summaryrefslogtreecommitdiffstats
path: root/security/sandbox/chromium/base/third_party/icu
diff options
context:
space:
mode:
Diffstat (limited to 'security/sandbox/chromium/base/third_party/icu')
-rw-r--r--security/sandbox/chromium/base/third_party/icu/LICENSE76
-rw-r--r--security/sandbox/chromium/base/third_party/icu/icu_utf.cc131
-rw-r--r--security/sandbox/chromium/base/third_party/icu/icu_utf.h442
3 files changed, 649 insertions, 0 deletions
diff --git a/security/sandbox/chromium/base/third_party/icu/LICENSE b/security/sandbox/chromium/base/third_party/icu/LICENSE
new file mode 100644
index 0000000000..2882e4ebda
--- /dev/null
+++ b/security/sandbox/chromium/base/third_party/icu/LICENSE
@@ -0,0 +1,76 @@
+COPYRIGHT AND PERMISSION NOTICE (ICU 58 and later)
+
+Copyright © 1991-2017 Unicode, Inc. All rights reserved.
+Distributed under the Terms of Use in http://www.unicode.org/copyright.html
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of the Unicode data files and any associated documentation
+(the "Data Files") or Unicode software and any associated documentation
+(the "Software") to deal in the Data Files or Software
+without restriction, including without limitation the rights to use,
+copy, modify, merge, publish, distribute, and/or sell copies of
+the Data Files or Software, and to permit persons to whom the Data Files
+or Software are furnished to do so, provided that either
+(a) this copyright and permission notice appear with all copies
+of the Data Files or Software, or
+(b) this copyright and permission notice appear in associated
+Documentation.
+
+THE DATA FILES AND SOFTWARE ARE PROVIDED "AS IS", WITHOUT WARRANTY OF
+ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE
+WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT OF THIRD PARTY RIGHTS.
+IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS INCLUDED IN THIS
+NOTICE BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL
+DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE,
+DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER
+TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
+PERFORMANCE OF THE DATA FILES OR SOFTWARE.
+
+Except as contained in this notice, the name of a copyright holder
+shall not be used in advertising or otherwise to promote the sale,
+use or other dealings in these Data Files or Software without prior
+written authorization of the copyright holder.
+
+---------------------
+
+Third-Party Software Licenses
+
+This section contains third-party software notices and/or additional
+terms for licensed third-party software components included within ICU
+libraries.
+
+1. ICU License - ICU 1.8.1 to ICU 57.1
+
+COPYRIGHT AND PERMISSION NOTICE
+
+Copyright (c) 1995-2016 International Business Machines Corporation and others
+All rights reserved.
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, and/or sell copies of the Software, and to permit persons
+to whom the Software is furnished to do so, provided that the above
+copyright notice(s) and this permission notice appear in all copies of
+the Software and that both the above copyright notice(s) and this
+permission notice appear in supporting documentation.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT
+OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR
+HOLDERS INCLUDED IN THIS NOTICE BE LIABLE FOR ANY CLAIM, OR ANY
+SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER
+RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF
+CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN
+CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+
+Except as contained in this notice, the name of a copyright holder
+shall not be used in advertising or otherwise to promote the sale, use
+or other dealings in this Software without prior written authorization
+of the copyright holder.
+
+All trademarks and registered trademarks mentioned herein are the
+property of their respective owners.
diff --git a/security/sandbox/chromium/base/third_party/icu/icu_utf.cc b/security/sandbox/chromium/base/third_party/icu/icu_utf.cc
new file mode 100644
index 0000000000..a3262b04d3
--- /dev/null
+++ b/security/sandbox/chromium/base/third_party/icu/icu_utf.cc
@@ -0,0 +1,131 @@
+// © 2016 and later: Unicode, Inc. and others.
+// License & terms of use: http://www.unicode.org/copyright.html
+/*
+******************************************************************************
+*
+* Copyright (C) 1999-2012, International Business Machines
+* Corporation and others. All Rights Reserved.
+*
+******************************************************************************
+* file name: utf_impl.cpp
+* encoding: UTF-8
+* tab size: 8 (not used)
+* indentation:4
+*
+* created on: 1999sep13
+* created by: Markus W. Scherer
+*
+* This file provides implementation functions for macros in the utfXX.h
+* that would otherwise be too long as macros.
+*/
+
+#include "base/third_party/icu/icu_utf.h"
+
+namespace base_icu {
+
+// source/common/utf_impl.cpp
+
+static const UChar32
+utf8_errorValue[6]={
+ // Same values as UTF8_ERROR_VALUE_1, UTF8_ERROR_VALUE_2, UTF_ERROR_VALUE,
+ // but without relying on the obsolete unicode/utf_old.h.
+ 0x15, 0x9f, 0xffff,
+ 0x10ffff
+};
+
+static UChar32
+errorValue(int32_t count, int8_t strict) {
+ if(strict>=0) {
+ return utf8_errorValue[count];
+ } else if(strict==-3) {
+ return 0xfffd;
+ } else {
+ return CBU_SENTINEL;
+ }
+}
+
+/*
+ * Handle the non-inline part of the U8_NEXT() and U8_NEXT_FFFD() macros
+ * and their obsolete sibling UTF8_NEXT_CHAR_SAFE().
+ *
+ * U8_NEXT() supports NUL-terminated strings indicated via length<0.
+ *
+ * The "strict" parameter controls the error behavior:
+ * <0 "Safe" behavior of U8_NEXT():
+ * -1: All illegal byte sequences yield U_SENTINEL=-1.
+ * -2: Same as -1, except for lenient treatment of surrogate code points as legal.
+ * Some implementations use this for roundtripping of
+ * Unicode 16-bit strings that are not well-formed UTF-16, that is, they
+ * contain unpaired surrogates.
+ * -3: All illegal byte sequences yield U+FFFD.
+ * 0 Obsolete "safe" behavior of UTF8_NEXT_CHAR_SAFE(..., FALSE):
+ * All illegal byte sequences yield a positive code point such that this
+ * result code point would be encoded with the same number of bytes as
+ * the illegal sequence.
+ * >0 Obsolete "strict" behavior of UTF8_NEXT_CHAR_SAFE(..., TRUE):
+ * Same as the obsolete "safe" behavior, but non-characters are also treated
+ * like illegal sequences.
+ *
+ * Note that a UBool is the same as an int8_t.
+ */
+UChar32
+utf8_nextCharSafeBody(const uint8_t *s, int32_t *pi, int32_t length, UChar32 c, UBool strict) {
+ // *pi is one after byte c.
+ int32_t i=*pi;
+ // length can be negative for NUL-terminated strings: Read and validate one byte at a time.
+ if(i==length || c>0xf4) {
+ // end of string, or not a lead byte
+ } else if(c>=0xf0) {
+ // Test for 4-byte sequences first because
+ // U8_NEXT() handles shorter valid sequences inline.
+ uint8_t t1=s[i], t2, t3;
+ c&=7;
+ if(CBU8_IS_VALID_LEAD4_AND_T1(c, t1) &&
+ ++i!=length && (t2=s[i]-0x80)<=0x3f &&
+ ++i!=length && (t3=s[i]-0x80)<=0x3f) {
+ ++i;
+ c=(c<<18)|((t1&0x3f)<<12)|(t2<<6)|t3;
+ // strict: forbid non-characters like U+fffe
+ if(strict<=0 || !CBU_IS_UNICODE_NONCHAR(c)) {
+ *pi=i;
+ return c;
+ }
+ }
+ } else if(c>=0xe0) {
+ c&=0xf;
+ if(strict!=-2) {
+ uint8_t t1=s[i], t2;
+ if(CBU8_IS_VALID_LEAD3_AND_T1(c, t1) &&
+ ++i!=length && (t2=s[i]-0x80)<=0x3f) {
+ ++i;
+ c=(c<<12)|((t1&0x3f)<<6)|t2;
+ // strict: forbid non-characters like U+fffe
+ if(strict<=0 || !CBU_IS_UNICODE_NONCHAR(c)) {
+ *pi=i;
+ return c;
+ }
+ }
+ } else {
+ // strict=-2 -> lenient: allow surrogates
+ uint8_t t1=s[i]-0x80, t2;
+ if(t1<=0x3f && (c>0 || t1>=0x20) &&
+ ++i!=length && (t2=s[i]-0x80)<=0x3f) {
+ *pi=i+1;
+ return (c<<12)|(t1<<6)|t2;
+ }
+ }
+ } else if(c>=0xc2) {
+ uint8_t t1=s[i]-0x80;
+ if(t1<=0x3f) {
+ *pi=i+1;
+ return ((c-0xc0)<<6)|t1;
+ }
+ } // else 0x80<=c<0xc2 is not a lead byte
+
+ /* error handling */
+ c=errorValue(i-*pi, strict);
+ *pi=i;
+ return c;
+}
+
+} // namespace base_icu
diff --git a/security/sandbox/chromium/base/third_party/icu/icu_utf.h b/security/sandbox/chromium/base/third_party/icu/icu_utf.h
new file mode 100644
index 0000000000..2ba82316c2
--- /dev/null
+++ b/security/sandbox/chromium/base/third_party/icu/icu_utf.h
@@ -0,0 +1,442 @@
+// © 2016 and later: Unicode, Inc. and others.
+// License & terms of use: http://www.unicode.org/copyright.html
+/*
+******************************************************************************
+*
+* Copyright (C) 1999-2015, International Business Machines
+* Corporation and others. All Rights Reserved.
+*
+******************************************************************************
+*/
+
+#ifndef BASE_THIRD_PARTY_ICU_ICU_UTF_H_
+#define BASE_THIRD_PARTY_ICU_ICU_UTF_H_
+
+#include <stdint.h>
+
+namespace base_icu {
+
+// source/common/unicode/umachine.h
+
+/** The ICU boolean type @stable ICU 2.0 */
+typedef int8_t UBool;
+
+/**
+ * Define UChar32 as a type for single Unicode code points.
+ * UChar32 is a signed 32-bit integer (same as int32_t).
+ *
+ * The Unicode code point range is 0..0x10ffff.
+ * All other values (negative or >=0x110000) are illegal as Unicode code points.
+ * They may be used as sentinel values to indicate "done", "error"
+ * or similar non-code point conditions.
+ *
+ * Before ICU 2.4 (Jitterbug 2146), UChar32 was defined
+ * to be wchar_t if that is 32 bits wide (wchar_t may be signed or unsigned)
+ * or else to be uint32_t.
+ * That is, the definition of UChar32 was platform-dependent.
+ *
+ * @see U_SENTINEL
+ * @stable ICU 2.4
+ */
+typedef int32_t UChar32;
+
+/**
+ * This value is intended for sentinel values for APIs that
+ * (take or) return single code points (UChar32).
+ * It is outside of the Unicode code point range 0..0x10ffff.
+ *
+ * For example, a "done" or "error" value in a new API
+ * could be indicated with U_SENTINEL.
+ *
+ * ICU APIs designed before ICU 2.4 usually define service-specific "done"
+ * values, mostly 0xffff.
+ * Those may need to be distinguished from
+ * actual U+ffff text contents by calling functions like
+ * CharacterIterator::hasNext() or UnicodeString::length().
+ *
+ * @return -1
+ * @see UChar32
+ * @stable ICU 2.4
+ */
+#define CBU_SENTINEL (-1)
+
+// source/common/unicode/utf.h
+
+/**
+ * Is this code point a Unicode noncharacter?
+ * @param c 32-bit code point
+ * @return TRUE or FALSE
+ * @stable ICU 2.4
+ */
+#define CBU_IS_UNICODE_NONCHAR(c) \
+ ((c)>=0xfdd0 && \
+ ((c)<=0xfdef || ((c)&0xfffe)==0xfffe) && (c)<=0x10ffff)
+
+/**
+ * Is c a Unicode code point value (0..U+10ffff)
+ * that can be assigned a character?
+ *
+ * Code points that are not characters include:
+ * - single surrogate code points (U+d800..U+dfff, 2048 code points)
+ * - the last two code points on each plane (U+__fffe and U+__ffff, 34 code points)
+ * - U+fdd0..U+fdef (new with Unicode 3.1, 32 code points)
+ * - the highest Unicode code point value is U+10ffff
+ *
+ * This means that all code points below U+d800 are character code points,
+ * and that boundary is tested first for performance.
+ *
+ * @param c 32-bit code point
+ * @return TRUE or FALSE
+ * @stable ICU 2.4
+ */
+#define CBU_IS_UNICODE_CHAR(c) \
+ ((uint32_t)(c)<0xd800 || \
+ (0xdfff<(c) && (c)<=0x10ffff && !CBU_IS_UNICODE_NONCHAR(c)))
+
+/**
+ * Is this code point a surrogate (U+d800..U+dfff)?
+ * @param c 32-bit code point
+ * @return TRUE or FALSE
+ * @stable ICU 2.4
+ */
+#define CBU_IS_SURROGATE(c) (((c)&0xfffff800)==0xd800)
+
+/**
+ * Assuming c is a surrogate code point (U_IS_SURROGATE(c)),
+ * is it a lead surrogate?
+ * @param c 32-bit code point
+ * @return TRUE or FALSE
+ * @stable ICU 2.4
+ */
+#define CBU_IS_SURROGATE_LEAD(c) (((c)&0x400)==0)
+
+// source/common/unicode/utf8.h
+
+/**
+ * Internal bit vector for 3-byte UTF-8 validity check, for use in U8_IS_VALID_LEAD3_AND_T1.
+ * Each bit indicates whether one lead byte + first trail byte pair starts a valid sequence.
+ * Lead byte E0..EF bits 3..0 are used as byte index,
+ * first trail byte bits 7..5 are used as bit index into that byte.
+ * @see U8_IS_VALID_LEAD3_AND_T1
+ * @internal
+ */
+#define CBU8_LEAD3_T1_BITS "\x20\x30\x30\x30\x30\x30\x30\x30\x30\x30\x30\x30\x30\x10\x30\x30"
+
+/**
+ * Internal 3-byte UTF-8 validity check.
+ * Non-zero if lead byte E0..EF and first trail byte 00..FF start a valid sequence.
+ * @internal
+ */
+#define CBU8_IS_VALID_LEAD3_AND_T1(lead, t1) (CBU8_LEAD3_T1_BITS[(lead)&0xf]&(1<<((uint8_t)(t1)>>5)))
+
+/**
+ * Internal bit vector for 4-byte UTF-8 validity check, for use in U8_IS_VALID_LEAD4_AND_T1.
+ * Each bit indicates whether one lead byte + first trail byte pair starts a valid sequence.
+ * First trail byte bits 7..4 are used as byte index,
+ * lead byte F0..F4 bits 2..0 are used as bit index into that byte.
+ * @see U8_IS_VALID_LEAD4_AND_T1
+ * @internal
+ */
+#define CBU8_LEAD4_T1_BITS "\x00\x00\x00\x00\x00\x00\x00\x00\x1E\x0F\x0F\x0F\x00\x00\x00\x00"
+
+/**
+ * Internal 4-byte UTF-8 validity check.
+ * Non-zero if lead byte F0..F4 and first trail byte 00..FF start a valid sequence.
+ * @internal
+ */
+#define CBU8_IS_VALID_LEAD4_AND_T1(lead, t1) (CBU8_LEAD4_T1_BITS[(uint8_t)(t1)>>4]&(1<<((lead)&7)))
+
+/**
+ * Function for handling "next code point" with error-checking.
+ *
+ * This is internal since it is not meant to be called directly by external clie
+nts;
+ * however it is U_STABLE (not U_INTERNAL) since it is called by public macros i
+n this
+ * file and thus must remain stable, and should not be hidden when other interna
+l
+ * functions are hidden (otherwise public macros would fail to compile).
+ * @internal
+ */
+UChar32
+utf8_nextCharSafeBody(const uint8_t *s, int32_t *pi, int32_t length, ::base_icu::UChar32 c, ::base_icu::UBool strict);
+
+/**
+ * Does this code unit (byte) encode a code point by itself (US-ASCII 0..0x7f)?
+ * @param c 8-bit code unit (byte)
+ * @return TRUE or FALSE
+ * @stable ICU 2.4
+ */
+#define CBU8_IS_SINGLE(c) (((c)&0x80)==0)
+
+/**
+ * Is this code unit (byte) a UTF-8 lead byte? (0xC2..0xF4)
+ * @param c 8-bit code unit (byte)
+ * @return TRUE or FALSE
+ * @stable ICU 2.4
+ */
+#define CBU8_IS_LEAD(c) ((uint8_t)((c)-0xc2)<=0x32)
+
+/**
+ * Is this code unit (byte) a UTF-8 trail byte? (0x80..0xBF)
+ * @param c 8-bit code unit (byte)
+ * @return TRUE or FALSE
+ * @stable ICU 2.4
+ */
+#define CBU8_IS_TRAIL(c) ((int8_t)(c)<-0x40)
+
+/**
+ * How many code units (bytes) are used for the UTF-8 encoding
+ * of this Unicode code point?
+ * @param c 32-bit code point
+ * @return 1..4, or 0 if c is a surrogate or not a Unicode code point
+ * @stable ICU 2.4
+ */
+#define CBU8_LENGTH(c) \
+ ((uint32_t)(c)<=0x7f ? 1 : \
+ ((uint32_t)(c)<=0x7ff ? 2 : \
+ ((uint32_t)(c)<=0xd7ff ? 3 : \
+ ((uint32_t)(c)<=0xdfff || (uint32_t)(c)>0x10ffff ? 0 : \
+ ((uint32_t)(c)<=0xffff ? 3 : 4)\
+ ) \
+ ) \
+ ) \
+ )
+
+/**
+ * The maximum number of UTF-8 code units (bytes) per Unicode code point (U+0000..U+10ffff).
+ * @return 4
+ * @stable ICU 2.4
+ */
+#define CBU8_MAX_LENGTH 4
+
+/**
+ * Get a code point from a string at a code point boundary offset,
+ * and advance the offset to the next code point boundary.
+ * (Post-incrementing forward iteration.)
+ * "Safe" macro, checks for illegal sequences and for string boundaries.
+ *
+ * The length can be negative for a NUL-terminated string.
+ *
+ * The offset may point to the lead byte of a multi-byte sequence,
+ * in which case the macro will read the whole sequence.
+ * If the offset points to a trail byte or an illegal UTF-8 sequence, then
+ * c is set to a negative value.
+ *
+ * @param s const uint8_t * string
+ * @param i int32_t string offset, must be i<length
+ * @param length int32_t string length
+ * @param c output UChar32 variable, set to <0 in case of an error
+ * @see U8_NEXT_UNSAFE
+ * @stable ICU 2.4
+ */
+#define CBU8_NEXT(s, i, length, c) { \
+ (c)=(uint8_t)(s)[(i)++]; \
+ if(!CBU8_IS_SINGLE(c)) { \
+ uint8_t __t1, __t2; \
+ if( /* handle U+0800..U+FFFF inline */ \
+ (0xe0<=(c) && (c)<0xf0) && \
+ (((i)+1)<(length) || (length)<0) && \
+ CBU8_IS_VALID_LEAD3_AND_T1((c), __t1=(s)[i]) && \
+ (__t2=(s)[(i)+1]-0x80)<=0x3f) { \
+ (c)=(((c)&0xf)<<12)|((__t1&0x3f)<<6)|__t2; \
+ (i)+=2; \
+ } else if( /* handle U+0080..U+07FF inline */ \
+ ((c)<0xe0 && (c)>=0xc2) && \
+ ((i)!=(length)) && \
+ (__t1=(s)[i]-0x80)<=0x3f) { \
+ (c)=(((c)&0x1f)<<6)|__t1; \
+ ++(i); \
+ } else { \
+ /* function call for "complicated" and error cases */ \
+ (c)=::base_icu::utf8_nextCharSafeBody((const uint8_t *)s, &(i), (length), c, -1); \
+ } \
+ } \
+}
+
+/**
+ * Append a code point to a string, overwriting 1 to 4 bytes.
+ * The offset points to the current end of the string contents
+ * and is advanced (post-increment).
+ * "Unsafe" macro, assumes a valid code point and sufficient space in the string.
+ * Otherwise, the result is undefined.
+ *
+ * @param s const uint8_t * string buffer
+ * @param i string offset
+ * @param c code point to append
+ * @see U8_APPEND
+ * @stable ICU 2.4
+ */
+#define CBU8_APPEND_UNSAFE(s, i, c) { \
+ if((uint32_t)(c)<=0x7f) { \
+ (s)[(i)++]=(uint8_t)(c); \
+ } else { \
+ if((uint32_t)(c)<=0x7ff) { \
+ (s)[(i)++]=(uint8_t)(((c)>>6)|0xc0); \
+ } else { \
+ if((uint32_t)(c)<=0xffff) { \
+ (s)[(i)++]=(uint8_t)(((c)>>12)|0xe0); \
+ } else { \
+ (s)[(i)++]=(uint8_t)(((c)>>18)|0xf0); \
+ (s)[(i)++]=(uint8_t)((((c)>>12)&0x3f)|0x80); \
+ } \
+ (s)[(i)++]=(uint8_t)((((c)>>6)&0x3f)|0x80); \
+ } \
+ (s)[(i)++]=(uint8_t)(((c)&0x3f)|0x80); \
+ } \
+}
+
+// source/common/unicode/utf16.h
+
+/**
+ * Does this code unit alone encode a code point (BMP, not a surrogate)?
+ * @param c 16-bit code unit
+ * @return TRUE or FALSE
+ * @stable ICU 2.4
+ */
+#define CBU16_IS_SINGLE(c) !CBU_IS_SURROGATE(c)
+
+/**
+ * Is this code unit a lead surrogate (U+d800..U+dbff)?
+ * @param c 16-bit code unit
+ * @return TRUE or FALSE
+ * @stable ICU 2.4
+ */
+#define CBU16_IS_LEAD(c) (((c)&0xfffffc00)==0xd800)
+
+/**
+ * Is this code unit a trail surrogate (U+dc00..U+dfff)?
+ * @param c 16-bit code unit
+ * @return TRUE or FALSE
+ * @stable ICU 2.4
+ */
+#define CBU16_IS_TRAIL(c) (((c)&0xfffffc00)==0xdc00)
+
+/**
+ * Is this code unit a surrogate (U+d800..U+dfff)?
+ * @param c 16-bit code unit
+ * @return TRUE or FALSE
+ * @stable ICU 2.4
+ */
+#define CBU16_IS_SURROGATE(c) CBU_IS_SURROGATE(c)
+
+/**
+ * Assuming c is a surrogate code point (U16_IS_SURROGATE(c)),
+ * is it a lead surrogate?
+ * @param c 16-bit code unit
+ * @return TRUE or FALSE
+ * @stable ICU 2.4
+ */
+#define CBU16_IS_SURROGATE_LEAD(c) (((c)&0x400)==0)
+
+/**
+ * Helper constant for U16_GET_SUPPLEMENTARY.
+ * @internal
+ */
+#define CBU16_SURROGATE_OFFSET ((0xd800<<10UL)+0xdc00-0x10000)
+
+/**
+ * Get a supplementary code point value (U+10000..U+10ffff)
+ * from its lead and trail surrogates.
+ * The result is undefined if the input values are not
+ * lead and trail surrogates.
+ *
+ * @param lead lead surrogate (U+d800..U+dbff)
+ * @param trail trail surrogate (U+dc00..U+dfff)
+ * @return supplementary code point (U+10000..U+10ffff)
+ * @stable ICU 2.4
+ */
+#define CBU16_GET_SUPPLEMENTARY(lead, trail) \
+ (((::base_icu::UChar32)(lead)<<10UL)+(::base_icu::UChar32)(trail)-CBU16_SURROGATE_OFFSET)
+
+/**
+ * Get the lead surrogate (0xd800..0xdbff) for a
+ * supplementary code point (0x10000..0x10ffff).
+ * @param supplementary 32-bit code point (U+10000..U+10ffff)
+ * @return lead surrogate (U+d800..U+dbff) for supplementary
+ * @stable ICU 2.4
+ */
+#define CBU16_LEAD(supplementary) (::base_icu::UChar)(((supplementary)>>10)+0xd7c0)
+
+/**
+ * Get the trail surrogate (0xdc00..0xdfff) for a
+ * supplementary code point (0x10000..0x10ffff).
+ * @param supplementary 32-bit code point (U+10000..U+10ffff)
+ * @return trail surrogate (U+dc00..U+dfff) for supplementary
+ * @stable ICU 2.4
+ */
+#define CBU16_TRAIL(supplementary) (::base_icu::UChar)(((supplementary)&0x3ff)|0xdc00)
+
+/**
+ * How many 16-bit code units are used to encode this Unicode code point? (1 or 2)
+ * The result is not defined if c is not a Unicode code point (U+0000..U+10ffff).
+ * @param c 32-bit code point
+ * @return 1 or 2
+ * @stable ICU 2.4
+ */
+#define CBU16_LENGTH(c) ((uint32_t)(c)<=0xffff ? 1 : 2)
+
+/**
+ * The maximum number of 16-bit code units per Unicode code point (U+0000..U+10ffff).
+ * @return 2
+ * @stable ICU 2.4
+ */
+#define CBU16_MAX_LENGTH 2
+
+/**
+ * Get a code point from a string at a code point boundary offset,
+ * and advance the offset to the next code point boundary.
+ * (Post-incrementing forward iteration.)
+ * "Safe" macro, handles unpaired surrogates and checks for string boundaries.
+ *
+ * The length can be negative for a NUL-terminated string.
+ *
+ * The offset may point to the lead surrogate unit
+ * for a supplementary code point, in which case the macro will read
+ * the following trail surrogate as well.
+ * If the offset points to a trail surrogate or
+ * to a single, unpaired lead surrogate, then c is set to that unpaired surrogate.
+ *
+ * @param s const UChar * string
+ * @param i string offset, must be i<length
+ * @param length string length
+ * @param c output UChar32 variable
+ * @see U16_NEXT_UNSAFE
+ * @stable ICU 2.4
+ */
+#define CBU16_NEXT(s, i, length, c) { \
+ (c)=(s)[(i)++]; \
+ if(CBU16_IS_LEAD(c)) { \
+ uint16_t __c2; \
+ if((i)!=(length) && CBU16_IS_TRAIL(__c2=(s)[(i)])) { \
+ ++(i); \
+ (c)=CBU16_GET_SUPPLEMENTARY((c), __c2); \
+ } \
+ } \
+}
+
+/**
+ * Append a code point to a string, overwriting 1 or 2 code units.
+ * The offset points to the current end of the string contents
+ * and is advanced (post-increment).
+ * "Unsafe" macro, assumes a valid code point and sufficient space in the string.
+ * Otherwise, the result is undefined.
+ *
+ * @param s const UChar * string buffer
+ * @param i string offset
+ * @param c code point to append
+ * @see U16_APPEND
+ * @stable ICU 2.4
+ */
+#define CBU16_APPEND_UNSAFE(s, i, c) { \
+ if((uint32_t)(c)<=0xffff) { \
+ (s)[(i)++]=(uint16_t)(c); \
+ } else { \
+ (s)[(i)++]=(uint16_t)(((c)>>10)+0xd7c0); \
+ (s)[(i)++]=(uint16_t)(((c)&0x3ff)|0xdc00); \
+ } \
+}
+
+} // namesapce base_icu
+
+#endif // BASE_THIRD_PARTY_ICU_ICU_UTF_H_