeType"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName CHAR = new AttributeName(ALL_NO_NS, SAME_LOCAL("char"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName COORDS = new AttributeName(ALL_NO_NS, SAME_LOCAL("coords"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName CHAROFF = new AttributeName(ALL_NO_NS, SAME_LOCAL("charoff"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName CHARSET = new AttributeName(ALL_NO_NS, SAME_LOCAL("charset"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName NOWRAP = new AttributeName(ALL_NO_NS, SAME_LOCAL("nowrap"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN); + public static final AttributeName NOHREF = new AttributeName(ALL_NO_NS, SAME_LOCAL("nohref"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN); + public static final AttributeName ONDRAG = new AttributeName(ALL_NO_NS, SAME_LOCAL("ondrag"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONDRAGENTER = new AttributeName(ALL_NO_NS, SAME_LOCAL("ondragenter"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONDRAGOVER = new AttributeName(ALL_NO_NS, SAME_LOCAL("ondragover"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONDRAGEND = new AttributeName(ALL_NO_NS, SAME_LOCAL("ondragend"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONDROP = new AttributeName(ALL_NO_NS, SAME_LOCAL("ondrop"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONDRAGDROP = new AttributeName(ALL_NO_NS, SAME_LOCAL("ondragdrop"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONERROR = new AttributeName(ALL_NO_NS, SAME_LOCAL("onerror"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName OPERATOR = new AttributeName(ALL_NO_NS, SAME_LOCAL("operator"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName OVERFLOW = new AttributeName(ALL_NO_NS, SAME_LOCAL("overflow"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONDRAGSTART = new AttributeName(ALL_NO_NS, SAME_LOCAL("ondragstart"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONDRAGLEAVE = new AttributeName(ALL_NO_NS, SAME_LOCAL("ondragleave"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName STARTOFFSET = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("startoffset", "startOffset"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName START = new AttributeName(ALL_NO_NS, SAME_LOCAL("start"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName AS = new AttributeName(ALL_NO_NS, SAME_LOCAL("as"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName AXIS = new AttributeName(ALL_NO_NS, SAME_LOCAL("axis"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName BIAS = new AttributeName(ALL_NO_NS, SAME_LOCAL("bias"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName COLSPAN = new AttributeName(ALL_NO_NS, SAME_LOCAL("colspan"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName CLASSID = new AttributeName(ALL_NO_NS, SAME_LOCAL("classid"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName CROSSORIGIN = new AttributeName(ALL_NO_NS, SAME_LOCAL("crossorigin"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName COLS = new AttributeName(ALL_NO_NS, SAME_LOCAL("cols"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName CURSOR = new AttributeName(ALL_NO_NS, SAME_LOCAL("cursor"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName CLOSURE = new AttributeName(ALL_NO_NS, SAME_LOCAL("closure"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName CLOSE = new AttributeName(ALL_NO_NS, SAME_LOCAL("close"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName CLASS = new AttributeName(ALL_NO_NS, SAME_LOCAL("class"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName IS = new AttributeName(ALL_NO_NS, SAME_LOCAL("is"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName KEYSYSTEM = new AttributeName(ALL_NO_NS, SAME_LOCAL("keysystem"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName KEYSPLINES = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("keysplines", "keySplines"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName LOWSRC = new AttributeName(ALL_NO_NS, SAME_LOCAL("lowsrc"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName MAXSIZE = new AttributeName(ALL_NO_NS, SAME_LOCAL("maxsize"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName MINSIZE = new AttributeName(ALL_NO_NS, SAME_LOCAL("minsize"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName OFFSET = new AttributeName(ALL_NO_NS, SAME_LOCAL("offset"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName PRESERVEALPHA = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("preservealpha", "preserveAlpha"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName PRESERVEASPECTRATIO = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("preserveaspectratio", "preserveAspectRatio"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ROWSPAN = new AttributeName(ALL_NO_NS, SAME_LOCAL("rowspan"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ROWSPACING = new AttributeName(ALL_NO_NS, SAME_LOCAL("rowspacing"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ROWS = new AttributeName(ALL_NO_NS, SAME_LOCAL("rows"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName SRCSET = new AttributeName(ALL_NO_NS, SAME_LOCAL("srcset"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName SUBSCRIPTSHIFT = new AttributeName(ALL_NO_NS, SAME_LOCAL("subscriptshift"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName VERSION = new AttributeName(ALL_NO_NS, SAME_LOCAL("version"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ALTTEXT = new AttributeName(ALL_NO_NS, SAME_LOCAL("alttext"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName CONTENTEDITABLE = new AttributeName(ALL_NO_NS, SAME_LOCAL("contenteditable"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName CONTROLS = new AttributeName(ALL_NO_NS, SAME_LOCAL("controls"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName CONTENT = new AttributeName(ALL_NO_NS, SAME_LOCAL("content"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName CONTEXTMENU = new AttributeName(ALL_NO_NS, SAME_LOCAL("contextmenu"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName DEPTH = new AttributeName(ALL_NO_NS, SAME_LOCAL("depth"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ENCTYPE = new AttributeName(ALL_NO_NS, SAME_LOCAL("enctype"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED); + public static final AttributeName FONT_STRETCH = new AttributeName(ALL_NO_NS, SAME_LOCAL("font-stretch"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName FILTER = new AttributeName(ALL_NO_NS, SAME_LOCAL("filter"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName FONTWEIGHT = new AttributeName(ALL_NO_NS, SAME_LOCAL("fontweight"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName FONT_WEIGHT = new AttributeName(ALL_NO_NS, SAME_LOCAL("font-weight"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName FONTSTYLE = new AttributeName(ALL_NO_NS, SAME_LOCAL("fontstyle"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName FONT_STYLE = new AttributeName(ALL_NO_NS, SAME_LOCAL("font-style"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName FONTFAMILY = new AttributeName(ALL_NO_NS, SAME_LOCAL("fontfamily"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName FONT_FAMILY = new AttributeName(ALL_NO_NS, SAME_LOCAL("font-family"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName FONT_VARIANT = new AttributeName(ALL_NO_NS, SAME_LOCAL("font-variant"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName FONT_SIZE_ADJUST = new AttributeName(ALL_NO_NS, SAME_LOCAL("font-size-adjust"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName FILTERUNITS = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("filterunits", "filterUnits"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName FONTSIZE = new AttributeName(ALL_NO_NS, SAME_LOCAL("fontsize"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName FONT_SIZE = new AttributeName(ALL_NO_NS, SAME_LOCAL("font-size"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName KEYTIMES = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("keytimes", "keyTimes"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName LETTER_SPACING = new AttributeName(ALL_NO_NS, SAME_LOCAL("letter-spacing"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName LIST = new AttributeName(ALL_NO_NS, SAME_LOCAL("list"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName MULTIPLE = new AttributeName(ALL_NO_NS, SAME_LOCAL("multiple"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN); + public static final AttributeName RT = new AttributeName(ALL_NO_NS, SAME_LOCAL("rt"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONSTOP = new AttributeName(ALL_NO_NS, SAME_LOCAL("onstop"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONSTART = new AttributeName(ALL_NO_NS, SAME_LOCAL("onstart"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName POSTER = new AttributeName(ALL_NO_NS, SAME_LOCAL("poster"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName PATTERNTRANSFORM = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("patterntransform", "patternTransform"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName PATTERN = new AttributeName(ALL_NO_NS, SAME_LOCAL("pattern"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName PATTERNUNITS = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("patternunits", "patternUnits"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName PATTERNCONTENTUNITS = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("patterncontentunits", "patternContentUnits"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName RESTART = new AttributeName(ALL_NO_NS, SAME_LOCAL("restart"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName STITCHTILES = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("stitchtiles", "stitchTiles"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName SYSTEMLANGUAGE = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("systemlanguage", "systemLanguage"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName TEXT_RENDERING = new AttributeName(ALL_NO_NS, SAME_LOCAL("text-rendering"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName TEXT_DECORATION = new AttributeName(ALL_NO_NS, SAME_LOCAL("text-decoration"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName TEXT_ANCHOR = new AttributeName(ALL_NO_NS, SAME_LOCAL("text-anchor"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName TEXTLENGTH = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("textlength", "textLength"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName TEXT = new AttributeName(ALL_NO_NS, SAME_LOCAL("text"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName WRITING_MODE = new AttributeName(ALL_NO_NS, SAME_LOCAL("writing-mode"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName WIDTH = new AttributeName(ALL_NO_NS, SAME_LOCAL("width"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ACCUMULATE = new AttributeName(ALL_NO_NS, SAME_LOCAL("accumulate"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName COLUMNSPAN = new AttributeName(ALL_NO_NS, SAME_LOCAL("columnspan"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName COLUMNLINES = new AttributeName(ALL_NO_NS, SAME_LOCAL("columnlines"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName COLUMNALIGN = new AttributeName(ALL_NO_NS, SAME_LOCAL("columnalign"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName COLUMNSPACING = new AttributeName(ALL_NO_NS, SAME_LOCAL("columnspacing"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName COLUMNWIDTH = new AttributeName(ALL_NO_NS, SAME_LOCAL("columnwidth"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName GROUPALIGN = new AttributeName(ALL_NO_NS, SAME_LOCAL("groupalign"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName INPUTMODE = new AttributeName(ALL_NO_NS, SAME_LOCAL("inputmode"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONSUBMIT = new AttributeName(ALL_NO_NS, SAME_LOCAL("onsubmit"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ONCUT = new AttributeName(ALL_NO_NS, SAME_LOCAL("oncut"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName REQUIRED = new AttributeName(ALL_NO_NS, SAME_LOCAL("required"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN); + public static final AttributeName REQUIREDFEATURES = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("requiredfeatures", "requiredFeatures"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName RESULT = new AttributeName(ALL_NO_NS, SAME_LOCAL("result"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName REQUIREDEXTENSIONS = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("requiredextensions", "requiredExtensions"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName VALUES = new AttributeName(ALL_NO_NS, SAME_LOCAL("values"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName VALUETYPE = new AttributeName(ALL_NO_NS, SAME_LOCAL("valuetype"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED); + public static final AttributeName VALUE = new AttributeName(ALL_NO_NS, SAME_LOCAL("value"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName ELEVATION = new AttributeName(ALL_NO_NS, SAME_LOCAL("elevation"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName VIEWTARGET = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("viewtarget", "viewTarget"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName VIEWBOX = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("viewbox", "viewBox"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName CX = new AttributeName(ALL_NO_NS, SAME_LOCAL("cx"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName DX = new AttributeName(ALL_NO_NS, SAME_LOCAL("dx"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName FX = new AttributeName(ALL_NO_NS, SAME_LOCAL("fx"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName RX = new AttributeName(ALL_NO_NS, SAME_LOCAL("rx"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName REFX = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("refx", "refX"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName BY = new AttributeName(ALL_NO_NS, SAME_LOCAL("by"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName CY = new AttributeName(ALL_NO_NS, SAME_LOCAL("cy"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName DY = new AttributeName(ALL_NO_NS, SAME_LOCAL("dy"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName FY = new AttributeName(ALL_NO_NS, SAME_LOCAL("fy"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName RY = new AttributeName(ALL_NO_NS, SAME_LOCAL("ry"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + public static final AttributeName REFY = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("refy", "refY"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG); + private final static @NoLength AttributeName[] ATTRIBUTE_NAMES = { + FILL, + DATETIME, + CHAROFF, + CLEAR, + IMAGESRCSET, + COLOR, + LETTER_SPACING, + ARIA_DISABLED, + SPECULAREXPONENT, + ONKEYUP, + DOMINANT_BASELINE, + OPEN, + SCROLLING, + MAXSIZE, + REQUIREDFEATURES, + Y, + ARIA_MULTISELECTABLE, + ROTATE, + ACCENTUNDER, + ONREPEAT, + SELECTION, + LIGHTING_COLOR, + BACKGROUND, + FROM, + XLINK_TITLE, + ONCOPY, + PROPERTY, + START, + DEPTH, + TEXT_ANCHOR, + RX, + MIN, + K3, + ARIA_CHANNEL, + ARIA_VALUENOW, + LOCAL, + ONABORT, + LOADING, + BASEPROFILE, + INTEGRITY, + ONBEGIN, + REPEATCOUNT, + SURFACESCALE, + MARGINWIDTH, + PATHLENGTH, + RADIOGROUP, + MASKUNITS, + STYLE, + ASYNC, + POINTSATZ, + AUTOPLAY, + NOMODULE, + TO, + DISPLAY, + STOP_OPACITY, + ONDROP, + CURSOR, + SRCSET, + FONTFAMILY, + PATTERN, + COLUMNALIGN, + VIEWBOX, + DY, + END, + SRC, + Y1, + ARIA_GRAB, + ARIA_REQUIRED, + ARIA_ATOMIC, + ARIA_OWNS, + ARIA_BUSY, + EQUALCOLUMNS, + ONDATAAVAILABLE, + XCHANNELSELECTOR, + ONSCROLL, + GRADIENTTRANSFORM, + SRCDOC, + ACCEPT, + CODETYPE, + ENTERKEYHINT, + MODE, + OTHER, + ONBEFORECOPY, + REPEAT, + SUPERSCRIPTSHIFT, + HREF, + ALIGNMENTSCOPE, + LARGEOP, + TARGETX, + MATHCOLOR, + ACTION, + MEDIA, + SCRIPTMINSIZE, + MARKER_END, + CELLSPACING, + ONBLUR, + FORMAT, + SYMMETRIC, + KERNELMATRIX, + POINTER_EVENTS, + TRANSFORM, + XMLNS, + BGCOLOR, + FLOOD_COLOR, + ONMOUSEOVER, + ONFOCUS, + STROKE_DASHOFFSET, + CLIP, + GLYPHREF, + SCOPE, + ATTRIBUTENAME, + ONDRAG, + OVERFLOW, + COLSPAN, + IS, + PRESERVEASPECTRATIO, + CONTENTEDITABLE, + FONTWEIGHT, + FILTERUNITS, + ONSTOP, + STITCHTILES, + WIDTH, + INPUTMODE, + VALUETYPE, + DX, + BY, + RY, + DIR, + IN2, + REL, + R, + K1, + X2, + XML_SPACE, + ARIA_LABELLEDBY, + ARIA_SELECTED, + ARIA_PRESSED, + ARIA_SECRET, + ARIA_TEMPLATEID, + ARIA_MULTILINE, + ARIA_RELEVANT, + ARIA_AUTOCOMPLETE, + ARIA_HASPOPUP, + DEFAULT, + HSPACE, + MOVABLELIMITS, + RSPACE, + SEPARATORS, + ENABLE_BACKGROUND, + CHECKED, + OPACITY, + BORDER, + HIDDEN, + RENDERING_INTENT, + SANDBOX, + ACCESSKEY, + BASEFREQUENCY, + BASE, + CITE, + EDGEMODE, + INDEX, + LABEL, + NORESIZE, + ONSELECT, + ONREADYSTATECHANGE, + ORIENT, + ONBEFOREPASTE, + ONKEYDOWN, + RULES, + SELECTED, + SCHEME, + TYPE, + ONAFTERPRINT, + ALIGN, + HEIGHT, + LANGUAGE, + LENGTHADJUST, + PING, + ARCHIVE, + METHOD, + NOSHADE, + ALTIMG, + ADDITIVE, + DEFINITIONURL, + ONFINISH, + SCRIPTLEVEL, + VALIGN, + MARKER_MID, + MARKER_START, + MASKCONTENTUNITS, + DECLARE, + MAXLENGTH, + ROWLINES, + TITLE, + FRAME, + PROMPT, + USEMAP, + IN, + KERNELUNITLENGTH, + ONEND, + POINTSATX, + STANDBY, + WHEN, + XLINK_ARCROLE, + XLINK_SHOW, + AUTOFOCUS, + COLOR_RENDERING, + ENCODING, + LQUOTE, + ONMOUSEWHEEL, + ONCONTEXTMENU, + ONMOUSEMOVE, + ONFOCUSOUT, + STROKE_LINECAP, + STROKE_MITERLIMIT, + STROKE_OPACITY, + CLIP_PATH, + GLYPH_ORIENTATION_VERTICAL, + KEYPOINTS, + STEP, + SLOPE, + WRAP, + CHAR, + NOWRAP, + ONDRAGOVER, + ONERROR, + ONDRAGLEAVE, + AXIS, + CROSSORIGIN, + CLOSE, + KEYSPLINES, + OFFSET, + ROWSPACING, + VERSION, + CONTENT, + FONT_STRETCH, + FONTSTYLE, + FONT_VARIANT, + FONT_SIZE, + MULTIPLE, + POSTER, + PATTERNCONTENTUNITS, + TEXT_RENDERING, + TEXT, + COLUMNSPAN, + COLUMNWIDTH, + ONCUT, + REQUIREDEXTENSIONS, + ELEVATION, + CX, + FX, + REFX, + CY, + FY, + REFY, + ALT, + DUR, + FOR, + LOW, + MAX, + REV, + D, + X, + Z, + X1, + K2, + Y2, + K4, + XML_LANG, + ARIA_VALUEMAX, + ARIA_DESCRIBEDBY, + ARIA_CHECKED, + ARIA_DROPEFFECT, + ARIA_EXPANDED, + ARIA_LEVEL, + ARIA_HIDDEN, + ARIA_POSINSET, + ARIA_INVALID, + ARIA_VALUEMIN, + ARIA_CONTROLS, + ARIA_READONLY, + ARIA_ACTIVEDESCENDANT, + ARIA_DATATYPE, + ARIA_SORT, + ARIA_FLOWTO, + ARIA_LIVE, + ARIA_SETSIZE, + DISABLED, + DATA, + EQUALROWS, + ISMAP, + LSPACE, + NOTATION, + ONPASTE, + ROWALIGN, + SEPARATOR, + VSPACE, + YCHANNELSELECTOR, + ONDBLCLICK, + CALCMODE, + FENCE, + ONACTIVATE, + SPACING, + SPECULARCONSTANT, + ID, + GRADIENTUNITS, + HEADERS, + READONLY, + SEED, + STDDEVIATION, + WORD_SPACING, + ACCEPT_CHARSET, + ACCENT, + BEVELLED, + BASELINE_SHIFT, + BASELINE, + CODE, + CODEBASE, + DEFER, + DIRECTION, + EDGE, + FACE, + INTERCEPT, + LINEBREAK, + LINETHICKNESS, + NAME, + ONBEFOREUNLOAD, + OBJECT, + ORDER, + ONRESET, + ONMESSAGE, + ONBEFOREPRINT, + ORIENTATION, + ONSELECTSTART, + ONKEYPRESS, + ONBEFORECUT, + ONRESIZE, + REFERRERPOLICY, + ROLE, + REPEATDUR, + SIZES, + STRETCHY, + SPREADMETHOD, + SIZE, + DIFFUSECONSTANT, + HREFLANG, + PROFILE, + XREF, + ALIGNMENT_BASELINE, + DRAGGABLE, + IMAGESIZES, + IMAGE_RENDERING, + LANG, + LONGDESC, + MARGINHEIGHT, + ORIGIN, + TARGET, + TARGETY, + HIGH, + MATHBACKGROUND, + MATHVARIANT, + MATHSIZE, + ONCHANGE, + PATH, + ACTIONTYPE, + ACTIVE, + BEGIN, + DIVISOR, + LIMITINGCONEANGLE, + MANIFEST, + OPTIMUM, + RADIUS, + SCRIPTSIZEMULTIPLIER, + TABINDEX, + VISIBILITY, + LINK, + MARKERHEIGHT, + MASK, + MARKERWIDTH, + MARKERUNITS, + AMPLITUDE, + CELLPADDING, + FILL_RULE, + FILL_OPACITY, + ONCLICK, + REPLACE, + SCALE, + TABLEVALUES, + AZIMUTH, + FRAMEBORDER, + FRAMESPACING, + FORM, + PRIMITIVEUNITS, + SUMMARY, + ZOOMANDPAN, + ALINK, + ICON, + KERNING, + ONUNLOAD, + ONINVALID, + ONINPUT, + POINTS, + POINTSATY, + SPAN, + TRANSFORM_ORIGIN, + VLINK, + XLINK_HREF, + XLINK_ROLE, + XMLNS_XLINK, + XLINK_TYPE, + XLINK_ACTUATE, + AUTOCOMPLETE, + AUTOCAPITALIZE, + COLOR_PROFILE, + COLOR_INTERPOLATION, + COLOR_INTERPOLATION_FILTERS, + EXPONENT, + FLOOD_OPACITY, + NUMOCTAVES, + ONLOAD, + ONMOUSEENTER, + ONFOCUSIN, + ONZOOM, + ONMOUSELEAVE, + ONMOUSEUP, + ONMOUSEOUT, + ONMOUSEDOWN, + RQUOTE, + STROKE_DASHARRAY, + STROKE_LINEJOIN, + STROKE, + STROKE_WIDTH, + COMPACT, + CLIP_RULE, + CLIPPATHUNITS, + DISPLAYSTYLE, + GLYPH_ORIENTATION_HORIZONTAL, + HTTP_EQUIV, + LOOP, + SCOPED, + SHAPE_RENDERING, + SHAPE, + STOP_COLOR, + TEMPLATE, + ABBR, + ATTRIBUTETYPE, + COORDS, + CHARSET, + NOHREF, + ONDRAGENTER, + ONDRAGEND, + ONDRAGDROP, + OPERATOR, + ONDRAGSTART, + STARTOFFSET, + AS, + BIAS, + CLASSID, + COLS, + CLOSURE, + CLASS, + KEYSYSTEM, + LOWSRC, + MINSIZE, + PRESERVEALPHA, + ROWSPAN, + ROWS, + SUBSCRIPTSHIFT, + ALTTEXT, + CONTROLS, + CONTEXTMENU, + ENCTYPE, + FILTER, + FONT_WEIGHT, + FONT_STYLE, + FONT_FAMILY, + FONT_SIZE_ADJUST, + FONTSIZE, + KEYTIMES, + LIST, + RT, + ONSTART, + PATTERNTRANSFORM, + PATTERNUNITS, + RESTART, + SYSTEMLANGUAGE, + TEXT_DECORATION, + TEXTLENGTH, + WRITING_MODE, + ACCUMULATE, + COLUMNLINES, + COLUMNSPACING, + GROUPALIGN, + ONSUBMIT, + REQUIRED, + RESULT, + VALUES, + VALUE, + VIEWTARGET, + }; + private final static int[] ATTRIBUTE_HASHES = { + 1867462756, + 1748971848, + 1966442279, + 1681174213, + 1785053243, + 1916286197, + 2004846654, + 1680165421, + 1723336432, + 1754899031, + 1816104145, + 1905628916, + 1924629705, + 1988784439, + 2024647008, + 71827457, + 1680282148, + 1689324870, + 1747295467, + 1754579720, + 1756889417, + 1803561214, + 1848600826, + 1884295780, + 1910441627, + 1922607670, + 1939976792, + 1975062341, + 2000752725, + 2009079867, + 2073034754, + 57205395, + 911736834, + 1680181996, + 1680368221, + 1685882101, + 1704526375, + 1736416327, + 1747906667, + 1751755561, + 1754698327, + 1756360955, + 1773606972, + 1787365531, + 1805715690, + 1823574314, + 1854497001, + 1874270021, + 1898415413, + 1906423097, + 1915025672, + 1921977416, + 1923088386, + 1933369607, + 1941550652, + 1972904518, + 1983398182, + 1991625270, + 2001710298, + 2007021895, + 2016810187, + 2060474743, + 2082471938, + 53006051, + 60345635, + 885522434, + 1680095865, + 1680165533, + 1680229115, + 1680343801, + 1680437801, + 1682440540, + 1687620127, + 1692408896, + 1721189160, + 1733874289, + 1740096054, + 1747479606, + 1748503880, + 1749549708, + 1753550036, + 1754644293, + 1754835516, + 1756147974, + 1756762256, + 1767725700, + 1781007934, + 1786775671, + 1791068279, + 1804081401, + 1814560070, + 1820727381, + 1824159037, + 1854366938, + 1865910331, + 1872343590, + 1884079398, + 1890996553, + 1903612236, + 1906408542, + 1908462185, + 1910503637, + 1915757815, + 1917857531, + 1922413307, + 1922677495, + 1924517489, + 1932959284, + 1934970504, + 1941435445, + 1965512429, + 1972656710, + 1972922984, + 1983157559, + 1984430082, + 1990107683, + 2000096287, + 2001634458, + 2001826027, + 2006459190, + 2008401563, + 2010716309, + 2019887833, + 2026893641, + 2065694722, + 2081423362, + 2089811970, + 52488851, + 55077603, + 59825747, + 68157441, + 878182402, + 901775362, + 1037879561, + 1680159327, + 1680165437, + 1680165692, + 1680198203, + 1680231247, + 1680315086, + 1680345965, + 1680413393, + 1680452349, + 1681879063, + 1683805446, + 1686731997, + 1689048326, + 1689839946, + 1699185409, + 1714763319, + 1721347639, + 1731048742, + 1734182982, + 1739583824, + 1740130375, + 1747309881, + 1747800157, + 1748021284, + 1748566068, + 1749350104, + 1751507685, + 1753049109, + 1754434872, + 1754612424, + 1754647074, + 1754794646, + 1754860061, + 1754927689, + 1756219733, + 1756704824, + 1756836998, + 1757421892, + 1771569964, + 1780879045, + 1784574102, + 1786622296, + 1786851500, + 1788842244, + 1797886599, + 1804054854, + 1804405895, + 1814517574, + 1814656840, + 1816178925, + 1821958888, + 1823829083, + 1825437894, + 1854285018, + 1854466380, + 1854497008, + 1866496199, + 1871251689, + 1873656984, + 1874788501, + 1884246821, + 1889569526, + 1891937366, + 1900544002, + 1903759600, + 1905754853, + 1906419001, + 1907701479, + 1909819252, + 1910441773, + 1910527802, + 1915341049, + 1916247343, + 1917295176, + 1921061206, + 1922400908, + 1922566877, + 1922665179, + 1922679610, + 1924443742, + 1924583073, + 1924773438, + 1933123337, + 1934917290, + 1937336473, + 1941286708, + 1941440197, + 1943317364, + 1966384692, + 1972151670, + 1972744954, + 1972908839, + 1972996699, + 1982254612, + 1983290011, + 1983432389, + 1987422362, + 1989522022, + 1991220282, + 1993343287, + 2000160071, + 2001527900, + 2001669449, + 2001732764, + 2001898809, + 2005342360, + 2006824246, + 2007064819, + 2009041198, + 2009231684, + 2016711994, + 2017010843, + 2023342821, + 2024794274, + 2034765641, + 2065170434, + 2066743298, + 2075005220, + 2081947650, + 2083520514, + 2091784484, + 50917059, + 52489043, + 53537523, + 56685811, + 57210387, + 59830867, + 60817409, + 71303169, + 72351745, + 884998146, + 894959618, + 902299650, + 928514050, + 1038063816, + 1680140893, + 1680159328, + 1680165436, + 1680165487, + 1680165613, + 1680181850, + 1680185931, + 1680198381, + 1680230940, + 1680251485, + 1680311085, + 1680323325, + 1680345685, + 1680347981, + 1680411449, + 1680433915, + 1680446153, + 1680511804, + 1681733672, + 1681969220, + 1682587945, + 1684319541, + 1685902598, + 1687164232, + 1687751191, + 1689130184, + 1689788441, + 1691145478, + 1692933184, + 1704262346, + 1714745560, + 1716303957, + 1721305962, + 1723309623, + 1723336528, + 1732771842, + 1733919469, + 1734404167, + 1739561208, + 1739927860, + 1740119884, + 1742183484, + 1747299630, + 1747446838, + 1747792072, + 1747839118, + 1747939528, + 1748306996, + 1748552744, + 1748869205, + 1749027145, + 1749399124, + 1749856356, + 1751679545, + 1752985897, + 1753297133, + 1754214628, + 1754546894, + 1754606246, + 1754643237, + 1754645079, + 1754647353, + 1754792749, + 1754798923, + 1754858317, + 1754872618, + 1754907227, + 1754958648, + 1756190926, + 1756302628, + 1756471625, + 1756737685, + 1756804936, + 1756874572, + 1757053236, + 1765800271, + 1767875272, + 1772032615, + 1776114564, + 1780975314, + 1782518297, + 1785051290, + 1785174319, + 1786740932, + 1786821704, + 1787193500, + 1788254870, + 1790814502, + 1791070327, + 1801312388, + 1804036350, + 1804069019, + 1804235064, + 1804978712, + 1805715716, + 1814558026, + 1814656326, + 1814986837, + 1816144023, + 1820262641, + 1820928104, + 1822002839, + 1823580230, + 1823841492, + 1824377064, + 1825677514, + 1853862084, + 1854302364, + 1854464212, + 1854474395, + 1854497003, + 1864698185, + 1865910347, + 1867448617, + 1867620412, + 1872034503, + 1873590471, + 1874261045, + 1874698443, + 1881750231, + 1884142379, + 1884267068, + 1884343396, + 1889633006, + 1891186903, + 1894552650, + 1898428101, + 1902640276, + 1903659239, + 1905541832, + 1905672729, + 1905902311, + 1906408598, + 1906421049, + 1907660596, + 1908316832, + 1909438149, + 1910328970, + 1910441770, + 1910487243, + 1910507338, + 1910572893, + 1915295948, + 1915394254, + 1916210285, + 1916278099, + 1916337499, + 1917327080, + 1917953597, + 1921894426, + 1922319046, + 1922413292, + 1922470745, + 1922567078, + 1922665052, + 1922671417, + 1922679386, + 1922699851, + 1924206934, + 1924462384, + 1924570799, + 1924585254, + 1924738716, + 1932870919, + 1932986153, + 1933145837, + 1933508940, + 1934917372, + 1935597338, + 1937777860, + 1941253366, + 1941409583, + 1941438085, + 1941454586, + 1942026440, + 1965349396, + 1965561677, + 1966439670, + 1966454567, + 1972196486, + 1972744939, + 1972863609, + 1972904522, + 1972909592, + 1972962123, + 1974849131, + 1980235778, + 1982640164, + 1983266615, + 1983347764, + 1983416119, + 1983461061, + 1987410233, + 1988132214, + 1988788535, + 1990062797, + 1991021879, + 1991392548, + 1991643278, + 1999273799, + 2000125224, + 2000162011, + 2001210183, + 2001578182, + 2001634459, + 2001669450, + 2001710299, + 2001814704, + 2001898808, + 2004199576, + 2004957380, + 2005925890, + 2006516551, + 2007019632, + 2007064812, + 2008084807, + 2008408414, + 2009071951, + 2009141482, + 2010452700, + 2015950026, + 2016787611, + 2016910397, + 2018908874, + 2023146024, + 2024616088, + 2024763702, + 2026741958, + 2026975253, + 2060302634, + }; +} diff --git a/parser/html/javasrc/ElementName.java b/parser/html/javasrc/ElementName.java new file mode 100644 index 0000000000..9ee2ad0152 --- /dev/null +++ b/parser/html/javasrc/ElementName.java @@ -0,0 +1,1896 @@ +/* + * Copyright (c) 2008-2017 Mozilla Foundation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + */ + +package nu.validator.htmlparser.impl; + +// uncomment to regenerate self +//import java.io.BufferedReader; +//import java.io.File; +//import java.io.FileInputStream; +//import java.io.IOException; +//import java.io.InputStreamReader; +//import java.util.Arrays; +//import java.util.Collections; +//import java.util.HashMap; +//import java.util.LinkedList; +//import java.util.List; +//import java.util.Map; +//import java.util.Map.Entry; +//import java.util.regex.Matcher; +//import java.util.regex.Pattern; + +import nu.validator.htmlparser.annotation.Inline; +import nu.validator.htmlparser.annotation.Local; +import nu.validator.htmlparser.annotation.NoLength; +import nu.validator.htmlparser.annotation.Unsigned; +import nu.validator.htmlparser.common.Interner; + +public final class ElementName + // uncomment when regenerating self +// implements Comparable<ElementName> +{ + + /** + * The mask for extracting the dispatch group. + */ + public static final int GROUP_MASK = 127; + + /** + * Indicates that the element is not a pre-interned element. Forbidden on + * preinterned elements. + */ + public static final int NOT_INTERNED = (1 << 30); + + /** + * Indicates that the element is in the "special" category. This bit should + * not be pre-set on MathML or SVG specials--only on HTML specials. + */ + public static final int SPECIAL = (1 << 29); + + /** + * The element is foster-parenting. This bit should be pre-set on elements + * that are foster-parenting as HTML. + */ + public static final int FOSTER_PARENTING = (1 << 28); + + /** + * The element is scoping. This bit should be pre-set on elements that are + * scoping as HTML. + */ + public static final int SCOPING = (1 << 27); + + /** + * The element is scoping as SVG. + */ + public static final int SCOPING_AS_SVG = (1 << 26); + + /** + * The element is scoping as MathML. + */ + public static final int SCOPING_AS_MATHML = (1 << 25); + + /** + * The element is an HTML integration point. + */ + public static final int HTML_INTEGRATION_POINT = (1 << 24); + + /** + * The element has an optional end tag. + */ + public static final int OPTIONAL_END_TAG = (1 << 23); + + private @Local String name; + + private @Local String camelCaseName; + + // CPPONLY: private @HtmlCreator Object htmlCreator; + + // CPPONLY: private @SvgCreator Object svgCreator; + + /** + * The lowest 7 bits are the dispatch group. The high bits are flags. + */ + public final int flags; + + @Inline public @Local String getName() { + return name; + } + + @Inline public @Local String getCamelCaseName() { + return camelCaseName; + } + + // CPPONLY: @Inline public @HtmlCreator Object getHtmlCreator() { + // CPPONLY: return htmlCreator; + // CPPONLY: } + + // CPPONLY: @Inline public @SvgCreator Object getSvgCreator() { + // CPPONLY: return svgCreator; + // CPPONLY: } + + @Inline public int getFlags() { + return flags; + } + + @Inline public int getGroup() { + return flags & ElementName.GROUP_MASK; + } + + @Inline public boolean isInterned() { + return (flags & ElementName.NOT_INTERNED) == 0; + } + + @Inline static int levelOrderBinarySearch(int[] data, int key) { + int n = data.length; + int i = 0; + + while (i < n) { + int val = data[i]; + if (val < key) { + i = 2 * i + 2; + } else if (val > key) { + i = 2 * i + 1; + } else { + return i; + } + } + + return -1; + } + + @Inline static ElementName elementNameByBuffer(@NoLength char[] buf, + int length, Interner interner) { + @Unsigned int hash = ElementName.bufToHash(buf, length); + int[] hashes; + hashes = ElementName.ELEMENT_HASHES; + int index = levelOrderBinarySearch(hashes, hash); + if (index < 0) { + return null; + } else { + ElementName elementName = ElementName.ELEMENT_NAMES[index]; + @Local String name = elementName.name; + if (!Portability.localEqualsBuffer(name, buf, length)) { + return null; + } + return elementName; + } + } + + /** + * This method has to return a unique positive integer for each well-known + * lower-cased element name. + * + * @param buf + * @param len + * @return + */ + @Inline private static @Unsigned int bufToHash(@NoLength char[] buf, + int length) { + @Unsigned int len = length; + @Unsigned int first = buf[0]; + first <<= 19; + @Unsigned int second = 1 << 23; + @Unsigned int third = 0; + @Unsigned int fourth = 0; + @Unsigned int fifth = 0; + if (length >= 4) { + second = buf[length - 4]; + second <<= 4; + third = buf[length - 3]; + third <<= 9; + fourth = buf[length - 2]; + fourth <<= 14; + fifth = buf[length - 1]; + fifth <<= 24; + } else if (length == 3) { + second = buf[1]; + second <<= 4; + third = buf[2]; + third <<= 9; + } else if (length == 2) { + second = buf[1]; + second <<= 24; + } + return len + first + second + third + fourth + fifth; + } + + private ElementName(@Local String name, @Local String camelCaseName, + // CPPONLY: @HtmlCreator Object htmlCreator, @SvgCreator Object + // CPPONLY: svgCreator, + int flags) { + this.name = name; + this.camelCaseName = camelCaseName; + // CPPONLY: this.htmlCreator = htmlCreator; + // CPPONLY: this.svgCreator = svgCreator; + this.flags = flags; + } + + public ElementName() { + this.name = null; + this.camelCaseName = null; + // CPPONLY: this.htmlCreator = NS_NewHTMLUnknownElement; + // CPPONLY: this.svgCreator = NS_NewSVGUnknownElement; + this.flags = TreeBuilder.OTHER | NOT_INTERNED; + } + + public void destructor() { + // The translator adds refcount debug code here. + } + + @Inline public void setNameForNonInterned(@Local String name + // CPPONLY: , boolean custom + ) { + // No need to worry about refcounting the local name, because in the + // C++ case the scoped atom table remembers its own atoms. + this.name = name; + this.camelCaseName = name; + // CPPONLY: if (custom) { + // CPPONLY: this.htmlCreator = NS_NewCustomElement; + // CPPONLY: } else { + // CPPONLY: this.htmlCreator = NS_NewHTMLUnknownElement; + // CPPONLY: } + // The assertion below relies on TreeBuilder.OTHER being zero! + // TreeBuilder.OTHER isn't referenced here, because it would create + // a circular C++ header dependency given that this method is inlined. + assert this.flags == ElementName.NOT_INTERNED; + } + + // CPPONLY: @Inline public boolean isCustom() { + // CPPONLY: return this.htmlCreator == NS_NewCustomElement; + // CPPONLY: } + + public static final ElementName ANNOTATION_XML = new ElementName( + "annotation-xml", "annotation-xml", + // CPPONLY: NS_NewHTMLUnknownElement, NS_NewSVGUnknownElement, + TreeBuilder.ANNOTATION_XML | SCOPING_AS_MATHML); + + // START CODE ONLY USED FOR GENERATING CODE uncomment and run to regenerate + +// private static final Pattern HTML_TAG_DEF = Pattern.compile( +// "^HTML_TAG\\(([^,]+),\\s*([^,]+),\\s*[^,]+\\).*$"); +// +// private static final Pattern HTML_HTMLELEMENT_TAG_DEF = Pattern.compile( +// "^HTML_HTMLELEMENT_TAG\\(([^\\)]+)\\).*$"); +// +// private static final Pattern SVG_TAG_DEF = Pattern.compile( +// "^SVG_(?:FROM_PARSER_)?TAG\\(([^,]+),\\s*([^\\)]+)\\).*$"); +// +// private static final Map<String, String> htmlMap = new HashMap<String, String>(); +// +// private static final Map<String, String> svgMap = new HashMap<String, String>(); +// +// private static void ingestHtmlTags(File htmlList) throws IOException { +// // This doesn't need to be efficient, so let's make it easy to write. +// BufferedReader htmlReader = new BufferedReader( +// new InputStreamReader(new FileInputStream(htmlList), "utf-8")); +// try { +// String line; +// while ((line = htmlReader.readLine()) != null) { +// if (!line.startsWith("HTML_")) { +// continue; +// } +// if (line.startsWith("HTML_OTHER")) { +// continue; +// } +// Matcher m = HTML_TAG_DEF.matcher(line); +// if (m.matches()) { +// String iface = m.group(2); +// if ("Unknown".equals(iface)) { +// continue; +// } +// htmlMap.put(m.group(1), "NS_NewHTML" + iface + "Element"); +// } else { +// m = HTML_HTMLELEMENT_TAG_DEF.matcher(line); +// if (!m.matches()) { +// throw new RuntimeException( +// "Malformed HTML element definition: " + line); +// } +// htmlMap.put(m.group(1), "NS_NewHTMLElement"); +// } +// } +// } finally { +// htmlReader.close(); +// } +// } +// +// private static void ingestSvgTags(File svgList) throws IOException { +// // This doesn't need to be efficient, so let's make it easy to write. +// BufferedReader svgReader = new BufferedReader( +// new InputStreamReader(new FileInputStream(svgList), "utf-8")); +// try { +// String line; +// while ((line = svgReader.readLine()) != null) { +// if (!line.startsWith("SVG_")) { +// continue; +// } +// Matcher m = SVG_TAG_DEF.matcher(line); +// if (!m.matches()) { +// throw new RuntimeException( +// "Malformed SVG element definition: " + line); +// } +// String name = m.group(1); +// if ("svgSwitch".equals(name)) { +// name = "switch"; +// } +// svgMap.put(name, "NS_NewSVG" + m.group(2) + "Element"); +// } +// } finally { +// svgReader.close(); +// } +// } +// +// private static String htmlCreator(String name) { +// String creator = htmlMap.remove(name); +// if (creator != null) { +// return creator; +// } +// return "NS_NewHTMLUnknownElement"; +// } +// +// private static String svgCreator(String name) { +// String creator = svgMap.remove(name); +// if (creator != null) { +// return creator; +// } +// return "NS_NewSVGUnknownElement"; +// } +// +// /** +// * @see java.lang.Object#toString() +// */ +// @Override public String toString() { +// return "(\"" + name + "\", \"" + camelCaseName + "\", \n// CPP" +// + "ONLY: " + htmlCreator(name) + ",\n// CPP" + "ONLY: " +// + svgCreator(camelCaseName) + ", \n" + decomposedFlags() + ")"; +// } +// +// private String decomposedFlags() { +// StringBuilder buf = new StringBuilder("TreeBuilder."); +// buf.append(treeBuilderGroupToName()); +// if ((flags & SPECIAL) != 0) { +// buf.append(" | SPECIAL"); +// } +// if ((flags & FOSTER_PARENTING) != 0) { +// buf.append(" | FOSTER_PARENTING"); +// } +// if ((flags & SCOPING) != 0) { +// buf.append(" | SCOPING"); +// } +// if ((flags & SCOPING_AS_MATHML) != 0) { +// buf.append(" | SCOPING_AS_MATHML"); +// } +// if ((flags & SCOPING_AS_SVG) != 0) { +// buf.append(" | SCOPING_AS_SVG"); +// } +// if ((flags & OPTIONAL_END_TAG) != 0) { +// buf.append(" | OPTIONAL_END_TAG"); +// } +// return buf.toString(); +// } +// +// private String constName() { +// char[] buf = new char[name.length()]; +// for (int i = 0; i < name.length(); i++) { +// char c = name.charAt(i); +// if (c == '-') { +// if (!"annotation-xml".equals(name)) { +// throw new RuntimeException( +// "Non-annotation-xml element name with hyphen: " +// + name); +// } +// buf[i] = '_'; +// } else if (c >= '0' && c <= '9') { +// buf[i] = c; +// } else { +// buf[i] = (char) (c - 0x20); +// } +// } +// return new String(buf); +// } +// +// private int hash() { +// return bufToHash(name.toCharArray(), name.length()); +// } +// +// public int compareTo(ElementName other) { +// int thisHash = this.hash(); +// int otherHash = other.hash(); +// if (thisHash < otherHash) { +// return -1; +// } else if (thisHash == otherHash) { +// return 0; +// } else { +// return 1; +// } +// } +// +// private String treeBuilderGroupToName() { +// switch (getGroup()) { +// case TreeBuilder.OTHER: +// return "OTHER"; +// case TreeBuilder.A: +// return "A"; +// case TreeBuilder.BASE: +// return "BASE"; +// case TreeBuilder.BODY: +// return "BODY"; +// case TreeBuilder.BR: +// return "BR"; +// case TreeBuilder.BUTTON: +// return "BUTTON"; +// case TreeBuilder.CAPTION: +// return "CAPTION"; +// case TreeBuilder.COL: +// return "COL"; +// case TreeBuilder.COLGROUP: +// return "COLGROUP"; +// case TreeBuilder.FONT: +// return "FONT"; +// case TreeBuilder.FORM: +// return "FORM"; +// case TreeBuilder.FRAME: +// return "FRAME"; +// case TreeBuilder.FRAMESET: +// return "FRAMESET"; +// case TreeBuilder.IMAGE: +// return "IMAGE"; +// case TreeBuilder.INPUT: +// return "INPUT"; +// case TreeBuilder.LI: +// return "LI"; +// case TreeBuilder.LINK_OR_BASEFONT_OR_BGSOUND: +// return "LINK_OR_BASEFONT_OR_BGSOUND"; +// case TreeBuilder.MATH: +// return "MATH"; +// case TreeBuilder.META: +// return "META"; +// case TreeBuilder.SVG: +// return "SVG"; +// case TreeBuilder.HEAD: +// return "HEAD"; +// case TreeBuilder.HR: +// return "HR"; +// case TreeBuilder.HTML: +// return "HTML"; +// case TreeBuilder.KEYGEN: +// return "KEYGEN"; +// case TreeBuilder.NOBR: +// return "NOBR"; +// case TreeBuilder.NOFRAMES: +// return "NOFRAMES"; +// case TreeBuilder.NOSCRIPT: +// return "NOSCRIPT"; +// case TreeBuilder.OPTGROUP: +// return "OPTGROUP"; +// case TreeBuilder.OPTION: +// return "OPTION"; +// case TreeBuilder.P: +// return "P"; +// case TreeBuilder.PLAINTEXT: +// return "PLAINTEXT"; +// case TreeBuilder.SCRIPT: +// return "SCRIPT"; +// case TreeBuilder.SELECT: +// return "SELECT"; +// case TreeBuilder.STYLE: +// return "STYLE"; +// case TreeBuilder.TABLE: +// return "TABLE"; +// case TreeBuilder.TEXTAREA: +// return "TEXTAREA"; +// case TreeBuilder.TITLE: +// return "TITLE"; +// case TreeBuilder.TEMPLATE: +// return "TEMPLATE"; +// case TreeBuilder.TR: +// return "TR"; +// case TreeBuilder.XMP: +// return "XMP"; +// case TreeBuilder.TBODY_OR_THEAD_OR_TFOOT: +// return "TBODY_OR_THEAD_OR_TFOOT"; +// case TreeBuilder.TD_OR_TH: +// return "TD_OR_TH"; +// case TreeBuilder.DD_OR_DT: +// return "DD_OR_DT"; +// case TreeBuilder.H1_OR_H2_OR_H3_OR_H4_OR_H5_OR_H6: +// return "H1_OR_H2_OR_H3_OR_H4_OR_H5_OR_H6"; +// case TreeBuilder.OBJECT: +// return "OBJECT"; +// case TreeBuilder.OUTPUT: +// return "OUTPUT"; +// case TreeBuilder.MARQUEE_OR_APPLET: +// return "MARQUEE_OR_APPLET"; +// case TreeBuilder.PRE_OR_LISTING: +// return "PRE_OR_LISTING"; +// case TreeBuilder.B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U: +// return "B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U"; +// case TreeBuilder.UL_OR_OL_OR_DL: +// return "UL_OR_OL_OR_DL"; +// case TreeBuilder.IFRAME: +// return "IFRAME"; +// case TreeBuilder.NOEMBED: +// return "NOEMBED"; +// case TreeBuilder.EMBED: +// return "EMBED"; +// case TreeBuilder.IMG: +// return "IMG"; +// case TreeBuilder.AREA_OR_WBR: +// return "AREA_OR_WBR"; +// case TreeBuilder.DIV_OR_BLOCKQUOTE_OR_CENTER_OR_MENU: +// return "DIV_OR_BLOCKQUOTE_OR_CENTER_OR_MENU"; +// case TreeBuilder.FIELDSET: +// return "FIELDSET"; +// case TreeBuilder.ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY: +// return "ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY"; +// case TreeBuilder.RUBY_OR_SPAN_OR_SUB_OR_SUP_OR_VAR: +// return "RUBY_OR_SPAN_OR_SUB_OR_SUP_OR_VAR"; +// case TreeBuilder.RB_OR_RTC: +// return "RB_OR_RTC"; +// case TreeBuilder.RT_OR_RP: +// return "RT_OR_RP"; +// case TreeBuilder.PARAM_OR_SOURCE_OR_TRACK: +// return "PARAM_OR_SOURCE_OR_TRACK"; +// case TreeBuilder.MGLYPH_OR_MALIGNMARK: +// return "MGLYPH_OR_MALIGNMARK"; +// case TreeBuilder.MI_MO_MN_MS_MTEXT: +// return "MI_MO_MN_MS_MTEXT"; +// case TreeBuilder.ANNOTATION_XML: +// return "ANNOTATION_XML"; +// case TreeBuilder.FOREIGNOBJECT_OR_DESC: +// return "FOREIGNOBJECT_OR_DESC"; +// } +// return null; +// } +// +// private static void fillLevelOrderArray(List<ElementName> sorted, int depth, +// int rootIdx, ElementName[] levelOrder) { +// if (rootIdx >= levelOrder.length) { +// return; +// } +// +// if (depth > 0) { +// fillLevelOrderArray(sorted, depth - 1, rootIdx * 2 + 1, levelOrder); +// } +// +// if (!sorted.isEmpty()) { +// levelOrder[rootIdx] = sorted.remove(0); +// } +// +// if (depth > 0) { +// fillLevelOrderArray(sorted, depth - 1, rootIdx * 2 + 2, levelOrder); +// } +// } +// +// /** +// * Regenerate self +// * +// * The args should be the paths to m-c files +// * parser/htmlparser/nsHTMLTagList.h and dom/svg/SVGTagList.h. +// */ +// public static void main(String[] args) { +// File htmlList = new File(args[0]); +// File svgList = new File(args[1]); +// try { +// ingestHtmlTags(htmlList); +// } catch (IOException e) { +// throw new RuntimeException(e); +// } +// try { +// ingestSvgTags(svgList); +// } catch (IOException e) { +// throw new RuntimeException(e); +// } +// +// Arrays.sort(ELEMENT_NAMES); +// for (int i = 0; i < ELEMENT_NAMES.length; i++) { +// int hash = ELEMENT_NAMES[i].hash(); +// if (hash < 0) { +// System.err.println("Negative hash: " + ELEMENT_NAMES[i].name); +// return; +// } +// for (int j = i + 1; j < ELEMENT_NAMES.length; j++) { +// if (hash == ELEMENT_NAMES[j].hash()) { +// System.err.println( +// "Hash collision: " + ELEMENT_NAMES[i].name + ", " +// + ELEMENT_NAMES[j].name); +// return; +// } +// } +// } +// for (int i = 0; i < ELEMENT_NAMES.length; i++) { +// ElementName el = ELEMENT_NAMES[i]; +// System.out.println( +// "public static final ElementName " + el.constName() +// + " = new ElementName" + el.toString() + ";"); +// } +// +// LinkedList<ElementName> sortedNames = new LinkedList<ElementName>(); +// Collections.addAll(sortedNames, ELEMENT_NAMES); +// ElementName[] levelOrder = new ElementName[ELEMENT_NAMES.length]; +// int bstDepth = (int) Math.ceil( +// Math.log(ELEMENT_NAMES.length) / Math.log(2)); +// fillLevelOrderArray(sortedNames, bstDepth, 0, levelOrder); +// +// System.out.println( +// "private final static @NoLength ElementName[] ELEMENT_NAMES = {"); +// for (int i = 0; i < levelOrder.length; i++) { +// ElementName el = levelOrder[i]; +// System.out.println(el.constName() + ","); +// } +// System.out.println("};"); +// System.out.println("private final static int[] ELEMENT_HASHES = {"); +// for (int i = 0; i < levelOrder.length; i++) { +// ElementName el = levelOrder[i]; +// System.out.println(Integer.toString(el.hash()) + ","); +// } +// System.out.println("};"); +// +// for (Entry<String, String> entry : htmlMap.entrySet()) { +// System.err.println("Missing HTML element: " + entry.getKey()); +// } +// for (Entry<String, String> entry : svgMap.entrySet()) { +// System.err.println("Missing SVG element: " + entry.getKey()); +// } +// } + + // START GENERATED CODE +public static final ElementName BIG = new ElementName("big", "big", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U); +public static final ElementName BDI = new ElementName("bdi", "bdi", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OTHER); +public static final ElementName BDO = new ElementName("bdo", "bdo", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OTHER); +public static final ElementName COL = new ElementName("col", "col", +// CPPONLY: NS_NewHTMLTableColElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.COL | SPECIAL); +public static final ElementName DEL = new ElementName("del", "del", +// CPPONLY: NS_NewHTMLModElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OTHER); +public static final ElementName DFN = new ElementName("dfn", "dfn", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OTHER); +public static final ElementName DIR = new ElementName("dir", "dir", +// CPPONLY: NS_NewHTMLSharedElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY | SPECIAL); +public static final ElementName DIV = new ElementName("div", "div", +// CPPONLY: NS_NewHTMLDivElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.DIV_OR_BLOCKQUOTE_OR_CENTER_OR_MENU | SPECIAL); +public static final ElementName IMG = new ElementName("img", "img", +// CPPONLY: NS_NewHTMLImageElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.IMG | SPECIAL); +public static final ElementName INS = new ElementName("ins", "ins", +// CPPONLY: NS_NewHTMLModElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OTHER); +public static final ElementName KBD = new ElementName("kbd", "kbd", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OTHER); +public static final ElementName MAP = new ElementName("map", "map", +// CPPONLY: NS_NewHTMLMapElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OTHER); +public static final ElementName NAV = new ElementName("nav", "nav", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY | SPECIAL); +public static final ElementName PRE = new ElementName("pre", "pre", +// CPPONLY: NS_NewHTMLPreElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.PRE_OR_LISTING | SPECIAL); +public static final ElementName A = new ElementName("a", "a", +// CPPONLY: NS_NewHTMLAnchorElement, +// CPPONLY: NS_NewSVGAElement, +TreeBuilder.A); +public static final ElementName B = new ElementName("b", "b", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U); +public static final ElementName RTC = new ElementName("rtc", "rtc", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.RB_OR_RTC | OPTIONAL_END_TAG); +public static final ElementName SUB = new ElementName("sub", "sub", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.RUBY_OR_SPAN_OR_SUB_OR_SUP_OR_VAR); +public static final ElementName SVG = new ElementName("svg", "svg", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGSVGElement, +TreeBuilder.SVG); +public static final ElementName SUP = new ElementName("sup", "sup", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.RUBY_OR_SPAN_OR_SUB_OR_SUP_OR_VAR); +public static final ElementName SET = new ElementName("set", "set", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGSetElement, +TreeBuilder.OTHER); +public static final ElementName USE = new ElementName("use", "use", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGUseElement, +TreeBuilder.OTHER); +public static final ElementName VAR = new ElementName("var", "var", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.RUBY_OR_SPAN_OR_SUB_OR_SUP_OR_VAR); +public static final ElementName G = new ElementName("g", "g", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGGElement, +TreeBuilder.OTHER); +public static final ElementName WBR = new ElementName("wbr", "wbr", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.AREA_OR_WBR | SPECIAL); +public static final ElementName XMP = new ElementName("xmp", "xmp", +// CPPONLY: NS_NewHTMLPreElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.XMP | SPECIAL); +public static final ElementName I = new ElementName("i", "i", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U); +public static final ElementName P = new ElementName("p", "p", +// CPPONLY: NS_NewHTMLParagraphElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.P | SPECIAL | OPTIONAL_END_TAG); +public static final ElementName Q = new ElementName("q", "q", +// CPPONLY: NS_NewHTMLSharedElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OTHER); +public static final ElementName S = new ElementName("s", "s", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U); +public static final ElementName U = new ElementName("u", "u", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U); +public static final ElementName H1 = new ElementName("h1", "h1", +// CPPONLY: NS_NewHTMLHeadingElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.H1_OR_H2_OR_H3_OR_H4_OR_H5_OR_H6 | SPECIAL); +public static final ElementName H2 = new ElementName("h2", "h2", +// CPPONLY: NS_NewHTMLHeadingElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.H1_OR_H2_OR_H3_OR_H4_OR_H5_OR_H6 | SPECIAL); +public static final ElementName H3 = new ElementName("h3", "h3", +// CPPONLY: NS_NewHTMLHeadingElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.H1_OR_H2_OR_H3_OR_H4_OR_H5_OR_H6 | SPECIAL); +public static final ElementName H4 = new ElementName("h4", "h4", +// CPPONLY: NS_NewHTMLHeadingElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.H1_OR_H2_OR_H3_OR_H4_OR_H5_OR_H6 | SPECIAL); +public static final ElementName H5 = new ElementName("h5", "h5", +// CPPONLY: NS_NewHTMLHeadingElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.H1_OR_H2_OR_H3_OR_H4_OR_H5_OR_H6 | SPECIAL); +public static final ElementName H6 = new ElementName("h6", "h6", +// CPPONLY: NS_NewHTMLHeadingElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.H1_OR_H2_OR_H3_OR_H4_OR_H5_OR_H6 | SPECIAL); +public static final ElementName AREA = new ElementName("area", "area", +// CPPONLY: NS_NewHTMLAreaElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.AREA_OR_WBR | SPECIAL); +public static final ElementName DATA = new ElementName("data", "data", +// CPPONLY: NS_NewHTMLDataElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OTHER); +public static final ElementName FEFUNCA = new ElementName("fefunca", "feFuncA", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGFEFuncAElement, +TreeBuilder.OTHER); +public static final ElementName METADATA = new ElementName("metadata", "metadata", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGMetadataElement, +TreeBuilder.OTHER); +public static final ElementName META = new ElementName("meta", "meta", +// CPPONLY: NS_NewHTMLMetaElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.META | SPECIAL); +public static final ElementName TEXTAREA = new ElementName("textarea", "textarea", +// CPPONLY: NS_NewHTMLTextAreaElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.TEXTAREA | SPECIAL); +public static final ElementName FEFUNCB = new ElementName("fefuncb", "feFuncB", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGFEFuncBElement, +TreeBuilder.OTHER); +public static final ElementName RB = new ElementName("rb", "rb", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.RB_OR_RTC | OPTIONAL_END_TAG); +public static final ElementName DESC = new ElementName("desc", "desc", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGDescElement, +TreeBuilder.FOREIGNOBJECT_OR_DESC | SCOPING_AS_SVG); +public static final ElementName DD = new ElementName("dd", "dd", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.DD_OR_DT | SPECIAL | OPTIONAL_END_TAG); +public static final ElementName BGSOUND = new ElementName("bgsound", "bgsound", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.LINK_OR_BASEFONT_OR_BGSOUND | SPECIAL); +public static final ElementName EMBED = new ElementName("embed", "embed", +// CPPONLY: NS_NewHTMLEmbedElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.EMBED | SPECIAL); +public static final ElementName FEBLEND = new ElementName("feblend", "feBlend", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGFEBlendElement, +TreeBuilder.OTHER); +public static final ElementName FEFLOOD = new ElementName("feflood", "feFlood", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGFEFloodElement, +TreeBuilder.OTHER); +public static final ElementName HEAD = new ElementName("head", "head", +// CPPONLY: NS_NewHTMLSharedElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.HEAD | SPECIAL | OPTIONAL_END_TAG); +public static final ElementName LEGEND = new ElementName("legend", "legend", +// CPPONLY: NS_NewHTMLLegendElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OTHER); +public static final ElementName NOEMBED = new ElementName("noembed", "noembed", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.NOEMBED | SPECIAL); +public static final ElementName TD = new ElementName("td", "td", +// CPPONLY: NS_NewHTMLTableCellElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.TD_OR_TH | SPECIAL | SCOPING | OPTIONAL_END_TAG); +public static final ElementName THEAD = new ElementName("thead", "thead", +// CPPONLY: NS_NewHTMLTableSectionElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.TBODY_OR_THEAD_OR_TFOOT | SPECIAL | FOSTER_PARENTING | OPTIONAL_END_TAG); +public static final ElementName ASIDE = new ElementName("aside", "aside", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY | SPECIAL); +public static final ElementName ARTICLE = new ElementName("article", "article", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY | SPECIAL); +public static final ElementName ANIMATE = new ElementName("animate", "animate", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGAnimateElement, +TreeBuilder.OTHER); +public static final ElementName BASE = new ElementName("base", "base", +// CPPONLY: NS_NewHTMLSharedElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.BASE | SPECIAL); +public static final ElementName BLOCKQUOTE = new ElementName("blockquote", "blockquote", +// CPPONLY: NS_NewHTMLSharedElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.DIV_OR_BLOCKQUOTE_OR_CENTER_OR_MENU | SPECIAL); +public static final ElementName CODE = new ElementName("code", "code", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U); +public static final ElementName CIRCLE = new ElementName("circle", "circle", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGCircleElement, +TreeBuilder.OTHER); +public static final ElementName CITE = new ElementName("cite", "cite", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OTHER); +public static final ElementName ELLIPSE = new ElementName("ellipse", "ellipse", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGEllipseElement, +TreeBuilder.OTHER); +public static final ElementName FETURBULENCE = new ElementName("feturbulence", "feTurbulence", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGFETurbulenceElement, +TreeBuilder.OTHER); +public static final ElementName FEMERGENODE = new ElementName("femergenode", "feMergeNode", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGFEMergeNodeElement, +TreeBuilder.OTHER); +public static final ElementName FEIMAGE = new ElementName("feimage", "feImage", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGFEImageElement, +TreeBuilder.OTHER); +public static final ElementName FEMERGE = new ElementName("femerge", "feMerge", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGFEMergeElement, +TreeBuilder.OTHER); +public static final ElementName FETILE = new ElementName("fetile", "feTile", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGFETileElement, +TreeBuilder.OTHER); +public static final ElementName FRAME = new ElementName("frame", "frame", +// CPPONLY: NS_NewHTMLFrameElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.FRAME | SPECIAL); +public static final ElementName FIGURE = new ElementName("figure", "figure", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY | SPECIAL); +public static final ElementName FECOMPOSITE = new ElementName("fecomposite", "feComposite", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGFECompositeElement, +TreeBuilder.OTHER); +public static final ElementName IMAGE = new ElementName("image", "image", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGImageElement, +TreeBuilder.IMAGE); +public static final ElementName IFRAME = new ElementName("iframe", "iframe", +// CPPONLY: NS_NewHTMLIFrameElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.IFRAME | SPECIAL); +public static final ElementName LINE = new ElementName("line", "line", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGLineElement, +TreeBuilder.OTHER); +public static final ElementName MARQUEE = new ElementName("marquee", "marquee", +// CPPONLY: NS_NewHTMLMarqueeElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.MARQUEE_OR_APPLET | SPECIAL | SCOPING); +public static final ElementName POLYLINE = new ElementName("polyline", "polyline", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGPolylineElement, +TreeBuilder.OTHER); +public static final ElementName PICTURE = new ElementName("picture", "picture", +// CPPONLY: NS_NewHTMLPictureElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OTHER); +public static final ElementName SOURCE = new ElementName("source", "source", +// CPPONLY: NS_NewHTMLSourceElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.PARAM_OR_SOURCE_OR_TRACK); +public static final ElementName STRIKE = new ElementName("strike", "strike", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U); +public static final ElementName STYLE = new ElementName("style", "style", +// CPPONLY: NS_NewHTMLStyleElement, +// CPPONLY: NS_NewSVGStyleElement, +TreeBuilder.STYLE | SPECIAL); +public static final ElementName TABLE = new ElementName("table", "table", +// CPPONLY: NS_NewHTMLTableElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.TABLE | SPECIAL | FOSTER_PARENTING | SCOPING); +public static final ElementName TITLE = new ElementName("title", "title", +// CPPONLY: NS_NewHTMLTitleElement, +// CPPONLY: NS_NewSVGTitleElement, +TreeBuilder.TITLE | SPECIAL | SCOPING_AS_SVG); +public static final ElementName TIME = new ElementName("time", "time", +// CPPONLY: NS_NewHTMLTimeElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OTHER); +public static final ElementName TEMPLATE = new ElementName("template", "template", +// CPPONLY: NS_NewHTMLTemplateElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.TEMPLATE | SPECIAL | SCOPING); +public static final ElementName ALTGLYPHDEF = new ElementName("altglyphdef", "altGlyphDef", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OTHER); +public static final ElementName GLYPHREF = new ElementName("glyphref", "glyphRef", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OTHER); +public static final ElementName DIALOG = new ElementName("dialog", "dialog", +// CPPONLY: NS_NewHTMLDialogElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY | SPECIAL); +public static final ElementName FEFUNCG = new ElementName("fefuncg", "feFuncG", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGFEFuncGElement, +TreeBuilder.OTHER); +public static final ElementName FEDIFFUSELIGHTING = new ElementName("fediffuselighting", "feDiffuseLighting", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGFEDiffuseLightingElement, +TreeBuilder.OTHER); +public static final ElementName FESPECULARLIGHTING = new ElementName("fespecularlighting", "feSpecularLighting", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGFESpecularLightingElement, +TreeBuilder.OTHER); +public static final ElementName LISTING = new ElementName("listing", "listing", +// CPPONLY: NS_NewHTMLPreElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.PRE_OR_LISTING | SPECIAL); +public static final ElementName STRONG = new ElementName("strong", "strong", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U); +public static final ElementName ALTGLYPH = new ElementName("altglyph", "altGlyph", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OTHER); +public static final ElementName CLIPPATH = new ElementName("clippath", "clipPath", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGClipPathElement, +TreeBuilder.OTHER); +public static final ElementName MGLYPH = new ElementName("mglyph", "mglyph", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.MGLYPH_OR_MALIGNMARK); +public static final ElementName MATH = new ElementName("math", "math", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.MATH); +public static final ElementName MPATH = new ElementName("mpath", "mpath", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGMPathElement, +TreeBuilder.OTHER); +public static final ElementName PATH = new ElementName("path", "path", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGPathElement, +TreeBuilder.OTHER); +public static final ElementName TH = new ElementName("th", "th", +// CPPONLY: NS_NewHTMLTableCellElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.TD_OR_TH | SPECIAL | SCOPING | OPTIONAL_END_TAG); +public static final ElementName SWITCH = new ElementName("switch", "switch", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGSwitchElement, +TreeBuilder.OTHER); +public static final ElementName TEXTPATH = new ElementName("textpath", "textPath", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGTextPathElement, +TreeBuilder.OTHER); +public static final ElementName LI = new ElementName("li", "li", +// CPPONLY: NS_NewHTMLLIElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.LI | SPECIAL | OPTIONAL_END_TAG); +public static final ElementName MI = new ElementName("mi", "mi", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.MI_MO_MN_MS_MTEXT | SCOPING_AS_MATHML); +public static final ElementName LINK = new ElementName("link", "link", +// CPPONLY: NS_NewHTMLLinkElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.LINK_OR_BASEFONT_OR_BGSOUND | SPECIAL); +public static final ElementName MARK = new ElementName("mark", "mark", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OTHER); +public static final ElementName MALIGNMARK = new ElementName("malignmark", "malignmark", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.MGLYPH_OR_MALIGNMARK); +public static final ElementName MASK = new ElementName("mask", "mask", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGMaskElement, +TreeBuilder.OTHER); +public static final ElementName TRACK = new ElementName("track", "track", +// CPPONLY: NS_NewHTMLTrackElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.PARAM_OR_SOURCE_OR_TRACK | SPECIAL); +public static final ElementName DL = new ElementName("dl", "dl", +// CPPONLY: NS_NewHTMLSharedListElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.UL_OR_OL_OR_DL | SPECIAL); +public static final ElementName HTML = new ElementName("html", "html", +// CPPONLY: NS_NewHTMLSharedElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.HTML | SPECIAL | SCOPING | OPTIONAL_END_TAG); +public static final ElementName OL = new ElementName("ol", "ol", +// CPPONLY: NS_NewHTMLSharedListElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.UL_OR_OL_OR_DL | SPECIAL); +public static final ElementName LABEL = new ElementName("label", "label", +// CPPONLY: NS_NewHTMLLabelElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OTHER); +public static final ElementName UL = new ElementName("ul", "ul", +// CPPONLY: NS_NewHTMLSharedListElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.UL_OR_OL_OR_DL | SPECIAL); +public static final ElementName SMALL = new ElementName("small", "small", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U); +public static final ElementName SYMBOL = new ElementName("symbol", "symbol", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGSymbolElement, +TreeBuilder.OTHER); +public static final ElementName ALTGLYPHITEM = new ElementName("altglyphitem", "altGlyphItem", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OTHER); +public static final ElementName ANIMATETRANSFORM = new ElementName("animatetransform", "animateTransform", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGAnimateTransformElement, +TreeBuilder.OTHER); +public static final ElementName ACRONYM = new ElementName("acronym", "acronym", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OTHER); +public static final ElementName EM = new ElementName("em", "em", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U); +public static final ElementName FORM = new ElementName("form", "form", +// CPPONLY: NS_NewHTMLFormElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.FORM | SPECIAL); +public static final ElementName PARAM = new ElementName("param", "param", +// CPPONLY: NS_NewHTMLSharedElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.PARAM_OR_SOURCE_OR_TRACK | SPECIAL); +public static final ElementName ANIMATEMOTION = new ElementName("animatemotion", "animateMotion", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGAnimateMotionElement, +TreeBuilder.OTHER); +public static final ElementName BUTTON = new ElementName("button", "button", +// CPPONLY: NS_NewHTMLButtonElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.BUTTON | SPECIAL); +public static final ElementName CAPTION = new ElementName("caption", "caption", +// CPPONLY: NS_NewHTMLTableCaptionElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.CAPTION | SPECIAL | SCOPING); +public static final ElementName FIGCAPTION = new ElementName("figcaption", "figcaption", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY | SPECIAL); +public static final ElementName MN = new ElementName("mn", "mn", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.MI_MO_MN_MS_MTEXT | SCOPING_AS_MATHML); +public static final ElementName KEYGEN = new ElementName("keygen", "keygen", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.KEYGEN | SPECIAL); +public static final ElementName MAIN = new ElementName("main", "main", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY | SPECIAL); +public static final ElementName OPTION = new ElementName("option", "option", +// CPPONLY: NS_NewHTMLOptionElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OPTION | OPTIONAL_END_TAG); +public static final ElementName POLYGON = new ElementName("polygon", "polygon", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGPolygonElement, +TreeBuilder.OTHER); +public static final ElementName PATTERN = new ElementName("pattern", "pattern", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGPatternElement, +TreeBuilder.OTHER); +public static final ElementName SPAN = new ElementName("span", "span", +// CPPONLY: NS_NewHTMLSpanElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.RUBY_OR_SPAN_OR_SUB_OR_SUP_OR_VAR); +public static final ElementName SECTION = new ElementName("section", "section", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY | SPECIAL); +public static final ElementName TSPAN = new ElementName("tspan", "tspan", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGTSpanElement, +TreeBuilder.OTHER); +public static final ElementName AUDIO = new ElementName("audio", "audio", +// CPPONLY: NS_NewHTMLAudioElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OTHER); +public static final ElementName MO = new ElementName("mo", "mo", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.MI_MO_MN_MS_MTEXT | SCOPING_AS_MATHML); +public static final ElementName VIDEO = new ElementName("video", "video", +// CPPONLY: NS_NewHTMLVideoElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OTHER); +public static final ElementName COLGROUP = new ElementName("colgroup", "colgroup", +// CPPONLY: NS_NewHTMLTableColElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.COLGROUP | SPECIAL | OPTIONAL_END_TAG); +public static final ElementName FEDISPLACEMENTMAP = new ElementName("fedisplacementmap", "feDisplacementMap", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGFEDisplacementMapElement, +TreeBuilder.OTHER); +public static final ElementName HGROUP = new ElementName("hgroup", "hgroup", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY | SPECIAL); +public static final ElementName RP = new ElementName("rp", "rp", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.RT_OR_RP | OPTIONAL_END_TAG); +public static final ElementName OPTGROUP = new ElementName("optgroup", "optgroup", +// CPPONLY: NS_NewHTMLOptGroupElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OPTGROUP | OPTIONAL_END_TAG); +public static final ElementName SAMP = new ElementName("samp", "samp", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OTHER); +public static final ElementName STOP = new ElementName("stop", "stop", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGStopElement, +TreeBuilder.OTHER); +public static final ElementName BR = new ElementName("br", "br", +// CPPONLY: NS_NewHTMLBRElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.BR | SPECIAL); +public static final ElementName ABBR = new ElementName("abbr", "abbr", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OTHER); +public static final ElementName ANIMATECOLOR = new ElementName("animatecolor", "animateColor", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OTHER); +public static final ElementName CENTER = new ElementName("center", "center", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.DIV_OR_BLOCKQUOTE_OR_CENTER_OR_MENU | SPECIAL); +public static final ElementName HR = new ElementName("hr", "hr", +// CPPONLY: NS_NewHTMLHRElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.HR | SPECIAL); +public static final ElementName FEFUNCR = new ElementName("fefuncr", "feFuncR", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGFEFuncRElement, +TreeBuilder.OTHER); +public static final ElementName FECOMPONENTTRANSFER = new ElementName("fecomponenttransfer", "feComponentTransfer", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGFEComponentTransferElement, +TreeBuilder.OTHER); +public static final ElementName FILTER = new ElementName("filter", "filter", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGFilterElement, +TreeBuilder.OTHER); +public static final ElementName FOOTER = new ElementName("footer", "footer", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY | SPECIAL); +public static final ElementName FEGAUSSIANBLUR = new ElementName("fegaussianblur", "feGaussianBlur", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGFEGaussianBlurElement, +TreeBuilder.OTHER); +public static final ElementName HEADER = new ElementName("header", "header", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY | SPECIAL); +public static final ElementName MARKER = new ElementName("marker", "marker", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGMarkerElement, +TreeBuilder.OTHER); +public static final ElementName METER = new ElementName("meter", "meter", +// CPPONLY: NS_NewHTMLMeterElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OTHER); +public static final ElementName NOBR = new ElementName("nobr", "nobr", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.NOBR); +public static final ElementName TR = new ElementName("tr", "tr", +// CPPONLY: NS_NewHTMLTableRowElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.TR | SPECIAL | FOSTER_PARENTING | OPTIONAL_END_TAG); +public static final ElementName ADDRESS = new ElementName("address", "address", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY | SPECIAL); +public static final ElementName CANVAS = new ElementName("canvas", "canvas", +// CPPONLY: NS_NewHTMLCanvasElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OTHER); +public static final ElementName DEFS = new ElementName("defs", "defs", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGDefsElement, +TreeBuilder.OTHER); +public static final ElementName DETAILS = new ElementName("details", "details", +// CPPONLY: NS_NewHTMLDetailsElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY | SPECIAL); +public static final ElementName MS = new ElementName("ms", "ms", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.MI_MO_MN_MS_MTEXT | SCOPING_AS_MATHML); +public static final ElementName NOFRAMES = new ElementName("noframes", "noframes", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.NOFRAMES | SPECIAL); +public static final ElementName PROGRESS = new ElementName("progress", "progress", +// CPPONLY: NS_NewHTMLProgressElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OTHER); +public static final ElementName DT = new ElementName("dt", "dt", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.DD_OR_DT | SPECIAL | OPTIONAL_END_TAG); +public static final ElementName APPLET = new ElementName("applet", "applet", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.MARQUEE_OR_APPLET | SPECIAL | SCOPING); +public static final ElementName BASEFONT = new ElementName("basefont", "basefont", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.LINK_OR_BASEFONT_OR_BGSOUND | SPECIAL); +public static final ElementName DATALIST = new ElementName("datalist", "datalist", +// CPPONLY: NS_NewHTMLDataListElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OTHER); +public static final ElementName FOREIGNOBJECT = new ElementName("foreignobject", "foreignObject", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGForeignObjectElement, +TreeBuilder.FOREIGNOBJECT_OR_DESC | SCOPING_AS_SVG); +public static final ElementName FIELDSET = new ElementName("fieldset", "fieldset", +// CPPONLY: NS_NewHTMLFieldSetElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.FIELDSET | SPECIAL); +public static final ElementName FRAMESET = new ElementName("frameset", "frameset", +// CPPONLY: NS_NewHTMLFrameSetElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.FRAMESET | SPECIAL); +public static final ElementName FEOFFSET = new ElementName("feoffset", "feOffset", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGFEOffsetElement, +TreeBuilder.OTHER); +public static final ElementName FESPOTLIGHT = new ElementName("fespotlight", "feSpotLight", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGFESpotLightElement, +TreeBuilder.OTHER); +public static final ElementName FEPOINTLIGHT = new ElementName("fepointlight", "fePointLight", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGFEPointLightElement, +TreeBuilder.OTHER); +public static final ElementName FEDISTANTLIGHT = new ElementName("fedistantlight", "feDistantLight", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGFEDistantLightElement, +TreeBuilder.OTHER); +public static final ElementName FONT = new ElementName("font", "font", +// CPPONLY: NS_NewHTMLFontElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.FONT); +public static final ElementName INPUT = new ElementName("input", "input", +// CPPONLY: NS_NewHTMLInputElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.INPUT | SPECIAL); +public static final ElementName LINEARGRADIENT = new ElementName("lineargradient", "linearGradient", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGLinearGradientElement, +TreeBuilder.OTHER); +public static final ElementName MTEXT = new ElementName("mtext", "mtext", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.MI_MO_MN_MS_MTEXT | SCOPING_AS_MATHML); +public static final ElementName NOSCRIPT = new ElementName("noscript", "noscript", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.NOSCRIPT | SPECIAL); +public static final ElementName RT = new ElementName("rt", "rt", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.RT_OR_RP | OPTIONAL_END_TAG); +public static final ElementName OBJECT = new ElementName("object", "object", +// CPPONLY: NS_NewHTMLObjectElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OBJECT | SPECIAL | SCOPING); +public static final ElementName OUTPUT = new ElementName("output", "output", +// CPPONLY: NS_NewHTMLOutputElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OUTPUT); +public static final ElementName PLAINTEXT = new ElementName("plaintext", "plaintext", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.PLAINTEXT | SPECIAL); +public static final ElementName TT = new ElementName("tt", "tt", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U); +public static final ElementName RECT = new ElementName("rect", "rect", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGRectElement, +TreeBuilder.OTHER); +public static final ElementName RADIALGRADIENT = new ElementName("radialgradient", "radialGradient", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGRadialGradientElement, +TreeBuilder.OTHER); +public static final ElementName SELECT = new ElementName("select", "select", +// CPPONLY: NS_NewHTMLSelectElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.SELECT | SPECIAL); +public static final ElementName SLOT = new ElementName("slot", "slot", +// CPPONLY: NS_NewHTMLSlotElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.OTHER); +public static final ElementName SCRIPT = new ElementName("script", "script", +// CPPONLY: NS_NewHTMLScriptElement, +// CPPONLY: NS_NewSVGScriptElement, +TreeBuilder.SCRIPT | SPECIAL); +public static final ElementName TFOOT = new ElementName("tfoot", "tfoot", +// CPPONLY: NS_NewHTMLTableSectionElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.TBODY_OR_THEAD_OR_TFOOT | SPECIAL | FOSTER_PARENTING | OPTIONAL_END_TAG); +public static final ElementName TEXT = new ElementName("text", "text", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGTextElement, +TreeBuilder.OTHER); +public static final ElementName MENU = new ElementName("menu", "menu", +// CPPONLY: NS_NewHTMLMenuElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.DIV_OR_BLOCKQUOTE_OR_CENTER_OR_MENU | SPECIAL); +public static final ElementName FEDROPSHADOW = new ElementName("fedropshadow", "feDropShadow", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGFEDropShadowElement, +TreeBuilder.OTHER); +public static final ElementName VIEW = new ElementName("view", "view", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGViewElement, +TreeBuilder.OTHER); +public static final ElementName FECOLORMATRIX = new ElementName("fecolormatrix", "feColorMatrix", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGFEColorMatrixElement, +TreeBuilder.OTHER); +public static final ElementName FECONVOLVEMATRIX = new ElementName("feconvolvematrix", "feConvolveMatrix", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGFEConvolveMatrixElement, +TreeBuilder.OTHER); +public static final ElementName BODY = new ElementName("body", "body", +// CPPONLY: NS_NewHTMLBodyElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.BODY | SPECIAL | OPTIONAL_END_TAG); +public static final ElementName FEMORPHOLOGY = new ElementName("femorphology", "feMorphology", +// CPPONLY: NS_NewHTMLUnknownElement, +// CPPONLY: NS_NewSVGFEMorphologyElement, +TreeBuilder.OTHER); +public static final ElementName RUBY = new ElementName("ruby", "ruby", +// CPPONLY: NS_NewHTMLElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.RUBY_OR_SPAN_OR_SUB_OR_SUP_OR_VAR); +public static final ElementName SUMMARY = new ElementName("summary", "summary", +// CPPONLY: NS_NewHTMLSummaryElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY | SPECIAL); +public static final ElementName TBODY = new ElementName("tbody", "tbody", +// CPPONLY: NS_NewHTMLTableSectionElement, +// CPPONLY: NS_NewSVGUnknownElement, +TreeBuilder.TBODY_OR_THEAD_OR_TFOOT | SPECIAL | FOSTER_PARENTING | OPTIONAL_END_TAG); +private final static @NoLength ElementName[] ELEMENT_NAMES = { +MN, +CITE, +FRAMESET, +H1, +CLIPPATH, +METER, +RADIALGRADIENT, +B, +BGSOUND, +SOURCE, +HTML, +OPTGROUP, +NOFRAMES, +MTEXT, +VIEW, +DIV, +G, +FEFUNCA, +THEAD, +FIGURE, +GLYPHREF, +LI, +ACRONYM, +TSPAN, +FEFUNCR, +CANVAS, +BASEFONT, +FEDISTANTLIGHT, +OUTPUT, +TFOOT, +FEMORPHOLOGY, +COL, +MAP, +SUP, +P, +H5, +FEFUNCB, +HEAD, +BASE, +FEIMAGE, +LINE, +TITLE, +FESPECULARLIGHTING, +PATH, +MALIGNMARK, +SMALL, +ANIMATEMOTION, +POLYGON, +COLGROUP, +ABBR, +FEGAUSSIANBLUR, +TR, +DETAILS, +DT, +FOREIGNOBJECT, +FESPOTLIGHT, +INPUT, +RT, +TT, +SLOT, +MENU, +FECONVOLVEMATRIX, +SUMMARY, +BDI, +DFN, +INS, +PRE, +SUB, +USE, +XMP, +S, +H3, +AREA, +META, +DESC, +FEBLEND, +NOEMBED, +ARTICLE, +CODE, +FETURBULENCE, +FETILE, +IMAGE, +POLYLINE, +STYLE, +TEMPLATE, +FEFUNCG, +STRONG, +MATH, +SWITCH, +LINK, +TRACK, +LABEL, +ALTGLYPHITEM, +FORM, +CAPTION, +MAIN, +SPAN, +MO, +HGROUP, +STOP, +CENTER, +FILTER, +MARKER, +NOBR, +ADDRESS, +DEFS, +MS, +PROGRESS, +APPLET, +DATALIST, +FIELDSET, +FEOFFSET, +FEPOINTLIGHT, +FONT, +LINEARGRADIENT, +NOSCRIPT, +OBJECT, +PLAINTEXT, +RECT, +SELECT, +SCRIPT, +TEXT, +FEDROPSHADOW, +FECOLORMATRIX, +BODY, +RUBY, +TBODY, +BIG, +BDO, +DEL, +DIR, +IMG, +KBD, +NAV, +A, +RTC, +SVG, +SET, +VAR, +WBR, +I, +Q, +U, +H2, +H4, +H6, +DATA, +METADATA, +TEXTAREA, +RB, +DD, +EMBED, +FEFLOOD, +LEGEND, +TD, +ASIDE, +ANIMATE, +BLOCKQUOTE, +CIRCLE, +ELLIPSE, +FEMERGENODE, +FEMERGE, +FRAME, +FECOMPOSITE, +IFRAME, +MARQUEE, +PICTURE, +STRIKE, +TABLE, +TIME, +ALTGLYPHDEF, +DIALOG, +FEDIFFUSELIGHTING, +LISTING, +ALTGLYPH, +MGLYPH, +MPATH, +TH, +TEXTPATH, +MI, +MARK, +MASK, +DL, +OL, +UL, +SYMBOL, +ANIMATETRANSFORM, +EM, +PARAM, +BUTTON, +FIGCAPTION, +KEYGEN, +OPTION, +PATTERN, +SECTION, +AUDIO, +VIDEO, +FEDISPLACEMENTMAP, +RP, +SAMP, +BR, +ANIMATECOLOR, +HR, +FECOMPONENTTRANSFER, +FOOTER, +HEADER, +}; +private final static int[] ELEMENT_HASHES = { +1902641154, +1748359220, +2001349720, +876609538, +1798686984, +1971465813, +2007781534, +59768833, +1730965751, +1756474198, +1868312196, +1939219752, +1988763672, +2005324101, +2060065124, +52490899, +62390273, +1682547543, +1740181637, +1749905526, +1766992520, +1818230786, +1881613047, +1907959605, +1967760215, +1982935782, +1999397992, +2001392798, +2006329158, +2008851557, +2085266636, +51961587, +57206291, +60352339, +67108865, +943718402, +1699324759, +1733890180, +1747814436, +1749715159, +1752979652, +1757146773, +1783388498, +1805502724, +1854228698, +1874053333, +1898223949, +1906087319, +1932928296, +1965115924, +1968053806, +1973420034, +1983633431, +1998585858, +2001309869, +2001392795, +2003183333, +2005925890, +2006974466, +2008325940, +2021937364, +2068523856, +2092255447, +51435587, +52486755, +55110883, +58773795, +60345171, +61395251, +62973651, +68681729, +910163970, +1679960596, +1686491348, +1715310660, +1733054663, +1737099991, +1747176599, +1748100148, +1749656156, +1749801286, +1751288021, +1755076808, +1756625221, +1757268168, +1783210839, +1790207270, +1803929812, +1806806678, +1853642948, +1857653029, +1870268949, +1881288348, +1884120164, +1899272519, +1904412884, +1907435316, +1919418370, +1935549734, +1941221172, +1966223078, +1967795910, +1971461414, +1971938532, +1982173479, +1983533124, +1986527234, +1990037800, +1998724870, +2000525512, +2001349704, +2001349736, +2001392796, +2001495140, +2004635806, +2005719336, +2006028454, +2006896969, +2007601444, +2008125638, +2008340774, +2008994116, +2051837468, +2068523853, +2083120164, +2091479332, +2092557349, +51434643, +51438659, +52485715, +52488851, +55104723, +56151587, +57733651, +59244545, +59821379, +60347747, +60354131, +61925907, +62450211, +63438849, +67633153, +69730305, +893386754, +926941186, +960495618, +1681770564, +1686489160, +1689922072, +1703936002, +1730150402, +1732381397, +1733076167, +1736200310, +1738539010, +1747048757, +1747306711, +1747838298, +1748225318, +1749395095, +1749673195, +1749723735, +1749813541, +1749932347, +1751386406, +1753362711, +1755148615, +1756600614, +1757137429, +1757157700, +1763839627, +1782357526, +1783388497, +1786534215, +1797585096, +1803876550, +1803929861, +1805647874, +1807599880, +1818755074, +1854228692, +1854245076, +1864368130, +1870135298, +1873281026, +1874102998, +1881498736, +1881669634, +1889085973, +1898753862, +1900845386, +1903302038, +1905563974, +1906135367, +1907661127, +1914900309, +1925844629, +1934172497, +1938817026, +1941178676, +1963982850, +1965334268, +1967128578, +1967788867, +1967795958, +1968836118, +}; +} diff --git a/parser/html/javasrc/Portability.java b/parser/html/javasrc/Portability.java new file mode 100644 index 0000000000..1d65894a86 --- /dev/null +++ b/parser/html/javasrc/Portability.java @@ -0,0 +1,159 @@ +/* + * Copyright (c) 2008-2015 Mozilla Foundation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + */ + +package nu.validator.htmlparser.impl; + +import org.xml.sax.SAXException; + +import nu.validator.htmlparser.annotation.Literal; +import nu.validator.htmlparser.annotation.Local; +import nu.validator.htmlparser.annotation.NoLength; +import nu.validator.htmlparser.common.Interner; + +public final class Portability { + + public static int checkedAdd(int a, int b) throws SAXException { + // This can't be translated code, because in C++ signed integer overflow is UB, so the below code would be wrong. + assert a >= 0; + assert b >= 0; + int sum = a + b; + if (sum < a || sum < b) { + throw new SAXException("Integer overflow"); + } + return sum; + } + + // Allocating methods + + /** + * Allocates a new local name object. In C++, the refcount must be set up in such a way that + * calling <code>releaseLocal</code> on the return value balances the refcount set by this method. + */ + public static @Local String newLocalNameFromBuffer(@NoLength char[] buf, int length, Interner interner) { + return new String(buf, 0, length).intern(); + } + + public static String newStringFromBuffer(@NoLength char[] buf, int offset, int length + // CPPONLY: , TreeBuilder treeBuilder, boolean maybeAtomize + ) { + return new String(buf, offset, length); + } + + public static String newEmptyString() { + return ""; + } + + public static String newStringFromLiteral(@Literal String literal) { + return literal; + } + + public static String newStringFromString(String string) { + return string; + } + + // XXX get rid of this + public static char[] newCharArrayFromLocal(@Local String local) { + return local.toCharArray(); + } + + public static char[] newCharArrayFromString(String string) { + return string.toCharArray(); + } + + // Deallocation methods + + public static void releaseString(String str) { + // No-op in Java + } + + // Comparison methods + + public static boolean localEqualsBuffer(@Local String local, @NoLength char[] buf, int length) { + if (local.length() != length) { + return false; + } + for (int i = 0; i < length; i++) { + if (local.charAt(i) != buf[i]) { + return false; + } + } + return true; + } + + public static boolean lowerCaseLiteralIsPrefixOfIgnoreAsciiCaseString(@Literal String lowerCaseLiteral, + String string) { + if (string == null) { + return false; + } + if (lowerCaseLiteral.length() > string.length()) { + return false; + } + for (int i = 0; i < lowerCaseLiteral.length(); i++) { + char c0 = lowerCaseLiteral.charAt(i); + char c1 = string.charAt(i); + if (c1 >= 'A' && c1 <= 'Z') { + c1 += 0x20; + } + if (c0 != c1) { + return false; + } + } + return true; + } + + public static boolean lowerCaseLiteralEqualsIgnoreAsciiCaseString(@Literal String lowerCaseLiteral, + String string) { + if (string == null) { + return false; + } + if (lowerCaseLiteral.length() != string.length()) { + return false; + } + for (int i = 0; i < lowerCaseLiteral.length(); i++) { + char c0 = lowerCaseLiteral.charAt(i); + char c1 = string.charAt(i); + if (c1 >= 'A' && c1 <= 'Z') { + c1 += 0x20; + } + if (c0 != c1) { + return false; + } + } + return true; + } + + public static boolean literalEqualsString(@Literal String literal, String string) { + return literal.equals(string); + } + + public static boolean stringEqualsString(String one, String other) { + return one.equals(other); + } + + public static void delete(Object o) { + + } + + public static void deleteArray(Object o) { + + } +} diff --git a/parser/html/javasrc/README.txt b/parser/html/javasrc/README.txt new file mode 100644 index 0000000000..4555969cad --- /dev/null +++ b/parser/html/javasrc/README.txt @@ -0,0 +1,6 @@ +The .java files in this directory were placed here by the Java-to-C++ +translator that lives in parser/html/java/translator. Together they represent +a snapshot of the Java code that was translated to produce the corresponding +.h and .cpp files in the parent directory. Changing these .java files is not +worthwhile, as they will just be overwritten by the next translation. See +parser/html/java/README.txt for information about performing the translation. diff --git a/parser/html/javasrc/StackNode.java b/parser/html/javasrc/StackNode.java new file mode 100644 index 0000000000..cfd570724e --- /dev/null +++ b/parser/html/javasrc/StackNode.java @@ -0,0 +1,364 @@ +/* + * Copyright (c) 2007 Henri Sivonen + * Copyright (c) 2007-2011 Mozilla Foundation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + */ + +package nu.validator.htmlparser.impl; + +import nu.validator.htmlparser.annotation.Inline; +import nu.validator.htmlparser.annotation.Local; +import nu.validator.htmlparser.annotation.NsUri; + +final class StackNode<T> { + // Index where this stack node is stored in the tree builder's list of stack nodes. + // A value of -1 indicates that the stack node is not owned by a tree builder and + // must delete itself when its refcount reaches 0. + final int idxInTreeBuilder; + + int flags; + + @Local String name; + + @Local String popName; + + @NsUri String ns; + + T node; + + // Only used on the list of formatting elements + HtmlAttributes attributes; + + private int refcount = 0; + + /* + * Only valid for formatting elements + */ + // CPPONLY: private @HtmlCreator Object htmlCreator; + + // [NOCPP[ + + private TaintableLocatorImpl locator; + + public TaintableLocatorImpl getLocator() { + return locator; + } + + // ]NOCPP] + + @Inline public int getFlags() { + return flags; + } + + public int getGroup() { + return flags & ElementName.GROUP_MASK; + } + + public boolean isScoping() { + return (flags & ElementName.SCOPING) != 0; + } + + public boolean isSpecial() { + return (flags & ElementName.SPECIAL) != 0; + } + + public boolean isFosterParenting() { + return (flags & ElementName.FOSTER_PARENTING) != 0; + } + + public boolean isHtmlIntegrationPoint() { + return (flags & ElementName.HTML_INTEGRATION_POINT) != 0; + } + + // [NOCPP[ + + public boolean isOptionalEndTag() { + return (flags & ElementName.OPTIONAL_END_TAG) != 0; + } + + // ]NOCPP] + + StackNode(int idxInTreeBuilder) { + this.idxInTreeBuilder = idxInTreeBuilder; + this.flags = 0; + this.name = null; + this.popName = null; + // CPPONLY: this.ns = 0; + this.node = null; + this.attributes = null; + this.refcount = 0; + // CPPONLY: this.htmlCreator = null; + } + + // CPPONLY: public @HtmlCreator Object getHtmlCreator() { + // CPPONLY: return htmlCreator; + // CPPONLY: } + + /** + * Setter for copying. This doesn't take another <code>StackNode</code> + * because in C++ the caller is responsible for reobtaining the local names + * from another interner. + * + * @param flags + * @param ns + * @param name + * @param node + * @param popName + * @param attributes + */ + void setValues(int flags, @NsUri String ns, @Local String name, T node, + @Local String popName, HtmlAttributes attributes, + // CPPONLY: @HtmlCreator Object htmlCreator + // [NOCPP[ + TaintableLocatorImpl locator + // ]NOCPP] + ) { + assert isUnused(); + this.flags = flags; + this.name = name; + this.popName = popName; + this.ns = ns; + this.node = node; + this.attributes = attributes; + this.refcount = 1; + /* + * Need to track creator for formatting elements when copying. + */ + // CPPONLY: this.htmlCreator = htmlCreator; + // [NOCPP[ + this.locator = locator; + // ]NOCPP] + } + + /** + * Short hand for well-known HTML elements. + * + * @param elementName + * @param node + */ + void setValues(ElementName elementName, T node + // [NOCPP[ + , TaintableLocatorImpl locator + // ]NOCPP] + ) { + assert isUnused(); + this.flags = elementName.getFlags(); + this.name = elementName.getName(); + this.popName = elementName.getName(); + this.ns = "http://www.w3.org/1999/xhtml"; + this.node = node; + this.attributes = null; + this.refcount = 1; + assert elementName.isInterned() : "Don't use this constructor for custom elements."; + /* + * Not used for formatting elements, so no need to track creator. + */ + // CPPONLY: this.htmlCreator = null; + // [NOCPP[ + this.locator = locator; + // ]NOCPP] + } + + /** + * Setter for HTML formatting elements. + * + * @param elementName + * @param node + * @param attributes + */ + void setValues(ElementName elementName, T node, HtmlAttributes attributes + // [NOCPP[ + , TaintableLocatorImpl locator + // ]NOCPP] + ) { + assert isUnused(); + this.flags = elementName.getFlags(); + this.name = elementName.getName(); + this.popName = elementName.getName(); + this.ns = "http://www.w3.org/1999/xhtml"; + this.node = node; + this.attributes = attributes; + this.refcount = 1; + assert elementName.isInterned() : "Don't use this constructor for custom elements."; + /* + * Need to track creator for formatting elements in order to be able + * to clone them. + */ + // CPPONLY: this.htmlCreator = elementName.getHtmlCreator(); + // [NOCPP[ + this.locator = locator; + // ]NOCPP] + } + + /** + * The common-case HTML setter. + * + * @param elementName + * @param node + * @param popName + */ + void setValues(ElementName elementName, T node, @Local String popName + // [NOCPP[ + , TaintableLocatorImpl locator + // ]NOCPP] + ) { + assert isUnused(); + this.flags = elementName.getFlags(); + this.name = elementName.getName(); + this.popName = popName; + this.ns = "http://www.w3.org/1999/xhtml"; + this.node = node; + this.attributes = null; + this.refcount = 1; + /* + * Not used for formatting elements, so no need to track creator. + */ + // CPPONLY: this.htmlCreator = null; + // [NOCPP[ + this.locator = locator; + // ]NOCPP] + } + + /** + * Setter for SVG elements. Note that the order of the arguments is + * what distinguishes this from the HTML setter. This is ugly, but + * AFAICT the least disruptive way to make this work with Java's generics + * and without unnecessary branches. :-( + * + * @param elementName + * @param popName + * @param node + */ + void setValues(ElementName elementName, @Local String popName, T node + // [NOCPP[ + , TaintableLocatorImpl locator + // ]NOCPP] + ) { + assert isUnused(); + this.flags = prepareSvgFlags(elementName.getFlags()); + this.name = elementName.getName(); + this.popName = popName; + this.ns = "http://www.w3.org/2000/svg"; + this.node = node; + this.attributes = null; + this.refcount = 1; + /* + * Not used for formatting elements, so no need to track creator. + */ + // CPPONLY: this.htmlCreator = null; + // [NOCPP[ + this.locator = locator; + // ]NOCPP] + } + + /** + * Setter for MathML. + * + * @param elementName + * @param node + * @param popName + * @param markAsIntegrationPoint + */ + void setValues(ElementName elementName, T node, @Local String popName, + boolean markAsIntegrationPoint + // [NOCPP[ + , TaintableLocatorImpl locator + // ]NOCPP] + ) { + assert isUnused(); + this.flags = prepareMathFlags(elementName.getFlags(), + markAsIntegrationPoint); + this.name = elementName.getName(); + this.popName = popName; + this.ns = "http://www.w3.org/1998/Math/MathML"; + this.node = node; + this.attributes = null; + this.refcount = 1; + /* + * Not used for formatting elements, so no need to track creator. + */ + // CPPONLY: this.htmlCreator = null; + // [NOCPP[ + this.locator = locator; + // ]NOCPP] + } + + private static int prepareSvgFlags(int flags) { + flags &= ~(ElementName.FOSTER_PARENTING | ElementName.SCOPING + | ElementName.SPECIAL | ElementName.OPTIONAL_END_TAG); + if ((flags & ElementName.SCOPING_AS_SVG) != 0) { + flags |= (ElementName.SCOPING | ElementName.SPECIAL | ElementName.HTML_INTEGRATION_POINT); + } + return flags; + } + + private static int prepareMathFlags(int flags, + boolean markAsIntegrationPoint) { + flags &= ~(ElementName.FOSTER_PARENTING | ElementName.SCOPING + | ElementName.SPECIAL | ElementName.OPTIONAL_END_TAG); + if ((flags & ElementName.SCOPING_AS_MATHML) != 0) { + flags |= (ElementName.SCOPING | ElementName.SPECIAL); + } + if (markAsIntegrationPoint) { + flags |= ElementName.HTML_INTEGRATION_POINT; + } + return flags; + } + + @SuppressWarnings("unused") private void destructor() { + // The translator adds refcount debug code here. + } + + public void dropAttributes() { + attributes = null; + } + + // [NOCPP[ + /** + * @see java.lang.Object#toString() + */ + @Override public @Local String toString() { + return name; + } + + // ]NOCPP] + + public void retain() { + refcount++; + } + + public void release(TreeBuilder<T> owningTreeBuilder) { + refcount--; + assert refcount >= 0; + if (refcount == 0) { + Portability.delete(attributes); + if (idxInTreeBuilder >= 0) { + owningTreeBuilder.notifyUnusedStackNode(idxInTreeBuilder); + } else { + assert owningTreeBuilder == null; + Portability.delete(this); + } + } + } + + boolean isUnused() { + return refcount == 0; + } +} diff --git a/parser/html/javasrc/StateSnapshot.java b/parser/html/javasrc/StateSnapshot.java new file mode 100644 index 0000000000..cba711f714 --- /dev/null +++ b/parser/html/javasrc/StateSnapshot.java @@ -0,0 +1,205 @@ +/* + * Copyright (c) 2009-2010 Mozilla Foundation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + */ + +package nu.validator.htmlparser.impl; + +import nu.validator.htmlparser.annotation.Auto; + + +public class StateSnapshot<T> implements TreeBuilderState<T> { + + private final @Auto StackNode<T>[] stack; + + private final @Auto StackNode<T>[] listOfActiveFormattingElements; + + private final @Auto int[] templateModeStack; + + private final T formPointer; + + private final T headPointer; + + private final int mode; + + private final int originalMode; + + private final boolean framesetOk; + + private final boolean needToDropLF; + + private final boolean quirks; + + /** + * @param stack + * @param listOfActiveFormattingElements + * @param templateModeStack + * @param formPointer + * @param headPointer + * @param deepTreeSurrogateParent + * @param mode + * @param originalMode + * @param framesetOk + * @param needToDropLF + * @param quirks + */ + StateSnapshot(StackNode<T>[] stack, + StackNode<T>[] listOfActiveFormattingElements, int[] templateModeStack, T formPointer, + T headPointer, int mode, int originalMode, + boolean framesetOk, boolean needToDropLF, boolean quirks) { + this.stack = stack; + this.listOfActiveFormattingElements = listOfActiveFormattingElements; + this.templateModeStack = templateModeStack; + this.formPointer = formPointer; + this.headPointer = headPointer; + this.mode = mode; + this.originalMode = originalMode; + this.framesetOk = framesetOk; + this.needToDropLF = needToDropLF; + this.quirks = quirks; + } + + /** + * @see nu.validator.htmlparser.impl.TreeBuilderState#getStack() + */ + @Override + public StackNode<T>[] getStack() { + return stack; + } + + /** + * @see nu.validator.htmlparser.impl.TreeBuilderState#getTemplateModeStack() + */ + @Override + public int[] getTemplateModeStack() { + return templateModeStack; + } + + /** + * @see nu.validator.htmlparser.impl.TreeBuilderState#getListOfActiveFormattingElements() + */ + @Override + public StackNode<T>[] getListOfActiveFormattingElements() { + return listOfActiveFormattingElements; + } + + /** + * @see nu.validator.htmlparser.impl.TreeBuilderState#getFormPointer() + */ + @Override + public T getFormPointer() { + return formPointer; + } + + /** + * Returns the headPointer. + * + * @return the headPointer + */ + @Override + public T getHeadPointer() { + return headPointer; + } + + /** + * Returns the mode. + * + * @return the mode + */ + @Override + public int getMode() { + return mode; + } + + /** + * Returns the originalMode. + * + * @return the originalMode + */ + @Override + public int getOriginalMode() { + return originalMode; + } + + /** + * Returns the framesetOk. + * + * @return the framesetOk + */ + @Override + public boolean isFramesetOk() { + return framesetOk; + } + + /** + * Returns the needToDropLF. + * + * @return the needToDropLF + */ + @Override + public boolean isNeedToDropLF() { + return needToDropLF; + } + + /** + * Returns the quirks. + * + * @return the quirks + */ + @Override + public boolean isQuirks() { + return quirks; + } + + /** + * @see nu.validator.htmlparser.impl.TreeBuilderState#getListOfActiveFormattingElementsLength() + */ + @Override + public int getListOfActiveFormattingElementsLength() { + return listOfActiveFormattingElements.length; + } + + /** + * @see nu.validator.htmlparser.impl.TreeBuilderState#getStackLength() + */ + @Override + public int getStackLength() { + return stack.length; + } + + /** + * @see nu.validator.htmlparser.impl.TreeBuilderState#getTemplateModeStackLength() + */ + @Override + public int getTemplateModeStackLength() { + return templateModeStack.length; + } + + @SuppressWarnings("unused") private void destructor() { + for (int i = 0; i < stack.length; i++) { + stack[i].release(null); + } + for (int i = 0; i < listOfActiveFormattingElements.length; i++) { + if (listOfActiveFormattingElements[i] != null) { + listOfActiveFormattingElements[i].release(null); + } + } + } +} diff --git a/parser/html/javasrc/Tokenizer.java b/parser/html/javasrc/Tokenizer.java new file mode 100644 index 0000000000..a8047c7a71 --- /dev/null +++ b/parser/html/javasrc/Tokenizer.java @@ -0,0 +1,7636 @@ +/* + * Copyright (c) 2005-2007 Henri Sivonen + * Copyright (c) 2007-2017 Mozilla Foundation + * Portions of comments Copyright 2004-2010 Apple Computer, Inc., Mozilla + * Foundation, and Opera Software ASA. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + */ + +/* + * The comments following this one that use the same comment syntax as this + * comment are quotes from the WHATWG HTML 5 spec as of 2 June 2007 + * amended as of June 18 2008 and May 31 2010. + * That document came with this statement: + * "© Copyright 2004-2010 Apple Computer, Inc., Mozilla Foundation, and + * Opera Software ASA. You are granted a license to use, reproduce and + * create derivative works of this document." + */ + +package nu.validator.htmlparser.impl; + +import org.xml.sax.ErrorHandler; +import org.xml.sax.Locator; +import org.xml.sax.ext.Locator2; +import org.xml.sax.SAXException; +import org.xml.sax.SAXParseException; + +import nu.validator.htmlparser.annotation.Auto; +import nu.validator.htmlparser.annotation.CharacterName; +import nu.validator.htmlparser.annotation.Const; +import nu.validator.htmlparser.annotation.Inline; +import nu.validator.htmlparser.annotation.Local; +import nu.validator.htmlparser.annotation.NoLength; +import nu.validator.htmlparser.common.EncodingDeclarationHandler; +import nu.validator.htmlparser.common.Interner; +import nu.validator.htmlparser.common.TokenHandler; +import nu.validator.htmlparser.common.XmlViolationPolicy; + +/** + * An implementation of + * https://html.spec.whatwg.org/multipage/syntax.html#tokenization + * + * This class implements the <code>Locator</code> interface. This is not an + * incidental implementation detail: Users of this class are encouraged to make + * use of the <code>Locator</code> nature. + * + * By default, the tokenizer may report data that XML 1.0 bans. The tokenizer + * can be configured to treat these conditions as fatal or to coerce the infoset + * to something that XML 1.0 allows. + * + * @version $Id$ + * @author hsivonen + */ +public class Tokenizer implements Locator, Locator2 { + + private static final int DATA_AND_RCDATA_MASK = ~1; + + public static final int DATA = 0; + + public static final int RCDATA = 1; + + public static final int SCRIPT_DATA = 2; + + public static final int RAWTEXT = 3; + + public static final int SCRIPT_DATA_ESCAPED = 4; + + public static final int ATTRIBUTE_VALUE_DOUBLE_QUOTED = 5; + + public static final int ATTRIBUTE_VALUE_SINGLE_QUOTED = 6; + + public static final int ATTRIBUTE_VALUE_UNQUOTED = 7; + + public static final int PLAINTEXT = 8; + + public static final int TAG_OPEN = 9; + + public static final int CLOSE_TAG_OPEN = 10; + + public static final int TAG_NAME = 11; + + public static final int BEFORE_ATTRIBUTE_NAME = 12; + + public static final int ATTRIBUTE_NAME = 13; + + public static final int AFTER_ATTRIBUTE_NAME = 14; + + public static final int BEFORE_ATTRIBUTE_VALUE = 15; + + public static final int AFTER_ATTRIBUTE_VALUE_QUOTED = 16; + + public static final int BOGUS_COMMENT = 17; + + public static final int MARKUP_DECLARATION_OPEN = 18; + + public static final int DOCTYPE = 19; + + public static final int BEFORE_DOCTYPE_NAME = 20; + + public static final int DOCTYPE_NAME = 21; + + public static final int AFTER_DOCTYPE_NAME = 22; + + public static final int BEFORE_DOCTYPE_PUBLIC_IDENTIFIER = 23; + + public static final int DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED = 24; + + public static final int DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED = 25; + + public static final int AFTER_DOCTYPE_PUBLIC_IDENTIFIER = 26; + + public static final int BEFORE_DOCTYPE_SYSTEM_IDENTIFIER = 27; + + public static final int DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED = 28; + + public static final int DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED = 29; + + public static final int AFTER_DOCTYPE_SYSTEM_IDENTIFIER = 30; + + public static final int BOGUS_DOCTYPE = 31; + + public static final int COMMENT_START = 32; + + public static final int COMMENT_START_DASH = 33; + + public static final int COMMENT = 34; + + public static final int COMMENT_END_DASH = 35; + + public static final int COMMENT_END = 36; + + public static final int COMMENT_END_BANG = 37; + + public static final int NON_DATA_END_TAG_NAME = 38; + + public static final int MARKUP_DECLARATION_HYPHEN = 39; + + public static final int MARKUP_DECLARATION_OCTYPE = 40; + + public static final int DOCTYPE_UBLIC = 41; + + public static final int DOCTYPE_YSTEM = 42; + + public static final int AFTER_DOCTYPE_PUBLIC_KEYWORD = 43; + + public static final int BETWEEN_DOCTYPE_PUBLIC_AND_SYSTEM_IDENTIFIERS = 44; + + public static final int AFTER_DOCTYPE_SYSTEM_KEYWORD = 45; + + public static final int CONSUME_CHARACTER_REFERENCE = 46; + + public static final int CONSUME_NCR = 47; + + public static final int CHARACTER_REFERENCE_TAIL = 48; + + public static final int HEX_NCR_LOOP = 49; + + public static final int DECIMAL_NRC_LOOP = 50; + + public static final int HANDLE_NCR_VALUE = 51; + + public static final int HANDLE_NCR_VALUE_RECONSUME = 52; + + public static final int CHARACTER_REFERENCE_HILO_LOOKUP = 53; + + public static final int SELF_CLOSING_START_TAG = 54; + + public static final int CDATA_START = 55; + + public static final int CDATA_SECTION = 56; + + public static final int CDATA_RSQB = 57; + + public static final int CDATA_RSQB_RSQB = 58; + + public static final int SCRIPT_DATA_LESS_THAN_SIGN = 59; + + public static final int SCRIPT_DATA_ESCAPE_START = 60; + + public static final int SCRIPT_DATA_ESCAPE_START_DASH = 61; + + public static final int SCRIPT_DATA_ESCAPED_DASH = 62; + + public static final int SCRIPT_DATA_ESCAPED_DASH_DASH = 63; + + public static final int BOGUS_COMMENT_HYPHEN = 64; + + public static final int RAWTEXT_RCDATA_LESS_THAN_SIGN = 65; + + public static final int SCRIPT_DATA_ESCAPED_LESS_THAN_SIGN = 66; + + public static final int SCRIPT_DATA_DOUBLE_ESCAPE_START = 67; + + public static final int SCRIPT_DATA_DOUBLE_ESCAPED = 68; + + public static final int SCRIPT_DATA_DOUBLE_ESCAPED_LESS_THAN_SIGN = 69; + + public static final int SCRIPT_DATA_DOUBLE_ESCAPED_DASH = 70; + + public static final int SCRIPT_DATA_DOUBLE_ESCAPED_DASH_DASH = 71; + + public static final int SCRIPT_DATA_DOUBLE_ESCAPE_END = 72; + + public static final int PROCESSING_INSTRUCTION = 73; + + public static final int PROCESSING_INSTRUCTION_QUESTION_MARK = 74; + + public static final int COMMENT_LESSTHAN = 76; + + public static final int COMMENT_LESSTHAN_BANG = 77; + + public static final int COMMENT_LESSTHAN_BANG_DASH = 78; + + public static final int COMMENT_LESSTHAN_BANG_DASH_DASH = 79; + + /** + * Magic value for UTF-16 operations. + */ + private static final int LEAD_OFFSET = (0xD800 - (0x10000 >> 10)); + + /** + * UTF-16 code unit array containing less than and greater than for emitting + * those characters on certain parse errors. + */ + private static final @NoLength char[] LT_GT = { '<', '>' }; + + /** + * UTF-16 code unit array containing less than and solidus for emitting + * those characters on certain parse errors. + */ + private static final @NoLength char[] LT_SOLIDUS = { '<', '/' }; + + /** + * UTF-16 code unit array containing ]] for emitting those characters on + * state transitions. + */ + private static final @NoLength char[] RSQB_RSQB = { ']', ']' }; + + /** + * Array version of U+FFFD. + */ + private static final @NoLength char[] REPLACEMENT_CHARACTER = { '\uFFFD' }; + + // [NOCPP[ + + /** + * Array version of space. + */ + private static final @NoLength char[] SPACE = { ' ' }; + + // ]NOCPP] + + /** + * Array version of line feed. + */ + private static final @NoLength char[] LF = { '\n' }; + + /** + * "CDATA[" as <code>char[]</code> + */ + private static final @NoLength char[] CDATA_LSQB = { 'C', 'D', 'A', 'T', + 'A', '[' }; + + /** + * "octype" as <code>char[]</code> + */ + private static final @NoLength char[] OCTYPE = { 'o', 'c', 't', 'y', 'p', + 'e' }; + + /** + * "ublic" as <code>char[]</code> + */ + private static final @NoLength char[] UBLIC = { 'u', 'b', 'l', 'i', 'c' }; + + /** + * "ystem" as <code>char[]</code> + */ + private static final @NoLength char[] YSTEM = { 'y', 's', 't', 'e', 'm' }; + + private static final char[] TITLE_ARR = { 't', 'i', 't', 'l', 'e' }; + + private static final char[] SCRIPT_ARR = { 's', 'c', 'r', 'i', 'p', 't' }; + + private static final char[] STYLE_ARR = { 's', 't', 'y', 'l', 'e' }; + + private static final char[] PLAINTEXT_ARR = { 'p', 'l', 'a', 'i', 'n', 't', + 'e', 'x', 't' }; + + private static final char[] XMP_ARR = { 'x', 'm', 'p' }; + + private static final char[] TEXTAREA_ARR = { 't', 'e', 'x', 't', 'a', 'r', + 'e', 'a' }; + + private static final char[] IFRAME_ARR = { 'i', 'f', 'r', 'a', 'm', 'e' }; + + private static final char[] NOEMBED_ARR = { 'n', 'o', 'e', 'm', 'b', 'e', + 'd' }; + + private static final char[] NOSCRIPT_ARR = { 'n', 'o', 's', 'c', 'r', 'i', + 'p', 't' }; + + private static final char[] NOFRAMES_ARR = { 'n', 'o', 'f', 'r', 'a', 'm', + 'e', 's' }; + + /** + * The token handler. + */ + protected final TokenHandler tokenHandler; + + protected EncodingDeclarationHandler encodingDeclarationHandler; + + // [NOCPP[ + + /** + * The error handler. + */ + protected ErrorHandler errorHandler; + + // ]NOCPP] + + /** + * Whether the previous char read was CR. + */ + protected boolean lastCR; + + protected int stateSave; + + private int returnStateSave; + + protected int index; + + private boolean forceQuirks; + + private char additional; + + private int entCol; + + private int firstCharKey; + + private int lo; + + private int hi; + + private int candidate; + + private int charRefBufMark; + + protected int value; + + private boolean seenDigits; + + private boolean suspendAfterCurrentNonTextToken; + + protected int cstart; + + /** + * The SAX public id for the resource being tokenized. (Only passed to back + * as part of locator data.) + */ + private String publicId; + + /** + * The SAX system id for the resource being tokenized. (Only passed to back + * as part of locator data.) + */ + private String systemId; + + /** + * Buffer for bufferable things other than those that fit the description + * of <code>charRefBuf</code>. + */ + private @Auto char[] strBuf; + + /** + * Number of significant <code>char</code>s in <code>strBuf</code>. + */ + private int strBufLen; + + /** + * Buffer for characters that might form a character reference but may + * end up not forming one. + */ + private final @Auto char[] charRefBuf; + + /** + * Number of significant <code>char</code>s in <code>charRefBuf</code>. + */ + private int charRefBufLen; + + /** + * Buffer for expanding NCRs falling into the Basic Multilingual Plane. + */ + private final @Auto char[] bmpChar; + + /** + * Buffer for expanding astral NCRs. + */ + private final @Auto char[] astralChar; + + /** + * The element whose end tag closes the current CDATA or RCDATA element. + */ + protected ElementName endTagExpectation = null; + + private char[] endTagExpectationAsArray; // not @Auto! + + /** + * <code>true</code> if tokenizing an end tag + */ + protected boolean endTag; + + /** + * <code>true</code> iff the current element/attribute name contains + * a hyphen. + */ + private boolean containsHyphen; + + /** + * The current tag token name. One of + * 1) null, + * 2) non-owning reference to nonInternedTagName + * 3) non-owning reference to a pre-interned ElementName + */ + private ElementName tagName = null; + + /** + * The recycled ElementName instance for the non-pre-interned cases. + */ + private ElementName nonInternedTagName = null; + + /** + * The current attribute name. + */ + protected AttributeName attributeName = null; + + // CPPONLY: private AttributeName nonInternedAttributeName = null; + + // [NOCPP[ + + /** + * Whether comment tokens are emitted. + */ + private boolean wantsComments = false; + + /** + * Whether the stream is past the first 1024 bytes. + */ + private boolean metaBoundaryPassed; + + // ]NOCPP] + + /** + * The name of the current doctype token. + */ + private @Local String doctypeName; + + /** + * The public id of the current doctype token. + */ + private String publicIdentifier; + + /** + * The system id of the current doctype token. + */ + private String systemIdentifier; + + /** + * The attribute holder. + */ + private HtmlAttributes attributes; + + // [NOCPP[ + + /** + * The policy for vertical tab and form feed. + */ + private XmlViolationPolicy contentSpacePolicy = XmlViolationPolicy.ALTER_INFOSET; + + /** + * The policy for comments. + */ + private XmlViolationPolicy commentPolicy = XmlViolationPolicy.ALTER_INFOSET; + + private XmlViolationPolicy xmlnsPolicy = XmlViolationPolicy.ALTER_INFOSET; + + private XmlViolationPolicy namePolicy = XmlViolationPolicy.ALTER_INFOSET; + + private int mappingLangToXmlLang; + + // ]NOCPP] + + private final boolean newAttributesEachTime; + + private boolean shouldSuspend; + + protected boolean confident; + + private int line; + + /* + * The line number of the current attribute. First set to the line of the + * attribute name and if there is a value, set to the line the value + * started on. + */ + // CPPONLY: private int attributeLine; + + private Interner interner; + + // CPPONLY: private boolean viewingXmlSource; + + // [NOCPP[ + + protected LocatorImpl ampersandLocation; + + public Tokenizer(TokenHandler tokenHandler, boolean newAttributesEachTime) { + this.tokenHandler = tokenHandler; + this.encodingDeclarationHandler = null; + this.lastCR = false; + this.stateSave = 0; + this.returnStateSave = 0; + this.index = 0; + this.forceQuirks = false; + this.additional = '\u0000'; + this.entCol = 0; + this.firstCharKey = 0; + this.lo = 0; + this.hi = 0; + this.candidate = 0; + this.charRefBufMark = 0; + this.value = 0; + this.seenDigits = false; + this.suspendAfterCurrentNonTextToken = false; + this.cstart = 0; + this.strBufLen = 0; + this.newAttributesEachTime = newAttributesEachTime; + // ∳ is the longest valid char ref and + // the semicolon never gets appended to the buffer. + this.charRefBuf = new char[32]; + this.charRefBufLen = 0; + this.bmpChar = new char[1]; + this.astralChar = new char[2]; + this.endTagExpectation = null; + this.endTagExpectationAsArray = null; + this.endTag = false; + this.containsHyphen = false; + this.tagName = null; + this.nonInternedTagName = new ElementName(); + this.attributeName = null; + // CPPONLY: this.nonInternedAttributeName = new AttributeName(); + this.doctypeName = null; + this.publicIdentifier = null; + this.systemIdentifier = null; + this.attributes = null; + this.shouldSuspend = false; + this.confident = false; + this.line = 0; + // CPPONLY: this.attributeLine = 0; + this.interner = null; + } + + // ]NOCPP] + + /** + * The constructor. + * + * @param tokenHandler + * the handler for receiving tokens + */ + public Tokenizer(TokenHandler tokenHandler + // CPPONLY: , boolean viewingXmlSource + ) { + this.tokenHandler = tokenHandler; + this.encodingDeclarationHandler = null; + // [NOCPP[ + this.newAttributesEachTime = false; + // ]NOCPP] + this.lastCR = false; + this.stateSave = 0; + this.returnStateSave = 0; + this.index = 0; + this.forceQuirks = false; + this.additional = '\u0000'; + this.entCol = 0; + this.firstCharKey = 0; + this.lo = 0; + this.hi = 0; + this.candidate = 0; + this.charRefBufMark = 0; + this.value = 0; + this.seenDigits = false; + this.suspendAfterCurrentNonTextToken = false; + this.cstart = 0; + this.strBufLen = 0; + // ∳ is the longest valid char ref and + // the semicolon never gets appended to the buffer. + this.charRefBuf = new char[32]; + this.charRefBufLen = 0; + this.bmpChar = new char[1]; + this.astralChar = new char[2]; + this.endTagExpectation = null; + this.endTagExpectationAsArray = null; + this.endTag = false; + this.containsHyphen = false; + this.tagName = null; + this.nonInternedTagName = new ElementName(); + this.attributeName = null; + // CPPONLY: this.nonInternedAttributeName = new AttributeName(); + this.doctypeName = null; + this.publicIdentifier = null; + this.systemIdentifier = null; + // [NOCPP[ + this.attributes = null; + // ]NOCPP] + // CPPONLY: this.attributes = tokenHandler.HasBuilder() ? new HtmlAttributes(mappingLangToXmlLang) : null; + // CPPONLY: this.newAttributesEachTime = !tokenHandler.HasBuilder(); + this.shouldSuspend = false; + this.confident = false; + this.line = 0; + // CPPONLY: this.attributeLine = 0; + this.interner = null; + // CPPONLY: this.viewingXmlSource = viewingXmlSource; + } + + public void setInterner(Interner interner) { + this.interner = interner; + } + + public void initLocation(String newPublicId, String newSystemId) { + this.systemId = newSystemId; + this.publicId = newPublicId; + + } + + // CPPONLY: boolean isViewingXmlSource() { + // CPPONLY: return viewingXmlSource; + // CPPONLY: } + + // [NOCPP[ + + /** + * Returns the mappingLangToXmlLang. + * + * @return the mappingLangToXmlLang + */ + public boolean isMappingLangToXmlLang() { + return mappingLangToXmlLang == AttributeName.HTML_LANG; + } + + /** + * Sets the mappingLangToXmlLang. + * + * @param mappingLangToXmlLang + * the mappingLangToXmlLang to set + */ + public void setMappingLangToXmlLang(boolean mappingLangToXmlLang) { + this.mappingLangToXmlLang = mappingLangToXmlLang ? AttributeName.HTML_LANG + : AttributeName.HTML; + } + + /** + * Sets the error handler. + * + * @see org.xml.sax.XMLReader#setErrorHandler(org.xml.sax.ErrorHandler) + */ + public void setErrorHandler(ErrorHandler eh) { + this.errorHandler = eh; + } + + public ErrorHandler getErrorHandler() { + return this.errorHandler; + } + + /** + * Sets the commentPolicy. + * + * @param commentPolicy + * the commentPolicy to set + */ + public void setCommentPolicy(XmlViolationPolicy commentPolicy) { + this.commentPolicy = commentPolicy; + } + + /** + * Sets the contentNonXmlCharPolicy. + * + * @param contentNonXmlCharPolicy + * the contentNonXmlCharPolicy to set + */ + public void setContentNonXmlCharPolicy( + XmlViolationPolicy contentNonXmlCharPolicy) { + if (contentNonXmlCharPolicy != XmlViolationPolicy.ALLOW) { + throw new IllegalArgumentException( + "Must use ErrorReportingTokenizer to set contentNonXmlCharPolicy to non-ALLOW."); + } + } + + /** + * Sets the contentSpacePolicy. + * + * @param contentSpacePolicy + * the contentSpacePolicy to set + */ + public void setContentSpacePolicy(XmlViolationPolicy contentSpacePolicy) { + this.contentSpacePolicy = contentSpacePolicy; + } + + /** + * Sets the xmlnsPolicy. + * + * @param xmlnsPolicy + * the xmlnsPolicy to set + */ + public void setXmlnsPolicy(XmlViolationPolicy xmlnsPolicy) { + if (xmlnsPolicy == XmlViolationPolicy.FATAL) { + throw new IllegalArgumentException("Can't use FATAL here."); + } + this.xmlnsPolicy = xmlnsPolicy; + } + + public void setNamePolicy(XmlViolationPolicy namePolicy) { + this.namePolicy = namePolicy; + } + + // ]NOCPP] + + // For the token handler to call + + /** + * Sets the tokenizer state and the associated element name. This should + * only ever used to put the tokenizer into one of the states that have + * a special end tag expectation. + * + * @param specialTokenizerState + * the tokenizer state to set + */ + public void setState(int specialTokenizerState) { + this.stateSave = specialTokenizerState; + this.endTagExpectation = null; + this.endTagExpectationAsArray = null; + } + + // [NOCPP[ + + /** + * Sets the tokenizer state and the associated element name. This should + * only ever used to put the tokenizer into one of the states that have + * a special end tag expectation. For use from the tokenizer test harness. + * + * @param specialTokenizerState + * the tokenizer state to set + * @param endTagExpectation + * the expected end tag for transitioning back to normal + */ + public void setStateAndEndTagExpectation(int specialTokenizerState, + @Local String endTagExpectation) { + this.stateSave = specialTokenizerState; + if (specialTokenizerState == Tokenizer.DATA) { + return; + } + @Auto char[] asArray = Portability.newCharArrayFromLocal(endTagExpectation); + this.endTagExpectation = ElementName.elementNameByBuffer(asArray, + asArray.length, interner); + assert this.endTagExpectation != null; + endTagExpectationToArray(); + } + + // ]NOCPP] + + /** + * Sets the tokenizer state and the associated element name. This should + * only ever used to put the tokenizer into one of the states that have + * a special end tag expectation. + * + * @param specialTokenizerState + * the tokenizer state to set + * @param endTagExpectation + * the expected end tag for transitioning back to normal + */ + public void setStateAndEndTagExpectation(int specialTokenizerState, + ElementName endTagExpectation) { + this.stateSave = specialTokenizerState; + this.endTagExpectation = endTagExpectation; + endTagExpectationToArray(); + } + + private void endTagExpectationToArray() { + switch (endTagExpectation.getGroup()) { + case TreeBuilder.TITLE: + endTagExpectationAsArray = TITLE_ARR; + return; + case TreeBuilder.SCRIPT: + endTagExpectationAsArray = SCRIPT_ARR; + return; + case TreeBuilder.STYLE: + endTagExpectationAsArray = STYLE_ARR; + return; + case TreeBuilder.PLAINTEXT: + endTagExpectationAsArray = PLAINTEXT_ARR; + return; + case TreeBuilder.XMP: + endTagExpectationAsArray = XMP_ARR; + return; + case TreeBuilder.TEXTAREA: + endTagExpectationAsArray = TEXTAREA_ARR; + return; + case TreeBuilder.IFRAME: + endTagExpectationAsArray = IFRAME_ARR; + return; + case TreeBuilder.NOEMBED: + endTagExpectationAsArray = NOEMBED_ARR; + return; + case TreeBuilder.NOSCRIPT: + endTagExpectationAsArray = NOSCRIPT_ARR; + return; + case TreeBuilder.NOFRAMES: + endTagExpectationAsArray = NOFRAMES_ARR; + return; + default: + assert false: "Bad end tag expectation."; + return; + } + } + + /** + * For C++ use only. + */ + public void setLineNumber(int line) { + // CPPONLY: this.attributeLine = line; // XXX is this needed? + this.line = line; + } + + // start Locator impl + + /** + * @see org.xml.sax.Locator#getLineNumber() + */ + @Inline public int getLineNumber() { + return line; + } + + // [NOCPP[ + + /** + * @see org.xml.sax.Locator#getColumnNumber() + */ + @Inline public int getColumnNumber() { + return -1; + } + + /** + * @see org.xml.sax.Locator#getPublicId() + */ + public String getPublicId() { + return publicId; + } + + /** + * @see org.xml.sax.Locator#getSystemId() + */ + public String getSystemId() { + return systemId; + } + + /** + * @see org.xml.sax.ext.Locator2#getXMLVersion() + */ + public String getXMLVersion() { + return "1.0"; + } + + /** + * @see org.xml.sax.ext.Locator2#getXMLVersion() + */ + public String getEncoding() { + try { + return encodingDeclarationHandler == null ? null : encodingDeclarationHandler.getCharacterEncoding(); + } catch (SAXException e) { + return null; + } + } + + // end Locator impl + + // end public API + + public void notifyAboutMetaBoundary() { + metaBoundaryPassed = true; + } + + // ]NOCPP] + + HtmlAttributes emptyAttributes() { + // [NOCPP[ + if (newAttributesEachTime) { + return new HtmlAttributes(mappingLangToXmlLang); + } else { + // ]NOCPP] + return HtmlAttributes.EMPTY_ATTRIBUTES; + // [NOCPP[ + } + // ]NOCPP] + } + + @Inline private void appendCharRefBuf(char c) { + // CPPONLY: assert charRefBufLen < charRefBuf.length: + // CPPONLY: "RELEASE: Attempted to overrun charRefBuf!"; + charRefBuf[charRefBufLen++] = c; + } + + private void emitOrAppendCharRefBuf(int returnState) throws SAXException { + if ((returnState & DATA_AND_RCDATA_MASK) != 0) { + appendCharRefBufToStrBuf(); + } else { + if (charRefBufLen > 0) { + tokenHandler.characters(charRefBuf, 0, charRefBufLen); + charRefBufLen = 0; + } + } + } + + @Inline private void clearStrBufAfterUse() { + strBufLen = 0; + } + + @Inline private void clearStrBufBeforeUse() { + assert strBufLen == 0: "strBufLen not reset after previous use!"; + strBufLen = 0; // no-op in the absence of bugs + } + + @Inline private void clearStrBufAfterOneHyphen() { + assert strBufLen == 1: "strBufLen length not one!"; + assert strBuf[0] == '-': "strBuf does not start with a hyphen!"; + strBufLen = 0; + } + + /** + * Appends to the buffer. + * + * @param c + * the UTF-16 code unit to append + */ + @Inline private void appendStrBuf(char c) { + // CPPONLY: assert strBufLen < strBuf.length: "Previous buffer length insufficient."; + // CPPONLY: if (strBufLen == strBuf.length) { + // CPPONLY: if (!EnsureBufferSpace(1)) { + // CPPONLY: assert false: "RELEASE: Unable to recover from buffer reallocation failure"; + // CPPONLY: } // TODO: Add telemetry when outer if fires but inner does not + // CPPONLY: } + strBuf[strBufLen++] = c; + } + + /** + * The buffer as a String. Currently only used for error reporting. + * + * <p> + * C++ memory note: The return value must be released. + * + * @return the buffer as a string + */ + protected String strBufToString() { + String str = Portability.newStringFromBuffer(strBuf, 0, strBufLen + // CPPONLY: , tokenHandler, !newAttributesEachTime && attributeName == AttributeName.CLASS + ); + clearStrBufAfterUse(); + return str; + } + + /** + * Returns the buffer as a local name. The return value is released in + * emitDoctypeToken(). + * + * @return the buffer as local name + */ + private void strBufToDoctypeName() { + doctypeName = Portability.newLocalNameFromBuffer(strBuf, strBufLen, interner); + clearStrBufAfterUse(); + } + + /** + * Emits the buffer as character tokens. + * + * @throws SAXException + * if the token handler threw + */ + private void emitStrBuf() throws SAXException { + if (strBufLen > 0) { + tokenHandler.characters(strBuf, 0, strBufLen); + clearStrBufAfterUse(); + } + } + + @Inline private void appendSecondHyphenToBogusComment() throws SAXException { + // [NOCPP[ + switch (commentPolicy) { + case ALTER_INFOSET: + appendStrBuf(' '); + // CPPONLY: MOZ_FALLTHROUGH; + case ALLOW: + warn("The document is not mappable to XML 1.0 due to two consecutive hyphens in a comment."); + // ]NOCPP] + appendStrBuf('-'); + // [NOCPP[ + break; + case FATAL: + fatal("The document is not mappable to XML 1.0 due to two consecutive hyphens in a comment."); + break; + } + // ]NOCPP] + } + + // [NOCPP[ + private void maybeAppendSpaceToBogusComment() throws SAXException { + switch (commentPolicy) { + case ALTER_INFOSET: + appendStrBuf(' '); + // CPPONLY: MOZ_FALLTHROUGH; + case ALLOW: + warn("The document is not mappable to XML 1.0 due to a trailing hyphen in a comment."); + break; + case FATAL: + fatal("The document is not mappable to XML 1.0 due to a trailing hyphen in a comment."); + break; + } + } + + // ]NOCPP] + + @Inline private void adjustDoubleHyphenAndAppendToStrBufAndErr(char c, boolean reportedConsecutiveHyphens) + throws SAXException { + // [NOCPP[ + switch (commentPolicy) { + case ALTER_INFOSET: + strBufLen--; + // WARNING!!! This expands the worst case of the buffer length + // given the length of input! + appendStrBuf(' '); + appendStrBuf('-'); + // CPPONLY: MOZ_FALLTHROUGH; + case ALLOW: + if (!reportedConsecutiveHyphens) { + warn("The document is not mappable to XML 1.0 due to two consecutive hyphens in a comment."); + } + // ]NOCPP] + appendStrBuf(c); + // [NOCPP[ + break; + case FATAL: + fatal("The document is not mappable to XML 1.0 due to two consecutive hyphens in a comment."); + break; + } + // ]NOCPP] + } + + private void appendStrBuf(@NoLength char[] buffer, int offset, int length) throws SAXException { + int newLen = Portability.checkedAdd(strBufLen, length); + // CPPONLY: assert newLen <= strBuf.length: "Previous buffer length insufficient."; + // CPPONLY: if (strBuf.length < newLen) { + // CPPONLY: if (!EnsureBufferSpace(length)) { + // CPPONLY: assert false: "RELEASE: Unable to recover from buffer reallocation failure"; + // CPPONLY: } // TODO: Add telemetry when outer if fires but inner does not + // CPPONLY: } + System.arraycopy(buffer, offset, strBuf, strBufLen, length); + strBufLen = newLen; + } + + /** + * Append the contents of the char reference buffer to the main one. + */ + @Inline private void appendCharRefBufToStrBuf() throws SAXException { + appendStrBuf(charRefBuf, 0, charRefBufLen); + charRefBufLen = 0; + } + + /** + * Emits the current comment token. + * + * NOTE: The method may set <code>shouldSuspend</code>, so the caller + * must have this pattern after the state's <code>transition</code> call: + * + * <pre> + * if (shouldSuspend) { + * break stateloop; + * } + * continue stateloop; + * </pre> + * + * @param pos + * TODO + * + * @throws SAXException + */ + private void emitComment(int provisionalHyphens, int pos) + throws SAXException { + // CPPONLY: RememberGt(pos); + // [NOCPP[ + if (wantsComments) { + // ]NOCPP] + tokenHandler.comment(strBuf, 0, strBufLen + - provisionalHyphens); + // [NOCPP[ + } + // ]NOCPP] + clearStrBufAfterUse(); + cstart = pos + 1; + suspendIfRequestedAfterCurrentNonTextToken(); + } + + /** + * Flushes coalesced character tokens. + * + * @param buf + * TODO + * @param pos + * TODO + * + * @throws SAXException + */ + protected void flushChars(@NoLength char[] buf, int pos) + throws SAXException { + if (pos > cstart) { + tokenHandler.characters(buf, cstart, pos - cstart); + } + cstart = Integer.MAX_VALUE; + } + + /** + * Reports an condition that would make the infoset incompatible with XML + * 1.0 as fatal. + * + * @param message + * the message + * @throws SAXException + * @throws SAXParseException + */ + public void fatal(String message) throws SAXException { + SAXParseException spe = new SAXParseException(message, this); + if (errorHandler != null) { + errorHandler.fatalError(spe); + } + throw spe; + } + + /** + * Reports a Parse Error. + * + * @param message + * the message + * @throws SAXException + */ + public void err(String message) throws SAXException { + if (errorHandler == null) { + return; + } + SAXParseException spe = new SAXParseException(message, this); + errorHandler.error(spe); + } + + public void errTreeBuilder(String message) throws SAXException { + ErrorHandler eh = null; + if (tokenHandler instanceof TreeBuilder<?>) { + TreeBuilder<?> treeBuilder = (TreeBuilder<?>) tokenHandler; + eh = treeBuilder.getErrorHandler(); + } + if (eh == null) { + eh = errorHandler; + } + if (eh == null) { + return; + } + SAXParseException spe = new SAXParseException(message, this); + eh.error(spe); + } + + /** + * Reports a warning + * + * @param message + * the message + * @throws SAXException + */ + public void warn(String message) throws SAXException { + if (errorHandler == null) { + return; + } + SAXParseException spe = new SAXParseException(message, this); + errorHandler.warning(spe); + } + + private void strBufToElementNameString() { + if (containsHyphen) { + // We've got a custom element or annotation-xml. + @Local String annotationName = ElementName.ANNOTATION_XML.getName(); + if (Portability.localEqualsBuffer(annotationName, strBuf, strBufLen)) { + tagName = ElementName.ANNOTATION_XML; + } else { + nonInternedTagName.setNameForNonInterned(Portability.newLocalNameFromBuffer(strBuf, strBufLen, + interner) + // CPPONLY: , true + ); + tagName = nonInternedTagName; + } + } else { + tagName = ElementName.elementNameByBuffer(strBuf, strBufLen, interner); + if (tagName == null) { + nonInternedTagName.setNameForNonInterned(Portability.newLocalNameFromBuffer(strBuf, strBufLen, + interner) + // CPPONLY: , false + ); + tagName = nonInternedTagName; + } + } + containsHyphen = false; + clearStrBufAfterUse(); + } + + /** + * Emits a tag token. + * + * NOTE: The method may set <code>shouldSuspend</code>, so the caller + * must have this pattern after the state's <code>transition</code> call: + * <pre> + * if (shouldSuspend) { + * break stateloop; + * } + * continue stateloop; + * </pre> + * + * @param selfClosing + * @param pos + * @return + * @throws SAXException + */ + private int emitCurrentTagToken(boolean selfClosing, int pos) + throws SAXException { + // CPPONLY: RememberGt(pos); + cstart = pos + 1; + maybeErrSlashInEndTag(selfClosing); + stateSave = Tokenizer.DATA; + HtmlAttributes attrs = (attributes == null ? HtmlAttributes.EMPTY_ATTRIBUTES + : attributes); + if (endTag) { + /* + * When an end tag token is emitted, the content model flag must be + * switched to the PCDATA state. + */ + maybeErrAttributesOnEndTag(attrs); + // CPPONLY: if (!viewingXmlSource) { + tokenHandler.endTag(tagName); + // CPPONLY: } + // CPPONLY: if (newAttributesEachTime) { + // CPPONLY: Portability.delete(attributes); + // CPPONLY: attributes = null; + // CPPONLY: } + } else { + // CPPONLY: if (viewingXmlSource) { + // CPPONLY: assert newAttributesEachTime; + // CPPONLY: Portability.delete(attributes); + // CPPONLY: attributes = null; + // CPPONLY: } else { + tokenHandler.startTag(tagName, attrs, selfClosing); + // CPPONLY: } + } + tagName = null; + if (newAttributesEachTime) { + attributes = null; + } else { + attributes.clear(mappingLangToXmlLang); + } + /* + * The token handler may have called setStateAndEndTagExpectation + * and changed stateSave since the start of this method. + */ + suspendIfRequestedAfterCurrentNonTextToken(); + return stateSave; + } + + private void attributeNameComplete() throws SAXException { + attributeName = AttributeName.nameByBuffer(strBuf, strBufLen, interner); + if (attributeName == null) { + // [NOCPP[ + attributeName = AttributeName.createAttributeName( + Portability.newLocalNameFromBuffer(strBuf, strBufLen, + interner), + namePolicy != XmlViolationPolicy.ALLOW); + // ]NOCPP] + // CPPONLY: nonInternedAttributeName.setNameForNonInterned(Portability.newLocalNameFromBuffer(strBuf, strBufLen, interner)); + // CPPONLY: attributeName = nonInternedAttributeName; + } + clearStrBufAfterUse(); + + if (attributes == null) { + attributes = new HtmlAttributes(mappingLangToXmlLang); + } + + /* + * When the user agent leaves the attribute name state (and before + * emitting the tag token, if appropriate), the complete attribute's + * name must be compared to the other attributes on the same token; if + * there is already an attribute on the token with the exact same name, + * then this is a parse error and the new attribute must be dropped, + * along with the value that gets associated with it (if any). + */ + if (attributes.contains(attributeName)) { + errDuplicateAttribute(); + attributeName = null; + } + } + + private void addAttributeWithoutValue() throws SAXException { + noteAttributeWithoutValue(); + + // [NOCPP[ + if (metaBoundaryPassed && AttributeName.CHARSET == attributeName + && ElementName.META == tagName) { + err("A \u201Ccharset\u201D attribute on a \u201Cmeta\u201D element found after the first 1024 bytes."); + } + // ]NOCPP] + if (attributeName != null) { + // [NOCPP[ + if (AttributeName.SRC == attributeName + || AttributeName.HREF == attributeName) { + warn("Attribute \u201C" + + attributeName.getLocal(AttributeName.HTML) + + "\u201D without an explicit value seen. The attribute may be dropped by IE7."); + } + // ]NOCPP] + attributes.addAttribute(attributeName, + Portability.newEmptyString() + // [NOCPP[ + , xmlnsPolicy + // ]NOCPP] + // CPPONLY: , attributeLine + ); + attributeName = null; + } else { + clearStrBufAfterUse(); + } + } + + private void addAttributeWithValue() throws SAXException { + // [NOCPP[ + if (metaBoundaryPassed && ElementName.META == tagName + && AttributeName.CHARSET == attributeName) { + err("A \u201Ccharset\u201D attribute on a \u201Cmeta\u201D element found after the first 1024 bytes."); + } + // ]NOCPP] + if (attributeName != null) { + String val = strBufToString(); // Ownership transferred to + // HtmlAttributes + // CPPONLY: if (mViewSource) { + // CPPONLY: mViewSource.MaybeLinkifyAttributeValue(attributeName, val); + // CPPONLY: } + attributes.addAttribute(attributeName, val + // [NOCPP[ + , xmlnsPolicy + // ]NOCPP] + // CPPONLY: , attributeLine + ); + attributeName = null; + } else { + // We have a duplicate attribute. Explicitly discard its value. + clearStrBufAfterUse(); + } + } + + // [NOCPP[ + + protected void startErrorReporting() throws SAXException { + + } + + // ]NOCPP] + + public void start() throws SAXException { + initializeWithoutStarting(); + tokenHandler.startTokenization(this); + // CPPONLY: line = 0; + // CPPONLY: col = 1; + // CPPONLY: nextCharOnNewLine = true; + // [NOCPP[ + startErrorReporting(); + // ]NOCPP] + } + + public boolean tokenizeBuffer(UTF16Buffer buffer) throws SAXException { + int state = stateSave; + int returnState = returnStateSave; + char c = '\u0000'; + shouldSuspend = false; + lastCR = false; + + int start = buffer.getStart(); + int end = buffer.getEnd(); + + // In C++, the caller of tokenizeBuffer needs to do this explicitly. + // [NOCPP[ + ensureBufferSpace(end - start); + // ]NOCPP] + + /** + * The index of the last <code>char</code> read from <code>buf</code>. + */ + int pos = start - 1; + + /** + * The index of the first <code>char</code> in <code>buf</code> that is + * part of a coalesced run of character tokens or + * <code>Integer.MAX_VALUE</code> if there is not a current run being + * coalesced. + */ + switch (state) { + case DATA: + case RCDATA: + case SCRIPT_DATA: + case PLAINTEXT: + case RAWTEXT: + case CDATA_SECTION: + case SCRIPT_DATA_ESCAPED: + case SCRIPT_DATA_ESCAPE_START: + case SCRIPT_DATA_ESCAPE_START_DASH: + case SCRIPT_DATA_ESCAPED_DASH: + case SCRIPT_DATA_ESCAPED_DASH_DASH: + case SCRIPT_DATA_DOUBLE_ESCAPE_START: + case SCRIPT_DATA_DOUBLE_ESCAPED: + case SCRIPT_DATA_DOUBLE_ESCAPED_LESS_THAN_SIGN: + case SCRIPT_DATA_DOUBLE_ESCAPED_DASH: + case SCRIPT_DATA_DOUBLE_ESCAPED_DASH_DASH: + case SCRIPT_DATA_DOUBLE_ESCAPE_END: + cstart = start; + break; + default: + cstart = Integer.MAX_VALUE; + break; + } + + /** + * The number of <code>char</code>s in <code>buf</code> that have + * meaning. (The rest of the array is garbage and should not be + * examined.) + */ + // CPPONLY: if (mViewSource) { + // CPPONLY: mViewSource.SetBuffer(buffer); + // CPPONLY: pos = stateLoop(state, c, pos, buffer.getBuffer(), false, returnState, buffer.getEnd()); + // CPPONLY: mViewSource.DropBuffer((pos == buffer.getEnd()) ? pos : pos + 1); + // CPPONLY: } else { + // CPPONLY: pos = stateLoop(state, c, pos, buffer.getBuffer(), false, returnState, buffer.getEnd()); + // CPPONLY: } + // [NOCPP[ + pos = stateLoop(state, c, pos, buffer.getBuffer(), false, returnState, + end); + // ]NOCPP] + if (pos == end) { + // exiting due to end of buffer + buffer.setStart(pos); + } else { + buffer.setStart(pos + 1); + } + return lastCR; + } + + // [NOCPP[ + private void ensureBufferSpace(int inputLength) throws SAXException { + // Add 2 to account for emissions of LT_GT, LT_SOLIDUS and RSQB_RSQB. + // Adding to the general worst case instead of only the + // TreeBuilder-exposed worst case to avoid re-introducing a bug when + // unifying the tokenizer and tree builder buffers in the future. + int worstCase = strBufLen + inputLength + charRefBufLen + 2; + tokenHandler.ensureBufferSpace(worstCase); + if (commentPolicy == XmlViolationPolicy.ALTER_INFOSET) { + // When altering infoset, if the comment contents are consecutive + // hyphens, each hyphen generates a space, too. These buffer + // contents never get emitted as characters() to the tokenHandler, + // which is why this calculation happens after the call to + // ensureBufferSpace on tokenHandler. + worstCase *= 2; + } + if (strBuf == null) { + // Add an arbitrary small value to avoid immediate reallocation + // once there are a few characters in the buffer. + strBuf = new char[worstCase + 128]; + } else if (worstCase > strBuf.length) { + // HotSpot reportedly allocates memory with 8-byte accuracy, so + // there's no point in trying to do math here to avoid slop. + // Maybe we should add some small constant to worstCase here + // but not doing that without profiling. In C++ with jemalloc, + // the corresponding method should do math to round up here + // to avoid slop. + char[] newBuf = new char[Math.max(worstCase, (strBuf.length*5)/4)]; + System.arraycopy(strBuf, 0, newBuf, 0, strBufLen); + strBuf = newBuf; + } + } + // ]NOCPP] + + @SuppressWarnings("unused") private int stateLoop(int state, char c, + int pos, @NoLength char[] buf, boolean reconsume, int returnState, + int endPos) throws SAXException { + boolean reportedConsecutiveHyphens = false; + /* + * Idioms used in this code: + * + * + * Consuming the next input character + * + * To consume the next input character, the code does this: if (++pos == + * endPos) { break stateloop; } c = checkChar(buf, pos); + * + * + * Staying in a state + * + * When there's a state that the tokenizer may stay in over multiple + * input characters, the state has a wrapper |for(;;)| loop and staying + * in the state continues the loop. + * + * + * Switching to another state + * + * To switch to another state, the code sets the state variable to the + * magic number of the new state. Then it either continues stateloop or + * breaks out of the state's own wrapper loop if the target state is + * right after the current state in source order. (This is a partial + * workaround for Java's lack of goto.) + * + * + * Reconsume support + * + * The spec sometimes says that an input character is reconsumed in + * another state. If a state can ever be entered so that an input + * character can be reconsumed in it, the state's code starts with an + * |if (reconsume)| that sets reconsume to false and skips over the + * normal code for consuming a new character. + * + * To reconsume the current character in another state, the code sets + * |reconsume| to true and then switches to the other state. + * + * + * Emitting character tokens + * + * This method emits character tokens lazily. Whenever a new range of + * character tokens starts, the field cstart must be set to the start + * index of the range. The flushChars() method must be called at the end + * of a range to flush it. + * + * + * U+0000 handling + * + * The various states have to handle the replacement of U+0000 with + * U+FFFD. However, if U+0000 would be reconsumed in another state, the + * replacement doesn't need to happen, because it's handled by the + * reconsuming state. + * + * + * LF handling + * + * Every state needs to increment the line number upon LF unless the LF + * gets reconsumed by another state which increments the line number. + * + * + * CR handling + * + * Every state needs to handle CR unless the CR gets reconsumed and is + * handled by the reconsuming state. The CR needs to be handled as if it + * were and LF, the lastCR field must be set to true and then this + * method must return. The IO driver will then swallow the next + * character if it is an LF to coalesce CRLF. + */ + stateloop: for (;;) { + switch (state) { + case DATA: + dataloop: for (;;) { + if (reconsume) { + reconsume = false; + } else { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + } + switch (c) { + case '&': + /* + * U+0026 AMPERSAND (&) Switch to the character + * reference in data state. + */ + flushChars(buf, pos); + assert charRefBufLen == 0: "charRefBufLen not reset after previous use!"; + appendCharRefBuf(c); + setAdditionalAndRememberAmpersandLocation('\u0000'); + returnState = state; + state = transition(state, Tokenizer.CONSUME_CHARACTER_REFERENCE, reconsume, pos); + continue stateloop; + case '<': + /* + * U+003C LESS-THAN SIGN (<) Switch to the tag + * open state. + */ + flushChars(buf, pos); + + state = transition(state, Tokenizer.TAG_OPEN, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break dataloop; + case '\u0000': + maybeEmitReplacementCharacter(buf, pos); + continue; + case '\r': + emitCarriageReturn(buf, pos); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + default: + /* + * Anything else Emit the input character as a + * character token. + * + * Stay in the data state. + */ + continue; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case TAG_OPEN: + tagopenloop: for (;;) { + /* + * The behavior of this state depends on the content + * model flag. + */ + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * If the content model flag is set to the PCDATA state + * Consume the next input character: + */ + if (c >= 'A' && c <= 'Z') { + /* + * U+0041 LATIN CAPITAL LETTER A through to U+005A + * LATIN CAPITAL LETTER Z Create a new start tag + * token, + */ + endTag = false; + /* + * set its tag name to the lowercase version of the + * input character (add 0x0020 to the character's + * code point), + */ + clearStrBufBeforeUse(); + appendStrBuf((char) (c + 0x20)); + containsHyphen = false; + /* then switch to the tag name state. */ + state = transition(state, Tokenizer.TAG_NAME, reconsume, pos); + /* + * (Don't emit the token yet; further details will + * be filled in before it is emitted.) + */ + // `break` optimizes; `continue stateloop;` would be valid + break tagopenloop; + } else if (c >= 'a' && c <= 'z') { + /* + * U+0061 LATIN SMALL LETTER A through to U+007A + * LATIN SMALL LETTER Z Create a new start tag + * token, + */ + endTag = false; + /* + * set its tag name to the input character, + */ + clearStrBufBeforeUse(); + appendStrBuf(c); + containsHyphen = false; + /* then switch to the tag name state. */ + state = transition(state, Tokenizer.TAG_NAME, reconsume, pos); + /* + * (Don't emit the token yet; further details will + * be filled in before it is emitted.) + */ + // `break` optimizes; `continue stateloop;` would be valid + break tagopenloop; + } + switch (c) { + case '!': + /* + * U+0021 EXCLAMATION MARK (!) Switch to the + * markup declaration open state. + */ + state = transition(state, Tokenizer.MARKUP_DECLARATION_OPEN, reconsume, pos); + continue stateloop; + case '/': + /* + * U+002F SOLIDUS (/) Switch to the close tag + * open state. + */ + state = transition(state, Tokenizer.CLOSE_TAG_OPEN, reconsume, pos); + continue stateloop; + case '?': + // CPPONLY: if (viewingXmlSource) { + // CPPONLY: state = transition(state, + // CPPONLY: Tokenizer.PROCESSING_INSTRUCTION, + // CPPONLY: reconsume, + // CPPONLY: pos); + // CPPONLY: continue stateloop; + // CPPONLY: } + /* + * U+003F QUESTION MARK (?) Parse error. + */ + errProcessingInstruction(); + /* + * Switch to the bogus comment state. + */ + clearStrBufBeforeUse(); + appendStrBuf(c); + state = transition(state, Tokenizer.BOGUS_COMMENT, reconsume, pos); + continue stateloop; + case '>': + /* + * U+003E GREATER-THAN SIGN (>) Parse error. + */ + errLtGt(); + /* + * Emit a U+003C LESS-THAN SIGN character token + * and a U+003E GREATER-THAN SIGN character + * token. + */ + tokenHandler.characters(Tokenizer.LT_GT, 0, 2); + /* Switch to the data state. */ + cstart = pos + 1; + state = transition(state, Tokenizer.DATA, reconsume, pos); + continue stateloop; + default: + /* + * Anything else Parse error. + */ + errBadCharAfterLt(c); + /* + * Emit a U+003C LESS-THAN SIGN character token + */ + tokenHandler.characters(Tokenizer.LT_GT, 0, 1); + /* + * and reconsume the current input character in + * the data state. + */ + cstart = pos; + reconsume = true; + state = transition(state, Tokenizer.DATA, reconsume, pos); + continue stateloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case TAG_NAME: + tagnameloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Consume the next input character: + */ + switch (c) { + case '\r': + silentCarriageReturn(); + strBufToElementNameString(); + state = transition(state, Tokenizer.BEFORE_ATTRIBUTE_NAME, reconsume, pos); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + case ' ': + case '\t': + case '\u000C': + /* + * U+0009 CHARACTER TABULATION U+000A LINE FEED + * (LF) U+000C FORM FEED (FF) U+0020 SPACE + * Switch to the before attribute name state. + */ + strBufToElementNameString(); + state = transition(state, Tokenizer.BEFORE_ATTRIBUTE_NAME, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break tagnameloop; + case '/': + /* + * U+002F SOLIDUS (/) Switch to the self-closing + * start tag state. + */ + strBufToElementNameString(); + state = transition(state, Tokenizer.SELF_CLOSING_START_TAG, reconsume, pos); + continue stateloop; + case '>': + /* + * U+003E GREATER-THAN SIGN (>) Emit the current + * tag token. + */ + strBufToElementNameString(); + state = transition(state, emitCurrentTagToken(false, pos), reconsume, pos); + if (shouldSuspend) { + break stateloop; + } + /* + * Switch to the data state. + */ + continue stateloop; + case '\u0000': + c = '\uFFFD'; + // CPPONLY: MOZ_FALLTHROUGH; + default: + if (c >= 'A' && c <= 'Z') { + /* + * U+0041 LATIN CAPITAL LETTER A through to + * U+005A LATIN CAPITAL LETTER Z Append the + * lowercase version of the current input + * character (add 0x0020 to the character's + * code point) to the current tag token's + * tag name. + */ + c += 0x20; + } else if (c == '-') { + containsHyphen = true; + } + /* + * Anything else Append the current input + * character to the current tag token's tag + * name. + */ + appendStrBuf(c); + /* + * Stay in the tag name state. + */ + continue; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case BEFORE_ATTRIBUTE_NAME: + beforeattributenameloop: for (;;) { + if (reconsume) { + reconsume = false; + } else { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + } + /* + * Consume the next input character: + */ + switch (c) { + case '\r': + silentCarriageReturn(); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + case ' ': + case '\t': + case '\u000C': + /* + * U+0009 CHARACTER TABULATION U+000A LINE FEED + * (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay + * in the before attribute name state. + */ + continue; + case '/': + /* + * U+002F SOLIDUS (/) Switch to the self-closing + * start tag state. + */ + state = transition(state, Tokenizer.SELF_CLOSING_START_TAG, reconsume, pos); + continue stateloop; + case '>': + /* + * U+003E GREATER-THAN SIGN (>) Emit the current + * tag token. + */ + state = transition(state, emitCurrentTagToken(false, pos), reconsume, pos); + if (shouldSuspend) { + break stateloop; + } + /* + * Switch to the data state. + */ + continue stateloop; + case '\u0000': + c = '\uFFFD'; + // CPPONLY: MOZ_FALLTHROUGH; + case '\"': + case '\'': + case '<': + case '=': + /* + * U+0022 QUOTATION MARK (") U+0027 APOSTROPHE + * (') U+003C LESS-THAN SIGN (<) U+003D EQUALS + * SIGN (=) Parse error. + */ + errBadCharBeforeAttributeNameOrNull(c); + /* + * Treat it as per the "anything else" entry + * below. + */ + // CPPONLY: MOZ_FALLTHROUGH; + default: + /* + * Anything else Start a new attribute in the + * current tag token. + */ + if (c >= 'A' && c <= 'Z') { + /* + * U+0041 LATIN CAPITAL LETTER A through to + * U+005A LATIN CAPITAL LETTER Z Set that + * attribute's name to the lowercase version + * of the current input character (add + * 0x0020 to the character's code point) + */ + c += 0x20; + } + // CPPONLY: attributeLine = line; + /* + * Set that attribute's name to the current + * input character, + */ + clearStrBufBeforeUse(); + appendStrBuf(c); + /* + * and its value to the empty string. + */ + // Will do later. + /* + * Switch to the attribute name state. + */ + state = transition(state, Tokenizer.ATTRIBUTE_NAME, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break beforeattributenameloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case ATTRIBUTE_NAME: + attributenameloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Consume the next input character: + */ + switch (c) { + case '\r': + silentCarriageReturn(); + attributeNameComplete(); + state = transition(state, Tokenizer.AFTER_ATTRIBUTE_NAME, reconsume, pos); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + case ' ': + case '\t': + case '\u000C': + /* + * U+0009 CHARACTER TABULATION U+000A LINE FEED + * (LF) U+000C FORM FEED (FF) U+0020 SPACE + * Switch to the after attribute name state. + */ + attributeNameComplete(); + state = transition(state, Tokenizer.AFTER_ATTRIBUTE_NAME, reconsume, pos); + continue stateloop; + case '/': + /* + * U+002F SOLIDUS (/) Switch to the self-closing + * start tag state. + */ + attributeNameComplete(); + addAttributeWithoutValue(); + state = transition(state, Tokenizer.SELF_CLOSING_START_TAG, reconsume, pos); + continue stateloop; + case '=': + /* + * U+003D EQUALS SIGN (=) Switch to the before + * attribute value state. + */ + attributeNameComplete(); + state = transition(state, Tokenizer.BEFORE_ATTRIBUTE_VALUE, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break attributenameloop; + case '>': + /* + * U+003E GREATER-THAN SIGN (>) Emit the current + * tag token. + */ + attributeNameComplete(); + addAttributeWithoutValue(); + state = transition(state, emitCurrentTagToken(false, pos), reconsume, pos); + if (shouldSuspend) { + break stateloop; + } + /* + * Switch to the data state. + */ + continue stateloop; + case '\u0000': + c = '\uFFFD'; + // CPPONLY: MOZ_FALLTHROUGH; + case '\"': + case '\'': + case '<': + /* + * U+0022 QUOTATION MARK (") U+0027 APOSTROPHE + * (') U+003C LESS-THAN SIGN (<) Parse error. + */ + errQuoteOrLtInAttributeNameOrNull(c); + /* + * Treat it as per the "anything else" entry + * below. + */ + // CPPONLY: MOZ_FALLTHROUGH; + default: + if (c >= 'A' && c <= 'Z') { + /* + * U+0041 LATIN CAPITAL LETTER A through to + * U+005A LATIN CAPITAL LETTER Z Append the + * lowercase version of the current input + * character (add 0x0020 to the character's + * code point) to the current attribute's + * name. + */ + c += 0x20; + } + /* + * Anything else Append the current input + * character to the current attribute's name. + */ + appendStrBuf(c); + /* + * Stay in the attribute name state. + */ + continue; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case BEFORE_ATTRIBUTE_VALUE: + beforeattributevalueloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Consume the next input character: + */ + switch (c) { + case '\r': + silentCarriageReturn(); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + case ' ': + case '\t': + case '\u000C': + /* + * U+0009 CHARACTER TABULATION U+000A LINE FEED + * (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay + * in the before attribute value state. + */ + continue; + case '"': + /* + * U+0022 QUOTATION MARK (") Switch to the + * attribute value (double-quoted) state. + */ + // CPPONLY: attributeLine = line; + clearStrBufBeforeUse(); + state = transition(state, Tokenizer.ATTRIBUTE_VALUE_DOUBLE_QUOTED, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break beforeattributevalueloop; + case '&': + /* + * U+0026 AMPERSAND (&) Switch to the attribute + * value (unquoted) state and reconsume this + * input character. + */ + // CPPONLY: attributeLine = line; + clearStrBufBeforeUse(); + reconsume = true; + state = transition(state, Tokenizer.ATTRIBUTE_VALUE_UNQUOTED, reconsume, pos); + noteUnquotedAttributeValue(); + continue stateloop; + case '\'': + /* + * U+0027 APOSTROPHE (') Switch to the attribute + * value (single-quoted) state. + */ + // CPPONLY: attributeLine = line; + clearStrBufBeforeUse(); + state = transition(state, Tokenizer.ATTRIBUTE_VALUE_SINGLE_QUOTED, reconsume, pos); + continue stateloop; + case '>': + /* + * U+003E GREATER-THAN SIGN (>) Parse error. + */ + errAttributeValueMissing(); + /* + * Emit the current tag token. + */ + addAttributeWithoutValue(); + state = transition(state, emitCurrentTagToken(false, pos), reconsume, pos); + if (shouldSuspend) { + break stateloop; + } + /* + * Switch to the data state. + */ + continue stateloop; + case '\u0000': + c = '\uFFFD'; + // CPPONLY: MOZ_FALLTHROUGH; + case '<': + case '=': + case '`': + /* + * U+003C LESS-THAN SIGN (<) U+003D EQUALS SIGN + * (=) U+0060 GRAVE ACCENT (`) + */ + errLtOrEqualsOrGraveInUnquotedAttributeOrNull(c); + /* + * Treat it as per the "anything else" entry + * below. + */ + // CPPONLY: MOZ_FALLTHROUGH; + default: + /* + * Anything else Append the current input + * character to the current attribute's value. + */ + // CPPONLY: attributeLine = line; + clearStrBufBeforeUse(); + appendStrBuf(c); + /* + * Switch to the attribute value (unquoted) + * state. + */ + + state = transition(state, Tokenizer.ATTRIBUTE_VALUE_UNQUOTED, reconsume, pos); + noteUnquotedAttributeValue(); + continue stateloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case ATTRIBUTE_VALUE_DOUBLE_QUOTED: + attributevaluedoublequotedloop: for (;;) { + if (reconsume) { + reconsume = false; + } else { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + } + /* + * Consume the next input character: + */ + switch (c) { + case '"': + /* + * U+0022 QUOTATION MARK (") Switch to the after + * attribute value (quoted) state. + */ + addAttributeWithValue(); + + state = transition(state, Tokenizer.AFTER_ATTRIBUTE_VALUE_QUOTED, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break attributevaluedoublequotedloop; + case '&': + /* + * U+0026 AMPERSAND (&) Switch to the character + * reference in attribute value state, with the + * additional allowed character being U+0022 + * QUOTATION MARK ("). + */ + assert charRefBufLen == 0: "charRefBufLen not reset after previous use!"; + appendCharRefBuf(c); + setAdditionalAndRememberAmpersandLocation('\"'); + returnState = state; + state = transition(state, Tokenizer.CONSUME_CHARACTER_REFERENCE, reconsume, pos); + continue stateloop; + case '\r': + appendStrBufCarriageReturn(); + break stateloop; + case '\n': + appendStrBufLineFeed(); + continue; + case '\u0000': + c = '\uFFFD'; + // CPPONLY: MOZ_FALLTHROUGH; + default: + /* + * Anything else Append the current input + * character to the current attribute's value. + */ + appendStrBuf(c); + /* + * Stay in the attribute value (double-quoted) + * state. + */ + continue; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case AFTER_ATTRIBUTE_VALUE_QUOTED: + afterattributevaluequotedloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Consume the next input character: + */ + switch (c) { + case '\r': + silentCarriageReturn(); + state = transition(state, Tokenizer.BEFORE_ATTRIBUTE_NAME, reconsume, pos); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + case ' ': + case '\t': + case '\u000C': + /* + * U+0009 CHARACTER TABULATION U+000A LINE FEED + * (LF) U+000C FORM FEED (FF) U+0020 SPACE + * Switch to the before attribute name state. + */ + state = transition(state, Tokenizer.BEFORE_ATTRIBUTE_NAME, reconsume, pos); + continue stateloop; + case '/': + /* + * U+002F SOLIDUS (/) Switch to the self-closing + * start tag state. + */ + state = transition(state, Tokenizer.SELF_CLOSING_START_TAG, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break afterattributevaluequotedloop; + case '>': + /* + * U+003E GREATER-THAN SIGN (>) Emit the current + * tag token. + */ + state = transition(state, emitCurrentTagToken(false, pos), reconsume, pos); + if (shouldSuspend) { + break stateloop; + } + /* + * Switch to the data state. + */ + continue stateloop; + default: + /* + * Anything else Parse error. + */ + errNoSpaceBetweenAttributes(); + /* + * Reconsume the character in the before + * attribute name state. + */ + reconsume = true; + state = transition(state, Tokenizer.BEFORE_ATTRIBUTE_NAME, reconsume, pos); + continue stateloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case SELF_CLOSING_START_TAG: + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Consume the next input character: + */ + switch (c) { + case '>': + /* + * U+003E GREATER-THAN SIGN (>) Set the self-closing + * flag of the current tag token. Emit the current + * tag token. + */ + state = transition(state, emitCurrentTagToken(true, pos), reconsume, pos); + if (shouldSuspend) { + break stateloop; + } + /* + * Switch to the data state. + */ + continue stateloop; + default: + /* Anything else Parse error. */ + errSlashNotFollowedByGt(); + /* + * Reconsume the character in the before attribute + * name state. + */ + reconsume = true; + state = transition(state, Tokenizer.BEFORE_ATTRIBUTE_NAME, reconsume, pos); + continue stateloop; + } + // no fallthrough, reordering opportunity + case ATTRIBUTE_VALUE_UNQUOTED: + for (;;) { + if (reconsume) { + reconsume = false; + } else { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + } + /* + * Consume the next input character: + */ + switch (c) { + case '\r': + silentCarriageReturn(); + addAttributeWithValue(); + state = transition(state, Tokenizer.BEFORE_ATTRIBUTE_NAME, reconsume, pos); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + case ' ': + case '\t': + case '\u000C': + /* + * U+0009 CHARACTER TABULATION U+000A LINE FEED + * (LF) U+000C FORM FEED (FF) U+0020 SPACE + * Switch to the before attribute name state. + */ + addAttributeWithValue(); + state = transition(state, Tokenizer.BEFORE_ATTRIBUTE_NAME, reconsume, pos); + continue stateloop; + case '&': + /* + * U+0026 AMPERSAND (&) Switch to the character + * reference in attribute value state, with the + * additional allowed character being U+003E + * GREATER-THAN SIGN (>) + */ + assert charRefBufLen == 0: "charRefBufLen not reset after previous use!"; + appendCharRefBuf(c); + setAdditionalAndRememberAmpersandLocation('>'); + returnState = state; + state = transition(state, Tokenizer.CONSUME_CHARACTER_REFERENCE, reconsume, pos); + continue stateloop; + case '>': + /* + * U+003E GREATER-THAN SIGN (>) Emit the current + * tag token. + */ + addAttributeWithValue(); + state = transition(state, emitCurrentTagToken(false, pos), reconsume, pos); + if (shouldSuspend) { + break stateloop; + } + /* + * Switch to the data state. + */ + continue stateloop; + case '\u0000': + c = '\uFFFD'; + // CPPONLY: MOZ_FALLTHROUGH; + case '<': + case '\"': + case '\'': + case '=': + case '`': + /* + * U+0022 QUOTATION MARK (") U+0027 APOSTROPHE + * (') U+003C LESS-THAN SIGN (<) U+003D EQUALS + * SIGN (=) U+0060 GRAVE ACCENT (`) Parse error. + */ + errUnquotedAttributeValOrNull(c); + /* + * Treat it as per the "anything else" entry + * below. + */ + // CPPONLY: MOZ_FALLTHROUGH; + default: + /* + * Anything else Append the current input + * character to the current attribute's value. + */ + appendStrBuf(c); + /* + * Stay in the attribute value (unquoted) state. + */ + continue; + } + } + // no fallthrough, reordering opportunity + case AFTER_ATTRIBUTE_NAME: + for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Consume the next input character: + */ + switch (c) { + case '\r': + silentCarriageReturn(); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + case ' ': + case '\t': + case '\u000C': + /* + * U+0009 CHARACTER TABULATION U+000A LINE FEED + * (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay + * in the after attribute name state. + */ + continue; + case '/': + /* + * U+002F SOLIDUS (/) Switch to the self-closing + * start tag state. + */ + addAttributeWithoutValue(); + state = transition(state, Tokenizer.SELF_CLOSING_START_TAG, reconsume, pos); + continue stateloop; + case '=': + /* + * U+003D EQUALS SIGN (=) Switch to the before + * attribute value state. + */ + state = transition(state, Tokenizer.BEFORE_ATTRIBUTE_VALUE, reconsume, pos); + continue stateloop; + case '>': + /* + * U+003E GREATER-THAN SIGN (>) Emit the current + * tag token. + */ + addAttributeWithoutValue(); + state = transition(state, emitCurrentTagToken(false, pos), reconsume, pos); + if (shouldSuspend) { + break stateloop; + } + /* + * Switch to the data state. + */ + continue stateloop; + case '\u0000': + c = '\uFFFD'; + // CPPONLY: MOZ_FALLTHROUGH; + case '\"': + case '\'': + case '<': + errQuoteOrLtInAttributeNameOrNull(c); + /* + * Treat it as per the "anything else" entry + * below. + */ + // CPPONLY: MOZ_FALLTHROUGH; + default: + addAttributeWithoutValue(); + /* + * Anything else Start a new attribute in the + * current tag token. + */ + if (c >= 'A' && c <= 'Z') { + /* + * U+0041 LATIN CAPITAL LETTER A through to + * U+005A LATIN CAPITAL LETTER Z Set that + * attribute's name to the lowercase version + * of the current input character (add + * 0x0020 to the character's code point) + */ + c += 0x20; + } + /* + * Set that attribute's name to the current + * input character, + */ + clearStrBufBeforeUse(); + appendStrBuf(c); + /* + * and its value to the empty string. + */ + // Will do later. + /* + * Switch to the attribute name state. + */ + state = transition(state, Tokenizer.ATTRIBUTE_NAME, reconsume, pos); + continue stateloop; + } + } + // no fallthrough, reordering opportunity + case MARKUP_DECLARATION_OPEN: + markupdeclarationopenloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * If the next two characters are both U+002D + * HYPHEN-MINUS characters (-), consume those two + * characters, create a comment token whose data is the + * empty string, and switch to the comment start state. + * + * Otherwise, if the next seven characters are an ASCII + * case-insensitive match for the word "DOCTYPE", then + * consume those characters and switch to the DOCTYPE + * state. + * + * Otherwise, if the insertion mode is + * "in foreign content" and the current node is not an + * element in the HTML namespace and the next seven + * characters are an case-sensitive match for the string + * "[CDATA[" (the five uppercase letters "CDATA" with a + * U+005B LEFT SQUARE BRACKET character before and + * after), then consume those characters and switch to + * the CDATA section state. + * + * Otherwise, is is a parse error. Switch to the bogus + * comment state. The next character that is consumed, + * if any, is the first character that will be in the + * comment. + */ + switch (c) { + case '-': + clearStrBufBeforeUse(); + appendStrBuf(c); + state = transition(state, Tokenizer.MARKUP_DECLARATION_HYPHEN, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break markupdeclarationopenloop; + case 'd': + case 'D': + clearStrBufBeforeUse(); + appendStrBuf(c); + index = 0; + state = transition(state, Tokenizer.MARKUP_DECLARATION_OCTYPE, reconsume, pos); + continue stateloop; + case '[': + if (tokenHandler.cdataSectionAllowed()) { + clearStrBufBeforeUse(); + appendStrBuf(c); + index = 0; + state = transition(state, Tokenizer.CDATA_START, reconsume, pos); + continue stateloop; + } + // CPPONLY: MOZ_FALLTHROUGH; + default: + errBogusComment(); + clearStrBufBeforeUse(); + reconsume = true; + state = transition(state, Tokenizer.BOGUS_COMMENT, reconsume, pos); + continue stateloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case MARKUP_DECLARATION_HYPHEN: + markupdeclarationhyphenloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + switch (c) { + case '-': + clearStrBufAfterOneHyphen(); + state = transition(state, Tokenizer.COMMENT_START, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break markupdeclarationhyphenloop; + default: + errBogusComment(); + reconsume = true; + state = transition(state, Tokenizer.BOGUS_COMMENT, reconsume, pos); + continue stateloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case COMMENT_START: + reportedConsecutiveHyphens = false; + commentstartloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Comment start state + * + * + * Consume the next input character: + */ + switch (c) { + case '-': + /* + * U+002D HYPHEN-MINUS (-) Switch to the comment + * start dash state. + */ + appendStrBuf(c); + state = transition(state, Tokenizer.COMMENT_START_DASH, reconsume, pos); + continue stateloop; + case '>': + /* + * U+003E GREATER-THAN SIGN (>) Parse error. + */ + errPrematureEndOfComment(); + /* Emit the comment token. */ + emitComment(0, pos); + /* + * Switch to the data state. + */ + state = transition(state, Tokenizer.DATA, reconsume, pos); + if (shouldSuspend) { + break stateloop; + } + continue stateloop; + case '<': + appendStrBuf(c); + state = transition(state, Tokenizer.COMMENT_LESSTHAN, reconsume, pos); + continue stateloop; + case '\r': + appendStrBufCarriageReturn(); + state = transition(state, Tokenizer.COMMENT, reconsume, pos); + break stateloop; + case '\n': + appendStrBufLineFeed(); + state = transition(state, Tokenizer.COMMENT, reconsume, pos); + break commentstartloop; + case '\u0000': + c = '\uFFFD'; + // CPPONLY: MOZ_FALLTHROUGH; + default: + /* + * Anything else Append the input character to + * the comment token's data. + */ + appendStrBuf(c); + /* + * Switch to the comment state. + */ + state = transition(state, Tokenizer.COMMENT, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break commentstartloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case COMMENT: + commentloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Comment state Consume the next input character: + */ + switch (c) { + case '-': + /* + * U+002D HYPHEN-MINUS (-) Switch to the comment + * end dash state + */ + appendStrBuf(c); + state = transition(state, Tokenizer.COMMENT_END_DASH, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break commentloop; + case '<': + appendStrBuf(c); + state = transition(state, Tokenizer.COMMENT_LESSTHAN, reconsume, pos); + continue stateloop; + case '\r': + appendStrBufCarriageReturn(); + break stateloop; + case '\n': + appendStrBufLineFeed(); + continue; + case '\u0000': + c = '\uFFFD'; + // CPPONLY: MOZ_FALLTHROUGH; + default: + /* + * Anything else Append the input character to + * the comment token's data. + */ + appendStrBuf(c); + /* + * Stay in the comment state. + */ + continue; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case COMMENT_END_DASH: + commentenddashloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Comment end dash state Consume the next input + * character: + */ + switch (c) { + case '-': + /* + * U+002D HYPHEN-MINUS (-) Switch to the comment + * end state + */ + appendStrBuf(c); + state = transition(state, Tokenizer.COMMENT_END, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break commentenddashloop; + case '<': + appendStrBuf(c); + state = transition(state, Tokenizer.COMMENT_LESSTHAN, reconsume, pos); + continue stateloop; + case '\r': + appendStrBufCarriageReturn(); + state = transition(state, Tokenizer.COMMENT, reconsume, pos); + break stateloop; + case '\n': + appendStrBufLineFeed(); + state = transition(state, Tokenizer.COMMENT, reconsume, pos); + continue stateloop; + case '\u0000': + c = '\uFFFD'; + // CPPONLY: MOZ_FALLTHROUGH; + default: + /* + * Anything else Append a U+002D HYPHEN-MINUS + * (-) character and the input character to the + * comment token's data. + */ + appendStrBuf(c); + /* + * Switch to the comment state. + */ + state = transition(state, Tokenizer.COMMENT, reconsume, pos); + continue stateloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case COMMENT_END: + commentendloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Comment end dash state Consume the next input + * character: + */ + switch (c) { + case '>': + /* + * U+003E GREATER-THAN SIGN (>) Emit the comment + * token. + */ + emitComment(2, pos); + /* + * Switch to the data state. + */ + state = transition(state, Tokenizer.DATA, reconsume, pos); + if (shouldSuspend) { + break stateloop; + } + continue stateloop; + case '-': + /* U+002D HYPHEN-MINUS (-) Parse error. */ + /* + * Append a U+002D HYPHEN-MINUS (-) character to + * the comment token's data. + */ + adjustDoubleHyphenAndAppendToStrBufAndErr(c, reportedConsecutiveHyphens); + reportedConsecutiveHyphens = true; + /* + * Stay in the comment end state. + */ + continue; + case '<': + appendStrBuf(c); + state = transition(state, Tokenizer.COMMENT_LESSTHAN, reconsume, pos); + continue stateloop; + case '\r': + adjustDoubleHyphenAndAppendToStrBufCarriageReturn(); + state = transition(state, Tokenizer.COMMENT, reconsume, pos); + break stateloop; + case '\n': + adjustDoubleHyphenAndAppendToStrBufLineFeed(); + state = transition(state, Tokenizer.COMMENT, reconsume, pos); + continue stateloop; + case '!': + appendStrBuf(c); + state = transition(state, Tokenizer.COMMENT_END_BANG, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break commentendloop; + case '\u0000': + c = '\uFFFD'; + // CPPONLY: MOZ_FALLTHROUGH; + default: + /* + * Append two U+002D HYPHEN-MINUS (-) characters + * and the input character to the comment + * token's data. + */ + adjustDoubleHyphenAndAppendToStrBufAndErr(c, reportedConsecutiveHyphens); + reportedConsecutiveHyphens = true; + /* + * Switch to the comment state. + */ + state = transition(state, Tokenizer.COMMENT, reconsume, pos); + continue stateloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case COMMENT_END_BANG: + for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Comment end bang state + * + * Consume the next input character: + */ + switch (c) { + case '>': + /* + * U+003E GREATER-THAN SIGN (>) Emit the comment + * token. + */ + emitComment(3, pos); + /* + * Switch to the data state. + */ + state = transition(state, Tokenizer.DATA, reconsume, pos); + if (shouldSuspend) { + break stateloop; + } + continue stateloop; + case '-': + /* + * Append two U+002D HYPHEN-MINUS (-) characters + * and a U+0021 EXCLAMATION MARK (!) character + * to the comment token's data. + */ + appendStrBuf(c); + /* + * Switch to the comment end dash state. + */ + state = transition(state, Tokenizer.COMMENT_END_DASH, reconsume, pos); + continue stateloop; + case '\r': + appendStrBufCarriageReturn(); + state = transition(state, Tokenizer.COMMENT, reconsume, pos); + break stateloop; + case '\n': + appendStrBufLineFeed(); + state = transition(state, Tokenizer.COMMENT, reconsume, pos); + continue stateloop; + case '\u0000': + c = '\uFFFD'; + // CPPONLY: MOZ_FALLTHROUGH; + default: + /* + * Anything else Append two U+002D HYPHEN-MINUS + * (-) characters, a U+0021 EXCLAMATION MARK (!) + * character, and the input character to the + * comment token's data. Switch to the comment + * state. + */ + appendStrBuf(c); + /* + * Switch to the comment state. + */ + state = transition(state, Tokenizer.COMMENT, reconsume, pos); + continue stateloop; + } + } + // no fallthrough, reordering opportunity + case COMMENT_LESSTHAN: + commentlessthanloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + switch (c) { + case '!': + appendStrBuf(c); + state = transition(state, Tokenizer.COMMENT_LESSTHAN_BANG, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break commentlessthanloop; + case '<': + appendStrBuf(c); + continue; + case '-': + appendStrBuf(c); + state = transition(state, Tokenizer.COMMENT_END_DASH, reconsume, pos); + continue stateloop; + case '\r': + appendStrBufCarriageReturn(); + state = transition(state, Tokenizer.COMMENT, reconsume, pos); + break stateloop; + case '\n': + appendStrBufLineFeed(); + state = transition(state, Tokenizer.COMMENT, reconsume, pos); + continue stateloop; + case '\u0000': + c = '\uFFFD'; + // CPPONLY: MOZ_FALLTHROUGH; + default: + appendStrBuf(c); + state = transition(state, Tokenizer.COMMENT, reconsume, pos); + continue stateloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case COMMENT_LESSTHAN_BANG: + commentlessthanbangloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + switch (c) { + case '-': + appendStrBuf(c); + state = transition(state, Tokenizer.COMMENT_LESSTHAN_BANG_DASH, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break commentlessthanbangloop; + case '<': + appendStrBuf(c); + state = transition(state, Tokenizer.COMMENT_LESSTHAN, reconsume, pos); + continue stateloop; + case '\r': + appendStrBufCarriageReturn(); + state = transition(state, Tokenizer.COMMENT, reconsume, pos); + break stateloop; + case '\n': + appendStrBufLineFeed(); + state = transition(state, Tokenizer.COMMENT, reconsume, pos); + continue stateloop; + case '\u0000': + c = '\uFFFD'; + // CPPONLY: MOZ_FALLTHROUGH; + default: + appendStrBuf(c); + state = transition(state, Tokenizer.COMMENT, reconsume, pos); + continue stateloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case COMMENT_LESSTHAN_BANG_DASH: + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + switch (c) { + case '-': + appendStrBuf(c); + state = transition(state, + Tokenizer.COMMENT_LESSTHAN_BANG_DASH_DASH, + reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break; + case '<': + appendStrBuf(c); + state = transition(state, + Tokenizer.COMMENT_LESSTHAN, reconsume, pos); + continue stateloop; + case '\r': + appendStrBufCarriageReturn(); + state = transition(state, Tokenizer.COMMENT, + reconsume, pos); + break stateloop; + case '\n': + appendStrBufLineFeed(); + state = transition(state, Tokenizer.COMMENT, + reconsume, pos); + continue stateloop; + case '\u0000': + c = '\uFFFD'; + // CPPONLY: MOZ_FALLTHROUGH; + default: + appendStrBuf(c); + state = transition(state, Tokenizer.COMMENT, + reconsume, pos); + continue stateloop; + } + // CPPONLY: MOZ_FALLTHROUGH; + case COMMENT_LESSTHAN_BANG_DASH_DASH: + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + switch (c) { + case '>': + appendStrBuf(c); + emitComment(3, pos); + state = transition(state, Tokenizer.DATA, reconsume, + pos); + if (shouldSuspend) { + break stateloop; + } + continue stateloop; + case '-': + errNestedComment(); + adjustDoubleHyphenAndAppendToStrBufAndErr(c, + reportedConsecutiveHyphens); + reportedConsecutiveHyphens = true; + state = transition(state, Tokenizer.COMMENT_END, + reconsume, pos); + continue stateloop; + case '\r': + c = '\n'; + silentCarriageReturn(); + errNestedComment(); + adjustDoubleHyphenAndAppendToStrBufAndErr(c, + reportedConsecutiveHyphens); + reportedConsecutiveHyphens = true; + state = transition(state, Tokenizer.COMMENT, + reconsume, pos); + break stateloop; + case '\n': + silentLineFeed(); + errNestedComment(); + adjustDoubleHyphenAndAppendToStrBufAndErr(c, + reportedConsecutiveHyphens); + reportedConsecutiveHyphens = true; + state = transition(state, Tokenizer.COMMENT, + reconsume, pos); + continue stateloop; + case '!': + errNestedComment(); + adjustDoubleHyphenAndAppendToStrBufAndErr(c, + reportedConsecutiveHyphens); + reportedConsecutiveHyphens = true; + state = transition(state, + Tokenizer.COMMENT_END_BANG, reconsume, pos); + continue stateloop; + case '\u0000': + c = '\uFFFD'; + // CPPONLY: MOZ_FALLTHROUGH; + default: + errNestedComment(); + adjustDoubleHyphenAndAppendToStrBufAndErr(c, + reportedConsecutiveHyphens); + reportedConsecutiveHyphens = true; + state = transition(state, Tokenizer.COMMENT, + reconsume, pos); + continue stateloop; + } + // no fallthrough, reordering opportunity + case COMMENT_START_DASH: + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Comment start dash state + * + * Consume the next input character: + */ + switch (c) { + case '-': + /* + * U+002D HYPHEN-MINUS (-) Switch to the comment end + * state + */ + appendStrBuf(c); + state = transition(state, Tokenizer.COMMENT_END, reconsume, pos); + continue stateloop; + case '>': + errPrematureEndOfComment(); + /* Emit the comment token. */ + emitComment(1, pos); + /* + * Switch to the data state. + */ + state = transition(state, Tokenizer.DATA, reconsume, pos); + if (shouldSuspend) { + break stateloop; + } + continue stateloop; + case '<': + appendStrBuf(c); + state = transition(state, Tokenizer.COMMENT_LESSTHAN, reconsume, pos); + continue stateloop; + case '\r': + appendStrBufCarriageReturn(); + state = transition(state, Tokenizer.COMMENT, reconsume, pos); + break stateloop; + case '\n': + appendStrBufLineFeed(); + state = transition(state, Tokenizer.COMMENT, reconsume, pos); + continue stateloop; + case '\u0000': + c = '\uFFFD'; + // CPPONLY: MOZ_FALLTHROUGH; + default: + /* + * Append a U+002D HYPHEN-MINUS character (-) and + * the current input character to the comment + * token's data. + */ + appendStrBuf(c); + /* + * Switch to the comment state. + */ + state = transition(state, Tokenizer.COMMENT, reconsume, pos); + continue stateloop; + } + // no fallthrough, reordering opportunity + case CDATA_START: + for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + if (index < 6) { // CDATA_LSQB.length + if (c == Tokenizer.CDATA_LSQB[index]) { + appendStrBuf(c); + } else { + errBogusComment(); + reconsume = true; + state = transition(state, Tokenizer.BOGUS_COMMENT, reconsume, pos); + continue stateloop; + } + index++; + continue; + } else { + clearStrBufAfterUse(); + cstart = pos; // start coalescing + reconsume = true; + state = transition(state, Tokenizer.CDATA_SECTION, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case CDATA_SECTION: + cdatasectionloop: for (;;) { + if (reconsume) { + reconsume = false; + } else { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + } + switch (c) { + case ']': + flushChars(buf, pos); + state = transition(state, Tokenizer.CDATA_RSQB, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break cdatasectionloop; + case '\u0000': + maybeEmitReplacementCharacter(buf, pos); + continue; + case '\r': + emitCarriageReturn(buf, pos); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + default: + continue; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case CDATA_RSQB: + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + switch (c) { + case ']': + state = transition(state, Tokenizer.CDATA_RSQB_RSQB, + reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break; + default: + tokenHandler.characters(Tokenizer.RSQB_RSQB, 0, 1); + cstart = pos; + reconsume = true; + state = transition(state, Tokenizer.CDATA_SECTION, + reconsume, pos); + continue stateloop; + } + // CPPONLY: MOZ_FALLTHROUGH; + case CDATA_RSQB_RSQB: + cdatarsqbrsqb: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + switch (c) { + case ']': + // Saw a third ]. Emit one ] (logically the + // first one) and stay in this state to + // remember that the last two characters seen + // have been ]]. + tokenHandler.characters(Tokenizer.RSQB_RSQB, 0, 1); + continue; + case '>': + cstart = pos + 1; + state = transition(state, Tokenizer.DATA, reconsume, pos); + // Since a CDATA section starts with a less-than sign, it + // participates in the suspension-after-current-token + // behavior. (The suspension can be requested when the + // less-than sign has been seen but we don't yet know the + // resulting token type.) Therefore, we need to deal with + // a potential request here. + suspendIfRequestedAfterCurrentNonTextToken(); + if (shouldSuspend) { + break stateloop; + } + continue stateloop; + default: + tokenHandler.characters(Tokenizer.RSQB_RSQB, 0, 2); + cstart = pos; + reconsume = true; + state = transition(state, Tokenizer.CDATA_SECTION, reconsume, pos); + continue stateloop; + } + } + // no fallthrough, reordering opportunity + case ATTRIBUTE_VALUE_SINGLE_QUOTED: + attributevaluesinglequotedloop: for (;;) { + if (reconsume) { + reconsume = false; + } else { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + } + /* + * Consume the next input character: + */ + switch (c) { + case '\'': + /* + * U+0027 APOSTROPHE (') Switch to the after + * attribute value (quoted) state. + */ + addAttributeWithValue(); + + state = transition(state, Tokenizer.AFTER_ATTRIBUTE_VALUE_QUOTED, reconsume, pos); + continue stateloop; + case '&': + /* + * U+0026 AMPERSAND (&) Switch to the character + * reference in attribute value state, with the + * + additional allowed character being U+0027 + * APOSTROPHE ('). + */ + assert charRefBufLen == 0: "charRefBufLen not reset after previous use!"; + appendCharRefBuf(c); + setAdditionalAndRememberAmpersandLocation('\''); + returnState = state; + state = transition(state, Tokenizer.CONSUME_CHARACTER_REFERENCE, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break attributevaluesinglequotedloop; + case '\r': + appendStrBufCarriageReturn(); + break stateloop; + case '\n': + appendStrBufLineFeed(); + continue; + case '\u0000': + c = '\uFFFD'; + // CPPONLY: MOZ_FALLTHROUGH; + default: + /* + * Anything else Append the current input + * character to the current attribute's value. + */ + appendStrBuf(c); + /* + * Stay in the attribute value (double-quoted) + * state. + */ + continue; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case CONSUME_CHARACTER_REFERENCE: + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Unlike the definition is the spec, this state does not + * return a value and never requires the caller to + * backtrack. This state takes care of emitting characters + * or appending to the current attribute value. It also + * takes care of that in the case when consuming the + * character reference fails. + */ + /* + * This section defines how to consume a character + * reference. This definition is used when parsing character + * references in text and in attributes. + * + * The behavior depends on the identity of the next + * character (the one immediately after the U+0026 AMPERSAND + * character): + */ + switch (c) { + case ' ': + case '\t': + case '\n': + case '\r': // we'll reconsume! + case '\u000C': + case '<': + case '&': + case '\u0000': + case ';': + emitOrAppendCharRefBuf(returnState); + if ((returnState & DATA_AND_RCDATA_MASK) == 0) { + cstart = pos; + } + reconsume = true; + state = transition(state, returnState, reconsume, pos); + continue stateloop; + case '#': + /* + * U+0023 NUMBER SIGN (#) Consume the U+0023 NUMBER + * SIGN. + */ + appendCharRefBuf('#'); + state = transition(state, Tokenizer.CONSUME_NCR, reconsume, pos); + continue stateloop; + default: + if (c == additional) { + emitOrAppendCharRefBuf(returnState); + reconsume = true; + state = transition(state, returnState, reconsume, pos); + continue stateloop; + } + if (c >= 'a' && c <= 'z') { + firstCharKey = c - 'a' + 26; + } else if (c >= 'A' && c <= 'Z') { + firstCharKey = c - 'A'; + } else { + // No match + if (c == ';') { + errNoNamedCharacterMatch(); + } + emitOrAppendCharRefBuf(returnState); + if ((returnState & DATA_AND_RCDATA_MASK) == 0) { + cstart = pos; + } + reconsume = true; + state = transition(state, returnState, reconsume, pos); + continue stateloop; + } + // Didn't fail yet + appendCharRefBuf(c); + state = transition(state, Tokenizer.CHARACTER_REFERENCE_HILO_LOOKUP, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break; + } + // CPPONLY: MOZ_FALLTHROUGH; + case CHARACTER_REFERENCE_HILO_LOOKUP: + { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * The data structure is as follows: + * + * HILO_ACCEL is a two-dimensional int array whose major + * index corresponds to the second character of the + * character reference (code point as index) and the + * minor index corresponds to the first character of the + * character reference (packed so that A-Z runs from 0 + * to 25 and a-z runs from 26 to 51). This layout makes + * it easier to use the sparseness of the data structure + * to omit parts of it: The second dimension of the + * table is null when no character reference starts with + * the character corresponding to that row. + * + * The int value HILO_ACCEL (by these indeces) is zero + * if there exists no character reference starting with + * that two-letter prefix. Otherwise, the value is an + * int that packs two shorts so that the higher short is + * the index of the highest character reference name + * with that prefix in NAMES and the lower short + * corresponds to the index of the lowest character + * reference name with that prefix. (It happens that the + * first two character reference names share their + * prefix so the packed int cannot be 0 by packing the + * two shorts.) + * + * NAMES is an array of byte arrays where each byte + * array encodes the name of a character references as + * ASCII. The names omit the first two letters of the + * name. (Since storing the first two letters would be + * redundant with the data contained in HILO_ACCEL.) The + * entries are lexically sorted. + * + * For a given index in NAMES, the same index in VALUES + * contains the corresponding expansion as an array of + * two UTF-16 code units (either the character and + * U+0000 or a suggogate pair). + */ + int hilo = 0; + if (c <= 'z') { + @Const @NoLength int[] row = NamedCharactersAccel.HILO_ACCEL[c]; + if (row != null) { + hilo = row[firstCharKey]; + } + } + if (hilo == 0) { + if (c == ';') { + errNoNamedCharacterMatch(); + } + emitOrAppendCharRefBuf(returnState); + if ((returnState & DATA_AND_RCDATA_MASK) == 0) { + cstart = pos; + } + reconsume = true; + state = transition(state, returnState, reconsume, pos); + continue stateloop; + } + // Didn't fail yet + appendCharRefBuf(c); + lo = hilo & 0xFFFF; + hi = hilo >> 16; + entCol = -1; + candidate = -1; + charRefBufMark = 0; + state = transition(state, Tokenizer.CHARACTER_REFERENCE_TAIL, reconsume, pos); + // fallthrough optimizes; `continue stateloop;` would also be valid + } + // CPPONLY: MOZ_FALLTHROUGH; + case CHARACTER_REFERENCE_TAIL: + outer: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + entCol++; + /* + * Consume the maximum number of characters possible, + * with the consumed characters matching one of the + * identifiers in the first column of the named + * character references table (in a case-sensitive + * manner). + */ + loloop: for (;;) { + if (hi < lo) { + break outer; + } + if (entCol == NamedCharacters.NAMES[lo].length()) { + candidate = lo; + charRefBufMark = charRefBufLen; + lo++; + } else if (entCol > NamedCharacters.NAMES[lo].length()) { + break outer; + } else if (c > NamedCharacters.NAMES[lo].charAt(entCol)) { + lo++; + } else { + break loloop; + } + } + + hiloop: for (;;) { + if (hi < lo) { + break outer; + } + if (entCol == NamedCharacters.NAMES[hi].length()) { + break hiloop; + } + if (entCol > NamedCharacters.NAMES[hi].length()) { + break outer; + } else if (c < NamedCharacters.NAMES[hi].charAt(entCol)) { + hi--; + } else { + break hiloop; + } + } + + if (c == ';') { + // If we see a semicolon, there cannot be a + // longer match. Break the loop. However, before + // breaking, take the longest match so far as the + // candidate, if we are just about to complete a + // match. + if (entCol + 1 == NamedCharacters.NAMES[lo].length()) { + candidate = lo; + charRefBufMark = charRefBufLen; + } + break outer; + } + + if (hi < lo) { + break outer; + } + appendCharRefBuf(c); + continue; + } + + if (candidate == -1) { + // reconsume deals with CR, LF or nul + if (c == ';') { + errNoNamedCharacterMatch(); + } + emitOrAppendCharRefBuf(returnState); + if ((returnState & DATA_AND_RCDATA_MASK) == 0) { + cstart = pos; + } + reconsume = true; + state = transition(state, returnState, reconsume, pos); + continue stateloop; + } else { + // c can't be CR, LF or nul if we got here + @Const @CharacterName String candidateName = NamedCharacters.NAMES[candidate]; + if (candidateName.length() == 0 + || candidateName.charAt(candidateName.length() - 1) != ';') { + /* + * If the last character matched is not a U+003B + * SEMICOLON (;), there is a parse error. + */ + if ((returnState & DATA_AND_RCDATA_MASK) != 0) { + /* + * If the entity is being consumed as part of an + * attribute, and the last character matched is + * not a U+003B SEMICOLON (;), + */ + char ch; + if (charRefBufMark == charRefBufLen) { + ch = c; + } else { + ch = charRefBuf[charRefBufMark]; + } + if (ch == '=' || (ch >= '0' && ch <= '9') + || (ch >= 'A' && ch <= 'Z') + || (ch >= 'a' && ch <= 'z')) { + /* + * and the next character is either a U+003D + * EQUALS SIGN character (=) or in the range + * U+0030 DIGIT ZERO to U+0039 DIGIT NINE, + * U+0041 LATIN CAPITAL LETTER A to U+005A + * LATIN CAPITAL LETTER Z, or U+0061 LATIN + * SMALL LETTER A to U+007A LATIN SMALL + * LETTER Z, then, for historical reasons, + * all the characters that were matched + * after the U+0026 AMPERSAND (&) must be + * unconsumed, and nothing is returned. + */ + if (c == ';') { + errNoNamedCharacterMatch(); + } + appendCharRefBufToStrBuf(); + reconsume = true; + state = transition(state, returnState, reconsume, pos); + continue stateloop; + } + } + if ((returnState & DATA_AND_RCDATA_MASK) != 0) { + errUnescapedAmpersandInterpretedAsCharacterReference(); + } else { + errNotSemicolonTerminated(); + } + } + + /* + * Otherwise, return a character token for the character + * corresponding to the entity name (as given by the + * second column of the named character references + * table). + */ + // CPPONLY: completedNamedCharacterReference(); + @Const @NoLength char[] val = NamedCharacters.VALUES[candidate]; + if ( + // [NOCPP[ + val.length == 1 + // ]NOCPP] + // CPPONLY: val[1] == 0 + ) { + emitOrAppendOne(val, returnState); + } else { + emitOrAppendTwo(val, returnState); + } + // this is so complicated! + if (charRefBufMark < charRefBufLen) { + if ((returnState & DATA_AND_RCDATA_MASK) != 0) { + appendStrBuf(charRefBuf, charRefBufMark, + charRefBufLen - charRefBufMark); + } else { + tokenHandler.characters(charRefBuf, charRefBufMark, + charRefBufLen - charRefBufMark); + } + } + // charRefBufLen will be zeroed below! + + // Check if we broke out early with c being the last + // character that matched as opposed to being the + // first one that didn't match. In the case of an + // early break, the next run on text should start + // *after* the current character and the current + // character shouldn't be reconsumed. + boolean earlyBreak = (c == ';' && charRefBufMark == charRefBufLen); + charRefBufLen = 0; + if ((returnState & DATA_AND_RCDATA_MASK) == 0) { + cstart = earlyBreak ? pos + 1 : pos; + } + reconsume = !earlyBreak; + state = transition(state, returnState, reconsume, pos); + continue stateloop; + /* + * If the markup contains I'm ¬it; I tell you, the + * entity is parsed as "not", as in, I'm ¬it; I tell + * you. But if the markup was I'm ∉ I tell you, + * the entity would be parsed as "notin;", resulting in + * I'm ∉ I tell you. + */ + } + // no fallthrough, reordering opportunity + case CONSUME_NCR: + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + value = 0; + seenDigits = false; + /* + * The behavior further depends on the character after the + * U+0023 NUMBER SIGN: + */ + switch (c) { + case 'x': + case 'X': + + /* + * U+0078 LATIN SMALL LETTER X U+0058 LATIN CAPITAL + * LETTER X Consume the X. + * + * Follow the steps below, but using the range of + * characters U+0030 DIGIT ZERO through to U+0039 + * DIGIT NINE, U+0061 LATIN SMALL LETTER A through + * to U+0066 LATIN SMALL LETTER F, and U+0041 LATIN + * CAPITAL LETTER A, through to U+0046 LATIN CAPITAL + * LETTER F (in other words, 0-9, A-F, a-f). + * + * When it comes to interpreting the number, + * interpret it as a hexadecimal number. + */ + appendCharRefBuf(c); + state = transition(state, Tokenizer.HEX_NCR_LOOP, reconsume, pos); + continue stateloop; + default: + /* + * Anything else Follow the steps below, but using + * the range of characters U+0030 DIGIT ZERO through + * to U+0039 DIGIT NINE (i.e. just 0-9). + * + * When it comes to interpreting the number, + * interpret it as a decimal number. + */ + reconsume = true; + state = transition(state, Tokenizer.DECIMAL_NRC_LOOP, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break; + } + // CPPONLY: MOZ_FALLTHROUGH; + case DECIMAL_NRC_LOOP: + decimalloop: for (;;) { + if (reconsume) { + reconsume = false; + } else { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + } + /* + * Consume as many characters as match the range of + * characters given above. + */ + assert value >= 0: "value must not become negative."; + if (c >= '0' && c <= '9') { + seenDigits = true; + // Avoid overflow + if (value <= 0x10FFFF) { + value *= 10; + value += c - '0'; + } + continue; + } else if (c == ';') { + if (seenDigits) { + if ((returnState & DATA_AND_RCDATA_MASK) == 0) { + cstart = pos + 1; + } + state = transition(state, Tokenizer.HANDLE_NCR_VALUE, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break decimalloop; + } else { + errNoDigitsInNCR(); + appendCharRefBuf(';'); + emitOrAppendCharRefBuf(returnState); + if ((returnState & DATA_AND_RCDATA_MASK) == 0) { + cstart = pos + 1; + } + state = transition(state, returnState, reconsume, pos); + continue stateloop; + } + } else { + /* + * If no characters match the range, then don't + * consume any characters (and unconsume the U+0023 + * NUMBER SIGN character and, if appropriate, the X + * character). This is a parse error; nothing is + * returned. + * + * Otherwise, if the next character is a U+003B + * SEMICOLON, consume that too. If it isn't, there + * is a parse error. + */ + if (!seenDigits) { + errNoDigitsInNCR(); + emitOrAppendCharRefBuf(returnState); + if ((returnState & DATA_AND_RCDATA_MASK) == 0) { + cstart = pos; + } + reconsume = true; + state = transition(state, returnState, reconsume, pos); + continue stateloop; + } else { + errCharRefLacksSemicolon(); + if ((returnState & DATA_AND_RCDATA_MASK) == 0) { + cstart = pos; + } + reconsume = true; + state = transition(state, Tokenizer.HANDLE_NCR_VALUE, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break decimalloop; + } + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case HANDLE_NCR_VALUE: + // WARNING previous state sets reconsume + // We are not going to emit the contents of charRefBuf. + charRefBufLen = 0; + // XXX inline this case if the method size can take it + handleNcrValue(returnState); + state = transition(state, returnState, reconsume, pos); + continue stateloop; + // no fallthrough, reordering opportunity + case HEX_NCR_LOOP: + for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Consume as many characters as match the range of + * characters given above. + */ + assert value >= 0: "value must not become negative."; + if (c >= '0' && c <= '9') { + seenDigits = true; + // Avoid overflow + if (value <= 0x10FFFF) { + value *= 16; + value += c - '0'; + } + continue; + } else if (c >= 'A' && c <= 'F') { + seenDigits = true; + // Avoid overflow + if (value <= 0x10FFFF) { + value *= 16; + value += c - 'A' + 10; + } + continue; + } else if (c >= 'a' && c <= 'f') { + seenDigits = true; + // Avoid overflow + if (value <= 0x10FFFF) { + value *= 16; + value += c - 'a' + 10; + } + continue; + } else if (c == ';') { + if (seenDigits) { + if ((returnState & DATA_AND_RCDATA_MASK) == 0) { + cstart = pos + 1; + } + state = transition(state, Tokenizer.HANDLE_NCR_VALUE, reconsume, pos); + continue stateloop; + } else { + errNoDigitsInNCR(); + appendCharRefBuf(';'); + emitOrAppendCharRefBuf(returnState); + if ((returnState & DATA_AND_RCDATA_MASK) == 0) { + cstart = pos + 1; + } + state = transition(state, returnState, reconsume, pos); + continue stateloop; + } + } else { + /* + * If no characters match the range, then don't + * consume any characters (and unconsume the U+0023 + * NUMBER SIGN character and, if appropriate, the X + * character). This is a parse error; nothing is + * returned. + * + * Otherwise, if the next character is a U+003B + * SEMICOLON, consume that too. If it isn't, there + * is a parse error. + */ + if (!seenDigits) { + errNoDigitsInNCR(); + emitOrAppendCharRefBuf(returnState); + if ((returnState & DATA_AND_RCDATA_MASK) == 0) { + cstart = pos; + } + reconsume = true; + state = transition(state, returnState, reconsume, pos); + continue stateloop; + } else { + errCharRefLacksSemicolon(); + if ((returnState & DATA_AND_RCDATA_MASK) == 0) { + cstart = pos; + } + reconsume = true; + state = transition(state, Tokenizer.HANDLE_NCR_VALUE, reconsume, pos); + continue stateloop; + } + } + } + // no fallthrough, reordering opportunity + case PLAINTEXT: + plaintextloop: for (;;) { + if (reconsume) { + reconsume = false; + } else { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + } + switch (c) { + case '\u0000': + emitPlaintextReplacementCharacter(buf, pos); + continue; + case '\r': + emitCarriageReturn(buf, pos); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + default: + /* + * Anything else Emit the current input + * character as a character token. Stay in the + * RAWTEXT state. + */ + continue; + } + } + // no fallthrough, reordering opportunity + case CLOSE_TAG_OPEN: + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Otherwise, if the content model flag is set to the PCDATA + * state, or if the next few characters do match that tag + * name, consume the next input character: + */ + switch (c) { + case '>': + /* U+003E GREATER-THAN SIGN (>) Parse error. */ + errLtSlashGt(); + /* + * Switch to the data state. + */ + cstart = pos + 1; + state = transition(state, Tokenizer.DATA, reconsume, pos); + continue stateloop; + case '\r': + silentCarriageReturn(); + /* Anything else Parse error. */ + errGarbageAfterLtSlash(); + /* + * Switch to the bogus comment state. + */ + clearStrBufBeforeUse(); + appendStrBuf('\n'); + state = transition(state, Tokenizer.BOGUS_COMMENT, reconsume, pos); + break stateloop; + case '\n': + silentLineFeed(); + /* Anything else Parse error. */ + errGarbageAfterLtSlash(); + /* + * Switch to the bogus comment state. + */ + clearStrBufBeforeUse(); + appendStrBuf(c); + state = transition(state, Tokenizer.BOGUS_COMMENT, reconsume, pos); + continue stateloop; + case '\u0000': + c = '\uFFFD'; + // CPPONLY: MOZ_FALLTHROUGH; + default: + if (c >= 'A' && c <= 'Z') { + c += 0x20; + } + if (c >= 'a' && c <= 'z') { + /* + * U+0061 LATIN SMALL LETTER A through to U+007A + * LATIN SMALL LETTER Z Create a new end tag + * token, + */ + endTag = true; + /* + * set its tag name to the input character, + */ + clearStrBufBeforeUse(); + appendStrBuf(c); + containsHyphen = false; + /* + * then switch to the tag name state. (Don't + * emit the token yet; further details will be + * filled in before it is emitted.) + */ + state = transition(state, Tokenizer.TAG_NAME, reconsume, pos); + continue stateloop; + } else { + /* Anything else Parse error. */ + errGarbageAfterLtSlash(); + /* + * Switch to the bogus comment state. + */ + clearStrBufBeforeUse(); + appendStrBuf(c); + state = transition(state, Tokenizer.BOGUS_COMMENT, reconsume, pos); + continue stateloop; + } + } + // no fallthrough, reordering opportunity + case RCDATA: + rcdataloop: for (;;) { + if (reconsume) { + reconsume = false; + } else { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + } + switch (c) { + case '&': + /* + * U+0026 AMPERSAND (&) Switch to the character + * reference in RCDATA state. + */ + flushChars(buf, pos); + assert charRefBufLen == 0: "charRefBufLen not reset after previous use!"; + appendCharRefBuf(c); + setAdditionalAndRememberAmpersandLocation('\u0000'); + returnState = state; + state = transition(state, Tokenizer.CONSUME_CHARACTER_REFERENCE, reconsume, pos); + continue stateloop; + case '<': + /* + * U+003C LESS-THAN SIGN (<) Switch to the + * RCDATA less-than sign state. + */ + flushChars(buf, pos); + + returnState = state; + state = transition(state, Tokenizer.RAWTEXT_RCDATA_LESS_THAN_SIGN, reconsume, pos); + continue stateloop; + case '\u0000': + emitReplacementCharacter(buf, pos); + continue; + case '\r': + emitCarriageReturn(buf, pos); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + default: + /* + * Emit the current input character as a + * character token. Stay in the RCDATA state. + */ + continue; + } + } + // no fallthrough, reordering opportunity + case RAWTEXT: + rawtextloop: for (;;) { + if (reconsume) { + reconsume = false; + } else { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + } + switch (c) { + case '<': + /* + * U+003C LESS-THAN SIGN (<) Switch to the + * RAWTEXT less-than sign state. + */ + flushChars(buf, pos); + + returnState = state; + state = transition(state, Tokenizer.RAWTEXT_RCDATA_LESS_THAN_SIGN, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break rawtextloop; + case '\u0000': + emitReplacementCharacter(buf, pos); + continue; + case '\r': + emitCarriageReturn(buf, pos); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + default: + /* + * Emit the current input character as a + * character token. Stay in the RAWTEXT state. + */ + continue; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case RAWTEXT_RCDATA_LESS_THAN_SIGN: + rawtextrcdatalessthansignloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + switch (c) { + case '/': + /* + * U+002F SOLIDUS (/) Set the temporary buffer + * to the empty string. Switch to the script + * data end tag open state. + */ + index = 0; + clearStrBufBeforeUse(); + state = transition(state, Tokenizer.NON_DATA_END_TAG_NAME, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break rawtextrcdatalessthansignloop; + default: + /* + * Otherwise, emit a U+003C LESS-THAN SIGN + * character token + */ + tokenHandler.characters(Tokenizer.LT_GT, 0, 1); + /* + * and reconsume the current input character in + * the data state. + */ + cstart = pos; + reconsume = true; + state = transition(state, returnState, reconsume, pos); + continue stateloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case NON_DATA_END_TAG_NAME: + for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * ASSERT! when entering this state, set index to 0 and + * call clearStrBufBeforeUse(); Let's implement the above + * without lookahead. strBuf is the 'temporary buffer'. + */ + if (endTagExpectationAsArray == null) { + tokenHandler.characters(Tokenizer.LT_SOLIDUS, + 0, 2); + cstart = pos; + reconsume = true; + state = transition(state, returnState, reconsume, pos); + continue stateloop; + } else if (index < endTagExpectationAsArray.length) { + char e = endTagExpectationAsArray[index]; + char folded = c; + if (c >= 'A' && c <= 'Z') { + folded += 0x20; + } + if (folded != e) { + // [NOCPP[ + errHtml4LtSlashInRcdata(folded); + // ]NOCPP] + tokenHandler.characters(Tokenizer.LT_SOLIDUS, + 0, 2); + emitStrBuf(); + cstart = pos; + reconsume = true; + state = transition(state, returnState, reconsume, pos); + continue stateloop; + } + appendStrBuf(c); + index++; + continue; + } else { + endTag = true; + // XXX replace contentModelElement with different + // type + tagName = endTagExpectation; + switch (c) { + case '\r': + silentCarriageReturn(); + clearStrBufAfterUse(); // strBuf not used + state = transition(state, Tokenizer.BEFORE_ATTRIBUTE_NAME, reconsume, pos); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + case ' ': + case '\t': + case '\u000C': + /* + * U+0009 CHARACTER TABULATION U+000A LINE + * FEED (LF) U+000C FORM FEED (FF) U+0020 + * SPACE If the current end tag token is an + * appropriate end tag token, then switch to + * the before attribute name state. + */ + clearStrBufAfterUse(); // strBuf not used + state = transition(state, Tokenizer.BEFORE_ATTRIBUTE_NAME, reconsume, pos); + continue stateloop; + case '/': + /* + * U+002F SOLIDUS (/) If the current end tag + * token is an appropriate end tag token, + * then switch to the self-closing start tag + * state. + */ + clearStrBufAfterUse(); // strBuf not used + state = transition(state, Tokenizer.SELF_CLOSING_START_TAG, reconsume, pos); + continue stateloop; + case '>': + /* + * U+003E GREATER-THAN SIGN (>) If the + * current end tag token is an appropriate + * end tag token, then emit the current tag + * token and switch to the data state. + */ + clearStrBufAfterUse(); // strBuf not used + state = transition(state, emitCurrentTagToken(false, pos), reconsume, pos); + if (shouldSuspend) { + break stateloop; + } + continue stateloop; + default: + /* + * Emit a U+003C LESS-THAN SIGN character + * token, a U+002F SOLIDUS character token, + * a character token for each of the + * characters in the temporary buffer (in + * the order they were added to the buffer), + * and reconsume the current input character + * in the RAWTEXT state. + */ + // [NOCPP[ + errWarnLtSlashInRcdata(); + // ]NOCPP] + tokenHandler.characters( + Tokenizer.LT_SOLIDUS, 0, 2); + emitStrBuf(); + cstart = pos; // don't drop the + // character + reconsume = true; + state = transition(state, returnState, reconsume, pos); + continue stateloop; + } + } + } + // no fallthrough, reordering opportunity + // BEGIN HOTSPOT WORKAROUND + case BOGUS_COMMENT: + boguscommentloop: for (;;) { + if (reconsume) { + reconsume = false; + } else { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + } + /* + * Consume every character up to and including the first + * U+003E GREATER-THAN SIGN character (>) or the end of + * the file (EOF), whichever comes first. Emit a comment + * token whose data is the concatenation of all the + * characters starting from and including the character + * that caused the state machine to switch into the + * bogus comment state, up to and including the + * character immediately before the last consumed + * character (i.e. up to the character just before the + * U+003E or EOF character). (If the comment was started + * by the end of the file (EOF), the token is empty.) + * + * Switch to the data state. + * + * If the end of the file was reached, reconsume the EOF + * character. + */ + switch (c) { + case '>': + emitComment(0, pos); + state = transition(state, Tokenizer.DATA, reconsume, pos); + if (shouldSuspend) { + break stateloop; + } + continue stateloop; + case '-': + appendStrBuf(c); + state = transition(state, Tokenizer.BOGUS_COMMENT_HYPHEN, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break boguscommentloop; + case '\r': + appendStrBufCarriageReturn(); + break stateloop; + case '\n': + appendStrBufLineFeed(); + continue; + case '\u0000': + c = '\uFFFD'; + // CPPONLY: MOZ_FALLTHROUGH; + default: + appendStrBuf(c); + continue; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case BOGUS_COMMENT_HYPHEN: + boguscommenthyphenloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + switch (c) { + case '>': + // [NOCPP[ + maybeAppendSpaceToBogusComment(); + // ]NOCPP] + emitComment(0, pos); + state = transition(state, Tokenizer.DATA, reconsume, pos); + if (shouldSuspend) { + break stateloop; + } + continue stateloop; + case '-': + appendSecondHyphenToBogusComment(); + continue boguscommenthyphenloop; + case '\r': + appendStrBufCarriageReturn(); + state = transition(state, Tokenizer.BOGUS_COMMENT, reconsume, pos); + break stateloop; + case '\n': + appendStrBufLineFeed(); + state = transition(state, Tokenizer.BOGUS_COMMENT, reconsume, pos); + continue stateloop; + case '\u0000': + c = '\uFFFD'; + // CPPONLY: MOZ_FALLTHROUGH; + default: + appendStrBuf(c); + state = transition(state, Tokenizer.BOGUS_COMMENT, reconsume, pos); + continue stateloop; + } + } + // no fallthrough, reordering opportunity + case SCRIPT_DATA: + scriptdataloop: for (;;) { + if (reconsume) { + reconsume = false; + } else { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + } + switch (c) { + case '<': + /* + * U+003C LESS-THAN SIGN (<) Switch to the + * script data less-than sign state. + */ + flushChars(buf, pos); + returnState = state; + state = transition(state, Tokenizer.SCRIPT_DATA_LESS_THAN_SIGN, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break scriptdataloop; + case '\u0000': + emitReplacementCharacter(buf, pos); + continue; + case '\r': + emitCarriageReturn(buf, pos); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + default: + /* + * Anything else Emit the current input + * character as a character token. Stay in the + * script data state. + */ + continue; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case SCRIPT_DATA_LESS_THAN_SIGN: + scriptdatalessthansignloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + switch (c) { + case '/': + /* + * U+002F SOLIDUS (/) Set the temporary buffer + * to the empty string. Switch to the script + * data end tag open state. + */ + index = 0; + clearStrBufBeforeUse(); + state = transition(state, Tokenizer.NON_DATA_END_TAG_NAME, reconsume, pos); + continue stateloop; + case '!': + tokenHandler.characters(Tokenizer.LT_GT, 0, 1); + cstart = pos; + state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPE_START, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break scriptdatalessthansignloop; + default: + /* + * Otherwise, emit a U+003C LESS-THAN SIGN + * character token + */ + tokenHandler.characters(Tokenizer.LT_GT, 0, 1); + /* + * and reconsume the current input character in + * the data state. + */ + cstart = pos; + reconsume = true; + state = transition(state, Tokenizer.SCRIPT_DATA, reconsume, pos); + continue stateloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case SCRIPT_DATA_ESCAPE_START: + scriptdataescapestartloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Consume the next input character: + */ + switch (c) { + case '-': + /* + * U+002D HYPHEN-MINUS (-) Emit a U+002D + * HYPHEN-MINUS character token. Switch to the + * script data escape start dash state. + */ + state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPE_START_DASH, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break scriptdataescapestartloop; + default: + /* + * Anything else Reconsume the current input + * character in the script data state. + */ + reconsume = true; + state = transition(state, Tokenizer.SCRIPT_DATA, reconsume, pos); + continue stateloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case SCRIPT_DATA_ESCAPE_START_DASH: + scriptdataescapestartdashloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Consume the next input character: + */ + switch (c) { + case '-': + /* + * U+002D HYPHEN-MINUS (-) Emit a U+002D + * HYPHEN-MINUS character token. Switch to the + * script data escaped dash dash state. + */ + state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED_DASH_DASH, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break scriptdataescapestartdashloop; + default: + /* + * Anything else Reconsume the current input + * character in the script data state. + */ + reconsume = true; + state = transition(state, Tokenizer.SCRIPT_DATA, reconsume, pos); + continue stateloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case SCRIPT_DATA_ESCAPED_DASH_DASH: + scriptdataescapeddashdashloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Consume the next input character: + */ + switch (c) { + case '-': + /* + * U+002D HYPHEN-MINUS (-) Emit a U+002D + * HYPHEN-MINUS character token. Stay in the + * script data escaped dash dash state. + */ + continue; + case '<': + /* + * U+003C LESS-THAN SIGN (<) Switch to the + * script data escaped less-than sign state. + */ + flushChars(buf, pos); + state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED_LESS_THAN_SIGN, reconsume, pos); + continue stateloop; + case '>': + /* + * U+003E GREATER-THAN SIGN (>) Emit a U+003E + * GREATER-THAN SIGN character token. Switch to + * the script data state. + */ + state = transition(state, Tokenizer.SCRIPT_DATA, reconsume, pos); + continue stateloop; + case '\u0000': + emitReplacementCharacter(buf, pos); + state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED, reconsume, pos); + break scriptdataescapeddashdashloop; + case '\r': + emitCarriageReturn(buf, pos); + state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED, reconsume, pos); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + default: + /* + * Anything else Emit the current input + * character as a character token. Switch to the + * script data escaped state. + */ + state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break scriptdataescapeddashdashloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case SCRIPT_DATA_ESCAPED: + scriptdataescapedloop: for (;;) { + if (reconsume) { + reconsume = false; + } else { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + } + /* + * Consume the next input character: + */ + switch (c) { + case '-': + /* + * U+002D HYPHEN-MINUS (-) Emit a U+002D + * HYPHEN-MINUS character token. Switch to the + * script data escaped dash state. + */ + state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED_DASH, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break scriptdataescapedloop; + case '<': + /* + * U+003C LESS-THAN SIGN (<) Switch to the + * script data escaped less-than sign state. + */ + flushChars(buf, pos); + state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED_LESS_THAN_SIGN, reconsume, pos); + continue stateloop; + case '\u0000': + emitReplacementCharacter(buf, pos); + continue; + case '\r': + emitCarriageReturn(buf, pos); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + default: + /* + * Anything else Emit the current input + * character as a character token. Stay in the + * script data escaped state. + */ + continue; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case SCRIPT_DATA_ESCAPED_DASH: + scriptdataescapeddashloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Consume the next input character: + */ + switch (c) { + case '-': + /* + * U+002D HYPHEN-MINUS (-) Emit a U+002D + * HYPHEN-MINUS character token. Switch to the + * script data escaped dash dash state. + */ + state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED_DASH_DASH, reconsume, pos); + continue stateloop; + case '<': + /* + * U+003C LESS-THAN SIGN (<) Switch to the + * script data escaped less-than sign state. + */ + flushChars(buf, pos); + state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED_LESS_THAN_SIGN, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break scriptdataescapeddashloop; + case '\u0000': + emitReplacementCharacter(buf, pos); + state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED, reconsume, pos); + continue stateloop; + case '\r': + emitCarriageReturn(buf, pos); + state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED, reconsume, pos); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + default: + /* + * Anything else Emit the current input + * character as a character token. Switch to the + * script data escaped state. + */ + state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED, reconsume, pos); + continue stateloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case SCRIPT_DATA_ESCAPED_LESS_THAN_SIGN: + scriptdataescapedlessthanloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Consume the next input character: + */ + switch (c) { + case '/': + /* + * U+002F SOLIDUS (/) Set the temporary buffer + * to the empty string. Switch to the script + * data escaped end tag open state. + */ + index = 0; + clearStrBufBeforeUse(); + returnState = Tokenizer.SCRIPT_DATA_ESCAPED; + state = transition(state, Tokenizer.NON_DATA_END_TAG_NAME, reconsume, pos); + continue stateloop; + case 'S': + case 's': + /* + * U+0041 LATIN CAPITAL LETTER A through to + * U+005A LATIN CAPITAL LETTER Z Emit a U+003C + * LESS-THAN SIGN character token and the + * current input character as a character token. + */ + tokenHandler.characters(Tokenizer.LT_GT, 0, 1); + cstart = pos; + index = 1; + /* + * Set the temporary buffer to the empty string. + * Append the lowercase version of the current + * input character (add 0x0020 to the + * character's code point) to the temporary + * buffer. Switch to the script data double + * escape start state. + */ + state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPE_START, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break scriptdataescapedlessthanloop; + default: + /* + * Anything else Emit a U+003C LESS-THAN SIGN + * character token and reconsume the current + * input character in the script data escaped + * state. + */ + tokenHandler.characters(Tokenizer.LT_GT, 0, 1); + cstart = pos; + reconsume = true; + state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED, reconsume, pos); + continue stateloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case SCRIPT_DATA_DOUBLE_ESCAPE_START: + scriptdatadoubleescapestartloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + assert index > 0; + if (index < 6) { // SCRIPT_ARR.length + char folded = c; + if (c >= 'A' && c <= 'Z') { + folded += 0x20; + } + if (folded != Tokenizer.SCRIPT_ARR[index]) { + reconsume = true; + state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED, reconsume, pos); + continue stateloop; + } + index++; + continue; + } + switch (c) { + case '\r': + emitCarriageReturn(buf, pos); + state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPED, reconsume, pos); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + case ' ': + case '\t': + case '\u000C': + case '/': + case '>': + /* + * U+0009 CHARACTER TABULATION U+000A LINE FEED + * (LF) U+000C FORM FEED (FF) U+0020 SPACE + * U+002F SOLIDUS (/) U+003E GREATER-THAN SIGN + * (>) Emit the current input character as a + * character token. If the temporary buffer is + * the string "script", then switch to the + * script data double escaped state. + */ + state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPED, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break scriptdatadoubleescapestartloop; + default: + /* + * Anything else Reconsume the current input + * character in the script data escaped state. + */ + reconsume = true; + state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED, reconsume, pos); + continue stateloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case SCRIPT_DATA_DOUBLE_ESCAPED: + scriptdatadoubleescapedloop: for (;;) { + if (reconsume) { + reconsume = false; + } else { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + } + /* + * Consume the next input character: + */ + switch (c) { + case '-': + /* + * U+002D HYPHEN-MINUS (-) Emit a U+002D + * HYPHEN-MINUS character token. Switch to the + * script data double escaped dash state. + */ + state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPED_DASH, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break scriptdatadoubleescapedloop; + case '<': + /* + * U+003C LESS-THAN SIGN (<) Emit a U+003C + * LESS-THAN SIGN character token. Switch to the + * script data double escaped less-than sign + * state. + */ + state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPED_LESS_THAN_SIGN, reconsume, pos); + continue stateloop; + case '\u0000': + emitReplacementCharacter(buf, pos); + continue; + case '\r': + emitCarriageReturn(buf, pos); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + default: + /* + * Anything else Emit the current input + * character as a character token. Stay in the + * script data double escaped state. + */ + continue; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case SCRIPT_DATA_DOUBLE_ESCAPED_DASH: + scriptdatadoubleescapeddashloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Consume the next input character: + */ + switch (c) { + case '-': + /* + * U+002D HYPHEN-MINUS (-) Emit a U+002D + * HYPHEN-MINUS character token. Switch to the + * script data double escaped dash dash state. + */ + state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPED_DASH_DASH, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break scriptdatadoubleescapeddashloop; + case '<': + /* + * U+003C LESS-THAN SIGN (<) Emit a U+003C + * LESS-THAN SIGN character token. Switch to the + * script data double escaped less-than sign + * state. + */ + state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPED_LESS_THAN_SIGN, reconsume, pos); + continue stateloop; + case '\u0000': + emitReplacementCharacter(buf, pos); + state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPED, reconsume, pos); + continue stateloop; + case '\r': + emitCarriageReturn(buf, pos); + state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPED, reconsume, pos); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + default: + /* + * Anything else Emit the current input + * character as a character token. Switch to the + * script data double escaped state. + */ + state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPED, reconsume, pos); + continue stateloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case SCRIPT_DATA_DOUBLE_ESCAPED_DASH_DASH: + scriptdatadoubleescapeddashdashloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Consume the next input character: + */ + switch (c) { + case '-': + /* + * U+002D HYPHEN-MINUS (-) Emit a U+002D + * HYPHEN-MINUS character token. Stay in the + * script data double escaped dash dash state. + */ + continue; + case '<': + /* + * U+003C LESS-THAN SIGN (<) Emit a U+003C + * LESS-THAN SIGN character token. Switch to the + * script data double escaped less-than sign + * state. + */ + state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPED_LESS_THAN_SIGN, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break scriptdatadoubleescapeddashdashloop; + case '>': + /* + * U+003E GREATER-THAN SIGN (>) Emit a U+003E + * GREATER-THAN SIGN character token. Switch to + * the script data state. + */ + state = transition(state, Tokenizer.SCRIPT_DATA, reconsume, pos); + continue stateloop; + case '\u0000': + emitReplacementCharacter(buf, pos); + state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPED, reconsume, pos); + continue stateloop; + case '\r': + emitCarriageReturn(buf, pos); + state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPED, reconsume, pos); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + default: + /* + * Anything else Emit the current input + * character as a character token. Switch to the + * script data double escaped state. + */ + state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPED, reconsume, pos); + continue stateloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case SCRIPT_DATA_DOUBLE_ESCAPED_LESS_THAN_SIGN: + scriptdatadoubleescapedlessthanloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Consume the next input character: + */ + switch (c) { + case '/': + /* + * U+002F SOLIDUS (/) Emit a U+002F SOLIDUS + * character token. Set the temporary buffer to + * the empty string. Switch to the script data + * double escape end state. + */ + index = 0; + state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPE_END, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break scriptdatadoubleescapedlessthanloop; + default: + /* + * Anything else Reconsume the current input + * character in the script data double escaped + * state. + */ + reconsume = true; + state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPED, reconsume, pos); + continue stateloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case SCRIPT_DATA_DOUBLE_ESCAPE_END: + scriptdatadoubleescapeendloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + if (index < 6) { // SCRIPT_ARR.length + char folded = c; + if (c >= 'A' && c <= 'Z') { + folded += 0x20; + } + if (folded != Tokenizer.SCRIPT_ARR[index]) { + reconsume = true; + state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPED, reconsume, pos); + continue stateloop; + } + index++; + continue; + } + switch (c) { + case '\r': + emitCarriageReturn(buf, pos); + state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED, reconsume, pos); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + case ' ': + case '\t': + case '\u000C': + case '/': + case '>': + /* + * U+0009 CHARACTER TABULATION U+000A LINE FEED + * (LF) U+000C FORM FEED (FF) U+0020 SPACE + * U+002F SOLIDUS (/) U+003E GREATER-THAN SIGN + * (>) Emit the current input character as a + * character token. If the temporary buffer is + * the string "script", then switch to the + * script data escaped state. + */ + state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED, reconsume, pos); + continue stateloop; + default: + /* + * Reconsume the current input character in the + * script data double escaped state. + */ + reconsume = true; + state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPED, reconsume, pos); + continue stateloop; + } + } + // no fallthrough, reordering opportunity + case MARKUP_DECLARATION_OCTYPE: + markupdeclarationdoctypeloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + if (index < 6) { // OCTYPE.length + char folded = c; + if (c >= 'A' && c <= 'Z') { + folded += 0x20; + } + if (folded == Tokenizer.OCTYPE[index]) { + appendStrBuf(c); + } else { + errBogusComment(); + reconsume = true; + state = transition(state, Tokenizer.BOGUS_COMMENT, reconsume, pos); + continue stateloop; + } + index++; + continue; + } else { + reconsume = true; + state = transition(state, Tokenizer.DOCTYPE, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break markupdeclarationdoctypeloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case DOCTYPE: + doctypeloop: for (;;) { + if (reconsume) { + reconsume = false; + } else { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + } + initDoctypeFields(); + /* + * Consume the next input character: + */ + switch (c) { + case '\r': + silentCarriageReturn(); + state = transition(state, Tokenizer.BEFORE_DOCTYPE_NAME, reconsume, pos); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + case ' ': + case '\t': + case '\u000C': + /* + * U+0009 CHARACTER TABULATION U+000A LINE FEED + * (LF) U+000C FORM FEED (FF) U+0020 SPACE + * Switch to the before DOCTYPE name state. + */ + state = transition(state, Tokenizer.BEFORE_DOCTYPE_NAME, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break doctypeloop; + default: + /* + * Anything else Parse error. + */ + errMissingSpaceBeforeDoctypeName(); + /* + * Reconsume the current character in the before + * DOCTYPE name state. + */ + reconsume = true; + state = transition(state, Tokenizer.BEFORE_DOCTYPE_NAME, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break doctypeloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case BEFORE_DOCTYPE_NAME: + beforedoctypenameloop: for (;;) { + if (reconsume) { + reconsume = false; + } else { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + } + /* + * Consume the next input character: + */ + switch (c) { + case '\r': + silentCarriageReturn(); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + case ' ': + case '\t': + case '\u000C': + /* + * U+0009 CHARACTER TABULATION U+000A LINE FEED + * (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay + * in the before DOCTYPE name state. + */ + continue; + case '>': + /* + * U+003E GREATER-THAN SIGN (>) Parse error. + */ + errNamelessDoctype(); + /* + * Create a new DOCTYPE token. Set its + * force-quirks flag to on. + */ + forceQuirks = true; + /* + * Emit the token. + */ + emitDoctypeToken(pos); + /* + * Switch to the data state. + */ + state = transition(state, Tokenizer.DATA, reconsume, pos); + if (shouldSuspend) { + break stateloop; + } + continue stateloop; + case '\u0000': + c = '\uFFFD'; + // CPPONLY: MOZ_FALLTHROUGH; + default: + if (c >= 'A' && c <= 'Z') { + /* + * U+0041 LATIN CAPITAL LETTER A through to + * U+005A LATIN CAPITAL LETTER Z Create a + * new DOCTYPE token. Set the token's name + * to the lowercase version of the input + * character (add 0x0020 to the character's + * code point). + */ + c += 0x20; + } + /* Anything else Create a new DOCTYPE token. */ + /* + * Set the token's name name to the current + * input character. + */ + clearStrBufBeforeUse(); + appendStrBuf(c); + /* + * Switch to the DOCTYPE name state. + */ + state = transition(state, Tokenizer.DOCTYPE_NAME, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break beforedoctypenameloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case DOCTYPE_NAME: + doctypenameloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Consume the next input character: + */ + switch (c) { + case '\r': + silentCarriageReturn(); + strBufToDoctypeName(); + state = transition(state, Tokenizer.AFTER_DOCTYPE_NAME, reconsume, pos); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + case ' ': + case '\t': + case '\u000C': + /* + * U+0009 CHARACTER TABULATION U+000A LINE FEED + * (LF) U+000C FORM FEED (FF) U+0020 SPACE + * Switch to the after DOCTYPE name state. + */ + strBufToDoctypeName(); + state = transition(state, Tokenizer.AFTER_DOCTYPE_NAME, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break doctypenameloop; + case '>': + /* + * U+003E GREATER-THAN SIGN (>) Emit the current + * DOCTYPE token. + */ + strBufToDoctypeName(); + emitDoctypeToken(pos); + /* + * Switch to the data state. + */ + state = transition(state, Tokenizer.DATA, reconsume, pos); + if (shouldSuspend) { + break stateloop; + } + continue stateloop; + case '\u0000': + c = '\uFFFD'; + // CPPONLY: MOZ_FALLTHROUGH; + default: + /* + * U+0041 LATIN CAPITAL LETTER A through to + * U+005A LATIN CAPITAL LETTER Z Append the + * lowercase version of the input character (add + * 0x0020 to the character's code point) to the + * current DOCTYPE token's name. + */ + if (c >= 'A' && c <= 'Z') { + c += 0x0020; + } + /* + * Anything else Append the current input + * character to the current DOCTYPE token's + * name. + */ + appendStrBuf(c); + /* + * Stay in the DOCTYPE name state. + */ + continue; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case AFTER_DOCTYPE_NAME: + afterdoctypenameloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Consume the next input character: + */ + switch (c) { + case '\r': + silentCarriageReturn(); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + case ' ': + case '\t': + case '\u000C': + /* + * U+0009 CHARACTER TABULATION U+000A LINE FEED + * (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay + * in the after DOCTYPE name state. + */ + continue; + case '>': + /* + * U+003E GREATER-THAN SIGN (>) Emit the current + * DOCTYPE token. + */ + emitDoctypeToken(pos); + /* + * Switch to the data state. + */ + state = transition(state, Tokenizer.DATA, reconsume, pos); + if (shouldSuspend) { + break stateloop; + } + continue stateloop; + case 'p': + case 'P': + index = 0; + state = transition(state, Tokenizer.DOCTYPE_UBLIC, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break afterdoctypenameloop; + case 's': + case 'S': + index = 0; + state = transition(state, Tokenizer.DOCTYPE_YSTEM, reconsume, pos); + continue stateloop; + default: + /* + * Otherwise, this is the parse error. + */ + bogusDoctype(); + + /* + * Set the DOCTYPE token's force-quirks flag to + * on. + */ + // done by bogusDoctype(); + /* + * Switch to the bogus DOCTYPE state. + */ + state = transition(state, Tokenizer.BOGUS_DOCTYPE, reconsume, pos); + continue stateloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case DOCTYPE_UBLIC: + doctypeublicloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * If the six characters starting from the current input + * character are an ASCII case-insensitive match for the + * word "PUBLIC", then consume those characters and + * switch to the before DOCTYPE public identifier state. + */ + if (index < 5) { // UBLIC.length + char folded = c; + if (c >= 'A' && c <= 'Z') { + folded += 0x20; + } + if (folded != Tokenizer.UBLIC[index]) { + bogusDoctype(); + // forceQuirks = true; + reconsume = true; + state = transition(state, Tokenizer.BOGUS_DOCTYPE, reconsume, pos); + continue stateloop; + } + index++; + continue; + } else { + reconsume = true; + state = transition(state, Tokenizer.AFTER_DOCTYPE_PUBLIC_KEYWORD, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break doctypeublicloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case AFTER_DOCTYPE_PUBLIC_KEYWORD: + afterdoctypepublickeywordloop: for (;;) { + if (reconsume) { + reconsume = false; + } else { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + } + /* + * Consume the next input character: + */ + switch (c) { + case '\r': + silentCarriageReturn(); + state = transition(state, Tokenizer.BEFORE_DOCTYPE_PUBLIC_IDENTIFIER, reconsume, pos); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + case ' ': + case '\t': + case '\u000C': + /* + * U+0009 CHARACTER TABULATION U+000A LINE FEED + * (LF) U+000C FORM FEED (FF) U+0020 SPACE + * Switch to the before DOCTYPE public + * identifier state. + */ + state = transition(state, Tokenizer.BEFORE_DOCTYPE_PUBLIC_IDENTIFIER, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break afterdoctypepublickeywordloop; + case '"': + /* + * U+0022 QUOTATION MARK (") Parse Error. + */ + errNoSpaceBetweenDoctypePublicKeywordAndQuote(); + /* + * Set the DOCTYPE token's public identifier to + * the empty string (not missing), + */ + clearStrBufBeforeUse(); + /* + * then switch to the DOCTYPE public identifier + * (double-quoted) state. + */ + state = transition(state, Tokenizer.DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED, reconsume, pos); + continue stateloop; + case '\'': + /* + * U+0027 APOSTROPHE (') Parse Error. + */ + errNoSpaceBetweenDoctypePublicKeywordAndQuote(); + /* + * Set the DOCTYPE token's public identifier to + * the empty string (not missing), + */ + clearStrBufBeforeUse(); + /* + * then switch to the DOCTYPE public identifier + * (single-quoted) state. + */ + state = transition(state, Tokenizer.DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED, reconsume, pos); + continue stateloop; + case '>': + /* U+003E GREATER-THAN SIGN (>) Parse error. */ + errExpectedPublicId(); + /* + * Set the DOCTYPE token's force-quirks flag to + * on. + */ + forceQuirks = true; + /* + * Emit that DOCTYPE token. + */ + emitDoctypeToken(pos); + /* + * Switch to the data state. + */ + state = transition(state, Tokenizer.DATA, reconsume, pos); + if (shouldSuspend) { + break stateloop; + } + continue stateloop; + default: + bogusDoctype(); + /* + * Set the DOCTYPE token's force-quirks flag to + * on. + */ + // done by bogusDoctype(); + /* + * Switch to the bogus DOCTYPE state. + */ + state = transition(state, Tokenizer.BOGUS_DOCTYPE, reconsume, pos); + continue stateloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case BEFORE_DOCTYPE_PUBLIC_IDENTIFIER: + beforedoctypepublicidentifierloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Consume the next input character: + */ + switch (c) { + case '\r': + silentCarriageReturn(); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + case ' ': + case '\t': + case '\u000C': + /* + * U+0009 CHARACTER TABULATION U+000A LINE FEED + * (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay + * in the before DOCTYPE public identifier + * state. + */ + continue; + case '"': + /* + * U+0022 QUOTATION MARK (") Set the DOCTYPE + * token's public identifier to the empty string + * (not missing), + */ + clearStrBufBeforeUse(); + /* + * then switch to the DOCTYPE public identifier + * (double-quoted) state. + */ + state = transition(state, Tokenizer.DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break beforedoctypepublicidentifierloop; + case '\'': + /* + * U+0027 APOSTROPHE (') Set the DOCTYPE token's + * public identifier to the empty string (not + * missing), + */ + clearStrBufBeforeUse(); + /* + * then switch to the DOCTYPE public identifier + * (single-quoted) state. + */ + state = transition(state, Tokenizer.DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED, reconsume, pos); + continue stateloop; + case '>': + /* U+003E GREATER-THAN SIGN (>) Parse error. */ + errExpectedPublicId(); + /* + * Set the DOCTYPE token's force-quirks flag to + * on. + */ + forceQuirks = true; + /* + * Emit that DOCTYPE token. + */ + emitDoctypeToken(pos); + /* + * Switch to the data state. + */ + state = transition(state, Tokenizer.DATA, reconsume, pos); + if (shouldSuspend) { + break stateloop; + } + continue stateloop; + default: + bogusDoctype(); + /* + * Set the DOCTYPE token's force-quirks flag to + * on. + */ + // done by bogusDoctype(); + /* + * Switch to the bogus DOCTYPE state. + */ + state = transition(state, Tokenizer.BOGUS_DOCTYPE, reconsume, pos); + continue stateloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED: + doctypepublicidentifierdoublequotedloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Consume the next input character: + */ + switch (c) { + case '"': + /* + * U+0022 QUOTATION MARK (") Switch to the after + * DOCTYPE public identifier state. + */ + publicIdentifier = strBufToString(); + state = transition(state, Tokenizer.AFTER_DOCTYPE_PUBLIC_IDENTIFIER, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break doctypepublicidentifierdoublequotedloop; + case '>': + /* + * U+003E GREATER-THAN SIGN (>) Parse error. + */ + errGtInPublicId(); + /* + * Set the DOCTYPE token's force-quirks flag to + * on. + */ + forceQuirks = true; + /* + * Emit that DOCTYPE token. + */ + publicIdentifier = strBufToString(); + emitDoctypeToken(pos); + /* + * Switch to the data state. + */ + state = transition(state, Tokenizer.DATA, reconsume, pos); + if (shouldSuspend) { + break stateloop; + } + continue stateloop; + case '\r': + appendStrBufCarriageReturn(); + break stateloop; + case '\n': + appendStrBufLineFeed(); + continue; + case '\u0000': + c = '\uFFFD'; + // CPPONLY: MOZ_FALLTHROUGH; + default: + /* + * Anything else Append the current input + * character to the current DOCTYPE token's + * public identifier. + */ + appendStrBuf(c); + /* + * Stay in the DOCTYPE public identifier + * (double-quoted) state. + */ + continue; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case AFTER_DOCTYPE_PUBLIC_IDENTIFIER: + afterdoctypepublicidentifierloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Consume the next input character: + */ + switch (c) { + case '\r': + silentCarriageReturn(); + state = transition(state, Tokenizer.BETWEEN_DOCTYPE_PUBLIC_AND_SYSTEM_IDENTIFIERS, reconsume, pos); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + case ' ': + case '\t': + case '\u000C': + /* + * U+0009 CHARACTER TABULATION U+000A LINE FEED + * (LF) U+000C FORM FEED (FF) U+0020 SPACE + * Switch to the between DOCTYPE public and + * system identifiers state. + */ + state = transition(state, Tokenizer.BETWEEN_DOCTYPE_PUBLIC_AND_SYSTEM_IDENTIFIERS, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break afterdoctypepublicidentifierloop; + case '>': + /* + * U+003E GREATER-THAN SIGN (>) Emit the current + * DOCTYPE token. + */ + emitDoctypeToken(pos); + /* + * Switch to the data state. + */ + state = transition(state, Tokenizer.DATA, reconsume, pos); + if (shouldSuspend) { + break stateloop; + } + continue stateloop; + case '"': + /* + * U+0022 QUOTATION MARK (") Parse error. + */ + errNoSpaceBetweenPublicAndSystemIds(); + /* + * Set the DOCTYPE token's system identifier to + * the empty string (not missing), + */ + clearStrBufBeforeUse(); + /* + * then switch to the DOCTYPE system identifier + * (double-quoted) state. + */ + state = transition(state, Tokenizer.DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED, reconsume, pos); + continue stateloop; + case '\'': + /* + * U+0027 APOSTROPHE (') Parse error. + */ + errNoSpaceBetweenPublicAndSystemIds(); + /* + * Set the DOCTYPE token's system identifier to + * the empty string (not missing), + */ + clearStrBufBeforeUse(); + /* + * then switch to the DOCTYPE system identifier + * (single-quoted) state. + */ + state = transition(state, Tokenizer.DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED, reconsume, pos); + continue stateloop; + default: + bogusDoctype(); + /* + * Set the DOCTYPE token's force-quirks flag to + * on. + */ + // done by bogusDoctype(); + /* + * Switch to the bogus DOCTYPE state. + */ + state = transition(state, Tokenizer.BOGUS_DOCTYPE, reconsume, pos); + continue stateloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case BETWEEN_DOCTYPE_PUBLIC_AND_SYSTEM_IDENTIFIERS: + betweendoctypepublicandsystemidentifiersloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Consume the next input character: + */ + switch (c) { + case '\r': + silentCarriageReturn(); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + case ' ': + case '\t': + case '\u000C': + /* + * U+0009 CHARACTER TABULATION U+000A LINE FEED + * (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay + * in the between DOCTYPE public and system + * identifiers state. + */ + continue; + case '>': + /* + * U+003E GREATER-THAN SIGN (>) Emit the current + * DOCTYPE token. + */ + emitDoctypeToken(pos); + /* + * Switch to the data state. + */ + state = transition(state, Tokenizer.DATA, reconsume, pos); + if (shouldSuspend) { + break stateloop; + } + continue stateloop; + case '"': + /* + * U+0022 QUOTATION MARK (") Set the DOCTYPE + * token's system identifier to the empty string + * (not missing), + */ + clearStrBufBeforeUse(); + /* + * then switch to the DOCTYPE system identifier + * (double-quoted) state. + */ + state = transition(state, Tokenizer.DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break betweendoctypepublicandsystemidentifiersloop; + case '\'': + /* + * U+0027 APOSTROPHE (') Set the DOCTYPE token's + * system identifier to the empty string (not + * missing), + */ + clearStrBufBeforeUse(); + /* + * then switch to the DOCTYPE system identifier + * (single-quoted) state. + */ + state = transition(state, Tokenizer.DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED, reconsume, pos); + continue stateloop; + default: + bogusDoctype(); + /* + * Set the DOCTYPE token's force-quirks flag to + * on. + */ + // done by bogusDoctype(); + /* + * Switch to the bogus DOCTYPE state. + */ + state = transition(state, Tokenizer.BOGUS_DOCTYPE, reconsume, pos); + continue stateloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED: + doctypesystemidentifierdoublequotedloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Consume the next input character: + */ + switch (c) { + case '"': + /* + * U+0022 QUOTATION MARK (") Switch to the after + * DOCTYPE system identifier state. + */ + systemIdentifier = strBufToString(); + state = transition(state, Tokenizer.AFTER_DOCTYPE_SYSTEM_IDENTIFIER, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break doctypesystemidentifierdoublequotedloop; + case '>': + /* + * U+003E GREATER-THAN SIGN (>) Parse error. + */ + errGtInSystemId(); + /* + * Set the DOCTYPE token's force-quirks flag to + * on. + */ + forceQuirks = true; + /* + * Emit that DOCTYPE token. + */ + systemIdentifier = strBufToString(); + emitDoctypeToken(pos); + /* + * Switch to the data state. + */ + state = transition(state, Tokenizer.DATA, reconsume, pos); + if (shouldSuspend) { + break stateloop; + } + continue stateloop; + case '\r': + appendStrBufCarriageReturn(); + break stateloop; + case '\n': + appendStrBufLineFeed(); + continue; + case '\u0000': + c = '\uFFFD'; + // CPPONLY: MOZ_FALLTHROUGH; + default: + /* + * Anything else Append the current input + * character to the current DOCTYPE token's + * system identifier. + */ + appendStrBuf(c); + /* + * Stay in the DOCTYPE system identifier + * (double-quoted) state. + */ + continue; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case AFTER_DOCTYPE_SYSTEM_IDENTIFIER: + afterdoctypesystemidentifierloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Consume the next input character: + */ + switch (c) { + case '\r': + silentCarriageReturn(); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + case ' ': + case '\t': + case '\u000C': + /* + * U+0009 CHARACTER TABULATION U+000A LINE FEED + * (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay + * in the after DOCTYPE system identifier state. + */ + continue; + case '>': + /* + * U+003E GREATER-THAN SIGN (>) Emit the current + * DOCTYPE token. + */ + emitDoctypeToken(pos); + /* + * Switch to the data state. + */ + state = transition(state, Tokenizer.DATA, reconsume, pos); + if (shouldSuspend) { + break stateloop; + } + continue stateloop; + default: + /* + * Switch to the bogus DOCTYPE state. (This does + * not set the DOCTYPE token's force-quirks flag + * to on.) + */ + bogusDoctypeWithoutQuirks(); + state = transition(state, Tokenizer.BOGUS_DOCTYPE, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break afterdoctypesystemidentifierloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case BOGUS_DOCTYPE: + for (;;) { + if (reconsume) { + reconsume = false; + } else { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + } + /* + * Consume the next input character: + */ + switch (c) { + case '>': + /* + * U+003E GREATER-THAN SIGN (>) Emit that + * DOCTYPE token. + */ + emitDoctypeToken(pos); + /* + * Switch to the data state. + */ + state = transition(state, Tokenizer.DATA, reconsume, pos); + if (shouldSuspend) { + break stateloop; + } + continue stateloop; + case '\r': + silentCarriageReturn(); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + default: + /* + * Anything else Stay in the bogus DOCTYPE + * state. + */ + continue; + } + } + // no fallthrough, reordering opportunity + case DOCTYPE_YSTEM: + doctypeystemloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Otherwise, if the six characters starting from the + * current input character are an ASCII case-insensitive + * match for the word "SYSTEM", then consume those + * characters and switch to the before DOCTYPE system + * identifier state. + */ + if (index < 5) { // YSTEM.length + char folded = c; + if (c >= 'A' && c <= 'Z') { + folded += 0x20; + } + if (folded != Tokenizer.YSTEM[index]) { + bogusDoctype(); + reconsume = true; + state = transition(state, Tokenizer.BOGUS_DOCTYPE, reconsume, pos); + continue stateloop; + } + index++; + continue stateloop; + } else { + reconsume = true; + state = transition(state, Tokenizer.AFTER_DOCTYPE_SYSTEM_KEYWORD, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break doctypeystemloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case AFTER_DOCTYPE_SYSTEM_KEYWORD: + afterdoctypesystemkeywordloop: for (;;) { + if (reconsume) { + reconsume = false; + } else { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + } + /* + * Consume the next input character: + */ + switch (c) { + case '\r': + silentCarriageReturn(); + state = transition(state, Tokenizer.BEFORE_DOCTYPE_SYSTEM_IDENTIFIER, reconsume, pos); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + case ' ': + case '\t': + case '\u000C': + /* + * U+0009 CHARACTER TABULATION U+000A LINE FEED + * (LF) U+000C FORM FEED (FF) U+0020 SPACE + * Switch to the before DOCTYPE public + * identifier state. + */ + state = transition(state, Tokenizer.BEFORE_DOCTYPE_SYSTEM_IDENTIFIER, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break afterdoctypesystemkeywordloop; + case '"': + /* + * U+0022 QUOTATION MARK (") Parse Error. + */ + errNoSpaceBetweenDoctypeSystemKeywordAndQuote(); + /* + * Set the DOCTYPE token's system identifier to + * the empty string (not missing), + */ + clearStrBufBeforeUse(); + /* + * then switch to the DOCTYPE public identifier + * (double-quoted) state. + */ + state = transition(state, Tokenizer.DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED, reconsume, pos); + continue stateloop; + case '\'': + /* + * U+0027 APOSTROPHE (') Parse Error. + */ + errNoSpaceBetweenDoctypeSystemKeywordAndQuote(); + /* + * Set the DOCTYPE token's public identifier to + * the empty string (not missing), + */ + clearStrBufBeforeUse(); + /* + * then switch to the DOCTYPE public identifier + * (single-quoted) state. + */ + state = transition(state, Tokenizer.DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED, reconsume, pos); + continue stateloop; + case '>': + /* U+003E GREATER-THAN SIGN (>) Parse error. */ + errExpectedPublicId(); + /* + * Set the DOCTYPE token's force-quirks flag to + * on. + */ + forceQuirks = true; + /* + * Emit that DOCTYPE token. + */ + emitDoctypeToken(pos); + /* + * Switch to the data state. + */ + state = transition(state, Tokenizer.DATA, reconsume, pos); + if (shouldSuspend) { + break stateloop; + } + continue stateloop; + default: + bogusDoctype(); + /* + * Set the DOCTYPE token's force-quirks flag to + * on. + */ + // done by bogusDoctype(); + /* + * Switch to the bogus DOCTYPE state. + */ + state = transition(state, Tokenizer.BOGUS_DOCTYPE, reconsume, pos); + continue stateloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case BEFORE_DOCTYPE_SYSTEM_IDENTIFIER: + beforedoctypesystemidentifierloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Consume the next input character: + */ + switch (c) { + case '\r': + silentCarriageReturn(); + break stateloop; + case '\n': + silentLineFeed(); + // CPPONLY: MOZ_FALLTHROUGH; + case ' ': + case '\t': + case '\u000C': + /* + * U+0009 CHARACTER TABULATION U+000A LINE FEED + * (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay + * in the before DOCTYPE system identifier + * state. + */ + continue; + case '"': + /* + * U+0022 QUOTATION MARK (") Set the DOCTYPE + * token's system identifier to the empty string + * (not missing), + */ + clearStrBufBeforeUse(); + /* + * then switch to the DOCTYPE system identifier + * (double-quoted) state. + */ + state = transition(state, Tokenizer.DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED, reconsume, pos); + continue stateloop; + case '\'': + /* + * U+0027 APOSTROPHE (') Set the DOCTYPE token's + * system identifier to the empty string (not + * missing), + */ + clearStrBufBeforeUse(); + /* + * then switch to the DOCTYPE system identifier + * (single-quoted) state. + */ + state = transition(state, Tokenizer.DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED, reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break beforedoctypesystemidentifierloop; + case '>': + /* U+003E GREATER-THAN SIGN (>) Parse error. */ + errExpectedSystemId(); + /* + * Set the DOCTYPE token's force-quirks flag to + * on. + */ + forceQuirks = true; + /* + * Emit that DOCTYPE token. + */ + emitDoctypeToken(pos); + /* + * Switch to the data state. + */ + state = transition(state, Tokenizer.DATA, reconsume, pos); + if (shouldSuspend) { + break stateloop; + } + continue stateloop; + default: + bogusDoctype(); + /* + * Set the DOCTYPE token's force-quirks flag to + * on. + */ + // done by bogusDoctype(); + /* + * Switch to the bogus DOCTYPE state. + */ + state = transition(state, Tokenizer.BOGUS_DOCTYPE, reconsume, pos); + continue stateloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED: + for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Consume the next input character: + */ + switch (c) { + case '\'': + /* + * U+0027 APOSTROPHE (') Switch to the after + * DOCTYPE system identifier state. + */ + systemIdentifier = strBufToString(); + state = transition(state, Tokenizer.AFTER_DOCTYPE_SYSTEM_IDENTIFIER, reconsume, pos); + continue stateloop; + case '>': + errGtInSystemId(); + /* + * Set the DOCTYPE token's force-quirks flag to + * on. + */ + forceQuirks = true; + /* + * Emit that DOCTYPE token. + */ + systemIdentifier = strBufToString(); + emitDoctypeToken(pos); + /* + * Switch to the data state. + */ + state = transition(state, Tokenizer.DATA, reconsume, pos); + if (shouldSuspend) { + break stateloop; + } + continue stateloop; + case '\r': + appendStrBufCarriageReturn(); + break stateloop; + case '\n': + appendStrBufLineFeed(); + continue; + case '\u0000': + c = '\uFFFD'; + // CPPONLY: MOZ_FALLTHROUGH; + default: + /* + * Anything else Append the current input + * character to the current DOCTYPE token's + * system identifier. + */ + appendStrBuf(c); + /* + * Stay in the DOCTYPE system identifier + * (double-quoted) state. + */ + continue; + } + } + // no fallthrough, reordering opportunity + case DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED: + for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + /* + * Consume the next input character: + */ + switch (c) { + case '\'': + /* + * U+0027 APOSTROPHE (') Switch to the after + * DOCTYPE public identifier state. + */ + publicIdentifier = strBufToString(); + state = transition(state, Tokenizer.AFTER_DOCTYPE_PUBLIC_IDENTIFIER, reconsume, pos); + continue stateloop; + case '>': + errGtInPublicId(); + /* + * Set the DOCTYPE token's force-quirks flag to + * on. + */ + forceQuirks = true; + /* + * Emit that DOCTYPE token. + */ + publicIdentifier = strBufToString(); + emitDoctypeToken(pos); + /* + * Switch to the data state. + */ + state = transition(state, Tokenizer.DATA, reconsume, pos); + if (shouldSuspend) { + break stateloop; + } + continue stateloop; + case '\r': + appendStrBufCarriageReturn(); + break stateloop; + case '\n': + appendStrBufLineFeed(); + continue; + case '\u0000': + c = '\uFFFD'; + // CPPONLY: MOZ_FALLTHROUGH; + default: + /* + * Anything else Append the current input + * character to the current DOCTYPE token's + * public identifier. + */ + appendStrBuf(c); + /* + * Stay in the DOCTYPE public identifier + * (single-quoted) state. + */ + continue; + } + } + // no fallthrough, reordering opportunity + case PROCESSING_INSTRUCTION: + processinginstructionloop: for (;;) { + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + switch (c) { + case '?': + state = transition( + state, + Tokenizer.PROCESSING_INSTRUCTION_QUESTION_MARK, + reconsume, pos); + // `break` optimizes; `continue stateloop;` would be valid + break processinginstructionloop; + default: + continue; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case PROCESSING_INSTRUCTION_QUESTION_MARK: + if (++pos == endPos) { + break stateloop; + } + c = checkChar(buf, pos); + switch (c) { + case '>': + state = transition(state, Tokenizer.DATA, + reconsume, pos); + // Processing instruction syntax goes through these + // states only in Gecko's XML View Source--not in HTML + // parsing in Java or in Gecko. + // Since XML View Source doesn't use the + // suspension-after-current-token facility, its extension + // to processing-instruction states is strictly unnecessary + // at the moment. However, if these states ever were to be + // used together with the suspension-after-current-token + // facility, these states would need to participate, since + // suspension could be requested when only less-than has been + // seen and we don't yet know if we end up here. Handling + // the currently-unnecessary case in order to avoid leaving + // a trap for future modification. + suspendIfRequestedAfterCurrentNonTextToken(); + if (shouldSuspend) { + break stateloop; + } + continue stateloop; + default: + state = transition(state, + Tokenizer.PROCESSING_INSTRUCTION, + reconsume, pos); + continue stateloop; + } + // END HOTSPOT WORKAROUND + } + } + flushChars(buf, pos); + /* + * if (prevCR && pos != endPos) { // why is this needed? pos--; col--; } + */ + // Save locals + stateSave = state; + returnStateSave = returnState; + return pos; + } + + // HOTSPOT WORKAROUND INSERTION POINT + + // [NOCPP[ + + protected int transition(int from, int to, boolean reconsume, int pos) throws SAXException { + return to; + } + + // ]NOCPP] + + private void initDoctypeFields() { + // Discard the characters "DOCTYPE" accumulated as a potential bogus + // comment into strBuf. + clearStrBufAfterUse(); + doctypeName = null; + if (systemIdentifier != null) { + Portability.releaseString(systemIdentifier); + systemIdentifier = null; + } + if (publicIdentifier != null) { + Portability.releaseString(publicIdentifier); + publicIdentifier = null; + } + forceQuirks = false; + } + + @Inline private void adjustDoubleHyphenAndAppendToStrBufCarriageReturn() + throws SAXException { + silentCarriageReturn(); + adjustDoubleHyphenAndAppendToStrBufAndErr('\n', false); + } + + @Inline private void adjustDoubleHyphenAndAppendToStrBufLineFeed() + throws SAXException { + silentLineFeed(); + adjustDoubleHyphenAndAppendToStrBufAndErr('\n', false); + } + + @Inline private void appendStrBufLineFeed() { + silentLineFeed(); + appendStrBuf('\n'); + } + + @Inline private void appendStrBufCarriageReturn() { + silentCarriageReturn(); + appendStrBuf('\n'); + } + + // [NOCPP[ + + @Inline protected void silentCarriageReturn() { + ++line; + lastCR = true; + } + + @Inline protected void silentLineFeed() { + ++line; + } + + // ]NOCPP] + + private void emitCarriageReturn(@NoLength char[] buf, int pos) + throws SAXException { + silentCarriageReturn(); + flushChars(buf, pos); + tokenHandler.characters(Tokenizer.LF, 0, 1); + cstart = Integer.MAX_VALUE; + } + + private void emitReplacementCharacter(@NoLength char[] buf, int pos) + throws SAXException { + flushChars(buf, pos); + tokenHandler.zeroOriginatingReplacementCharacter(); + cstart = pos + 1; + } + + private void maybeEmitReplacementCharacter(@NoLength char[] buf, int pos) + throws SAXException { + flushChars(buf, pos); + tokenHandler.zeroOrReplacementCharacter(); + cstart = pos + 1; + } + + private void emitPlaintextReplacementCharacter(@NoLength char[] buf, int pos) + throws SAXException { + flushChars(buf, pos); + tokenHandler.characters(REPLACEMENT_CHARACTER, 0, 1); + cstart = pos + 1; + } + + private void setAdditionalAndRememberAmpersandLocation(char add) { + additional = add; + // [NOCPP[ + ampersandLocation = new LocatorImpl(this); + // ]NOCPP] + } + + private void bogusDoctype() throws SAXException { + errBogusDoctype(); + forceQuirks = true; + } + + private void bogusDoctypeWithoutQuirks() throws SAXException { + errBogusDoctype(); + forceQuirks = false; + } + + private void handleNcrValue(int returnState) throws SAXException { + /* + * If one or more characters match the range, then take them all and + * interpret the string of characters as a number (either hexadecimal or + * decimal as appropriate). + */ + if (value <= 0xFFFF) { + if (value >= 0x80 && value <= 0x9f) { + /* + * If that number is one of the numbers in the first column of + * the following table, then this is a parse error. + */ + errNcrInC1Range(); + /* + * Find the row with that number in the first column, and return + * a character token for the Unicode character given in the + * second column of that row. + */ + @NoLength char[] val = NamedCharacters.WINDOWS_1252[value - 0x80]; + emitOrAppendOne(val, returnState); + // [NOCPP[ + } else if (value == 0xC + && contentSpacePolicy != XmlViolationPolicy.ALLOW) { + if (contentSpacePolicy == XmlViolationPolicy.ALTER_INFOSET) { + emitOrAppendOne(Tokenizer.SPACE, returnState); + } else if (contentSpacePolicy == XmlViolationPolicy.FATAL) { + fatal("A character reference expanded to a form feed which is not legal XML 1.0 white space."); + } + // ]NOCPP] + } else if (value == 0x0) { + errNcrZero(); + emitOrAppendOne(Tokenizer.REPLACEMENT_CHARACTER, returnState); + } else if ((value & 0xF800) == 0xD800) { + errNcrSurrogate(); + emitOrAppendOne(Tokenizer.REPLACEMENT_CHARACTER, returnState); + } else { + /* + * Otherwise, return a character token for the Unicode character + * whose code point is that number. + */ + char ch = (char) value; + // [NOCPP[ + if (value == 0x0D) { + errNcrCr(); + } else if ((value <= 0x0008) || (value == 0x000B) + || (value >= 0x000E && value <= 0x001F)) { + ch = errNcrControlChar(ch); + } else if (value >= 0xFDD0 && value <= 0xFDEF) { + errNcrUnassigned(); + } else if ((value & 0xFFFE) == 0xFFFE) { + ch = errNcrNonCharacter(ch); + } else if (value >= 0x007F && value <= 0x009F) { + errNcrControlChar(); + } else { + maybeWarnPrivateUse(ch); + } + // ]NOCPP] + bmpChar[0] = ch; + emitOrAppendOne(bmpChar, returnState); + } + } else if (value <= 0x10FFFF) { + // [NOCPP[ + maybeWarnPrivateUseAstral(); + if ((value & 0xFFFE) == 0xFFFE) { + errAstralNonCharacter(value); + } + // ]NOCPP] + astralChar[0] = (char) (Tokenizer.LEAD_OFFSET + (value >> 10)); + astralChar[1] = (char) (0xDC00 + (value & 0x3FF)); + emitOrAppendTwo(astralChar, returnState); + } else { + errNcrOutOfRange(); + emitOrAppendOne(Tokenizer.REPLACEMENT_CHARACTER, returnState); + } + } + + public void eof() throws SAXException { + int state = stateSave; + int returnState = returnStateSave; + + eofloop: for (;;) { + switch (state) { + case SCRIPT_DATA_LESS_THAN_SIGN: + case SCRIPT_DATA_ESCAPED_LESS_THAN_SIGN: + /* + * Otherwise, emit a U+003C LESS-THAN SIGN character token + */ + tokenHandler.characters(Tokenizer.LT_GT, 0, 1); + /* + * and reconsume the current input character in the data + * state. + */ + break eofloop; + case TAG_OPEN: + /* + * The behavior of this state depends on the content model + * flag. + */ + /* + * Anything else Parse error. + */ + errEofAfterLt(); + /* + * Emit a U+003C LESS-THAN SIGN character token + */ + tokenHandler.characters(Tokenizer.LT_GT, 0, 1); + /* + * and reconsume the current input character in the data + * state. + */ + break eofloop; + case RAWTEXT_RCDATA_LESS_THAN_SIGN: + /* + * Emit a U+003C LESS-THAN SIGN character token + */ + tokenHandler.characters(Tokenizer.LT_GT, 0, 1); + /* + * and reconsume the current input character in the RCDATA + * state. + */ + break eofloop; + case NON_DATA_END_TAG_NAME: + /* + * Emit a U+003C LESS-THAN SIGN character token, a U+002F + * SOLIDUS character token, + */ + tokenHandler.characters(Tokenizer.LT_SOLIDUS, 0, 2); + /* + * a character token for each of the characters in the + * temporary buffer (in the order they were added to the + * buffer), + */ + emitStrBuf(); + /* + * and reconsume the current input character in the RCDATA + * state. + */ + break eofloop; + case CLOSE_TAG_OPEN: + /* EOF Parse error. */ + errEofAfterLt(); + /* + * Emit a U+003C LESS-THAN SIGN character token and a U+002F + * SOLIDUS character token. + */ + tokenHandler.characters(Tokenizer.LT_SOLIDUS, 0, 2); + /* + * Reconsume the EOF character in the data state. + */ + break eofloop; + case TAG_NAME: + /* + * EOF Parse error. + */ + errEofInTagName(); + /* + * Reconsume the EOF character in the data state. + */ + break eofloop; + case BEFORE_ATTRIBUTE_NAME: + case AFTER_ATTRIBUTE_VALUE_QUOTED: + case SELF_CLOSING_START_TAG: + /* EOF Parse error. */ + errEofWithoutGt(); + /* + * Reconsume the EOF character in the data state. + */ + break eofloop; + case ATTRIBUTE_NAME: + /* + * EOF Parse error. + */ + errEofInAttributeName(); + /* + * Reconsume the EOF character in the data state. + */ + break eofloop; + case AFTER_ATTRIBUTE_NAME: + case BEFORE_ATTRIBUTE_VALUE: + /* EOF Parse error. */ + errEofWithoutGt(); + /* + * Reconsume the EOF character in the data state. + */ + break eofloop; + case ATTRIBUTE_VALUE_DOUBLE_QUOTED: + case ATTRIBUTE_VALUE_SINGLE_QUOTED: + case ATTRIBUTE_VALUE_UNQUOTED: + /* EOF Parse error. */ + errEofInAttributeValue(); + /* + * Reconsume the EOF character in the data state. + */ + break eofloop; + case BOGUS_COMMENT: + emitComment(0, 0); + break eofloop; + case BOGUS_COMMENT_HYPHEN: + // [NOCPP[ + maybeAppendSpaceToBogusComment(); + // ]NOCPP] + emitComment(0, 0); + break eofloop; + case MARKUP_DECLARATION_OPEN: + errBogusComment(); + emitComment(0, 0); + break eofloop; + case MARKUP_DECLARATION_HYPHEN: + errBogusComment(); + emitComment(0, 0); + break eofloop; + case MARKUP_DECLARATION_OCTYPE: + if (index < 6) { + errBogusComment(); + emitComment(0, 0); + } else { + /* EOF Parse error. */ + errEofInDoctype(); + /* + * Create a new DOCTYPE token. Set its force-quirks flag + * to on. + */ + doctypeName = null; + if (systemIdentifier != null) { + Portability.releaseString(systemIdentifier); + systemIdentifier = null; + } + if (publicIdentifier != null) { + Portability.releaseString(publicIdentifier); + publicIdentifier = null; + } + forceQuirks = true; + /* + * Emit the token. + */ + emitDoctypeToken(0); + /* + * Reconsume the EOF character in the data state. + */ + break eofloop; + } + break eofloop; + case COMMENT_START: + case COMMENT: + case COMMENT_LESSTHAN: + case COMMENT_LESSTHAN_BANG: + /* + * EOF Parse error. + */ + errEofInComment(); + /* Emit the comment token. */ + emitComment(0, 0); + /* + * Reconsume the EOF character in the data state. + */ + break eofloop; + case COMMENT_END: + case COMMENT_LESSTHAN_BANG_DASH_DASH: + errEofInComment(); + /* Emit the comment token. */ + emitComment(2, 0); + /* + * Reconsume the EOF character in the data state. + */ + break eofloop; + case COMMENT_END_DASH: + case COMMENT_START_DASH: + case COMMENT_LESSTHAN_BANG_DASH: + errEofInComment(); + /* Emit the comment token. */ + emitComment(1, 0); + /* + * Reconsume the EOF character in the data state. + */ + break eofloop; + case COMMENT_END_BANG: + errEofInComment(); + /* Emit the comment token. */ + emitComment(3, 0); + /* + * Reconsume the EOF character in the data state. + */ + break eofloop; + case DOCTYPE: + case BEFORE_DOCTYPE_NAME: + errEofInDoctype(); + /* + * Create a new DOCTYPE token. Set its force-quirks flag to + * on. + */ + forceQuirks = true; + /* + * Emit the token. + */ + emitDoctypeToken(0); + /* + * Reconsume the EOF character in the data state. + */ + break eofloop; + case DOCTYPE_NAME: + errEofInDoctype(); + strBufToDoctypeName(); + /* + * Set the DOCTYPE token's force-quirks flag to on. + */ + forceQuirks = true; + /* + * Emit that DOCTYPE token. + */ + emitDoctypeToken(0); + /* + * Reconsume the EOF character in the data state. + */ + break eofloop; + case DOCTYPE_UBLIC: + case DOCTYPE_YSTEM: + case AFTER_DOCTYPE_NAME: + case AFTER_DOCTYPE_PUBLIC_KEYWORD: + case AFTER_DOCTYPE_SYSTEM_KEYWORD: + case BEFORE_DOCTYPE_PUBLIC_IDENTIFIER: + errEofInDoctype(); + /* + * Set the DOCTYPE token's force-quirks flag to on. + */ + forceQuirks = true; + /* + * Emit that DOCTYPE token. + */ + emitDoctypeToken(0); + /* + * Reconsume the EOF character in the data state. + */ + break eofloop; + case DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED: + case DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED: + /* EOF Parse error. */ + errEofInPublicId(); + /* + * Set the DOCTYPE token's force-quirks flag to on. + */ + forceQuirks = true; + /* + * Emit that DOCTYPE token. + */ + publicIdentifier = strBufToString(); + emitDoctypeToken(0); + /* + * Reconsume the EOF character in the data state. + */ + break eofloop; + case AFTER_DOCTYPE_PUBLIC_IDENTIFIER: + case BEFORE_DOCTYPE_SYSTEM_IDENTIFIER: + case BETWEEN_DOCTYPE_PUBLIC_AND_SYSTEM_IDENTIFIERS: + errEofInDoctype(); + /* + * Set the DOCTYPE token's force-quirks flag to on. + */ + forceQuirks = true; + /* + * Emit that DOCTYPE token. + */ + emitDoctypeToken(0); + /* + * Reconsume the EOF character in the data state. + */ + break eofloop; + case DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED: + case DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED: + /* EOF Parse error. */ + errEofInSystemId(); + /* + * Set the DOCTYPE token's force-quirks flag to on. + */ + forceQuirks = true; + /* + * Emit that DOCTYPE token. + */ + systemIdentifier = strBufToString(); + emitDoctypeToken(0); + /* + * Reconsume the EOF character in the data state. + */ + break eofloop; + case AFTER_DOCTYPE_SYSTEM_IDENTIFIER: + errEofInDoctype(); + /* + * Set the DOCTYPE token's force-quirks flag to on. + */ + forceQuirks = true; + /* + * Emit that DOCTYPE token. + */ + emitDoctypeToken(0); + /* + * Reconsume the EOF character in the data state. + */ + break eofloop; + case BOGUS_DOCTYPE: + /* + * Emit that DOCTYPE token. + */ + emitDoctypeToken(0); + /* + * Reconsume the EOF character in the data state. + */ + break eofloop; + case CONSUME_CHARACTER_REFERENCE: + /* + * Unlike the definition is the spec, this state does not + * return a value and never requires the caller to + * backtrack. This state takes care of emitting characters + * or appending to the current attribute value. It also + * takes care of that in the case when consuming the entity + * fails. + */ + /* + * This section defines how to consume an entity. This + * definition is used when parsing entities in text and in + * attributes. + * + * The behavior depends on the identity of the next + * character (the one immediately after the U+0026 AMPERSAND + * character): + */ + + emitOrAppendCharRefBuf(returnState); + state = returnState; + continue; + case CHARACTER_REFERENCE_HILO_LOOKUP: + emitOrAppendCharRefBuf(returnState); + state = returnState; + continue; + case CHARACTER_REFERENCE_TAIL: + outer: for (;;) { + char c = '\u0000'; + entCol++; + /* + * Consume the maximum number of characters possible, + * with the consumed characters matching one of the + * identifiers in the first column of the named + * character references table (in a case-sensitive + * manner). + */ + hiloop: for (;;) { + if (hi == -1) { + break hiloop; + } + if (entCol == NamedCharacters.NAMES[hi].length()) { + break hiloop; + } + if (entCol > NamedCharacters.NAMES[hi].length()) { + break outer; + } else if (c < NamedCharacters.NAMES[hi].charAt(entCol)) { + hi--; + } else { + break hiloop; + } + } + + loloop: for (;;) { + if (hi < lo) { + break outer; + } + if (entCol == NamedCharacters.NAMES[lo].length()) { + candidate = lo; + charRefBufMark = charRefBufLen; + lo++; + } else if (entCol > NamedCharacters.NAMES[lo].length()) { + break outer; + } else if (c > NamedCharacters.NAMES[lo].charAt(entCol)) { + lo++; + } else { + break loloop; + } + } + if (hi < lo) { + break outer; + } + continue; + } + + if (candidate == -1) { + emitOrAppendCharRefBuf(returnState); + state = returnState; + continue eofloop; + } else { + @Const @CharacterName String candidateName = NamedCharacters.NAMES[candidate]; + if (candidateName.length() == 0 + || candidateName.charAt(candidateName.length() - 1) != ';') { + /* + * If the last character matched is not a U+003B + * SEMICOLON (;), there is a parse error. + */ + if ((returnState & DATA_AND_RCDATA_MASK) != 0) { + /* + * If the entity is being consumed as part of an + * attribute, and the last character matched is + * not a U+003B SEMICOLON (;), + */ + char ch; + if (charRefBufMark == charRefBufLen) { + ch = '\u0000'; + } else { + ch = charRefBuf[charRefBufMark]; + } + if ((ch >= '0' && ch <= '9') + || (ch >= 'A' && ch <= 'Z') + || (ch >= 'a' && ch <= 'z')) { + /* + * and the next character is in the range + * U+0030 DIGIT ZERO to U+0039 DIGIT NINE, + * U+0041 LATIN CAPITAL LETTER A to U+005A + * LATIN CAPITAL LETTER Z, or U+0061 LATIN + * SMALL LETTER A to U+007A LATIN SMALL + * LETTER Z, then, for historical reasons, + * all the characters that were matched + * after the U+0026 AMPERSAND (&) must be + * unconsumed, and nothing is returned. + */ + appendCharRefBufToStrBuf(); + state = returnState; + continue eofloop; + } + } + if ((returnState & DATA_AND_RCDATA_MASK) != 0) { + errUnescapedAmpersandInterpretedAsCharacterReference(); + } else { + errNotSemicolonTerminated(); + } + } + + /* + * Otherwise, return a character token for the character + * corresponding to the entity name (as given by the + * second column of the named character references + * table). + */ + @Const @NoLength char[] val = NamedCharacters.VALUES[candidate]; + if ( + // [NOCPP[ + val.length == 1 + // ]NOCPP] + // CPPONLY: val[1] == 0 + ) { + emitOrAppendOne(val, returnState); + } else { + emitOrAppendTwo(val, returnState); + } + // this is so complicated! + if (charRefBufMark < charRefBufLen) { + if ((returnState & DATA_AND_RCDATA_MASK) != 0) { + appendStrBuf(charRefBuf, charRefBufMark, + charRefBufLen - charRefBufMark); + } else { + tokenHandler.characters(charRefBuf, charRefBufMark, + charRefBufLen - charRefBufMark); + } + } + charRefBufLen = 0; + state = returnState; + continue eofloop; + /* + * If the markup contains I'm ¬it; I tell you, the + * entity is parsed as "not", as in, I'm ¬it; I tell + * you. But if the markup was I'm ∉ I tell you, + * the entity would be parsed as "notin;", resulting in + * I'm ∉ I tell you. + */ + } + case CONSUME_NCR: + case DECIMAL_NRC_LOOP: + case HEX_NCR_LOOP: + /* + * If no characters match the range, then don't consume any + * characters (and unconsume the U+0023 NUMBER SIGN + * character and, if appropriate, the X character). This is + * a parse error; nothing is returned. + * + * Otherwise, if the next character is a U+003B SEMICOLON, + * consume that too. If it isn't, there is a parse error. + */ + if (!seenDigits) { + errNoDigitsInNCR(); + emitOrAppendCharRefBuf(returnState); + state = returnState; + continue; + } else { + errCharRefLacksSemicolon(); + } + // WARNING previous state sets reconsume + handleNcrValue(returnState); + state = returnState; + continue; + case CDATA_RSQB: + tokenHandler.characters(Tokenizer.RSQB_RSQB, 0, 1); + break eofloop; + case CDATA_RSQB_RSQB: + tokenHandler.characters(Tokenizer.RSQB_RSQB, 0, 2); + break eofloop; + case DATA: + default: + break eofloop; + } + } + // case DATA: + /* + * EOF Emit an end-of-file token. + */ + tokenHandler.eof(); + return; + } + + /** + * Emits a doctype token. + * + * NOTE: The method may set <code>shouldSuspend</code>, so the caller + * must have this pattern after the state's <code>transition</code> call: + * <pre> + * if (shouldSuspend) { + * break stateloop; + * } + * continue stateloop; + * </pre> + * + * @param pos + * @throws SAXException + */ + private void emitDoctypeToken(int pos) throws SAXException { + // CPPONLY: RememberGt(pos); + cstart = pos + 1; + tokenHandler.doctype(doctypeName, publicIdentifier, systemIdentifier, + forceQuirks); + // It is OK and sufficient to release these here, since + // there's no way out of the doctype states than through paths + // that call this method. + doctypeName = null; + Portability.releaseString(publicIdentifier); + publicIdentifier = null; + Portability.releaseString(systemIdentifier); + systemIdentifier = null; + suspendIfRequestedAfterCurrentNonTextToken(); + } + + /** + * If a previous call to <code>suspendAfterCurrentTokenIfNotInText()</code> + * happened in a non-text context, this method turns that deferred suspension + * request into an immediately-pending suspension request. + */ + private void suspendIfRequestedAfterCurrentNonTextToken() { + if (suspendAfterCurrentNonTextToken) { + suspendAfterCurrentNonTextToken = false; + shouldSuspend = true; + } + } + + // Making this private until the full Java implementation is done. + /** + * Request suspension after the current token if the tokenizer is currently + * in a non-text state (i.e. it's known that the next token will be a + * non-text token). + * + * Must not be called when <code>tokenizeBuffer()</code> is on the call + * stack. + */ + @SuppressWarnings("unused") private void suspendAfterCurrentTokenIfNotInText() { + switch (stateSave) { + case DATA: + case RCDATA: + case SCRIPT_DATA: + case RAWTEXT: + case SCRIPT_DATA_ESCAPED: + case PLAINTEXT: + case NON_DATA_END_TAG_NAME: // We haven't yet committed to the next + // token being a non-text token, though + // it could be. + case SCRIPT_DATA_LESS_THAN_SIGN: + case SCRIPT_DATA_ESCAPE_START: + case SCRIPT_DATA_ESCAPE_START_DASH: + case SCRIPT_DATA_ESCAPED_DASH: + case SCRIPT_DATA_ESCAPED_DASH_DASH: + case RAWTEXT_RCDATA_LESS_THAN_SIGN: + case SCRIPT_DATA_ESCAPED_LESS_THAN_SIGN: + case SCRIPT_DATA_DOUBLE_ESCAPE_START: + case SCRIPT_DATA_DOUBLE_ESCAPED: + case SCRIPT_DATA_DOUBLE_ESCAPED_LESS_THAN_SIGN: + case SCRIPT_DATA_DOUBLE_ESCAPED_DASH: + case SCRIPT_DATA_DOUBLE_ESCAPED_DASH_DASH: + case SCRIPT_DATA_DOUBLE_ESCAPE_END: + return; + case TAG_NAME: + case BEFORE_ATTRIBUTE_NAME: + case ATTRIBUTE_NAME: + case AFTER_ATTRIBUTE_NAME: + case BEFORE_ATTRIBUTE_VALUE: + case AFTER_ATTRIBUTE_VALUE_QUOTED: + case BOGUS_COMMENT: + case MARKUP_DECLARATION_OPEN: + case DOCTYPE: + case BEFORE_DOCTYPE_NAME: + case DOCTYPE_NAME: + case AFTER_DOCTYPE_NAME: + case BEFORE_DOCTYPE_PUBLIC_IDENTIFIER: + case DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED: + case DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED: + case AFTER_DOCTYPE_PUBLIC_IDENTIFIER: + case BEFORE_DOCTYPE_SYSTEM_IDENTIFIER: + case DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED: + case DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED: + case AFTER_DOCTYPE_SYSTEM_IDENTIFIER: + case BOGUS_DOCTYPE: + case COMMENT_START: + case COMMENT_START_DASH: + case COMMENT: + case COMMENT_END_DASH: + case COMMENT_END: + case COMMENT_END_BANG: + case TAG_OPEN: + case CLOSE_TAG_OPEN: + case MARKUP_DECLARATION_HYPHEN: + case MARKUP_DECLARATION_OCTYPE: + case DOCTYPE_UBLIC: + case DOCTYPE_YSTEM: + case AFTER_DOCTYPE_PUBLIC_KEYWORD: + case BETWEEN_DOCTYPE_PUBLIC_AND_SYSTEM_IDENTIFIERS: + case AFTER_DOCTYPE_SYSTEM_KEYWORD: + case SELF_CLOSING_START_TAG: + case ATTRIBUTE_VALUE_DOUBLE_QUOTED: + case ATTRIBUTE_VALUE_SINGLE_QUOTED: + case ATTRIBUTE_VALUE_UNQUOTED: + case BOGUS_COMMENT_HYPHEN: + case COMMENT_LESSTHAN: + case COMMENT_LESSTHAN_BANG: + case COMMENT_LESSTHAN_BANG_DASH: + case COMMENT_LESSTHAN_BANG_DASH_DASH: + case CDATA_START: + case CDATA_SECTION: + case CDATA_RSQB: + case CDATA_RSQB_RSQB: + case PROCESSING_INSTRUCTION: + case PROCESSING_INSTRUCTION_QUESTION_MARK: + break; + case CONSUME_CHARACTER_REFERENCE: + case CONSUME_NCR: + case CHARACTER_REFERENCE_TAIL: + case HEX_NCR_LOOP: + case DECIMAL_NRC_LOOP: + case HANDLE_NCR_VALUE: + case HANDLE_NCR_VALUE_RECONSUME: + case CHARACTER_REFERENCE_HILO_LOOKUP: + if (returnStateSave == DATA || returnStateSave == RCDATA) { + return; + } + break; + default: + assert false : "Incomplete switch"; + return; + } + suspendAfterCurrentNonTextToken = true; + } + + // Making this private until the full Java implementation is done. + /** + * Queries if we are about to suspend after the current non-text token due to a request + * from <code>suspendAfterCurrentTokenIfNotInText()</code>. + * @return <code>true</code> iff <code>suspendAfterCurrentTokenIfNotInText()</code> was + * called in a non-text position and the then-current token has not been emitted yet. + */ + @SuppressWarnings("unused") private boolean suspensionAfterCurrentNonTextTokenPending() { + return suspendAfterCurrentNonTextToken; + } + + // [NOCPP[ + + @Inline protected char checkChar(@NoLength char[] buf, int pos) + throws SAXException { + return buf[pos]; + } + + // ]NOCPP] + + public boolean internalEncodingDeclaration(String internalCharset) + throws SAXException { + if (encodingDeclarationHandler != null) { + return encodingDeclarationHandler.internalEncodingDeclaration(internalCharset); + } + return false; + } + + /** + * @param val + * @throws SAXException + */ + private void emitOrAppendTwo(@Const @NoLength char[] val, int returnState) + throws SAXException { + if ((returnState & DATA_AND_RCDATA_MASK) != 0) { + appendStrBuf(val[0]); + appendStrBuf(val[1]); + } else { + tokenHandler.characters(val, 0, 2); + } + } + + private void emitOrAppendOne(@Const @NoLength char[] val, int returnState) + throws SAXException { + if ((returnState & DATA_AND_RCDATA_MASK) != 0) { + appendStrBuf(val[0]); + } else { + tokenHandler.characters(val, 0, 1); + } + } + + public void end() throws SAXException { + strBuf = null; + doctypeName = null; + if (systemIdentifier != null) { + Portability.releaseString(systemIdentifier); + systemIdentifier = null; + } + if (publicIdentifier != null) { + Portability.releaseString(publicIdentifier); + publicIdentifier = null; + } + tagName = null; + nonInternedTagName.setNameForNonInterned(null + // CPPONLY: , false + ); + attributeName = null; + // CPPONLY: nonInternedAttributeName.setNameForNonInterned(null); + tokenHandler.endTokenization(); + if (attributes != null) { + // [NOCPP[ + attributes = null; + // ]NOCPP] + // CPPONLY: attributes.clear(mappingLangToXmlLang); + } + } + + public void requestSuspension() { + shouldSuspend = true; + } + + // [NOCPP[ + + public void becomeConfident() { + confident = true; + } + + /** + * Returns the nextCharOnNewLine. + * + * @return the nextCharOnNewLine + */ + public boolean isNextCharOnNewLine() { + return false; + } + + public boolean isPrevCR() { + return lastCR; + } + + /** + * Returns the line. + * + * @return the line + */ + public int getLine() { + return -1; + } + + /** + * Returns the col. + * + * @return the col + */ + public int getCol() { + return -1; + } + + // ]NOCPP] + + public boolean isInDataState() { + return (stateSave == DATA); + } + + public void resetToDataState() { + clearStrBufAfterUse(); + charRefBufLen = 0; + stateSave = Tokenizer.DATA; + // line = 1; XXX line numbers + lastCR = false; + index = 0; + forceQuirks = false; + additional = '\u0000'; + entCol = -1; + firstCharKey = -1; + lo = 0; + hi = 0; // will always be overwritten before use anyway + candidate = -1; + charRefBufMark = 0; + value = 0; + seenDigits = false; + suspendAfterCurrentNonTextToken = false; + endTag = false; + shouldSuspend = false; + initDoctypeFields(); + containsHyphen = false; + tagName = null; + attributeName = null; + if (newAttributesEachTime) { + if (attributes != null) { + Portability.delete(attributes); + attributes = null; + } + } + } + + public void loadState(Tokenizer other) throws SAXException { + strBufLen = other.strBufLen; + if (strBufLen > strBuf.length) { + strBuf = new char[strBufLen]; + } + System.arraycopy(other.strBuf, 0, strBuf, 0, strBufLen); + + charRefBufLen = other.charRefBufLen; + System.arraycopy(other.charRefBuf, 0, charRefBuf, 0, charRefBufLen); + + stateSave = other.stateSave; + returnStateSave = other.returnStateSave; + endTagExpectation = other.endTagExpectation; + endTagExpectationAsArray = other.endTagExpectationAsArray; + // line = 1; XXX line numbers + lastCR = other.lastCR; + index = other.index; + forceQuirks = other.forceQuirks; + additional = other.additional; + entCol = other.entCol; + firstCharKey = other.firstCharKey; + lo = other.lo; + hi = other.hi; + candidate = other.candidate; + charRefBufMark = other.charRefBufMark; + value = other.value; + seenDigits = other.seenDigits; + endTag = other.endTag; + shouldSuspend = false; + suspendAfterCurrentNonTextToken = false; + doctypeName = other.doctypeName; + + Portability.releaseString(systemIdentifier); + if (other.systemIdentifier == null) { + systemIdentifier = null; + } else { + systemIdentifier = Portability.newStringFromString(other.systemIdentifier); + } + + Portability.releaseString(publicIdentifier); + if (other.publicIdentifier == null) { + publicIdentifier = null; + } else { + publicIdentifier = Portability.newStringFromString(other.publicIdentifier); + } + + containsHyphen = other.containsHyphen; + if (other.tagName == null) { + tagName = null; + } else if (other.tagName.isInterned()) { + tagName = other.tagName; + } else { + // In the C++ case, the atoms in the other tokenizer are from a + // different tokenizer-scoped atom table. Therefore, we have to + // obtain the correspoding atom from our own atom table. + nonInternedTagName.setNameForNonInterned(other.tagName.getName() + // CPPONLY: , other.tagName.isCustom() + ); + tagName = nonInternedTagName; + } + + // [NOCPP[ + attributeName = other.attributeName; + // ]NOCPP] + // CPPONLY: if (other.attributeName == null) { + // CPPONLY: attributeName = null; + // CPPONLY: } else if (other.attributeName.isInterned()) { + // CPPONLY: attributeName = other.attributeName; + // CPPONLY: } else { + // CPPONLY: // In the C++ case, the atoms in the other tokenizer are from a + // CPPONLY: // different tokenizer-scoped atom table. Therefore, we have to + // CPPONLY: // obtain the correspoding atom from our own atom table. + // CPPONLY: nonInternedAttributeName.setNameForNonInterned(other.attributeName.getLocal(AttributeName.HTML)); + // CPPONLY: attributeName = nonInternedAttributeName; + // CPPONLY: } + + Portability.delete(attributes); + if (other.attributes == null) { + attributes = null; + } else { + attributes = other.attributes.cloneAttributes(); + } + } + + public void initializeWithoutStarting() throws SAXException { + confident = false; + strBuf = null; + line = 1; + // CPPONLY: attributeLine = 1; + // [NOCPP[ + metaBoundaryPassed = false; + wantsComments = tokenHandler.wantsComments(); + if (!newAttributesEachTime) { + attributes = new HtmlAttributes(mappingLangToXmlLang); + } + // ]NOCPP] + resetToDataState(); + } + + protected void errGarbageAfterLtSlash() throws SAXException { + } + + protected void errLtSlashGt() throws SAXException { + } + + protected void errWarnLtSlashInRcdata() throws SAXException { + } + + protected void errHtml4LtSlashInRcdata(char folded) throws SAXException { + } + + protected void errCharRefLacksSemicolon() throws SAXException { + } + + protected void errNoDigitsInNCR() throws SAXException { + } + + protected void errGtInSystemId() throws SAXException { + } + + protected void errGtInPublicId() throws SAXException { + } + + protected void errNamelessDoctype() throws SAXException { + } + + protected void errNestedComment() throws SAXException { + } + + protected void errPrematureEndOfComment() throws SAXException { + } + + protected void errBogusComment() throws SAXException { + } + + protected void errUnquotedAttributeValOrNull(char c) throws SAXException { + } + + protected void errSlashNotFollowedByGt() throws SAXException { + } + + protected void errNoSpaceBetweenAttributes() throws SAXException { + } + + protected void errLtOrEqualsOrGraveInUnquotedAttributeOrNull(char c) + throws SAXException { + } + + protected void errAttributeValueMissing() throws SAXException { + } + + protected void errBadCharBeforeAttributeNameOrNull(char c) + throws SAXException { + } + + protected void errEqualsSignBeforeAttributeName() throws SAXException { + } + + protected void errBadCharAfterLt(char c) throws SAXException { + } + + protected void errLtGt() throws SAXException { + } + + protected void errProcessingInstruction() throws SAXException { + } + + protected void errUnescapedAmpersandInterpretedAsCharacterReference() + throws SAXException { + } + + protected void errNotSemicolonTerminated() throws SAXException { + } + + protected void errNoNamedCharacterMatch() throws SAXException { + } + + protected void errQuoteBeforeAttributeName(char c) throws SAXException { + } + + protected void errQuoteOrLtInAttributeNameOrNull(char c) + throws SAXException { + } + + protected void errExpectedPublicId() throws SAXException { + } + + protected void errBogusDoctype() throws SAXException { + } + + protected void maybeWarnPrivateUseAstral() throws SAXException { + } + + protected void maybeWarnPrivateUse(char ch) throws SAXException { + } + + protected void maybeErrAttributesOnEndTag(HtmlAttributes attrs) + throws SAXException { + } + + protected void maybeErrSlashInEndTag(boolean selfClosing) + throws SAXException { + } + + protected char errNcrNonCharacter(char ch) throws SAXException { + return ch; + } + + protected void errAstralNonCharacter(int ch) throws SAXException { + } + + protected void errNcrSurrogate() throws SAXException { + } + + protected char errNcrControlChar(char ch) throws SAXException { + return ch; + } + + protected void errNcrCr() throws SAXException { + } + + protected void errNcrInC1Range() throws SAXException { + } + + protected void errEofInPublicId() throws SAXException { + } + + protected void errEofInComment() throws SAXException { + } + + protected void errEofInDoctype() throws SAXException { + } + + protected void errEofInAttributeValue() throws SAXException { + } + + protected void errEofInAttributeName() throws SAXException { + } + + protected void errEofWithoutGt() throws SAXException { + } + + protected void errEofInTagName() throws SAXException { + } + + protected void errEofInEndTag() throws SAXException { + } + + protected void errEofAfterLt() throws SAXException { + } + + protected void errNcrOutOfRange() throws SAXException { + } + + protected void errNcrUnassigned() throws SAXException { + } + + protected void errDuplicateAttribute() throws SAXException { + } + + protected void errEofInSystemId() throws SAXException { + } + + protected void errExpectedSystemId() throws SAXException { + } + + protected void errMissingSpaceBeforeDoctypeName() throws SAXException { + } + + protected void errNcrControlChar() throws SAXException { + } + + protected void errNcrZero() throws SAXException { + } + + protected void errNoSpaceBetweenDoctypeSystemKeywordAndQuote() + throws SAXException { + } + + protected void errNoSpaceBetweenPublicAndSystemIds() throws SAXException { + } + + protected void errNoSpaceBetweenDoctypePublicKeywordAndQuote() + throws SAXException { + } + + protected void noteAttributeWithoutValue() throws SAXException { + } + + protected void noteUnquotedAttributeValue() throws SAXException { + } + + /** + * Sets the encodingDeclarationHandler. + * + * @param encodingDeclarationHandler + * the encodingDeclarationHandler to set + */ + public void setEncodingDeclarationHandler( + EncodingDeclarationHandler encodingDeclarationHandler) { + this.encodingDeclarationHandler = encodingDeclarationHandler; + } + + void destructor() { + Portability.delete(nonInternedTagName); + nonInternedTagName = null; + // CPPONLY: Portability.delete(nonInternedAttributeName); + // CPPONLY: nonInternedAttributeName = null; + // The translator will write refcount tracing stuff here + Portability.delete(attributes); + attributes = null; + } + + // [NOCPP[ + + /** + * Sets an offset to be added to the position reported to + * <code>TransitionHandler</code>. + * + * @param offset the offset + */ + public void setTransitionBaseOffset(int offset) { + + } + + // ]NOCPP] + +} diff --git a/parser/html/javasrc/TreeBuilder.java b/parser/html/javasrc/TreeBuilder.java new file mode 100644 index 0000000000..1f437bf744 --- /dev/null +++ b/parser/html/javasrc/TreeBuilder.java @@ -0,0 +1,6550 @@ +/* + * Copyright (c) 2007 Henri Sivonen + * Copyright (c) 2007-2017 Mozilla Foundation + * Portions of comments Copyright 2004-2008 Apple Computer, Inc., Mozilla + * Foundation, and Opera Software ASA. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + */ + +/* + * The comments following this one that use the same comment syntax as this + * comment are quotes from the WHATWG HTML 5 spec as of 27 June 2007 + * amended as of June 28 2007. + * That document came with this statement: + * "© Copyright 2004-2007 Apple Computer, Inc., Mozilla Foundation, and + * Opera Software ASA. You are granted a license to use, reproduce and + * create derivative works of this document." + */ + +package nu.validator.htmlparser.impl; + +import java.util.Arrays; +import java.util.HashMap; +import java.util.Map; + +import org.xml.sax.ErrorHandler; +import org.xml.sax.Locator; +import org.xml.sax.SAXException; +import org.xml.sax.SAXParseException; + +import nu.validator.htmlparser.annotation.Auto; +import nu.validator.htmlparser.annotation.Const; +import nu.validator.htmlparser.annotation.IdType; +import nu.validator.htmlparser.annotation.Inline; +import nu.validator.htmlparser.annotation.Literal; +import nu.validator.htmlparser.annotation.Local; +import nu.validator.htmlparser.annotation.NoLength; +import nu.validator.htmlparser.annotation.NsUri; +import nu.validator.htmlparser.common.DocumentMode; +import nu.validator.htmlparser.common.DocumentModeHandler; +import nu.validator.htmlparser.common.Interner; +import nu.validator.htmlparser.common.TokenHandler; +import nu.validator.htmlparser.common.XmlViolationPolicy; + +public abstract class TreeBuilder<T> implements TokenHandler, + TreeBuilderState<T> { + + /** + * Array version of U+FFFD. + */ + private static final @NoLength char[] REPLACEMENT_CHARACTER = { '\uFFFD' }; + + // Start dispatch groups + + final static int OTHER = 0; + + final static int A = 1; + + final static int BASE = 2; + + final static int BODY = 3; + + final static int BR = 4; + + final static int BUTTON = 5; + + final static int CAPTION = 6; + + final static int COL = 7; + + final static int COLGROUP = 8; + + final static int FORM = 9; + + final static int FRAME = 10; + + final static int FRAMESET = 11; + + final static int IMAGE = 12; + + final static int INPUT = 13; + + final static int RT_OR_RP = 14; + + final static int LI = 15; + + final static int LINK_OR_BASEFONT_OR_BGSOUND = 16; + + final static int MATH = 17; + + final static int META = 18; + + final static int SVG = 19; + + final static int HEAD = 20; + + final static int HR = 22; + + final static int HTML = 23; + + final static int NOBR = 24; + + final static int NOFRAMES = 25; + + final static int NOSCRIPT = 26; + + final static int OPTGROUP = 27; + + final static int OPTION = 28; + + final static int P = 29; + + final static int PLAINTEXT = 30; + + final static int SCRIPT = 31; + + final static int SELECT = 32; + + final static int STYLE = 33; + + final static int TABLE = 34; + + final static int TEXTAREA = 35; + + final static int TITLE = 36; + + final static int TR = 37; + + final static int XMP = 38; + + final static int TBODY_OR_THEAD_OR_TFOOT = 39; + + final static int TD_OR_TH = 40; + + final static int DD_OR_DT = 41; + + final static int H1_OR_H2_OR_H3_OR_H4_OR_H5_OR_H6 = 42; + + final static int MARQUEE_OR_APPLET = 43; + + final static int PRE_OR_LISTING = 44; + + final static int B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U = 45; + + final static int UL_OR_OL_OR_DL = 46; + + final static int IFRAME = 47; + + final static int EMBED = 48; + + final static int AREA_OR_WBR = 49; + + final static int DIV_OR_BLOCKQUOTE_OR_CENTER_OR_MENU = 50; + + final static int ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY = 51; + + final static int RUBY_OR_SPAN_OR_SUB_OR_SUP_OR_VAR = 52; + + final static int RB_OR_RTC = 53; + + final static int PARAM_OR_SOURCE_OR_TRACK = 55; + + final static int MGLYPH_OR_MALIGNMARK = 56; + + final static int MI_MO_MN_MS_MTEXT = 57; + + final static int ANNOTATION_XML = 58; + + final static int FOREIGNOBJECT_OR_DESC = 59; + + final static int NOEMBED = 60; + + final static int FIELDSET = 61; + + final static int OUTPUT = 62; + + final static int OBJECT = 63; + + final static int FONT = 64; + + final static int KEYGEN = 65; + + final static int TEMPLATE = 66; + + final static int IMG = 67; + + // start insertion modes + + private static final int IN_ROW = 0; + + private static final int IN_TABLE_BODY = 1; + + private static final int IN_TABLE = 2; + + private static final int IN_CAPTION = 3; + + private static final int IN_CELL = 4; + + private static final int FRAMESET_OK = 5; + + private static final int IN_BODY = 6; + + private static final int IN_HEAD = 7; + + private static final int IN_HEAD_NOSCRIPT = 8; + + // no fall-through + + private static final int IN_COLUMN_GROUP = 9; + + // no fall-through + + private static final int IN_SELECT_IN_TABLE = 10; + + private static final int IN_SELECT = 11; + + // no fall-through + + private static final int AFTER_BODY = 12; + + // no fall-through + + private static final int IN_FRAMESET = 13; + + private static final int AFTER_FRAMESET = 14; + + // no fall-through + + private static final int INITIAL = 15; + + // could add fall-through + + private static final int BEFORE_HTML = 16; + + // could add fall-through + + private static final int BEFORE_HEAD = 17; + + // no fall-through + + private static final int AFTER_HEAD = 18; + + // no fall-through + + private static final int AFTER_AFTER_BODY = 19; + + // no fall-through + + private static final int AFTER_AFTER_FRAMESET = 20; + + // no fall-through + + private static final int TEXT = 21; + + private static final int IN_TEMPLATE = 22; + + // start charset states + + private static final int CHARSET_INITIAL = 0; + + private static final int CHARSET_C = 1; + + private static final int CHARSET_H = 2; + + private static final int CHARSET_A = 3; + + private static final int CHARSET_R = 4; + + private static final int CHARSET_S = 5; + + private static final int CHARSET_E = 6; + + private static final int CHARSET_T = 7; + + private static final int CHARSET_EQUALS = 8; + + private static final int CHARSET_SINGLE_QUOTED = 9; + + private static final int CHARSET_DOUBLE_QUOTED = 10; + + private static final int CHARSET_UNQUOTED = 11; + + // end pseudo enums + + @Literal private final static String[] QUIRKY_PUBLIC_IDS = { + "+//silmaril//dtd html pro v0r11 19970101//", + "-//advasoft ltd//dtd html 3.0 aswedit + extensions//", + "-//as//dtd html 3.0 aswedit + extensions//", + "-//ietf//dtd html 2.0 level 1//", + "-//ietf//dtd html 2.0 level 2//", + "-//ietf//dtd html 2.0 strict level 1//", + "-//ietf//dtd html 2.0 strict level 2//", + "-//ietf//dtd html 2.0 strict//", + "-//ietf//dtd html 2.0//", + "-//ietf//dtd html 2.1e//", + "-//ietf//dtd html 3.0//", + "-//ietf//dtd html 3.2 final//", + "-//ietf//dtd html 3.2//", + "-//ietf//dtd html 3//", + "-//ietf//dtd html level 0//", + "-//ietf//dtd html level 1//", + "-//ietf//dtd html level 2//", + "-//ietf//dtd html level 3//", + "-//ietf//dtd html strict level 0//", + "-//ietf//dtd html strict level 1//", + "-//ietf//dtd html strict level 2//", + "-//ietf//dtd html strict level 3//", + "-//ietf//dtd html strict//", + "-//ietf//dtd html//", + "-//metrius//dtd metrius presentational//", + "-//microsoft//dtd internet explorer 2.0 html strict//", + "-//microsoft//dtd internet explorer 2.0 html//", + "-//microsoft//dtd internet explorer 2.0 tables//", + "-//microsoft//dtd internet explorer 3.0 html strict//", + "-//microsoft//dtd internet explorer 3.0 html//", + "-//microsoft//dtd internet explorer 3.0 tables//", + "-//netscape comm. corp.//dtd html//", + "-//netscape comm. corp.//dtd strict html//", + "-//o'reilly and associates//dtd html 2.0//", + "-//o'reilly and associates//dtd html extended 1.0//", + "-//o'reilly and associates//dtd html extended relaxed 1.0//", + "-//softquad software//dtd hotmetal pro 6.0::19990601::extensions to html 4.0//", + "-//softquad//dtd hotmetal pro 4.0::19971010::extensions to html 4.0//", + "-//spyglass//dtd html 2.0 extended//", + "-//sq//dtd html 2.0 hotmetal + extensions//", + "-//sun microsystems corp.//dtd hotjava html//", + "-//sun microsystems corp.//dtd hotjava strict html//", + "-//w3c//dtd html 3 1995-03-24//", "-//w3c//dtd html 3.2 draft//", + "-//w3c//dtd html 3.2 final//", "-//w3c//dtd html 3.2//", + "-//w3c//dtd html 3.2s draft//", "-//w3c//dtd html 4.0 frameset//", + "-//w3c//dtd html 4.0 transitional//", + "-//w3c//dtd html experimental 19960712//", + "-//w3c//dtd html experimental 970421//", "-//w3c//dtd w3 html//", + "-//w3o//dtd w3 html 3.0//", "-//webtechs//dtd mozilla html 2.0//", + "-//webtechs//dtd mozilla html//" }; + + private static final int NOT_FOUND_ON_STACK = Integer.MAX_VALUE; + + // [NOCPP[ + + private static final @Local String HTML_LOCAL = "html"; + + // ]NOCPP] + + private int mode = INITIAL; + + private int originalMode = INITIAL; + + /** + * Used only when moving back to IN_BODY. + */ + private boolean framesetOk = true; + + protected Tokenizer tokenizer; + + // [NOCPP[ + + protected ErrorHandler errorHandler; + + private DocumentModeHandler documentModeHandler; + + // ]NOCPP] + + private boolean scriptingEnabled = false; + + private boolean needToDropLF; + + // [NOCPP[ + + private boolean wantingComments; + + // ]NOCPP] + + private boolean fragment; + + private @Local String contextName; + + private @NsUri String contextNamespace; + + private T contextNode; + + /** + * Stack of template insertion modes + */ + private @Auto int[] templateModeStack; + + /** + * Current template mode stack pointer. + */ + private int templateModePtr = -1; + + private @Auto StackNode<T>[] stackNodes; + + /** + * Index of the earliest possible unused or empty element in stackNodes. + */ + private int stackNodesIdx = -1; + + private int numStackNodes = 0; + + private @Auto StackNode<T>[] stack; + + private int currentPtr = -1; + + private @Auto StackNode<T>[] listOfActiveFormattingElements; + + private int listPtr = -1; + + private T formPointer; + + private T headPointer; + + protected @Auto char[] charBuffer; + + protected int charBufferLen = 0; + + private boolean quirks = false; + + private boolean forceNoQuirks = false; + + // [NOCPP[ + + private boolean reportingDoctype = true; + + private XmlViolationPolicy namePolicy = XmlViolationPolicy.ALTER_INFOSET; + + private final Map<String, LocatorImpl> idLocations = new HashMap<String, LocatorImpl>(); + + // ]NOCPP] + + protected TreeBuilder() { + fragment = false; + } + + /** + * Reports an condition that would make the infoset incompatible with XML + * 1.0 as fatal. + * + * @throws SAXException + * @throws SAXParseException + */ + protected void fatal() throws SAXException { + } + + // CPPONLY: @Inline private @Creator Object htmlCreator(@HtmlCreator Object htmlCreator) { + // CPPONLY: @Creator Object creator; + // CPPONLY: creator.html = htmlCreator; + // CPPONLY: return creator; + // CPPONLY: } + // CPPONLY: + // CPPONLY: @Inline private @Creator Object svgCreator(@SvgCreator Object svgCreator) { + // CPPONLY: @Creator Object creator; + // CPPONLY: creator.svg = svgCreator; + // CPPONLY: return creator; + // CPPONLY: } + + // [NOCPP[ + + protected final void fatal(Exception e) throws SAXException { + SAXParseException spe = new SAXParseException(e.getMessage(), + tokenizer, e); + if (errorHandler != null) { + errorHandler.fatalError(spe); + } + throw spe; + } + + final void fatal(String s) throws SAXException { + SAXParseException spe = new SAXParseException(s, tokenizer); + if (errorHandler != null) { + errorHandler.fatalError(spe); + } + throw spe; + } + + /** + * Reports a Parse Error. + * + * @param message + * the message + * @throws SAXException + */ + final void err(String message) throws SAXException { + if (errorHandler == null) { + return; + } + errNoCheck(message); + } + + /** + * Reports a Parse Error without checking if an error handler is present. + * + * @param message + * the message + * @throws SAXException + */ + final void errNoCheck(String message) throws SAXException { + SAXParseException spe = new SAXParseException(message, tokenizer); + errorHandler.error(spe); + } + + private void errListUnclosedStartTags(int eltPos) throws SAXException { + if (currentPtr != -1) { + for (int i = currentPtr; i > eltPos; i--) { + reportUnclosedElementNameAndLocation(i); + } + } + } + + /** + * Reports the name and location of an unclosed element. + * + * @throws SAXException + */ + private final void reportUnclosedElementNameAndLocation(int pos) throws SAXException { + StackNode<T> node = stack[pos]; + if (node.isOptionalEndTag()) { + return; + } + TaintableLocatorImpl locator = node.getLocator(); + if (locator.isTainted()) { + return; + } + locator.markTainted(); + SAXParseException spe = new SAXParseException( + "Unclosed element \u201C" + node.popName + "\u201D.", locator); + errorHandler.error(spe); + } + + /** + * Reports a warning + * + * @param message + * the message + * @throws SAXException + */ + final void warn(String message) throws SAXException { + if (errorHandler == null) { + return; + } + SAXParseException spe = new SAXParseException(message, tokenizer); + errorHandler.warning(spe); + } + + /** + * Reports a warning with an explicit locator + * + * @param message + * the message + * @throws SAXException + */ + final void warn(String message, Locator locator) throws SAXException { + if (errorHandler == null) { + return; + } + SAXParseException spe = new SAXParseException(message, locator); + errorHandler.warning(spe); + } + + // ]NOCPP] + + @SuppressWarnings("unchecked") public final void startTokenization(Tokenizer self) throws SAXException { + tokenizer = self; + stackNodes = new StackNode[64]; + stack = new StackNode[64]; + templateModeStack = new int[64]; + listOfActiveFormattingElements = new StackNode[64]; + needToDropLF = false; + originalMode = INITIAL; + templateModePtr = -1; + stackNodesIdx = 0; + numStackNodes = 0; + currentPtr = -1; + listPtr = -1; + formPointer = null; + headPointer = null; + // [NOCPP[ + idLocations.clear(); + wantingComments = wantsComments(); + // ]NOCPP] + start(fragment); + charBufferLen = 0; + charBuffer = null; + framesetOk = true; + if (fragment) { + T elt; + if (contextNode != null) { + elt = contextNode; + } else { + elt = createHtmlElementSetAsRoot(tokenizer.emptyAttributes()); + } + // When the context node is not in the HTML namespace, contrary + // to the spec, the first node on the stack is not set to "html" + // in the HTML namespace. Instead, it is set to a node that has + // the characteristics of the appropriate "adjusted current node". + // This way, there is no need to perform "adjusted current node" + // checks during tree construction. Instead, it's sufficient to + // just look at the current node. However, this also means that it + // is not safe to treat "html" in the HTML namespace as a sentinel + // that ends stack popping. Instead, stack popping loops that are + // meant not to pop the first element on the stack need to check + // for currentPos becoming zero. + if (contextNamespace == "http://www.w3.org/2000/svg") { + ElementName elementName = ElementName.SVG; + if ("title" == contextName || "desc" == contextName + || "foreignObject" == contextName) { + // These elements are all alike and we don't care about + // the exact name. + elementName = ElementName.FOREIGNOBJECT; + } + // This is the SVG variant of the StackNode constructor. + StackNode<T> node = createStackNode(elementName, + elementName.getCamelCaseName(), elt + // [NOCPP[ + , errorHandler == null ? null + : new TaintableLocatorImpl(tokenizer) + // ]NOCPP] + ); + currentPtr++; + stack[currentPtr] = node; + tokenizer.setState(Tokenizer.DATA); + // The frameset-ok flag is set even though <frameset> never + // ends up being allowed as HTML frameset in the fragment case. + mode = FRAMESET_OK; + } else if (contextNamespace == "http://www.w3.org/1998/Math/MathML") { + ElementName elementName = ElementName.MATH; + if ("mi" == contextName || "mo" == contextName + || "mn" == contextName || "ms" == contextName + || "mtext" == contextName) { + // These elements are all alike and we don't care about + // the exact name. + elementName = ElementName.MTEXT; + } else if ("annotation-xml" == contextName) { + elementName = ElementName.ANNOTATION_XML; + // Blink does not check the encoding attribute of the + // annotation-xml element innerHTML is being set on. + // Let's do the same at least until + // https://www.w3.org/Bugs/Public/show_bug.cgi?id=26783 + // is resolved. + } + // This is the MathML variant of the StackNode constructor. + StackNode<T> node = createStackNode(elementName, elt, + elementName.getName(), false + // [NOCPP[ + , errorHandler == null ? null + : new TaintableLocatorImpl(tokenizer) + // ]NOCPP] + ); + currentPtr++; + stack[currentPtr] = node; + tokenizer.setState(Tokenizer.DATA); + // The frameset-ok flag is set even though <frameset> never + // ends up being allowed as HTML frameset in the fragment case. + mode = FRAMESET_OK; + } else { // html + StackNode<T> node = createStackNode(ElementName.HTML, elt + // [NOCPP[ + , errorHandler == null ? null + : new TaintableLocatorImpl(tokenizer) + // ]NOCPP] + ); + currentPtr++; + stack[currentPtr] = node; + if ("template" == contextName) { + pushTemplateMode(IN_TEMPLATE); + } + resetTheInsertionMode(); + formPointer = getFormPointerForContext(contextNode); + if ("title" == contextName || "textarea" == contextName) { + tokenizer.setState(Tokenizer.RCDATA); + } else if ("style" == contextName || "xmp" == contextName + || "iframe" == contextName || "noembed" == contextName + || "noframes" == contextName + || (scriptingEnabled && "noscript" == contextName)) { + tokenizer.setState(Tokenizer.RAWTEXT); + } else if ("plaintext" == contextName) { + tokenizer.setState(Tokenizer.PLAINTEXT); + } else if ("script" == contextName) { + tokenizer.setState(Tokenizer.SCRIPT_DATA); + } else { + tokenizer.setState(Tokenizer.DATA); + } + } + } else { + mode = INITIAL; + // If we are viewing XML source, put a foreign element permanently + // on the stack so that cdataSectionAllowed() returns true. + // CPPONLY: if (tokenizer.isViewingXmlSource()) { + // CPPONLY: T elt = createElement("http://www.w3.org/2000/svg", + // CPPONLY: "svg", + // CPPONLY: tokenizer.emptyAttributes(), null, + // CPPONLY: svgCreator(NS_NewSVGSVGElement)); + // CPPONLY: StackNode<T> node = createStackNode(ElementName.SVG, + // CPPONLY: "svg", + // CPPONLY: elt); + // CPPONLY: currentPtr++; + // CPPONLY: stack[currentPtr] = node; + // CPPONLY: } + } + } + + public final void doctype(@Local String name, String publicIdentifier, + String systemIdentifier, boolean forceQuirks) throws SAXException { + needToDropLF = false; + if (!isInForeign() && mode == INITIAL) { + // [NOCPP[ + if (reportingDoctype) { + // ]NOCPP] + String emptyString = Portability.newEmptyString(); + appendDoctypeToDocument(name == null ? "" : name, + publicIdentifier == null ? emptyString + : publicIdentifier, + systemIdentifier == null ? emptyString + : systemIdentifier); + Portability.releaseString(emptyString); + // [NOCPP[ + } + // ]NOCPP] + if (isQuirky(name, publicIdentifier, systemIdentifier, + forceQuirks)) { + errQuirkyDoctype(); + documentModeInternal(DocumentMode.QUIRKS_MODE, + publicIdentifier, systemIdentifier); + } else if (isAlmostStandards(publicIdentifier, + systemIdentifier)) { + errAlmostStandardsDoctype(); + documentModeInternal( + DocumentMode.ALMOST_STANDARDS_MODE, + publicIdentifier, systemIdentifier); + } else { + // [NOCPP[ + if ((Portability.literalEqualsString( + "-//W3C//DTD HTML 4.0//EN", publicIdentifier) && (systemIdentifier == null || Portability.literalEqualsString( + "http://www.w3.org/TR/REC-html40/strict.dtd", + systemIdentifier))) + || (Portability.literalEqualsString( + "-//W3C//DTD HTML 4.01//EN", + publicIdentifier) && (systemIdentifier == null || Portability.literalEqualsString( + "http://www.w3.org/TR/html4/strict.dtd", + systemIdentifier))) + || (Portability.literalEqualsString( + "-//W3C//DTD XHTML 1.0 Strict//EN", + publicIdentifier) && Portability.literalEqualsString( + "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd", + systemIdentifier)) + || (Portability.literalEqualsString( + "-//W3C//DTD XHTML 1.1//EN", + publicIdentifier) && Portability.literalEqualsString( + "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd", + systemIdentifier)) + + ) { + err("Obsolete doctype. Expected \u201C<!DOCTYPE html>\u201D."); + } else if (!((systemIdentifier == null || Portability.literalEqualsString( + "about:legacy-compat", systemIdentifier)) && publicIdentifier == null)) { + err("Legacy doctype. Expected \u201C<!DOCTYPE html>\u201D."); + } + // ]NOCPP] + documentModeInternal(DocumentMode.STANDARDS_MODE, + publicIdentifier, systemIdentifier); + } + + /* + * + * Then, switch to the root element mode of the tree construction + * stage. + */ + mode = BEFORE_HTML; + return; + } + /* + * A DOCTYPE token Parse error. + */ + errStrayDoctype(); + /* + * Ignore the token. + */ + return; + } + + public final void comment(@NoLength char[] buf, int start, int length) + throws SAXException { + needToDropLF = false; + // [NOCPP[ + if (!wantingComments) { + return; + } + // ]NOCPP] + if (!isInForeign()) { + switch (mode) { + case INITIAL: + case BEFORE_HTML: + case AFTER_AFTER_BODY: + case AFTER_AFTER_FRAMESET: + /* + * A comment token Append a Comment node to the Document + * object with the data attribute set to the data given in + * the comment token. + */ + appendCommentToDocument(buf, start, length); + return; + case AFTER_BODY: + /* + * A comment token Append a Comment node to the first + * element in the stack of open elements (the html element), + * with the data attribute set to the data given in the + * comment token. + */ + flushCharacters(); + appendComment(stack[0].node, buf, start, length); + return; + default: + break; + } + } + /* + * A comment token Append a Comment node to the current node with the + * data attribute set to the data given in the comment token. + */ + flushCharacters(); + appendComment(stack[currentPtr].node, buf, start, length); + return; + } + + /** + * @see nu.validator.htmlparser.common.TokenHandler#characters(char[], int, + * int) + */ + public final void characters(@Const @NoLength char[] buf, int start, int length) + throws SAXException { + // Note: Can't attach error messages to EOF in C++ yet + + // CPPONLY: if (tokenizer.isViewingXmlSource()) { + // CPPONLY: return; + // CPPONLY: } + if (needToDropLF) { + needToDropLF = false; + if (buf[start] == '\n') { + start++; + length--; + if (length == 0) { + return; + } + } + } + + // optimize the most common case + switch (mode) { + case IN_BODY: + case IN_CELL: + case IN_CAPTION: + if (!isInForeignButNotHtmlOrMathTextIntegrationPoint()) { + reconstructTheActiveFormattingElements(); + } + // CPPONLY: MOZ_FALLTHROUGH; + case TEXT: + accumulateCharacters(buf, start, length); + return; + case IN_TABLE: + case IN_TABLE_BODY: + case IN_ROW: + accumulateCharactersForced(buf, start, length); + return; + default: + int end = start + length; + charactersloop: for (int i = start; i < end; i++) { + switch (buf[i]) { + case ' ': + case '\t': + case '\n': + case '\r': + case '\u000C': + /* + * A character token that is one of one of U+0009 + * CHARACTER TABULATION, U+000A LINE FEED (LF), + * U+000C FORM FEED (FF), or U+0020 SPACE + */ + switch (mode) { + case INITIAL: + case BEFORE_HTML: + case BEFORE_HEAD: + /* + * Ignore the token. + */ + start = i + 1; + continue; + case IN_HEAD: + case IN_HEAD_NOSCRIPT: + case AFTER_HEAD: + case IN_COLUMN_GROUP: + case IN_FRAMESET: + case AFTER_FRAMESET: + /* + * Append the character to the current node. + */ + continue; + case FRAMESET_OK: + case IN_TEMPLATE: + case IN_BODY: + case IN_CELL: + case IN_CAPTION: + if (start < i) { + accumulateCharacters(buf, start, i + - start); + start = i; + } + + /* + * Reconstruct the active formatting + * elements, if any. + */ + if (!isInForeignButNotHtmlOrMathTextIntegrationPoint()) { + flushCharacters(); + reconstructTheActiveFormattingElements(); + } + /* + * Append the token's character to the + * current node. + */ + break charactersloop; + case IN_SELECT: + case IN_SELECT_IN_TABLE: + break charactersloop; + case IN_TABLE: + case IN_TABLE_BODY: + case IN_ROW: + accumulateCharactersForced(buf, i, 1); + start = i + 1; + continue; + case AFTER_BODY: + case AFTER_AFTER_BODY: + case AFTER_AFTER_FRAMESET: + if (start < i) { + accumulateCharacters(buf, start, i + - start); + start = i; + } + /* + * Reconstruct the active formatting + * elements, if any. + */ + flushCharacters(); + reconstructTheActiveFormattingElements(); + /* + * Append the token's character to the + * current node. + */ + continue; + } + // CPPONLY: MOZ_FALLTHROUGH_ASSERT(); + default: + /* + * A character token that is not one of one of + * U+0009 CHARACTER TABULATION, U+000A LINE FEED + * (LF), U+000C FORM FEED (FF), or U+0020 SPACE + */ + switch (mode) { + case INITIAL: + /* + * Parse error. + */ + // [NOCPP[ + // XXX figure out a way to report this in the Gecko View Source case + err("Non-space characters found without seeing a doctype first. Expected \u201C<!DOCTYPE html>\u201D."); + // ]NOCPP] + /* + * + * Set the document to quirks mode. + */ + documentModeInternal( + DocumentMode.QUIRKS_MODE, null, + null); + /* + * Then, switch to the root element mode of + * the tree construction stage + */ + mode = BEFORE_HTML; + /* + * and reprocess the current token. + */ + i--; + continue; + case BEFORE_HTML: + /* + * Create an HTMLElement node with the tag + * name html, in the HTML namespace. Append + * it to the Document object. + */ + // No need to flush characters here, + // because there's nothing to flush. + appendHtmlElementToDocumentAndPush(); + /* Switch to the main mode */ + mode = BEFORE_HEAD; + /* + * reprocess the current token. + */ + i--; + continue; + case BEFORE_HEAD: + if (start < i) { + accumulateCharacters(buf, start, i + - start); + start = i; + } + /* + * /Act as if a start tag token with the tag + * name "head" and no attributes had been + * seen, + */ + flushCharacters(); + appendToCurrentNodeAndPushHeadElement(HtmlAttributes.EMPTY_ATTRIBUTES); + mode = IN_HEAD; + /* + * then reprocess the current token. + * + * This will result in an empty head element + * being generated, with the current token + * being reprocessed in the "after head" + * insertion mode. + */ + i--; + continue; + case IN_HEAD: + if (start < i) { + accumulateCharacters(buf, start, i + - start); + start = i; + } + /* + * Act as if an end tag token with the tag + * name "head" had been seen, + */ + flushCharacters(); + pop(); + mode = AFTER_HEAD; + /* + * and reprocess the current token. + */ + i--; + continue; + case IN_HEAD_NOSCRIPT: + if (start < i) { + accumulateCharacters(buf, start, i + - start); + start = i; + } + /* + * Parse error. Act as if an end tag with + * the tag name "noscript" had been seen + */ + errNonSpaceInNoscriptInHead(); + flushCharacters(); + pop(); + mode = IN_HEAD; + /* + * and reprocess the current token. + */ + i--; + continue; + case AFTER_HEAD: + if (start < i) { + accumulateCharacters(buf, start, i + - start); + start = i; + } + /* + * Act as if a start tag token with the tag + * name "body" and no attributes had been + * seen, + */ + flushCharacters(); + appendToCurrentNodeAndPushBodyElement(); + mode = FRAMESET_OK; + /* + * and then reprocess the current token. + */ + i--; + continue; + case FRAMESET_OK: + framesetOk = false; + mode = IN_BODY; + i--; + continue; + case IN_TEMPLATE: + case IN_BODY: + case IN_CELL: + case IN_CAPTION: + if (start < i) { + accumulateCharacters(buf, start, i + - start); + start = i; + } + /* + * Reconstruct the active formatting + * elements, if any. + */ + if (!isInForeignButNotHtmlOrMathTextIntegrationPoint()) { + flushCharacters(); + reconstructTheActiveFormattingElements(); + } + /* + * Append the token's character to the + * current node. + */ + break charactersloop; + case IN_TABLE: + case IN_TABLE_BODY: + case IN_ROW: + accumulateCharactersForced(buf, i, 1); + start = i + 1; + continue; + case IN_COLUMN_GROUP: + if (start < i) { + accumulateCharacters(buf, start, i + - start); + start = i; + } + /* + * Act as if an end tag with the tag name + * "colgroup" had been seen, and then, if + * that token wasn't ignored, reprocess the + * current token. + */ + if (currentPtr == 0 || stack[currentPtr].getGroup() == + TreeBuilder.TEMPLATE) { + errNonSpaceInColgroupInFragment(); + start = i + 1; + continue; + } + flushCharacters(); + pop(); + mode = IN_TABLE; + i--; + continue; + case IN_SELECT: + case IN_SELECT_IN_TABLE: + break charactersloop; + case AFTER_BODY: + errNonSpaceAfterBody(); + fatal(); + mode = framesetOk ? FRAMESET_OK : IN_BODY; + i--; + continue; + case IN_FRAMESET: + if (start < i) { + accumulateCharacters(buf, start, i + - start); + // start index is adjusted below. + } + /* + * Parse error. + */ + errNonSpaceInFrameset(); + /* + * Ignore the token. + */ + start = i + 1; + continue; + case AFTER_FRAMESET: + if (start < i) { + accumulateCharacters(buf, start, i + - start); + // start index is adjusted below. + } + /* + * Parse error. + */ + errNonSpaceAfterFrameset(); + /* + * Ignore the token. + */ + start = i + 1; + continue; + case AFTER_AFTER_BODY: + /* + * Parse error. + */ + errNonSpaceInTrailer(); + /* + * Switch back to the main mode and + * reprocess the token. + */ + mode = framesetOk ? FRAMESET_OK : IN_BODY; + i--; + continue; + case AFTER_AFTER_FRAMESET: + if (start < i) { + accumulateCharacters(buf, start, i + - start); + // start index is adjusted below. + } + /* + * Parse error. + */ + errNonSpaceInTrailer(); + /* + * Ignore the token. + */ + start = i + 1; + continue; + } + } + } + if (start < end) { + accumulateCharacters(buf, start, end - start); + } + } + } + + /** + * @see nu.validator.htmlparser.common.TokenHandler#zeroOriginatingReplacementCharacter() + */ + public void zeroOriginatingReplacementCharacter() throws SAXException { + if (mode == TEXT) { + accumulateCharacters(REPLACEMENT_CHARACTER, 0, 1); + return; + } + if (currentPtr >= 0) { + if (isSpecialParentInForeign(stack[currentPtr])) { + return; + } + accumulateCharacters(REPLACEMENT_CHARACTER, 0, 1); + } + } + + /** + * @see nu.validator.htmlparser.common.TokenHandler#zeroOrReplacementCharacter() + */ + public void zeroOrReplacementCharacter() throws SAXException { + zeroOriginatingReplacementCharacter(); + } + + public final void eof() throws SAXException { + flushCharacters(); + // Note: Can't attach error messages to EOF in C++ yet + eofloop: for (;;) { + switch (mode) { + case INITIAL: + /* + * Parse error. + */ + // [NOCPP[ + err("End of file seen without seeing a doctype first. Expected \u201C<!DOCTYPE html>\u201D."); + // ]NOCPP] + /* + * + * Set the document to quirks mode. + */ + documentModeInternal(DocumentMode.QUIRKS_MODE, null, null); + /* + * Then, switch to the root element mode of the tree + * construction stage + */ + mode = BEFORE_HTML; + /* + * and reprocess the current token. + */ + continue; + case BEFORE_HTML: + /* + * Create an HTMLElement node with the tag name html, in the + * HTML namespace. Append it to the Document object. + */ + appendHtmlElementToDocumentAndPush(); + // XXX application cache manifest + /* Switch to the main mode */ + mode = BEFORE_HEAD; + /* + * reprocess the current token. + */ + continue; + case BEFORE_HEAD: + appendToCurrentNodeAndPushHeadElement(HtmlAttributes.EMPTY_ATTRIBUTES); + mode = IN_HEAD; + continue; + case IN_HEAD: + // [NOCPP[ + if (errorHandler != null && currentPtr > 1) { + errEofWithUnclosedElements(); + } + // ]NOCPP] + while (currentPtr > 0) { + popOnEof(); + } + mode = AFTER_HEAD; + continue; + case IN_HEAD_NOSCRIPT: + // [NOCPP[ + errEofWithUnclosedElements(); + // ]NOCPP] + while (currentPtr > 1) { + popOnEof(); + } + mode = IN_HEAD; + continue; + case AFTER_HEAD: + appendToCurrentNodeAndPushBodyElement(); + mode = IN_BODY; + continue; + case IN_TABLE_BODY: + case IN_ROW: + case IN_TABLE: + case IN_SELECT_IN_TABLE: + case IN_SELECT: + case IN_COLUMN_GROUP: + case FRAMESET_OK: + case IN_CAPTION: + case IN_CELL: + case IN_BODY: + // [NOCPP[ + // i > 0 to stop in time in the foreign fragment case. + openelementloop: for (int i = currentPtr; i > 0; i--) { + int group = stack[i].getGroup(); + switch (group) { + case DD_OR_DT: + case LI: + case P: + case TBODY_OR_THEAD_OR_TFOOT: + case TD_OR_TH: + case BODY: + case HTML: + break; + default: + errEofWithUnclosedElements(); + break openelementloop; + } + } + // ]NOCPP] + + if (isTemplateModeStackEmpty()) { + break eofloop; + } + + // fall through to IN_TEMPLATE + // CPPONLY: MOZ_FALLTHROUGH; + case IN_TEMPLATE: + int eltPos = findLast("template"); + if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) { + assert fragment; + break eofloop; + } + if (errorHandler != null) { + errListUnclosedStartTags(0); + } + while (currentPtr >= eltPos) { + pop(); + } + clearTheListOfActiveFormattingElementsUpToTheLastMarker(); + popTemplateMode(); + resetTheInsertionMode(); + + // Reprocess token. + continue; + case TEXT: + // [NOCPP[ + if (errorHandler != null) { + errNoCheck("End of file seen when expecting text or an end tag."); + errListUnclosedStartTags(0); + } + // ]NOCPP] + // XXX mark script as already executed + if (originalMode == AFTER_HEAD) { + popOnEof(); + } + popOnEof(); + mode = originalMode; + continue; + case IN_FRAMESET: + // [NOCPP[ + if (errorHandler != null && currentPtr > 0) { + errEofWithUnclosedElements(); + } + // ]NOCPP] + break eofloop; + case AFTER_BODY: + case AFTER_FRAMESET: + case AFTER_AFTER_BODY: + case AFTER_AFTER_FRAMESET: + default: + // [NOCPP[ + if (currentPtr == 0) { // This silliness is here to poison + // buggy compiler optimizations in + // GWT + System.currentTimeMillis(); + } + // ]NOCPP] + break eofloop; + } + } + while (currentPtr > 0) { + popOnEof(); + } + if (!fragment) { + popOnEof(); + } + /* Stop parsing. */ + } + + /** + * @see nu.validator.htmlparser.common.TokenHandler#endTokenization() + */ + public final void endTokenization() throws SAXException { + formPointer = null; + headPointer = null; + contextName = null; + contextNode = null; + templateModeStack = null; + if (stack != null) { + while (currentPtr > -1) { + stack[currentPtr].release(this); + currentPtr--; + } + stack = null; + } + if (listOfActiveFormattingElements != null) { + while (listPtr > -1) { + if (listOfActiveFormattingElements[listPtr] != null) { + listOfActiveFormattingElements[listPtr].release(this); + } + listPtr--; + } + listOfActiveFormattingElements = null; + } + if (stackNodes != null) { + for (int i = 0; i < numStackNodes; i++) { + assert stackNodes[i].isUnused(); + Portability.delete(stackNodes[i]); + } + numStackNodes = 0; + stackNodesIdx = 0; + stackNodes = null; + } + // [NOCPP[ + idLocations.clear(); + // ]NOCPP] + charBuffer = null; + end(); + } + + public final void startTag(ElementName elementName, + HtmlAttributes attributes, boolean selfClosing) throws SAXException { + flushCharacters(); + + // [NOCPP[ + if (errorHandler != null) { + // ID uniqueness + @IdType String id = attributes.getId(); + if (id != null) { + LocatorImpl oldLoc = idLocations.get(id); + if (oldLoc != null) { + err("Duplicate ID \u201C" + id + "\u201D."); + errorHandler.warning(new SAXParseException( + "The first occurrence of ID \u201C" + id + + "\u201D was here.", oldLoc)); + } else { + idLocations.put(id, new LocatorImpl(tokenizer)); + } + } + } + // ]NOCPP] + + int eltPos; + needToDropLF = false; + starttagloop: for (;;) { + int group = elementName.getGroup(); + @Local String name = elementName.getName(); + if (isInForeign()) { + StackNode<T> currentNode = stack[currentPtr]; + @NsUri String currNs = currentNode.ns; + if (!(currentNode.isHtmlIntegrationPoint() || (currNs == "http://www.w3.org/1998/Math/MathML" && ((currentNode.getGroup() == MI_MO_MN_MS_MTEXT && group != MGLYPH_OR_MALIGNMARK) || (currentNode.getGroup() == ANNOTATION_XML && group == SVG))))) { + switch (group) { + case B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U: + case DIV_OR_BLOCKQUOTE_OR_CENTER_OR_MENU: + case BODY: + case BR: + case RUBY_OR_SPAN_OR_SUB_OR_SUP_OR_VAR: + case DD_OR_DT: + case UL_OR_OL_OR_DL: + case EMBED: + case IMG: + case H1_OR_H2_OR_H3_OR_H4_OR_H5_OR_H6: + case HEAD: + case HR: + case LI: + case META: + case NOBR: + case P: + case PRE_OR_LISTING: + case TABLE: + case FONT: + // re-check FONT to deal with the special case + if (!(group == FONT && !(attributes.contains(AttributeName.COLOR) + || attributes.contains(AttributeName.FACE) || attributes.contains(AttributeName.SIZE)))) { + errHtmlStartTagInForeignContext(name); + if (!fragment) { + while (!isSpecialParentInForeign(stack[currentPtr])) { + popForeign(-1, -1); + } + continue starttagloop; + } // else fall thru + } + // CPPONLY: MOZ_FALLTHROUGH; + default: + if ("http://www.w3.org/2000/svg" == currNs) { + attributes.adjustForSvg(); + if (selfClosing) { + appendVoidElementToCurrentMayFosterSVG( + elementName, attributes); + selfClosing = false; + } else { + appendToCurrentNodeAndPushElementMayFosterSVG( + elementName, attributes); + } + attributes = null; // CPP + break starttagloop; + } else { + attributes.adjustForMath(); + if (selfClosing) { + appendVoidElementToCurrentMayFosterMathML( + elementName, attributes); + selfClosing = false; + } else { + appendToCurrentNodeAndPushElementMayFosterMathML( + elementName, attributes); + } + attributes = null; // CPP + break starttagloop; + } + } // switch + } // foreignObject / annotation-xml + } + switch (mode) { + case IN_TEMPLATE: + switch (group) { + case COL: + popTemplateMode(); + pushTemplateMode(IN_COLUMN_GROUP); + mode = IN_COLUMN_GROUP; + // Reprocess token. + continue; + case CAPTION: + case COLGROUP: + case TBODY_OR_THEAD_OR_TFOOT: + popTemplateMode(); + pushTemplateMode(IN_TABLE); + mode = IN_TABLE; + // Reprocess token. + continue; + case TR: + popTemplateMode(); + pushTemplateMode(IN_TABLE_BODY); + mode = IN_TABLE_BODY; + // Reprocess token. + continue; + case TD_OR_TH: + popTemplateMode(); + pushTemplateMode(IN_ROW); + mode = IN_ROW; + // Reprocess token. + continue; + case META: + checkMetaCharset(attributes); + appendVoidElementToCurrentMayFoster( + elementName, + attributes); + selfClosing = false; + attributes = null; // CPP + break starttagloop; + case TITLE: + startTagTitleInHead(elementName, attributes); + attributes = null; // CPP + break starttagloop; + case BASE: + case LINK_OR_BASEFONT_OR_BGSOUND: + appendVoidElementToCurrentMayFoster( + elementName, + attributes); + selfClosing = false; + attributes = null; // CPP + break starttagloop; + case SCRIPT: + startTagScriptInHead(elementName, attributes); + attributes = null; // CPP + break starttagloop; + case NOFRAMES: + case STYLE: + startTagGenericRawText(elementName, attributes); + attributes = null; // CPP + break starttagloop; + case TEMPLATE: + startTagTemplateInHead(elementName, attributes); + attributes = null; // CPP + break starttagloop; + default: + popTemplateMode(); + pushTemplateMode(IN_BODY); + mode = IN_BODY; + // Reprocess token. + continue; + } + case IN_ROW: + switch (group) { + case TD_OR_TH: + clearStackBackTo(findLastOrRoot(TreeBuilder.TR)); + appendToCurrentNodeAndPushElement( + elementName, + attributes); + mode = IN_CELL; + insertMarker(); + attributes = null; // CPP + break starttagloop; + case CAPTION: + case COL: + case COLGROUP: + case TBODY_OR_THEAD_OR_TFOOT: + case TR: + eltPos = findLastOrRoot(TreeBuilder.TR); + if (eltPos == 0) { + assert fragment || isTemplateContents(); + errNoTableRowToClose(); + break starttagloop; + } + clearStackBackTo(eltPos); + pop(); + mode = IN_TABLE_BODY; + continue; + default: + // fall through to IN_TABLE + } + // CPPONLY: MOZ_FALLTHROUGH; + case IN_TABLE_BODY: + switch (group) { + case TR: + clearStackBackTo(findLastInTableScopeOrRootTemplateTbodyTheadTfoot()); + appendToCurrentNodeAndPushElement( + elementName, + attributes); + mode = IN_ROW; + attributes = null; // CPP + break starttagloop; + case TD_OR_TH: + errStartTagInTableBody(name); + clearStackBackTo(findLastInTableScopeOrRootTemplateTbodyTheadTfoot()); + appendToCurrentNodeAndPushElement( + ElementName.TR, + HtmlAttributes.EMPTY_ATTRIBUTES); + mode = IN_ROW; + continue; + case CAPTION: + case COL: + case COLGROUP: + case TBODY_OR_THEAD_OR_TFOOT: + eltPos = findLastInTableScopeOrRootTemplateTbodyTheadTfoot(); + if (eltPos == 0 || stack[eltPos].getGroup() == TEMPLATE) { + assert fragment || isTemplateContents(); + errStrayStartTag(name); + break starttagloop; + } else { + clearStackBackTo(eltPos); + pop(); + mode = IN_TABLE; + continue; + } + default: + // fall through to IN_TABLE + } + // CPPONLY: MOZ_FALLTHROUGH; + case IN_TABLE: + intableloop: for (;;) { + switch (group) { + case CAPTION: + clearStackBackTo(findLastOrRoot(TreeBuilder.TABLE)); + insertMarker(); + appendToCurrentNodeAndPushElement( + elementName, + attributes); + mode = IN_CAPTION; + attributes = null; // CPP + break starttagloop; + case COLGROUP: + clearStackBackTo(findLastOrRoot(TreeBuilder.TABLE)); + appendToCurrentNodeAndPushElement( + elementName, + attributes); + mode = IN_COLUMN_GROUP; + attributes = null; // CPP + break starttagloop; + case COL: + clearStackBackTo(findLastOrRoot(TreeBuilder.TABLE)); + appendToCurrentNodeAndPushElement( + ElementName.COLGROUP, + HtmlAttributes.EMPTY_ATTRIBUTES); + mode = IN_COLUMN_GROUP; + continue starttagloop; + case TBODY_OR_THEAD_OR_TFOOT: + clearStackBackTo(findLastOrRoot(TreeBuilder.TABLE)); + appendToCurrentNodeAndPushElement( + elementName, + attributes); + mode = IN_TABLE_BODY; + attributes = null; // CPP + break starttagloop; + case TR: + case TD_OR_TH: + clearStackBackTo(findLastOrRoot(TreeBuilder.TABLE)); + appendToCurrentNodeAndPushElement( + ElementName.TBODY, + HtmlAttributes.EMPTY_ATTRIBUTES); + mode = IN_TABLE_BODY; + continue starttagloop; + case TEMPLATE: + // fall through to IN_HEAD + break intableloop; + case TABLE: + errTableSeenWhileTableOpen(); + eltPos = findLastInTableScope(name); + if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) { + assert fragment || isTemplateContents(); + break starttagloop; + } + generateImpliedEndTags(); + if (errorHandler != null && !isCurrent("table")) { + errNoCheckUnclosedElementsOnStack(); + } + while (currentPtr >= eltPos) { + pop(); + } + resetTheInsertionMode(); + continue starttagloop; + case SCRIPT: + // XXX need to manage much more stuff + // here if + // supporting + // document.write() + appendToCurrentNodeAndPushElement( + elementName, + attributes); + originalMode = mode; + mode = TEXT; + tokenizer.setStateAndEndTagExpectation( + Tokenizer.SCRIPT_DATA, elementName); + attributes = null; // CPP + break starttagloop; + case STYLE: + appendToCurrentNodeAndPushElement( + elementName, + attributes); + originalMode = mode; + mode = TEXT; + tokenizer.setStateAndEndTagExpectation( + Tokenizer.RAWTEXT, elementName); + attributes = null; // CPP + break starttagloop; + case INPUT: + errStartTagInTable(name); + if (!Portability.lowerCaseLiteralEqualsIgnoreAsciiCaseString( + "hidden", + attributes.getValue(AttributeName.TYPE))) { + break intableloop; + } + appendVoidInputToCurrent( + attributes, + formPointer); + selfClosing = false; + attributes = null; // CPP + break starttagloop; + case FORM: + if (formPointer != null || isTemplateContents()) { + errFormWhenFormOpen(); + break starttagloop; + } else { + errStartTagInTable(name); + appendVoidFormToCurrent(attributes); + attributes = null; // CPP + break starttagloop; + } + default: + errStartTagInTable(name); + // fall through to IN_BODY + break intableloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case IN_CAPTION: + switch (group) { + case CAPTION: + case COL: + case COLGROUP: + case TBODY_OR_THEAD_OR_TFOOT: + case TR: + case TD_OR_TH: + eltPos = findLastInTableScope("caption"); + if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) { + assert fragment || isTemplateContents(); + errStrayStartTag(name); + break starttagloop; + } + generateImpliedEndTags(); + if (errorHandler != null && currentPtr != eltPos) { + errNoCheckUnclosedElementsOnStack(); + } + while (currentPtr >= eltPos) { + pop(); + } + clearTheListOfActiveFormattingElementsUpToTheLastMarker(); + mode = IN_TABLE; + continue; + default: + // fall through to IN_BODY + } + // CPPONLY: MOZ_FALLTHROUGH; + case IN_CELL: + switch (group) { + case CAPTION: + case COL: + case COLGROUP: + case TBODY_OR_THEAD_OR_TFOOT: + case TR: + case TD_OR_TH: + eltPos = findLastInTableScopeTdTh(); + if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) { + errNoCellToClose(); + break starttagloop; + } else { + closeTheCell(eltPos); + continue; + } + default: + // fall through to IN_BODY + } + // CPPONLY: MOZ_FALLTHROUGH; + case FRAMESET_OK: + switch (group) { + case FRAMESET: + if (mode == FRAMESET_OK) { + if (currentPtr == 0 || stack[1].getGroup() != BODY) { + assert fragment || isTemplateContents(); + errStrayStartTag(name); + break starttagloop; + } else { + errFramesetStart(); + detachFromParent(stack[1].node); + while (currentPtr > 0) { + pop(); + } + appendToCurrentNodeAndPushElement( + elementName, + attributes); + mode = IN_FRAMESET; + attributes = null; // CPP + break starttagloop; + } + } else { + errStrayStartTag(name); + break starttagloop; + } + // NOT falling through! + case PRE_OR_LISTING: + case LI: + case DD_OR_DT: + case BUTTON: + case MARQUEE_OR_APPLET: + case OBJECT: + case TABLE: + case AREA_OR_WBR: + case KEYGEN: + case BR: + case EMBED: + case IMG: + case INPUT: + case HR: + case TEXTAREA: + case XMP: + case IFRAME: + case SELECT: + if (mode == FRAMESET_OK + && !(group == INPUT && Portability.lowerCaseLiteralEqualsIgnoreAsciiCaseString( + "hidden", + attributes.getValue(AttributeName.TYPE)))) { + framesetOk = false; + mode = IN_BODY; + } + // CPPONLY: MOZ_FALLTHROUGH; + default: + // fall through to IN_BODY + } + // CPPONLY: MOZ_FALLTHROUGH; + case IN_BODY: + inbodyloop: for (;;) { + switch (group) { + case HTML: + errStrayStartTag(name); + if (!fragment && !isTemplateContents()) { + addAttributesToHtml(attributes); + attributes = null; // CPP + } + break starttagloop; + case BASE: + case LINK_OR_BASEFONT_OR_BGSOUND: + case META: + case STYLE: + case SCRIPT: + case TITLE: + case TEMPLATE: + // Fall through to IN_HEAD + break inbodyloop; + case BODY: + if (currentPtr == 0 || stack[1].getGroup() != BODY || isTemplateContents()) { + assert fragment || isTemplateContents(); + errStrayStartTag(name); + break starttagloop; + } + errFooSeenWhenFooOpen(name); + framesetOk = false; + if (mode == FRAMESET_OK) { + mode = IN_BODY; + } + if (addAttributesToBody(attributes)) { + attributes = null; // CPP + } + break starttagloop; + case P: + case DIV_OR_BLOCKQUOTE_OR_CENTER_OR_MENU: + case UL_OR_OL_OR_DL: + case ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY: + implicitlyCloseP(); + appendToCurrentNodeAndPushElementMayFoster( + elementName, + attributes); + attributes = null; // CPP + break starttagloop; + case H1_OR_H2_OR_H3_OR_H4_OR_H5_OR_H6: + implicitlyCloseP(); + if (stack[currentPtr].getGroup() == H1_OR_H2_OR_H3_OR_H4_OR_H5_OR_H6) { + errHeadingWhenHeadingOpen(); + pop(); + } + appendToCurrentNodeAndPushElementMayFoster( + elementName, + attributes); + attributes = null; // CPP + break starttagloop; + case FIELDSET: + implicitlyCloseP(); + appendToCurrentNodeAndPushElementMayFoster( + elementName, + attributes, formPointer); + attributes = null; // CPP + break starttagloop; + case PRE_OR_LISTING: + implicitlyCloseP(); + appendToCurrentNodeAndPushElementMayFoster( + elementName, + attributes); + needToDropLF = true; + attributes = null; // CPP + break starttagloop; + case FORM: + if (formPointer != null && !isTemplateContents()) { + errFormWhenFormOpen(); + break starttagloop; + } else { + implicitlyCloseP(); + appendToCurrentNodeAndPushFormElementMayFoster(attributes); + attributes = null; // CPP + break starttagloop; + } + case LI: + case DD_OR_DT: + eltPos = currentPtr; + for (;;) { + StackNode<T> node = stack[eltPos]; // weak + // ref + if (node.getGroup() == group) { // LI or + // DD_OR_DT + generateImpliedEndTagsExceptFor(node.name); + if (errorHandler != null + && eltPos != currentPtr) { + errUnclosedElementsImplied(eltPos, name); + } + while (currentPtr >= eltPos) { + pop(); + } + break; + } else if (eltPos == 0 || (node.isSpecial() + && (node.ns != "http://www.w3.org/1999/xhtml" + || (node.name != "p" + && node.name != "address" + && node.name != "div")))) { + break; + } + eltPos--; + } + implicitlyCloseP(); + appendToCurrentNodeAndPushElementMayFoster( + elementName, + attributes); + attributes = null; // CPP + break starttagloop; + case PLAINTEXT: + implicitlyCloseP(); + appendToCurrentNodeAndPushElementMayFoster( + elementName, + attributes); + tokenizer.setStateAndEndTagExpectation( + Tokenizer.PLAINTEXT, elementName); + attributes = null; // CPP + break starttagloop; + case A: + int activeAPos = findInListOfActiveFormattingElementsContainsBetweenEndAndLastMarker("a"); + if (activeAPos != -1) { + errFooSeenWhenFooOpen(name); + StackNode<T> activeA = listOfActiveFormattingElements[activeAPos]; + activeA.retain(); + adoptionAgencyEndTag("a"); + removeFromStack(activeA); + activeAPos = findInListOfActiveFormattingElements(activeA); + if (activeAPos != -1) { + removeFromListOfActiveFormattingElements(activeAPos); + } + activeA.release(this); + } + reconstructTheActiveFormattingElements(); + appendToCurrentNodeAndPushFormattingElementMayFoster( + elementName, + attributes); + attributes = null; // CPP + break starttagloop; + case B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U: + case FONT: + reconstructTheActiveFormattingElements(); + maybeForgetEarlierDuplicateFormattingElement(elementName.getName(), attributes); + appendToCurrentNodeAndPushFormattingElementMayFoster( + elementName, + attributes); + attributes = null; // CPP + break starttagloop; + case NOBR: + reconstructTheActiveFormattingElements(); + if (TreeBuilder.NOT_FOUND_ON_STACK != findLastInScope("nobr")) { + errFooSeenWhenFooOpen(name); + adoptionAgencyEndTag("nobr"); + reconstructTheActiveFormattingElements(); + } + appendToCurrentNodeAndPushFormattingElementMayFoster( + elementName, + attributes); + attributes = null; // CPP + break starttagloop; + case BUTTON: + eltPos = findLastInScope(name); + if (eltPos != TreeBuilder.NOT_FOUND_ON_STACK) { + errFooSeenWhenFooOpen(name); + generateImpliedEndTags(); + if (errorHandler != null + && !isCurrent(name)) { + errUnclosedElementsImplied(eltPos, name); + } + while (currentPtr >= eltPos) { + pop(); + } + continue starttagloop; + } else { + reconstructTheActiveFormattingElements(); + appendToCurrentNodeAndPushElementMayFoster( + elementName, + attributes, formPointer); + attributes = null; // CPP + break starttagloop; + } + case OBJECT: + reconstructTheActiveFormattingElements(); + appendToCurrentNodeAndPushElementMayFoster( + elementName, + attributes, formPointer); + insertMarker(); + attributes = null; // CPP + break starttagloop; + case MARQUEE_OR_APPLET: + reconstructTheActiveFormattingElements(); + appendToCurrentNodeAndPushElementMayFoster( + elementName, + attributes); + insertMarker(); + attributes = null; // CPP + break starttagloop; + case TABLE: + // The only quirk. Blame Hixie and + // Acid2. + if (!quirks) { + implicitlyCloseP(); + } + appendToCurrentNodeAndPushElementMayFoster( + elementName, + attributes); + mode = IN_TABLE; + attributes = null; // CPP + break starttagloop; + case BR: + case EMBED: + case AREA_OR_WBR: + case KEYGEN: + reconstructTheActiveFormattingElements(); + // FALL THROUGH to PARAM_OR_SOURCE_OR_TRACK + // CPPONLY: MOZ_FALLTHROUGH; + case PARAM_OR_SOURCE_OR_TRACK: + appendVoidElementToCurrentMayFoster( + elementName, + attributes); + selfClosing = false; + attributes = null; // CPP + break starttagloop; + case HR: + implicitlyCloseP(); + appendVoidElementToCurrentMayFoster( + elementName, + attributes); + selfClosing = false; + attributes = null; // CPP + break starttagloop; + case IMAGE: + errImage(); + elementName = ElementName.IMG; + continue starttagloop; + case IMG: + case INPUT: + reconstructTheActiveFormattingElements(); + appendVoidElementToCurrentMayFoster( + elementName, attributes, + formPointer); + selfClosing = false; + attributes = null; // CPP + break starttagloop; + case TEXTAREA: + appendToCurrentNodeAndPushElementMayFoster( + elementName, + attributes, formPointer); + tokenizer.setStateAndEndTagExpectation( + Tokenizer.RCDATA, elementName); + originalMode = mode; + mode = TEXT; + needToDropLF = true; + attributes = null; // CPP + break starttagloop; + case XMP: + implicitlyCloseP(); + reconstructTheActiveFormattingElements(); + appendToCurrentNodeAndPushElementMayFoster( + elementName, + attributes); + originalMode = mode; + mode = TEXT; + tokenizer.setStateAndEndTagExpectation( + Tokenizer.RAWTEXT, elementName); + attributes = null; // CPP + break starttagloop; + case NOSCRIPT: + if (!scriptingEnabled) { + reconstructTheActiveFormattingElements(); + appendToCurrentNodeAndPushElementMayFoster( + elementName, + attributes); + attributes = null; // CPP + break starttagloop; + } + // CPPONLY: MOZ_FALLTHROUGH; + case NOFRAMES: + case IFRAME: + case NOEMBED: + startTagGenericRawText(elementName, attributes); + attributes = null; // CPP + break starttagloop; + case SELECT: + reconstructTheActiveFormattingElements(); + appendToCurrentNodeAndPushElementMayFoster( + elementName, + attributes, formPointer); + switch (mode) { + case IN_TABLE: + case IN_CAPTION: + case IN_COLUMN_GROUP: + case IN_TABLE_BODY: + case IN_ROW: + case IN_CELL: + mode = IN_SELECT_IN_TABLE; + break; + default: + mode = IN_SELECT; + break; + } + attributes = null; // CPP + break starttagloop; + case OPTGROUP: + case OPTION: + if (isCurrent("option")) { + pop(); + } + reconstructTheActiveFormattingElements(); + appendToCurrentNodeAndPushElementMayFoster( + elementName, + attributes); + attributes = null; // CPP + break starttagloop; + case RB_OR_RTC: + eltPos = findLastInScope("ruby"); + if (eltPos != NOT_FOUND_ON_STACK) { + generateImpliedEndTags(); + } + if (eltPos != currentPtr) { + if (eltPos == NOT_FOUND_ON_STACK) { + errStartTagSeenWithoutRuby(name); + } else { + errUnclosedChildrenInRuby(); + } + } + appendToCurrentNodeAndPushElementMayFoster( + elementName, + attributes); + attributes = null; // CPP + break starttagloop; + case RT_OR_RP: + eltPos = findLastInScope("ruby"); + if (eltPos != NOT_FOUND_ON_STACK) { + generateImpliedEndTagsExceptFor("rtc"); + } + if (eltPos != currentPtr) { + if (!isCurrent("rtc")) { + if (eltPos == NOT_FOUND_ON_STACK) { + errStartTagSeenWithoutRuby(name); + } else { + errUnclosedChildrenInRuby(); + } + } + } + appendToCurrentNodeAndPushElementMayFoster( + elementName, + attributes); + attributes = null; // CPP + break starttagloop; + case MATH: + reconstructTheActiveFormattingElements(); + attributes.adjustForMath(); + if (selfClosing) { + appendVoidElementToCurrentMayFosterMathML( + elementName, attributes); + selfClosing = false; + } else { + appendToCurrentNodeAndPushElementMayFosterMathML( + elementName, attributes); + } + attributes = null; // CPP + break starttagloop; + case SVG: + reconstructTheActiveFormattingElements(); + attributes.adjustForSvg(); + if (selfClosing) { + appendVoidElementToCurrentMayFosterSVG( + elementName, + attributes); + selfClosing = false; + } else { + appendToCurrentNodeAndPushElementMayFosterSVG( + elementName, attributes); + } + attributes = null; // CPP + break starttagloop; + case CAPTION: + case COL: + case COLGROUP: + case TBODY_OR_THEAD_OR_TFOOT: + case TR: + case TD_OR_TH: + case FRAME: + case FRAMESET: + case HEAD: + errStrayStartTag(name); + break starttagloop; + case OUTPUT: + reconstructTheActiveFormattingElements(); + appendToCurrentNodeAndPushElementMayFoster( + elementName, + attributes, formPointer); + attributes = null; // CPP + break starttagloop; + default: + reconstructTheActiveFormattingElements(); + appendToCurrentNodeAndPushElementMayFoster( + elementName, + attributes); + attributes = null; // CPP + break starttagloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case IN_HEAD: + inheadloop: for (;;) { + switch (group) { + case HTML: + errStrayStartTag(name); + if (!fragment && !isTemplateContents()) { + addAttributesToHtml(attributes); + attributes = null; // CPP + } + break starttagloop; + case BASE: + case LINK_OR_BASEFONT_OR_BGSOUND: + appendVoidElementToCurrentMayFoster( + elementName, + attributes); + selfClosing = false; + attributes = null; // CPP + break starttagloop; + case META: + // Fall through to IN_HEAD_NOSCRIPT + break inheadloop; + case TITLE: + startTagTitleInHead(elementName, attributes); + attributes = null; // CPP + break starttagloop; + case NOSCRIPT: + if (scriptingEnabled) { + appendToCurrentNodeAndPushElement( + elementName, + attributes); + originalMode = mode; + mode = TEXT; + tokenizer.setStateAndEndTagExpectation( + Tokenizer.RAWTEXT, elementName); + } else { + appendToCurrentNodeAndPushElementMayFoster( + elementName, + attributes); + mode = IN_HEAD_NOSCRIPT; + } + attributes = null; // CPP + break starttagloop; + case SCRIPT: + startTagScriptInHead(elementName, attributes); + attributes = null; // CPP + break starttagloop; + case STYLE: + case NOFRAMES: + startTagGenericRawText(elementName, attributes); + attributes = null; // CPP + break starttagloop; + case HEAD: + /* Parse error. */ + errFooSeenWhenFooOpen(name); + /* Ignore the token. */ + break starttagloop; + case TEMPLATE: + startTagTemplateInHead(elementName, attributes); + attributes = null; // CPP + break starttagloop; + default: + pop(); + mode = AFTER_HEAD; + continue starttagloop; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case IN_HEAD_NOSCRIPT: + switch (group) { + case HTML: + // XXX did Hixie really mean to omit "base" + // here? + errStrayStartTag(name); + if (!fragment && !isTemplateContents()) { + addAttributesToHtml(attributes); + attributes = null; // CPP + } + break starttagloop; + case LINK_OR_BASEFONT_OR_BGSOUND: + appendVoidElementToCurrentMayFoster( + elementName, + attributes); + selfClosing = false; + attributes = null; // CPP + break starttagloop; + case META: + checkMetaCharset(attributes); + appendVoidElementToCurrentMayFoster( + elementName, + attributes); + selfClosing = false; + attributes = null; // CPP + break starttagloop; + case STYLE: + case NOFRAMES: + appendToCurrentNodeAndPushElement( + elementName, + attributes); + originalMode = mode; + mode = TEXT; + tokenizer.setStateAndEndTagExpectation( + Tokenizer.RAWTEXT, elementName); + attributes = null; // CPP + break starttagloop; + case HEAD: + errFooSeenWhenFooOpen(name); + break starttagloop; + case NOSCRIPT: + errFooSeenWhenFooOpen(name); + break starttagloop; + default: + errBadStartTagInNoscriptInHead(name); + pop(); + mode = IN_HEAD; + continue; + } + case IN_COLUMN_GROUP: + switch (group) { + case HTML: + errStrayStartTag(name); + if (!fragment && !isTemplateContents()) { + addAttributesToHtml(attributes); + attributes = null; // CPP + } + break starttagloop; + case COL: + appendVoidElementToCurrentMayFoster( + elementName, + attributes); + selfClosing = false; + attributes = null; // CPP + break starttagloop; + case TEMPLATE: + startTagTemplateInHead(elementName, attributes); + attributes = null; // CPP + break starttagloop; + default: + if (currentPtr == 0 || stack[currentPtr].getGroup() == TEMPLATE) { + assert fragment || isTemplateContents(); + errGarbageInColgroup(); + break starttagloop; + } + pop(); + mode = IN_TABLE; + continue; + } + case IN_SELECT_IN_TABLE: + switch (group) { + case CAPTION: + case TBODY_OR_THEAD_OR_TFOOT: + case TR: + case TD_OR_TH: + case TABLE: + errStartTagWithSelectOpen(name); + eltPos = findLastInTableScope("select"); + if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) { + assert fragment; + break starttagloop; // http://www.w3.org/Bugs/Public/show_bug.cgi?id=8375 + } + while (currentPtr >= eltPos) { + pop(); + } + resetTheInsertionMode(); + continue; + default: + // fall through to IN_SELECT + } + // CPPONLY: MOZ_FALLTHROUGH; + case IN_SELECT: + switch (group) { + case HTML: + errStrayStartTag(name); + if (!fragment) { + addAttributesToHtml(attributes); + attributes = null; // CPP + } + break starttagloop; + case OPTION: + if (isCurrent("option")) { + pop(); + } + appendToCurrentNodeAndPushElement( + elementName, + attributes); + attributes = null; // CPP + break starttagloop; + case OPTGROUP: + if (isCurrent("option")) { + pop(); + } + if (isCurrent("optgroup")) { + pop(); + } + appendToCurrentNodeAndPushElement( + elementName, + attributes); + attributes = null; // CPP + break starttagloop; + case SELECT: + errStartSelectWhereEndSelectExpected(); + eltPos = findLastInTableScope(name); + if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) { + assert fragment; + errNoSelectInTableScope(); + break starttagloop; + } else { + while (currentPtr >= eltPos) { + pop(); + } + resetTheInsertionMode(); + break starttagloop; + } + case INPUT: + case TEXTAREA: + errStartTagWithSelectOpen(name); + eltPos = findLastInTableScope("select"); + if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) { + assert fragment; + break starttagloop; + } + while (currentPtr >= eltPos) { + pop(); + } + resetTheInsertionMode(); + continue; + case SCRIPT: + startTagScriptInHead(elementName, attributes); + attributes = null; // CPP + break starttagloop; + case TEMPLATE: + startTagTemplateInHead(elementName, attributes); + attributes = null; // CPP + break starttagloop; + default: + errStrayStartTag(name); + break starttagloop; + } + case AFTER_BODY: + switch (group) { + case HTML: + errStrayStartTag(name); + if (!fragment && !isTemplateContents()) { + addAttributesToHtml(attributes); + attributes = null; // CPP + } + break starttagloop; + default: + errStrayStartTag(name); + mode = framesetOk ? FRAMESET_OK : IN_BODY; + continue; + } + case IN_FRAMESET: + switch (group) { + case FRAMESET: + appendToCurrentNodeAndPushElement( + elementName, + attributes); + attributes = null; // CPP + break starttagloop; + case FRAME: + appendVoidElementToCurrentMayFoster( + elementName, + attributes); + selfClosing = false; + attributes = null; // CPP + break starttagloop; + default: + // fall through to AFTER_FRAMESET + } + // CPPONLY: MOZ_FALLTHROUGH; + case AFTER_FRAMESET: + switch (group) { + case HTML: + errStrayStartTag(name); + if (!fragment && !isTemplateContents()) { + addAttributesToHtml(attributes); + attributes = null; // CPP + } + break starttagloop; + case NOFRAMES: + appendToCurrentNodeAndPushElement( + elementName, + attributes); + originalMode = mode; + mode = TEXT; + tokenizer.setStateAndEndTagExpectation( + Tokenizer.RAWTEXT, elementName); + attributes = null; // CPP + break starttagloop; + default: + errStrayStartTag(name); + break starttagloop; + } + case INITIAL: + /* + * Parse error. + */ + errStartTagWithoutDoctype(); + /* + * + * Set the document to quirks mode. + */ + documentModeInternal(DocumentMode.QUIRKS_MODE, null, null); + /* + * Then, switch to the root element mode of the tree + * construction stage + */ + mode = BEFORE_HTML; + /* + * and reprocess the current token. + */ + continue; + case BEFORE_HTML: + switch (group) { + case HTML: + // optimize error check and streaming SAX by + // hoisting + // "html" handling here. + if (attributes == HtmlAttributes.EMPTY_ATTRIBUTES) { + // This has the right magic side effect + // that + // it + // makes attributes in SAX Tree mutable. + appendHtmlElementToDocumentAndPush(); + } else { + appendHtmlElementToDocumentAndPush(attributes); + } + // XXX application cache should fire here + mode = BEFORE_HEAD; + attributes = null; // CPP + break starttagloop; + default: + /* + * Create an HTMLElement node with the tag name + * html, in the HTML namespace. Append it to the + * Document object. + */ + appendHtmlElementToDocumentAndPush(); + /* Switch to the main mode */ + mode = BEFORE_HEAD; + /* + * reprocess the current token. + */ + continue; + } + case BEFORE_HEAD: + switch (group) { + case HTML: + errStrayStartTag(name); + if (!fragment && !isTemplateContents()) { + addAttributesToHtml(attributes); + attributes = null; // CPP + } + break starttagloop; + case HEAD: + /* + * A start tag whose tag name is "head" + * + * Create an element for the token. + * + * Set the head element pointer to this new element + * node. + * + * Append the new element to the current node and + * push it onto the stack of open elements. + */ + appendToCurrentNodeAndPushHeadElement(attributes); + /* + * Change the insertion mode to "in head". + */ + mode = IN_HEAD; + attributes = null; // CPP + break starttagloop; + default: + /* + * Any other start tag token + * + * Act as if a start tag token with the tag name + * "head" and no attributes had been seen, + */ + appendToCurrentNodeAndPushHeadElement(HtmlAttributes.EMPTY_ATTRIBUTES); + mode = IN_HEAD; + /* + * then reprocess the current token. + * + * This will result in an empty head element being + * generated, with the current token being + * reprocessed in the "after head" insertion mode. + */ + continue; + } + case AFTER_HEAD: + switch (group) { + case HTML: + errStrayStartTag(name); + if (!fragment && !isTemplateContents()) { + addAttributesToHtml(attributes); + attributes = null; // CPP + } + break starttagloop; + case BODY: + if (attributes.getLength() == 0) { + // This has the right magic side effect + // that + // it + // makes attributes in SAX Tree mutable. + appendToCurrentNodeAndPushBodyElement(); + } else { + appendToCurrentNodeAndPushBodyElement(attributes); + } + framesetOk = false; + mode = IN_BODY; + attributes = null; // CPP + break starttagloop; + case FRAMESET: + appendToCurrentNodeAndPushElement( + elementName, + attributes); + mode = IN_FRAMESET; + attributes = null; // CPP + break starttagloop; + case TEMPLATE: + errFooBetweenHeadAndBody(name); + pushHeadPointerOntoStack(); + StackNode<T> headOnStack = stack[currentPtr]; + startTagTemplateInHead(elementName, attributes); + removeFromStack(headOnStack); + attributes = null; // CPP + break starttagloop; + case BASE: + case LINK_OR_BASEFONT_OR_BGSOUND: + errFooBetweenHeadAndBody(name); + pushHeadPointerOntoStack(); + appendVoidElementToCurrentMayFoster( + elementName, + attributes); + selfClosing = false; + pop(); // head + attributes = null; // CPP + break starttagloop; + case META: + errFooBetweenHeadAndBody(name); + checkMetaCharset(attributes); + pushHeadPointerOntoStack(); + appendVoidElementToCurrentMayFoster( + elementName, + attributes); + selfClosing = false; + pop(); // head + attributes = null; // CPP + break starttagloop; + case SCRIPT: + errFooBetweenHeadAndBody(name); + pushHeadPointerOntoStack(); + appendToCurrentNodeAndPushElement( + elementName, + attributes); + originalMode = mode; + mode = TEXT; + tokenizer.setStateAndEndTagExpectation( + Tokenizer.SCRIPT_DATA, elementName); + attributes = null; // CPP + break starttagloop; + case STYLE: + case NOFRAMES: + errFooBetweenHeadAndBody(name); + pushHeadPointerOntoStack(); + appendToCurrentNodeAndPushElement( + elementName, + attributes); + originalMode = mode; + mode = TEXT; + tokenizer.setStateAndEndTagExpectation( + Tokenizer.RAWTEXT, elementName); + attributes = null; // CPP + break starttagloop; + case TITLE: + errFooBetweenHeadAndBody(name); + pushHeadPointerOntoStack(); + appendToCurrentNodeAndPushElement( + elementName, + attributes); + originalMode = mode; + mode = TEXT; + tokenizer.setStateAndEndTagExpectation( + Tokenizer.RCDATA, elementName); + attributes = null; // CPP + break starttagloop; + case HEAD: + errStrayStartTag(name); + break starttagloop; + default: + appendToCurrentNodeAndPushBodyElement(); + mode = FRAMESET_OK; + continue; + } + case AFTER_AFTER_BODY: + switch (group) { + case HTML: + errStrayStartTag(name); + if (!fragment && !isTemplateContents()) { + addAttributesToHtml(attributes); + attributes = null; // CPP + } + break starttagloop; + default: + errStrayStartTag(name); + fatal(); + mode = framesetOk ? FRAMESET_OK : IN_BODY; + continue; + } + case AFTER_AFTER_FRAMESET: + switch (group) { + case HTML: + errStrayStartTag(name); + if (!fragment && !isTemplateContents()) { + addAttributesToHtml(attributes); + attributes = null; // CPP + } + break starttagloop; + case NOFRAMES: + startTagGenericRawText(elementName, attributes); + attributes = null; // CPP + break starttagloop; + default: + errStrayStartTag(name); + break starttagloop; + } + case TEXT: + assert false; + break starttagloop; // Avoid infinite loop if the assertion + // fails + } + } + if (selfClosing) { + errSelfClosing(); + } + // CPPONLY: if (mBuilder == null && attributes != HtmlAttributes.EMPTY_ATTRIBUTES) { + // CPPONLY: Portability.delete(attributes); + // CPPONLY: } + } + + private void startTagTitleInHead(ElementName elementName, HtmlAttributes attributes) throws SAXException { + appendToCurrentNodeAndPushElementMayFoster(elementName, attributes); + originalMode = mode; + mode = TEXT; + tokenizer.setStateAndEndTagExpectation(Tokenizer.RCDATA, elementName); + } + + private void startTagGenericRawText(ElementName elementName, HtmlAttributes attributes) throws SAXException { + appendToCurrentNodeAndPushElementMayFoster(elementName, attributes); + originalMode = mode; + mode = TEXT; + tokenizer.setStateAndEndTagExpectation(Tokenizer.RAWTEXT, elementName); + } + + private void startTagScriptInHead(ElementName elementName, HtmlAttributes attributes) throws SAXException { + // XXX need to manage much more stuff here if supporting document.write() + appendToCurrentNodeAndPushElementMayFoster(elementName, attributes); + originalMode = mode; + mode = TEXT; + tokenizer.setStateAndEndTagExpectation(Tokenizer.SCRIPT_DATA, elementName); + } + + private void startTagTemplateInHead(ElementName elementName, HtmlAttributes attributes) throws SAXException { + appendToCurrentNodeAndPushElement(elementName, attributes); + insertMarker(); + framesetOk = false; + originalMode = mode; + mode = IN_TEMPLATE; + pushTemplateMode(IN_TEMPLATE); + } + + private boolean isTemplateContents() { + return TreeBuilder.NOT_FOUND_ON_STACK != findLast("template"); + } + + private boolean isTemplateModeStackEmpty() { + return templateModePtr == -1; + } + + private boolean isSpecialParentInForeign(StackNode<T> stackNode) { + @NsUri String ns = stackNode.ns; + return ("http://www.w3.org/1999/xhtml" == ns) + || (stackNode.isHtmlIntegrationPoint()) + || (("http://www.w3.org/1998/Math/MathML" == ns) && (stackNode.getGroup() == MI_MO_MN_MS_MTEXT)); + } + + /** + * + * <p> + * C++ memory note: The return value must be released. + * + * @return + * @throws SAXException + * @throws StopSniffingException + */ + public static String extractCharsetFromContent(String attributeValue + // CPPONLY: , TreeBuilder tb + ) { + // This is a bit ugly. Converting the string to char array in order to + // make the portability layer smaller. + int charsetState = CHARSET_INITIAL; + int start = -1; + int end = -1; + @Auto char[] buffer = Portability.newCharArrayFromString(attributeValue); + + charsetloop: for (int i = 0; i < buffer.length; i++) { + char c = buffer[i]; + switch (charsetState) { + case CHARSET_INITIAL: + switch (c) { + case 'c': + case 'C': + charsetState = CHARSET_C; + continue; + default: + continue; + } + case CHARSET_C: + switch (c) { + case 'h': + case 'H': + charsetState = CHARSET_H; + continue; + default: + charsetState = CHARSET_INITIAL; + continue; + } + case CHARSET_H: + switch (c) { + case 'a': + case 'A': + charsetState = CHARSET_A; + continue; + default: + charsetState = CHARSET_INITIAL; + continue; + } + case CHARSET_A: + switch (c) { + case 'r': + case 'R': + charsetState = CHARSET_R; + continue; + default: + charsetState = CHARSET_INITIAL; + continue; + } + case CHARSET_R: + switch (c) { + case 's': + case 'S': + charsetState = CHARSET_S; + continue; + default: + charsetState = CHARSET_INITIAL; + continue; + } + case CHARSET_S: + switch (c) { + case 'e': + case 'E': + charsetState = CHARSET_E; + continue; + default: + charsetState = CHARSET_INITIAL; + continue; + } + case CHARSET_E: + switch (c) { + case 't': + case 'T': + charsetState = CHARSET_T; + continue; + default: + charsetState = CHARSET_INITIAL; + continue; + } + case CHARSET_T: + switch (c) { + case '\t': + case '\n': + case '\u000C': + case '\r': + case ' ': + continue; + case '=': + charsetState = CHARSET_EQUALS; + continue; + default: + return null; + } + case CHARSET_EQUALS: + switch (c) { + case '\t': + case '\n': + case '\u000C': + case '\r': + case ' ': + continue; + case '\'': + start = i + 1; + charsetState = CHARSET_SINGLE_QUOTED; + continue; + case '\"': + start = i + 1; + charsetState = CHARSET_DOUBLE_QUOTED; + continue; + default: + start = i; + charsetState = CHARSET_UNQUOTED; + continue; + } + case CHARSET_SINGLE_QUOTED: + switch (c) { + case '\'': + end = i; + break charsetloop; + default: + continue; + } + case CHARSET_DOUBLE_QUOTED: + switch (c) { + case '\"': + end = i; + break charsetloop; + default: + continue; + } + case CHARSET_UNQUOTED: + switch (c) { + case '\t': + case '\n': + case '\u000C': + case '\r': + case ' ': + case ';': + end = i; + break charsetloop; + default: + continue; + } + } + } + if (start != -1) { + if (end == -1) { + if (charsetState == CHARSET_UNQUOTED) { + end = buffer.length; + } else { + return null; + } + } + return Portability.newStringFromBuffer(buffer, start, end + - start + // CPPONLY: , tb, false + ); + } + return null; + } + + private void checkMetaCharset(HtmlAttributes attributes) + throws SAXException { + String charset = attributes.getValue(AttributeName.CHARSET); + if (charset != null) { + if (tokenizer.internalEncodingDeclaration(charset)) { + requestSuspension(); + return; + } + return; + } + if (!Portability.lowerCaseLiteralEqualsIgnoreAsciiCaseString( + "content-type", + attributes.getValue(AttributeName.HTTP_EQUIV))) { + return; + } + String content = attributes.getValue(AttributeName.CONTENT); + if (content != null) { + String extract = TreeBuilder.extractCharsetFromContent(content + // CPPONLY: , this + ); + // remember not to return early without releasing the string + if (extract != null) { + if (tokenizer.internalEncodingDeclaration(extract)) { + requestSuspension(); + } + } + Portability.releaseString(extract); + } + } + + public final void endTag(ElementName elementName) throws SAXException { + flushCharacters(); + needToDropLF = false; + int eltPos; + int group = elementName.getGroup(); + @Local String name = elementName.getName(); + endtagloop: for (;;) { + if (isInForeign()) { + if (stack[currentPtr].name != name) { + if (currentPtr == 0) { + errStrayEndTag(name); + } else { + errEndTagDidNotMatchCurrentOpenElement(name, stack[currentPtr].popName); + } + } + eltPos = currentPtr; + int origPos = currentPtr; + for (;;) { + if (eltPos == 0) { + assert fragment: "We can get this close to the root of the stack in foreign content only in the fragment case."; + break endtagloop; + } + if (stack[eltPos].name == name) { + while (currentPtr >= eltPos) { + popForeign(origPos, eltPos); + } + break endtagloop; + } + if (stack[--eltPos].ns == "http://www.w3.org/1999/xhtml") { + break; + } + } + } + switch (mode) { + case IN_TEMPLATE: + switch (group) { + case TEMPLATE: + // fall through to IN_HEAD + break; + default: + errStrayEndTag(name); + break endtagloop; + } + // CPPONLY: MOZ_FALLTHROUGH; + case IN_ROW: + switch (group) { + case TR: + eltPos = findLastOrRoot(TreeBuilder.TR); + if (eltPos == 0) { + assert fragment || isTemplateContents(); + errNoTableRowToClose(); + break endtagloop; + } + clearStackBackTo(eltPos); + pop(); + mode = IN_TABLE_BODY; + break endtagloop; + case TABLE: + eltPos = findLastOrRoot(TreeBuilder.TR); + if (eltPos == 0) { + assert fragment || isTemplateContents(); + errNoTableRowToClose(); + break endtagloop; + } + clearStackBackTo(eltPos); + pop(); + mode = IN_TABLE_BODY; + continue; + case TBODY_OR_THEAD_OR_TFOOT: + if (findLastInTableScope(name) == TreeBuilder.NOT_FOUND_ON_STACK) { + errStrayEndTag(name); + break endtagloop; + } + eltPos = findLastOrRoot(TreeBuilder.TR); + if (eltPos == 0) { + assert fragment || isTemplateContents(); + errNoTableRowToClose(); + break endtagloop; + } + clearStackBackTo(eltPos); + pop(); + mode = IN_TABLE_BODY; + continue; + case BODY: + case CAPTION: + case COL: + case COLGROUP: + case HTML: + case TD_OR_TH: + errStrayEndTag(name); + break endtagloop; + default: + // fall through to IN_TABLE + } + // CPPONLY: MOZ_FALLTHROUGH; + case IN_TABLE_BODY: + switch (group) { + case TBODY_OR_THEAD_OR_TFOOT: + eltPos = findLastOrRoot(name); + if (eltPos == 0) { + errStrayEndTag(name); + break endtagloop; + } + clearStackBackTo(eltPos); + pop(); + mode = IN_TABLE; + break endtagloop; + case TABLE: + eltPos = findLastInTableScopeOrRootTemplateTbodyTheadTfoot(); + if (eltPos == 0 || stack[eltPos].getGroup() == TEMPLATE) { + assert fragment || isTemplateContents(); + errStrayEndTag(name); + break endtagloop; + } + clearStackBackTo(eltPos); + pop(); + mode = IN_TABLE; + continue; + case BODY: + case CAPTION: + case COL: + case COLGROUP: + case HTML: + case TD_OR_TH: + case TR: + errStrayEndTag(name); + break endtagloop; + default: + // fall through to IN_TABLE + } + // CPPONLY: MOZ_FALLTHROUGH; + case IN_TABLE: + switch (group) { + case TABLE: + eltPos = findLast("table"); + if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) { + assert fragment || isTemplateContents(); + errStrayEndTag(name); + break endtagloop; + } + while (currentPtr >= eltPos) { + pop(); + } + resetTheInsertionMode(); + break endtagloop; + case BODY: + case CAPTION: + case COL: + case COLGROUP: + case HTML: + case TBODY_OR_THEAD_OR_TFOOT: + case TD_OR_TH: + case TR: + errStrayEndTag(name); + break endtagloop; + case TEMPLATE: + // fall through to IN_HEAD + break; + default: + errStrayEndTag(name); + // fall through to IN_BODY + } + // CPPONLY: MOZ_FALLTHROUGH; + case IN_CAPTION: + switch (group) { + case CAPTION: + eltPos = findLastInTableScope("caption"); + if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) { + break endtagloop; + } + generateImpliedEndTags(); + if (errorHandler != null && currentPtr != eltPos) { + errUnclosedElements(eltPos, name); + } + while (currentPtr >= eltPos) { + pop(); + } + clearTheListOfActiveFormattingElementsUpToTheLastMarker(); + mode = IN_TABLE; + break endtagloop; + case TABLE: + eltPos = findLastInTableScope("caption"); + + if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) { + assert fragment || isTemplateContents(); + errStrayEndTag(name); + break endtagloop; + } + generateImpliedEndTags(); + if (errorHandler != null && currentPtr != eltPos) { + errUnclosedElements(eltPos, name); + } + while (currentPtr >= eltPos) { + pop(); + } + clearTheListOfActiveFormattingElementsUpToTheLastMarker(); + mode = IN_TABLE; + continue; + case BODY: + case COL: + case COLGROUP: + case HTML: + case TBODY_OR_THEAD_OR_TFOOT: + case TD_OR_TH: + case TR: + errStrayEndTag(name); + break endtagloop; + default: + // fall through to IN_BODY + } + // CPPONLY: MOZ_FALLTHROUGH; + case IN_CELL: + switch (group) { + case TD_OR_TH: + eltPos = findLastInTableScope(name); + if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) { + errStrayEndTag(name); + break endtagloop; + } + generateImpliedEndTags(); + if (errorHandler != null && !isCurrent(name)) { + errUnclosedElements(eltPos, name); + } + while (currentPtr >= eltPos) { + pop(); + } + clearTheListOfActiveFormattingElementsUpToTheLastMarker(); + mode = IN_ROW; + break endtagloop; + case TABLE: + case TBODY_OR_THEAD_OR_TFOOT: + case TR: + if (findLastInTableScope(name) == TreeBuilder.NOT_FOUND_ON_STACK) { + assert name == "tbody" || name == "tfoot" || name == "thead" || fragment || isTemplateContents(); + errStrayEndTag(name); + break endtagloop; + } + closeTheCell(findLastInTableScopeTdTh()); + continue; + case BODY: + case CAPTION: + case COL: + case COLGROUP: + case HTML: + errStrayEndTag(name); + break endtagloop; + default: + // fall through to IN_BODY + } + // CPPONLY: MOZ_FALLTHROUGH; + case FRAMESET_OK: + case IN_BODY: + switch (group) { + case BODY: + if (!isSecondOnStackBody()) { + assert fragment || isTemplateContents(); + errStrayEndTag(name); + break endtagloop; + } + assert currentPtr >= 1; + if (errorHandler != null) { + uncloseloop1: for (int i = 2; i <= currentPtr; i++) { + switch (stack[i].getGroup()) { + case DD_OR_DT: + case LI: + case OPTGROUP: + case OPTION: // is this possible? + case P: + case RB_OR_RTC: + case RT_OR_RP: + case TD_OR_TH: + case TBODY_OR_THEAD_OR_TFOOT: + break; + default: + errEndWithUnclosedElements(name); + break uncloseloop1; + } + } + } + mode = AFTER_BODY; + break endtagloop; + case HTML: + if (!isSecondOnStackBody()) { + assert fragment || isTemplateContents(); + errStrayEndTag(name); + break endtagloop; + } + if (errorHandler != null) { + uncloseloop2: for (int i = 0; i <= currentPtr; i++) { + switch (stack[i].getGroup()) { + case DD_OR_DT: + case LI: + case P: + case RB_OR_RTC: + case RT_OR_RP: + case TBODY_OR_THEAD_OR_TFOOT: + case TD_OR_TH: + case BODY: + case HTML: + break; + default: + errEndWithUnclosedElements(name); + break uncloseloop2; + } + } + } + mode = AFTER_BODY; + continue; + case DIV_OR_BLOCKQUOTE_OR_CENTER_OR_MENU: + case UL_OR_OL_OR_DL: + case PRE_OR_LISTING: + case FIELDSET: + case BUTTON: + case ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY: + eltPos = findLastInScope(name); + if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) { + errStrayEndTag(name); + } else { + generateImpliedEndTags(); + if (errorHandler != null && !isCurrent(name)) { + errUnclosedElements(eltPos, name); + } + while (currentPtr >= eltPos) { + pop(); + } + } + break endtagloop; + case FORM: + if (!isTemplateContents()) { + if (formPointer == null) { + errStrayEndTag(name); + break endtagloop; + } + formPointer = null; + eltPos = findLastInScope(name); + if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) { + errStrayEndTag(name); + break endtagloop; + } + generateImpliedEndTags(); + if (errorHandler != null && !isCurrent(name)) { + errUnclosedElements(eltPos, name); + } + removeFromStack(eltPos); + break endtagloop; + } else { + eltPos = findLastInScope(name); + if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) { + errStrayEndTag(name); + break endtagloop; + } + generateImpliedEndTags(); + if (errorHandler != null && !isCurrent(name)) { + errUnclosedElements(eltPos, name); + } + while (currentPtr >= eltPos) { + pop(); + } + break endtagloop; + } + case P: + eltPos = findLastInButtonScope("p"); + if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) { + errNoElementToCloseButEndTagSeen("p"); + // XXX Can the 'in foreign' case happen anymore? + if (isInForeign()) { + errHtmlStartTagInForeignContext(name); + // Check for currentPtr for the fragment + // case. + while (currentPtr >= 0 && stack[currentPtr].ns != "http://www.w3.org/1999/xhtml") { + pop(); + } + } + appendVoidElementToCurrentMayFoster( + elementName, + HtmlAttributes.EMPTY_ATTRIBUTES); + break endtagloop; + } + generateImpliedEndTagsExceptFor("p"); + assert eltPos != TreeBuilder.NOT_FOUND_ON_STACK; + if (errorHandler != null && eltPos != currentPtr) { + errUnclosedElements(eltPos, name); + } + while (currentPtr >= eltPos) { + pop(); + } + break endtagloop; + case LI: + eltPos = findLastInListScope(name); + if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) { + errNoElementToCloseButEndTagSeen(name); + } else { + generateImpliedEndTagsExceptFor(name); + if (errorHandler != null + && eltPos != currentPtr) { + errUnclosedElements(eltPos, name); + } + while (currentPtr >= eltPos) { + pop(); + } + } + break endtagloop; + case DD_OR_DT: + eltPos = findLastInScope(name); + if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) { + errNoElementToCloseButEndTagSeen(name); + } else { + generateImpliedEndTagsExceptFor(name); + if (errorHandler != null + && eltPos != currentPtr) { + errUnclosedElements(eltPos, name); + } + while (currentPtr >= eltPos) { + pop(); + } + } + break endtagloop; + case H1_OR_H2_OR_H3_OR_H4_OR_H5_OR_H6: + eltPos = findLastInScopeHn(); + if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) { + errStrayEndTag(name); + } else { + generateImpliedEndTags(); + if (errorHandler != null && !isCurrent(name)) { + errUnclosedElements(eltPos, name); + } + while (currentPtr >= eltPos) { + pop(); + } + } + break endtagloop; + case OBJECT: + case MARQUEE_OR_APPLET: + eltPos = findLastInScope(name); + if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) { + errStrayEndTag(name); + } else { + generateImpliedEndTags(); + if (errorHandler != null && !isCurrent(name)) { + errUnclosedElements(eltPos, name); + } + while (currentPtr >= eltPos) { + pop(); + } + clearTheListOfActiveFormattingElementsUpToTheLastMarker(); + } + break endtagloop; + case BR: + errEndTagBr(); + if (isInForeign()) { + // XXX can this happen anymore? + errHtmlStartTagInForeignContext(name); + // Check for currentPtr for the fragment + // case. + while (currentPtr >= 0 && stack[currentPtr].ns != "http://www.w3.org/1999/xhtml") { + pop(); + } + } + reconstructTheActiveFormattingElements(); + appendVoidElementToCurrentMayFoster( + elementName, + HtmlAttributes.EMPTY_ATTRIBUTES); + break endtagloop; + case TEMPLATE: + // fall through to IN_HEAD; + break; + case AREA_OR_WBR: + case KEYGEN: // XXX?? + case PARAM_OR_SOURCE_OR_TRACK: + case EMBED: + case IMG: + case IMAGE: + case INPUT: + case HR: + case IFRAME: + case NOEMBED: // XXX??? + case NOFRAMES: // XXX?? + case SELECT: + case TABLE: + case TEXTAREA: // XXX?? + errStrayEndTag(name); + break endtagloop; + case NOSCRIPT: + if (scriptingEnabled) { + errStrayEndTag(name); + break endtagloop; + } + // CPPONLY: MOZ_FALLTHROUGH; + case A: + case B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U: + case FONT: + case NOBR: + if (adoptionAgencyEndTag(name)) { + break endtagloop; + } + // else handle like any other tag + // CPPONLY: MOZ_FALLTHROUGH; + default: + if (isCurrent(name)) { + pop(); + break endtagloop; + } + + eltPos = currentPtr; + for (;;) { + StackNode<T> node = stack[eltPos]; + if (node.ns == "http://www.w3.org/1999/xhtml" && node.name == name) { + generateImpliedEndTags(); + if (errorHandler != null + && !isCurrent(name)) { + errUnclosedElements(eltPos, name); + } + while (currentPtr >= eltPos) { + pop(); + } + break endtagloop; + } else if (eltPos == 0 || node.isSpecial()) { + errStrayEndTag(name); + break endtagloop; + } + eltPos--; + } + } + // CPPONLY: MOZ_FALLTHROUGH; + case IN_HEAD: + switch (group) { + case HEAD: + pop(); + mode = AFTER_HEAD; + break endtagloop; + case BR: + case HTML: + case BODY: + pop(); + mode = AFTER_HEAD; + continue; + case TEMPLATE: + endTagTemplateInHead(); + break endtagloop; + default: + errStrayEndTag(name); + break endtagloop; + } + case IN_HEAD_NOSCRIPT: + switch (group) { + case NOSCRIPT: + pop(); + mode = IN_HEAD; + break endtagloop; + case BR: + errStrayEndTag(name); + pop(); + mode = IN_HEAD; + continue; + default: + errStrayEndTag(name); + break endtagloop; + } + case IN_COLUMN_GROUP: + switch (group) { + case COLGROUP: + if (currentPtr == 0 || stack[currentPtr].getGroup() == + TreeBuilder.TEMPLATE) { + assert fragment || isTemplateContents(); + errGarbageInColgroup(); + break endtagloop; + } + pop(); + mode = IN_TABLE; + break endtagloop; + case COL: + errStrayEndTag(name); + break endtagloop; + case TEMPLATE: + endTagTemplateInHead(); + break endtagloop; + default: + if (currentPtr == 0 || stack[currentPtr].getGroup() == + TreeBuilder.TEMPLATE) { + assert fragment || isTemplateContents(); + errGarbageInColgroup(); + break endtagloop; + } + pop(); + mode = IN_TABLE; + continue; + } + case IN_SELECT_IN_TABLE: + switch (group) { + case CAPTION: + case TABLE: + case TBODY_OR_THEAD_OR_TFOOT: + case TR: + case TD_OR_TH: + errEndTagSeenWithSelectOpen(name); + if (findLastInTableScope(name) != TreeBuilder.NOT_FOUND_ON_STACK) { + eltPos = findLastInTableScope("select"); + if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) { + assert fragment; + break endtagloop; // http://www.w3.org/Bugs/Public/show_bug.cgi?id=8375 + } + while (currentPtr >= eltPos) { + pop(); + } + resetTheInsertionMode(); + continue; + } else { + break endtagloop; + } + default: + // fall through to IN_SELECT + } + // CPPONLY: MOZ_FALLTHROUGH; + case IN_SELECT: + switch (group) { + case OPTION: + if (isCurrent("option")) { + pop(); + break endtagloop; + } else { + errStrayEndTag(name); + break endtagloop; + } + case OPTGROUP: + if (isCurrent("option") + && "optgroup" == stack[currentPtr - 1].name) { + pop(); + } + if (isCurrent("optgroup")) { + pop(); + } else { + errStrayEndTag(name); + } + break endtagloop; + case SELECT: + eltPos = findLastInTableScope("select"); + if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) { + assert fragment; + errStrayEndTag(name); + break endtagloop; + } + while (currentPtr >= eltPos) { + pop(); + } + resetTheInsertionMode(); + break endtagloop; + case TEMPLATE: + endTagTemplateInHead(); + break endtagloop; + default: + errStrayEndTag(name); + break endtagloop; + } + case AFTER_BODY: + switch (group) { + case HTML: + if (fragment) { + errStrayEndTag(name); + break endtagloop; + } else { + mode = AFTER_AFTER_BODY; + break endtagloop; + } + default: + errEndTagAfterBody(); + mode = framesetOk ? FRAMESET_OK : IN_BODY; + continue; + } + case IN_FRAMESET: + switch (group) { + case FRAMESET: + if (currentPtr == 0) { + assert fragment; + errStrayEndTag(name); + break endtagloop; + } + pop(); + if ((!fragment) && !isCurrent("frameset")) { + mode = AFTER_FRAMESET; + } + break endtagloop; + default: + errStrayEndTag(name); + break endtagloop; + } + case AFTER_FRAMESET: + switch (group) { + case HTML: + mode = AFTER_AFTER_FRAMESET; + break endtagloop; + default: + errStrayEndTag(name); + break endtagloop; + } + case INITIAL: + /* + * Parse error. + */ + errEndTagSeenWithoutDoctype(); + /* + * + * Set the document to quirks mode. + */ + documentModeInternal(DocumentMode.QUIRKS_MODE, null, null); + /* + * Then, switch to the root element mode of the tree + * construction stage + */ + mode = BEFORE_HTML; + /* + * and reprocess the current token. + */ + continue; + case BEFORE_HTML: + switch (group) { + case HEAD: + case BR: + case HTML: + case BODY: + /* + * Create an HTMLElement node with the tag name + * html, in the HTML namespace. Append it to the + * Document object. + */ + appendHtmlElementToDocumentAndPush(); + /* Switch to the main mode */ + mode = BEFORE_HEAD; + /* + * reprocess the current token. + */ + continue; + default: + errStrayEndTag(name); + break endtagloop; + } + case BEFORE_HEAD: + switch (group) { + case HEAD: + case BR: + case HTML: + case BODY: + appendToCurrentNodeAndPushHeadElement(HtmlAttributes.EMPTY_ATTRIBUTES); + mode = IN_HEAD; + continue; + default: + errStrayEndTag(name); + break endtagloop; + } + case AFTER_HEAD: + switch (group) { + case TEMPLATE: + endTagTemplateInHead(); + break endtagloop; + case HTML: + case BODY: + case BR: + appendToCurrentNodeAndPushBodyElement(); + mode = FRAMESET_OK; + continue; + default: + errStrayEndTag(name); + break endtagloop; + } + case AFTER_AFTER_BODY: + errStrayEndTag(name); + mode = framesetOk ? FRAMESET_OK : IN_BODY; + continue; + case AFTER_AFTER_FRAMESET: + errStrayEndTag(name); + break endtagloop; + case TEXT: + // XXX need to manage insertion point here + pop(); + if (originalMode == AFTER_HEAD) { + silentPop(); + } + mode = originalMode; + break endtagloop; + } + } // endtagloop + } + + private void endTagTemplateInHead() throws SAXException { + int eltPos = findLast("template"); + if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) { + errStrayEndTag("template"); + return; + } + generateImpliedEndTagsThoroughly(); + if (errorHandler != null && !isCurrent("template")) { + errUnclosedElements(eltPos, "template"); + } + while (currentPtr >= eltPos) { + pop(); + } + clearTheListOfActiveFormattingElementsUpToTheLastMarker(); + popTemplateMode(); + resetTheInsertionMode(); + } + + private int findLastInTableScopeOrRootTemplateTbodyTheadTfoot() { + for (int i = currentPtr; i > 0; i--) { + if (stack[i].ns == "http://www.w3.org/1999/xhtml" + && (stack[i].getGroup() == TreeBuilder.TBODY_OR_THEAD_OR_TFOOT + || stack[i].getGroup() == TreeBuilder.TEMPLATE)) { + return i; + } + } + return 0; + } + + private int findLast(@Local String name) { + for (int i = currentPtr; i > 0; i--) { + if (stack[i].ns == "http://www.w3.org/1999/xhtml" && stack[i].name == name) { + return i; + } + } + return TreeBuilder.NOT_FOUND_ON_STACK; + } + + private int findLastInTableScope(@Local String name) { + for (int i = currentPtr; i > 0; i--) { + if (stack[i].ns == "http://www.w3.org/1999/xhtml") { + if (stack[i].name == name) { + return i; + } else if (stack[i].name == "table" || stack[i].name == "template") { + return TreeBuilder.NOT_FOUND_ON_STACK; + } + } + } + return TreeBuilder.NOT_FOUND_ON_STACK; + } + + private int findLastInButtonScope(@Local String name) { + for (int i = currentPtr; i > 0; i--) { + if (stack[i].ns == "http://www.w3.org/1999/xhtml") { + if (stack[i].name == name) { + return i; + } else if (stack[i].name == "button") { + return TreeBuilder.NOT_FOUND_ON_STACK; + } + } + + if (stack[i].isScoping()) { + return TreeBuilder.NOT_FOUND_ON_STACK; + } + } + return TreeBuilder.NOT_FOUND_ON_STACK; + } + + private int findLastInScope(@Local String name) { + for (int i = currentPtr; i > 0; i--) { + if (stack[i].ns == "http://www.w3.org/1999/xhtml" && stack[i].name == name) { + return i; + } else if (stack[i].isScoping()) { + return TreeBuilder.NOT_FOUND_ON_STACK; + } + } + return TreeBuilder.NOT_FOUND_ON_STACK; + } + + private int findLastInListScope(@Local String name) { + for (int i = currentPtr; i > 0; i--) { + if (stack[i].ns == "http://www.w3.org/1999/xhtml") { + if (stack[i].name == name) { + return i; + } else if (stack[i].name == "ul" || stack[i].name == "ol") { + return TreeBuilder.NOT_FOUND_ON_STACK; + } + } + + if (stack[i].isScoping()) { + return TreeBuilder.NOT_FOUND_ON_STACK; + } + } + return TreeBuilder.NOT_FOUND_ON_STACK; + } + + private int findLastInScopeHn() { + for (int i = currentPtr; i > 0; i--) { + if (stack[i].getGroup() == TreeBuilder.H1_OR_H2_OR_H3_OR_H4_OR_H5_OR_H6) { + return i; + } else if (stack[i].isScoping()) { + return TreeBuilder.NOT_FOUND_ON_STACK; + } + } + return TreeBuilder.NOT_FOUND_ON_STACK; + } + + private void generateImpliedEndTagsExceptFor(@Local String name) + throws SAXException { + for (;;) { + StackNode<T> node = stack[currentPtr]; + switch (node.getGroup()) { + case P: + case LI: + case DD_OR_DT: + case OPTION: + case OPTGROUP: + case RB_OR_RTC: + case RT_OR_RP: + if (node.ns == "http://www.w3.org/1999/xhtml" && node.name == name) { + return; + } + pop(); + continue; + default: + return; + } + } + } + + private void generateImpliedEndTags() throws SAXException { + for (;;) { + switch (stack[currentPtr].getGroup()) { + case P: + case LI: + case DD_OR_DT: + case OPTION: + case OPTGROUP: + case RB_OR_RTC: + case RT_OR_RP: + pop(); + continue; + default: + return; + } + } + } + + private void generateImpliedEndTagsThoroughly() throws SAXException { + for (;;) { + switch (stack[currentPtr].getGroup()) { + case CAPTION: + case COLGROUP: + case DD_OR_DT: + case LI: + case OPTGROUP: + case OPTION: + case P: + case RB_OR_RTC: + case RT_OR_RP: + case TBODY_OR_THEAD_OR_TFOOT: + case TD_OR_TH: + case TR: + pop(); + continue; + default: + return; + } + } + } + + private boolean isSecondOnStackBody() { + return currentPtr >= 1 && stack[1].getGroup() == TreeBuilder.BODY; + } + + private void documentModeInternal(DocumentMode m, String publicIdentifier, + String systemIdentifier) + throws SAXException { + + if (forceNoQuirks) { + // Srcdoc documents are always rendered in standards mode. + quirks = false; + if (documentModeHandler != null) { + documentModeHandler.documentMode( + DocumentMode.STANDARDS_MODE + // [NOCPP[ + , null, null + // ]NOCPP] + ); + } + return; + } + + quirks = (m == DocumentMode.QUIRKS_MODE); + if (documentModeHandler != null) { + documentModeHandler.documentMode( + m + // [NOCPP[ + , publicIdentifier, systemIdentifier + // ]NOCPP] + ); + } + // [NOCPP[ + documentMode(m, publicIdentifier, systemIdentifier); + // ]NOCPP] + } + + private boolean isAlmostStandards(String publicIdentifier, + String systemIdentifier) { + if (Portability.lowerCaseLiteralIsPrefixOfIgnoreAsciiCaseString( + "-//w3c//dtd xhtml 1.0 transitional//", publicIdentifier)) { + return true; + } + if (Portability.lowerCaseLiteralIsPrefixOfIgnoreAsciiCaseString( + "-//w3c//dtd xhtml 1.0 frameset//", publicIdentifier)) { + return true; + } + if (systemIdentifier != null) { + if (Portability.lowerCaseLiteralIsPrefixOfIgnoreAsciiCaseString( + "-//w3c//dtd html 4.01 transitional//", publicIdentifier)) { + return true; + } + if (Portability.lowerCaseLiteralIsPrefixOfIgnoreAsciiCaseString( + "-//w3c//dtd html 4.01 frameset//", publicIdentifier)) { + return true; + } + } + return false; + } + + private boolean isQuirky(@Local String name, String publicIdentifier, + String systemIdentifier, boolean forceQuirks) { + if (forceQuirks) { + return true; + } + if (name != HTML_LOCAL) { + return true; + } + if (publicIdentifier != null) { + for (int i = 0; i < TreeBuilder.QUIRKY_PUBLIC_IDS.length; i++) { + if (Portability.lowerCaseLiteralIsPrefixOfIgnoreAsciiCaseString( + TreeBuilder.QUIRKY_PUBLIC_IDS[i], publicIdentifier)) { + return true; + } + } + if (Portability.lowerCaseLiteralEqualsIgnoreAsciiCaseString( + "-//w3o//dtd w3 html strict 3.0//en//", publicIdentifier) + || Portability.lowerCaseLiteralEqualsIgnoreAsciiCaseString( + "-/w3c/dtd html 4.0 transitional/en", + publicIdentifier) + || Portability.lowerCaseLiteralEqualsIgnoreAsciiCaseString( + "html", publicIdentifier)) { + return true; + } + } + if (systemIdentifier == null) { + if (Portability.lowerCaseLiteralIsPrefixOfIgnoreAsciiCaseString( + "-//w3c//dtd html 4.01 transitional//", publicIdentifier)) { + return true; + } else if (Portability.lowerCaseLiteralIsPrefixOfIgnoreAsciiCaseString( + "-//w3c//dtd html 4.01 frameset//", publicIdentifier)) { + return true; + } + } else if (Portability.lowerCaseLiteralEqualsIgnoreAsciiCaseString( + "http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd", + systemIdentifier)) { + return true; + } + return false; + } + + private void closeTheCell(int eltPos) throws SAXException { + generateImpliedEndTags(); + if (errorHandler != null && eltPos != currentPtr) { + errUnclosedElementsCell(eltPos); + } + while (currentPtr >= eltPos) { + pop(); + } + clearTheListOfActiveFormattingElementsUpToTheLastMarker(); + mode = IN_ROW; + return; + } + + private int findLastInTableScopeTdTh() { + for (int i = currentPtr; i > 0; i--) { + @Local String name = stack[i].name; + if (stack[i].ns == "http://www.w3.org/1999/xhtml") { + if ("td" == name || "th" == name) { + return i; + } else if (name == "table" || name == "template") { + return TreeBuilder.NOT_FOUND_ON_STACK; + } + } + } + return TreeBuilder.NOT_FOUND_ON_STACK; + } + + private void clearStackBackTo(int eltPos) throws SAXException { + int eltGroup = stack[eltPos].getGroup(); + while (currentPtr > eltPos) { // > not >= intentional + if (stack[currentPtr].ns == "http://www.w3.org/1999/xhtml" + && stack[currentPtr].getGroup() == TEMPLATE + && (eltGroup == TABLE || eltGroup == TBODY_OR_THEAD_OR_TFOOT|| eltGroup == TR || eltPos == 0)) { + return; + } + pop(); + } + } + + private void resetTheInsertionMode() { + StackNode<T> node; + @Local String name; + @NsUri String ns; + for (int i = currentPtr; i >= 0; i--) { + node = stack[i]; + name = node.name; + ns = node.ns; + if (i == 0) { + if (!(contextNamespace == "http://www.w3.org/1999/xhtml" && (contextName == "td" || contextName == "th"))) { + if (fragment) { + // Make sure we are parsing a fragment otherwise the context element doesn't make sense. + name = contextName; + ns = contextNamespace; + } + } else { + mode = framesetOk ? FRAMESET_OK : IN_BODY; // XXX from Hixie's email + return; + } + } + if ("select" == name) { + int ancestorIndex = i; + while (ancestorIndex > 0) { + StackNode<T> ancestor = stack[ancestorIndex--]; + if ("http://www.w3.org/1999/xhtml" == ancestor.ns) { + if ("template" == ancestor.name) { + break; + } + if ("table" == ancestor.name) { + mode = IN_SELECT_IN_TABLE; + return; + } + } + } + mode = IN_SELECT; + return; + } else if ("td" == name || "th" == name) { + mode = IN_CELL; + return; + } else if ("tr" == name) { + mode = IN_ROW; + return; + } else if ("tbody" == name || "thead" == name || "tfoot" == name) { + mode = IN_TABLE_BODY; + return; + } else if ("caption" == name) { + mode = IN_CAPTION; + return; + } else if ("colgroup" == name) { + mode = IN_COLUMN_GROUP; + return; + } else if ("table" == name) { + mode = IN_TABLE; + return; + } else if ("http://www.w3.org/1999/xhtml" != ns) { + mode = framesetOk ? FRAMESET_OK : IN_BODY; + return; + } else if ("template" == name) { + assert templateModePtr >= 0; + mode = templateModeStack[templateModePtr]; + return; + } else if ("head" == name) { + if (name == contextName) { + mode = framesetOk ? FRAMESET_OK : IN_BODY; // really + } else { + mode = IN_HEAD; + } + return; + } else if ("body" == name) { + mode = framesetOk ? FRAMESET_OK : IN_BODY; + return; + } else if ("frameset" == name) { + // TODO: Fragment case. Add error reporting. + mode = IN_FRAMESET; + return; + } else if ("html" == name) { + if (headPointer == null) { + // TODO: Fragment case. Add error reporting. + mode = BEFORE_HEAD; + } else { + mode = AFTER_HEAD; + } + return; + } else if (i == 0) { + mode = framesetOk ? FRAMESET_OK : IN_BODY; + return; + } + } + } + + /** + * @throws SAXException + * + */ + private void implicitlyCloseP() throws SAXException { + int eltPos = findLastInButtonScope("p"); + if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) { + return; + } + generateImpliedEndTagsExceptFor("p"); + if (errorHandler != null && eltPos != currentPtr) { + errUnclosedElementsImplied(eltPos, "p"); + } + while (currentPtr >= eltPos) { + pop(); + } + } + + private boolean debugOnlyClearLastStackSlot() { + stack[currentPtr] = null; + return true; + } + + private boolean debugOnlyClearLastListSlot() { + listOfActiveFormattingElements[listPtr] = null; + return true; + } + + private void pushTemplateMode(int mode) { + templateModePtr++; + if (templateModePtr == templateModeStack.length) { + int[] newStack = new int[templateModeStack.length + 64]; + System.arraycopy(templateModeStack, 0, newStack, 0, templateModeStack.length); + templateModeStack = newStack; + } + templateModeStack[templateModePtr] = mode; + } + + @SuppressWarnings("unchecked") private void push(StackNode<T> node) throws SAXException { + currentPtr++; + if (currentPtr == stack.length) { + StackNode<T>[] newStack = new StackNode[stack.length + 64]; + System.arraycopy(stack, 0, newStack, 0, stack.length); + stack = newStack; + } + stack[currentPtr] = node; + elementPushed(node.ns, node.popName, node.node); + } + + @SuppressWarnings("unchecked") private void silentPush(StackNode<T> node) throws SAXException { + currentPtr++; + if (currentPtr == stack.length) { + StackNode<T>[] newStack = new StackNode[stack.length + 64]; + System.arraycopy(stack, 0, newStack, 0, stack.length); + stack = newStack; + } + stack[currentPtr] = node; + } + + @SuppressWarnings("unchecked") private void append(StackNode<T> node) { + listPtr++; + if (listPtr == listOfActiveFormattingElements.length) { + StackNode<T>[] newList = new StackNode[listOfActiveFormattingElements.length + 64]; + System.arraycopy(listOfActiveFormattingElements, 0, newList, 0, + listOfActiveFormattingElements.length); + listOfActiveFormattingElements = newList; + } + listOfActiveFormattingElements[listPtr] = node; + } + + @Inline private void insertMarker() { + append(null); + } + + private void clearTheListOfActiveFormattingElementsUpToTheLastMarker() { + while (listPtr > -1) { + if (listOfActiveFormattingElements[listPtr] == null) { + --listPtr; + return; + } + listOfActiveFormattingElements[listPtr].release(this); + --listPtr; + } + } + + @Inline private boolean isCurrent(@Local String name) { + return stack[currentPtr].ns == "http://www.w3.org/1999/xhtml" && + name == stack[currentPtr].name; + } + + private void removeFromStack(int pos) throws SAXException { + if (currentPtr == pos) { + pop(); + } else { + fatal(); + stack[pos].release(this); + System.arraycopy(stack, pos + 1, stack, pos, currentPtr - pos); + assert debugOnlyClearLastStackSlot(); + currentPtr--; + } + } + + private void removeFromStack(StackNode<T> node) throws SAXException { + if (stack[currentPtr] == node) { + pop(); + } else { + int pos = currentPtr - 1; + while (pos >= 0 && stack[pos] != node) { + pos--; + } + if (pos == -1) { + // dead code? + return; + } + fatal(); + node.release(this); + System.arraycopy(stack, pos + 1, stack, pos, currentPtr - pos); + currentPtr--; + } + } + + private void removeFromListOfActiveFormattingElements(int pos) { + assert listOfActiveFormattingElements[pos] != null; + listOfActiveFormattingElements[pos].release(this); + if (pos == listPtr) { + assert debugOnlyClearLastListSlot(); + listPtr--; + return; + } + assert pos < listPtr; + System.arraycopy(listOfActiveFormattingElements, pos + 1, + listOfActiveFormattingElements, pos, listPtr - pos); + assert debugOnlyClearLastListSlot(); + listPtr--; + } + + /** + * Adoption agency algorithm. + * + * @param name subject as described in the specified algorithm. + * @return Returns true if the algorithm has completed and there is nothing remaining to + * be done. Returns false if the algorithm needs to "act as described in the 'any other + * end tag' entry" as described in the specified algorithm. + * @throws SAXException + */ + private boolean adoptionAgencyEndTag(@Local String name) throws SAXException { + // This check intends to ensure that for properly nested tags, closing tags will match + // against the stack instead of the listOfActiveFormattingElements. + if (stack[currentPtr].ns == "http://www.w3.org/1999/xhtml" && + stack[currentPtr].name == name && + findInListOfActiveFormattingElements(stack[currentPtr]) == -1) { + // If the current element matches the name but isn't on the list of active + // formatting elements, then it is possible that the list was mangled by the Noah's Ark + // clause. In this case, we want to match the end tag against the stack instead of + // proceeding with the AAA algorithm that may match against the list of + // active formatting elements (and possibly mangle the tree in unexpected ways). + pop(); + return true; + } + + // If you crash around here, perhaps some stack node variable claimed to + // be a weak ref isn't. + for (int i = 0; i < 8; ++i) { + int formattingEltListPos = listPtr; + while (formattingEltListPos > -1) { + StackNode<T> listNode = listOfActiveFormattingElements[formattingEltListPos]; // weak ref + if (listNode == null) { + formattingEltListPos = -1; + break; + } else if (listNode.name == name) { + break; + } + formattingEltListPos--; + } + if (formattingEltListPos == -1) { + return false; + } + // this *looks* like a weak ref to the list of formatting elements + StackNode<T> formattingElt = listOfActiveFormattingElements[formattingEltListPos]; + int formattingEltStackPos = currentPtr; + boolean inScope = true; + while (formattingEltStackPos > -1) { + StackNode<T> node = stack[formattingEltStackPos]; // weak ref + if (node == formattingElt) { + break; + } else if (node.isScoping()) { + inScope = false; + } + formattingEltStackPos--; + } + if (formattingEltStackPos == -1) { + errNoElementToCloseButEndTagSeen(name); + removeFromListOfActiveFormattingElements(formattingEltListPos); + return true; + } + if (!inScope) { + errNoElementToCloseButEndTagSeen(name); + return true; + } + // stackPos now points to the formatting element and it is in scope + if (formattingEltStackPos != currentPtr) { + errEndTagViolatesNestingRules(name); + } + int furthestBlockPos = formattingEltStackPos + 1; + while (furthestBlockPos <= currentPtr) { + StackNode<T> node = stack[furthestBlockPos]; // weak ref + assert furthestBlockPos > 0: "How is formattingEltStackPos + 1 not > 0?"; + if (node.isSpecial()) { + break; + } + furthestBlockPos++; + } + if (furthestBlockPos > currentPtr) { + // no furthest block + while (currentPtr >= formattingEltStackPos) { + pop(); + } + removeFromListOfActiveFormattingElements(formattingEltListPos); + return true; + } + // commonAncestor is used for running the algorithm and + // insertionCommonAncestor is used for the actual insertions to + // keep them depth-limited. + StackNode<T> commonAncestor = stack[formattingEltStackPos - 1]; // weak ref + T insertionCommonAncestor = nodeFromStackWithBlinkCompat(formattingEltStackPos - 1); // weak ref + StackNode<T> furthestBlock = stack[furthestBlockPos]; // weak ref + // detachFromParent(furthestBlock.node); XXX AAA CHANGE + int bookmark = formattingEltListPos; + int nodePos = furthestBlockPos; + StackNode<T> lastNode = furthestBlock; // weak ref + int j = 0; + for (;;) { + ++j; + nodePos--; + if (nodePos == formattingEltStackPos) { + break; + } + StackNode<T> node = stack[nodePos]; // weak ref + int nodeListPos = findInListOfActiveFormattingElements(node); + + if (j > 3 && nodeListPos != -1) { + removeFromListOfActiveFormattingElements(nodeListPos); + + // Adjust the indices into the list to account + // for the removal of nodeListPos. + if (nodeListPos <= formattingEltListPos) { + formattingEltListPos--; + } + if (nodeListPos <= bookmark) { + bookmark--; + } + + // Update position to reflect removal from list. + nodeListPos = -1; + } + + if (nodeListPos == -1) { + assert formattingEltStackPos < nodePos; + assert bookmark < nodePos; + assert furthestBlockPos > nodePos; + removeFromStack(nodePos); // node is now a bad pointer in C++ + furthestBlockPos--; + continue; + } + // now node is both on stack and in the list + if (nodePos == furthestBlockPos) { + bookmark = nodeListPos + 1; + } + // if (hasChildren(node.node)) { XXX AAA CHANGE + assert node == listOfActiveFormattingElements[nodeListPos]; + assert node == stack[nodePos]; + T clone = createElement("http://www.w3.org/1999/xhtml", + node.name, node.attributes.cloneAttributes(), insertionCommonAncestor + // CPPONLY: , htmlCreator(node.getHtmlCreator()) + ); + StackNode<T> newNode = createStackNode(node.getFlags(), node.ns, + node.name, clone, node.popName, node.attributes + // CPPONLY: , node.getHtmlCreator() + // [NOCPP[ + , node.getLocator() + // ]NOCPP] + ); // creation ownership goes to stack + node.dropAttributes(); // adopt ownership to newNode + stack[nodePos] = newNode; + newNode.retain(); // retain for list + listOfActiveFormattingElements[nodeListPos] = newNode; + node.release(this); // release from stack + node.release(this); // release from list + node = newNode; + // } XXX AAA CHANGE + detachFromParent(lastNode.node); + appendElement(lastNode.node, nodeFromStackWithBlinkCompat(nodePos)); + lastNode = node; + } + // If we insert into a foster parent, for simplicity, we insert + // accoding to the spec without Blink's depth limit. + if (commonAncestor.isFosterParenting()) { + fatal(); + detachFromParent(lastNode.node); + insertIntoFosterParent(lastNode.node); + } else { + detachFromParent(lastNode.node); + appendElement(lastNode.node, insertionCommonAncestor); + } + T clone = createElement("http://www.w3.org/1999/xhtml", + formattingElt.name, + formattingElt.attributes.cloneAttributes(), furthestBlock.node + // CPPONLY: , htmlCreator(formattingElt.getHtmlCreator()) + ); + StackNode<T> formattingClone = createStackNode( + formattingElt.getFlags(), formattingElt.ns, + formattingElt.name, clone, formattingElt.popName, + formattingElt.attributes + // CPPONLY: , formattingElt.getHtmlCreator() + // [NOCPP[ + , errorHandler == null ? null : new TaintableLocatorImpl(tokenizer) + // ]NOCPP] + ); // Ownership transfers to stack below + formattingElt.dropAttributes(); // transfer ownership to + // formattingClone + appendChildrenToNewParent(furthestBlock.node, clone); + appendElement(clone, furthestBlock.node); + removeFromListOfActiveFormattingElements(formattingEltListPos); + insertIntoListOfActiveFormattingElements(formattingClone, bookmark); + assert formattingEltStackPos < furthestBlockPos; + removeFromStack(formattingEltStackPos); + // furthestBlockPos is now off by one and points to the slot after + // it + insertIntoStack(formattingClone, furthestBlockPos); + } + return true; + } + + private void insertIntoStack(StackNode<T> node, int position) + throws SAXException { + assert currentPtr + 1 < stack.length; + assert position <= currentPtr + 1; + if (position == currentPtr + 1) { + push(node); + } else { + System.arraycopy(stack, position, stack, position + 1, + (currentPtr - position) + 1); + currentPtr++; + stack[position] = node; + } + } + + private void insertIntoListOfActiveFormattingElements( + StackNode<T> formattingClone, int bookmark) { + formattingClone.retain(); + assert listPtr + 1 < listOfActiveFormattingElements.length; + if (bookmark <= listPtr) { + System.arraycopy(listOfActiveFormattingElements, bookmark, + listOfActiveFormattingElements, bookmark + 1, + (listPtr - bookmark) + 1); + } + listPtr++; + listOfActiveFormattingElements[bookmark] = formattingClone; + } + + private int findInListOfActiveFormattingElements(StackNode<T> node) { + for (int i = listPtr; i >= 0; i--) { + if (node == listOfActiveFormattingElements[i]) { + return i; + } + } + return -1; + } + + private int findInListOfActiveFormattingElementsContainsBetweenEndAndLastMarker( + @Local String name) { + for (int i = listPtr; i >= 0; i--) { + StackNode<T> node = listOfActiveFormattingElements[i]; + if (node == null) { + return -1; + } else if (node.name == name) { + return i; + } + } + return -1; + } + + + private void maybeForgetEarlierDuplicateFormattingElement( + @Local String name, HtmlAttributes attributes) throws SAXException { + int candidate = -1; + int count = 0; + for (int i = listPtr; i >= 0; i--) { + StackNode<T> node = listOfActiveFormattingElements[i]; + if (node == null) { + break; + } + if (node.name == name && node.attributes.equalsAnother(attributes)) { + candidate = i; + ++count; + } + } + if (count >= 3) { + removeFromListOfActiveFormattingElements(candidate); + } + } + + private int findLastOrRoot(@Local String name) { + for (int i = currentPtr; i > 0; i--) { + if (stack[i].ns == "http://www.w3.org/1999/xhtml" && stack[i].name == name) { + return i; + } + } + return 0; + } + + private int findLastOrRoot(int group) { + for (int i = currentPtr; i > 0; i--) { + if (stack[i].ns == "http://www.w3.org/1999/xhtml" && stack[i].getGroup() == group) { + return i; + } + } + return 0; + } + + /** + * Attempt to add attribute to the body element. + * @param attributes the attributes + * @return <code>true</code> iff the attributes were added + * @throws SAXException + */ + private boolean addAttributesToBody(HtmlAttributes attributes) + throws SAXException { + // [NOCPP[ + checkAttributes(attributes, "http://www.w3.org/1999/xhtml"); + // ]NOCPP] + if (currentPtr >= 1) { + StackNode<T> body = stack[1]; + if (body.getGroup() == TreeBuilder.BODY) { + addAttributesToElement(body.node, attributes); + return true; + } + } + return false; + } + + private void addAttributesToHtml(HtmlAttributes attributes) + throws SAXException { + // [NOCPP[ + checkAttributes(attributes, "http://www.w3.org/1999/xhtml"); + // ]NOCPP] + addAttributesToElement(stack[0].node, attributes); + } + + private void pushHeadPointerOntoStack() throws SAXException { + assert headPointer != null; + assert mode == AFTER_HEAD; + fatal(); + silentPush(createStackNode(ElementName.HEAD, headPointer + // [NOCPP[ + , errorHandler == null ? null : new TaintableLocatorImpl(tokenizer) + // ]NOCPP] + )); + } + + /** + * @throws SAXException + * + */ + private void reconstructTheActiveFormattingElements() throws SAXException { + if (listPtr == -1) { + return; + } + StackNode<T> mostRecent = listOfActiveFormattingElements[listPtr]; + if (mostRecent == null || isInStack(mostRecent)) { + return; + } + int entryPos = listPtr; + for (;;) { + entryPos--; + if (entryPos == -1) { + break; + } + if (listOfActiveFormattingElements[entryPos] == null) { + break; + } + if (isInStack(listOfActiveFormattingElements[entryPos])) { + break; + } + } + while (entryPos < listPtr) { + entryPos++; + StackNode<T> entry = listOfActiveFormattingElements[entryPos]; + StackNode<T> current = stack[currentPtr]; + + T clone; + if (current.isFosterParenting()) { + clone = createAndInsertFosterParentedElement("http://www.w3.org/1999/xhtml", entry.name, + entry.attributes.cloneAttributes() + // CPPONLY: , htmlCreator(entry.getHtmlCreator()) + ); + } else { + T currentNode = nodeFromStackWithBlinkCompat(currentPtr); + clone = createElement("http://www.w3.org/1999/xhtml", entry.name, + entry.attributes.cloneAttributes(), currentNode + // CPPONLY: , htmlCreator(entry.getHtmlCreator()) + ); + appendElement(clone, currentNode); + } + + StackNode<T> entryClone = createStackNode(entry.getFlags(), + entry.ns, entry.name, clone, entry.popName, + entry.attributes + // CPPONLY: , entry.getHtmlCreator() + // [NOCPP[ + , entry.getLocator() + // ]NOCPP] + ); + + entry.dropAttributes(); // transfer ownership to entryClone + + push(entryClone); + // stack takes ownership of the local variable + listOfActiveFormattingElements[entryPos] = entryClone; + // overwriting the old entry on the list, so release & retain + entry.release(this); + entryClone.retain(); + } + } + + void notifyUnusedStackNode(int idxInStackNodes) { + // stackNodesIdx is the earliest possible index of a stack node that might be unused, + // so update the index if necessary. + if (idxInStackNodes < stackNodesIdx) { + stackNodesIdx = idxInStackNodes; + } + } + + @SuppressWarnings("unchecked") private StackNode<T> getUnusedStackNode() { + // Search for an unused stack node. + while (stackNodesIdx < numStackNodes) { + if (stackNodes[stackNodesIdx].isUnused()) { + return stackNodes[stackNodesIdx++]; + } + stackNodesIdx++; + } + + if (stackNodesIdx < stackNodes.length) { + // No unused stack nodes, but there is still space in the storage array. + stackNodes[stackNodesIdx] = new StackNode<T>(stackNodesIdx); + numStackNodes++; + return stackNodes[stackNodesIdx++]; + } + + // Could not find an unused stack node and storage array is full. + StackNode<T>[] newStack = new StackNode[stackNodes.length + 64]; + System.arraycopy(stackNodes, 0, newStack, 0, stackNodes.length); + stackNodes = newStack; + + // Create a new stack node and return it. + stackNodes[stackNodesIdx] = new StackNode<T>(stackNodesIdx); + numStackNodes++; + return stackNodes[stackNodesIdx++]; + } + + private StackNode<T> createStackNode(int flags, @NsUri String ns, @Local String name, T node, + @Local String popName, HtmlAttributes attributes + // CPPONLY: , @HtmlCreator Object htmlCreator + // [NOCPP[ + , TaintableLocatorImpl locator + // ]NOCPP] + ) { + StackNode<T> instance = getUnusedStackNode(); + instance.setValues(flags, ns, name, node, popName, attributes + // CPPONLY: , htmlCreator + // [NOCPP[ + , locator + // ]NOCPP] + ); + return instance; + } + + private StackNode<T> createStackNode(ElementName elementName, T node + // [NOCPP[ + , TaintableLocatorImpl locator + // ]NOCPP] + ) { + StackNode<T> instance = getUnusedStackNode(); + instance.setValues(elementName, node + // [NOCPP[ + , locator + // ]NOCPP] + ); + return instance; + } + + private StackNode<T> createStackNode(ElementName elementName, T node, HtmlAttributes attributes + // [NOCPP[ + , TaintableLocatorImpl locator + // ]NOCPP] + ) { + StackNode<T> instance = getUnusedStackNode(); + instance.setValues(elementName, node, attributes + // [NOCPP[ + , locator + // ]NOCPP] + ); + return instance; + } + + private StackNode<T> createStackNode(ElementName elementName, T node, @Local String popName + // [NOCPP[ + , TaintableLocatorImpl locator + // ]NOCPP] + ) { + StackNode<T> instance = getUnusedStackNode(); + instance.setValues(elementName, node, popName + // [NOCPP[ + , locator + // ]NOCPP] + ); + return instance; + } + + private StackNode<T> createStackNode(ElementName elementName, @Local String popName, T node + // [NOCPP[ + , TaintableLocatorImpl locator + // ]NOCPP] + ) { + StackNode<T> instance = getUnusedStackNode(); + instance.setValues(elementName, popName, node + // [NOCPP[ + , locator + // ]NOCPP] + ); + return instance; + } + + private StackNode<T> createStackNode(ElementName elementName, T node, @Local String popName, + boolean markAsIntegrationPoint + // [NOCPP[ + , TaintableLocatorImpl locator + // ]NOCPP] + ) { + StackNode<T> instance = getUnusedStackNode(); + instance.setValues(elementName, node, popName, markAsIntegrationPoint + // [NOCPP[ + , locator + // ]NOCPP] + ); + return instance; + } + + private void insertIntoFosterParent(T child) throws SAXException { + int tablePos = findLastOrRoot(TreeBuilder.TABLE); + int templatePos = findLastOrRoot(TreeBuilder.TEMPLATE); + + if (templatePos >= tablePos) { + appendElement(child, stack[templatePos].node); + return; + } + + StackNode<T> node = stack[tablePos]; + insertFosterParentedChild(child, node.node, stack[tablePos - 1].node); + } + + private T createAndInsertFosterParentedElement(@NsUri String ns, @Local String name, + HtmlAttributes attributes + // CPPONLY: , @Creator Object creator + ) throws SAXException { + return createAndInsertFosterParentedElement(ns, name, attributes, null + // CPPONLY: , creator + ); + } + + private T createAndInsertFosterParentedElement(@NsUri String ns, @Local String name, + HtmlAttributes attributes, T form + // CPPONLY: , @Creator Object creator + ) throws SAXException { + int tablePos = findLastOrRoot(TreeBuilder.TABLE); + int templatePos = findLastOrRoot(TreeBuilder.TEMPLATE); + + if (templatePos >= tablePos) { + T child = createElement(ns, name, attributes, form, stack[templatePos].node + // CPPONLY: , creator + ); + appendElement(child, stack[templatePos].node); + return child; + } + + StackNode<T> node = stack[tablePos]; + return createAndInsertFosterParentedElement(ns, name, attributes, form, node.node, stack[tablePos - 1].node + // CPPONLY: , creator + ); + } + + private boolean isInStack(StackNode<T> node) { + for (int i = currentPtr; i >= 0; i--) { + if (stack[i] == node) { + return true; + } + } + return false; + } + + private void popTemplateMode() { + templateModePtr--; + } + + private void pop() throws SAXException { + StackNode<T> node = stack[currentPtr]; + assert debugOnlyClearLastStackSlot(); + currentPtr--; + elementPopped(node.ns, node.popName, node.node); + node.release(this); + } + + private void popForeign(int origPos, int eltPos) throws SAXException { + StackNode<T> node = stack[currentPtr]; + if (origPos != currentPtr || eltPos != currentPtr) { + markMalformedIfScript(node.node); + } + assert debugOnlyClearLastStackSlot(); + currentPtr--; + elementPopped(node.ns, node.popName, node.node); + node.release(this); + } + + private void silentPop() throws SAXException { + StackNode<T> node = stack[currentPtr]; + assert debugOnlyClearLastStackSlot(); + currentPtr--; + node.release(this); + } + + private void popOnEof() throws SAXException { + StackNode<T> node = stack[currentPtr]; + assert debugOnlyClearLastStackSlot(); + currentPtr--; + markMalformedIfScript(node.node); + elementPopped(node.ns, node.popName, node.node); + node.release(this); + } + + // [NOCPP[ + private void checkAttributes(HtmlAttributes attributes, @NsUri String ns) + throws SAXException { + if (errorHandler != null) { + int len = attributes.getXmlnsLength(); + for (int i = 0; i < len; i++) { + AttributeName name = attributes.getXmlnsAttributeName(i); + if (name == AttributeName.XMLNS) { + String xmlns = attributes.getXmlnsValue(i); + if (!ns.equals(xmlns)) { + err("Bad value \u201C" + + xmlns + + "\u201D for the attribute \u201Cxmlns\u201D (only \u201C" + + ns + "\u201D permitted here)."); + switch (namePolicy) { + case ALTER_INFOSET: + // fall through + case ALLOW: + warn("Attribute \u201Cxmlns\u201D is not serializable as XML 1.0."); + break; + case FATAL: + fatal("Attribute \u201Cxmlns\u201D is not serializable as XML 1.0."); + break; + } + } + } else if (ns != "http://www.w3.org/1999/xhtml" + && name == AttributeName.XMLNS_XLINK) { + String xmlns = attributes.getXmlnsValue(i); + if (!"http://www.w3.org/1999/xlink".equals(xmlns)) { + err("Bad value \u201C" + + xmlns + + "\u201D for the attribute \u201Cxmlns:link\u201D (only \u201Chttp://www.w3.org/1999/xlink\u201D permitted here)."); + switch (namePolicy) { + case ALTER_INFOSET: + // fall through + case ALLOW: + warn("Attribute \u201Cxmlns:xlink\u201D with a value other than \u201Chttp://www.w3.org/1999/xlink\u201D is not serializable as XML 1.0 without changing document semantics."); + break; + case FATAL: + fatal("Attribute \u201Cxmlns:xlink\u201D with a value other than \u201Chttp://www.w3.org/1999/xlink\u201D is not serializable as XML 1.0 without changing document semantics."); + break; + } + } + } else { + err("Attribute \u201C" + attributes.getXmlnsLocalName(i) + + "\u201D not allowed here."); + switch (namePolicy) { + case ALTER_INFOSET: + // fall through + case ALLOW: + warn("Attribute with the local name \u201C" + + attributes.getXmlnsLocalName(i) + + "\u201D is not serializable as XML 1.0."); + break; + case FATAL: + fatal("Attribute with the local name \u201C" + + attributes.getXmlnsLocalName(i) + + "\u201D is not serializable as XML 1.0."); + break; + } + } + } + } + attributes.processNonNcNames(this, namePolicy); + } + + private String checkPopName(@Local String name) throws SAXException { + if (NCName.isNCName(name)) { + return name; + } else { + switch (namePolicy) { + case ALLOW: + warn("Element name \u201C" + name + + "\u201D cannot be represented as XML 1.0."); + return name; + case ALTER_INFOSET: + warn("Element name \u201C" + name + + "\u201D cannot be represented as XML 1.0."); + return NCName.escapeName(name); + case FATAL: + fatal("Element name \u201C" + name + + "\u201D cannot be represented as XML 1.0."); + } + } + return null; // keep compiler happy + } + + // ]NOCPP] + + private void appendHtmlElementToDocumentAndPush(HtmlAttributes attributes) + throws SAXException { + // [NOCPP[ + checkAttributes(attributes, "http://www.w3.org/1999/xhtml"); + // ]NOCPP] + T elt = createHtmlElementSetAsRoot(attributes); + StackNode<T> node = createStackNode(ElementName.HTML, + elt + // [NOCPP[ + , errorHandler == null ? null : new TaintableLocatorImpl(tokenizer) + // ]NOCPP] + ); + push(node); + } + + private void appendHtmlElementToDocumentAndPush() throws SAXException { + appendHtmlElementToDocumentAndPush(tokenizer.emptyAttributes()); + } + + private void appendToCurrentNodeAndPushHeadElement(HtmlAttributes attributes) + throws SAXException { + // [NOCPP[ + checkAttributes(attributes, "http://www.w3.org/1999/xhtml"); + // ]NOCPP] + T currentNode = nodeFromStackWithBlinkCompat(currentPtr); + T elt = createElement("http://www.w3.org/1999/xhtml", "head", attributes, currentNode + /* + * head uses NS_NewHTMLSharedElement creator + */ + // CPPONLY: , htmlCreator(NS_NewHTMLSharedElement) + ); + appendElement(elt, currentNode); + headPointer = elt; + StackNode<T> node = createStackNode(ElementName.HEAD, + elt + // [NOCPP[ + , errorHandler == null ? null : new TaintableLocatorImpl(tokenizer) + // ]NOCPP] + ); + push(node); + } + + private void appendToCurrentNodeAndPushBodyElement(HtmlAttributes attributes) + throws SAXException { + appendToCurrentNodeAndPushElement(ElementName.BODY, + attributes); + } + + private void appendToCurrentNodeAndPushBodyElement() throws SAXException { + appendToCurrentNodeAndPushBodyElement(tokenizer.emptyAttributes()); + } + + private void appendToCurrentNodeAndPushFormElementMayFoster( + HtmlAttributes attributes) throws SAXException { + // [NOCPP[ + checkAttributes(attributes, "http://www.w3.org/1999/xhtml"); + // ]NOCPP] + + T elt; + StackNode<T> current = stack[currentPtr]; + if (current.isFosterParenting()) { + fatal(); + elt = createAndInsertFosterParentedElement("http://www.w3.org/1999/xhtml", "form", attributes + // CPPONLY: , htmlCreator(NS_NewHTMLFormElement) + ); + } else { + T currentNode = nodeFromStackWithBlinkCompat(currentPtr); + elt = createElement("http://www.w3.org/1999/xhtml", "form", attributes, currentNode + // CPPONLY: , htmlCreator(NS_NewHTMLFormElement) + ); + appendElement(elt, currentNode); + } + + if (!isTemplateContents()) { + formPointer = elt; + } + + StackNode<T> node = createStackNode(ElementName.FORM, + elt + // [NOCPP[ + , errorHandler == null ? null : new TaintableLocatorImpl(tokenizer) + // ]NOCPP] + ); + push(node); + } + + private void appendToCurrentNodeAndPushFormattingElementMayFoster( + ElementName elementName, HtmlAttributes attributes) + throws SAXException { + // [NOCPP[ + checkAttributes(attributes, "http://www.w3.org/1999/xhtml"); + // ]NOCPP] + // This method can't be called for custom elements + HtmlAttributes clone = attributes.cloneAttributes(); + // Attributes must not be read after calling createElement, because + // createElement may delete attributes in C++. + T elt; + StackNode<T> current = stack[currentPtr]; + if (current.isFosterParenting()) { + fatal(); + elt = createAndInsertFosterParentedElement("http://www.w3.org/1999/xhtml", elementName.getName(), attributes + // CPPONLY: , htmlCreator(elementName.getHtmlCreator()) + ); + } else { + T currentNode = nodeFromStackWithBlinkCompat(currentPtr); + elt = createElement("http://www.w3.org/1999/xhtml", elementName.getName(), attributes, currentNode + // CPPONLY: , htmlCreator(elementName.getHtmlCreator()) + ); + appendElement(elt, currentNode); + } + StackNode<T> node = createStackNode(elementName, elt, clone + // [NOCPP[ + , errorHandler == null ? null : new TaintableLocatorImpl(tokenizer) + // ]NOCPP] + ); + push(node); + append(node); + node.retain(); // append doesn't retain itself + } + + private void appendToCurrentNodeAndPushElement(ElementName elementName, + HtmlAttributes attributes) + throws SAXException { + // [NOCPP[ + checkAttributes(attributes, "http://www.w3.org/1999/xhtml"); + // ]NOCPP] + // This method can't be called for custom elements + T currentNode = nodeFromStackWithBlinkCompat(currentPtr); + T elt = createElement("http://www.w3.org/1999/xhtml", elementName.getName(), attributes, currentNode + // CPPONLY: , htmlCreator(elementName.getHtmlCreator()) + ); + appendElement(elt, currentNode); + if (ElementName.TEMPLATE == elementName) { + elt = getDocumentFragmentForTemplate(elt); + } + StackNode<T> node = createStackNode(elementName, elt + // [NOCPP[ + , errorHandler == null ? null : new TaintableLocatorImpl(tokenizer) + // ]NOCPP] + ); + push(node); + } + + private void appendToCurrentNodeAndPushElementMayFoster(ElementName elementName, + HtmlAttributes attributes) + throws SAXException { + @Local String popName = elementName.getName(); + // [NOCPP[ + checkAttributes(attributes, "http://www.w3.org/1999/xhtml"); + if (!elementName.isInterned()) { + popName = checkPopName(popName); + } + // ]NOCPP] + T elt; + StackNode<T> current = stack[currentPtr]; + if (current.isFosterParenting()) { + fatal(); + elt = createAndInsertFosterParentedElement("http://www.w3.org/1999/xhtml", popName, attributes + // CPPONLY: , htmlCreator(elementName.getHtmlCreator()) + ); + } else { + T currentNode = nodeFromStackWithBlinkCompat(currentPtr); + elt = createElement("http://www.w3.org/1999/xhtml", popName, attributes, currentNode + // CPPONLY: , htmlCreator(elementName.getHtmlCreator()) + ); + appendElement(elt, currentNode); + } + StackNode<T> node = createStackNode(elementName, elt, popName + // [NOCPP[ + , errorHandler == null ? null : new TaintableLocatorImpl(tokenizer) + // ]NOCPP] + ); + push(node); + } + + private void appendToCurrentNodeAndPushElementMayFosterMathML( + ElementName elementName, HtmlAttributes attributes) + throws SAXException { + @Local String popName = elementName.getName(); + // [NOCPP[ + checkAttributes(attributes, "http://www.w3.org/1998/Math/MathML"); + if (!elementName.isInterned()) { + popName = checkPopName(popName); + } + // ]NOCPP] + boolean markAsHtmlIntegrationPoint = false; + if (ElementName.ANNOTATION_XML == elementName + && annotationXmlEncodingPermitsHtml(attributes)) { + markAsHtmlIntegrationPoint = true; + } + // Attributes must not be read after calling createElement(), since + // createElement may delete the object in C++. + T elt; + StackNode<T> current = stack[currentPtr]; + if (current.isFosterParenting()) { + fatal(); + elt = createAndInsertFosterParentedElement("http://www.w3.org/1998/Math/MathML", popName, attributes + // CPPONLY: , htmlCreator(null) + ); + } else { + T currentNode = nodeFromStackWithBlinkCompat(currentPtr); + elt = createElement("http://www.w3.org/1998/Math/MathML", popName, attributes, currentNode + // CPPONLY: , htmlCreator(null) + ); + appendElement(elt, currentNode); + } + StackNode<T> node = createStackNode(elementName, elt, popName, + markAsHtmlIntegrationPoint + // [NOCPP[ + , errorHandler == null ? null : new TaintableLocatorImpl(tokenizer) + // ]NOCPP] + ); + push(node); + } + + // [NOCPP[ + T getDocumentFragmentForTemplate(T template) { + return template; + } + + T getFormPointerForContext(T context) { + return null; + } + // ]NOCPP] + + private boolean annotationXmlEncodingPermitsHtml(HtmlAttributes attributes) { + String encoding = attributes.getValue(AttributeName.ENCODING); + if (encoding == null) { + return false; + } + return Portability.lowerCaseLiteralEqualsIgnoreAsciiCaseString( + "application/xhtml+xml", encoding) + || Portability.lowerCaseLiteralEqualsIgnoreAsciiCaseString( + "text/html", encoding); + } + + private void appendToCurrentNodeAndPushElementMayFosterSVG( + ElementName elementName, HtmlAttributes attributes) + throws SAXException { + @Local String popName = elementName.getCamelCaseName(); + // [NOCPP[ + checkAttributes(attributes, "http://www.w3.org/2000/svg"); + if (!elementName.isInterned()) { + popName = checkPopName(popName); + } + // ]NOCPP] + T elt; + StackNode<T> current = stack[currentPtr]; + if (current.isFosterParenting()) { + fatal(); + elt = createAndInsertFosterParentedElement("http://www.w3.org/2000/svg", popName, attributes + // CPPONLY: , svgCreator(elementName.getSvgCreator()) + ); + } else { + T currentNode = nodeFromStackWithBlinkCompat(currentPtr); + elt = createElement("http://www.w3.org/2000/svg", popName, attributes, currentNode + // CPPONLY: , svgCreator(elementName.getSvgCreator()) + ); + appendElement(elt, currentNode); + } + StackNode<T> node = createStackNode(elementName, popName, elt + // [NOCPP[ + , errorHandler == null ? null : new TaintableLocatorImpl(tokenizer) + // ]NOCPP] + ); + push(node); + } + + private void appendToCurrentNodeAndPushElementMayFoster(ElementName elementName, + HtmlAttributes attributes, T form) + throws SAXException { + // [NOCPP[ + checkAttributes(attributes, "http://www.w3.org/1999/xhtml"); + // ]NOCPP] + // Can't be called for custom elements + T elt; + T formOwner = form == null || fragment || isTemplateContents() ? null : form; + StackNode<T> current = stack[currentPtr]; + if (current.isFosterParenting()) { + fatal(); + elt = createAndInsertFosterParentedElement("http://www.w3.org/1999/xhtml", elementName.getName(), + attributes, formOwner + // CPPONLY: , htmlCreator(elementName.getHtmlCreator()) + ); + } else { + T currentNode = nodeFromStackWithBlinkCompat(currentPtr); + elt = createElement("http://www.w3.org/1999/xhtml", elementName.getName(), + attributes, formOwner, currentNode + // CPPONLY: , htmlCreator(elementName.getHtmlCreator()) + ); + appendElement(elt, currentNode); + } + StackNode<T> node = createStackNode(elementName, elt + // [NOCPP[ + , errorHandler == null ? null : new TaintableLocatorImpl(tokenizer) + // ]NOCPP] + ); + push(node); + } + + private void appendVoidElementToCurrentMayFoster( + ElementName elementName, HtmlAttributes attributes, T form) throws SAXException { + @Local String name = elementName.getName(); + // [NOCPP[ + checkAttributes(attributes, "http://www.w3.org/1999/xhtml"); + // ]NOCPP] + // Can't be called for custom elements + T elt; + T formOwner = form == null || fragment || isTemplateContents() ? null : form; + StackNode<T> current = stack[currentPtr]; + if (current.isFosterParenting()) { + fatal(); + elt = createAndInsertFosterParentedElement("http://www.w3.org/1999/xhtml", name, + attributes, formOwner + // CPPONLY: , htmlCreator(elementName.getHtmlCreator()) + ); + } else { + T currentNode = nodeFromStackWithBlinkCompat(currentPtr); + elt = createElement("http://www.w3.org/1999/xhtml", name, + attributes, formOwner, currentNode + // CPPONLY: , htmlCreator(elementName.getHtmlCreator()) + ); + appendElement(elt, currentNode); + } + elementPushed("http://www.w3.org/1999/xhtml", name, elt); + elementPopped("http://www.w3.org/1999/xhtml", name, elt); + } + + private void appendVoidElementToCurrentMayFoster( + ElementName elementName, HtmlAttributes attributes) + throws SAXException { + @Local String popName = elementName.getName(); + // [NOCPP[ + checkAttributes(attributes, "http://www.w3.org/1999/xhtml"); + if (!elementName.isInterned()) { + popName = checkPopName(popName); + } + // ]NOCPP] + T elt; + StackNode<T> current = stack[currentPtr]; + if (current.isFosterParenting()) { + fatal(); + elt = createAndInsertFosterParentedElement("http://www.w3.org/1999/xhtml", popName, attributes + // CPPONLY: , htmlCreator(elementName.getHtmlCreator()) + ); + } else { + T currentNode = nodeFromStackWithBlinkCompat(currentPtr); + elt = createElement("http://www.w3.org/1999/xhtml", popName, attributes, currentNode + // CPPONLY: , htmlCreator(elementName.getHtmlCreator()) + ); + appendElement(elt, currentNode); + } + elementPushed("http://www.w3.org/1999/xhtml", popName, elt); + elementPopped("http://www.w3.org/1999/xhtml", popName, elt); + } + + private void appendVoidElementToCurrentMayFosterSVG( + ElementName elementName, HtmlAttributes attributes) + throws SAXException { + @Local String popName = elementName.getCamelCaseName(); + // [NOCPP[ + checkAttributes(attributes, "http://www.w3.org/2000/svg"); + if (!elementName.isInterned()) { + popName = checkPopName(popName); + } + // ]NOCPP] + T elt; + StackNode<T> current = stack[currentPtr]; + if (current.isFosterParenting()) { + fatal(); + elt = createAndInsertFosterParentedElement("http://www.w3.org/2000/svg", popName, attributes + // CPPONLY: , svgCreator(elementName.getSvgCreator()) + ); + } else { + T currentNode = nodeFromStackWithBlinkCompat(currentPtr); + elt = createElement("http://www.w3.org/2000/svg", popName, attributes, currentNode + // CPPONLY: , svgCreator(elementName.getSvgCreator()) + ); + appendElement(elt, currentNode); + } + elementPushed("http://www.w3.org/2000/svg", popName, elt); + elementPopped("http://www.w3.org/2000/svg", popName, elt); + } + + private void appendVoidElementToCurrentMayFosterMathML( + ElementName elementName, HtmlAttributes attributes) + throws SAXException { + @Local String popName = elementName.getName(); + // [NOCPP[ + checkAttributes(attributes, "http://www.w3.org/1998/Math/MathML"); + if (!elementName.isInterned()) { + popName = checkPopName(popName); + } + // ]NOCPP] + T elt; + StackNode<T> current = stack[currentPtr]; + if (current.isFosterParenting()) { + fatal(); + elt = createAndInsertFosterParentedElement("http://www.w3.org/1998/Math/MathML", popName, attributes + // CPPONLY: , htmlCreator(null) + ); + } else { + T currentNode = nodeFromStackWithBlinkCompat(currentPtr); + elt = createElement("http://www.w3.org/1998/Math/MathML", popName, attributes, currentNode + // CPPONLY: , htmlCreator(null) + ); + appendElement(elt, currentNode); + } + elementPushed("http://www.w3.org/1998/Math/MathML", popName, elt); + elementPopped("http://www.w3.org/1998/Math/MathML", popName, elt); + } + + private void appendVoidInputToCurrent(HtmlAttributes attributes, T form) throws SAXException { + // [NOCPP[ + checkAttributes(attributes, "http://www.w3.org/1999/xhtml"); + // ]NOCPP] + // Can't be called for custom elements + T currentNode = nodeFromStackWithBlinkCompat(currentPtr); + T elt = createElement("http://www.w3.org/1999/xhtml", "input", attributes, + form == null || fragment || isTemplateContents() ? null : form, currentNode + // CPPONLY: , htmlCreator(NS_NewHTMLInputElement) + ); + appendElement(elt, currentNode); + elementPushed("http://www.w3.org/1999/xhtml", "input", elt); + elementPopped("http://www.w3.org/1999/xhtml", "input", elt); + } + + private void appendVoidFormToCurrent(HtmlAttributes attributes) throws SAXException { + // [NOCPP[ + checkAttributes(attributes, "http://www.w3.org/1999/xhtml"); + // ]NOCPP] + T currentNode = nodeFromStackWithBlinkCompat(currentPtr); + T elt = createElement("http://www.w3.org/1999/xhtml", "form", + attributes, currentNode + // CPPONLY: , htmlCreator(NS_NewHTMLFormElement) + ); + formPointer = elt; + // ownership transferred to form pointer + appendElement(elt, currentNode); + elementPushed("http://www.w3.org/1999/xhtml", "form", elt); + elementPopped("http://www.w3.org/1999/xhtml", "form", elt); + } + + // [NOCPP[ + + private final void accumulateCharactersForced(@Const @NoLength char[] buf, + int start, int length) throws SAXException { + System.arraycopy(buf, start, charBuffer, charBufferLen, length); + charBufferLen += length; + } + + @Override public void ensureBufferSpace(int inputLength) + throws SAXException { + // TODO: Unify Tokenizer.strBuf and TreeBuilder.charBuffer so that + // this method becomes unnecessary. + int worstCase = charBufferLen + inputLength; + if (charBuffer == null) { + // Add an arbitrary small value to avoid immediate reallocation + // once there are a few characters in the buffer. + charBuffer = new char[worstCase + 128]; + } else if (worstCase > charBuffer.length) { + // HotSpot reportedly allocates memory with 8-byte accuracy, so + // there's no point in trying to do math here to avoid slop. + // Maybe we should add some small constant to worstCase here + // but not doing that without profiling. In C++ with jemalloc, + // the corresponding method should do math to round up here + // to avoid slop. + char[] newBuf = new char[worstCase]; + System.arraycopy(charBuffer, 0, newBuf, 0, charBufferLen); + charBuffer = newBuf; + } + } + + // ]NOCPP] + + protected void accumulateCharacters(@Const @NoLength char[] buf, int start, + int length) throws SAXException { + appendCharacters(stack[currentPtr].node, buf, start, length); + } + + // ------------------------------- // + + protected final void requestSuspension() { + tokenizer.requestSuspension(); + } + + protected abstract T createElement(@NsUri String ns, @Local String name, + HtmlAttributes attributes, T intendedParent + // CPPONLY: , @Creator Object creator + ) throws SAXException; + + protected T createElement(@NsUri String ns, @Local String name, + HtmlAttributes attributes, T form, T intendedParent + // CPPONLY: , @Creator Object creator + ) throws SAXException { + return createElement("http://www.w3.org/1999/xhtml", name, attributes, intendedParent + // CPPONLY: , creator + ); + } + + protected abstract T createHtmlElementSetAsRoot(HtmlAttributes attributes) + throws SAXException; + + protected abstract void detachFromParent(T element) throws SAXException; + + protected abstract boolean hasChildren(T element) throws SAXException; + + protected abstract void appendElement(T child, T newParent) + throws SAXException; + + protected abstract void appendChildrenToNewParent(T oldParent, T newParent) + throws SAXException; + + protected abstract void insertFosterParentedChild(T child, T table, + T stackParent) throws SAXException; + + // We don't generate CPP code for this method because it is not used in generated CPP + // code. Instead, the form owner version of this method is called with a null form owner. + // [NOCPP[ + + protected abstract T createAndInsertFosterParentedElement(@NsUri String ns, @Local String name, + HtmlAttributes attributes, T table, T stackParent) throws SAXException; + + // ]NOCPP] + + protected T createAndInsertFosterParentedElement(@NsUri String ns, @Local String name, + HtmlAttributes attributes, T form, T table, T stackParent + // CPPONLY: , @Creator Object creator + ) throws SAXException { + return createAndInsertFosterParentedElement(ns, name, attributes, table, stackParent); + }; + + protected abstract void insertFosterParentedCharacters( + @NoLength char[] buf, int start, int length, T table, T stackParent) + throws SAXException; + + protected abstract void appendCharacters(T parent, @NoLength char[] buf, + int start, int length) throws SAXException; + + protected abstract void appendComment(T parent, @NoLength char[] buf, + int start, int length) throws SAXException; + + protected abstract void appendCommentToDocument(@NoLength char[] buf, + int start, int length) throws SAXException; + + protected abstract void addAttributesToElement(T element, + HtmlAttributes attributes) throws SAXException; + + protected void markMalformedIfScript(T elt) throws SAXException { + + } + + protected void start(boolean fragmentMode) throws SAXException { + + } + + protected void end() throws SAXException { + + } + + protected void appendDoctypeToDocument(@Local String name, + String publicIdentifier, String systemIdentifier) + throws SAXException { + + } + + protected void elementPushed(@NsUri String ns, @Local String name, T node) + throws SAXException { + + } + + protected void elementPopped(@NsUri String ns, @Local String name, T node) + throws SAXException { + + } + + // [NOCPP[ + + protected void documentMode(DocumentMode m, String publicIdentifier, + String systemIdentifier) + throws SAXException { + + } + + /** + * @see nu.validator.htmlparser.common.TokenHandler#wantsComments() + */ + public boolean wantsComments() { + return wantingComments; + } + + public void setIgnoringComments(boolean ignoreComments) { + wantingComments = !ignoreComments; + } + + /** + * Sets the errorHandler. + * + * @param errorHandler + * the errorHandler to set + */ + public final void setErrorHandler(ErrorHandler errorHandler) { + this.errorHandler = errorHandler; + } + + /** + * Returns the errorHandler. + * + * @return the errorHandler + */ + public ErrorHandler getErrorHandler() { + return errorHandler; + } + + /** + * The argument MUST be an interned string or <code>null</code>. + * + * @param context + */ + public final void setFragmentContext(@Local String context) { + this.contextName = context; + this.contextNamespace = "http://www.w3.org/1999/xhtml"; + this.contextNode = null; + this.fragment = (contextName != null); + this.quirks = false; + } + + // ]NOCPP] + + /** + * @see nu.validator.htmlparser.common.TokenHandler#cdataSectionAllowed() + */ + @Inline public boolean cdataSectionAllowed() throws SAXException { + return isInForeign(); + } + + private boolean isInForeign() { + return currentPtr >= 0 + && stack[currentPtr].ns != "http://www.w3.org/1999/xhtml"; + } + + private boolean isInForeignButNotHtmlOrMathTextIntegrationPoint() { + if (currentPtr < 0) { + return false; + } + return !isSpecialParentInForeign(stack[currentPtr]); + } + + /** + * The argument MUST be an interned string or <code>null</code>. + * + * @param context + */ + public final void setFragmentContext(@Local String context, + @NsUri String ns, T node, boolean quirks) { + // [NOCPP[ + if (!((context == null && ns == null) + || "http://www.w3.org/1999/xhtml" == ns + || "http://www.w3.org/2000/svg" == ns || "http://www.w3.org/1998/Math/MathML" == ns)) { + throw new IllegalArgumentException( + "The namespace must be the HTML, SVG or MathML namespace (or null when the local name is null). Got: " + + ns); + } + // ]NOCPP] + this.contextName = context; + this.contextNamespace = ns; + this.contextNode = node; + this.fragment = (contextName != null); + this.quirks = quirks; + } + + protected final T currentNode() { + return stack[currentPtr].node; + } + + /** + * Returns the scriptingEnabled. + * + * @return the scriptingEnabled + */ + public boolean isScriptingEnabled() { + return scriptingEnabled; + } + + /** + * Sets the scriptingEnabled. + * + * @param scriptingEnabled + * the scriptingEnabled to set + */ + public void setScriptingEnabled(boolean scriptingEnabled) { + this.scriptingEnabled = scriptingEnabled; + } + + public void setForceNoQuirks(boolean forceNoQuirks) { + this.forceNoQuirks = forceNoQuirks; + } + + // Redundant method retained because previously public. + public void setIsSrcdocDocument(boolean isSrcdocDocument) { + this.setForceNoQuirks(isSrcdocDocument); + } + + // [NOCPP[ + + public void setNamePolicy(XmlViolationPolicy namePolicy) { + this.namePolicy = namePolicy; + } + + /** + * Sets the documentModeHandler. + * + * @param documentModeHandler + * the documentModeHandler to set + */ + public void setDocumentModeHandler(DocumentModeHandler documentModeHandler) { + this.documentModeHandler = documentModeHandler; + } + + /** + * Sets the reportingDoctype. + * + * @param reportingDoctype + * the reportingDoctype to set + */ + public void setReportingDoctype(boolean reportingDoctype) { + this.reportingDoctype = reportingDoctype; + } + + // ]NOCPP] + + /** + * Flushes the pending characters. Public for document.write use cases only. + * @throws SAXException + */ + public final void flushCharacters() throws SAXException { + if (charBufferLen > 0) { + if ((mode == IN_TABLE || mode == IN_TABLE_BODY || mode == IN_ROW) + && charBufferContainsNonWhitespace()) { + errNonSpaceInTable(); + reconstructTheActiveFormattingElements(); + if (!stack[currentPtr].isFosterParenting()) { + // reconstructing gave us a new current node + appendCharacters(currentNode(), charBuffer, 0, + charBufferLen); + charBufferLen = 0; + return; + } + + int tablePos = findLastOrRoot(TreeBuilder.TABLE); + int templatePos = findLastOrRoot(TreeBuilder.TEMPLATE); + + if (templatePos >= tablePos) { + appendCharacters(stack[templatePos].node, charBuffer, 0, charBufferLen); + charBufferLen = 0; + return; + } + + StackNode<T> tableElt = stack[tablePos]; + insertFosterParentedCharacters(charBuffer, 0, charBufferLen, + tableElt.node, stack[tablePos - 1].node); + charBufferLen = 0; + return; + } + appendCharacters(currentNode(), charBuffer, 0, charBufferLen); + charBufferLen = 0; + } + } + + private boolean charBufferContainsNonWhitespace() { + for (int i = 0; i < charBufferLen; i++) { + switch (charBuffer[i]) { + case ' ': + case '\t': + case '\n': + case '\r': + case '\u000C': + continue; + default: + return true; + } + } + return false; + } + + /** + * Creates a comparable snapshot of the tree builder state. Snapshot + * creation is only supported immediately after a script end tag has been + * processed. In C++ the caller is responsible for calling + * <code>delete</code> on the returned object. + * + * @return a snapshot. + * @throws SAXException + */ + @SuppressWarnings("unchecked") public TreeBuilderState<T> newSnapshot() + throws SAXException { + StackNode<T>[] listCopy = new StackNode[listPtr + 1]; + for (int i = 0; i < listCopy.length; i++) { + StackNode<T> node = listOfActiveFormattingElements[i]; + if (node != null) { + StackNode<T> newNode = new StackNode<T>(-1); + newNode.setValues(node.getFlags(), node.ns, + node.name, node.node, node.popName, + node.attributes.cloneAttributes() + // CPPONLY: , node.getHtmlCreator() + // [NOCPP[ + , node.getLocator() + // ]NOCPP] + ); + listCopy[i] = newNode; + } else { + listCopy[i] = null; + } + } + StackNode<T>[] stackCopy = new StackNode[currentPtr + 1]; + for (int i = 0; i < stackCopy.length; i++) { + StackNode<T> node = stack[i]; + int listIndex = findInListOfActiveFormattingElements(node); + if (listIndex == -1) { + StackNode<T> newNode = new StackNode<T>(-1); + newNode.setValues(node.getFlags(), node.ns, + node.name, node.node, node.popName, + null + // CPPONLY: , node.getHtmlCreator() + // [NOCPP[ + , node.getLocator() + // ]NOCPP] + ); + stackCopy[i] = newNode; + } else { + stackCopy[i] = listCopy[listIndex]; + stackCopy[i].retain(); + } + } + int[] templateModeStackCopy = new int[templateModePtr + 1]; + System.arraycopy(templateModeStack, 0, templateModeStackCopy, 0, + templateModeStackCopy.length); + return new StateSnapshot<T>(stackCopy, listCopy, templateModeStackCopy, formPointer, + headPointer, mode, originalMode, framesetOk, + needToDropLF, quirks); + } + + public boolean snapshotMatches(TreeBuilderState<T> snapshot) { + StackNode<T>[] stackCopy = snapshot.getStack(); + int stackLen = snapshot.getStackLength(); + StackNode<T>[] listCopy = snapshot.getListOfActiveFormattingElements(); + int listLen = snapshot.getListOfActiveFormattingElementsLength(); + int[] templateModeStackCopy = snapshot.getTemplateModeStack(); + int templateModeStackLen = snapshot.getTemplateModeStackLength(); + + if (stackLen != currentPtr + 1 + || listLen != listPtr + 1 + || templateModeStackLen != templateModePtr + 1 + || formPointer != snapshot.getFormPointer() + || headPointer != snapshot.getHeadPointer() + || mode != snapshot.getMode() + || originalMode != snapshot.getOriginalMode() + || framesetOk != snapshot.isFramesetOk() + || needToDropLF != snapshot.isNeedToDropLF() + || quirks != snapshot.isQuirks()) { // maybe just assert quirks + return false; + } + for (int i = listLen - 1; i >= 0; i--) { + if (listCopy[i] == null + && listOfActiveFormattingElements[i] == null) { + continue; + } else if (listCopy[i] == null + || listOfActiveFormattingElements[i] == null) { + return false; + } + if (listCopy[i].node != listOfActiveFormattingElements[i].node) { + return false; // it's possible that this condition is overly + // strict + } + } + for (int i = stackLen - 1; i >= 0; i--) { + if (stackCopy[i].node != stack[i].node) { + return false; + } + } + for (int i = templateModeStackLen - 1; i >=0; i--) { + if (templateModeStackCopy[i] != templateModeStack[i]) { + return false; + } + } + return true; + } + + @SuppressWarnings("unchecked") public void loadState( + TreeBuilderState<T> snapshot) + throws SAXException { + // CPPONLY: mCurrentHtmlScriptIsAsyncOrDefer = false; + StackNode<T>[] stackCopy = snapshot.getStack(); + int stackLen = snapshot.getStackLength(); + StackNode<T>[] listCopy = snapshot.getListOfActiveFormattingElements(); + int listLen = snapshot.getListOfActiveFormattingElementsLength(); + int[] templateModeStackCopy = snapshot.getTemplateModeStack(); + int templateModeStackLen = snapshot.getTemplateModeStackLength(); + + for (int i = 0; i <= listPtr; i++) { + if (listOfActiveFormattingElements[i] != null) { + listOfActiveFormattingElements[i].release(this); + } + } + if (listOfActiveFormattingElements.length < listLen) { + listOfActiveFormattingElements = new StackNode[listLen]; + } + listPtr = listLen - 1; + + for (int i = 0; i <= currentPtr; i++) { + stack[i].release(this); + } + if (stack.length < stackLen) { + stack = new StackNode[stackLen]; + } + currentPtr = stackLen - 1; + + if (templateModeStack.length < templateModeStackLen) { + templateModeStack = new int[templateModeStackLen]; + } + templateModePtr = templateModeStackLen - 1; + + for (int i = 0; i < listLen; i++) { + StackNode<T> node = listCopy[i]; + if (node != null) { + StackNode<T> newNode = createStackNode(node.getFlags(), node.ns, + node.name, node.node, + node.popName, + node.attributes.cloneAttributes() + // CPPONLY: , node.getHtmlCreator() + // [NOCPP[ + , node.getLocator() + // ]NOCPP] + ); + listOfActiveFormattingElements[i] = newNode; + } else { + listOfActiveFormattingElements[i] = null; + } + } + for (int i = 0; i < stackLen; i++) { + StackNode<T> node = stackCopy[i]; + int listIndex = findInArray(node, listCopy); + if (listIndex == -1) { + StackNode<T> newNode = createStackNode(node.getFlags(), node.ns, + node.name, node.node, + node.popName, + null + // CPPONLY: , node.getHtmlCreator() + // [NOCPP[ + , node.getLocator() + // ]NOCPP] + ); + stack[i] = newNode; + } else { + stack[i] = listOfActiveFormattingElements[listIndex]; + stack[i].retain(); + } + } + System.arraycopy(templateModeStackCopy, 0, templateModeStack, 0, templateModeStackLen); + formPointer = snapshot.getFormPointer(); + headPointer = snapshot.getHeadPointer(); + mode = snapshot.getMode(); + originalMode = snapshot.getOriginalMode(); + framesetOk = snapshot.isFramesetOk(); + needToDropLF = snapshot.isNeedToDropLF(); + quirks = snapshot.isQuirks(); + } + + private int findInArray(StackNode<T> node, StackNode<T>[] arr) { + for (int i = listPtr; i >= 0; i--) { + if (node == arr[i]) { + return i; + } + } + return -1; + } + + /** + * Returns <code>stack[stackPos].node</code> if <code>stackPos</code> is + * smaller than Blink's magic limit or the node at Blink's magic limit + * otherwise. + * + * In order to get Blink-compatible handling of excessive deeply-nested + * markup, this method must be used to obtain the node that is used as the + * parent node of an insertion. + * + * Blink's magic number is 512, but our counting is off by one compared to + * Blink's way of counting, so in order to get the same + * externally-observable outcome, we use 511 as our magic number. + * + * @param stackPos the stack position to attempt to read + * @return node at the position capped to Blink's magic number + * @throws SAXException + */ + private T nodeFromStackWithBlinkCompat(int stackPos) throws SAXException { + // Magic number if off by one relative to Blink's magic number, but the + // outcome is the same, because the counting is different by one. + if (stackPos > 511) { + errDeepTree(); + return stack[511].node; + } + return stack[stackPos].node; + } + /** + * @see nu.validator.htmlparser.impl.TreeBuilderState#getFormPointer() + */ + @Override + public T getFormPointer() { + return formPointer; + } + + /** + * Returns the headPointer. + * + * @return the headPointer + */ + @Override + public T getHeadPointer() { + return headPointer; + } + + /** + * @see nu.validator.htmlparser.impl.TreeBuilderState#getListOfActiveFormattingElements() + */ + @Override + public StackNode<T>[] getListOfActiveFormattingElements() { + return listOfActiveFormattingElements; + } + + /** + * @see nu.validator.htmlparser.impl.TreeBuilderState#getStack() + */ + @Override + public StackNode<T>[] getStack() { + return stack; + } + + /** + * @see nu.validator.htmlparser.impl.TreeBuilderState#getTemplateModeStack() + */ + @Override + public int[] getTemplateModeStack() { + return templateModeStack; + } + + /** + * Returns the mode. + * + * @return the mode + */ + @Override + public int getMode() { + return mode; + } + + /** + * Returns the originalMode. + * + * @return the originalMode + */ + @Override + public int getOriginalMode() { + return originalMode; + } + + /** + * Returns the framesetOk. + * + * @return the framesetOk + */ + @Override + public boolean isFramesetOk() { + return framesetOk; + } + + /** + * Returns the needToDropLF. + * + * @return the needToDropLF + */ + @Override + public boolean isNeedToDropLF() { + return needToDropLF; + } + + /** + * Returns the quirks. + * + * @return the quirks + */ + @Override + public boolean isQuirks() { + return quirks; + } + + /** + * @see nu.validator.htmlparser.impl.TreeBuilderState#getListOfActiveFormattingElementsLength() + */ + @Override + public int getListOfActiveFormattingElementsLength() { + return listPtr + 1; + } + + /** + * @see nu.validator.htmlparser.impl.TreeBuilderState#getStackLength() + */ + @Override + public int getStackLength() { + return currentPtr + 1; + } + + /** + * @see nu.validator.htmlparser.impl.TreeBuilderState#getTemplateModeStackLength() + */ + @Override + public int getTemplateModeStackLength() { + return templateModePtr + 1; + } + + /** + * Complains about an over-deep tree. Theoretically this should just be + * a warning, but in practice authors should take this as an error. + * + * @throws SAXException + */ + private void errDeepTree() throws SAXException { + err("The document tree is more than 513 elements deep, which causes Firefox and Chrome to flatten the tree."); + } + + /** + * Reports a stray start tag. + * @param name the name of the stray tag + * + * @throws SAXException + */ + private void errStrayStartTag(@Local String name) throws SAXException { + err("Stray start tag \u201C" + name + "\u201D."); + } + + /** + * Reports a stray end tag. + * @param name the name of the stray tag + * + * @throws SAXException + */ + private void errStrayEndTag(@Local String name) throws SAXException { + err("Stray end tag \u201C" + name + "\u201D."); + } + + /** + * Reports a state when elements expected to be closed were not. + * + * @param eltPos the position of the start tag on the stack of the element + * being closed. + * @param name the name of the end tag + * + * @throws SAXException + */ + private void errUnclosedElements(int eltPos, @Local String name) throws SAXException { + errNoCheck("End tag \u201C" + name + "\u201D seen, but there were open elements."); + errListUnclosedStartTags(eltPos); + } + + /** + * Reports a state when elements expected to be closed ahead of an implied + * end tag but were not. + * + * @param eltPos the position of the start tag on the stack of the element + * being closed. + * @param name the name of the end tag + * + * @throws SAXException + */ + private void errUnclosedElementsImplied(int eltPos, String name) throws SAXException { + errNoCheck("End tag \u201C" + name + "\u201D implied, but there were open elements."); + errListUnclosedStartTags(eltPos); + } + + /** + * Reports a state when elements expected to be closed ahead of an implied + * table cell close. + * + * @param eltPos the position of the start tag on the stack of the element + * being closed. + * @throws SAXException + */ + private void errUnclosedElementsCell(int eltPos) throws SAXException { + errNoCheck("A table cell was implicitly closed, but there were open elements."); + errListUnclosedStartTags(eltPos); + } + + private void errStrayDoctype() throws SAXException { + err("Stray doctype."); + } + + private void errAlmostStandardsDoctype() throws SAXException { + if (!forceNoQuirks) { + err("Almost standards mode doctype. Expected \u201C<!DOCTYPE html>\u201D."); + } + } + + private void errQuirkyDoctype() throws SAXException { + if (!forceNoQuirks) { + err("Quirky doctype. Expected \u201C<!DOCTYPE html>\u201D."); + } + } + + private void errNonSpaceInTrailer() throws SAXException { + err("Non-space character in page trailer."); + } + + private void errNonSpaceAfterFrameset() throws SAXException { + err("Non-space after \u201Cframeset\u201D."); + } + + private void errNonSpaceInFrameset() throws SAXException { + err("Non-space in \u201Cframeset\u201D."); + } + + private void errNonSpaceAfterBody() throws SAXException { + err("Non-space character after body."); + } + + private void errNonSpaceInColgroupInFragment() throws SAXException { + err("Non-space in \u201Ccolgroup\u201D when parsing fragment."); + } + + private void errNonSpaceInNoscriptInHead() throws SAXException { + err("Non-space character inside \u201Cnoscript\u201D inside \u201Chead\u201D."); + } + + private void errFooBetweenHeadAndBody(@Local String name) throws SAXException { + if (errorHandler == null) { + return; + } + errNoCheck("\u201C" + name + "\u201D element between \u201Chead\u201D and \u201Cbody\u201D."); + } + + private void errStartTagWithoutDoctype() throws SAXException { + if (!forceNoQuirks) { + err("Start tag seen without seeing a doctype first. Expected \u201C<!DOCTYPE html>\u201D."); + } + } + + private void errNoSelectInTableScope() throws SAXException { + err("No \u201Cselect\u201D in table scope."); + } + + private void errStartSelectWhereEndSelectExpected() throws SAXException { + err("\u201Cselect\u201D start tag where end tag expected."); + } + + private void errStartTagWithSelectOpen(@Local String name) + throws SAXException { + if (errorHandler == null) { + return; + } + errNoCheck("\u201C" + name + + "\u201D start tag with \u201Cselect\u201D open."); + } + + private void errBadStartTagInNoscriptInHead(@Local String name) throws SAXException { + if (errorHandler == null) { + return; + } + errNoCheck("Bad start tag in \u201C" + name + + "\u201D in \u201Cnoscript\u201D in \u201Chead\u201D."); + } + + private void errImage() throws SAXException { + err("Saw a start tag \u201Cimage\u201D."); + } + + private void errFooSeenWhenFooOpen(@Local String name) throws SAXException { + if (errorHandler == null) { + return; + } + errNoCheck("Start tag \u201C" + name + "\u201D seen but an element of the same type was already open."); + } + + private void errHeadingWhenHeadingOpen() throws SAXException { + err("Heading cannot be a child of another heading."); + } + + private void errFramesetStart() throws SAXException { + err("\u201Cframeset\u201D start tag seen."); + } + + private void errNoCellToClose() throws SAXException { + err("No cell to close."); + } + + private void errStartTagInTable(@Local String name) throws SAXException { + if (errorHandler == null) { + return; + } + errNoCheck("Start tag \u201C" + name + + "\u201D seen in \u201Ctable\u201D."); + } + + private void errFormWhenFormOpen() throws SAXException { + err("Saw a \u201Cform\u201D start tag, but there was already an active \u201Cform\u201D element. Nested forms are not allowed. Ignoring the tag."); + } + + private void errTableSeenWhileTableOpen() throws SAXException { + err("Start tag for \u201Ctable\u201D seen but the previous \u201Ctable\u201D is still open."); + } + + private void errStartTagInTableBody(@Local String name) throws SAXException { + if (errorHandler == null) { + return; + } + errNoCheck("\u201C" + name + "\u201D start tag in table body."); + } + + private void errEndTagSeenWithoutDoctype() throws SAXException { + if (!forceNoQuirks) { + err("End tag seen without seeing a doctype first. Expected \u201C<!DOCTYPE html>\u201D."); + } + } + + private void errEndTagAfterBody() throws SAXException { + err("Saw an end tag after \u201Cbody\u201D had been closed."); + } + + private void errEndTagSeenWithSelectOpen(@Local String name) throws SAXException { + if (errorHandler == null) { + return; + } + errNoCheck("\u201C" + name + + "\u201D end tag with \u201Cselect\u201D open."); + } + + private void errGarbageInColgroup() throws SAXException { + err("Garbage in \u201Ccolgroup\u201D fragment."); + } + + private void errEndTagBr() throws SAXException { + err("End tag \u201Cbr\u201D."); + } + + private void errNoElementToCloseButEndTagSeen(@Local String name) + throws SAXException { + if (errorHandler == null) { + return; + } + errNoCheck("No \u201C" + name + "\u201D element in scope but a \u201C" + + name + "\u201D end tag seen."); + } + + private void errHtmlStartTagInForeignContext(@Local String name) + throws SAXException { + if (errorHandler == null) { + return; + } + errNoCheck("HTML start tag \u201C" + name + + "\u201D in a foreign namespace context."); + } + + private void errNoTableRowToClose() throws SAXException { + err("No table row to close."); + } + + private void errNonSpaceInTable() throws SAXException { + err("Misplaced non-space characters inside a table."); + } + + private void errUnclosedChildrenInRuby() throws SAXException { + if (errorHandler == null) { + return; + } + errNoCheck("Unclosed children in \u201Cruby\u201D."); + } + + private void errStartTagSeenWithoutRuby(@Local String name) throws SAXException { + if (errorHandler == null) { + return; + } + errNoCheck("Start tag \u201C" + + name + + "\u201D seen without a \u201Cruby\u201D element being open."); + } + + private void errSelfClosing() throws SAXException { + if (errorHandler == null) { + return; + } + errNoCheck("Self-closing syntax (\u201C/>\u201D) used on a non-void HTML element. Ignoring the slash and treating as a start tag."); + } + + private void errNoCheckUnclosedElementsOnStack() throws SAXException { + errNoCheck("Unclosed elements on stack."); + } + + private void errEndTagDidNotMatchCurrentOpenElement(@Local String name, + @Local String currOpenName) throws SAXException { + if (errorHandler == null) { + return; + } + errNoCheck("End tag \u201C" + + name + + "\u201D did not match the name of the current open element (\u201C" + + currOpenName + "\u201D)."); + } + + private void errEndTagViolatesNestingRules(@Local String name) throws SAXException { + if (errorHandler == null) { + return; + } + errNoCheck("End tag \u201C" + name + "\u201D violates nesting rules."); + } + + private void errEofWithUnclosedElements() throws SAXException { + if (errorHandler == null) { + return; + } + errNoCheck("End of file seen and there were open elements."); + // just report all remaining unclosed elements + errListUnclosedStartTags(0); + } + + /** + * Reports arriving at/near end of document with unclosed elements remaining. + * + * @param message + * the message + * @throws SAXException + */ + private void errEndWithUnclosedElements(@Local String name) throws SAXException { + if (errorHandler == null) { + return; + } + errNoCheck("End tag for \u201C" + + name + + "\u201D seen, but there were unclosed elements."); + // just report all remaining unclosed elements + errListUnclosedStartTags(0); + } +} diff --git a/parser/html/javasrc/UTF16Buffer.java b/parser/html/javasrc/UTF16Buffer.java new file mode 100644 index 0000000000..ec79185ec2 --- /dev/null +++ b/parser/html/javasrc/UTF16Buffer.java @@ -0,0 +1,151 @@ +/* + * Copyright (c) 2008-2010 Mozilla Foundation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + */ + +package nu.validator.htmlparser.impl; + +import nu.validator.htmlparser.annotation.NoLength; + +/** + * An UTF-16 buffer that knows the start and end indeces of its unconsumed + * content. + * + * @version $Id$ + * @author hsivonen + */ +public final class UTF16Buffer { + + /** + * The backing store of the buffer. May be larger than the logical content + * of this <code>UTF16Buffer</code>. + */ + private final @NoLength char[] buffer; + + /** + * The index of the first unconsumed character in the backing buffer. + */ + private int start; + + /** + * The index of the slot immediately after the last character in the backing + * buffer that is part of the logical content of this + * <code>UTF16Buffer</code>. + */ + private int end; + + //[NOCPP[ + + /** + * Constructor for wrapping an existing UTF-16 code unit array. + * + * @param buffer + * the backing buffer + * @param start + * the index of the first character to consume + * @param end + * the index immediately after the last character to consume + */ + public UTF16Buffer(@NoLength char[] buffer, int start, int end) { + this.buffer = buffer; + this.start = start; + this.end = end; + } + + // ]NOCPP] + + /** + * Returns the start index. + * + * @return the start index + */ + public int getStart() { + return start; + } + + /** + * Sets the start index. + * + * @param start + * the start index + */ + public void setStart(int start) { + this.start = start; + } + + /** + * Returns the backing buffer. + * + * @return the backing buffer + */ + public @NoLength char[] getBuffer() { + return buffer; + } + + /** + * Returns the end index. + * + * @return the end index + */ + public int getEnd() { + return end; + } + + /** + * Checks if the buffer has data left. + * + * @return <code>true</code> if there's data left + */ + public boolean hasMore() { + return start < end; + } + + /** + * Returns <code>end - start</code>. + * + * @return <code>end - start</code> + */ + public int getLength() { + return end - start; + } + + /** + * Adjusts the start index to skip over the first character if it is a line + * feed and the previous character was a carriage return. + * + * @param lastWasCR + * whether the previous character was a carriage return + */ + public void adjust(boolean lastWasCR) { + if (lastWasCR && buffer[start] == '\n') { + start++; + } + } + + /** + * Sets the end index. + * + * @param end + * the end index + */ + public void setEnd(int end) { + this.end = end; + } +} |