diff options
Diffstat (limited to 'lib/libUPnP/Neptune/Source/Tests/Xml1')
| -rw-r--r-- | lib/libUPnP/Neptune/Source/Tests/Xml1/XmlTest1.cpp | 591 | ||||
| -rw-r--r-- | lib/libUPnP/Neptune/Source/Tests/Xml1/XmlTest1Data.cpp | 843 | ||||
| -rw-r--r-- | lib/libUPnP/Neptune/Source/Tests/Xml1/big.xml | 3277 | ||||
| -rw-r--r-- | lib/libUPnP/Neptune/Source/Tests/Xml1/test.xml | 16 | ||||
| -rw-r--r-- | lib/libUPnP/Neptune/Source/Tests/Xml1/unicode.xml | 1 |
5 files changed, 4728 insertions, 0 deletions
diff --git a/lib/libUPnP/Neptune/Source/Tests/Xml1/XmlTest1.cpp b/lib/libUPnP/Neptune/Source/Tests/Xml1/XmlTest1.cpp new file mode 100644 index 0000000..0b101ee --- /dev/null +++ b/lib/libUPnP/Neptune/Source/Tests/Xml1/XmlTest1.cpp @@ -0,0 +1,591 @@ +/***************************************************************** +| +| XML Test Program 1 +| +| (c) 2001-2003 Gilles Boccon-Gibod +| Author: Gilles Boccon-Gibod (bok@bok.net) +| + ****************************************************************/ + +/*---------------------------------------------------------------------- +| includes ++---------------------------------------------------------------------*/ +#include <stdlib.h> +#include <assert.h> +#include "Neptune.h" +#include "NptDebug.h" + +/*---------------------------------------------------------------------- +| CHECK ++---------------------------------------------------------------------*/ +#define CHECK(test) \ +do { \ + if (!(test)) { \ + fprintf(stderr, "FAILED: line %d\n", __LINE__); \ + assert(0); \ + } \ +} while(0) + +/*---------------------------------------------------------------------- +| TestWriter ++---------------------------------------------------------------------*/ +static void +TestWriter() +{ + NPT_XmlElementNode* top = new NPT_XmlElementNode("top"); + NPT_XmlElementNode* child1 = new NPT_XmlElementNode("child1"); + child1->SetAttribute("someAttribute", "someValue"); + top->AddChild(child1); + NPT_XmlElementNode* child2 = new NPT_XmlElementNode("child2"); + child2->SetAttribute("someOtherAttribute", "someOtherValue"); + child2->AddText("Some Text"); + child1->AddChild(child2); + NPT_XmlElementNode* child3 = new NPT_XmlElementNode("child3"); + child3->SetAttribute("thirdArrtibute", "3"); + child2->AddChild(child3); + + NPT_XmlWriter writer; + NPT_File out(NPT_FILE_STANDARD_OUTPUT); + out.Open(NPT_FILE_OPEN_MODE_WRITE); + NPT_OutputStreamReference out_stream; + out.GetOutputStream(out_stream); + + writer.Serialize(*top, *out_stream); +} + +#if defined(_WIN32) && defined(_DEBUG) && !defined(UNDER_CE) +#include <crtdbg.h> +#endif + +/*---------------------------------------------------------------------- +| TestFinders ++---------------------------------------------------------------------*/ +static void +TestFinders() +{ + const char* xml = "<a b='foo' c='bar' ns:b='bla' ns:d='123' xmlns:ns='ns-uri' xmlns:ns1='ns1-uri' xmlns:ns2='ns2-uri' xmlns:ns3='ns3-uri'><b xmlns='ns4-uri' ba='123' ns2:bo='345'></b><b ba='123' ns2:bo='345'></b><ns2:b></ns2:b><ns1:b></ns1:b></a>"; + NPT_XmlParser parser; + NPT_XmlNode* root; + CHECK(NPT_SUCCEEDED(parser.Parse(xml, root))); + + NPT_XmlElementNode* elem = root->AsElementNode(); + const NPT_String* attr = elem->GetAttribute("d"); + CHECK(attr == NULL); + attr = elem->GetAttribute("b"); + CHECK(attr != NULL && *attr == "foo"); + attr = elem->GetAttribute("b", "ns-uri"); + CHECK(attr != NULL && *attr == "bla"); + attr = elem->GetAttribute("c", NPT_XML_ANY_NAMESPACE); + CHECK(attr != NULL && *attr == "bar"); + attr = elem->GetAttribute("b", NPT_XML_ANY_NAMESPACE); + CHECK(attr != NULL && *attr == "foo"); + attr = elem->GetAttribute("b", "boubou"); + CHECK(attr == NULL); + attr = elem->GetAttribute("d", NPT_XML_NO_NAMESPACE); + CHECK(attr == NULL); + + NPT_XmlElementNode* child; + child = elem->GetChild("b"); + CHECK(child != NULL && *child->GetAttribute("ba") == "123"); + child = elem->GetChild("b", "ns4-uri"); + CHECK(child != NULL && child->GetAttribute("ba", "ns4-uri") == NULL); + CHECK(child != NULL && *child->GetAttribute("bo", NPT_XML_ANY_NAMESPACE) == "345"); + CHECK(child != NULL && child->GetAttribute("bo", NPT_XML_NO_NAMESPACE) == NULL); + CHECK(child != NULL && child->GetAttribute("bo", "foo") == NULL); + CHECK(child != NULL && *child->GetAttribute("bo", "ns2-uri") == "345"); + child = elem->GetChild("b", NPT_XML_ANY_NAMESPACE); + CHECK(child != NULL && *child->GetNamespace() == "ns4-uri"); + child = elem->GetChild("b", "ns2-uri"); + CHECK(child != NULL && *child->GetNamespace() == "ns2-uri"); + child = elem->GetChild("b", "boubou"); + CHECK(child == NULL); + + delete root; +} + +/*---------------------------------------------------------------------- +| TestNamespaces ++---------------------------------------------------------------------*/ +static void +TestNamespaces() +{ + NPT_XmlElementNode* top = new NPT_XmlElementNode("top"); + top->SetNamespaceUri("", "http://namespace1.com"); + CHECK(top->GetNamespaceUri("") && + *(top->GetNamespaceUri("")) == "http://namespace1.com"); + + NPT_XmlElementNode* child1 = new NPT_XmlElementNode("child1"); + top->AddChild(child1); + CHECK(child1->GetNamespaceUri("")); + CHECK(*(child1->GetNamespaceUri("")) == "http://namespace1.com"); + + NPT_XmlElementNode* child2 = new NPT_XmlElementNode("ns1", "child2"); + top->AddChild(child2); + CHECK(child2->GetNamespaceUri("")); + CHECK(*(child2->GetNamespaceUri("")) == "http://namespace1.com"); + CHECK(child2->GetNamespaceUri("ns1") == NULL); + child2->SetNamespaceUri("ns1", "http://blabla"); + CHECK(child2->GetNamespaceUri("ns1")); + CHECK(*child2->GetNamespaceUri("ns1") == "http://blabla"); + CHECK(*child2->GetNamespace() == "http://blabla"); + + // testing a child with a namespace defined in parent + NPT_XmlElementNode* child3 = new NPT_XmlElementNode("ns1", "child3"); + child2->AddChild(child3); + CHECK(child3->GetNamespaceUri("")); + CHECK(*(child3->GetNamespaceUri("")) == "http://namespace1.com"); + CHECK(child3->GetNamespaceUri("ns1")); + CHECK(*child3->GetNamespaceUri("ns1") == "http://blabla"); + CHECK(*child3->GetNamespace() == "http://blabla"); + + // testing adding a namespace in a node which namespace is defined in parent + child3->SetNamespaceUri("ns3", "http://foofoo"); + CHECK(child3->GetNamespaceUri("ns1")); + CHECK(*child3->GetNamespaceUri("ns1") == "http://blabla"); + CHECK(*child3->GetNamespace() == "http://blabla"); + + const char* xml1 = + "<top>" + " <child1 xmlns:foo='blabla'><cc1 foo:attr1='0'/></child1>" + " <child2 xmlns='foobar' attr1='1'>" + " <cc2/>" + " <cc3 />" + " </child2 >" + " <ns2:child3 xmlns:ns2='abcd'><cc3/></ns2:child3>" + " <child4 ns3:attr1='3' xmlns:ns3='efgh'>" + " <ns3:cc4 ns3:attr1='4'/>" + " </child4>" + "</top>"; + NPT_XmlParser parser; + NPT_XmlNode* root = NULL; + NPT_Result result = parser.Parse(xml1, root); + CHECK(NPT_SUCCEEDED(result)); + CHECK(root != NULL); + + NPT_XmlWriter writer; + NPT_MemoryStream output; + writer.Serialize(*root, output); + NPT_LargeSize size; + output.GetSize(size); + printf("%s", NPT_String((const char*)output.GetData(), (NPT_Size)size).GetChars()); + + delete top; + delete root; + + // test default and empty namespaces + const char* xml2 = "<top><a></a><b xmlns='foo'><c xmlns=''></c></b></top>"; + result = parser.Parse(xml2, root); + CHECK(root->AsElementNode()->GetNamespace() == NULL); + NPT_XmlElementNode* a_elem = (*root->AsElementNode()->GetChildren().GetItem(0))->AsElementNode(); + CHECK(a_elem->GetNamespace() == NULL); + NPT_XmlElementNode* b_elem = (*root->AsElementNode()->GetChildren().GetItem(1))->AsElementNode(); + CHECK(*b_elem->GetNamespace() == "foo"); + NPT_XmlElementNode* c_elem = (*b_elem->GetChildren().GetItem(0))->AsElementNode(); + CHECK(c_elem->GetNamespace() == NULL); + + delete root; +} + +/*---------------------------------------------------------------------- +| TestSerializer ++---------------------------------------------------------------------*/ +static void +TestSerializer() +{ + NPT_XmlWriter writer; + NPT_MemoryStream output; + NPT_String check; + NPT_LargeSize size; + + // + // test without namespaces + // + + // simple element with no prefix and no namespace + NPT_XmlElementNode* top = new NPT_XmlElementNode("top"); + writer.Serialize(*top, output); + output.GetSize(size); + check.Assign((const char*)output.GetData(), (NPT_Size)size); + CHECK(check == "<top/>"); + + // with one attribute + output.SetDataSize(0); + top->SetAttribute("attr1", "b&w"); + writer.Serialize(*top, output); + output.GetSize(size); + check.Assign((const char*)output.GetData(), (NPT_Size)size); + CHECK(check == "<top attr1=\"b&w\"/>"); + + // add one child + output.SetDataSize(0); + delete top; + top = new NPT_XmlElementNode("top"); + NPT_XmlElementNode* child1 = new NPT_XmlElementNode("child1"); + top->AddChild(child1); + writer.Serialize(*top, output); + output.GetSize(size); + check.Assign((const char*)output.GetData(), (NPT_Size)size); + CHECK(check == "<top><child1/></top>"); + + // + // test with namespaces + // + + // test default namespaces + output.SetDataSize(0); + delete top; + top = new NPT_XmlElementNode("top"); + top->SetNamespaceUri("", "http://namespace.com"); + writer.Serialize(*top, output); + output.GetSize(size); + check.Assign((const char*)output.GetData(), (NPT_Size)size); + CHECK(check == "<top xmlns=\"http://namespace.com\"/>"); + + // test attribute prefixes + output.SetDataSize(0); + delete top; + top = new NPT_XmlElementNode("top"); + top->SetAttribute(NULL, "foo", "6"); + top->SetAttribute("ns1", "foo", "3"); + top->SetAttribute("ns2", "foo", "4"); + top->SetAttribute("ns1", "foo", "5"); + writer.Serialize(*top, output); + output.GetSize(size); + check.Assign((const char*)output.GetData(), (NPT_Size)size); + CHECK(check == "<top foo=\"6\" ns1:foo=\"5\" ns2:foo=\"4\"/>"); + + delete top; +} + +/*---------------------------------------------------------------------- +| TestCanonicalizer ++---------------------------------------------------------------------*/ +static void +TestCanonicalizer() +{ + extern const char* xml_cano_1[]; + + NPT_XmlParser parser(true); // do not ignore whitespaces + NPT_XmlNode* root; + + for (unsigned int i=0; xml_cano_1[i]; i+=2) { + const char* xml_in = xml_cano_1[i]; + const char* xml_out = xml_cano_1[i+1]; + CHECK(NPT_SUCCEEDED(parser.Parse(xml_in, root))); + CHECK(root); + + NPT_XmlCanonicalizer canonicalizer; + NPT_MemoryStream buffer1; + NPT_Result result = canonicalizer.Serialize(*root, buffer1); + CHECK(result == NPT_SUCCESS); + + NPT_String str((const char*)buffer1.GetData(), buffer1.GetDataSize()); + NPT_Debug("%s", str.GetChars()); + CHECK(str == xml_out); + + delete root; + + CHECK(NPT_SUCCEEDED(parser.Parse(str, root))); + CHECK(root); + NPT_MemoryStream buffer2; + result = canonicalizer.Serialize(*root, buffer2); + CHECK(buffer1.GetBuffer() == buffer2.GetBuffer()); + + delete root; + } +} + +/*---------------------------------------------------------------------- +| TestRegression ++---------------------------------------------------------------------*/ +static void +TestRegression() +{ + // test for a bug found when the XML parser would try + // to compare a null prefix + NPT_XmlElementNode* element = new NPT_XmlElementNode("hello"); + element->SetAttribute("ns", "foo", "6"); + element->SetAttribute("foo", "5"); + element->SetAttribute("ns", "foo", "7"); + element->SetAttribute("foo", "8"); + element->SetNamespaceUri("ns", "blabla"); + CHECK(*element->GetAttribute("foo") == "8"); + CHECK(*element->GetAttribute("foo", "blabla") == "7"); + + delete element; +} + +/*---------------------------------------------------------------------- +| TestWhitespace ++---------------------------------------------------------------------*/ +static void +TestWhitespace() +{ + const char* xml = +"<doc>\r\n" +" <clean> </clean>\r\n" +" <dirty> A B </dirty>\r\n" +" <mixed>\r\n" +" A\r\n" +" <clean> </clean>\r\n" +" B\r\n" +" <dirty> A B </dirty>\r\n" +" C\r\n" +" </mixed>\r\n" +"</doc>\r\n"; + + const char* expect1 = +"<doc><clean/><dirty> A B </dirty><mixed>\n" +" A\n" +" <clean/>\n" +" B\n" +" <dirty> A B </dirty>\n" +" C\n" +" </mixed></doc>"; + + const char* expect2 = +"<doc>\n" +" <clean> </clean>\n" +" <dirty> A B </dirty>\n" +" <mixed>\n" +" A\n" +" <clean> </clean>\n" +" B\n" +" <dirty> A B </dirty>\n" +" C\n" +" </mixed>\n" +"</doc>"; + + NPT_XmlParser parser1(false); // ignore whitespace + NPT_XmlNode* root; + CHECK(NPT_SUCCEEDED(parser1.Parse(xml, root))); + CHECK(root); + + NPT_XmlWriter writer; + NPT_MemoryStream buffer; + writer.Serialize(*root, buffer); + CHECK(buffer.GetBuffer() == NPT_DataBuffer(expect1, NPT_StringLength(expect1))); + + delete root; + + NPT_XmlParser parser2(true); // keep whitespace + CHECK(NPT_SUCCEEDED(parser2.Parse(xml, root))); + CHECK(root); + + buffer.SetDataSize(0); + writer.Serialize(*root, buffer); + CHECK(buffer.GetBuffer() == NPT_DataBuffer(expect2, NPT_StringLength(expect2))); + + delete root; +} + +/*---------------------------------------------------------------------- +| TestComments ++---------------------------------------------------------------------*/ +static void +TestComments() +{ + const char* xml = + "<!-- comment outside the element -->\n" + "<doc> blabla <!-- --> foo <!-- you <g> &foo -> &bar --> blibli</doc>"; + const char* expect = "<doc> blabla foo blibli</doc>"; + + NPT_XmlParser parser; + NPT_XmlNode* root; + CHECK(NPT_SUCCEEDED(parser.Parse(xml, root))); + CHECK(root); + + NPT_XmlWriter writer; + NPT_MemoryStream buffer; + writer.Serialize(*root, buffer); + CHECK(buffer.GetBuffer() == NPT_DataBuffer(expect, NPT_StringLength(expect))); + + delete root; +} + +/*---------------------------------------------------------------------- +| TestCdata ++---------------------------------------------------------------------*/ +static void +TestCdata() +{ + const char* xml = + "<doc> blabla <![CDATA[ < [[ Smith ]] > ]]> blibli</doc>"; + const char* expect = "<doc> blabla < [[ Smith ]] > blibli</doc>"; + + NPT_XmlParser parser; + NPT_XmlNode* root; + CHECK(NPT_SUCCEEDED(parser.Parse(xml, root))); + CHECK(root); + + NPT_XmlWriter writer; + NPT_MemoryStream buffer; + writer.Serialize(*root, buffer); + CHECK(buffer.GetBuffer() == NPT_DataBuffer(expect, NPT_StringLength(expect))); + + delete root; +} + +/*---------------------------------------------------------------------- +| TestAttributes ++---------------------------------------------------------------------*/ +static void +TestAttributes() +{ + const char* xml = + "<element foo='blabla'><cc1 attr1='0'/></element>"; + NPT_XmlParser parser; + NPT_XmlNode* root = NULL; + NPT_Result result = parser.Parse(xml, root); + CHECK(NPT_SUCCEEDED(result)); + CHECK(root != NULL); + CHECK(root->AsElementNode() != NULL); + const NPT_String* a = root->AsElementNode()->GetAttribute("foo"); + CHECK(*a == "blabla"); + delete root; +} + +/*---------------------------------------------------------------------- +| TestAttributeNormalization ++---------------------------------------------------------------------*/ +static void +TestAttributeNormalization() +{ + const char* xml = "<x a='\n\n xyz abc 
 
 	   12\r\n3\r4\n5 6 '/>"; + NPT_XmlParser parser; + NPT_XmlNode* root = NULL; + NPT_Result result = parser.Parse(xml, root); + CHECK(NPT_SUCCEEDED(result)); + CHECK(root != NULL); + CHECK(root->AsElementNode() != NULL); + const NPT_String* a = root->AsElementNode()->GetAttribute("a"); + CHECK(*a == " xyz abc \r \n \t 12 3 4 5 6 "); + delete root; +} + + +/*---------------------------------------------------------------------- +| TestMakeStandalone ++---------------------------------------------------------------------*/ +static void +TestMakeStandalone() +{ + const char* xml = + "<parent xmlns:foo='foo-ns' xmlns:bar='bar-ns' xmlns='default-ns'><inter xmlns:bli='bli-ns' xmlns:bou='bou-ns'><child><foo:a>a-text</foo:a><bar:b xml:fifi='0'>b-text</bar:b><c>c-text</c><d bou:att='b-att'/></child></inter></parent>"; + const char* expected = + "<child xmlns=\"default-ns\" xmlns:foo=\"foo-ns\" xmlns:bar=\"bar-ns\" xmlns:bou=\"bou-ns\"><foo:a>a-text</foo:a><bar:b xml:fifi=\"0\">b-text</bar:b><c>c-text</c><d bou:att=\"b-att\"/></child>"; + NPT_XmlParser parser; + NPT_XmlNode* root = NULL; + NPT_Result result = parser.Parse(xml, root); + CHECK(NPT_SUCCEEDED(result)); + CHECK(root != NULL); + CHECK(root->AsElementNode() != NULL); + NPT_XmlElementNode* inter = root->AsElementNode()->GetChild("inter", NPT_XML_ANY_NAMESPACE); + CHECK(inter != NULL); + NPT_XmlElementNode* child = inter->GetChild("child", NPT_XML_ANY_NAMESPACE); + CHECK(child != NULL); + child->MakeStandalone(); + NPT_XmlWriter writer; + NPT_MemoryStream buffer; + writer.Serialize(*child, buffer); + CHECK(buffer.GetBuffer() == NPT_DataBuffer(expected, NPT_StringLength(expected))); + + + delete root; +} + +/*---------------------------------------------------------------------- +| TestFile ++---------------------------------------------------------------------*/ +static void +TestFile(const char* filename) +{ + NPT_InputStreamReference stream; + NPT_Result result; + + // open the input file + NPT_File input(filename); + result = input.Open(NPT_FILE_OPEN_MODE_READ); + if (NPT_FAILED(result)) { + NPT_Debug("XmtTest1:: cannot open input (%d)\n", result); + return; + } + result = input.GetInputStream(stream); + + // parse the buffer + NPT_XmlParser parser; + NPT_XmlNode* tree = NULL; + result = parser.Parse(*stream, tree); + if (NPT_FAILED(result)) { + NPT_Debug("XmlTest1:: cannot parse input (%d)\n", result); + return; + } + + + // dump the tree + NPT_XmlWriter writer(2); + NPT_File output(NPT_FILE_STANDARD_OUTPUT); + output.Open(NPT_FILE_OPEN_MODE_WRITE); + NPT_OutputStreamReference output_stream_ref; + output.GetOutputStream(output_stream_ref); + writer.Serialize(*tree, *output_stream_ref); + + // delete the tree + delete tree; +} + +/*---------------------------------------------------------------------- +| TestBadInput ++---------------------------------------------------------------------*/ +static void +TestBadInput() +{ + NPT_XmlParser parser; + NPT_XmlNode* root = NULL; + + const char* doc = "<top1></top1><top2></top2>"; + NPT_Result result = parser.Parse(doc, root); + CHECK(result == NPT_ERROR_XML_MULTIPLE_ROOTS); + CHECK(root == NULL); +} + +/*---------------------------------------------------------------------- +| main ++---------------------------------------------------------------------*/ +int +main(int argc, char** argv) +{ + // setup debugging +#if defined(_WIN32) && defined(_DEBUG) && !defined(UNDER_CE) + int flags = _crtDbgFlag | + _CRTDBG_ALLOC_MEM_DF | + _CRTDBG_DELAY_FREE_MEM_DF | + _CRTDBG_CHECK_ALWAYS_DF; + + _CrtSetDbgFlag(flags); + //AllocConsole(); + //freopen("CONOUT$", "w", stdout); +#endif + + // check args + if (argc == 2) { + TestFile(argv[1]); + return 0; + } + + TestRegression(); + TestComments(); + TestCdata(); + TestWhitespace(); + TestAttributes(); + TestAttributeNormalization(); + TestNamespaces(); + TestSerializer(); + TestMakeStandalone(); + TestCanonicalizer(); + TestFinders(); + TestWriter(); + TestBadInput(); + + return 0; +} diff --git a/lib/libUPnP/Neptune/Source/Tests/Xml1/XmlTest1Data.cpp b/lib/libUPnP/Neptune/Source/Tests/Xml1/XmlTest1Data.cpp new file mode 100644 index 0000000..3171284 --- /dev/null +++ b/lib/libUPnP/Neptune/Source/Tests/Xml1/XmlTest1Data.cpp @@ -0,0 +1,843 @@ +const char* xml_cano_1[] = { +// test 1 +"<doc>\r\n" +" <e1 />\r\n" +" <e2 ></e2>\r\n" +" <e3 name = 'elem3' id='elem3' />\r\n" +" <e4 name='elem4' id='elem4' ></e4>\r\n" +" <e5 a:attr='out' b:attr='sorted' attr2='all' attr=\"I'm\"\r\n" +" xmlns:b=\"http://www.ietf.org\"\r\n" +" xmlns:a=\"http://www.w3.org\"\r\n" +" xmlns=\"http://example.org\"/>\r\n" +" <e6 xmlns=\"\" xmlns:a=\"http://www.w3.org\">\r\n" +" <e7 xmlns=\"http://www.ietf.org\">\r\n" +" <e8 xmlns=\"\" xmlns:a=\"http://www.w3.org\">\r\n" +" <e9 xmlns=\"\" xmlns:a=\"http://www.ietf.org\"/>\r\n" +" </e8>\r\n" +" </e7>\r\n" +" </e6>\r\n" +"</doc>", + +"<doc>\n" +" <e1></e1>\n" +" <e2></e2>\n" +" <e3 id=\"elem3\" name=\"elem3\"></e3>\n" +" <e4 id=\"elem4\" name=\"elem4\"></e4>\n" +" <e5 xmlns=\"http://example.org\" xmlns:a=\"http://www.w3.org\" xmlns:b=\"http://www.ietf.org\" attr=\"I'm\" attr2=\"all\" b:attr=\"sorted\" a:attr=\"out\"></e5>\n" +" <e6>\n" +" <e7 xmlns=\"http://www.ietf.org\">\n" +" <e8 xmlns=\"\">\n" +" <e9></e9>\n" +" </e8>\n" +" </e7>\n" +" </e6>\n" +"</doc>", + +// test 2 +"<a>\n" +" <b xmlns:foo='foo-ns'>\n" +" <c xmlns='d1-ns'>\n" +" <foo:d/>\n" +" <e xmlns='e1-ns'>\n" +" <gloo:f xmlns:gloo='e1-ns'/>\n" +" </e>\n" +" <f xmlns=''>\n" +" <foo:g/>\n" +" </f>\n" +" </c>\n" +" </b>\n" +"</a>", + +"<a>\n" +" <b>\n" +" <c xmlns=\"d1-ns\">\n" +" <foo:d xmlns:foo=\"foo-ns\"></foo:d>\n" +" <e xmlns=\"e1-ns\">\n" +" <gloo:f xmlns:gloo=\"e1-ns\"></gloo:f>\n" +" </e>\n" +" <f xmlns=\"\">\n" +" <foo:g xmlns:foo=\"foo-ns\"></foo:g>\n" +" </f>\n" +" </c>\n" +" </b>\n" +"</a>", + +// test 3 +"<foo:bar xmlns:foo=\"http://a.com\">\n" +" <bla:zoo xmlns:bla=\"http://a.com\">\n" +" <elt foo:att=\"att1\" bla:btt=\"att2\">youf</elt>\n" +" </bla:zoo>\n" +"</foo:bar>", + +"<foo:bar xmlns:foo=\"http://a.com\">\n" +" <bla:zoo xmlns:bla=\"http://a.com\">\n" +" <elt foo:att=\"att1\" bla:btt=\"att2\">youf</elt>\n" +" </bla:zoo>\n" +"</foo:bar>", + +// test 4 +"<foo:bar xmlns:foo=\"http://a.com\">\n" +" <bla:zoo xmlns:bla=\"http://a.com\">\n" +" <elt foo:btt=\"att1\" bla:att=\"att2\">youf</elt>\n" +" </bla:zoo>\n" +"</foo:bar>", + +"<foo:bar xmlns:foo=\"http://a.com\">\n" +" <bla:zoo xmlns:bla=\"http://a.com\">\n" +" <elt bla:att=\"att2\" foo:btt=\"att1\">youf</elt>\n" +" </bla:zoo>\n" +"</foo:bar>", +// Test att1-xmlsec.xml +"<elt xmlns:foo = 'http://a.org'>\n" +"<elt2 foo:att='1'>lolo</elt2>\n" +"</elt>" +, +"<elt>\n" +"<elt2 xmlns:foo=\"http://a.org\" foo:att=\"1\">lolo</elt2>\n" +"</elt>" +, +// Test att2-xmlsec.xml +"<elt xmlns:foo = 'http://a.org' xmlns:bar='http://b.org'>\n" +" <elt1 bar:att=\"2\" foo:att='1'>babar</elt1>\n" +"</elt>" +, +"<elt>\n" +" <elt1 xmlns:bar=\"http://b.org\" xmlns:foo=\"http://a.org\" foo:att=\"1\" bar:att=\"2\">babar</elt1>\n" +"</elt>" +, +// Test char_modi-xmlsec.xml +"<doc>\n" +" <norm attr='	'/>\n" +"</doc>" +, +"<doc>\n" +" <norm attr=\"	\"></norm>\n" +"</doc>" +, +// Test char_modif_char_ref-xmlsec.xml +"<doc>\n" +" <text>First line
 Second line</text>\n" +" <value>2</value>\n" +" <compute></compute>\n" +" <compute expr='value>\"0\" && value<\"10\" ?\"valid\":\"error\"'>valid</compute>\n" +" <norm attr=' '   
	 ' '/>\n" +" <normNames attr=' A   
	 B '/>\n" +"</doc>" +, +"<doc>\n" +" <text>First line
\n" +"Second line</text>\n" +" <value>2</value>\n" +" <compute></compute>\n" +" <compute expr=\"value>"0" && value<"10" ?"valid":"error"\">valid</compute>\n" +" <norm attr=\" ' 
	 ' \"></norm>\n" +" <normNames attr=\" A 
	 B \"></normNames>\n" +"</doc>" +, +// Test comments-xmlsec.xml +"<?xml version=\"1.0\"?>\n" +"\n" +"\n" +"\n" +"<doc>Bonjour le monde !<!-- Commentaire 1 --></doc>\n" +"\n" +"<!-- Commentaire 2 -->" +, +"<doc>Bonjour le monde !</doc>" +, +// Test document_subset-xmlsec.xml +"<doc xmlns=\"http://www.ietf.org\" xmlns:w3c=\"http://www.w3.org\">\n" +" <e1>\n" +" <e2 xmlns=\"\">\n" +" <e3 id=\"E3\"/>\n" +" </e2>\n" +" </e1>\n" +"</doc>" +, +"<doc xmlns=\"http://www.ietf.org\">\n" +" <e1>\n" +" <e2 xmlns=\"\">\n" +" <e3 id=\"E3\"></e3>\n" +" </e2>\n" +" </e1>\n" +"</doc>" +, +// Test namespaces2-xmlsec.xml +"<elt xmlns:foo = 'http://a.org' xmlns:bar='http://b.org'>\n" +" <elt1 bar:att=\"2\" foo:att='1'>\n" +" <elt2 xmlns:foo = 'http://c.org'>\n" +" <elt3 xmlns:bar = \"http://d.org\">\n" +" <elt4 bar:att2=\"rab\" foo:att2='oof'>octopous</elt4>\n" +" </elt3>\n" +" </elt2>\n" +" </elt1>\n" +"</elt>" +, +"<elt>\n" +" <elt1 xmlns:bar=\"http://b.org\" xmlns:foo=\"http://a.org\" foo:att=\"1\" bar:att=\"2\">\n" +" <elt2>\n" +" <elt3>\n" +" <elt4 xmlns:bar=\"http://d.org\" xmlns:foo=\"http://c.org\" foo:att2=\"oof\" bar:att2=\"rab\">octopous</elt4>\n" +" </elt3>\n" +" </elt2>\n" +" </elt1>\n" +"</elt>" +, +// Test namespaces3-xmlsec.xml +"<elt xmlns:foo = 'http://a.org' xmlns:bar='http://b.org' xmlns=\"\">\n" +" <elt1>\n" +" <elt2 xmlns:foo = 'http://c.org'>\n" +" <elt3 xmlns:bar = \"http://d.org\">\n" +" <elt4 bar:att2=\"rab\" foo:att2='oof'>octopous</elt4>\n" +" </elt3>\n" +" </elt2>\n" +" </elt1>\n" +"</elt>" +, +"<elt>\n" +" <elt1>\n" +" <elt2>\n" +" <elt3>\n" +" <elt4 xmlns:bar=\"http://d.org\" xmlns:foo=\"http://c.org\" foo:att2=\"oof\" bar:att2=\"rab\">octopous</elt4>\n" +" </elt3>\n" +" </elt2>\n" +" </elt1>\n" +"</elt>" +, +// Test namespaces4-xmlsec.xml +"<elt xmlns:foo = 'http://a.org' xmlns:bar='http://b.org'>\n" +" <elt1>\n" +" <elt2 xmlns:foo = 'http://c.org'>\n" +" <elt3 bar:att=\"2\" foo:att='1' xmlns:bar = \"http://d.org\">\n" +" <elt4 bar:att2=\"rab\" foo:att2='oof'>octopous</elt4>\n" +" </elt3>\n" +" </elt2>\n" +" </elt1>\n" +"</elt>" +, +"<elt>\n" +" <elt1>\n" +" <elt2>\n" +" <elt3 xmlns:bar=\"http://d.org\" xmlns:foo=\"http://c.org\" foo:att=\"1\" bar:att=\"2\">\n" +" <elt4 foo:att2=\"oof\" bar:att2=\"rab\">octopous</elt4>\n" +" </elt3>\n" +" </elt2>\n" +" </elt1>\n" +"</elt>" +, +// Test namespaces5-xmlsec.xml +"<elt xmlns:foo = 'http://a.org' xmlns:bar='http://b.org'>\n" +" <elt1>\n" +" <elt2>\n" +" <elt3 bar:att=\"2\" xmlns:bar = \"http://d.org\">\n" +" <elt4 xmlns:bar='http://rab.org'>octopous</elt4>\n" +" </elt3>\n" +" </elt2>\n" +" </elt1>\n" +"</elt>" +, +"<elt>\n" +" <elt1>\n" +" <elt2>\n" +" <elt3 xmlns:bar=\"http://d.org\" bar:att=\"2\">\n" +" <elt4>octopous</elt4>\n" +" </elt3>\n" +" </elt2>\n" +" </elt1>\n" +"</elt>" +, +// Test prefixe-xmlsec.xml +"<elt>\n" +" <elt1 xmlns:bar=\"http://d.com\" bar:att=\"2\">\n" +" <bar:elt2/>\n" +" </elt1>\n" +"</elt>" +, +"<elt>\n" +" <elt1 xmlns:bar=\"http://d.com\" bar:att=\"2\">\n" +" <bar:elt2></bar:elt2>\n" +" </elt1>\n" +"</elt>" +, +// Test same_namespaces-xmlsec.xml +"<foo:bar xmlns:foo=\"http://a.com\">\n" +" <bla:zoo xmlns:bla=\"http://a.com\"/>\n" +"</foo:bar>" +, +"<foo:bar xmlns:foo=\"http://a.com\">\n" +" <bla:zoo xmlns:bla=\"http://a.com\"></bla:zoo>\n" +"</foo:bar>" +, +// Test same_namespaces2-xmlsec.xml +"<foo:bar xmlns:foo=\"http://a.com\">\n" +" <bla:zoo xmlns:bla=\"http://a.com\">\n" +" <elt foo:att=\"att1\" bla:btt=\"att2\">youf</elt>\n" +" </bla:zoo>\n" +"</foo:bar>" +, +"<foo:bar xmlns:foo=\"http://a.com\">\n" +" <bla:zoo xmlns:bla=\"http://a.com\">\n" +" <elt foo:att=\"att1\" bla:btt=\"att2\">youf</elt>\n" +" </bla:zoo>\n" +"</foo:bar>" +, +// Test same_namespaces2b-xmlsec.xml +"<foo:bar xmlns:foo=\"http://b.com\">\n" +" <bla:zoo xmlns:bla=\"http://a.com\">\n" +" <elt foo:att=\"att1\" bla:att2=\"att2\">youf</elt>\n" +" </bla:zoo>\n" +"</foo:bar>" +, +"<foo:bar xmlns:foo=\"http://b.com\">\n" +" <bla:zoo xmlns:bla=\"http://a.com\">\n" +" <elt bla:att2=\"att2\" foo:att=\"att1\">youf</elt>\n" +" </bla:zoo>\n" +"</foo:bar>" +, +// Test same_namespaces2c-xmlsec.xml +"<foo:bar xmlns:foo=\"http://b.com\">\n" +" <bla:zoo xmlns:bla=\"http://a.com\">\n" +" <elt foo:att=\"att1\" bla:att=\"att2\">youf</elt>\n" +" </bla:zoo>\n" +"</foo:bar>" +, +"<foo:bar xmlns:foo=\"http://b.com\">\n" +" <bla:zoo xmlns:bla=\"http://a.com\">\n" +" <elt bla:att=\"att2\" foo:att=\"att1\">youf</elt>\n" +" </bla:zoo>\n" +"</foo:bar>" +, +// Test start_end_tags-xmlsec.xml +"<doc>\n" +" <e1 />\n" +" <e2 ></e2>\n" +" <e3 name = \"elem3\" id=\"elem3\" />\n" +" <e4 name=\"elem4\" id=\"elem4\" ></e4>\n" +" <e5 a:attr=\"out\" b:attr=\"sorted\" attr2=\"all\" attr=\"I'm\"\n" +" xmlns:b=\"http://www.ietf.org\"\n" +" xmlns:a=\"http://www.w3.org\"\n" +" xmlns=\"http://example.org\"/>\n" +" <e6 xmlns=\"\" xmlns:a=\"http://www.w3.org\">\n" +" <e7 xmlns=\"http://www.ietf.org\">\n" +" <e8 xmlns=\"\" xmlns:a=\"http://www.w3.org\">\n" +" <e9 xmlns=\"\" xmlns:a=\"http://www.ietf.org\"/>\n" +" </e8>\n" +" </e7>\n" +" </e6>\n" +"</doc>" +, +"<doc>\n" +" <e1></e1>\n" +" <e2></e2>\n" +" <e3 id=\"elem3\" name=\"elem3\"></e3>\n" +" <e4 id=\"elem4\" name=\"elem4\"></e4>\n" +" <e5 xmlns=\"http://example.org\" xmlns:a=\"http://www.w3.org\" xmlns:b=\"http://www.ietf.org\" attr=\"I'm\" attr2=\"all\" b:attr=\"sorted\" a:attr=\"out\"></e5>\n" +" <e6>\n" +" <e7 xmlns=\"http://www.ietf.org\">\n" +" <e8 xmlns=\"\">\n" +" <e9></e9>\n" +" </e8>\n" +" </e7>\n" +" </e6>\n" +"</doc>" +, +// Test utf8-xmlsec.xml +"<?xml version=\"1.0\" encoding=\"ISO-8859-1\"?>\n" +"<doc>©</doc>" +, +"<doc>\302\251</doc>" +, +// Test whitespaces-xmlsec.xml +"<doc>\n" +" <clean> </clean>\n" +" <dirty> A B </dirty>\n" +" <mixed>\n" +" A\n" +" <clean> </clean>\n" +" B\n" +" <dirty> A B </dirty>\n" +" C\n" +" </mixed>\n" +"</doc>" +, +"<doc>\n" +" <clean> </clean>\n" +" <dirty> A B </dirty>\n" +" <mixed>\n" +" A\n" +" <clean> </clean>\n" +" B\n" +" <dirty> A B </dirty>\n" +" C\n" +" </mixed>\n" +"</doc>", +// Test merlin-c14n-two-09.xml +"<?xml version=\"1.0\"?>\n" +"<foo:Root xmlns:bar=\"http://example.org/bar\" xmlns:baz=\"http://example.org/baz\" xmlns:foo=\"http://example.org/foo\" xmlns=\"http://example.org/\" xml:lang=\"en-ie\">\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something />\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +"<foo:Root xmlns:foo=\"http://example.org/foo\" xml:lang=\"en-ie\">\n" +" <bar:Something xmlns:bar=\"http://example.org/bar\">\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something xmlns:baz=\"http://example.org/baz\"></baz:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +// Test merlin-c14n-two-10.xml +"<?xml version=\"1.0\"?>\n" +"<foo:Root xmlns:bar=\"http://example.org/bar\" xmlns:baz=\"http://example.org/baz\" xmlns:foo=\"http://example.org/foo\" xmlns=\"http://example.org/\" xml:lang=\"en-ie\">\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something />\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +"<foo:Root xmlns:foo=\"http://example.org/foo\" xml:lang=\"en-ie\">\n" +" <bar:Something xmlns:bar=\"http://example.org/bar\">\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something xmlns:baz=\"http://example.org/baz\"></baz:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +// Test merlin-c14n-two-11.xml +"<?xml version=\"1.0\"?>\n" +"<foo:Root xmlns:bar=\"http://example.org/bar\" xmlns:baz=\"http://example.org/baz\" xmlns:foo=\"http://example.org/foo\" xmlns=\"http://example.org/\" xml:lang=\"en-ie\">\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something />\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +"<foo:Root xmlns:foo=\"http://example.org/foo\" xml:lang=\"en-ie\">\n" +" <bar:Something xmlns:bar=\"http://example.org/bar\">\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something xmlns:baz=\"http://example.org/baz\"></baz:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +// Test merlin-c14n-two-12.xml +"<?xml version=\"1.0\"?>\n" +"<foo:Root xmlns:bar=\"http://example.org/bar\" xmlns:baz=\"http://example.org/baz\" xmlns:foo=\"http://example.org/foo\" xmlns=\"http://example.org/\" xml:lang=\"en-ie\">\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something />\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +"<foo:Root xmlns:foo=\"http://example.org/foo\" xml:lang=\"en-ie\">\n" +" <bar:Something xmlns:bar=\"http://example.org/bar\">\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something xmlns:baz=\"http://example.org/baz\"></baz:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +// Test merlin-c14n-two-13.xml +"<?xml version=\"1.0\"?>\n" +"<foo:Root xmlns:bar=\"http://example.org/bar\" xmlns:baz=\"http://example.org/baz\" xmlns:foo=\"http://example.org/foo\" xmlns=\"http://example.org/\" xml:lang=\"en-ie\">\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something />\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +"<foo:Root xmlns:foo=\"http://example.org/foo\" xml:lang=\"en-ie\">\n" +" <bar:Something xmlns:bar=\"http://example.org/bar\">\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something xmlns:baz=\"http://example.org/baz\"></baz:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +// Test merlin-c14n-two-14.xml +"<?xml version=\"1.0\"?>\n" +"<foo:Root xmlns:bar=\"http://example.org/bar\" xmlns:baz=\"http://example.org/baz\" xmlns:foo=\"http://example.org/foo\" xmlns=\"http://example.org/\" xml:lang=\"en-ie\">\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something />\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +"<foo:Root xmlns:foo=\"http://example.org/foo\" xml:lang=\"en-ie\">\n" +" <bar:Something xmlns:bar=\"http://example.org/bar\">\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something xmlns:baz=\"http://example.org/baz\"></baz:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +// Test merlin-c14n-two-15.xml +"<?xml version=\"1.0\"?>\n" +"<foo:Root xmlns:bar=\"http://example.org/bar\" xmlns:baz=\"http://example.org/baz\" xmlns:foo=\"http://example.org/foo\" xmlns=\"http://example.org/\" xml:lang=\"en-ie\">\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something />\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +"<foo:Root xmlns:foo=\"http://example.org/foo\" xml:lang=\"en-ie\">\n" +" <bar:Something xmlns:bar=\"http://example.org/bar\">\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something xmlns:baz=\"http://example.org/baz\"></baz:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +// Test merlin-c14n-two-16.xml +"<?xml version=\"1.0\"?>\n" +"<foo:Root xmlns:bar=\"http://example.org/bar\" xmlns:baz=\"http://example.org/baz\" xmlns:foo=\"http://example.org/foo\" xmlns=\"http://example.org/\" xml:lang=\"en-ie\">\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something />\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +"<foo:Root xmlns:foo=\"http://example.org/foo\" xml:lang=\"en-ie\">\n" +" <bar:Something xmlns:bar=\"http://example.org/bar\">\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something xmlns:baz=\"http://example.org/baz\"></baz:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +// Test merlin-c14n-two-17.xml +"<?xml version=\"1.0\"?>\n" +"<foo:Root xmlns:bar=\"http://example.org/bar\" xmlns:baz=\"http://example.org/baz\" xmlns:foo=\"http://example.org/foo\" xmlns=\"http://example.org/\" xml:lang=\"en-ie\">\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something />\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +"<foo:Root xmlns:foo=\"http://example.org/foo\" xml:lang=\"en-ie\">\n" +" <bar:Something xmlns:bar=\"http://example.org/bar\">\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something xmlns:baz=\"http://example.org/baz\"></baz:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +// Test merlin-c14n-two-18.xml +"<?xml version=\"1.0\"?>\n" +"<foo:Root xmlns:bar=\"http://example.org/bar\" xmlns:baz=\"http://example.org/baz\" xmlns:foo=\"http://example.org/foo\" xmlns=\"http://example.org/\" xml:lang=\"en-ie\">\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something />\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +"<foo:Root xmlns:foo=\"http://example.org/foo\" xml:lang=\"en-ie\">\n" +" <bar:Something xmlns:bar=\"http://example.org/bar\">\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something xmlns:baz=\"http://example.org/baz\"></baz:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +// Test merlin-c14n-two-19.xml +"<?xml version=\"1.0\"?>\n" +"<foo:Root xmlns:bar=\"http://example.org/bar\" xmlns:baz=\"http://example.org/baz\" xmlns:foo=\"http://example.org/foo\" xmlns=\"http://example.org/\" xml:lang=\"en-ie\">\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something />\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +"<foo:Root xmlns:foo=\"http://example.org/foo\" xml:lang=\"en-ie\">\n" +" <bar:Something xmlns:bar=\"http://example.org/bar\">\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something xmlns:baz=\"http://example.org/baz\"></baz:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +// Test merlin-c14n-two-20.xml +"<?xml version=\"1.0\"?>\n" +"<foo:Root xmlns:bar=\"http://example.org/bar\" xmlns:baz=\"http://example.org/baz\" xmlns:foo=\"http://example.org/foo\" xmlns=\"http://example.org/\" xml:lang=\"en-ie\">\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something />\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +"<foo:Root xmlns:foo=\"http://example.org/foo\" xml:lang=\"en-ie\">\n" +" <bar:Something xmlns:bar=\"http://example.org/bar\">\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something xmlns:baz=\"http://example.org/baz\"></baz:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +// Test merlin-c14n-two-21.xml +"<?xml version=\"1.0\"?>\n" +"<foo:Root xmlns:bar=\"http://example.org/bar\" xmlns:baz=\"http://example.org/baz\" xmlns:foo=\"http://example.org/foo\" xmlns=\"http://example.org/\" xml:lang=\"en-ie\">\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something />\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +"<foo:Root xmlns:foo=\"http://example.org/foo\" xml:lang=\"en-ie\">\n" +" <bar:Something xmlns:bar=\"http://example.org/bar\">\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something xmlns:baz=\"http://example.org/baz\"></baz:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +// Test merlin-c14n-two-22.xml +"<?xml version=\"1.0\"?>\n" +"<foo:Root xmlns:bar=\"http://example.org/bar\" xmlns:baz=\"http://example.org/baz\" xmlns:foo=\"http://example.org/foo\" xmlns=\"http://example.org/\" xml:lang=\"en-ie\">\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something />\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +"<foo:Root xmlns:foo=\"http://example.org/foo\" xml:lang=\"en-ie\">\n" +" <bar:Something xmlns:bar=\"http://example.org/bar\">\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something xmlns:baz=\"http://example.org/baz\"></baz:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +// Test merlin-c14n-two-23.xml +"<?xml version=\"1.0\"?>\n" +"<foo:Root xmlns:bar=\"http://example.org/bar\" xmlns:baz=\"http://example.org/baz\" xmlns:foo=\"http://example.org/foo\" xmlns=\"http://example.org/\" xml:lang=\"en-ie\">\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something />\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +"<foo:Root xmlns:foo=\"http://example.org/foo\" xml:lang=\"en-ie\">\n" +" <bar:Something xmlns:bar=\"http://example.org/bar\">\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something xmlns:baz=\"http://example.org/baz\"></baz:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +// Test merlin-c14n-two-24.xml +"<?xml version=\"1.0\"?>\n" +"<foo:Root xmlns:bar=\"http://example.org/bar\" xmlns:baz=\"http://example.org/baz\" xmlns:foo=\"http://example.org/foo\" xmlns=\"http://example.org/\" xml:lang=\"en-ie\">\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something />\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +"<foo:Root xmlns:foo=\"http://example.org/foo\" xml:lang=\"en-ie\">\n" +" <bar:Something xmlns:bar=\"http://example.org/bar\">\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something xmlns:baz=\"http://example.org/baz\"></baz:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +// Test merlin-c14n-two-25.xml +"<?xml version=\"1.0\"?>\n" +"<foo:Root xmlns:bar=\"http://example.org/bar\" xmlns:baz=\"http://example.org/baz\" xmlns:foo=\"http://example.org/foo\" xmlns=\"http://example.org/\" xml:lang=\"en-ie\">\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something />\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +"<foo:Root xmlns:foo=\"http://example.org/foo\" xml:lang=\"en-ie\">\n" +" <bar:Something xmlns:bar=\"http://example.org/bar\">\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something xmlns:baz=\"http://example.org/baz\"></baz:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +// Test merlin-c14n-two-26.xml +"<?xml version=\"1.0\"?>\n" +"<foo:Root xmlns:bar=\"http://example.org/bar\" xmlns:baz=\"http://example.org/baz\" xmlns:foo=\"http://example.org/foo\" xmlns=\"http://example.org/\" xml:lang=\"en-ie\">\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something />\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>" +, +"<foo:Root xmlns:foo=\"http://example.org/foo\" xml:lang=\"en-ie\">\n" +" <bar:Something xmlns:bar=\"http://example.org/bar\">\n" +" <foo:Something>\n" +" <bar:Something>\n" +" <foo:Something>\n" +" <baz:Something xmlns:baz=\"http://example.org/baz\"></baz:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +" </foo:Something>\n" +" </bar:Something>\n" +"</foo:Root>", + +0 +}; diff --git a/lib/libUPnP/Neptune/Source/Tests/Xml1/big.xml b/lib/libUPnP/Neptune/Source/Tests/Xml1/big.xml new file mode 100644 index 0000000..ef590ac --- /dev/null +++ b/lib/libUPnP/Neptune/Source/Tests/Xml1/big.xml @@ -0,0 +1,3277 @@ +<?xml version="1.0" encoding="iso-8859-1"?> +<!DOCTYPE spec PUBLIC "-//W3C//DTD Specification V2.1//EN" + "http://www.w3.org/XML/1998/06/xmlspec-v21.dtd" [ +<!--ArborText, Inc., 1988-2000, v.4002--> +<!ENTITY http-ident "http://www.w3.org/TR/2000/REC-xml"> +<!ENTITY draft.month "October"> +<!ENTITY draft.day "6"> +<!ENTITY iso6.doc.date "20001006"> +<!ENTITY draft.year "2000"> +<!ENTITY versionOfXML "1.0"> +<!ENTITY pio "'<?xml'"> +<!ENTITY doc.date "10 February 1998"> +<!ENTITY w3c.doc.date "02-Feb-1998"> +<!ENTITY WebSGML "WebSGML Adaptations Annex to ISO 8879"> +<!ENTITY pic "'?>'"> +<!ENTITY br "\n"> +<!ENTITY cellback "#c0d9c0"> +<!ENTITY mdash "--"> +<!ENTITY com "--"> +<!ENTITY como "--"> +<!ENTITY comc "--"> +<!ENTITY hcro "&#x"> +<!ENTITY nbsp " "> +<!ENTITY magicents "<code>amp</code>, +<code>lt</code>, +<code>gt</code>, +<code>apos</code>, +<code>quot</code>"> +<!ENTITY doc.audience "public review and discussion"> +<!ENTITY doc.distribution "may be distributed freely, as long as +all text and legal notices remain intact"> +]> +<spec w3c-doctype="rec"> +<!-- +Notes on preparation of the Second Edition: + +- Worked from http://www.w3.org/XML/xml-19980210-errata. +- Changed DTD reference to point to V2.1 of XMLspec. +- Moved version number from <title> to <version> element and + added "second edition" wording. Mentioned edition information + in status. +- Removed bgcolor="&cellback;" attributes from all <td> + elements because that attribute is not in the current table model. +- Reversed status and abstract, so that abstract is first, according + to W3C guidelines. +- Changed some <emph>s to <titleref>s in bibliography. +- Changed some <code>s to <at> etc. throughout; where used <attval>, + removed existing <quote>s because the stylesheet produces them. +- Removed some spurious spaces. +- Added affiliation markup to the original member list. +- Added commas between individual <thisver> elements, because + whitespace is now significant there. +- Moved <eg>s, <scrap>s, and lists outside of <p>s for cleaner HTML + conversion. +- Revised Status section to reflect new status. +- Fixed all titleref hrefs so they get transformed properly; at + next revision, these all probably need to be changed to some + other markup. +- Incorporated all errata (barring obsoleted and invalid ones); + added links to the errata document with <loc role="erratumref"> + elements; used diff="{add|chg|del}" attribute. This version + expects that the official HTML output will have diff="del" + elements suppressed. +--> +<header> +<title>Extensible Markup Language (XML)</title> +<version>1.0 (Second Edition)</version> +<w3c-designation>REC-xml-&iso6.doc.date;</w3c-designation> +<w3c-doctype>W3C Recommendation</w3c-doctype> +<pubdate><day>&draft.day;</day><month>&draft.month;</month><year>&draft.year;</year> +</pubdate> +<publoc><loc href="&http-ident;-&iso6.doc.date;">&http-ident;-&iso6.doc.date;</loc> +(<loc href="&http-ident;-&iso6.doc.date;.html">XHTML</loc>, <loc href="&http-ident;-&iso6.doc.date;.xml">XML</loc>, <loc +href="&http-ident;-&iso6.doc.date;.pdf">PDF</loc>, <loc href="&http-ident;-&iso6.doc.date;-review.html">XHTML +review version</loc> with color-coded revision indicators)</publoc> +<latestloc><loc href="http://www.w3.org/TR/REC-xml">http://www.w3.org/TR/REC-xml</loc></latestloc> +<prevlocs><loc href="http://www.w3.org/TR/2000/WD-xml-2e-20000814"> http://www.w3.org/TR/2000/WD-xml-2e-20000814</loc> +<loc href="http://www.w3.org/TR/1998/REC-xml-19980210"> http://www.w3.org/TR/1998/REC-xml-19980210</loc><!-- +<loc href='http://www.w3.org/TR/PR-xml-971208'> +http://www.w3.org/TR/PR-xml-971208</loc> +<loc href='http://www.w3.org/TR/WD-xml-961114'> +http://www.w3.org/TR/WD-xml-961114</loc> +<loc href='http://www.w3.org/TR/WD-xml-lang-970331'> +http://www.w3.org/TR/WD-xml-lang-970331</loc> +<loc href='http://www.w3.org/TR/WD-xml-lang-970630'> +http://www.w3.org/TR/WD-xml-lang-970630</loc> +<loc href='http://www.w3.org/TR/WD-xml-970807'> +http://www.w3.org/TR/WD-xml-970807</loc> +<loc href='http://www.w3.org/TR/WD-xml-971117'> +http://www.w3.org/TR/WD-xml-971117</loc>--> </prevlocs> +<authlist> +<author role="1e"><name>Tim Bray</name><affiliation>Textuality and Netscape</affiliation> +<email href="mailto:tbray@textuality.com">tbray@textuality.com</email></author> +<author role="1e"><name>Jean Paoli</name><affiliation>Microsoft</affiliation> +<email href="mailto:jeanpa@microsoft.com">jeanpa@microsoft.com</email></author> +<author role="1e" diff="chg"><name>C. M. Sperberg-McQueen</name><affiliation>University +of Illinois at Chicago and Text Encoding Initiative</affiliation><email href="mailto:cmsmcq@uic.edu">cmsmcq@uic.edu</email> +</author> +<author role="2e" diff="add"><name>Eve Maler</name><affiliation>Sun Microsystems, +Inc.</affiliation><email href="mailto:elm@east.sun.com">eve.maler@east.sun.com</email> +</author> +</authlist> +<abstract> +<p>The Extensible Markup Language (XML) is a subset of SGML that is completely +described in this document. Its goal is to enable generic SGML to be served, +received, and processed on the Web in the way that is now possible with HTML. +XML has been designed for ease of implementation and for interoperability +with both SGML and HTML.</p> +</abstract> +<status> +<p>This document has been reviewed by W3C Members and other interested parties +and has been endorsed by the Director as a W3C Recommendation. It is a stable +document and may be used as reference material or cited as a normative reference +from another document. W3C's role in making the Recommendation is to draw +attention to the specification and to promote its widespread deployment. This +enhances the functionality and interoperability of the Web.</p> +<p>This document specifies a syntax created by subsetting an existing, widely +used international text processing standard (Standard Generalized Markup Language, +ISO 8879:1986(E) as amended and corrected) for use on the World Wide Web. +It is a product of the W3C XML Activity, details of which can be found at <loc +href="http://www.w3.org/XML/">http://www.w3.org/XML</loc>. <phrase diff="add"><loc +role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E100">[E100]</loc> +The English version of this specification is the only normative version. However, +for translations of this document, see <loc href="http://www.w3.org/XML/#trans">http://www.w3.org/XML/#trans</loc>. </phrase>A +list of current W3C Recommendations and other technical documents can be found +at <loc href="http://www.w3.org/TR/">http://www.w3.org/TR</loc>.</p> +<p diff="del"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E66">[E66]</loc>This +specification uses the term URI, which is defined by <bibref ref="Berners-Lee"/>, +a work in progress expected to update <bibref ref="RFC1738"/> and <bibref +ref="RFC1808"/>.</p> +<p diff="add">This second edition is <emph>not</emph> a new version of XML (first published 10 February 1998); +it merely incorporates the changes dictated by the first-edition errata (available +at <loc href="http://www.w3.org/XML/xml-19980210-errata">http://www.w3.org/XML/xml-19980210-errata</loc>) +as a convenience to readers. The errata list for this second edition is available +at <loc href="http://www.w3.org/XML/xml-V10-2e-errata">http://www.w3.org/XML/xml-V10-2e-errata</loc>.</p> +<p>Please report errors in this document to <loc href="mailto:xml-editor@w3.org">xml-editor@w3.org</loc><phrase +diff="add"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E101">[E101]</loc>; <loc +href="http://lists.w3.org/Archives/Public/xml-editor">archives</loc> are available</phrase>.</p> +<note diff="add"> +<p>C. M. Sperberg-McQueen's affiliation has changed since the publication +of the first edition. He is now at the World Wide Web Consortium, and can +be contacted at <loc href="mailto:cmsmcq@w3.org">cmsmcq@w3.org</loc>.</p> +</note> +</status> +<pubstmt> +<p>Chicago, Vancouver, Mountain View, et al.: World-Wide Web Consortium, XML +Working Group, 1996, 1997, 2000.</p> +</pubstmt> +<sourcedesc> +<p>Created in electronic form.</p> +</sourcedesc> +<langusage> +<language id="EN">English</language> +<language id="ebnf">Extended Backus-Naur Form (formal grammar)</language> +</langusage> +<revisiondesc> +<slist> +<sitem>1997-12-03 : CMSMcQ : yet further changes</sitem> +<sitem>1997-12-02 : TB : further changes (see TB to XML WG, 2 December 1997)</sitem> +<sitem>1997-12-02 : CMSMcQ : deal with as many corrections and comments from +the proofreaders as possible: entify hard-coded document date in pubdate element, +change expansion of entity WebSGML, update status description as per Dan Connolly +(am not sure about refernece to Berners-Lee et al.), add 'The' to abstract +as per WG decision, move Relationship to Existing Standards to back matter +and combine with References, re-order back matter so normative appendices +come first, re-tag back matter so informative appendices are tagged informdiv1, +remove XXX XXX from list of 'normative' specs in prose, move some references +from Other References to Normative References, add RFC 1738, 1808, and 2141 +to Other References (they are not normative since we do not require the processor +to enforce any rules based on them), add reference to 'Fielding draft' (Berners-Lee +et al.), move notation section to end of body, drop URIchar non-terminal and +use SkipLit instead, lose stray reference to defunct nonterminal 'markupdecls', +move reference to Aho et al. into appendix (Tim's right), add prose note saying +that hash marks and fragment identifiers are NOT part of the URI formally +speaking, and are NOT legal in system identifiers (processor 'may' signal +an error). Work through: Tim Bray reacting to James Clark, Tim Bray on his +own, Eve Maler, NOT DONE YET: change binary / text to unparsed / parsed. handle +James's suggestion about < in attriubte values uppercase hex characters, +namechar list, </sitem> +<sitem>1997-12-01 : JB : add some column-width parameters</sitem> +<sitem>1997-12-01 : CMSMcQ : begin round of changes to incorporate recent +WG decisions and other corrections: binding sources of character encoding +info (27 Aug / 3 Sept), correct wording of Faust quotation (restore dropped +line), drop SDD from EncodingDecl, change text at version number 1.0, drop +misleading (wrong!) sentence about ignorables and extenders, modify definition +of PCData to make bar on msc grammatical, change grammar's handling of internal +subset (drop non-terminal markupdecls), change definition of includeSect to +allow conditional sections, add integral-declaration constraint on internal +subset, drop misleading / dangerous sentence about relationship of entities +with system storage objects, change table body tag to htbody as per EM change +to DTD, add rule about space normalization in public identifiers, add description +of how to generate our name-space rules from Unicode character database (needs +further work!). </sitem> +<sitem>1997-10-08 : TB : Removed %-constructs again, new rules for PE appearance.</sitem> +<sitem>1997-10-01 : TB : Case-sensitive markup; cleaned up element-type defs, +lotsa little edits for style</sitem> +<sitem>1997-09-25 : TB : Change to elm's new DTD, with substantial detail +cleanup as a side-effect</sitem> +<sitem>1997-07-24 : CMSMcQ : correct error (lost *) in definition of ignoreSectContents +(thanks to Makoto Murata)</sitem> +<sitem>Allow all empty elements to have end-tags, consistent with SGML TC +(as per JJC).</sitem> +<sitem>1997-07-23 : CMSMcQ : pre-emptive strike on pending corrections: introduce +the term 'empty-element tag', note that all empty elements may use it, and +elements declared EMPTY must use it. Add WFC requiring encoding decl to come +first in an entity. Redefine notations to point to PIs as well as binary entities. +Change autodetection table by removing bytes 3 and 4 from examples with Byte +Order Mark. Add content model as a term and clarify that it applies to both +mixed and element content. </sitem> +<sitem>1997-06-30 : CMSMcQ : change date, some cosmetic changes, changes to +productions for choice, seq, Mixed, NotationType, Enumeration. Follow James +Clark's suggestion and prohibit conditional sections in internal subset. TO +DO: simplify production for ignored sections as a result, since we don't need +to worry about parsers which don't expand PErefs finding a conditional section.</sitem> +<sitem>1997-06-29 : TB : various edits</sitem> +<sitem>1997-06-29 : CMSMcQ : further changes: Suppress old FINAL EDIT comments +and some dead material. Revise occurrences of % in grammar to exploit Henry +Thompson's pun, especially markupdecl and attdef. Remove RMD requirement relating +to element content (?). </sitem> +<sitem>1997-06-28 : CMSMcQ : Various changes for 1 July draft: Add text for +draconian error handling (introduce the term Fatal Error). RE deleta est (changing +wording from original announcement to restrict the requirement to validating +parsers). Tag definition of validating processor and link to it. Add colon +as name character. Change def of %operator. Change standard definitions of +lt, gt, amp. Strip leading zeros from #x00nn forms.</sitem> +<sitem>1997-04-02 : CMSMcQ : final corrections of editorial errors found in +last night's proofreading. Reverse course once more on well-formed: Webster's +Second hyphenates it, and that's enough for me.</sitem> +<sitem>1997-04-01 : CMSMcQ : corrections from JJC, EM, HT, and self</sitem> +<sitem>1997-03-31 : Tim Bray : many changes</sitem> +<sitem>1997-03-29 : CMSMcQ : some Henry Thompson (on entity handling), some +Charles Goldfarb, some ERB decisions (PE handling in miscellaneous declarations. +Changed Ident element to accept def attribute. Allow normalization of Unicode +characters. move def of systemliteral into section on literals.</sitem> +<sitem>1997-03-28 : CMSMcQ : make as many corrections as possible, from Terry +Allen, Norbert Mikula, James Clark, Jon Bosak, Henry Thompson, Paul Grosso, +and self. Among other things: give in on "well formed" (Terry is right), tentatively +rename QuotedCData as AttValue and Literal as EntityValue to be more informative, +since attribute values are the <emph>only</emph> place QuotedCData was used, +and vice versa for entity text and Literal. (I'd call it Entity Text, but +8879 uses that name for both internal and external entities.)</sitem> +<sitem>1997-03-26 : CMSMcQ : resynch the two forks of this draft, reapply +my changes dated 03-20 and 03-21. Normalize old 'may not' to 'must not' except +in the one case where it meant 'may or may not'.</sitem> +<sitem>1997-03-21 : TB : massive changes on plane flight from Chicago to Vancouver</sitem> +<sitem>1997-03-21 : CMSMcQ : correct as many reported errors as possible. </sitem> +<sitem>1997-03-20 : CMSMcQ : correct typos listed in CMSMcQ hand copy of spec.</sitem> +<sitem>1997-03-20 : CMSMcQ : cosmetic changes preparatory to revision for +WWW conference April 1997: restore some of the internal entity references +(e.g. to docdate, etc.), change character xA0 to &nbsp; and define nbsp +as &#160;, and refill a lot of paragraphs for legibility.</sitem> +<sitem>1996-11-12 : CMSMcQ : revise using Tim's edits: Add list type of NUMBERED +and change most lists either to BULLETS or to NUMBERED. Suppress QuotedNames, +Names (not used). Correct trivial-grammar doc type decl. Rename 'marked section' +as 'CDATA section' passim. Also edits from James Clark: Define the set of +characters from which [^abc] subtracts. Charref should use just [0-9] not +Digit. Location info needs cleaner treatment: remove? (ERB question). One +example of a PI has wrong pic. Clarify discussion of encoding names. Encoding +failure should lead to unspecified results; don't prescribe error recovery. +Don't require exposure of entity boundaries. Ignore white space in element +content. Reserve entity names of the form u-NNNN. Clarify relative URLs. And +some of my own: Correct productions for content model: model cannot consist +of a name, so "elements ::= cp" is no good. </sitem> +<sitem>1996-11-11 : CMSMcQ : revise for style. Add new rhs to entity declaration, +for parameter entities.</sitem> +<sitem>1996-11-10 : CMSMcQ : revise for style. Fix / complete section on names, +characters. Add sections on parameter entities, conditional sections. Still +to do: Add compatibility note on deterministic content models. Finish stylistic +revision.</sitem> +<sitem>1996-10-31 : TB : Add Entity Handling section</sitem> +<sitem>1996-10-30 : TB : Clean up term & termdef. Slip in ERB decision +re EMPTY.</sitem> +<sitem>1996-10-28 : TB : Change DTD. Implement some of Michael's suggestions. +Change comments back to //. Introduce language for XML namespace reservation. +Add section on white-space handling. Lots more cleanup.</sitem> +<sitem>1996-10-24 : CMSMcQ : quick tweaks, implement some ERB decisions. Characters +are not integers. Comments are /* */ not //. Add bibliographic refs to 10646, +HyTime, Unicode. Rename old Cdata as MsData since it's <emph>only</emph> seen +in marked sections. Call them attribute-value pairs not name-value pairs, +except once. Internal subset is optional, needs '?'. Implied attributes should +be signaled to the app, not have values supplied by processor.</sitem> +<sitem>1996-10-16 : TB : track down & excise all DSD references; introduce +some EBNF for entity declarations.</sitem> +<sitem>1996-10-?? : TB : consistency check, fix up scraps so they all parse, +get formatter working, correct a few productions.</sitem> +<sitem>1996-10-10/11 : CMSMcQ : various maintenance, stylistic, and organizational +changes: Replace a few literals with xmlpio and pic entities, to make them +consistent and ensure we can change pic reliably when the ERB votes. Drop +paragraph on recognizers from notation section. Add match, exact match to +terminology. Move old 2.2 XML Processors and Apps into intro. Mention comments, +PIs, and marked sections in discussion of delimiter escaping. Streamline discussion +of doctype decl syntax. Drop old section of 'PI syntax' for doctype decl, +and add section on partial-DTD summary PIs to end of Logical Structures section. +Revise DSD syntax section to use Tim's subset-in-a-PI mechanism.</sitem> +<sitem>1996-10-10 : TB : eliminate name recognizers (and more?)</sitem> +<sitem>1996-10-09 : CMSMcQ : revise for style, consistency through 2.3 (Characters)</sitem> +<sitem>1996-10-09 : CMSMcQ : re-unite everything for convenience, at least +temporarily, and revise quickly</sitem> +<sitem>1996-10-08 : TB : first major homogenization pass</sitem> +<sitem>1996-10-08 : TB : turn "current" attribute on div type into CDATA</sitem> +<sitem>1996-10-02 : TB : remould into skeleton + entities</sitem> +<sitem>1996-09-30 : CMSMcQ : add a few more sections prior to exchange with +Tim.</sitem> +<sitem>1996-09-20 : CMSMcQ : finish transcribing notes.</sitem> +<sitem>1996-09-19 : CMSMcQ : begin transcribing notes for draft.</sitem> +<sitem>1996-09-13 : CMSMcQ : made outline from notes of 09-06, do some housekeeping</sitem> +</slist> +</revisiondesc> +</header> +<body> +<div1 id="sec-intro"> +<head>Introduction</head> +<p>Extensible Markup Language, abbreviated XML, describes a class of data +objects called <termref def="dt-xml-doc">XML documents</termref> and partially +describes the behavior of computer programs which process them. XML is an +application profile or restricted form of SGML, the Standard Generalized Markup +Language <bibref ref="ISO8879"/>. By construction, XML documents are conforming +SGML documents.</p> +<p>XML documents are made up of storage units called <termref def="dt-entity">entities</termref>, +which contain either parsed or unparsed data. Parsed data is made up of <termref +def="dt-character">characters</termref>, some of which form <termref def="dt-chardata">character +data</termref>, and some of which form <termref def="dt-markup">markup</termref>. +Markup encodes a description of the document's storage layout and logical +structure. XML provides a mechanism to impose constraints on the storage layout +and logical structure.</p> +<p><termdef id="dt-xml-proc" term="XML Processor">A software module called +an <term>XML processor</term> is used to read XML documents and provide access +to their content and structure.</termdef> <termdef id="dt-app" term="Application">It +is assumed that an XML processor is doing its work on behalf of another module, +called the <term>application</term>.</termdef> This specification describes +the required behavior of an XML processor in terms of how it must read XML +data and the information it must provide to the application.</p> +<div2 id="sec-origin-goals"> +<head>Origin and Goals</head> +<p>XML was developed by an XML Working Group (originally known as the SGML +Editorial Review Board) formed under the auspices of the World Wide Web Consortium +(W3C) in 1996. It was chaired by Jon Bosak of Sun Microsystems with the active +participation of an XML Special Interest Group (previously known as the SGML +Working Group) also organized by the W3C. The membership of the XML Working +Group is given in an appendix. Dan Connolly served as the WG's contact with +the W3C.</p> +<p>The design goals for XML are:</p> +<olist> +<item><p>XML shall be straightforwardly usable over the Internet.</p></item> +<item><p>XML shall support a wide variety of applications.</p></item> +<item><p>XML shall be compatible with SGML.</p></item> +<item><p>It shall be easy to write programs which process XML documents.</p> +</item> +<item><p>The number of optional features in XML is to be kept to the absolute +minimum, ideally zero.</p></item> +<item><p>XML documents should be human-legible and reasonably clear.</p></item> +<item><p>The XML design should be prepared quickly.</p></item> +<item><p>The design of XML shall be formal and concise.</p></item> +<item><p>XML documents shall be easy to create.</p></item> +<item><p>Terseness in XML markup is of minimal importance.</p></item> +</olist> +<p>This specification, together with associated standards (Unicode and ISO/IEC +10646 for characters, Internet RFC 1766 for language identification tags, +ISO 639 for language name codes, and ISO 3166 for country name codes), provides +all the information necessary to understand XML Version &versionOfXML; and +construct computer programs to process it.</p> +<p>This version of the XML specification <!-- is for &doc.audience;.--> &doc.distribution;.</p> +</div2> +<div2 id="sec-terminology"> +<head>Terminology</head> +<p>The terminology used to describe XML documents is defined in the body of +this specification. The terms defined in the following list are used in building +those definitions and in describing the actions of an XML processor: <glist> +<gitem><label>may</label> +<def> +<p><termdef id="dt-may" term="May">Conforming documents and XML processors +are permitted to but need not behave as described.</termdef></p> +</def></gitem> +<gitem><label>must</label> +<def> +<p><termdef id="dt-must" term="Must">Conforming documents and XML processors +are required to behave as described; otherwise they are in error. <!-- do NOT change this! this is what defines a violation of +a 'must' clause as 'an error'. -MSM --></termdef></p> +</def></gitem> +<gitem><label>error</label> +<def> +<p><termdef id="dt-error" term="Error">A violation of the rules of this specification; +results are undefined. Conforming software may detect and report an error +and may recover from it.</termdef></p> +</def></gitem> +<gitem><label>fatal error</label> +<def> +<p><termdef id="dt-fatal" term="Fatal Error">An error which a conforming <termref +def="dt-xml-proc">XML processor</termref> must detect and report to the application. +After encountering a fatal error, the processor may continue processing the +data to search for further errors and may report such errors to the application. +In order to support correction of errors, the processor may make unprocessed +data from the document (with intermingled character data and markup) available +to the application. Once a fatal error is detected, however, the processor +must not continue normal processing (i.e., it must not continue to pass character +data and information about the document's logical structure to the application +in the normal way).</termdef></p> +</def></gitem> +<gitem><label>at user option</label> +<def> +<p><termdef id="dt-atuseroption" term="At user option">Conforming software +may or must (depending on the modal verb in the sentence) behave as described; +if it does, it must provide users a means to enable or disable the behavior +described.</termdef></p> +</def></gitem> +<gitem><label>validity constraint</label> +<def> +<p><termdef id="dt-vc" term="Validity constraint">A rule which applies to +all <termref def="dt-valid">valid</termref> XML documents. Violations of validity +constraints are errors; they must, at user option, be reported by <termref +def="dt-validating">validating XML processors</termref>.</termdef></p> +</def></gitem> +<gitem><label>well-formedness constraint</label> +<def> +<p><termdef id="dt-wfc" term="Well-formedness constraint">A rule which applies +to all <termref def="dt-wellformed">well-formed</termref> XML documents. Violations +of well-formedness constraints are <termref def="dt-fatal">fatal errors</termref>.</termdef></p> +</def></gitem> +<gitem><label>match</label> +<def> +<p><termdef id="dt-match" term="match">(Of strings or names:) Two strings +or names being compared must be identical. Characters with multiple possible +representations in ISO/IEC 10646 (e.g. characters with both precomposed and +base+diacritic forms) match only if they have the same representation in both +strings. <phrase diff="del"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E85">[E85]</loc>At +user option, processors may normalize such characters to some canonical form. </phrase>No +case folding is performed. (Of strings and rules in the grammar:) A string +matches a grammatical production if it belongs to the language generated by +that production. (Of content and content models:) An element matches its declaration +when it conforms in the fashion described in the constraint <specref ref="elementvalid"/>.</termdef></p> +</def></gitem> +<gitem><label>for compatibility</label> +<def> +<p><termdef id="dt-compat" term="For Compatibility"><phrase diff="add"><loc +role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E87">[E87]</loc>Marks +a sentence describing</phrase> a feature of XML included solely to ensure +that XML remains compatible with SGML.</termdef></p> +</def></gitem> +<gitem><label>for interoperability</label> +<def> +<p><termdef id="dt-interop" term="For interoperability"><phrase diff="add"><loc +role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E87">[E87]</loc>Marks +a sentence describing</phrase> a non-binding recommendation included to increase +the chances that XML documents can be processed by the existing installed +base of SGML processors which predate the &WebSGML;.</termdef></p> +</def></gitem> +</glist></p> +</div2> +</div1> +<!-- &Docs; --> +<div1 id="sec-documents"> +<head>Documents</head> +<p><termdef id="dt-xml-doc" term="XML Document"> A data object is an <term>XML +document</term> if it is <termref def="dt-wellformed">well-formed</termref>, +as defined in this specification. A well-formed XML document may in addition +be <termref def="dt-valid">valid</termref> if it meets certain further constraints.</termdef></p> +<p>Each XML document has both a logical and a physical structure. Physically, +the document is composed of units called <termref def="dt-entity">entities</termref>. +An entity may <termref def="dt-entref">refer</termref> to other entities to +cause their inclusion in the document. A document begins in a <quote>root</quote> +or <termref def="dt-docent">document entity</termref>. Logically, the document +is composed of declarations, elements, comments, character references, and +processing instructions, all of which are indicated in the document by explicit +markup. The logical and physical structures must nest properly, as described +in <specref ref="wf-entities"/>.</p> +<div2 id="sec-well-formed"> +<head>Well-Formed XML Documents</head> +<p><termdef id="dt-wellformed" term="Well-Formed"> A textual object is a <term>well-formed</term> +XML document if:</termdef></p> +<olist> +<item><p>Taken as a whole, it matches the production labeled <nt def="NT-document">document</nt>.</p> +</item> +<item><p>It meets all the well-formedness constraints given in this specification.</p> +</item> +<item><p>Each of the <termref def="dt-parsedent">parsed entities</termref> +which is referenced directly or indirectly within the document is <termref +def="dt-wellformed">well-formed</termref>.</p></item> +</olist> +<scrap id="document" lang="ebnf"> +<head>Document</head> +<prod id="NT-document"> +<lhs>document</lhs><rhs><nt def="NT-prolog">prolog</nt> <nt def="NT-element">element</nt> <nt +def="NT-Misc">Misc</nt>*</rhs> +</prod> +</scrap> +<p>Matching the <nt def="NT-document">document</nt> production implies that:</p> +<olist> +<item><p>It contains one or more <termref def="dt-element">elements</termref>.</p> +</item> +<!--* N.B. some readers (notably JC) find the following +paragraph awkward and redundant. I agree it's logically redundant: +it *says* it is summarizing the logical implications of +matching the grammar, and that means by definition it's +logically redundant. I don't think it's rhetorically +redundant or unnecessary, though, so I'm keeping it. It +could however use some recasting when the editors are feeling +stronger. -MSM *--> +<item><p><termdef id="dt-root" term="Root Element">There is exactly one element, +called the <term>root</term>, or document element, no part of which appears +in the <termref def="dt-content">content</termref> of any other element.</termdef> <phrase +diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E17">[E17]</loc>For +all other elements, if the <termref def="dt-stag">start-tag</termref> is in +the content of another element, the <termref def="dt-etag">end-tag</termref> +is in the content of the same element.</phrase> More simply stated, the elements, +delimited by start- and end-tags, nest properly within each other.</p></item> +</olist> +<p><termdef id="dt-parentchild" term="Parent/Child">As a consequence of this, +for each non-root element <el>C</el> in the document, there is one other element <el>P</el> +in the document such that <el>C</el> is in the content of <el>P</el>, but +is not in the content of any other element that is in the content of <el>P</el>. <el>P</el> +is referred to as the <term>parent</term> of <el>C</el>, and <el>C</el> as +a <term>child</term> of <el>P</el>.</termdef></p> +</div2> +<div2 id="charsets"> +<head>Characters</head> +<p><termdef id="dt-text" term="Text">A parsed entity contains <term>text</term>, +a sequence of <termref def="dt-character">characters</termref>, which may +represent markup or character data.</termdef> <termdef id="dt-character" term="Character">A <term>character</term> +is an atomic unit of text as specified by ISO/IEC 10646 <bibref ref="ISO10646"/> <phrase +diff="add"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E67">[E67]</loc>(see +also <bibref ref="ISO10646-2000"/>)</phrase>. Legal characters are tab, carriage +return, line feed, and the legal <phrase diff="del"><loc role="erratumref" +href="http://www.w3.org/XML/xml-19980210-errata#E35">[E35]</loc>graphic </phrase>characters +of Unicode and ISO/IEC 10646. <phrase diff="add"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E69">[E69]</loc>The +versions of these standards cited in <specref ref="sec-existing-stds"/> were +current at the time this document was prepared. New characters may be added +to these standards by amendments or new editions. Consequently, XML processors +must accept any character in the range specified for <nt def="NT-Char">Char</nt>.</phrase> +The use of <quote>compatibility characters</quote>, as defined in section +6.8 of <bibref ref="Unicode"/> <phrase diff="add"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E67">[E67]</loc>(see +also D21 in section 3.6 of <bibref ref="Unicode3"/>)</phrase>, is discouraged.</termdef></p> +<scrap id="char32" lang="ebnf"> +<head>Character Range</head> +<prodgroup pcw2="4" pcw4="17.5" pcw5="11"> +<prod id="NT-Char"> +<lhs>Char</lhs><rhs>#x9 | #xA | #xD | [#x20-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF]</rhs> +<com>any Unicode character, excluding the surrogate blocks, FFFE, and FFFF.</com> +</prod> +</prodgroup></scrap> +<p>The mechanism for encoding character code points into bit patterns may +vary from entity to entity. All XML processors must accept the UTF-8 and UTF-16 +encodings of 10646; the mechanisms for signaling which of the two is in use, +or for bringing other encodings into play, are discussed later, in <specref +ref="charencoding"/>.</p> +<!-- +<p>Regardless of the specific encoding used, any character in +the ISO/IEC 10646 character set may be referred to by the decimal +or hexadecimal equivalent of its UCS-4 code value. +</p>--> +</div2> +<div2 id="sec-common-syn"> +<head>Common Syntactic Constructs</head> +<p>This section defines some symbols used widely in the grammar.</p> +<p><nt def="NT-S">S</nt> (white space) consists of one or more space (#x20) +characters, carriage returns, line feeds, or tabs.</p> +<scrap id="white" lang="ebnf"> +<head>White Space</head> +<prodgroup pcw2="4" pcw4="17.5" pcw5="11"> +<prod id="NT-S"> +<lhs>S</lhs><rhs>(#x20 | #x9 | #xD | #xA)+</rhs> +</prod> +</prodgroup></scrap> +<p>Characters are classified for convenience as letters, digits, or other +characters. <phrase diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E30">[E30]</loc>A +letter consists of an alphabetic or syllabic base character or an ideographic +character.</phrase> Full definitions of the specific characters in each class +are given in <specref ref="CharClasses"/>.</p> +<p><termdef id="dt-name" term="Name">A <term>Name</term> is a token beginning +with a letter or one of a few punctuation characters, and continuing with +letters, digits, hyphens, underscores, colons, or full stops, together known +as name characters.</termdef> Names beginning with the string <quote><code>xml</code></quote>, +or any string which would match <code>(('X'|'x') ('M'|'m') ('L'|'l'))</code>, +are reserved for standardization in this or future versions of this specification.</p> +<note> +<p diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E98">[E98]</loc>The +Namespaces in XML Recommendation <bibref ref="xml-names"/> assigns a meaning +to names containing colon characters. Therefore, authors should not use the +colon in XML names except for namespace purposes, but XML processors must +accept the colon as a name character.</p> +</note> +<p>An <nt def="NT-Nmtoken">Nmtoken</nt> (name token) is any mixture of name +characters.</p> +<scrap lang="ebnf"> +<head>Names and Tokens</head> +<prod id="NT-NameChar"> +<lhs>NameChar</lhs><rhs><nt def="NT-Letter">Letter</nt> | <nt def="NT-Digit">Digit</nt> +| '.' | '-' | '_' | ':' | <nt def="NT-CombiningChar">CombiningChar</nt> | <nt +def="NT-Extender">Extender</nt></rhs> +</prod> +<prod id="NT-Name"> +<lhs>Name</lhs><rhs>(<nt def="NT-Letter">Letter</nt> | '_' | ':') (<nt def="NT-NameChar">NameChar</nt>)*</rhs> +</prod> +<prod id="NT-Names"> +<lhs>Names</lhs><rhs><nt def="NT-Name">Name</nt> (<nt def="NT-S">S</nt> <nt +def="NT-Name">Name</nt>)*</rhs> +</prod> +<prod id="NT-Nmtoken"> +<lhs>Nmtoken</lhs><rhs>(<nt def="NT-NameChar">NameChar</nt>)+</rhs> +</prod> +<prod id="NT-Nmtokens"> +<lhs>Nmtokens</lhs><rhs><nt def="NT-Nmtoken">Nmtoken</nt> (<nt def="NT-S">S</nt> <nt +def="NT-Nmtoken">Nmtoken</nt>)*</rhs> +</prod> +</scrap> +<p>Literal data is any quoted string not containing the quotation mark used +as a delimiter for that string. Literals are used for specifying the content +of internal entities (<nt def="NT-EntityValue">EntityValue</nt>), the values +of attributes (<nt def="NT-AttValue">AttValue</nt>), and external identifiers +(<nt def="NT-SystemLiteral">SystemLiteral</nt>). Note that a <nt def="NT-SystemLiteral">SystemLiteral</nt> +can be parsed without scanning for markup.</p> +<scrap lang="ebnf"> +<head>Literals</head> +<prod id="NT-EntityValue"> +<lhs>EntityValue</lhs><rhs>'"' ([^%&"] | <nt def="NT-PEReference">PEReference</nt> +| <nt def="NT-Reference">Reference</nt>)* '"' </rhs> +<rhs>| "'" ([^%&'] | <nt def="NT-PEReference">PEReference</nt> | <nt +def="NT-Reference">Reference</nt>)* "'"</rhs> +</prod> +<prod id="NT-AttValue"> +<lhs>AttValue</lhs><rhs>'"' ([^<&"] | <nt def="NT-Reference">Reference</nt>)* +'"' </rhs> +<rhs>| "'" ([^<&'] | <nt def="NT-Reference">Reference</nt>)* +"'"</rhs> +</prod> +<prod id="NT-SystemLiteral"> +<lhs>SystemLiteral</lhs><rhs>('"' [^"]* '"') | ("'" [^']* "'") </rhs> +</prod> +<prod id="NT-PubidLiteral"> +<lhs>PubidLiteral</lhs><rhs>'"' <nt def="NT-PubidChar">PubidChar</nt>* '"' +| "'" (<nt def="NT-PubidChar">PubidChar</nt> - "'")* "'"</rhs> +</prod> +<prod id="NT-PubidChar"> +<lhs>PubidChar</lhs><rhs>#x20 | #xD | #xA | [a-zA-Z0-9] | [-'()+,./:=?;!*#@$_%]</rhs> +</prod> +</scrap> +<note diff="add"> +<p><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E72">[E72]</loc>Although +the <nt def="NT-EntityValue">EntityValue</nt> production allows the definition +of an entity consisting of a single explicit <code><</code> in the literal +(e.g., <code><!ENTITY mylt "<"></code>), it is strongly advised to avoid +this practice since any reference to that entity will cause a well-formedness +error.</p> +</note> +</div2> +<div2 id="syntax"> +<head>Character Data and Markup</head> +<p><termref def="dt-text">Text</termref> consists of intermingled <termref +def="dt-chardata">character data</termref> and markup. <termdef id="dt-markup" +term="Markup"><term>Markup</term> takes the form of <termref def="dt-stag">start-tags</termref>, <termref +def="dt-etag">end-tags</termref>, <termref def="dt-empty">empty-element tags</termref>, <termref +def="dt-entref">entity references</termref>, <termref def="dt-charref">character +references</termref>, <termref def="dt-comment">comments</termref>, <termref +def="dt-cdsection">CDATA section</termref> delimiters, <termref def="dt-doctype">document +type declarations</termref>, <termref def="dt-pi">processing instructions</termref>, <phrase +diff="add"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E89">[E89]</loc><nt +def="NT-XMLDecl">XML declarations</nt>, <nt def="NT-TextDecl">text declarations</nt>, +and any white space that is at the top level of the document entity (that +is, outside the document element and not inside any other markup).</phrase></termdef></p> +<p><termdef id="dt-chardata" term="Character Data">All text that is not markup +constitutes the <term>character data</term> of the document.</termdef></p> +<p>The ampersand character (&) and the left angle bracket (<) may appear +in their literal form <emph>only</emph> when used as markup delimiters, or +within a <termref def="dt-comment">comment</termref>, a <termref def="dt-pi">processing +instruction</termref>, or a <termref def="dt-cdsection">CDATA section</termref>.<phrase +diff="del"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E18">[E18]</loc>They +are also legal within the <termref def="dt-litentval">literal entity value</termref> +of an internal entity declaration; see <specref ref="wf-entities"/>.</phrase> <!-- FINAL EDIT: restore internal entity decl or leave it out. --> +If they are needed elsewhere, they must be <termref def="dt-escape">escaped</termref> +using either <termref def="dt-charref">numeric character references</termref> +or the strings <quote><code>&amp;</code></quote> and <quote><code>&lt;</code></quote> +respectively. The right angle bracket (>) may be represented using the string <quote><code>&gt;</code></quote>, +and must, <termref def="dt-compat">for compatibility</termref>, be escaped +using <quote><code>&gt;</code></quote> or a character reference when it +appears in the string <quote><code>]]></code></quote> in content, when +that string is not marking the end of a <termref def="dt-cdsection">CDATA +section</termref>.</p> +<p>In the content of elements, character data is any string of characters +which does not contain the start-delimiter of any markup. In a CDATA section, +character data is any string of characters not including the CDATA-section-close +delimiter, <quote><code>]]></code></quote>.</p> +<p>To allow attribute values to contain both single and double quotes, the +apostrophe or single-quote character (') may be represented as <quote><code>&apos;</code></quote>, +and the double-quote character (") as <quote><code>&quot;</code></quote>.</p> +<scrap lang="ebnf"> +<head>Character Data</head> +<prod id="NT-CharData"> +<lhs>CharData</lhs><rhs>[^<&]* - ([^<&]* ']]>' [^<&]*)</rhs> +</prod> +</scrap> +</div2> +<div2 id="sec-comments"> +<head>Comments</head> +<p><termdef id="dt-comment" term="Comment"><term>Comments</term> may appear +anywhere in a document outside other <termref def="dt-markup">markup</termref>; +in addition, they may appear within the document type declaration at places +allowed by the grammar. They are not part of the document's <termref def="dt-chardata">character +data</termref>; an XML processor may, but need not, make it possible for an +application to retrieve the text of comments. <termref def="dt-compat">For +compatibility</termref>, the string <quote><code>--</code></quote> (double-hyphen) +must not occur within comments.</termdef> <phrase diff="add"><loc role="erratumref" +href="http://www.w3.org/XML/xml-19980210-errata#E63">[E63]</loc>Parameter +entity references are not recognized within comments.</phrase></p> +<scrap lang="ebnf"> +<head>Comments</head> +<prod id="NT-Comment"> +<lhs>Comment</lhs><rhs>'<!--' ((<nt def="NT-Char">Char</nt> - '-') | ('-' +(<nt def="NT-Char">Char</nt> - '-')))* '-->'</rhs> +</prod> +</scrap> +<p>An example of a comment:</p> +<eg><!&como; declarations for <head> & <body> &comc;></eg> +<p diff="add"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E27">[E27]</loc>Note +that the grammar does not allow a comment ending in <code>---></code>. The +following example is <emph>not</emph> well-formed.</p> +<eg diff="add"><!-- B+, B, or B---></eg> +</div2> +<div2 id="sec-pi"> +<head>Processing Instructions</head> +<p><termdef id="dt-pi" term="Processing instruction"><term>Processing instructions</term> +(PIs) allow documents to contain instructions for applications.</termdef></p> +<scrap lang="ebnf"> +<head>Processing Instructions</head> +<prod id="NT-PI"> +<lhs>PI</lhs><rhs>'<?' <nt def="NT-PITarget">PITarget</nt> (<nt def="NT-S">S</nt> +(<nt def="NT-Char">Char</nt>* - (<nt def="NT-Char">Char</nt>* &pic; <nt def="NT-Char">Char</nt>*)))? &pic;</rhs> +</prod> +<prod id="NT-PITarget"> +<lhs>PITarget</lhs><rhs><nt def="NT-Name">Name</nt> - (('X' | 'x') ('M' | +'m') ('L' | 'l'))</rhs> +</prod> +</scrap> +<p>PIs are not part of the document's <termref def="dt-chardata">character +data</termref>, but must be passed through to the application. The PI begins +with a target (<nt def="NT-PITarget">PITarget</nt>) used to identify the application +to which the instruction is directed. The target names <quote><code>XML</code></quote>, <quote><code>xml</code></quote>, +and so on are reserved for standardization in this or future versions of this +specification. The XML <termref def="dt-notation">Notation</termref> mechanism +may be used for formal declaration of PI targets. <phrase diff="add"><loc +role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E63">[E63]</loc>Parameter +entity references are not recognized within processing instructions.</phrase></p> +</div2> +<div2 id="sec-cdata-sect"> +<head>CDATA Sections</head> +<p><termdef id="dt-cdsection" term="CDATA Section"><term>CDATA sections</term> +may occur anywhere character data may occur; they are used to escape blocks +of text containing characters which would otherwise be recognized as markup. +CDATA sections begin with the string <quote><code><![CDATA[</code></quote> +and end with the string <quote><code>]]></code></quote>:</termdef></p> +<scrap lang="ebnf"> +<head>CDATA Sections</head> +<prod id="NT-CDSect"> +<lhs>CDSect</lhs><rhs><nt def="NT-CDStart">CDStart</nt> <nt def="NT-CData">CData</nt> <nt +def="NT-CDEnd">CDEnd</nt></rhs> +</prod> +<prod id="NT-CDStart"> +<lhs>CDStart</lhs><rhs>'<![CDATA['</rhs> +</prod> +<prod id="NT-CData"> +<lhs>CData</lhs><rhs>(<nt def="NT-Char">Char</nt>* - (<nt def="NT-Char">Char</nt>* +']]>' <nt def="NT-Char">Char</nt>*)) </rhs> +</prod> +<prod id="NT-CDEnd"> +<lhs>CDEnd</lhs><rhs>']]>'</rhs> +</prod> +</scrap> +<p>Within a CDATA section, only the <nt def="NT-CDEnd">CDEnd</nt> string is +recognized as markup, so that left angle brackets and ampersands may occur +in their literal form; they need not (and cannot) be escaped using <quote><code>&lt;</code></quote> +and <quote><code>&amp;</code></quote>. CDATA sections cannot nest.</p> +<p>An example of a CDATA section, in which <quote><code><greeting></code></quote> +and <quote><code></greeting></code></quote> are recognized as <termref +def="dt-chardata">character data</termref>, not <termref def="dt-markup">markup</termref>:</p> +<eg><![CDATA[<greeting>Hello, world!</greeting>]]> </eg> +</div2> +<div2 id="sec-prolog-dtd"> +<head>Prolog and Document Type Declaration</head> +<p><termdef id="dt-xmldecl" term="XML Declaration">XML documents <phrase diff="chg"><loc +role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E107">[E107]</loc>should</phrase> +begin with an <term>XML declaration</term> which specifies the version of +XML being used.</termdef> For example, the following is a complete XML document, <termref +def="dt-wellformed">well-formed</termref> but not <termref def="dt-valid">valid</termref>:</p> +<eg><![CDATA[<?xml version="1.0"?> <greeting>Hello, world!</greeting> ]]></eg> +<p>and so is this:</p> +<eg><![CDATA[<greeting>Hello, world!</greeting>]]></eg> +<p>The version number <quote><code>1.0</code></quote> should be used to indicate +conformance to this version of this specification; it is an error for a document +to use the value <quote><code>1.0</code></quote> if it does not conform to +this version of this specification. It is the intent of the XML working group +to give later versions of this specification numbers other than <quote><code>1.0</code></quote>, +but this intent does not indicate a commitment to produce any future versions +of XML, nor if any are produced, to use any particular numbering scheme. Since +future versions are not ruled out, this construct is provided as a means to +allow the possibility of automatic version recognition, should it become necessary. +Processors may signal an error if they receive documents labeled with versions +they do not support.</p> +<p>The function of the markup in an XML document is to describe its storage +and logical structure and to associate attribute-value pairs with its logical +structures. XML provides a mechanism, the <termref def="dt-doctype">document +type declaration</termref>, to define constraints on the logical structure +and to support the use of predefined storage units. <termdef id="dt-valid" +term="Validity">An XML document is <term>valid</term> if it has an associated +document type declaration and if the document complies with the constraints +expressed in it.</termdef></p> +<p>The document type declaration must appear before the first <termref def="dt-element">element</termref> +in the document.</p> +<scrap id="xmldoc" lang="ebnf"> +<head>Prolog</head> +<prodgroup pcw2="6" pcw4="17.5" pcw5="9"> +<prod id="NT-prolog"> +<lhs>prolog</lhs><rhs><nt def="NT-XMLDecl">XMLDecl</nt>? <nt def="NT-Misc">Misc</nt>* +(<nt def="NT-doctypedecl">doctypedecl</nt> <nt def="NT-Misc">Misc</nt>*)?</rhs> +</prod> +<prod id="NT-XMLDecl"> +<lhs>XMLDecl</lhs><rhs>&pio; <nt def="NT-VersionInfo">VersionInfo</nt> <nt +def="NT-EncodingDecl">EncodingDecl</nt>? <nt def="NT-SDDecl">SDDecl</nt>? <nt +def="NT-S">S</nt>? &pic;</rhs> +</prod> +<prod id="NT-VersionInfo" diff="chg"> +<lhs>VersionInfo</lhs><rhs><nt def="NT-S">S</nt> 'version' <nt def="NT-Eq">Eq</nt> +("'" <nt def="NT-VersionNum">VersionNum</nt> "'" | '"' <nt def="NT-VersionNum">VersionNum</nt> +'"')<com><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E15">[E15]</loc></com></rhs> +</prod> +<prod id="NT-Eq"> +<lhs>Eq</lhs><rhs><nt def="NT-S">S</nt>? '=' <nt def="NT-S">S</nt>?</rhs> +</prod> +<prod id="NT-VersionNum"> +<lhs>VersionNum</lhs><rhs>([a-zA-Z0-9_.:] | '-')+</rhs> +</prod> +<prod id="NT-Misc"> +<lhs>Misc</lhs><rhs><nt def="NT-Comment">Comment</nt> | <nt def="NT-PI">PI</nt> +| <nt def="NT-S">S</nt></rhs> +</prod> +</prodgroup></scrap> +<p><termdef id="dt-doctype" term="Document Type Declaration">The XML <term>document +type declaration</term> contains or points to <termref def="dt-markupdecl">markup +declarations</termref> that provide a grammar for a class of documents. This +grammar is known as a document type definition, or <term>DTD</term>. The document +type declaration can point to an external subset (a special kind of <termref +def="dt-extent">external entity</termref>) containing markup declarations, +or can contain the markup declarations directly in an internal subset, or +can do both. The DTD for a document consists of both subsets taken together.</termdef></p> +<p><termdef id="dt-markupdecl" term="markup declaration"> A <term>markup declaration</term> +is an <termref def="dt-eldecl">element type declaration</termref>, an <termref +def="dt-attdecl">attribute-list declaration</termref>, an <termref def="dt-entdecl">entity +declaration</termref>, or a <termref def="dt-notdecl">notation declaration</termref>.</termdef> +These declarations may be contained in whole or in part within <termref def="dt-PE">parameter +entities</termref>, as described in the well-formedness and validity constraints +below. For <phrase diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E14">[E14]</loc>further</phrase> +information, see <specref ref="sec-physical-struct"/>.</p> +<scrap id="dtd" lang="ebnf"> +<head>Document Type Definition</head> +<prodgroup pcw2="6" pcw4="17.5" pcw5="9"> +<prod id="NT-doctypedecl" diff="chg"> +<lhs>doctypedecl</lhs><rhs>'<!DOCTYPE' <nt def="NT-S">S</nt> <nt def="NT-Name">Name</nt> +(<nt def="NT-S">S</nt> <nt def="NT-ExternalID">ExternalID</nt>)? <nt def="NT-S">S</nt>? +('[' (<nt def="NT-markupdecl">markupdecl</nt> | <nt diff="chg" def="NT-DeclSep">DeclSep</nt>)* +']' <nt def="NT-S">S</nt>?)? '>'</rhs><vc def="vc-roottype"/><wfc def="ExtSubset" +diff="add"/><com><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E109">[E109]</loc></com> +</prod> +<prod id="NT-DeclSep" diff="add"> +<lhs>DeclSep</lhs><rhs><nt def="NT-PEReference">PEReference</nt> | <nt def="NT-S">S</nt></rhs> +<wfc def="PE-between-Decls" diff="add"/><com><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E109">[E109]</loc></com> +</prod> +<prod id="NT-markupdecl"> +<lhs>markupdecl</lhs><rhs><nt def="NT-elementdecl">elementdecl</nt> | <nt +def="NT-AttlistDecl">AttlistDecl</nt> | <nt def="NT-EntityDecl">EntityDecl</nt> +| <nt def="NT-NotationDecl">NotationDecl</nt> | <nt def="NT-PI">PI</nt> | <nt +def="NT-Comment">Comment</nt> </rhs><vc def="vc-PEinMarkupDecl"/><wfc def="wfc-PEinInternalSubset"/> +</prod> +</prodgroup></scrap> +<p diff="add"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E82">[E82]</loc>Note +that it is possible to construct a well-formed document containing a <nt def="NT-doctypedecl">doctypedecl</nt> +that neither points to an external subset nor contains an internal subset.</p> +<p>The markup declarations may be made up in whole or in part of the <termref +def="dt-repltext">replacement text</termref> of <termref def="dt-PE">parameter +entities</termref>. The productions later in this specification for individual +nonterminals (<nt def="NT-elementdecl">elementdecl</nt>, <nt def="NT-AttlistDecl">AttlistDecl</nt>, +and so on) describe the declarations <emph>after</emph> all the parameter +entities have been <termref def="dt-include">included</termref>.</p> +<p diff="add"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E75">[E75]</loc>Parameter +entity references are recognized anywhere in the DTD (internal and external +subsets and external parameter entities), except in literals, processing instructions, +comments, and the contents of ignored conditional sections (see <specref ref="sec-condition-sect"/>). +They are also recognized in entity value literals. The use of parameter entities +in the internal subset is restricted as described below.</p> +<vcnote id="vc-roottype"><head>Root Element Type</head><p>The <nt def="NT-Name">Name</nt> +in the document type declaration must match the element type of the <termref +def="dt-root">root element</termref>.</p> +</vcnote> +<vcnote id="vc-PEinMarkupDecl"><head>Proper Declaration/PE Nesting</head> +<p>Parameter-entity <termref def="dt-repltext">replacement text</termref> +must be properly nested with markup declarations. That is to say, if either +the first character or the last character of a markup declaration (<nt def="NT-markupdecl">markupdecl</nt> +above) is contained in the replacement text for a <termref def="dt-PERef">parameter-entity +reference</termref>, both must be contained in the same replacement text.</p> +</vcnote> +<wfcnote id="wfc-PEinInternalSubset"><head>PEs in Internal Subset</head><p>In +the internal DTD subset, <termref def="dt-PERef">parameter-entity references</termref> +can occur only where markup declarations can occur, not within markup declarations. +(This does not apply to references that occur in external parameter entities +or to the external subset.)</p> +</wfcnote> +<wfcnote id="ExtSubset" diff="add"><head><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E109">[E109]</loc>External +Subset</head><p>The external subset, if any, must match the production for <nt +def="NT-extSubset">extSubset</nt>.</p> +</wfcnote> +<wfcnote id="PE-between-Decls" diff="add"><head><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E109">[E109]</loc>PE +Between Declarations</head><p>The replacement text of a parameter entity reference +in a <nt def="NT-DeclSep">DeclSep</nt> must match the production <nt def="NT-extSubsetDecl">extSubsetDecl</nt>.</p> +</wfcnote> +<p>Like the internal subset, the external subset and any external parameter +entities <phrase diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E109">[E109]</loc>referenced +in a <nt def="NT-DeclSep">DeclSep</nt></phrase> must consist of a series of +complete markup declarations of the types allowed by the non-terminal symbol <nt +def="NT-markupdecl">markupdecl</nt>, interspersed with white space or <termref +def="dt-PERef">parameter-entity references</termref>. However, portions of +the contents of the external subset or of <phrase diff="add"><loc role="erratumref" +href="http://www.w3.org/XML/xml-19980210-errata#E109">[E109]</loc>these </phrase> +external parameter entities may conditionally be ignored by using the <termref +def="dt-cond-section">conditional section</termref> construct; this is not +allowed in the internal subset.</p> +<scrap id="ext-Subset"> +<head>External Subset</head> +<prodgroup pcw2="6" pcw4="17.5" pcw5="9"> +<prod id="NT-extSubset"> +<lhs>extSubset</lhs><rhs><nt def="NT-TextDecl">TextDecl</nt>? <nt def="NT-extSubsetDecl">extSubsetDecl</nt></rhs> +</prod> +<prod id="NT-extSubsetDecl" diff="chg"> +<lhs>extSubsetDecl</lhs><rhs>( <nt def="NT-markupdecl">markupdecl</nt> | <nt +def="NT-conditionalSect">conditionalSect</nt> | <nt diff="chg" def="NT-DeclSep">DeclSep</nt>)*</rhs> +<com><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E109">[E109]</loc></com> +</prod> +</prodgroup></scrap> +<p>The external subset and external parameter entities also differ from the +internal subset in that in them, <termref def="dt-PERef">parameter-entity +references</termref> are permitted <emph>within</emph> markup declarations, +not only <emph>between</emph> markup declarations.</p> +<p>An example of an XML document with a document type declaration:</p> +<eg><![CDATA[<?xml version="1.0"?> <!DOCTYPE greeting SYSTEM "hello.dtd"> <greeting>Hello, world!</greeting> ]]></eg> +<p>The <termref def="dt-sysid">system identifier</termref> <quote><code>hello.dtd</code></quote> +gives the <phrase diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E78">[E78]</loc>address +(a URI reference)</phrase> of a DTD for the document.</p> +<p>The declarations can also be given locally, as in this example:</p> +<eg><![CDATA[<?xml version="1.0" encoding="UTF-8" ?> +<!DOCTYPE greeting [ + <!ELEMENT greeting (#PCDATA)> +]> +<greeting>Hello, world!</greeting>]]></eg> +<p>If both the external and internal subsets are used, the internal subset +is considered to occur before the external subset. <!-- 'is considered to'? boo. whazzat mean? --> +This has the effect that entity and attribute-list declarations in the internal +subset take precedence over those in the external subset.</p> +</div2> +<div2 id="sec-rmd"> +<head>Standalone Document Declaration</head> +<p>Markup declarations can affect the content of the document, as passed from +an <termref def="dt-xml-proc">XML processor</termref> to an application; examples +are attribute defaults and entity declarations. The standalone document declaration, +which may appear as a component of the XML declaration, signals whether or +not there are such declarations which appear external to the <termref def="dt-docent">document +entity</termref><phrase diff="add"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E64">[E64]</loc> +or in parameter entities. <termdef id="dt-extmkpdecl" term="External Markup Declaration">An <term>external +markup declaration</term> is defined as a markup declaration occurring in +the external subset or in a parameter entity (external or internal, the latter +being included because non-validating processors are not required to read +them).</termdef></phrase></p> +<scrap id="fulldtd" lang="ebnf"> +<head>Standalone Document Declaration</head> +<prodgroup pcw2="4" pcw4="19.5" pcw5="9"> +<prod id="NT-SDDecl"> +<lhs>SDDecl</lhs><rhs> <nt def="NT-S">S</nt> 'standalone' <nt def="NT-Eq">Eq</nt> +(("'" ('yes' | 'no') "'") | ('"' ('yes' | 'no') '"')) </rhs><vc def="vc-check-rmd"/> +</prod> +</prodgroup></scrap> +<p>In a standalone document declaration, the value <attval>yes</attval> indicates +that there are no <phrase diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E64">[E64]</loc><termref +def="dt-extmkpdecl">external markup declarations</termref></phrase> which +affect the information passed from the XML processor to the application. The +value <attval>no</attval> indicates that there are or may be such external +markup declarations. Note that the standalone document declaration only denotes +the presence of external <emph>declarations</emph>; the presence, in a document, +of references to external <emph>entities</emph>, when those entities are internally +declared, does not change its standalone status.</p> +<p>If there are no external markup declarations, the standalone document declaration +has no meaning. If there are external markup declarations but there is no +standalone document declaration, the value <attval>no</attval> is assumed.</p> +<p>Any XML document for which <code>standalone="no"</code> holds can be converted +algorithmically to a standalone document, which may be desirable for some +network delivery applications.</p> +<vcnote id="vc-check-rmd"><head>Standalone Document Declaration</head><p>The +standalone document declaration must have the value <attval>no</attval> if +any external markup declarations contain declarations of:</p> +<ulist> +<item><p>attributes with <termref def="dt-default">default</termref> values, +if elements to which these attributes apply appear in the document without +specifications of values for these attributes, or</p></item> +<item><p>entities (other than &magicents;), if <termref def="dt-entref">references</termref> +to those entities appear in the document, or</p></item> +<item><p>attributes with values subject to <titleref href="#AVNormalize">normalization</titleref>, +where the attribute appears in the document with a value which will change +as a result of normalization, or</p></item> +<item><p>element types with <termref def="dt-elemcontent">element content</termref>, +if white space occurs directly within any instance of those types.</p></item> +</ulist> +</vcnote> +<p>An example XML declaration with a standalone document declaration:</p> +<eg><?xml version="&versionOfXML;" standalone='yes'?></eg> +</div2> +<div2 id="sec-white-space"> +<head>White Space Handling</head> +<p>In editing XML documents, it is often convenient to use <quote>white space</quote> +(spaces, tabs, and blank lines<phrase diff="del"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E39">[E39]</loc>, +denoted by the nonterminal <nt def="NT-S">S</nt> in this specification</phrase>) +to set apart the markup for greater readability. Such white space is typically +not intended for inclusion in the delivered version of the document. On the +other hand, <quote>significant</quote> white space that should be preserved +in the delivered version is common, for example in poetry and source code.</p> +<p>An <termref def="dt-xml-proc">XML processor</termref> must always pass +all characters in a document that are not markup through to the application. +A <termref def="dt-validating"> validating XML processor</termref> must also +inform the application which of these characters constitute white space appearing +in <termref def="dt-elemcontent">element content</termref>.</p> +<p>A special <termref def="dt-attr">attribute</termref> named <att>xml:space</att> +may be attached to an element to signal an intention that in that element, +white space should be preserved by applications. In valid documents, this +attribute, like any other, must be <termref def="dt-attdecl">declared</termref> +if it is used. When declared, it must be given as an <termref def="dt-enumerated">enumerated +type</termref> whose <phrase diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E81">[E81]</loc>values +are one or both of</phrase> <attval>default</attval> and <attval>preserve</attval>. +For example:</p> +<eg diff="chg"><![CDATA[<!ATTLIST poem xml:space (default|preserve) 'preserve'>]]> + +<!-- <loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E81">[E81]</loc>--> +<!ATTLIST pre xml:space (preserve) #FIXED 'preserve'></eg> +<p>The value <attval>default</attval> signals that applications' default white-space +processing modes are acceptable for this element; the value <attval>preserve</attval> +indicates the intent that applications preserve all the white space. This +declared intent is considered to apply to all elements within the content +of the element where it is specified, unless overriden with another instance +of the <att>xml:space</att> attribute.</p> +<p>The <termref def="dt-root">root element</termref> of any document is considered +to have signaled no intentions as regards application space handling, unless +it provides a value for this attribute or the attribute is declared with a +default value.</p> +</div2> +<div2 id="sec-line-ends"> +<head>End-of-Line Handling</head> +<p>XML <termref def="dt-parsedent">parsed entities</termref> are often stored +in computer files which, for editing convenience, are organized into lines. +These lines are typically separated by some combination of the characters +carriage-return (#xD) and line-feed (#xA).</p> +<p diff="del">To simplify the tasks of <termref def="dt-app">applications</termref>, +wherever an external parsed entity or the literal entity value of an internal +parsed entity contains either the literal two-character sequence <quote>#xD#xA</quote> +or a standalone literal #xD, an <termref def="dt-xml-proc">XML processor</termref> +must pass to the application the single character #xA. (This behavior can +conveniently be produced by normalizing all line breaks to #xA on input, before +parsing.)</p> +<p diff="add"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E104">[E104]</loc>To +simplify the tasks of <termref def="dt-app">applications</termref>, the characters +passed to an application by the <termref def="dt-xml-proc">XML processor</termref> +must be as if the XML processor normalized all line breaks in external parsed +entities (including the document entity) on input, before parsing, by translating +both the two-character sequence #xD #xA and any #xD that is not followed by +#xA to a single #xA character.</p> +</div2> +<div2 id="sec-lang-tag"> +<head>Language Identification</head> +<p>In document processing, it is often useful to identify the natural or formal +language in which the content is written. A special <termref def="dt-attr">attribute</termref> +named <att>xml:lang</att> may be inserted in documents to specify the language +used in the contents and attribute values of any element in an XML document. +In valid documents, this attribute, like any other, must be <termref def="dt-attdecl">declared</termref> +if it is used. <phrase diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E73">[E73]</loc>The +values of the attribute are language identifiers as defined by <bibref ref="RFC1766"/>, <titleref>Tags +for the Identification of Languages</titleref>, or its successor on the IETF +Standards Track.</phrase></p> +<note diff="add"> +<p><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E73">[E73]</loc><bibref +ref="RFC1766"/> tags are constructed from two-letter language codes as defined +by <bibref ref="ISO639"/>, from two-letter country codes as defined by <bibref +ref="ISO3166"/>, or from language identifiers registered with the Internet +Assigned Numbers Authority <phrase diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E58">[E58]</loc><bibref +diff="chg" ref="IANA-LANGCODES"/></phrase>. It is expected that the successor +to <bibref ref="RFC1766"/> will introduce three-letter language codes for +languages not presently covered by <bibref ref="ISO639"/>.</p> +</note> +<p diff="add"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E73">[E73]</loc>(Productions +33 through 38 have been removed.)</p> +<scrap diff="del" lang="ebnf"> +<head>Language Identification</head> +<prod id="NT-LanguageID"> +<lhs>LanguageID</lhs><rhs><nt def="NT-Langcode">Langcode</nt> ('-' <nt def="NT-Subcode">Subcode</nt>)*</rhs> +</prod> +<prod id="NT-Langcode"> +<lhs>Langcode</lhs><rhs><nt def="NT-ISO639Code">ISO639Code</nt> | <nt def="NT-IanaCode">IanaCode</nt> +| <nt def="NT-UserCode">UserCode</nt></rhs> +</prod> +<prod id="NT-ISO639Code"> +<lhs>ISO639Code</lhs><rhs>([a-z] | [A-Z]) ([a-z] | [A-Z])</rhs> +</prod> +<prod id="NT-IanaCode"> +<lhs>IanaCode</lhs><rhs>('i' | 'I') '-' ([a-z] | [A-Z])+</rhs> +</prod> +<prod id="NT-UserCode"> +<lhs>UserCode</lhs><rhs>('x' | 'X') '-' ([a-z] | [A-Z])+</rhs> +</prod> +<prod id="NT-Subcode"> +<lhs>Subcode</lhs><rhs>([a-z] | [A-Z])+</rhs> +</prod> +</scrap> +<p diff="del">The <nt def="NT-Langcode">Langcode</nt> may be any of the following:</p> +<ulist diff="del"> +<item><p>a two-letter language code as defined by <bibref ref="ISO639"/>, <titleref>Codes +for the representation of names of languages</titleref></p></item> +<item><p>a language identifier registered with the Internet Assigned Numbers +Authority <bibref diff="chg" ref="IANA-LANGCODES"/>; these begin with the +prefix <quote><code>i-</code></quote> (or <quote><code>I-</code></quote>)</p> +</item> +<item><p>a language identifier assigned by the user, or agreed on between +parties in private use; these must begin with the prefix <quote><code>x-</code></quote> +or <quote><code>X-</code></quote> in order to ensure that they do not conflict +with names later standardized or registered with IANA</p></item> +</ulist> +<p diff="del">There may be any number of <nt def="NT-Subcode">Subcode</nt> +segments; if the first subcode segment exists and the Subcode consists of +two letters, then it must be a country code from <bibref ref="ISO3166"/>, +"Codes for the representation of names of countries." If the first subcode +consists of more than two letters, it must be a subcode for the language in +question registered with IANA, unless the <nt def="NT-Langcode">Langcode</nt> +begins with the prefix "<code>x-</code>" or "<code>X-</code>". </p> +<p diff="del">It is customary to give the language code in lower case, and +the country code (if any) in upper case. Note that these values, unlike other +names in XML documents, are case insensitive.</p> +<p>For example:</p> +<eg><![CDATA[<p xml:lang="en">The quick brown fox jumps over the lazy dog.</p> +<p xml:lang="en-GB">What colour is it?</p> +<p xml:lang="en-US">What color is it?</p> +<sp who="Faust" desc='leise' xml:lang="de"> + <l>Habe nun, ach! Philosophie,</l> + <l>Juristerei, und Medizin</l> + <l>und leider auch Theologie</l> + <l>durchaus studiert mit heißem Bemüh'n.</l> +</sp>]]></eg> +<!--<p>The xml:lang value is considered to apply both to the contents of an +element and +(unless otherwise via attribute default values) to the +values of all of its attributes with free-text (CDATA) values. --> +<p>The intent declared with <att>xml:lang</att> is considered to apply to +all attributes and content of the element where it is specified, unless overridden +with an instance of <att>xml:lang</att> on another element within that content.</p> +<!-- +If no +value is specified for xml:lang on an element, and no default value is +defined for it in the DTD, then the xml:lang attribute of any element +takes the same value it has in the parent element, if any. The two +technical terms in the following example both have the same effective +value for xml:lang: + + <p xml:lang="en">Here the keywords are + <term xml:lang="en">shift</term> and + <term>reduce</term>. ...</p> + +The application, not the XML processor, is responsible for this ' +inheritance' of attribute values. +--> +<p>A simple declaration for <att>xml:lang</att> might take the form</p> +<eg>xml:lang NMTOKEN #IMPLIED</eg> +<p>but specific default values may also be given, if appropriate. In a collection +of French poems for English students, with glosses and notes in English, the <att>xml:lang</att> +attribute might be declared this way:</p> +<eg><![CDATA[<!ATTLIST poem xml:lang NMTOKEN 'fr'> +<!ATTLIST gloss xml:lang NMTOKEN 'en'> +<!ATTLIST note xml:lang NMTOKEN 'en'>]]></eg> +</div2> +</div1> +<!-- &Elements; --> +<div1 id="sec-logical-struct"> +<head>Logical Structures</head> +<p><termdef id="dt-element" term="Element">Each <termref def="dt-xml-doc">XML +document</termref> contains one or more <term>elements</term>, the boundaries +of which are either delimited by <termref def="dt-stag">start-tags</termref> +and <termref def="dt-etag">end-tags</termref>, or, for <termref def="dt-empty">empty</termref> +elements, by an <termref def="dt-eetag">empty-element tag</termref>. Each +element has a type, identified by name, sometimes called its <quote>generic +identifier</quote> (GI), and may have a set of attribute specifications.</termdef> +Each attribute specification has a <termref def="dt-attrname">name</termref> +and a <termref def="dt-attrval">value</termref>.</p> +<scrap lang="ebnf"> +<head>Element</head> +<prod id="NT-element"> +<lhs>element</lhs><rhs><nt def="NT-EmptyElemTag">EmptyElemTag</nt></rhs> +<rhs>| <nt def="NT-STag">STag</nt> <nt def="NT-content">content</nt> <nt def="NT-ETag">ETag</nt></rhs> +<wfc def="GIMatch"/><vc def="elementvalid"/> +</prod> +</scrap> +<p>This specification does not constrain the semantics, use, or (beyond syntax) +names of the element types and attributes, except that names beginning with +a match to <code>(('X'|'x')('M'|'m')('L'|'l'))</code> are reserved for standardization +in this or future versions of this specification.</p> +<wfcnote id="GIMatch"><head>Element Type Match</head><p>The <nt def="NT-Name">Name</nt> +in an element's end-tag must match the element type in the start-tag.</p> +</wfcnote> +<vcnote id="elementvalid"><head>Element Valid</head><p>An element is valid +if there is a declaration matching <nt def="NT-elementdecl">elementdecl</nt> +where the <nt def="NT-Name">Name</nt> matches the element type, and one of +the following holds:</p> +<olist> +<item><p>The declaration matches <kw>EMPTY</kw> and the element has no <termref +def="dt-content">content</termref>.</p></item> +<item><p>The declaration matches <nt def="NT-children">children</nt> and the +sequence of <termref def="dt-parentchild">child elements</termref> belongs +to the language generated by the regular expression in the content model, +with optional white space (characters matching the nonterminal <nt def="NT-S">S</nt>) +between <phrase diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E59">[E59]</loc>the +start-tag and the first child element, between child elements, or between +the last child element and the end-tag. Note that a CDATA section containing +only white space does not match the nonterminal <nt def="NT-S">S</nt>, and +hence cannot appear in these positions.</phrase></p></item> +<item><p>The declaration matches <nt def="NT-Mixed">Mixed</nt> and the content +consists of <termref def="dt-chardata">character data</termref> and <termref +def="dt-parentchild">child elements</termref> whose types match names in the +content model.</p></item> +<item><p>The declaration matches <kw>ANY</kw>, and the types of any <termref +def="dt-parentchild">child elements</termref> have been declared.</p></item> +</olist> +</vcnote> +<div2 id="sec-starttags"> +<head>Start-Tags, End-Tags, and Empty-Element Tags</head> +<p><termdef id="dt-stag" term="Start-Tag">The beginning of every non-empty +XML element is marked by a <term>start-tag</term>.</termdef></p> +<scrap lang="ebnf"> +<head>Start-tag</head> +<prodgroup pcw2="6" pcw4="15" pcw5="11.5"> +<prod id="NT-STag"> +<lhs>STag</lhs><rhs>'<' <nt def="NT-Name">Name</nt> (<nt def="NT-S">S</nt> <nt +def="NT-Attribute">Attribute</nt>)* <nt def="NT-S">S</nt>? '>'</rhs><wfc def="uniqattspec"/> +</prod> +<prod id="NT-Attribute"> +<lhs>Attribute</lhs><rhs><nt def="NT-Name">Name</nt> <nt def="NT-Eq">Eq</nt> <nt +def="NT-AttValue">AttValue</nt></rhs><vc def="ValueType"/><wfc def="NoExternalRefs"/> +<wfc def="CleanAttrVals"/> +</prod> +</prodgroup></scrap> +<p>The <nt def="NT-Name">Name</nt> in the start- and end-tags gives the element's <term>type</term>. <termdef +id="dt-attr" term="Attribute"> The <nt def="NT-Name">Name</nt>-<nt def="NT-AttValue">AttValue</nt> +pairs are referred to as the <term>attribute specifications</term> of the +element</termdef>, <termdef id="dt-attrname" term="Attribute Name">with the <nt +def="NT-Name">Name</nt> in each pair referred to as the <term>attribute name</term></termdef> +and <termdef id="dt-attrval" term="Attribute Value">the content of the <nt +def="NT-AttValue">AttValue</nt> (the text between the <code>'</code> or <code>"</code> +delimiters) as the <term>attribute value</term>.</termdef><phrase diff="add"><loc +role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E46">[E46]</loc>Note +that the order of attribute specifications in a start-tag or empty-element +tag is not significant.</phrase></p> +<wfcnote id="uniqattspec"><head>Unique Att Spec</head><p>No attribute name +may appear more than once in the same start-tag or empty-element tag.</p> +</wfcnote> +<vcnote id="ValueType"><head>Attribute Value Type</head><p>The attribute must +have been declared; the value must be of the type declared for it. (For attribute +types, see <specref ref="attdecls"/>.)</p> +</vcnote> +<wfcnote id="NoExternalRefs"><head>No External Entity References</head><p>Attribute +values cannot contain direct or indirect entity references to external entities.</p> +</wfcnote> +<wfcnote id="CleanAttrVals"><head>No <code><</code> in Attribute Values</head> +<p>The <termref def="dt-repltext">replacement text</termref> of any entity +referred to directly or indirectly in an attribute value <phrase diff="del"><loc +role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E83">[E83]</loc>(other +than <quote><code>&lt;</code></quote>) </phrase>must not contain a <code><</code>.</p> +</wfcnote> +<p>An example of a start-tag:</p> +<eg><termdef id="dt-dog" term="dog"></eg> +<p><termdef id="dt-etag" term="End Tag">The end of every element that begins +with a start-tag must be marked by an <term>end-tag</term> containing a name +that echoes the element's type as given in the start-tag:</termdef></p> +<scrap lang="ebnf"> +<head>End-tag</head> +<prodgroup pcw2="6" pcw4="15" pcw5="11.5"> +<prod id="NT-ETag"> +<lhs>ETag</lhs><rhs>'</' <nt def="NT-Name">Name</nt> <nt def="NT-S">S</nt>? +'>'</rhs> +</prod> +</prodgroup></scrap> +<p>An example of an end-tag:</p> +<eg></termdef></eg> +<p><termdef id="dt-content" term="Content">The <termref def="dt-text">text</termref> +between the start-tag and end-tag is called the element's <term>content</term>:</termdef></p> +<scrap lang="ebnf"> +<head>Content of Elements</head> +<prodgroup pcw2="6" pcw4="15" pcw5="11.5"> +<prod id="NT-content" diff="chg"> +<lhs>content</lhs><rhs><nt def="NT-CharData">CharData</nt>? ((<nt def="NT-element">element</nt> +| <nt def="NT-Reference">Reference</nt> | <nt def="NT-CDSect">CDSect</nt> +| <nt def="NT-PI">PI</nt> | <nt def="NT-Comment">Comment</nt>) <nt def="NT-CharData">CharData</nt>?)*</rhs> +<com><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E71">[E71]</loc></com> +</prod> +</prodgroup></scrap> +<p><phrase diff="chg"><termdef id="dt-empty" term="Empty"><loc role="erratumref" +href="http://www.w3.org/XML/xml-19980210-errata#E97">[E97]</loc>An element +with no content is said to be <term>empty</term>.</termdef> The representation +of an empty element is either a start-tag immediately followed by an end-tag, +or an empty-element tag.</phrase> <termdef id="dt-eetag" term="empty-element tag">An <term>empty-element +tag</term> takes a special form:</termdef></p> +<scrap lang="ebnf"> +<head>Tags for Empty Elements</head> +<prodgroup pcw2="6" pcw4="15" pcw5="11.5"> +<prod id="NT-EmptyElemTag"> +<lhs>EmptyElemTag</lhs><rhs>'<' <nt def="NT-Name">Name</nt> (<nt def="NT-S">S</nt> <nt +def="NT-Attribute">Attribute</nt>)* <nt def="NT-S">S</nt>? '/>'</rhs><wfc +def="uniqattspec"/> +</prod> +</prodgroup></scrap> +<p>Empty-element tags may be used for any element which has no content, whether +or not it is declared using the keyword <kw>EMPTY</kw>. <termref def="dt-interop">For +interoperability</termref>, the empty-element tag <phrase diff="chg"><loc +role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E45">[E45]</loc>should +be used, and should only be used,</phrase> for elements which are declared +EMPTY.</p> +<p>Examples of empty elements:</p> +<eg><IMG align="left" + src="http://www.w3.org/Icons/WWW/w3c_home" /> +<br></br> +<br/></eg> +</div2> +<div2 id="elemdecls"> +<head>Element Type Declarations</head> +<p>The <termref def="dt-element">element</termref> structure of an <termref +def="dt-xml-doc">XML document</termref> may, for <termref def="dt-valid">validation</termref> +purposes, be constrained using element type and attribute-list declarations. +An element type declaration constrains the element's <termref def="dt-content">content</termref>.</p> +<p>Element type declarations often constrain which element types can appear +as <termref def="dt-parentchild">children</termref> of the element. At user +option, an XML processor may issue a warning when a declaration mentions an +element type for which no declaration is provided, but this is not an error.</p> +<p><termdef id="dt-eldecl" term="Element Type declaration">An <term>element +type declaration</term> takes the form:</termdef></p> +<scrap lang="ebnf"> +<head>Element Type Declaration</head> +<prodgroup pcw2="5.5" pcw4="18" pcw5="9"> +<prod id="NT-elementdecl"> +<lhs>elementdecl</lhs><rhs>'<!ELEMENT' <nt def="NT-S">S</nt> <nt def="NT-Name">Name</nt> <nt +def="NT-S">S</nt> <nt def="NT-contentspec">contentspec</nt> <nt def="NT-S">S</nt>? +'>'</rhs><vc def="EDUnique"/> +</prod> +<prod id="NT-contentspec"> +<lhs>contentspec</lhs><rhs>'EMPTY' | 'ANY' | <nt def="NT-Mixed">Mixed</nt> +| <nt def="NT-children">children</nt> </rhs> +</prod> +</prodgroup></scrap> +<p>where the <nt def="NT-Name">Name</nt> gives the element type being declared.</p> +<vcnote id="EDUnique"><head>Unique Element Type Declaration</head><p>No element +type may be declared more than once.</p> +</vcnote> +<p>Examples of element type declarations:</p> +<eg><!ELEMENT br EMPTY> +<!ELEMENT p (#PCDATA|emph)* > +<!ELEMENT %name.para; %content.para; > +<!ELEMENT container ANY></eg> +<div3 id="sec-element-content"> +<head>Element Content</head> +<p><termdef id="dt-elemcontent" term="Element content">An element <termref +def="dt-stag">type</termref> has <term>element content</term> when elements +of that type must contain only <termref def="dt-parentchild">child</termref> +elements (no character data), optionally separated by white space (characters +matching the nonterminal <nt def="NT-S">S</nt>).</termdef><termdef id="dt-content-model" +term="Content model">In this case, the constraint includes a <phrase diff="chg"><loc +role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E55">[E55]</loc><term>content +model</term></phrase>, a simple grammar governing the allowed types of the +child elements and the order in which they are allowed to appear.</termdef> +The grammar is built on content particles (<nt def="NT-cp">cp</nt>s), which +consist of names, choice lists of content particles, or sequence lists of +content particles:</p> +<scrap lang="ebnf"> +<head>Element-content Models</head> +<prodgroup pcw2="5.5" pcw4="16" pcw5="11"> +<prod id="NT-children"> +<lhs>children</lhs><rhs>(<nt def="NT-choice">choice</nt> | <nt def="NT-seq">seq</nt>) +('?' | '*' | '+')?</rhs> +</prod> +<prod id="NT-cp"> +<lhs>cp</lhs><rhs>(<nt def="NT-Name">Name</nt> | <nt def="NT-choice">choice</nt> +| <nt def="NT-seq">seq</nt>) ('?' | '*' | '+')?</rhs> +</prod> +<prod id="NT-choice" diff="chg"> +<lhs>choice</lhs><rhs>'(' <nt def="NT-S">S</nt>? <nt def="NT-cp">cp</nt> ( <nt +def="NT-S">S</nt>? '|' <nt def="NT-S">S</nt>? <nt def="NT-cp">cp</nt> )+ <nt +def="NT-S">S</nt>? ')'</rhs><com><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E50">[E50]</loc></com> +<com><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E52">[E52]</loc></com> +<vc def="vc-PEinGroup"/> +</prod> +<prod id="NT-seq" diff="chg"> +<lhs>seq</lhs><rhs>'(' <nt def="NT-S">S</nt>? <nt def="NT-cp">cp</nt> ( <nt +def="NT-S">S</nt>? ',' <nt def="NT-S">S</nt>? <nt def="NT-cp">cp</nt> )* <nt +def="NT-S">S</nt>? ')'</rhs><com><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E52">[E52]</loc></com> +<vc def="vc-PEinGroup"/> +</prod> +</prodgroup></scrap> +<p>where each <nt def="NT-Name">Name</nt> is the type of an element which +may appear as a <termref def="dt-parentchild">child</termref>. Any content +particle in a choice list may appear in the <termref def="dt-elemcontent">element +content</termref> at the location where the choice list appears in the grammar; +content particles occurring in a sequence list must each appear in the <termref +def="dt-elemcontent">element content</termref> in the order given in the list. +The optional character following a name or list governs whether the element +or the content particles in the list may occur one or more (<code>+</code>), +zero or more (<code>*</code>), or zero or one times (<code>?</code>). The +absence of such an operator means that the element or content particle must +appear exactly once. This syntax and meaning are identical to those used in +the productions in this specification.</p> +<p>The content of an element matches a content model if and only if it is +possible to trace out a path through the content model, obeying the sequence, +choice, and repetition operators and matching each element in the content +against an element type in the content model. <termref def="dt-compat">For +compatibility</termref>, it is an error if an element in the document can +match more than one occurrence of an element type in the content model. For +more information, see <specref ref="determinism"/>.</p> +<!--appendix <specref ref="determinism"/>.--> +<!-- appendix on deterministic content models. --> +<vcnote id="vc-PEinGroup"><head>Proper Group/PE Nesting</head><p>Parameter-entity <termref +def="dt-repltext">replacement text</termref> must be properly nested with <phrase +diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E11">[E11]</loc>parenthesized</phrase> +groups. That is to say, if either of the opening or closing parentheses in +a <nt def="NT-choice">choice</nt>, <nt def="NT-seq">seq</nt>, or <nt def="NT-Mixed">Mixed</nt> +construct is contained in the replacement text for a <termref def="dt-PERef">parameter +entity</termref>, both must be contained in the same replacement text.</p> +<p diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E19">[E19]</loc><termref +def="dt-interop">For interoperability</termref>, if a parameter-entity reference +appears in a <nt def="NT-choice">choice</nt>, <nt def="NT-seq">seq</nt>, or <nt +def="NT-Mixed">Mixed</nt> construct, its replacement text should contain at +least one non-blank character, and neither the first nor last non-blank character +of the replacement text should be a connector (<code>|</code> or <code>,</code>).</p> +</vcnote> +<p>Examples of element-content models:</p> +<eg><!ELEMENT spec (front, body, back?)> +<!ELEMENT div1 (head, (p | list | note)*, div2*)> +<!ELEMENT dictionary-body (%div.mix; | %dict.mix;)*></eg> +</div3> +<div3 id="sec-mixed-content"> +<head>Mixed Content</head> +<p><termdef id="dt-mixed" term="Mixed Content">An element <termref def="dt-stag">type</termref> +has <term>mixed content</term> when elements of that type may contain character +data, optionally interspersed with <termref def="dt-parentchild">child</termref> +elements.</termdef> In this case, the types of the child elements may be constrained, +but not their order or their number of occurrences:</p> +<scrap lang="ebnf"> +<head>Mixed-content Declaration</head> +<prodgroup pcw2="5.5" pcw4="16" pcw5="11"> +<prod id="NT-Mixed"> +<lhs>Mixed</lhs><rhs>'(' <nt def="NT-S">S</nt>? '#PCDATA' (<nt def="NT-S">S</nt>? +'|' <nt def="NT-S">S</nt>? <nt def="NT-Name">Name</nt>)* <nt def="NT-S">S</nt>? +')*' </rhs> +<rhs>| '(' <nt def="NT-S">S</nt>? '#PCDATA' <nt def="NT-S">S</nt>? ')' </rhs> +<vc def="vc-PEinGroup"/><vc def="vc-MixedChildrenUnique"/> +</prod> +</prodgroup></scrap> +<p>where the <nt def="NT-Name">Name</nt>s give the types of elements that +may appear as children. <phrase diff="add"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E10">[E10]</loc>The +keyword <kw>#PCDATA</kw> derives historically from the term <quote>parsed +character data.</quote></phrase></p> +<vcnote id="vc-MixedChildrenUnique"><head>No Duplicate Types</head><p>The +same name must not appear more than once in a single mixed-content declaration.</p> +</vcnote> +<p>Examples of mixed content declarations:</p> +<eg><!ELEMENT p (#PCDATA|a|ul|b|i|em)*> +<!ELEMENT p (#PCDATA | %font; | %phrase; | %special; | %form;)* > +<!ELEMENT b (#PCDATA)></eg> +</div3> +</div2> +<div2 id="attdecls"> +<head>Attribute-List Declarations</head> +<p><termref def="dt-attr">Attributes</termref> are used to associate name-value +pairs with <termref def="dt-element">elements</termref>. Attribute specifications +may appear only within <termref def="dt-stag">start-tags</termref> and <termref +def="dt-eetag">empty-element tags</termref>; thus, the productions used to +recognize them appear in <specref ref="sec-starttags"/>. Attribute-list declarations +may be used:</p> +<ulist> +<item><p>To define the set of attributes pertaining to a given element type.</p> +</item> +<item><p>To establish type constraints for these attributes.</p></item> +<item><p>To provide <termref def="dt-default">default values</termref> for +attributes.</p></item> +</ulist> +<p><termdef id="dt-attdecl" term="Attribute-List Declaration"> <term>Attribute-list +declarations</term> specify the name, data type, and default value (if any) +of each attribute associated with a given element type:</termdef></p> +<scrap lang="ebnf"> +<head>Attribute-list Declaration</head> +<prod id="NT-AttlistDecl"> +<lhs>AttlistDecl</lhs><rhs>'<!ATTLIST' <nt def="NT-S">S</nt> <nt def="NT-Name">Name</nt> <nt +def="NT-AttDef">AttDef</nt>* <nt def="NT-S">S</nt>? '>'</rhs> +</prod> +<prod id="NT-AttDef"> +<lhs>AttDef</lhs><rhs><nt def="NT-S">S</nt> <nt def="NT-Name">Name</nt> <nt +def="NT-S">S</nt> <nt def="NT-AttType">AttType</nt> <nt def="NT-S">S</nt> <nt +def="NT-DefaultDecl">DefaultDecl</nt></rhs> +</prod> +</scrap> +<p>The <nt def="NT-Name">Name</nt> in the <nt def="NT-AttlistDecl">AttlistDecl</nt> +rule is the type of an element. At user option, an XML processor may issue +a warning if attributes are declared for an element type not itself declared, +but this is not an error. The <nt def="NT-Name">Name</nt> in the <nt def="NT-AttDef">AttDef</nt> +rule is the name of the attribute.</p> +<p>When more than one <nt def="NT-AttlistDecl">AttlistDecl</nt> is provided +for a given element type, the contents of all those provided are merged. When +more than one definition is provided for the same attribute of a given element +type, the first declaration is binding and later declarations are ignored. <phrase +diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E9">[E9]</loc><termref +def="dt-interop">For interoperability,</termref> writers of DTDs may choose +to provide at most one attribute-list declaration for a given element type, +at most one attribute definition for a given attribute name in an attribute-list +declaration, and at least one attribute definition in each attribute-list +declaration.</phrase> For interoperability, an XML processor may at user option +issue a warning when more than one attribute-list declaration is provided +for a given element type, or more than one attribute definition is provided +for a given attribute, but this is not an error.</p> +<div3 id="sec-attribute-types"> +<head>Attribute Types</head> +<p>XML attribute types are of three kinds: a string type, a set of tokenized +types, and enumerated types. The string type may take any literal string as +a value; the tokenized types have varying lexical and semantic constraints<phrase +diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E8">[E8]</loc>. +The validity constraints noted in the grammar are applied after the attribute +value has been normalized as described in <specref ref="attdecls"/>.</phrase></p> +<scrap lang="ebnf"> +<head>Attribute Types</head> +<prodgroup pcw4="14" pcw5="11.5"> +<prod id="NT-AttType"> +<lhs>AttType</lhs><rhs><nt def="NT-StringType">StringType</nt> | <nt def="NT-TokenizedType">TokenizedType</nt> +| <nt def="NT-EnumeratedType">EnumeratedType</nt> </rhs> +</prod> +<prod id="NT-StringType"> +<lhs>StringType</lhs><rhs>'CDATA'</rhs> +</prod> +<prod id="NT-TokenizedType"> +<lhs>TokenizedType</lhs><rhs>'ID'</rhs><vc def="id"/><vc def="one-id-per-el"/> +<vc def="id-default"/> +<rhs>| 'IDREF'</rhs><vc def="idref"/> +<rhs>| 'IDREFS'</rhs><vc def="idref"/> +<rhs>| 'ENTITY'</rhs><vc def="entname"/> +<rhs>| 'ENTITIES'</rhs><vc def="entname"/> +<rhs>| 'NMTOKEN'</rhs><vc def="nmtok"/> +<rhs>| 'NMTOKENS'</rhs><vc def="nmtok"/> +</prod> +</prodgroup></scrap> +<vcnote id="id"><head>ID</head><p>Values of type <kw>ID</kw> must match the <nt +def="NT-Name">Name</nt> production. A name must not appear more than once +in an XML document as a value of this type; i.e., ID values must uniquely +identify the elements which bear them.</p> +</vcnote> +<vcnote id="one-id-per-el"><head>One ID per Element Type</head><p>No element +type may have more than one ID attribute specified.</p> +</vcnote> +<vcnote id="id-default"><head>ID Attribute Default</head><p>An ID attribute +must have a declared default of <kw>#IMPLIED</kw> or <kw>#REQUIRED</kw>.</p> +</vcnote> +<vcnote id="idref"><head>IDREF</head><p>Values of type <kw>IDREF</kw> must +match the <nt def="NT-Name">Name</nt> production, and values of type <kw>IDREFS</kw> +must match <nt def="NT-Names">Names</nt>; each <nt def="NT-Name">Name</nt> +must match the value of an ID attribute on some element in the XML document; +i.e. <kw>IDREF</kw> values must match the value of some ID attribute.</p> +</vcnote> +<vcnote id="entname"><head>Entity Name</head><p>Values of type <kw>ENTITY</kw> +must match the <nt def="NT-Name">Name</nt> production, values of type <kw>ENTITIES</kw> +must match <nt def="NT-Names">Names</nt>; each <nt def="NT-Name">Name</nt> +must match the name of an <termref def="dt-unparsed">unparsed entity</termref> +declared in the <termref def="dt-doctype">DTD</termref>.</p> +</vcnote> +<vcnote id="nmtok"><head>Name Token</head><p>Values of type <kw>NMTOKEN</kw> +must match the <nt def="NT-Nmtoken">Nmtoken</nt> production; values of type <kw>NMTOKENS</kw> +must match <termref def="NT-Nmtokens">Nmtokens</termref>.</p> +</vcnote> +<!-- why? +<p>The XML processor must normalize attribute values before +passing them to the application, as described in +<specref ref="AVNormalize"/>.</p>--> +<p><termdef id="dt-enumerated" term="Enumerated Attribute +Values"><term>Enumerated attributes</term> can take one of a list of values +provided in the declaration</termdef>. There are two kinds of enumerated types:</p> +<scrap lang="ebnf"> +<head>Enumerated Attribute Types</head> +<prod id="NT-EnumeratedType"> +<lhs>EnumeratedType</lhs><rhs><nt def="NT-NotationType">NotationType</nt> +| <nt def="NT-Enumeration">Enumeration</nt> </rhs> +</prod> +<prod id="NT-NotationType"> +<lhs>NotationType</lhs><rhs>'NOTATION' <nt def="NT-S">S</nt> '(' <nt def="NT-S">S</nt>? <nt +def="NT-Name">Name</nt> (<nt def="NT-S">S</nt>? '|' <nt def="NT-S">S</nt>? <nt +def="NT-Name">Name</nt>)* <nt def="NT-S">S</nt>? ')' </rhs><vc def="notatn"/> +<vc def="OneNotationPer" diff="add"/><vc def="NoNotationEmpty" diff="add"/> +</prod> +<prod id="NT-Enumeration"> +<lhs>Enumeration</lhs><rhs>'(' <nt def="NT-S">S</nt>? <nt def="NT-Nmtoken">Nmtoken</nt> +(<nt def="NT-S">S</nt>? '|' <nt def="NT-S">S</nt>? <nt def="NT-Nmtoken">Nmtoken</nt>)* <nt +def="NT-S">S</nt>? ')'</rhs><vc def="enum"/> +</prod> +</scrap> +<p>A <kw>NOTATION</kw> attribute identifies a <termref def="dt-notation">notation</termref>, +declared in the DTD with associated system and/or public identifiers, to be +used in interpreting the element to which the attribute is attached.</p> +<vcnote id="notatn"><head>Notation Attributes</head><p>Values of this type +must match one of the <titleref href="#Notations">notation</titleref> names +included in the declaration; all notation names in the declaration must be +declared.</p> +</vcnote> +<vcnote id="OneNotationPer" diff="add"><head><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E7">[E7]</loc>One +Notation Per Element Type</head><p>No element type may have more than one <kw>NOTATION</kw> +attribute specified.</p> +</vcnote> +<vcnote id="NoNotationEmpty" diff="add"><head><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E68">[E68]</loc>No +Notation on Empty Element</head><p><termref def="dt-compat">For compatibility</termref>, +an attribute of type <kw>NOTATION</kw> must not be declared on an element +declared <kw>EMPTY</kw>.</p> +</vcnote> +<vcnote id="enum"><head>Enumeration</head><p>Values of this type must match +one of the <nt def="NT-Nmtoken">Nmtoken</nt> tokens in the declaration.</p> +</vcnote> +<p><termref def="dt-interop">For interoperability,</termref> the same <nt +def="NT-Nmtoken">Nmtoken</nt> should not occur more than once in the enumerated +attribute types of a single element type.</p> +</div3> +<div3 id="sec-attr-defaults"> +<head>Attribute Defaults</head> +<p>An <termref def="dt-attdecl">attribute declaration</termref> provides information +on whether the attribute's presence is required, and if not, how an XML processor +should react if a declared attribute is absent in a document.</p> +<scrap lang="ebnf"> +<head>Attribute Defaults</head> +<prodgroup pcw4="14" pcw5="11.5"> +<prod id="NT-DefaultDecl"> +<lhs>DefaultDecl</lhs><rhs>'#REQUIRED' | '#IMPLIED' </rhs> +<rhs>| (('#FIXED' S)? <nt def="NT-AttValue">AttValue</nt>)</rhs><vc def="RequiredAttr"/> +<vc def="defattrvalid"/><wfc def="CleanAttrVals"/><vc def="FixedAttr"/> +</prod> +</prodgroup></scrap> +<p>In an attribute declaration, <kw>#REQUIRED</kw> means that the attribute +must always be provided, <kw>#IMPLIED</kw> that no default value is provided. <!-- not any more!! +<kw>#IMPLIED</kw> means that if the attribute is omitted +from an element of this type, +the XML processor must inform the application +that no value was specified; no constraint is placed on the behavior +of the application. --> <termdef id="dt-default" term="Attribute Default">If +the declaration is neither <kw>#REQUIRED</kw> nor <kw>#IMPLIED</kw>, then +the <nt def="NT-AttValue">AttValue</nt> value contains the declared <term>default</term> +value; the <kw>#FIXED</kw> keyword states that the attribute must always have +the default value. If a default value is declared, when an XML processor encounters +an omitted attribute, it is to behave as though the attribute were present +with the declared default value.</termdef></p> +<vcnote id="RequiredAttr"><head>Required Attribute</head><p>If the default +declaration is the keyword <kw>#REQUIRED</kw>, then the attribute must be +specified for all elements of the type in the attribute-list declaration.</p> +</vcnote> +<vcnote id="defattrvalid"><head>Attribute Default Legal</head><p>The declared +default value must meet the lexical constraints of the declared attribute +type.</p> +</vcnote> +<vcnote id="FixedAttr"><head>Fixed Attribute Default</head><p>If an attribute +has a default value declared with the <kw>#FIXED</kw> keyword, instances of +that attribute must match the default value.</p> +</vcnote> +<p>Examples of attribute-list declarations:</p> +<eg><!ATTLIST termdef + id ID #REQUIRED + name CDATA #IMPLIED> +<!ATTLIST list + type (bullets|ordered|glossary) "ordered"> +<!ATTLIST form + method CDATA #FIXED "POST"></eg> +</div3> +<div3 id="AVNormalize" diff="chg"> +<head><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E70">[E70]</loc>Attribute-Value +Normalization</head> +<p>Before the value of an attribute is passed to the application or checked +for validity, the XML processor must normalize the attribute value by applying +the algorithm below, or by using some other method such that the value passed +to the application is the same as that produced by the algorithm.</p> +<olist> +<item><p>All line breaks must have been normalized on input to #xA as described +in <specref ref="sec-line-ends"/>, so the rest of this algorithm operates +on text normalized in this way.</p></item> +<item><p>Begin with a normalized value consisting of the empty string.</p> +</item> +<item><p>For each character, entity reference, or character reference in the +unnormalized attribute value, beginning with the first and continuing to the +last, do the following:</p> +<ulist> +<item><p>For a character reference, append the referenced character to the +normalized value.</p></item> +<item><p>For an entity reference, recursively apply step 3 of this algorithm +to the replacement text of the entity.</p></item> +<item><p>For a white space character (#x20, #xD, #xA, #x9), append a space +character (#x20) to the normalized value.</p></item> +<item><p>For another character, append the character to the normalized value.</p> +</item> +</ulist> +</item> +</olist> +<p>If the attribute type is not CDATA, then the XML processor must further +process the normalized attribute value by discarding any leading and trailing +space (#x20) characters, and by replacing sequences of space (#x20) characters +by a single space (#x20) character.</p> +<p>Note that if the unnormalized attribute value contains a character reference +to a white space character other than space (#x20), the normalized value contains +the referenced character itself (#xD, #xA or #x9). This contrasts with the +case where the unnormalized value contains a white space character (not a +reference), which is replaced with a space character (#x20) in the normalized +value and also contrasts with the case where the unnormalized value contains +an entity reference whose replacement text contains a white space character; +being recursively processed, the white space character is replaced with a +space character (#x20) in the normalized value.</p> +<p>All attributes for which no declaration has been read should be treated +by a non-validating <phrase diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E95">[E95]</loc>processor</phrase> +as if declared <kw>CDATA</kw>.</p> +<p>Following are examples of attribute normalization. Given the following +declarations:</p> +<eg><!ENTITY d "&#xD;"> +<!ENTITY a "&#xA;"> +<!ENTITY da "&#xD;&#xA;"></eg> +<p>the attribute specifications in the left column below would be normalized +to the character sequences of the middle column if the attribute <att>a</att> +is declared <kw>NMTOKENS</kw> and to those of the right columns if <att>a</att> +is declared <kw>CDATA</kw>.</p> +<table border="1" frame="border"><thead><tr><th>Attribute specification</th> +<th>a is NMTOKENS</th><th>a is CDATA</th></tr></thead><tbody><tr><td><eg>a=" + +xyz"</eg></td><td><code>x y z</code></td><td><code>#x20 #x20 x y z</code></td> +</tr><tr><td><eg>a="&d;&d;A&a;&a;B&da;"</eg></td><td><code>A +#x20 B</code></td><td><code>#x20 #x20 A #x20 #x20 B #x20 #x20</code></td> +</tr><tr><td><eg>a= +"&#xd;&#xd;A&#xa;&#xa;B&#xd;&#xa;"</eg></td><td><code>#xD +#xD A #xA #xA B #xD #xA</code></td><td><code>#xD #xD A #xA #xA B #xD #xD</code></td> +</tr></tbody></table> +<p>Note that the last example is invalid (but well-formed) if <att>a</att> +is declared to be of type <kw>NMTOKENS</kw>.</p> +</div3> +</div2> +<div2 id="sec-condition-sect"> +<head>Conditional Sections</head> +<p><termdef id="dt-cond-section" term="conditional section"> <term>Conditional +sections</term> are portions of the <termref def="dt-doctype">document type +declaration external subset</termref> which are included in, or excluded from, +the logical structure of the DTD based on the keyword which governs them.</termdef></p> +<scrap lang="ebnf"> +<head>Conditional Section</head> +<prodgroup pcw2="9" pcw4="14.5"> +<prod id="NT-conditionalSect"> +<lhs>conditionalSect</lhs><rhs><nt def="NT-includeSect">includeSect</nt> | <nt +def="NT-ignoreSect">ignoreSect</nt> </rhs> +</prod> +<prod id="NT-includeSect"> +<lhs>includeSect</lhs><rhs>'<![' S? 'INCLUDE' S? '[' <nt def="NT-extSubsetDecl">extSubsetDecl</nt> +']]>' </rhs><com><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E90">[E90]</loc></com> +<vc def="condsec-nesting" diff="add"/> +</prod> +<prod id="NT-ignoreSect"> +<lhs>ignoreSect</lhs><rhs>'<![' S? 'IGNORE' S? '[' <nt def="NT-ignoreSectContents">ignoreSectContents</nt>* +']]>'</rhs><com><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E90">[E90]</loc></com> +<vc def="condsec-nesting" diff="add"/> +</prod> +<prod id="NT-ignoreSectContents"> +<lhs>ignoreSectContents</lhs><rhs><nt def="NT-Ignore">Ignore</nt> ('<![' <nt +def="NT-ignoreSectContents">ignoreSectContents</nt> ']]>' <nt def="NT-Ignore">Ignore</nt>)*</rhs> +</prod> +<prod id="NT-Ignore"> +<lhs>Ignore</lhs><rhs><nt def="NT-Char">Char</nt>* - (<nt def="NT-Char">Char</nt>* +('<![' | ']]>') <nt def="NT-Char">Char</nt>*) </rhs> +</prod> +</prodgroup></scrap> +<vcnote id="condsec-nesting" diff="add"><head><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E90">[E90]</loc>Proper +Conditional Section/PE Nesting</head><p>If any of the "<code><![</code>", +"<code>[</code>", or "<code>]]></code>" of a conditional section is contained +in the replacement text for a parameter-entity reference, all of them must +be contained in the same replacement text.</p> +</vcnote> +<p>Like the internal and external DTD subsets, a conditional section may contain +one or more complete declarations, comments, processing instructions, or nested +conditional sections, intermingled with white space.</p> +<p>If the keyword of the conditional section is <kw>INCLUDE</kw>, then the +contents of the conditional section are part of the DTD. If the keyword of +the conditional section is <kw>IGNORE</kw>, then the contents of the conditional +section are not logically part of the DTD. <phrase diff="del"><loc role="erratumref" +href="http://www.w3.org/XML/xml-19980210-errata#E90">[E90]</loc>Note that +for reliable parsing, the contents of even ignored conditional sections must +be read in order to detect nested conditional sections and ensure that the +end of the outermost (ignored) conditional section is properly detected.</phrase> +If a conditional section with a keyword of <kw>INCLUDE</kw> occurs within +a larger conditional section with a keyword of <kw>IGNORE</kw>, both the outer +and the inner conditional sections are ignored.<phrase diff="add"> <loc role="erratumref" +href="http://www.w3.org/XML/xml-19980210-errata#E90">[E90]</loc>The contents +of an ignored conditional section are parsed by ignoring all characters after +the "<code>[</code>" following the keyword, except conditional section starts +"<code><![</code>" and ends "<code>]]></code>", until the matching conditional +section end is found. Parameter entity references are not recognized in this +process.</phrase></p> +<p>If the keyword of the conditional section is a parameter-entity reference, +the parameter entity must be replaced by its content before the processor +decides whether to include or ignore the conditional section.</p> +<p>An example:</p> +<eg><!ENTITY % draft 'INCLUDE' > +<!ENTITY % final 'IGNORE' > + +<![%draft;[ +<!ELEMENT book (comments*, title, body, supplements?)> +]]> +<![%final;[ +<!ELEMENT book (title, body, supplements?)> +]]></eg> +</div2> +<!-- +<div2 id='sec-pass-to-app'> +<head>XML Processor Treatment of Logical Structure</head> +<p>When an XML processor encounters a start-tag, it must make +at least the following information available to the application: +<ulist> +<item> +<p>the element type's generic identifier</p> +</item> +<item> +<p>the names of attributes known to apply to this element type +(validating processors must make available names of all attributes +declared for the element type; non-validating processors must +make available at least the names of the attributes for which +values are specified. +</p> +</item> +</ulist> +</p> +</div2> +--> +</div1> +<!-- &Entities; --> +<div1 id="sec-physical-struct"> +<head>Physical Structures</head> +<p><termdef id="dt-entity" term="Entity">An XML document may consist of one +or many storage units. <phrase diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E6">[E6]</loc>These +are called <term>entities</term>; they all have <term>content</term> and are +all (except for the <termref def="dt-docent">document entity</termref> and +the <termref def="dt-doctype">external DTD subset</termref>) identified by +entity <term>name</term></phrase>.</termdef> Each XML document has one entity +called the <termref def="dt-docent">document entity</termref>, which serves +as the starting point for the <termref def="dt-xml-proc">XML processor</termref> +and may contain the whole document.</p> +<p>Entities may be either parsed or unparsed. <termdef id="dt-parsedent" term="Text Entity">A <term>parsed +entity's</term> contents are referred to as its <termref def="dt-repltext">replacement +text</termref>; this <termref def="dt-text">text</termref> is considered an +integral part of the document.</termdef></p> +<p><termdef id="dt-unparsed" term="Unparsed Entity">An <term>unparsed entity</term> +is a resource whose contents may or may not be <termref def="dt-text">text</termref>, +and if text, <phrase diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E25">[E25]</loc>may +be other than</phrase> XML. Each unparsed entity has an associated <termref +def="dt-notation">notation</termref>, identified by name. Beyond a requirement +that an XML processor make the identifiers for the entity and notation available +to the application, XML places no constraints on the contents of unparsed +entities.</termdef></p> +<p>Parsed entities are invoked by name using entity references; unparsed entities +by name, given in the value of <kw>ENTITY</kw> or <kw>ENTITIES</kw> attributes.</p> +<p><termdef id="gen-entity" term="general entity"><term>General entities</term> +are entities for use within the document content. In this specification, general +entities are sometimes referred to with the unqualified term <emph>entity</emph> +when this leads to no ambiguity.</termdef> <termdef id="dt-PE" term="Parameter entity"><phrase +diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E53">[E53]</loc><term>Parameter +entities</term></phrase> are parsed entities for use within the DTD.</termdef> +These two types of entities use different forms of reference and are recognized +in different contexts. Furthermore, they occupy different namespaces; a parameter +entity and a general entity with the same name are two distinct entities.</p> +<div2 id="sec-references"> +<head>Character and Entity References</head> +<p><termdef id="dt-charref" term="Character Reference"> A <term>character +reference</term> refers to a specific character in the ISO/IEC 10646 character +set, for example one not directly accessible from available input devices.</termdef></p> +<scrap lang="ebnf"> +<head>Character Reference</head> +<prod id="NT-CharRef"> +<lhs>CharRef</lhs><rhs>'&#' [0-9]+ ';' </rhs> +<rhs>| '&hcro;' [0-9a-fA-F]+ ';'</rhs><wfc def="wf-Legalchar"/> +</prod> +</scrap> +<wfcnote id="wf-Legalchar"><head>Legal Character</head><p>Characters referred +to using character references must match the production for <termref def="NT-Char">Char</termref>.</p> +</wfcnote> +<p>If the character reference begins with <quote><code>&#x</code></quote>, +the digits and letters up to the terminating <code>;</code> provide a hexadecimal +representation of the character's code point in ISO/IEC 10646. If it begins +just with <quote><code>&#</code></quote>, the digits up to the terminating <code>;</code> +provide a decimal representation of the character's code point.</p> +<p><termdef id="dt-entref" term="Entity Reference">An <term>entity reference</term> +refers to the content of a named entity.</termdef> <termdef id="dt-GERef" +term="General Entity Reference">References to parsed general entities use +ampersand (<code>&</code>) and semicolon (<code>;</code>) as delimiters.</termdef> <termdef +id="dt-PERef" term="Parameter-entity reference"> <term>Parameter-entity references</term> +use percent-sign (<code>%</code>) and semicolon (<code>;</code>) as delimiters.</termdef></p> +<scrap lang="ebnf"> +<head>Entity Reference</head> +<prod id="NT-Reference"> +<lhs>Reference</lhs><rhs><nt def="NT-EntityRef">EntityRef</nt> | <nt def="NT-CharRef">CharRef</nt></rhs> +</prod> +<prod id="NT-EntityRef"> +<lhs>EntityRef</lhs><rhs>'&' <nt def="NT-Name">Name</nt> ';'</rhs><wfc +def="wf-entdeclared"/><vc def="vc-entdeclared"/><wfc def="textent"/><wfc def="norecursion"/> +</prod> +<prod id="NT-PEReference"> +<lhs>PEReference</lhs><rhs>'%' <nt def="NT-Name">Name</nt> ';'</rhs><vc def="vc-entdeclared"/> +<wfc def="norecursion"/><wfc def="indtd"/> +</prod> +</scrap> +<wfcnote id="wf-entdeclared"><head>Entity Declared</head><p>In a document +without any DTD, a document with only an internal DTD subset which contains +no parameter entity references, or a document with <quote><code>standalone='yes'</code></quote>, <phrase +diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E34">[E34]</loc>for +an entity reference that does not occur within the external subset or a parameter +entity, the <nt def="NT-Name">Name</nt> given in the entity reference must <termref +def="dt-match">match</termref> that in an <titleref href="#sec-entity-decl">entity +declaration</titleref> that does not occur within the external subset or a +parameter entity</phrase>, except that well-formed documents need not declare +any of the following entities: &magicents;. <phrase diff="del"><loc role="erratumref" +href="http://www.w3.org/XML/xml-19980210-errata#E29">[E29]</loc>The declaration +of a parameter entity must precede any reference to it. Similarly, </phrase>The +declaration of a general entity must precede any reference to it which appears +in a default value in an attribute-list declaration.</p> +<p>Note that if entities are declared in the external subset or in external +parameter entities, a non-validating processor is <titleref href="#include-if-valid">not +obligated to</titleref> read and process their declarations; for such documents, +the rule that an entity must be declared is a well-formedness constraint only +if <titleref href="#sec-rmd">standalone='yes'</titleref>.</p> +</wfcnote> +<vcnote id="vc-entdeclared"><head>Entity Declared</head><p>In a document with +an external subset or external parameter entities with <quote><code>standalone='no'</code></quote>, +the <nt def="NT-Name">Name</nt> given in the entity reference must <termref +def="dt-match">match</termref> that in an <titleref href="#sec-entity-decl">entity +declaration</titleref>. For interoperability, valid documents should declare +the entities &magicents;, in the form specified in <specref ref="sec-predefined-ent"/>. +The declaration of a parameter entity must precede any reference to it. Similarly, +the declaration of a general entity must precede any <phrase diff="chg"><loc +role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E92">[E92]</loc>attribute-list +declaration containing a default value with a direct or indirect reference +to that general entity.</phrase></p> +</vcnote> +<!-- FINAL EDIT: is this duplication too clumsy? --> +<wfcnote id="textent"><head>Parsed Entity</head><p>An entity reference must +not contain the name of an <termref def="dt-unparsed">unparsed entity</termref>. +Unparsed entities may be referred to only in <termref def="dt-attrval">attribute +values</termref> declared to be of type <kw>ENTITY</kw> or <kw>ENTITIES</kw>.</p> +</wfcnote> +<wfcnote id="norecursion"><head>No Recursion</head><p>A parsed entity must +not contain a recursive reference to itself, either directly or indirectly.</p> +</wfcnote> +<wfcnote id="indtd"><head>In DTD</head><p>Parameter-entity references may +only appear in the <termref def="dt-doctype">DTD</termref>.</p> +</wfcnote> +<p>Examples of character and entity references:</p> +<eg>Type <key>less-than</key> (&hcro;3C;) to save options. +This document was prepared on &docdate; and +is classified &security-level;.</eg> +<p>Example of a parameter-entity reference:</p> +<eg><![CDATA[<!-- declare the parameter entity "ISOLat2"... --> +<!ENTITY % ISOLat2 + SYSTEM "http://www.xml.com/iso/isolat2-xml.entities" > +<!-- ... now reference it. --> +%ISOLat2;]]></eg> +</div2> +<div2 id="sec-entity-decl"> +<head>Entity Declarations</head> +<p><termdef id="dt-entdecl" term="entity declaration"> Entities are declared +thus:</termdef></p> +<scrap lang="ebnf"> +<head>Entity Declaration</head> +<prodgroup pcw2="5" pcw4="18.5"> +<prod id="NT-EntityDecl"> +<lhs>EntityDecl</lhs><rhs><nt def="NT-GEDecl">GEDecl</nt><!--</rhs><com>General entities</com> +<rhs>--> | <nt def="NT-PEDecl">PEDecl</nt></rhs> +<!--<com>Parameter entities</com>--> +</prod> +<prod id="NT-GEDecl"> +<lhs>GEDecl</lhs><rhs>'<!ENTITY' <nt def="NT-S">S</nt> <nt def="NT-Name">Name</nt> <nt +def="NT-S">S</nt> <nt def="NT-EntityDef">EntityDef</nt> <nt def="NT-S">S</nt>? +'>'</rhs> +</prod> +<prod id="NT-PEDecl"> +<lhs>PEDecl</lhs><rhs>'<!ENTITY' <nt def="NT-S">S</nt> '%' <nt def="NT-S">S</nt> <nt +def="NT-Name">Name</nt> <nt def="NT-S">S</nt> <nt def="NT-PEDef">PEDef</nt> <nt +def="NT-S">S</nt>? '>'</rhs> +<!--<com>Parameter entities</com>--> +</prod> +<prod id="NT-EntityDef"> +<lhs>EntityDef</lhs><rhs><nt def="NT-EntityValue">EntityValue</nt> <!--</rhs> +<rhs>-->| (<nt def="NT-ExternalID">ExternalID</nt> <nt def="NT-NDataDecl">NDataDecl</nt>?)</rhs> +<!-- <nt def='NT-ExternalDef'>ExternalDef</nt></rhs> --> +</prod> +<!-- FINAL EDIT: what happened to WFs here? --> +<prod id="NT-PEDef"> +<lhs>PEDef</lhs><rhs><nt def="NT-EntityValue">EntityValue</nt> | <nt def="NT-ExternalID">ExternalID</nt></rhs> +</prod> +</prodgroup></scrap> +<p>The <nt def="NT-Name">Name</nt> identifies the entity in an <termref def="dt-entref">entity +reference</termref> or, in the case of an unparsed entity, in the value of +an <kw>ENTITY</kw> or <kw>ENTITIES</kw> attribute. If the same entity is declared +more than once, the first declaration encountered is binding; at user option, +an XML processor may issue a warning if entities are declared multiple times.</p> +<div3 id="sec-internal-ent"> +<head>Internal Entities</head> +<p><termdef id="dt-internent" term="Internal Entity Replacement Text">If the +entity definition is an <nt def="NT-EntityValue">EntityValue</nt>, the defined +entity is called an <term>internal entity</term>. There is no separate physical +storage object, and the content of the entity is given in the declaration.</termdef> +Note that some processing of entity and character references in the <termref +def="dt-litentval">literal entity value</termref> may be required to produce +the correct <termref def="dt-repltext">replacement text</termref>: see <specref +ref="intern-replacement"/>.</p> +<p>An internal entity is a <termref def="dt-parsedent">parsed entity</termref>.</p> +<p>Example of an internal entity declaration:</p> +<eg><!ENTITY Pub-Status "This is a pre-release of the + specification."></eg> +</div3> +<div3 id="sec-external-ent"> +<head>External Entities</head> +<p><termdef id="dt-extent" term="External Entity">If the entity is not internal, +it is an <term>external entity</term>, declared as follows:</termdef></p> +<scrap lang="ebnf"> +<head>External Entity Declaration</head> +<!-- +<prod id='NT-ExternalDef'><lhs>ExternalDef</lhs> +<rhs></prod> --> +<prod id="NT-ExternalID"> +<lhs>ExternalID</lhs><rhs>'SYSTEM' <nt def="NT-S">S</nt> <nt def="NT-SystemLiteral">SystemLiteral</nt></rhs> +<rhs>| 'PUBLIC' <nt def="NT-S">S</nt> <nt def="NT-PubidLiteral">PubidLiteral</nt> <nt +def="NT-S">S</nt> <nt def="NT-SystemLiteral">SystemLiteral</nt> </rhs> +</prod> +<prod id="NT-NDataDecl"> +<lhs>NDataDecl</lhs><rhs><nt def="NT-S">S</nt> 'NDATA' <nt def="NT-S">S</nt> <nt +def="NT-Name">Name</nt></rhs><vc def="not-declared"/> +</prod> +</scrap> +<p>If the <nt def="NT-NDataDecl">NDataDecl</nt> is present, this is a general <termref +def="dt-unparsed">unparsed entity</termref>; otherwise it is a parsed entity.</p> +<vcnote id="not-declared"><head>Notation Declared</head><p>The <nt def="NT-Name">Name</nt> +must match the declared name of a <termref def="dt-notation">notation</termref>.</p> +</vcnote> +<p><phrase diff="chg"><termdef id="dt-sysid" term="System Identifier">The <nt +def="NT-SystemLiteral">SystemLiteral</nt> is called the entity's <term>system +identifier</term>. It is a <phrase diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E88">[E88]</loc>URI +reference</phrase><phrase diff="add"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E66">[E66]</loc> +(as defined in <bibref ref="rfc2396"/>, updated by <bibref ref="rfc2732"/>)</phrase>, <loc +role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E76">[E76]</loc>meant +to be dereferenced to obtain input for the XML processor to construct the +entity's replacement text.</termdef> It is an error for a fragment identifier +(beginning with a <code>#</code> character) to be part of a system identifier.</phrase> +Unless otherwise provided by information outside the scope of this specification +(e.g. a special XML element type defined by a particular DTD, or a processing +instruction defined by a particular application specification), relative URIs +are relative to the location of the resource within which the entity declaration +occurs. A URI might thus be relative to the <termref def="dt-docent">document +entity</termref>, to the entity containing the <termref def="dt-doctype">external +DTD subset</termref>, or to some other <termref def="dt-extent">external parameter +entity</termref>.</p> +<p diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E78">[E78]</loc>URI +references require encoding and escaping of certain characters. The disallowed +characters include all non-ASCII characters, plus the excluded characters +listed in Section 2.4 of <bibref ref="rfc2396"/>, except for the number sign +(<code>#</code>) and percent sign (<code>%</code>) characters and the square +bracket characters re-allowed in <bibref ref="rfc2732"/>. Disallowed characters +must be escaped as follows:</p> +<olist diff="add"> +<item><p>Each disallowed character is converted to UTF-8 <bibref ref="rfc2279"/> +as one or more bytes.</p></item> +<item><p>Any octets corresponding to a disallowed character are escaped with +the URI escaping mechanism (that is, converted to <code>%</code><var>HH</var>, +where HH is the hexadecimal notation of the byte value).</p></item> +<item><p>The original character is replaced by the resulting character sequence.</p> +</item> +</olist> +<p><termdef id="dt-pubid" term="Public identifier"> In addition to a system +identifier, an external identifier may include a <term>public identifier</term>.</termdef> +An XML processor attempting to retrieve the entity's content may use the public +identifier to try to generate an alternative <phrase diff="chg"><loc role="erratumref" +href="http://www.w3.org/XML/xml-19980210-errata#E88">[E88]</loc>URI reference</phrase>. +If the processor is unable to do so, it must use the <phrase diff="chg"><loc +role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E88">[E88]</loc>URI +reference</phrase> specified in the system literal. Before a match is attempted, +all strings of white space in the public identifier must be normalized to +single space characters (#x20), and leading and trailing white space must +be removed.</p> +<p>Examples of external entity declarations:</p> +<eg><!ENTITY open-hatch + SYSTEM "http://www.textuality.com/boilerplate/OpenHatch.xml"> +<!ENTITY open-hatch + PUBLIC "-//Textuality//TEXT Standard open-hatch boilerplate//EN" + "http://www.textuality.com/boilerplate/OpenHatch.xml"> +<!ENTITY hatch-pic + SYSTEM "../grafix/OpenHatch.gif" + NDATA gif ></eg> +</div3> +</div2> +<div2 id="TextEntities"> +<head>Parsed Entities</head> +<div3 id="sec-TextDecl"> +<head>The Text Declaration</head> +<p>External parsed entities <phrase diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E107">[E107]</loc>should</phrase +> each begin with a <term>text declaration</term>.</p> +<scrap lang="ebnf"> +<head>Text Declaration</head> +<prodgroup pcw4="12.5" pcw5="13"> +<prod id="NT-TextDecl"> +<lhs>TextDecl</lhs><rhs>&pio; <nt def="NT-VersionInfo">VersionInfo</nt>? <nt +def="NT-EncodingDecl">EncodingDecl</nt> <nt def="NT-S">S</nt>? &pic;</rhs> +</prod> +</prodgroup></scrap> +<p>The text declaration must be provided literally, not by reference to a +parsed entity. No text declaration may appear at any position other than the +beginning of an external parsed entity. <phrase diff="add"><loc role="erratumref" +href="http://www.w3.org/XML/xml-19980210-errata#E94">[E94]</loc>The text declaration +in an external parsed entity is not considered part of its <termref def="dt-repltext">replacement +text</termref>.</phrase></p> +</div3> +<div3 id="wf-entities"> +<head>Well-Formed Parsed Entities</head> +<p>The document entity is well-formed if it matches the production labeled <nt +def="NT-document">document</nt>. An external general parsed entity is well-formed +if it matches the production labeled <nt def="NT-extParsedEnt">extParsedEnt</nt>. <phrase +diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E109">[E109]</loc>All +external parameter entities are well-formed by definition.</phrase></p> +<scrap lang="ebnf"> +<head>Well-Formed External Parsed Entity</head> +<prod id="NT-extParsedEnt"> +<lhs>extParsedEnt</lhs><rhs><nt def="NT-TextDecl">TextDecl</nt>? <nt def="NT-content">content</nt></rhs> +</prod> +<prod id="NT-extPE" diff="del"> +<lhs>extPE</lhs><rhs><nt def="NT-TextDecl">TextDecl</nt>? <nt def="NT-extSubsetDecl">extSubsetDecl</nt></rhs> +<com><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E109">[E109]</loc></com> +</prod> +</scrap> +<p>An internal general parsed entity is well-formed if its replacement text +matches the production labeled <nt def="NT-content">content</nt>. All internal +parameter entities are well-formed by definition.</p> +<p>A consequence of well-formedness in entities is that the logical and physical +structures in an XML document are properly nested; no <termref def="dt-stag">start-tag</termref>, <termref +def="dt-etag">end-tag</termref>, <termref def="dt-empty">empty-element tag</termref>, <termref +def="dt-element">element</termref>, <termref def="dt-comment">comment</termref>, <termref +def="dt-pi">processing instruction</termref>, <termref def="dt-charref">character +reference</termref>, or <termref def="dt-entref">entity reference</termref> +can begin in one entity and end in another.</p> +</div3> +<div3 id="charencoding"> +<head>Character Encoding in Entities</head> +<p>Each external parsed entity in an XML document may use a different encoding +for its characters. All XML processors must be able to read entities in <phrase +diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E56">[E56]</loc>both +the UTF-8 and UTF-16 encodings.</phrase> <phrase diff="add"><loc role="erratumref" +href="http://www.w3.org/XML/xml-19980210-errata#E77">[E77]</loc>The terms <quote>UTF-8</quote> +and <quote>UTF-16</quote> in this specification do not apply to character +encodings with any other labels, even if the encodings or labels are very +similar to UTF-8 or UTF-16.</phrase></p> +<p>Entities encoded in UTF-16 must begin with the Byte Order Mark described +by <phrase diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E67">[E67]</loc>Annex +F of <bibref ref="ISO10646"/>, Annex H of <bibref ref="ISO10646-2000"/>, section +2.4 of <bibref ref="Unicode"/>, and section 2.7 of <bibref ref="Unicode3"/></phrase> +(the ZERO WIDTH NO-BREAK SPACE character, #xFEFF). This is an encoding signature, +not part of either the markup or the character data of the XML document. XML +processors must be able to use this character to differentiate between UTF-8 +and UTF-16 encoded documents.</p> +<p>Although an XML processor is required to read only entities in the UTF-8 +and UTF-16 encodings, it is recognized that other encodings are used around +the world, and it may be desired for XML processors to read entities that +use them. <phrase diff="add"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E47">[E47]</loc>In +the absence of external character encoding information (such as MIME headers),</phrase> +parsed entities which are stored in an encoding other than UTF-8 or UTF-16 +must begin with a text declaration <phrase diff="add">(see <specref ref="sec-TextDecl"/>) </phrase>containing +an encoding declaration:</p> +<scrap lang="ebnf"> +<head>Encoding Declaration</head> +<prod id="NT-EncodingDecl"> +<lhs>EncodingDecl</lhs><rhs><nt def="NT-S">S</nt> 'encoding' <nt def="NT-Eq">Eq</nt> +('"' <nt def="NT-EncName">EncName</nt> '"' | "'" <nt def="NT-EncName">EncName</nt> +"'" ) </rhs> +</prod> +<prod id="NT-EncName"> +<lhs>EncName</lhs><rhs>[A-Za-z] ([A-Za-z0-9._] | '-')*</rhs><com>Encoding +name contains only Latin characters</com> +</prod> +</scrap> +<p>In the <termref def="dt-docent">document entity</termref>, the encoding +declaration is part of the <termref def="dt-xmldecl">XML declaration</termref>. +The <nt def="NT-EncName">EncName</nt> is the name of the encoding used.</p> +<!-- FINAL EDIT: check name of IANA and charset names --> +<p>In an encoding declaration, the values <quote><code>UTF-8</code></quote>, <quote><code>UTF-16</code></quote>, <quote><code>ISO-10646-UCS-2</code +></quote>, and <quote><code>ISO-10646-UCS-4</code></quote> should be used +for the various encodings and transformations of Unicode / ISO/IEC 10646, +the values <quote><code>ISO-8859-1</code></quote>, <quote><code>ISO-8859-2</code></quote>, +... <loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E106">[E106]</loc><phrase +diff="chg"><quote><code>ISO-8859-</code><var>n</var></quote> (where <var>n</var> +is the part number)</phrase> should be used for the parts of ISO 8859, and +the values <quote><code>ISO-2022-JP</code></quote>, <quote><code>Shift_JIS</code></quote>, +and <quote><code>EUC-JP</code></quote> should be used for the various encoded +forms of JIS X-0208-1997. <phrase diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E57">[E57]</loc>It +is recommended that character encodings registered (as <emph>charset</emph>s) +with the Internet Assigned Numbers Authority <phrase diff="chg"><loc role="erratumref" +href="http://www.w3.org/XML/xml-19980210-errata#E58">[E58]</loc><bibref ref="IANA"/></phrase>, +other than those just listed, be referred to using their registered names; +other encodings should use names starting with an <quote>x-</quote> prefix. +XML processors should match character encoding names in a case-insensitive +way and should either interpret an IANA-registered name as the encoding registered +at IANA for that name or treat it as unknown (processors are, of course, not +required to support all IANA-registered encodings).</phrase></p> +<p>In the absence of information provided by an external transport protocol +(e.g. HTTP or MIME), it is an <termref def="dt-error">error</termref> for +an entity including an encoding declaration to be presented to the XML processor +in an encoding other than that named in the declaration, <phrase diff="del"><loc +role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E5">[E5]</loc>for +an encoding declaration to occur other than at the beginning of an external +entity, </phrase>or for an entity which begins with neither a Byte Order Mark +nor an encoding declaration to use an encoding other than UTF-8. Note that +since ASCII is a subset of UTF-8, ordinary ASCII entities do not strictly +need an encoding declaration.</p> +<p diff="add"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E5">[E5]</loc>It +is <phrase diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E36">[E36]</loc>a +fatal</phrase> error for a <nt def="NT-TextDecl">TextDecl</nt> to occur other +than at the beginning of an external entity.</p> +<p>It is a <termref def="dt-fatal">fatal error</termref> when an XML processor +encounters an entity with an encoding that it is unable to process. <phrase +diff="add"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E79">[E79]</loc>It +is a fatal error if an XML entity is determined (via default, encoding declaration, +or higher-level protocol) to be in a certain encoding but contains octet sequences +that are not legal in that encoding. It is also a fatal error if an XML entity +contains no encoding declaration and its content is not legal UTF-8 or UTF-16.</phrase></p> +<p>Examples of <phrase diff="add"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E23">[E23]</loc>text +declarations containing </phrase>encoding declarations:</p> +<eg><?xml encoding='UTF-8'?> +<?xml encoding='EUC-JP'?></eg> +</div3> +</div2> +<div2 id="entproc"> +<head>XML Processor Treatment of Entities and References</head> +<p>The table below summarizes the contexts in which character references, +entity references, and invocations of unparsed entities might appear and the +required behavior of an <termref def="dt-xml-proc">XML processor</termref> +in each case. The labels in the leftmost column describe the recognition context: <glist> +<gitem><label>Reference in Content</label> +<def> +<p>as a reference anywhere after the <termref def="dt-stag">start-tag</termref> +and before the <termref def="dt-etag">end-tag</termref> of an element; corresponds +to the nonterminal <nt def="NT-content">content</nt>.</p> +</def></gitem> +<gitem><label>Reference in Attribute Value</label> +<def> +<p>as a reference within either the value of an attribute in a <termref def="dt-stag">start-tag</termref>, +or a default value in an <termref def="dt-attdecl">attribute declaration</termref>; +corresponds to the nonterminal <nt def="NT-AttValue">AttValue</nt>.</p> +</def></gitem> +<gitem><label>Occurs as Attribute Value</label> +<def> +<p>as a <nt def="NT-Name">Name</nt>, not a reference, appearing either as +the value of an attribute which has been declared as type <kw>ENTITY</kw>, +or as one of the space-separated tokens in the value of an attribute which +has been declared as type <kw>ENTITIES</kw>.</p> +</def></gitem> +<gitem><label>Reference in Entity Value</label> +<def> +<p>as a reference within a parameter or internal entity's <termref def="dt-litentval">literal +entity value</termref> in the entity's declaration; corresponds to the nonterminal <nt +def="NT-EntityValue">EntityValue</nt>.</p> +</def></gitem> +<gitem><label>Reference in DTD</label> +<def> +<p diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E90">[E90]</loc>as +a reference within either the internal or external subsets of the <termref +def="dt-doctype">DTD</termref>, but outside of an <nt def="NT-EntityValue">EntityValue</nt>, <nt +def="NT-AttValue">AttValue</nt>, <nt def="NT-PI">PI</nt>, <nt def="NT-Comment">Comment</nt>, <nt +def="NT-SystemLiteral">SystemLiteral</nt>, <nt def="NT-PubidLiteral">PubidLiteral</nt>, +or the contents of an ignored conditional section (see <specref ref="sec-condition-sect"/>).</p> +<p>.</p> +</def></gitem> +</glist></p> +<table border="1" frame="border" cellpadding="7"><tbody align="center"><tr> +<td rowspan="2" colspan="1"></td><td colspan="4" align="center" valign="bottom">Entity +Type</td><td rowspan="2" align="center">Character</td></tr><tr align="center" +valign="bottom"><td>Parameter</td><td>Internal General</td><td>External Parsed +General</td><td>Unparsed</td></tr><tr align="center" valign="middle"><td align="right">Reference +in Content</td><td><titleref href="#not-recognized">Not recognized</titleref></td> +<td><titleref href="#included">Included</titleref></td><td><titleref href="#include-if-valid">Included +if validating</titleref></td><td><titleref href="#forbidden">Forbidden</titleref></td> +<td><titleref href="#included">Included</titleref></td></tr><tr align="center" +valign="middle"><td align="right">Reference in Attribute Value</td><td><titleref +href="#not-recognized">Not recognized</titleref></td><td><titleref href="#inliteral">Included +in literal</titleref></td><td><titleref href="#forbidden">Forbidden</titleref></td> +<td><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E51">[E51]</loc><titleref +diff="chg" href="#forbidden">Forbidden</titleref></td><td><titleref href="#included">Included</titleref></td> +</tr><tr align="center" valign="middle"><td align="right">Occurs as Attribute +Value</td><td><titleref href="#not-recognized">Not recognized</titleref></td> +<td><titleref href="#forbidden">Forbidden</titleref></td><td><loc role="erratumref" +href="http://www.w3.org/XML/xml-19980210-errata#E51">[E51]</loc><titleref +diff="chg" href="#forbidden">Forbidden</titleref></td><td><titleref href="#notify">Notify</titleref></td> +<td><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E51">[E51]</loc><titleref +diff="chg" href="#not-recognized">Not recognized</titleref></td></tr><tr align="center" +valign="middle"><td align="right">Reference in EntityValue</td><td><titleref +href="#inliteral">Included in literal</titleref></td><td><titleref href="#bypass">Bypassed</titleref></td> +<td><titleref href="#bypass">Bypassed</titleref></td><td><titleref href="#forbidden">Forbidden</titleref></td> +<td><titleref href="#included">Included</titleref></td></tr><tr align="center" +valign="middle"><td align="right">Reference in DTD</td><td><titleref href="#as-PE">Included +as PE</titleref></td><td><titleref href="#forbidden">Forbidden</titleref></td> +<td><titleref href="#forbidden">Forbidden</titleref></td><td><titleref href="#forbidden">Forbidden</titleref></td> +<td><titleref href="#forbidden">Forbidden</titleref></td></tr></tbody></table> +<div3 id="not-recognized"> +<head>Not Recognized</head> +<p>Outside the DTD, the <code>%</code> character has no special significance; +thus, what would be parameter entity references in the DTD are not recognized +as markup in <nt def="NT-content">content</nt>. Similarly, the names of unparsed +entities are not recognized except when they appear in the value of an appropriately +declared attribute.</p> +</div3> +<div3 id="included"> +<head>Included</head> +<p><termdef id="dt-include" term="Include">An entity is <term>included</term> +when its <termref def="dt-repltext">replacement text</termref> is retrieved +and processed, in place of the reference itself, as though it were part of +the document at the location the reference was recognized.</termdef> The replacement +text may contain both <termref def="dt-chardata">character data</termref> +and (except for parameter entities) <termref def="dt-markup">markup</termref>, +which must be recognized in the usual way<phrase diff="del"><loc role="erratumref" +href="http://www.w3.org/XML/xml-19980210-errata#E65">[E65]</loc>, except that +the replacement text of entities used to escape markup delimiters (the entities &magicents;) +is always treated as data</phrase>. (The string <quote><code>AT&amp;T;</code></quote> +expands to <quote><code>AT&T;</code></quote> and the remaining ampersand +is not recognized as an entity-reference delimiter.) A character reference +is <term>included</term> when the indicated character is processed in place +of the reference itself. </p> +</div3> +<div3 id="include-if-valid"> +<head>Included If Validating</head> +<p>When an XML processor recognizes a reference to a parsed entity, in order +to <termref def="dt-valid">validate</termref> the document, the processor +must <termref def="dt-include">include</termref> its replacement text. If +the entity is external, and the processor is not attempting to validate the +XML document, the processor <termref def="dt-may">may</termref>, but need +not, include the entity's replacement text. If a non-validating <phrase diff="chg"><loc +role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E95">[E95]</loc>processor</phrase> +does not include the replacement text, it must inform the application that +it recognized, but did not read, the entity.</p> +<p>This rule is based on the recognition that the automatic inclusion provided +by the SGML and XML entity mechanism, primarily designed to support modularity +in authoring, is not necessarily appropriate for other applications, in particular +document browsing. Browsers, for example, when encountering an external parsed +entity reference, might choose to provide a visual indication of the entity's +presence and retrieve it for display only on demand.</p> +</div3> +<div3 id="forbidden"> +<head>Forbidden</head> +<p>The following are forbidden, and constitute <termref def="dt-fatal">fatal</termref> +errors:</p> +<ulist> +<item><p>the appearance of a reference to an <termref def="dt-unparsed">unparsed +entity</termref>.</p></item> +<item><p>the appearance of any character or general-entity reference in the +DTD except within an <nt def="NT-EntityValue">EntityValue</nt> or <nt def="NT-AttValue">AttValue</nt>.</p> +</item> +<item><p>a reference to an external entity in an attribute value.</p></item> +</ulist> +</div3> +<div3 id="inliteral"> +<head>Included in Literal</head> +<p>When an <termref def="dt-entref">entity reference</termref> appears in +an attribute value, or a parameter entity reference appears in a literal entity +value, its <termref def="dt-repltext">replacement text</termref> is processed +in place of the reference itself as though it were part of the document at +the location the reference was recognized, except that a single or double +quote character in the replacement text is always treated as a normal data +character and will not terminate the literal. For example, this is well-formed:</p> +<eg diff="chg"><!-- <loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E4">[E4]</loc> --> +<![CDATA[<!ENTITY % YN '"Yes"' > +<!ENTITY WhatHeSaid "He said %YN;" >]]></eg> +<p>while this is not:</p> +<eg><!ENTITY EndAttr "27'" > +<element attribute='a-&EndAttr;></eg> +</div3> +<div3 id="notify"> +<head>Notify</head> +<p>When the name of an <termref def="dt-unparsed">unparsed entity</termref> +appears as a token in the value of an attribute of declared type <kw>ENTITY</kw> +or <kw>ENTITIES</kw>, a validating processor must inform the application of +the <termref def="dt-sysid">system</termref> and <termref def="dt-pubid">public</termref> +(if any) identifiers for both the entity and its associated <termref def="dt-notation">notation</termref>.</p> +</div3> +<div3 id="bypass"> +<head>Bypassed</head> +<p>When a general entity reference appears in the <nt def="NT-EntityValue">EntityValue</nt> +in an entity declaration, it is bypassed and left as is.</p> +</div3> +<div3 id="as-PE"> +<head>Included as PE</head> +<p>Just as with external parsed entities, parameter entities need only be <titleref +href="#include-if-valid">included if validating</titleref>. When a parameter-entity +reference is recognized in the DTD and included, its <termref def="dt-repltext">replacement +text</termref> is enlarged by the attachment of one leading and one following +space (#x20) character; the intent is to constrain the replacement text of +parameter entities to contain an integral number of grammatical tokens in +the DTD. <phrase diff="add"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E96">[E96]</loc>This +behavior does not apply to parameter entity references within entity values; +these are described in <specref ref="inliteral"/>.</phrase></p> +</div3> +</div2> +<div2 id="intern-replacement"> +<head>Construction of Internal Entity Replacement Text</head> +<p>In discussing the treatment of internal entities, it is useful to distinguish +two forms of the entity's value. <termdef id="dt-litentval" term="Literal Entity Value">The <term>literal +entity value</term> is the quoted string actually present in the entity declaration, +corresponding to the non-terminal <nt def="NT-EntityValue">EntityValue</nt>.</termdef> <termdef +id="dt-repltext" term="Replacement Text">The <term>replacement text</term> +is the content of the entity, after replacement of character references and +parameter-entity references.</termdef></p> +<p>The literal entity value as given in an internal entity declaration (<nt +def="NT-EntityValue">EntityValue</nt>) may contain character, parameter-entity, +and general-entity references. Such references must be contained entirely +within the literal entity value. The actual replacement text that is <termref +def="dt-include">included</termref> as described above must contain the <emph>replacement +text</emph> of any parameter entities referred to, and must contain the character +referred to, in place of any character references in the literal entity value; +however, general-entity references must be left as-is, unexpanded. For example, +given the following declarations:</p> +<eg><![CDATA[<!ENTITY % pub "Éditions Gallimard" > +<!ENTITY rights "All rights reserved" > +<!ENTITY book "La Peste: Albert Camus, +© 1947 %pub;. &rights;" >]]></eg> +<p>then the replacement text for the entity <quote><code>book</code></quote> +is:</p> +<eg>La Peste: Albert Camus, +© 1947 Éditions Gallimard. &rights;</eg> +<p>The general-entity reference <quote><code>&rights;</code></quote> would +be expanded should the reference <quote><code>&book;</code></quote> appear +in the document's content or an attribute value.</p> +<p>These simple rules may have complex interactions; for a detailed discussion +of a difficult example, see <specref ref="sec-entexpand"/>.</p> +</div2> +<div2 id="sec-predefined-ent"> +<head>Predefined Entities</head> +<p><termdef id="dt-escape" term="escape">Entity and character references can +both be used to <term>escape</term> the left angle bracket, ampersand, and +other delimiters. A set of general entities (&magicents;) is specified for +this purpose. Numeric character references may also be used; they are expanded +immediately when recognized and must be treated as character data, so the +numeric character references <quote><code>&#60;</code></quote> and <quote><code>&#38;</code></quote> +may be used to escape <code><</code> and <code>&</code> when they occur +in character data.</termdef></p> +<p>All XML processors must recognize these entities whether they are declared +or not. <termref def="dt-interop">For interoperability</termref>, valid XML +documents should declare these entities, like any others, before using them. <phrase +diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E80">[E80]</loc>If +the entities <code>lt</code> or <code>amp</code> are declared, they must be +declared as internal entities whose replacement text is a character reference +to the <phrase diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E103">[E103]</loc>respective +character (less-than sign or ampersand)</phrase> being escaped; the double +escaping is required for these entities so that references to them produce +a well-formed result. If the entities <code>gt</code>, <code>apos</code>, +or <code>quot</code> are declared, they must be declared as internal entities +whose replacement text is the single character being escaped (or a character +reference to that character; the double escaping here is unnecessary but harmless). +For example:</phrase></p> +<eg><![CDATA[<!ENTITY lt "&#60;"> +<!ENTITY gt ">"> +<!ENTITY amp "&#38;"> +<!ENTITY apos "'"> +<!ENTITY quot """>]]></eg> +<p diff="del">Note that the <code><</code> and <code>&</code> characters +in the declarations of <quote><code>lt</code></quote> and <quote><code>amp</code></quote> +are doubly escaped to meet the requirement that entity replacement be well-formed.</p> +</div2> +<div2 id="Notations"> +<head>Notation Declarations</head> +<p><termdef id="dt-notation" term="Notation"><term>Notations</term> identify +by name the format of <termref def="dt-extent">unparsed entities</termref>, +the format of elements which bear a notation attribute, or the application +to which a <termref def="dt-pi">processing instruction</termref> is addressed.</termdef></p> +<p><termdef id="dt-notdecl" term="Notation Declaration"> <term>Notation declarations</term> +provide a name for the notation, for use in entity and attribute-list declarations +and in attribute specifications, and an external identifier for the notation +which may allow an XML processor or its client application to locate a helper +application capable of processing data in the given notation.</termdef></p> +<scrap lang="ebnf"> +<head>Notation Declarations</head> +<prod id="NT-NotationDecl"> +<lhs>NotationDecl</lhs><rhs>'<!NOTATION' <nt def="NT-S">S</nt> <nt def="NT-Name">Name</nt> <nt +def="NT-S">S</nt> (<nt def="NT-ExternalID">ExternalID</nt> | <nt def="NT-PublicID">PublicID</nt>) <nt +def="NT-S">S</nt>? '>'</rhs><vc def="UniqueNotationName" diff="add"/> +</prod> +<prod id="NT-PublicID"> +<lhs>PublicID</lhs><rhs>'PUBLIC' <nt def="NT-S">S</nt> <nt def="NT-PubidLiteral">PubidLiteral</nt> </rhs> +</prod> +</scrap> +<vcnote id="UniqueNotationName" diff="add"><head><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E22">[E22]</loc>Unique +Notation Name</head><p>Only one notation declaration can declare a given <nt +def="NT-Name">Name</nt>.</p> +</vcnote> +<p>XML processors must provide applications with the name and external identifier(s) +of any notation declared and referred to in an attribute value, attribute +definition, or entity declaration. They may additionally resolve the external +identifier into the <termref def="dt-sysid">system identifier</termref>, file +name, or other information needed to allow the application to call a processor +for data in the notation described. (It is not an error, however, for XML +documents to declare and refer to notations for which notation-specific applications +are not available on the system where the XML processor or application is +running.)</p> +</div2> +<div2 id="sec-doc-entity"> +<head>Document Entity</head> +<p><termdef id="dt-docent" term="Document Entity">The <term>document entity</term> +serves as the root of the entity tree and a starting-point for an <termref +def="dt-xml-proc">XML processor</termref>.</termdef> This specification does +not specify how the document entity is to be located by an XML processor; +unlike other entities, the document entity has no name and might well appear +on a processor input stream without any identification at all.</p> +</div2> +</div1> +<!-- &Conformance; --> +<div1 id="sec-conformance"> +<head>Conformance</head> +<div2 id="proc-types"> +<head>Validating and Non-Validating Processors</head> +<p>Conforming <termref def="dt-xml-proc">XML processors</termref> fall into +two classes: validating and non-validating.</p> +<p>Validating and non-validating processors alike must report violations of +this specification's well-formedness constraints in the content of the <termref +def="dt-docent">document entity</termref> and any other <termref def="dt-parsedent">parsed +entities</termref> that they read.</p> +<p><termdef id="dt-validating" term="Validating Processor"><term>Validating +processors</term> must<phrase diff="add"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E21">[E21]</loc>, +at user option,</phrase> report violations of the constraints expressed by +the declarations in the <termref def="dt-doctype">DTD</termref>, and failures +to fulfill the validity constraints given in this specification.</termdef> +To accomplish this, validating XML processors must read and process the entire +DTD and all external parsed entities referenced in the document.</p> +<p>Non-validating processors are required to check only the <termref def="dt-docent">document +entity</termref>, including the entire internal DTD subset, for well-formedness. <termdef +id="dt-use-mdecl" term="Process Declarations"> While they are not required +to check the document for validity, they are required to <term>process</term> +all the declarations they read in the internal DTD subset and in any parameter +entity that they read, up to the first reference to a parameter entity that +they do <emph>not</emph> read; that is to say, they must use the information +in those declarations to <titleref href="#AVNormalize">normalize</titleref> +attribute values, <titleref href="#included">include</titleref> the replacement +text of internal entities, and supply <titleref href="#sec-attr-defaults">default +attribute values</titleref>.</termdef> <phrase diff="add"><loc role="erratumref" +href="http://www.w3.org/XML/xml-19980210-errata#E33">[E33]</loc>Except when <code>standalone="yes"</code>, </phrase>they +must not <termref def="dt-use-mdecl">process</termref> <termref def="dt-entdecl">entity +declarations</termref> or <termref def="dt-attdecl">attribute-list declarations</termref> +encountered after a reference to a parameter entity that is not read, since +the entity may have contained overriding declarations.</p> +</div2> +<div2 id="safe-behavior"> +<head>Using XML Processors</head> +<p>The behavior of a validating XML processor is highly predictable; it must +read every piece of a document and report all well-formedness and validity +violations. Less is required of a non-validating processor; it need not read +any part of the document other than the document entity. This has two effects +that may be important to users of XML processors:</p> +<ulist> +<item><p>Certain well-formedness errors, specifically those that require reading +external entities, may not be detected by a non-validating processor. Examples +include the constraints entitled <titleref href="#wf-entdeclared">Entity Declared</titleref>, <titleref +href="#textent">Parsed Entity</titleref>, and <titleref href="#norecursion">No +Recursion</titleref>, as well as some of the cases described as <titleref +href="#forbidden">forbidden</titleref> in <specref ref="entproc"/>.</p></item> +<item><p>The information passed from the processor to the application may +vary, depending on whether the processor reads parameter and external entities. +For example, a non-validating processor may not <titleref href="#AVNormalize">normalize</titleref> +attribute values, <titleref href="#included">include</titleref> the replacement +text of internal entities, or supply <titleref href="#sec-attr-defaults">default +attribute values</titleref>, where doing so depends on having read declarations +in external or parameter entities.</p></item> +</ulist> +<p>For maximum reliability in interoperating between different XML processors, +applications which use non-validating processors should not rely on any behaviors +not required of such processors. Applications which require facilities such +as the use of default attributes or internal entities which are declared in +external entities should use validating XML processors.</p> +</div2> +</div1> +<div1 id="sec-notation"> +<head>Notation</head> +<p>The formal grammar of XML is given in this specification using a simple +Extended Backus-Naur Form (EBNF) notation. Each rule in the grammar defines +one symbol, in the form</p> +<eg>symbol ::= expression</eg> +<p>Symbols are written with an initial capital letter if they are <phrase +diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E42">[E42]</loc>the +start symbol of a regular language,</phrase> otherwise with an initial lower +case letter. Literal strings are quoted.</p> +<p>Within the expression on the right-hand side of a rule, the following expressions +are used to match strings of one or more characters: <glist> +<gitem><label><code>#xN</code></label> +<def> +<p>where <code>N</code> is a hexadecimal integer, the expression matches the +character in ISO/IEC 10646 whose canonical (UCS-4) code value, when interpreted +as an unsigned binary number, has the value indicated. The number of leading +zeros in the <code>#xN</code> form is insignificant; the number of leading +zeros in the corresponding code value is governed by the character encoding +in use and is not significant for XML.</p> +</def></gitem> +<gitem><label><code>[a-zA-Z]</code>, <code>[#xN-#xN]</code></label> +<def> +<p>matches any <phrase diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E93">[E93]</loc><nt +def="NT-Char">Char</nt></phrase> with a value in the range(s) indicated (inclusive).</p> +</def></gitem> +<gitem diff="add"><label><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E3">[E3]</loc><code>[abc]</code>, <code>[#xN#xN#xN]</code +></label> +<def> +<p>matches any <nt def="NT-Char">Char</nt> with a value among the characters +enumerated. Enumerations and ranges can be mixed in one set of brackets.</p> +</def></gitem> +<gitem><label><code>[^a-z]</code>, <code>[^#xN-#xN]</code></label> +<def> +<p>matches any <phrase diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E93">[E93]</loc><nt +def="NT-Char">Char</nt></phrase> with a value <emph>outside</emph> the range +indicated.</p> +</def></gitem> +<gitem><label><code>[^abc]</code>, <code>[^#xN#xN#xN]</code></label> +<def> +<p>matches any <phrase diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E93">[E93]</loc><nt +def="NT-Char">Char</nt></phrase> with a value not among the characters given. <phrase +diff="add"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E3">[E3]</loc>Enumerations +and ranges of forbidden values can be mixed in one set of brackets.</phrase></p> +</def></gitem> +<gitem><label><code>"string"</code></label> +<def> +<p>matches a literal string <termref def="dt-match">matching</termref> that +given inside the double quotes.</p> +</def></gitem> +<gitem><label><code>'string'</code></label> +<def> +<p>matches a literal string <termref def="dt-match">matching</termref> that +given inside the single quotes.</p> +</def></gitem> +</glist> These symbols may be combined to match more complex patterns as follows, +where <code>A</code> and <code>B</code> represent simple expressions: <glist> +<gitem><label>(<code>expression</code>)</label> +<def> +<p><code>expression</code> is treated as a unit and may be combined as described +in this list.</p> +</def></gitem> +<gitem><label><code>A?</code></label> +<def> +<p>matches <code>A</code> or nothing; optional <code>A</code>.</p> +</def></gitem> +<gitem><label><code>A B</code></label> +<def> +<p>matches <code>A</code> followed by <code>B</code>. <phrase diff="add"><loc +role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E20">[E20]</loc>This +operator has higher precedence than alternation; thus <code>A B | C D</code> +is identical to <code>(A B) | (C D)</code>.</phrase></p> +</def></gitem> +<gitem><label><code>A | B</code></label> +<def> +<p>matches <code>A</code> or <code>B</code> but not both.</p> +</def></gitem> +<gitem><label><code>A - B</code></label> +<def> +<p>matches any string that matches <code>A</code> but does not match <code>B</code>.</p> +</def></gitem> +<gitem><label><code>A+</code></label> +<def> +<p>matches one or more occurrences of <code>A</code>.<phrase diff="add"><loc +role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E20">[E20]</loc>Concatenation +has higher precedence than alternation; thus <code>A+ | B+</code> is identical +to <code>(A+) | (B+)</code>.</phrase></p> +</def></gitem> +<gitem><label><code>A*</code></label> +<def> +<p>matches zero or more occurrences of <code>A</code>. <phrase diff="add"><loc +role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E20">[E20]</loc>Concatenation +has higher precedence than alternation; thus <code>A* | B*</code> is identical +to <code>(A*) | (B*)</code>.</phrase></p> +</def></gitem> +</glist> Other notations used in the productions are: <glist> +<gitem><label><code>/* ... */</code></label> +<def> +<p>comment.</p> +</def></gitem> +<gitem><label><code>[ wfc: ... ]</code></label> +<def> +<p>well-formedness constraint; this identifies by name a constraint on <termref +def="dt-wellformed">well-formed</termref> documents associated with a production.</p> +</def></gitem> +<gitem><label><code>[ vc: ... ]</code></label> +<def> +<p>validity constraint; this identifies by name a constraint on <termref def="dt-valid">valid</termref> +documents associated with a production.</p> +</def></gitem> +</glist></p> +</div1> +</body><back> +<!-- &SGML; --> +<!-- &Biblio; --> +<div1 id="sec-bibliography"> +<head>References</head> +<div2 id="sec-existing-stds"> +<head>Normative References</head> +<blist> +<bibl id="IANA" diff="chg" key="IANA-CHARSETS"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E58">[E58]</loc>(Internet +Assigned Numbers Authority) <titleref>Official Names for Character Sets</titleref>, +ed. Keld Simonsen et al. See <loc href="ftp://ftp.isi.edu/in-notes/iana/assignments/character-sets">ftp://ftp.isi.edu/in-notes/iana/assignments/character-sets</loc +>. </bibl> +<bibl id="RFC1766" href="http://www.ietf.org/rfc/rfc1766.txt" key="IETF RFC 1766">IETF +(Internet Engineering Task Force). <titleref>RFC 1766: Tags for the Identification +of Languages</titleref>, ed. H. Alvestrand. 1995.</bibl> +<bibl id="ISO639-old" diff="del" key="ISO 639"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E38">[E38]</loc> +(International Organization for Standardization). <titleref>ISO 639:1988 (E). +Code for the representation of names of languages.</titleref> [Geneva]: International +Organization for Standardization, 1988.</bibl> +<bibl id="ISO3166-old" diff="del" key="ISO 3166"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E38">[E38]</loc> +(International Organization for Standardization). <titleref>ISO 3166-1:1997 +(E). Codes for the representation of names of countries and their subdivisions — +Part 1: Country codes</titleref> [Geneva]: International Organization for +Standardization, 1997.</bibl> +<bibl id="ISO10646" key="ISO/IEC 10646">ISO (International Organization for +Standardization). <titleref>ISO/IEC 10646-1993 (E). Information technology — +Universal Multiple-Octet Coded Character Set (UCS) — Part 1: Architecture +and Basic Multilingual Plane.</titleref> [Geneva]: International Organization +for Standardization, 1993 (plus amendments AM 1 through AM 7).</bibl> +<bibl id="ISO10646-2000" diff="add" key="ISO/IEC 10646-2000"><loc role="erratumref" +href="http://www.w3.org/XML/xml-19980210-errata#E67">[E67]</loc> ISO (International +Organization for Standardization). <titleref>ISO/IEC 10646-1:2000. Information +technology — Universal Multiple-Octet Coded Character Set (UCS) — +Part 1: Architecture and Basic Multilingual Plane.</titleref> [Geneva]: International +Organization for Standardization, 2000.</bibl> +<bibl id="Unicode" key="Unicode">The Unicode Consortium. <emph>The Unicode +Standard, Version 2.0.</emph> Reading, Mass.: Addison-Wesley Developers Press, +1996.</bibl> +<bibl id="Unicode3" diff="add" key="Unicode3"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E67">[E67]</loc> +The Unicode Consortium. <emph>The Unicode Standard, Version 3.0.</emph> Reading, +Mass.: Addison-Wesley Developers Press, 2000. ISBN 0-201-61633-5.</bibl> +</blist></div2> +<div2 id="null"> +<!-- +ID made "null" to match its previous value in the First +Edition; it's odd, but if there's no set value, the stylesheet +currently generates an odd string that would be backwards +incompatible with any references anyone might have made before. +--> +<head>Other References</head> +<blist> +<bibl id="Aho" key="Aho/Ullman">Aho, Alfred V., Ravi Sethi, and Jeffrey D. +Ullman. <titleref>Compilers: Principles, Techniques, and Tools</titleref>. +Reading: Addison-Wesley, 1986, rpt. corr. 1988.</bibl> +<bibl id="Berners-Lee" key="Berners-Lee et al."> Berners-Lee, T., R. Fielding, +and L. Masinter. <titleref>Uniform Resource Identifiers (URI): Generic Syntax +and Semantics</titleref>. 1997. (Work in progress; see updates to RFC1738.)</bibl> +<bibl id="ABK" diff="chg" key="Brüggemann-Klein"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E2">[E2]</loc>Brüggemann-Klein, +Anne. Formal Models in Document Processing. Habilitationsschrift. Faculty +of Mathematics at the University of Freiburg, 1993. (See <loc href="ftp://ftp.informatik.uni-freiburg.de/documents/papers/brueggem/habil.ps">ftp://ftp.informatik.uni-freiburg.de/documents/papers/brueggem/habil.ps</loc +>.)</bibl> +<bibl id="ABKDW" diff="chg" key="Brüggemann-Klein and Wood"><loc role="erratumref" +href="http://www.w3.org/XML/xml-19980210-errata#E2">[E2]</loc>Brüggemann-Klein, +Anne, and Derick Wood. <titleref>Deterministic Regular Languages</titleref>. +Universität Freiburg, Institut für Informatik, Bericht 38, Oktober 1991. Extended +abstract in A. Finkel, M. Jantzen, Hrsg., STACS 1992, S. 173-184. Springer-Verlag, +Berlin 1992. Lecture Notes in Computer Science 577. Full version titled <titleref>One-Unambiguous +Regular Languages</titleref> in Information and Computation 140 (2): 229-253, +February 1998.</bibl> +<bibl id="Clark" key="Clark">James Clark. Comparison of SGML and XML. See <loc +href="http://www.w3.org/TR/NOTE-sgml-xml-971215">http://www.w3.org/TR/NOTE-sgml-xml-971215</loc>. </bibl> +<bibl id="IANA-LANGCODES" diff="add" href="http://www.isi.edu/in-notes/iana/assignments/languages/" +key="IANA-LANGCODES"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E58">[E58]</loc>(Internet +Assigned Numbers Authority) <titleref>Registry of Language Tags</titleref>, +ed. Keld Simonsen et al.</bibl> +<bibl id="RFC1738" diff="del" href="http://www.ietf.org/rfc/rfc1738.txt" key="IETF RFC1738">IETF +(Internet Engineering Task Force). <titleref>RFC 1738: Uniform Resource Locators +(URL)</titleref>, ed. T. Berners-Lee, L. Masinter, M. McCahill. 1994. </bibl> +<bibl id="RFC1808" diff="del" href="http://www.ietf.org/rfc/rfc1808.txt" key="IETF RFC1808">IETF +(Internet Engineering Task Force). <titleref>RFC 1808: Relative Uniform Resource +Locators</titleref>, ed. R. Fielding. 1995. </bibl> +<bibl id="RFC2141" href="http://www.ietf.org/rfc/rfc2141.txt" key="IETF RFC2141">IETF +(Internet Engineering Task Force). <emph>RFC 2141: URN Syntax</emph>, ed. +R. Moats. 1997. </bibl> +<bibl id="rfc2279" diff="add" href="http://www.ietf.org/rfc/rfc2279.txt" key="IETF RFC 2279"><loc +role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E78">[E78]</loc>IETF +(Internet Engineering Task Force). <titleref>RFC 2279: UTF-8, a transformation +format of ISO 10646</titleref>, <phrase diff="add">ed. F. Yergeau, </phrase>1998.</bibl> +<bibl id="rfc2376" diff="add" href="http://www.ietf.org/rfc/rfc2376.txt" key="IETF RFC 2376"><loc +role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E48">[E48]</loc>IETF +(Internet Engineering Task Force). <titleref>RFC 2376: XML Media Types</titleref>. +ed. E. Whitehead, M. Murata. 1998.</bibl> +<bibl id="rfc2396" diff="add" href="http://www.ietf.org/rfc/rfc2396.txt" key="IETF RFC 2396"><loc +role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E66">[E66]</loc>IETF +(Internet Engineering Task Force). <titleref>RFC 2396: Uniform Resource Identifiers +(URI): Generic Syntax</titleref>. T. Berners-Lee, R. Fielding, L. Masinter. +1998.</bibl> +<bibl id="rfc2732" diff="add" href="http://www.ietf.org/rfc/rfc2732.txt" key="IETF RFC 2732"><loc +role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E66">[E66]</loc>IETF +(Internet Engineering Task Force). <titleref>RFC 2732: Format for Literal +IPv6 Addresses in URL's</titleref>. R. Hinden, B. Carpenter, L. Masinter. +1999.</bibl> +<bibl id="rfc2781" diff="add" href="http://www.ietf.org/rfc/rfc2781.txt" key="IETF RFC 2781"><loc +role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E77">[E77]</loc> +IETF (Internet Engineering Task Force). <emph>RFC 2781: UTF-16, an encoding +of ISO 10646</emph>, ed. P. Hoffman, F. Yergeau. 2000.</bibl> +<bibl id="ISO639" diff="add" key="ISO 639"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E38">[E38]</loc> +(International Organization for Standardization). <titleref>ISO 639:1988 (E). +Code for the representation of names of languages.</titleref> [Geneva]: International +Organization for Standardization, 1988.</bibl> +<bibl id="ISO3166" diff="add" key="ISO 3166"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E38">[E38]</loc> +(International Organization for Standardization). <titleref>ISO 3166-1:1997 +(E). Codes for the representation of names of countries and their subdivisions — +Part 1: Country codes</titleref> [Geneva]: International Organization for +Standardization, 1997.</bibl> +<bibl id="ISO8879" key="ISO 8879">ISO (International Organization for Standardization). <titleref>ISO +8879:1986(E). Information processing — Text and Office Systems — +Standard Generalized Markup Language (SGML).</titleref> First edition — +1986-10-15. [Geneva]: International Organization for Standardization, 1986. </bibl> +<bibl id="ISO10744" key="ISO/IEC 10744">ISO (International Organization for +Standardization). <titleref>ISO/IEC 10744-1992 (E). Information technology — +Hypermedia/Time-based Structuring Language (HyTime). </titleref> [Geneva]: +International Organization for Standardization, 1992. <emph>Extended Facilities +Annexe.</emph> [Geneva]: International Organization for Standardization, 1996. </bibl> +<bibl id="websgml" diff="add" href="http://www.sgmlsource.com/8879rev/n0029.htm" +key="WEBSGML"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E43">[E43]</loc>ISO +(International Organization for Standardization). <titleref>ISO 8879:1986 +TC2. Information technology — Document Description and Processing Languages. </titleref> +[Geneva]: International Organization for Standardization, 1998.</bibl> +<bibl id="xml-names" diff="add" xmlns:xlink="http://www.w3.org/TR/WD-xlink" +href="http://www.w3.org/TR/REC-xml-names/" key="XML Names"><loc role="erratumref" +href="http://www.w3.org/XML/xml-19980210-errata#E98">[E98]</loc>Tim Bray, +Dave Hollander, and Andrew Layman, editors. <titleref>Namespaces in XML</titleref>. +Textuality, Hewlett-Packard, and Microsoft. World Wide Web Consortium, 1999.</bibl> +</blist></div2> +</div1> +<div1 id="CharClasses"> +<head>Character Classes</head> +<p>Following the characteristics defined in the Unicode standard, characters +are classed as base characters (among others, these contain the alphabetic +characters of the Latin alphabet<phrase diff="del"><loc role="erratumref" +href="http://www.w3.org/XML/xml-19980210-errata#E84">[E84]</loc>, without +diacritics</phrase>), ideographic characters, and combining characters (among +others, this class contains most diacritics)<phrase diff="del"><loc role="erratumref" +href="http://www.w3.org/XML/xml-19980210-errata#E30">[E30]</loc>; these classes +combine to form the class of letters.</phrase> Digits and extenders are also +distinguished.</p> +<scrap id="CHARACTERS" lang="ebnf"> +<head>Characters</head> +<prodgroup pcw3="3" pcw4="15"> +<prod id="NT-Letter"> +<lhs>Letter</lhs><rhs><nt def="NT-BaseChar">BaseChar</nt> | <nt def="NT-Ideographic">Ideographic</nt></rhs> +</prod> +<prod id="NT-BaseChar"> +<lhs>BaseChar</lhs><rhs>[#x0041-#x005A] | [#x0061-#x007A] | [#x00C0-#x00D6] +| [#x00D8-#x00F6] | [#x00F8-#x00FF] | [#x0100-#x0131] | [#x0134-#x013E] +| [#x0141-#x0148] | [#x014A-#x017E] | [#x0180-#x01C3] | [#x01CD-#x01F0] +| [#x01F4-#x01F5] | [#x01FA-#x0217] | [#x0250-#x02A8] | [#x02BB-#x02C1] +| #x0386 | [#x0388-#x038A] | #x038C | [#x038E-#x03A1] +| [#x03A3-#x03CE] | [#x03D0-#x03D6] | #x03DA | #x03DC +| #x03DE | #x03E0 | [#x03E2-#x03F3] | [#x0401-#x040C] +| [#x040E-#x044F] | [#x0451-#x045C] | [#x045E-#x0481] | [#x0490-#x04C4] +| [#x04C7-#x04C8] | [#x04CB-#x04CC] | [#x04D0-#x04EB] | [#x04EE-#x04F5] +| [#x04F8-#x04F9] | [#x0531-#x0556] | #x0559 | [#x0561-#x0586] +| [#x05D0-#x05EA] | [#x05F0-#x05F2] | [#x0621-#x063A] | [#x0641-#x064A] +| [#x0671-#x06B7] | [#x06BA-#x06BE] | [#x06C0-#x06CE] | [#x06D0-#x06D3] +| #x06D5 | [#x06E5-#x06E6] | [#x0905-#x0939] | #x093D +| [#x0958-#x0961] | [#x0985-#x098C] | [#x098F-#x0990] | [#x0993-#x09A8] +| [#x09AA-#x09B0] | #x09B2 | [#x09B6-#x09B9] | [#x09DC-#x09DD] +| [#x09DF-#x09E1] | [#x09F0-#x09F1] | [#x0A05-#x0A0A] | [#x0A0F-#x0A10] +| [#x0A13-#x0A28] | [#x0A2A-#x0A30] | [#x0A32-#x0A33] | [#x0A35-#x0A36] +| [#x0A38-#x0A39] | [#x0A59-#x0A5C] | #x0A5E | [#x0A72-#x0A74] +| [#x0A85-#x0A8B] | #x0A8D | [#x0A8F-#x0A91] | [#x0A93-#x0AA8] +| [#x0AAA-#x0AB0] | [#x0AB2-#x0AB3] | [#x0AB5-#x0AB9] | #x0ABD +| #x0AE0 | [#x0B05-#x0B0C] | [#x0B0F-#x0B10] | [#x0B13-#x0B28] +| [#x0B2A-#x0B30] | [#x0B32-#x0B33] | [#x0B36-#x0B39] | #x0B3D +| [#x0B5C-#x0B5D] | [#x0B5F-#x0B61] | [#x0B85-#x0B8A] | [#x0B8E-#x0B90] +| [#x0B92-#x0B95] | [#x0B99-#x0B9A] | #x0B9C | [#x0B9E-#x0B9F] +| [#x0BA3-#x0BA4] | [#x0BA8-#x0BAA] | [#x0BAE-#x0BB5] | [#x0BB7-#x0BB9] +| [#x0C05-#x0C0C] | [#x0C0E-#x0C10] | [#x0C12-#x0C28] | [#x0C2A-#x0C33] +| [#x0C35-#x0C39] | [#x0C60-#x0C61] | [#x0C85-#x0C8C] | [#x0C8E-#x0C90] +| [#x0C92-#x0CA8] | [#x0CAA-#x0CB3] | [#x0CB5-#x0CB9] | #x0CDE +| [#x0CE0-#x0CE1] | [#x0D05-#x0D0C] | [#x0D0E-#x0D10] | [#x0D12-#x0D28] +| [#x0D2A-#x0D39] | [#x0D60-#x0D61] | [#x0E01-#x0E2E] | #x0E30 +| [#x0E32-#x0E33] | [#x0E40-#x0E45] | [#x0E81-#x0E82] | #x0E84 +| [#x0E87-#x0E88] | #x0E8A | #x0E8D | [#x0E94-#x0E97] +| [#x0E99-#x0E9F] | [#x0EA1-#x0EA3] | #x0EA5 | #x0EA7 +| [#x0EAA-#x0EAB] | [#x0EAD-#x0EAE] | #x0EB0 | [#x0EB2-#x0EB3] +| #x0EBD | [#x0EC0-#x0EC4] | [#x0F40-#x0F47] | [#x0F49-#x0F69] +| [#x10A0-#x10C5] | [#x10D0-#x10F6] | #x1100 | [#x1102-#x1103] +| [#x1105-#x1107] | #x1109 | [#x110B-#x110C] | [#x110E-#x1112] +| #x113C | #x113E | #x1140 | #x114C | #x114E | #x1150 +| [#x1154-#x1155] | #x1159 | [#x115F-#x1161] | #x1163 +| #x1165 | #x1167 | #x1169 | [#x116D-#x116E] | [#x1172-#x1173] +| #x1175 | #x119E | #x11A8 | #x11AB | [#x11AE-#x11AF] +| [#x11B7-#x11B8] | #x11BA | [#x11BC-#x11C2] | #x11EB +| #x11F0 | #x11F9 | [#x1E00-#x1E9B] | [#x1EA0-#x1EF9] +| [#x1F00-#x1F15] | [#x1F18-#x1F1D] | [#x1F20-#x1F45] | [#x1F48-#x1F4D] +| [#x1F50-#x1F57] | #x1F59 | #x1F5B | #x1F5D | [#x1F5F-#x1F7D] +| [#x1F80-#x1FB4] | [#x1FB6-#x1FBC] | #x1FBE | [#x1FC2-#x1FC4] +| [#x1FC6-#x1FCC] | [#x1FD0-#x1FD3] | [#x1FD6-#x1FDB] | [#x1FE0-#x1FEC] +| [#x1FF2-#x1FF4] | [#x1FF6-#x1FFC] | #x2126 | [#x212A-#x212B] +| #x212E | [#x2180-#x2182] | [#x3041-#x3094] | [#x30A1-#x30FA] +| [#x3105-#x312C] | [#xAC00-#xD7A3] </rhs> +</prod> +<prod id="NT-Ideographic"> +<lhs>Ideographic</lhs><rhs>[#x4E00-#x9FA5] | #x3007 | [#x3021-#x3029] </rhs> +</prod> +<prod id="NT-CombiningChar"> +<lhs>CombiningChar</lhs><rhs>[#x0300-#x0345] | [#x0360-#x0361] | [#x0483-#x0486] +| [#x0591-#x05A1] | [#x05A3-#x05B9] | [#x05BB-#x05BD] | #x05BF +| [#x05C1-#x05C2] | #x05C4 | [#x064B-#x0652] | #x0670 +| [#x06D6-#x06DC] | [#x06DD-#x06DF] | [#x06E0-#x06E4] | [#x06E7-#x06E8] +| [#x06EA-#x06ED] | [#x0901-#x0903] | #x093C | [#x093E-#x094C] +| #x094D | [#x0951-#x0954] | [#x0962-#x0963] | [#x0981-#x0983] +| #x09BC | #x09BE | #x09BF | [#x09C0-#x09C4] | [#x09C7-#x09C8] +| [#x09CB-#x09CD] | #x09D7 | [#x09E2-#x09E3] | #x0A02 +| #x0A3C | #x0A3E | #x0A3F | [#x0A40-#x0A42] | [#x0A47-#x0A48] +| [#x0A4B-#x0A4D] | [#x0A70-#x0A71] | [#x0A81-#x0A83] | #x0ABC +| [#x0ABE-#x0AC5] | [#x0AC7-#x0AC9] | [#x0ACB-#x0ACD] | [#x0B01-#x0B03] +| #x0B3C | [#x0B3E-#x0B43] | [#x0B47-#x0B48] | [#x0B4B-#x0B4D] +| [#x0B56-#x0B57] | [#x0B82-#x0B83] | [#x0BBE-#x0BC2] | [#x0BC6-#x0BC8] +| [#x0BCA-#x0BCD] | #x0BD7 | [#x0C01-#x0C03] | [#x0C3E-#x0C44] +| [#x0C46-#x0C48] | [#x0C4A-#x0C4D] | [#x0C55-#x0C56] | [#x0C82-#x0C83] +| [#x0CBE-#x0CC4] | [#x0CC6-#x0CC8] | [#x0CCA-#x0CCD] | [#x0CD5-#x0CD6] +| [#x0D02-#x0D03] | [#x0D3E-#x0D43] | [#x0D46-#x0D48] | [#x0D4A-#x0D4D] +| #x0D57 | #x0E31 | [#x0E34-#x0E3A] | [#x0E47-#x0E4E] +| #x0EB1 | [#x0EB4-#x0EB9] | [#x0EBB-#x0EBC] | [#x0EC8-#x0ECD] +| [#x0F18-#x0F19] | #x0F35 | #x0F37 | #x0F39 | #x0F3E +| #x0F3F | [#x0F71-#x0F84] | [#x0F86-#x0F8B] | [#x0F90-#x0F95] +| #x0F97 | [#x0F99-#x0FAD] | [#x0FB1-#x0FB7] | #x0FB9 +| [#x20D0-#x20DC] | #x20E1 | [#x302A-#x302F] | #x3099 +| #x309A </rhs> +</prod> +<prod id="NT-Digit"> +<lhs>Digit</lhs><rhs>[#x0030-#x0039] | [#x0660-#x0669] | [#x06F0-#x06F9] +| [#x0966-#x096F] | [#x09E6-#x09EF] | [#x0A66-#x0A6F] | [#x0AE6-#x0AEF] +| [#x0B66-#x0B6F] | [#x0BE7-#x0BEF] | [#x0C66-#x0C6F] | [#x0CE6-#x0CEF] +| [#x0D66-#x0D6F] | [#x0E50-#x0E59] | [#x0ED0-#x0ED9] | [#x0F20-#x0F29] </rhs> +</prod> +<prod id="NT-Extender"> +<lhs>Extender</lhs><rhs>#x00B7 | #x02D0 | #x02D1 | #x0387 | #x0640 +| #x0E46 | #x0EC6 | #x3005 | [#x3031-#x3035] | [#x309D-#x309E] +| [#x30FC-#x30FE] </rhs> +</prod> +</prodgroup></scrap> +<p>The character classes defined here can be derived from the Unicode <phrase +diff="add"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E67">[E67]</loc>2.0</phrase> +character database as follows:</p> +<ulist> +<item><p>Name start characters must have one of the categories Ll, Lu, Lo, +Lt, Nl.</p></item> +<item><p>Name characters other than Name-start characters must have one of +the categories Mc, Me, Mn, Lm, or Nd.</p></item> +<item><p>Characters in the compatibility area (i.e. with character code greater +than #xF900 and less than #xFFFE) are not allowed in XML names.</p></item> +<item><p>Characters which have a font or compatibility decomposition (i.e. +those with a <quote>compatibility formatting tag</quote> in field 5 of the +database -- marked by field 5 beginning with a <quote><</quote>) are not +allowed.</p></item> +<item><p>The following characters are treated as name-start characters rather +than name characters, because the property file classifies them as Alphabetic: +[#x02BB-#x02C1], #x0559, #x06E5, #x06E6.</p></item> +<item><p>Characters #x20DD-#x20E0 are excluded (in accordance with Unicode <phrase +diff="add"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E67">[E67]</loc>2.0</phrase>, +section 5.14).</p></item> +<item><p>Character #x00B7 is classified as an extender, because the property +list so identifies it.</p></item> +<item><p>Character #x0387 is added as a name character, because #x00B7 is +its canonical equivalent.</p></item> +<item><p>Characters ':' and '_' are allowed as name-start characters.</p> +</item> +<item><p>Characters '-' and '.' are allowed as name characters.</p></item> +</ulist> +</div1> +<inform-div1 id="sec-xml-and-sgml"> +<head>XML and SGML</head> +<p><phrase diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E43">[E43]</loc>XML +is designed to be a subset of SGML, in that every XML document should also +be a conforming SGML document.</phrase> For a detailed comparison of the additional +restrictions that XML places on documents beyond those of SGML, see <bibref +ref="Clark"/>.</p> +</inform-div1> +<inform-div1 id="sec-entexpand"> +<head>Expansion of Entity and Character References</head> +<p>This appendix contains some examples illustrating the sequence of entity- +and character-reference recognition and expansion, as specified in <specref +ref="entproc"/>.</p> +<p>If the DTD contains the declaration</p> +<eg><![CDATA[<!ENTITY example "<p>An ampersand (&#38;) may be escaped +numerically (&#38;#38;) or with a general entity +(&amp;).</p>" >]]></eg> +<p>then the XML processor will recognize the character references when it +parses the entity declaration, and resolve them before storing the following +string as the value of the entity <quote><code>example</code></quote>:</p> +<eg><![CDATA[<p>An ampersand (&) may be escaped +numerically (&#38;) or with a general entity +(&amp;).</p>]]></eg> +<p>A reference in the document to <quote><code>&example;</code></quote> +will cause the text to be reparsed, at which time the start- and end-tags +of the <el>p</el> element will be recognized and the three references will +be recognized and expanded, resulting in a <el>p</el> element with the following +content (all data, no delimiters or markup):</p> +<eg><![CDATA[An ampersand (&) may be escaped +numerically (&) or with a general entity +(&).]]></eg> +<p>A more complex example will illustrate the rules and their effects fully. +In the following example, the line numbers are solely for reference.</p> +<eg><![CDATA[1 <?xml version='1.0'?> +2 <!DOCTYPE test [ +3 <!ELEMENT test (#PCDATA) > +4 <!ENTITY % xx '%zz;'> +5 <!ENTITY % zz '<!ENTITY tricky "error-prone" >' > +6 %xx; +7 ]> +8 <test>This sample shows a &tricky; method.</test>]]></eg> +<p>This produces the following:</p> +<ulist spacing="compact"> +<item><p>in line 4, the reference to character 37 is expanded immediately, +and the parameter entity <quote><code>xx</code></quote> is stored in the symbol +table with the value <quote><code>%zz;</code></quote>. Since the replacement +text is not rescanned, the reference to parameter entity <quote><code>zz</code></quote> +is not recognized. (And it would be an error if it were, since <quote><code>zz</code></quote> +is not yet declared.)</p></item> +<item><p>in line 5, the character reference <quote><code>&#60;</code></quote> +is expanded immediately and the parameter entity <quote><code>zz</code></quote> +is stored with the replacement text <quote><code><!ENTITY tricky "error-prone" +></code></quote>, which is a well-formed entity declaration.</p></item> +<item><p>in line 6, the reference to <quote><code>xx</code></quote> is recognized, +and the replacement text of <quote><code>xx</code></quote> (namely <quote><code>%zz;</code></quote>) +is parsed. The reference to <quote><code>zz</code></quote> is recognized in +its turn, and its replacement text (<quote><code><!ENTITY tricky "error-prone" +></code></quote>) is parsed. The general entity <quote><code>tricky</code></quote> +has now been declared, with the replacement text <quote><code>error-prone</code></quote>.</p> +</item> +<item><p>in line 8, the reference to the general entity <quote><code>tricky</code></quote> +is recognized, and it is expanded, so the full content of the <el>test</el> +element is the self-describing (and ungrammatical) string <emph>This sample +shows a error-prone method.</emph></p></item> +</ulist> +</inform-div1> +<inform-div1 id="determinism"> +<head>Deterministic Content Models</head> +<p><phrase diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E102">[E102]</loc>As +noted in <specref ref="sec-element-content"/>, it is required that content +models in element type declarations be deterministic. This requirement is <termref +def="dt-compat">for compatibility</termref> with SGML (which calls deterministic +content models <quote>unambiguous</quote>);</phrase> XML processors built +using SGML systems may flag non-deterministic content models as errors.</p> +<p>For example, the content model <code>((b, c) | (b, d))</code> is non-deterministic, +because given an initial <el>b</el> the <phrase diff="chg"><loc role="erratumref" +href="http://www.w3.org/XML/xml-19980210-errata#E95">[E95]</loc>XML processor</phrase> +cannot know which <el>b</el> in the model is being matched without looking +ahead to see which element follows the <el>b</el>. In this case, the two references +to <el>b</el> can be collapsed into a single reference, making the model read <code>(b, +(c | d))</code>. An initial <el>b</el> now clearly matches only a single name +in the content model. The <phrase diff="chg"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E95">[E95]</loc>processor</phrase +> doesn't need to look ahead to see what follows; either <el>c</el> or <el>d</el> +would be accepted.</p> +<p>More formally: a finite state automaton may be constructed from the content +model using the standard algorithms, e.g. algorithm 3.5 in section 3.9 of +Aho, Sethi, and Ullman <bibref ref="Aho"/>. In many such algorithms, a follow +set is constructed for each position in the regular expression (i.e., each +leaf node in the syntax tree for the regular expression); if any position +has a follow set in which more than one following position is labeled with +the same element type name, then the content model is in error and may be +reported as an error.</p> +<p>Algorithms exist which allow many but not all non-deterministic content +models to be reduced automatically to equivalent deterministic models; see +Brüggemann-Klein 1991 <bibref ref="ABK"/>.</p> +</inform-div1> +<inform-div1 id="sec-guessing"> +<head><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E105">[E105]</loc><loc +role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E48">[E48]</loc>Autodetection +of Character Encodings</head> +<p>The XML encoding declaration functions as an internal label on each entity, +indicating which character encoding is in use. Before an XML processor can +read the internal label, however, it apparently has to know what character +encoding is in use—which is what the internal label is trying to indicate. +In the general case, this is a hopeless situation. It is not entirely hopeless +in XML, however, because XML limits the general case in two ways: each implementation +is assumed to support only a finite set of character encodings, and the XML +encoding declaration is restricted in position and content in order to make +it feasible to autodetect the character encoding in use in each entity in +normal cases. Also, in many cases other sources of information are available +in addition to the XML data stream itself. Two cases may be distinguished, +depending on whether the XML entity is presented to the processor without, +or with, any accompanying (external) information. We consider the first case +first.</p> +<div2 id="sec-guessing-no-ext-info"> +<head diff="add">Detection Without External Encoding Information</head> +<p>Because each XML entity <phrase diff="add">not accompanied by external +encoding information and </phrase>not in UTF-8 or UTF-16 <phrase diff="chg">encoding</phrase> <emph>must</emph> +begin with an XML encoding declaration, in which the first characters must +be '<code><?xml</code>', any conforming processor can detect, after two +to four octets of input, which of the following cases apply. In reading this +list, it may help to know that in UCS-4, '<' is <quote><code>#x0000003C</code></quote> +and '?' is <quote><code>#x0000003F</code></quote>, and the Byte Order Mark +required of UTF-16 data streams is <quote><code>#xFEFF</code></quote>. <phrase +diff="add">The notation <var>##</var> is used to denote any byte value except <phrase +diff="chg">that two consecutive <var>##</var>s cannot be both 00</phrase>.</phrase></p> +<p diff="add">With a Byte Order Mark:</p> +<table diff="add" border="1" frame="border"><tbody><tr><td><code>00 00 FE +FF</code></td><td>UCS-4, big-endian machine (1234 order)</td></tr><tr><td><code>FF +FE 00 00</code></td><td>UCS-4, little-endian machine (4321 order)</td></tr> +<tr><td><code>00 00 FF FE</code></td><td>UCS-4, unusual octet order (2143)</td> +</tr><tr><td><code>FE FF 00 00</code></td><td>UCS-4, unusual octet order (3412)</td> +</tr><tr><td><code>FE FF ## ##</code></td><td>UTF-16, big-endian</td></tr> +<tr><td><code>FF FE ## ##</code></td><td>UTF-16, little-endian</td></tr><tr> +<td><code>EF BB BF</code></td><td>UTF-8</td></tr></tbody></table> +<p diff="add">Without a Byte Order Mark:</p> +<table diff="add" border="1" frame="border"><tbody><tr><td><code>00 00 00 3C</code></td> +<td rowspan="4">UCS-4 or other encoding with a 32-bit code unit and ASCII +characters encoded as ASCII values, in respectively big-endian (1234), little-endian +(4321) and two unusual byte orders (2143 and 3412). The encoding declaration +must be read to determine which of UCS-4 or other supported 32-bit encodings +applies.</td></tr><tr><td><code>3C 00 00 00</code></td> +<!--<td>UCS-4, little-endian machine (4321 order)</td>--> +</tr><tr><td><code>00 00 3C 00</code></td> +<!--<td>UCS-4, unusual octet order (2143)</td>--> +</tr><tr><td><code>00 3C 00 00</code></td> +<!--<td>UCS-4, unusual octet order (3412)</td>--> +</tr><tr><td><code>00 3C 00 3F</code></td><td>UTF-16BE or big-endian ISO-10646-UCS-2 +or other encoding with a 16-bit code unit in big-endian order and ASCII characters +encoded as ASCII values (the encoding declaration must be read to determine +which)</td></tr><tr><td><code>3C 00 3F 00</code></td><td>UTF-16LE or little-endian +ISO-10646-UCS-2 or other encoding with a 16-bit code unit in little-endian +order and ASCII characters encoded as ASCII values (the encoding declaration +must be read to determine which)</td></tr><tr><td><code>3C 3F 78 6D</code></td> +<td>UTF-8, ISO 646, ASCII, some part of ISO 8859, Shift-JIS, EUC, or any other +7-bit, 8-bit, or mixed-width encoding which ensures that the characters of +ASCII have their normal positions, width, and values; the actual encoding +declaration must be read to detect which of these applies, but since all of +these encodings use the same bit patterns for the relevant ASCII characters, +the encoding declaration itself may be read reliably</td></tr><tr><td><code>4C +6F A7 94</code></td><td>EBCDIC (in some flavor; the full encoding declaration +must be read to tell which code page is in use)</td></tr><tr><td>Other</td> +<td>UTF-8 without an encoding declaration, or else the data stream is mislabeled +(lacking a required encoding declaration), corrupt, fragmentary, or enclosed +in a wrapper of some kind</td></tr></tbody></table> +<note diff="add"> +<p>In cases above which do not require reading the encoding declaration to +determine the encoding, section 4.3.3 still requires that the encoding declaration, +if present, be read and that the encoding name be checked to match the actual +encoding of the entity. Also, it is possible that new character encodings +will be invented that will make it necessary to use the encoding declaration +to determine the encoding, in cases where this is not required at present.</p> +</note> +<p>This level of autodetection is enough to read the XML encoding declaration +and parse the character-encoding identifier, which is still necessary to distinguish +the individual members of each family of encodings (e.g. to tell UTF-8 from +8859, and the parts of 8859 from each other, or to distinguish the specific +EBCDIC code page in use, and so on).</p> +<p>Because the contents of the encoding declaration are restricted to <phrase +diff="chg">characters from the ASCII repertoire (however encoded)</phrase>, +a processor can reliably read the entire encoding declaration as soon as it +has detected which family of encodings is in use. Since in practice, all widely +used character encodings fall into one of the categories above, the XML encoding +declaration allows reasonably reliable in-band labeling of character encodings, +even when external sources of information at the operating-system or transport-protocol +level are unreliable. <phrase diff="del">Note that since external parsed entities +in UTF-16 may begin with any character, this autodetection does not always +work. Also, </phrase><phrase diff="add">Character encodings such as UTF-7 +that make overloaded usage of ASCII-valued bytes may fail to be reliably detected.</phrase></p> +<p>Once the processor has detected the character encoding in use, it can act +appropriately, whether by invoking a separate input routine for each case, +or by calling the proper conversion function on each character of input.</p> +<p>Like any self-labeling system, the XML encoding declaration will not work +if any software changes the entity's character set or encoding without updating +the encoding declaration. Implementors of character-encoding routines should +be careful to ensure the accuracy of the internal and external information +used to label the entity.</p> +</div2> +<div2 id="sec-guessing-with-ext-info"> +<head diff="add">Priorities in the Presence of External Encoding Information</head> +<p>The second possible case occurs when the XML entity is accompanied by encoding +information, as in some file systems and some network protocols. When multiple +sources of information are available, their relative priority and the preferred +method of handling conflict should be specified as part of the higher-level +protocol used to deliver XML. <phrase diff="chg">In particular, please refer +to <bibref ref="rfc2376"/> or its successor, which defines the <code>text/xml</code> +and <code>application/xml</code> MIME types and provides some useful guidance. +In the interests of interoperability, however, the following rule is recommended.</phrase></p> +<ulist> +<item><p>If an XML entity is in a file, the Byte-Order Mark and encoding declaration <phrase +diff="del">PI </phrase>are used (if present) to determine the character encoding.<phrase +diff="del"><loc role="erratumref" href="http://www.w3.org/XML/xml-19980210-errata#E74">[E74]</loc> +All other heuristics and sources of information are solely for error recovery.</phrase></p> +</item> +</ulist> +<ulist diff="del"> +<item><p>If an XML entity is delivered with a MIME type of text/xml, then +the <code>charset</code> parameter on the MIME type determines the character +encoding method; all other heuristics and sources of information are solely +for error recovery.</p></item> +<item><p>If an XML entity is delivered with a MIME type of application/xml, +then the Byte-Order Mark and encoding-declaration PI are used (if present) +to determine the character encoding. All other heuristics and sources of information +are solely for error recovery.</p></item> +</ulist> +<p diff="del">These rules apply only in the absence of protocol-level documentation; +in particular, when the MIME types text/xml and application/xml are defined, +the recommendations of the relevant RFC will supersede these rules.</p> +</div2> +</inform-div1> +<inform-div1 id="sec-xml-wg"> +<head>W3C XML Working Group</head> +<p>This specification was prepared and approved for publication by the W3C +XML Working Group (WG). WG approval of this specification does not necessarily +imply that all WG members voted for its approval. The current and former members +of the XML WG are:</p> +<orglist> +<member><name>Jon Bosak</name><affiliation>Sun</affiliation><role>Chair</role> +</member> +<member><name>James Clark</name><role>Technical Lead</role></member> +<member><name>Tim Bray</name><affiliation>Textuality and Netscape</affiliation> +<role>XML Co-editor</role></member> +<member><name>Jean Paoli</name><affiliation>Microsoft</affiliation><role>XML +Co-editor</role></member> +<member><name>C. M. Sperberg-McQueen</name><affiliation>U. of Ill.</affiliation> +<role>XML Co-editor</role></member> +<member><name>Dan Connolly</name><affiliation>W3C</affiliation><role>W3C Liaison</role> +</member> +<member><name>Paula Angerstein</name><affiliation>Texcel</affiliation></member> +<member><name>Steve DeRose</name><affiliation>INSO</affiliation></member> +<member><name>Dave Hollander</name><affiliation>HP</affiliation></member> +<member><name>Eliot Kimber</name><affiliation>ISOGEN</affiliation></member> +<member><name>Eve Maler</name><affiliation>ArborText</affiliation></member> +<member><name>Tom Magliery</name><affiliation>NCSA</affiliation></member> +<member><name>Murray Maloney</name><affiliation diff="chg">SoftQuad, Grif +SA, Muzmo and Veo Systems</affiliation></member> +<member><name diff="chg">MURATA Makoto (FAMILY Given)</name><affiliation>Fuji +Xerox Information Systems</affiliation></member> +<member><name>Joel Nava</name><affiliation>Adobe</affiliation></member> +<member><name>Conleth O'Connell</name><affiliation>Vignette</affiliation> +</member> +<member><name>Peter Sharpe</name><affiliation>SoftQuad</affiliation></member> +<member><name>John Tigue</name><affiliation>DataChannel</affiliation></member> +</orglist> +</inform-div1> +<inform-div1 id="sec-core-wg" diff="add"> +<head>W3C XML Core Group</head> +<p>The second edition of this specification was prepared by the W3C XML Core +Working Group (WG). The members of the WG at the time of publication of this +edition were:</p> +<orglist> +<member><name>Paula Angerstein</name><affiliation>Vignette</affiliation></member> +<member><name>Daniel Austin</name><affiliation>Ask Jeeves</affiliation></member> +<member><name>Tim Boland</name></member> +<member><name>Allen Brown</name><affiliation>Microsoft</affiliation></member> +<member><name>Dan Connolly</name><affiliation>W3C</affiliation><role>Staff +Contact</role></member> +<member><name>John Cowan</name><affiliation>Reuters Limited</affiliation> +</member> +<member><name>John Evdemon</name><affiliation>XMLSolutions Corporation</affiliation> +</member> +<member><name>Paul Grosso</name><affiliation>Arbortext</affiliation><role>Co-Chair</role> +</member> +<member><name>Arnaud Le Hors</name><affiliation>IBM</affiliation><role>Co-Chair</role> +</member> +<member><name>Eve Maler</name><affiliation>Sun Microsystems</affiliation> +<role>Second Edition Editor</role></member> +<member><name>Jonathan Marsh</name><affiliation>Microsoft</affiliation></member> +<member><name>MURATA Makoto (FAMILY Given)</name><affiliation>IBM</affiliation> +</member> +<member><name>Mark Needleman</name><affiliation>Data Research Associates</affiliation> +</member> +<member><name>David Orchard</name><affiliation>Jamcracker</affiliation></member> +<member><name>Lew Shannon</name><affiliation>NCR</affiliation></member> +<member><name>Richard Tobin</name><affiliation>University of Edinburgh</affiliation> +</member> +<member><name>Daniel Veillard</name><affiliation>W3C</affiliation></member> +<member><name>Dan Vint</name><affiliation>Lexica</affiliation></member> +<member><name>Norman Walsh</name><affiliation>Sun Microsystems</affiliation> +</member> +<member><name>François Yergeau</name><affiliation>Alis Technologies</affiliation> +<role>Errata List Editor</role></member> +<member><name>Kongyi Zhou</name><affiliation>Oracle</affiliation></member> +</orglist> +</inform-div1> +<inform-div1 diff="add"> +<head>Production Notes</head> +<p>This Second Edition was encoded in the <loc href="http://www.w3.org/XML/1998/06/xmlspec-v21.dtd">XMLspec +DTD</loc> (which has <loc href="http://www.w3.org/XML/1998/06/xmlspec-report-v21.htm">documentation</loc> +available). The HTML versions were produced with a combination of the <loc +href="http://www.w3.org/XML/1998/06/xmlspec.xsl">xmlspec.xsl</loc>, <loc href="http://www.w3.org/XML/1998/06/diffspec.xsl">diffspec.xsl</loc>, +and <loc href="http://www.w3.org/XML/1998/06/REC-xml-2e.xsl">REC-xml-2e.xsl</loc> +XSLT stylesheets. The PDF version was produced with the <loc href="http://www.tdb.uu.se/~jan/html2ps.html">html2ps</loc> +facility and a distiller program.</p> +</inform-div1> +</back></spec> diff --git a/lib/libUPnP/Neptune/Source/Tests/Xml1/test.xml b/lib/libUPnP/Neptune/Source/Tests/Xml1/test.xml new file mode 100644 index 0000000..87e9ccc --- /dev/null +++ b/lib/libUPnP/Neptune/Source/Tests/Xml1/test.xml @@ -0,0 +1,16 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- edited with XMLSPY v5 U (http://www.xmlspy.com) by Gilles Boccon-Gibod --> +<RootElement xmlns="foo.com" xmlns:pfy="bar.com" xmlns:prefix="prefix.com">Hello, I'm the first part<FirstChild first-attribute="some value">Hi, I'm at level 1</FirstChild>I'm the second part <ubu > oh & hu<prefix:SecondChild pfy:second-attribute="hello">some text here in brackets</prefix:SecondChild> +<data>Hello <![CDATA[This is some <cdata> stuff with ] and ] and ]] ]]> bla</data> + <TestElement some-attr='single quotes' attr2='single quote with " also' attr3="double quotes" attr4="double quotes with ' also" attr5='single with "<" entity' attr6="double with '>' entity"/> + <SomeElement> + the white + spaces 
should be + preserved + </SomeElement> +<EmptyElement attr1="foo"/> + + +<TestEscapes attr1="'"'">

&  @©</TestEscapes> +</RootElement> +<!--this is a comment - and some stuff - --> diff --git a/lib/libUPnP/Neptune/Source/Tests/Xml1/unicode.xml b/lib/libUPnP/Neptune/Source/Tests/Xml1/unicode.xml new file mode 100644 index 0000000..947e44f --- /dev/null +++ b/lib/libUPnP/Neptune/Source/Tests/Xml1/unicode.xml @@ -0,0 +1 @@ +<text>For example, the references &#916;, &#1049;, &#1511;, &#1605;, &#3671;, &#12354;, &#21494;, &#33865;, and &#45307; (or the same numeric values expressed in hexadecimal, with &#x as the prefix) display on browsers as Δ, Й, ק,? م, ๗, あ, 叶, 葉 and 냻— if the proper fonts exist, these symbols look like the Greek capital letter "Delta", Cyrillic capital letter "Short I", Hebrew letter "Qof", Arabic letter "Meem", Thai numeral 7, Japanese Hiragana "A", simplified Chinese "Leaf", traditional Chinese "Leaf", and Korean Hangul syllable "Nyaelh", respectively</text>
\ No newline at end of file |