aboutsummaryrefslogtreecommitdiff
path: root/lib
diff options
context:
space:
mode:
Diffstat (limited to 'lib')
-rw-r--r--lib/AST/CMakeLists.txt1
-rw-r--r--lib/AST/CommentLexer.cpp6
-rw-r--r--lib/Basic/CMakeLists.txt2
-rw-r--r--lib/Basic/ConvertUTF.c571
-rw-r--r--lib/Basic/ConvertUTFWrapper.cpp76
-rw-r--r--lib/CodeGen/CGExpr.cpp3
-rw-r--r--lib/CodeGen/CodeGenModule.cpp3
-rw-r--r--lib/Frontend/TextDiagnostic.cpp2
-rw-r--r--lib/Lex/Lexer.cpp20
-rw-r--r--lib/Lex/LiteralSupport.cpp3
-rw-r--r--lib/Lex/Preprocessor.cpp4
-rw-r--r--lib/Sema/SemaChecking.cpp2
12 files changed, 25 insertions, 668 deletions
diff --git a/lib/AST/CMakeLists.txt b/lib/AST/CMakeLists.txt
index 923c519d49..328f385153 100644
--- a/lib/AST/CMakeLists.txt
+++ b/lib/AST/CMakeLists.txt
@@ -68,6 +68,7 @@ add_dependencies(clangAST
ClangCommentNodes
ClangCommentHTMLTags
ClangCommentHTMLTagsProperties
+ ClangCommentHTMLNamedCharacterReferences
ClangDeclNodes
ClangDiagnosticAST
ClangDiagnosticComment
diff --git a/lib/AST/CommentLexer.cpp b/lib/AST/CommentLexer.cpp
index 464771340d..b92b1fb33d 100644
--- a/lib/AST/CommentLexer.cpp
+++ b/lib/AST/CommentLexer.cpp
@@ -1,8 +1,8 @@
#include "clang/AST/CommentLexer.h"
#include "clang/AST/CommentCommandTraits.h"
-#include "clang/Basic/ConvertUTF.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/ADT/StringSwitch.h"
+#include "llvm/Support/ConvertUTF.h"
#include "llvm/Support/ErrorHandling.h"
namespace clang {
@@ -48,7 +48,7 @@ static unsigned getCodePoint(StringRef Name) {
StringRef Lexer::helperResolveHTMLHexCharacterReference(unsigned CodePoint) const {
char *Resolved = Allocator.Allocate<char>(UNI_MAX_UTF8_BYTES_PER_CODE_POINT);
char *ResolvedPtr = Resolved;
- if (ConvertCodePointToUTF8(CodePoint, ResolvedPtr))
+ if (llvm::ConvertCodePointToUTF8(CodePoint, ResolvedPtr))
return StringRef(Resolved, ResolvedPtr - Resolved);
else
return StringRef();
@@ -223,7 +223,7 @@ StringRef Lexer::resolveHTMLDecimalCharacterReference(StringRef Name) const {
char *Resolved = Allocator.Allocate<char>(UNI_MAX_UTF8_BYTES_PER_CODE_POINT);
char *ResolvedPtr = Resolved;
- if (ConvertCodePointToUTF8(CodePoint, ResolvedPtr))
+ if (llvm::ConvertCodePointToUTF8(CodePoint, ResolvedPtr))
return StringRef(Resolved, ResolvedPtr - Resolved);
else
return StringRef();
diff --git a/lib/Basic/CMakeLists.txt b/lib/Basic/CMakeLists.txt
index 19ec875c05..7c5e42c984 100644
--- a/lib/Basic/CMakeLists.txt
+++ b/lib/Basic/CMakeLists.txt
@@ -2,8 +2,6 @@ set(LLVM_LINK_COMPONENTS mc)
add_clang_library(clangBasic
Builtins.cpp
- ConvertUTF.c
- ConvertUTFWrapper.cpp
Diagnostic.cpp
DiagnosticIDs.cpp
FileManager.cpp
diff --git a/lib/Basic/ConvertUTF.c b/lib/Basic/ConvertUTF.c
deleted file mode 100644
index d16965ddd8..0000000000
--- a/lib/Basic/ConvertUTF.c
+++ /dev/null
@@ -1,571 +0,0 @@
-/*===--- ConvertUTF.c - Universal Character Names conversions ---------------===
- *
- * The LLVM Compiler Infrastructure
- *
- * This file is distributed under the University of Illinois Open Source
- * License. See LICENSE.TXT for details.
- *
- *===------------------------------------------------------------------------=*/
-/*
- * Copyright 2001-2004 Unicode, Inc.
- *
- * Disclaimer
- *
- * This source code is provided as is by Unicode, Inc. No claims are
- * made as to fitness for any particular purpose. No warranties of any
- * kind are expressed or implied. The recipient agrees to determine
- * applicability of information provided. If this file has been
- * purchased on magnetic or optical media from Unicode, Inc., the
- * sole remedy for any claim will be exchange of defective media
- * within 90 days of receipt.
- *
- * Limitations on Rights to Redistribute This Code
- *
- * Unicode, Inc. hereby grants the right to freely use the information
- * supplied in this file in the creation of products supporting the
- * Unicode Standard, and to make copies of this file in any form
- * for internal or external distribution as long as this notice
- * remains attached.
- */
-
-/* ---------------------------------------------------------------------
-
- Conversions between UTF32, UTF-16, and UTF-8. Source code file.
- Author: Mark E. Davis, 1994.
- Rev History: Rick McGowan, fixes & updates May 2001.
- Sept 2001: fixed const & error conditions per
- mods suggested by S. Parent & A. Lillich.
- June 2002: Tim Dodd added detection and handling of incomplete
- source sequences, enhanced error detection, added casts
- to eliminate compiler warnings.
- July 2003: slight mods to back out aggressive FFFE detection.
- Jan 2004: updated switches in from-UTF8 conversions.
- Oct 2004: updated to use UNI_MAX_LEGAL_UTF32 in UTF-32 conversions.
-
- See the header file "ConvertUTF.h" for complete documentation.
-
------------------------------------------------------------------------- */
-
-
-#include "clang/Basic/ConvertUTF.h"
-#ifdef CVTUTF_DEBUG
-#include <stdio.h>
-#endif
-
-static const int halfShift = 10; /* used for shifting by 10 bits */
-
-static const UTF32 halfBase = 0x0010000UL;
-static const UTF32 halfMask = 0x3FFUL;
-
-#define UNI_SUR_HIGH_START (UTF32)0xD800
-#define UNI_SUR_HIGH_END (UTF32)0xDBFF
-#define UNI_SUR_LOW_START (UTF32)0xDC00
-#define UNI_SUR_LOW_END (UTF32)0xDFFF
-#define false 0
-#define true 1
-
-/* --------------------------------------------------------------------- */
-
-/*
- * Index into the table below with the first byte of a UTF-8 sequence to
- * get the number of trailing bytes that are supposed to follow it.
- * Note that *legal* UTF-8 values can't have 4 or 5-bytes. The table is
- * left as-is for anyone who may want to do such conversion, which was
- * allowed in earlier algorithms.
- */
-static const char trailingBytesForUTF8[256] = {
- 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
- 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
- 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
- 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
- 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
- 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
- 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
- 2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, 3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5
-};
-
-/*
- * Magic values subtracted from a buffer value during UTF8 conversion.
- * This table contains as many values as there might be trailing bytes
- * in a UTF-8 sequence.
- */
-static const UTF32 offsetsFromUTF8[6] = { 0x00000000UL, 0x00003080UL, 0x000E2080UL,
- 0x03C82080UL, 0xFA082080UL, 0x82082080UL };
-
-/*
- * Once the bits are split out into bytes of UTF-8, this is a mask OR-ed
- * into the first byte, depending on how many bytes follow. There are
- * as many entries in this table as there are UTF-8 sequence types.
- * (I.e., one byte sequence, two byte... etc.). Remember that sequencs
- * for *legal* UTF-8 will be 4 or fewer bytes total.
- */
-static const UTF8 firstByteMark[7] = { 0x00, 0x00, 0xC0, 0xE0, 0xF0, 0xF8, 0xFC };
-
-/* --------------------------------------------------------------------- */
-
-/* The interface converts a whole buffer to avoid function-call overhead.
- * Constants have been gathered. Loops & conditionals have been removed as
- * much as possible for efficiency, in favor of drop-through switches.
- * (See "Note A" at the bottom of the file for equivalent code.)
- * If your compiler supports it, the "isLegalUTF8" call can be turned
- * into an inline function.
- */
-
-
-/* --------------------------------------------------------------------- */
-
-ConversionResult ConvertUTF32toUTF16 (
- const UTF32** sourceStart, const UTF32* sourceEnd,
- UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags) {
- ConversionResult result = conversionOK;
- const UTF32* source = *sourceStart;
- UTF16* target = *targetStart;
- while (source < sourceEnd) {
- UTF32 ch;
- if (target >= targetEnd) {
- result = targetExhausted; break;
- }
- ch = *source++;
- if (ch <= UNI_MAX_BMP) { /* Target is a character <= 0xFFFF */
- /* UTF-16 surrogate values are illegal in UTF-32; 0xffff or 0xfffe are both reserved values */
- if (ch >= UNI_SUR_HIGH_START && ch <= UNI_SUR_LOW_END) {
- if (flags == strictConversion) {
- --source; /* return to the illegal value itself */
- result = sourceIllegal;
- break;
- } else {
- *target++ = UNI_REPLACEMENT_CHAR;
- }
- } else {
- *target++ = (UTF16)ch; /* normal case */
- }
- } else if (ch > UNI_MAX_LEGAL_UTF32) {
- if (flags == strictConversion) {
- result = sourceIllegal;
- } else {
- *target++ = UNI_REPLACEMENT_CHAR;
- }
- } else {
- /* target is a character in range 0xFFFF - 0x10FFFF. */
- if (target + 1 >= targetEnd) {
- --source; /* Back up source pointer! */
- result = targetExhausted; break;
- }
- ch -= halfBase;
- *target++ = (UTF16)((ch >> halfShift) + UNI_SUR_HIGH_START);
- *target++ = (UTF16)((ch & halfMask) + UNI_SUR_LOW_START);
- }
- }
- *sourceStart = source;
- *targetStart = target;
- return result;
-}
-
-/* --------------------------------------------------------------------- */
-
-ConversionResult ConvertUTF16toUTF32 (
- const UTF16** sourceStart, const UTF16* sourceEnd,
- UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags) {
- ConversionResult result = conversionOK;
- const UTF16* source = *sourceStart;
- UTF32* target = *targetStart;
- UTF32 ch, ch2;
- while (source < sourceEnd) {
- const UTF16* oldSource = source; /* In case we have to back up because of target overflow. */
- ch = *source++;
- /* If we have a surrogate pair, convert to UTF32 first. */
- if (ch >= UNI_SUR_HIGH_START && ch <= UNI_SUR_HIGH_END) {
- /* If the 16 bits following the high surrogate are in the source buffer... */
- if (source < sourceEnd) {
- ch2 = *source;
- /* If it's a low surrogate, convert to UTF32. */
- if (ch2 >= UNI_SUR_LOW_START && ch2 <= UNI_SUR_LOW_END) {
- ch = ((ch - UNI_SUR_HIGH_START) << halfShift)
- + (ch2 - UNI_SUR_LOW_START) + halfBase;
- ++source;
- } else if (flags == strictConversion) { /* it's an unpaired high surrogate */
- --source; /* return to the illegal value itself */
- result = sourceIllegal;
- break;
- }
- } else { /* We don't have the 16 bits following the high surrogate. */
- --source; /* return to the high surrogate */
- result = sourceExhausted;
- break;
- }
- } else if (flags == strictConversion) {
- /* UTF-16 surrogate values are illegal in UTF-32 */
- if (ch >= UNI_SUR_LOW_START && ch <= UNI_SUR_LOW_END) {
- --source; /* return to the illegal value itself */
- result = sourceIllegal;
- break;
- }
- }
- if (target >= targetEnd) {
- source = oldSource; /* Back up source pointer! */
- result = targetExhausted; break;
- }
- *target++ = ch;
- }
- *sourceStart = source;
- *targetStart = target;
-#ifdef CVTUTF_DEBUG
-if (result == sourceIllegal) {
- fprintf(stderr, "ConvertUTF16toUTF32 illegal seq 0x%04x,%04x\n", ch, ch2);
- fflush(stderr);
-}
-#endif
- return result;
-}
-ConversionResult ConvertUTF16toUTF8 (
- const UTF16** sourceStart, const UTF16* sourceEnd,
- UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags) {
- ConversionResult result = conversionOK;
- const UTF16* source = *sourceStart;
- UTF8* target = *targetStart;
- while (source < sourceEnd) {
- UTF32 ch;
- unsigned short bytesToWrite = 0;
- const UTF32 byteMask = 0xBF;
- const UTF32 byteMark = 0x80;
- const UTF16* oldSource = source; /* In case we have to back up because of target overflow. */
- ch = *source++;
- /* If we have a surrogate pair, convert to UTF32 first. */
- if (ch >= UNI_SUR_HIGH_START && ch <= UNI_SUR_HIGH_END) {
- /* If the 16 bits following the high surrogate are in the source buffer... */
- if (source < sourceEnd) {
- UTF32 ch2 = *source;
- /* If it's a low surrogate, convert to UTF32. */
- if (ch2 >= UNI_SUR_LOW_START && ch2 <= UNI_SUR_LOW_END) {
- ch = ((ch - UNI_SUR_HIGH_START) << halfShift)
- + (ch2 - UNI_SUR_LOW_START) + halfBase;
- ++source;
- } else if (flags == strictConversion) { /* it's an unpaired high surrogate */
- --source; /* return to the illegal value itself */
- result = sourceIllegal;
- break;
- }
- } else { /* We don't have the 16 bits following the high surrogate. */
- --source; /* return to the high surrogate */
- result = sourceExhausted;
- break;
- }
- } else if (flags == strictConversion) {
- /* UTF-16 surrogate values are illegal in UTF-32 */
- if (ch >= UNI_SUR_LOW_START && ch <= UNI_SUR_LOW_END) {
- --source; /* return to the illegal value itself */
- result = sourceIllegal;
- break;
- }
- }
- /* Figure out how many bytes the result will require */
- if (ch < (UTF32)0x80) { bytesToWrite = 1;
- } else if (ch < (UTF32)0x800) { bytesToWrite = 2;
- } else if (ch < (UTF32)0x10000) { bytesToWrite = 3;
- } else if (ch < (UTF32)0x110000) { bytesToWrite = 4;
- } else { bytesToWrite = 3;
- ch = UNI_REPLACEMENT_CHAR;
- }
-
- target += bytesToWrite;
- if (target > targetEnd) {
- source = oldSource; /* Back up source pointer! */
- target -= bytesToWrite; result = targetExhausted; break;
- }
- switch (bytesToWrite) { /* note: everything falls through. */
- case 4: *--target = (UTF8)((ch | byteMark) & byteMask); ch >>= 6;
- case 3: *--target = (UTF8)((ch | byteMark) & byteMask); ch >>= 6;
- case 2: *--target = (UTF8)((ch | byteMark) & byteMask); ch >>= 6;
- case 1: *--target = (UTF8)(ch | firstByteMark[bytesToWrite]);
- }
- target += bytesToWrite;
- }
- *sourceStart = source;
- *targetStart = target;
- return result;
-}
-
-/* --------------------------------------------------------------------- */
-
-ConversionResult ConvertUTF32toUTF8 (
- const UTF32** sourceStart, const UTF32* sourceEnd,
- UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags) {
- ConversionResult result = conversionOK;
- const UTF32* source = *sourceStart;
- UTF8* target = *targetStart;
- while (source < sourceEnd) {
- UTF32 ch;
- unsigned short bytesToWrite = 0;
- const UTF32 byteMask = 0xBF;
- const UTF32 byteMark = 0x80;
- ch = *source++;
- if (flags == strictConversion ) {
- /* UTF-16 surrogate values are illegal in UTF-32 */
- if (ch >= UNI_SUR_HIGH_START && ch <= UNI_SUR_LOW_END) {
- --source; /* return to the illegal value itself */
- result = sourceIllegal;
- break;
- }
- }
- /*
- * Figure out how many bytes the result will require. Turn any
- * illegally large UTF32 things (> Plane 17) into replacement chars.
- */
- if (ch < (UTF32)0x80) { bytesToWrite = 1;
- } else if (ch < (UTF32)0x800) { bytesToWrite = 2;
- } else if (ch < (UTF32)0x10000) { bytesToWrite = 3;
- } else if (ch <= UNI_MAX_LEGAL_UTF32) { bytesToWrite = 4;
- } else { bytesToWrite = 3;
- ch = UNI_REPLACEMENT_CHAR;
- result = sourceIllegal;
- }
-
- target += bytesToWrite;
- if (target > targetEnd) {
- --source; /* Back up source pointer! */
- target -= bytesToWrite; result = targetExhausted; break;
- }
- switch (bytesToWrite) { /* note: everything falls through. */
- case 4: *--target = (UTF8)((ch | byteMark) & byteMask); ch >>= 6;
- case 3: *--target = (UTF8)((ch | byteMark) & byteMask); ch >>= 6;
- case 2: *--target = (UTF8)((ch | byteMark) & byteMask); ch >>= 6;
- case 1: *--target = (UTF8) (ch | firstByteMark[bytesToWrite]);
- }
- target += bytesToWrite;
- }
- *sourceStart = source;
- *targetStart = target;
- return result;
-}
-
-/* --------------------------------------------------------------------- */
-
-/*
- * Utility routine to tell whether a sequence of bytes is legal UTF-8.
- * This must be called with the length pre-determined by the first byte.
- * If not calling this from ConvertUTF8to*, then the length can be set by:
- * length = trailingBytesForUTF8[*source]+1;
- * and the sequence is illegal right away if there aren't that many bytes
- * available.
- * If presented with a length > 4, this returns false. The Unicode
- * definition of UTF-8 goes up to 4-byte sequences.
- */
-
-static Boolean isLegalUTF8(const UTF8 *source, int length) {
- UTF8 a;
- const UTF8 *srcptr = source+length;
- switch (length) {
- default: return false;
- /* Everything else falls through when "true"... */
- case 4: if ((a = (*--srcptr)) < 0x80 || a > 0xBF) return false;
- case 3: if ((a = (*--srcptr)) < 0x80 || a > 0xBF) return false;
- case 2: if ((a = (*--srcptr)) < 0x80 || a > 0xBF) return false;
-
- switch (*source) {
- /* no fall-through in this inner switch */
- case 0xE0: if (a < 0xA0) return false; break;
- case 0xED: if (a > 0x9F) return false; break;
- case 0xF0: if (a < 0x90) return false; break;
- case 0xF4: if (a > 0x8F) return false; break;
- default: if (a < 0x80) return false;
- }
-
- case 1: if (*source >= 0x80 && *source < 0xC2) return false;
- }
- if (*source > 0xF4) return false;
- return true;
-}
-
-/* --------------------------------------------------------------------- */
-
-/*
- * Exported function to return whether a UTF-8 sequence is legal or not.
- * This is not used here; it's just exported.
- */
-Boolean isLegalUTF8Sequence(const UTF8 *source, const UTF8 *sourceEnd) {
- int length = trailingBytesForUTF8[*source]+1;
- if (length > sourceEnd - source) {
- return false;
- }
- return isLegalUTF8(source, length);
-}
-
-/* --------------------------------------------------------------------- */
-
-/*
- * Exported function to return the total number of bytes in a codepoint
- * represented in UTF-8, given the value of the first byte.
- */
-unsigned getNumBytesForUTF8(UTF8 first) {
- return trailingBytesForUTF8[first] + 1;
-}
-
-/* --------------------------------------------------------------------- */
-
-/*
- * Exported function to return whether a UTF-8 string is legal or not.
- * This is not used here; it's just exported.
- */
-Boolean isLegalUTF8String(const UTF8 **source, const UTF8 *sourceEnd) {
- while (*source != sourceEnd) {
- int length = trailingBytesForUTF8[**source] + 1;
- if (length > sourceEnd - *source || !isLegalUTF8(*source, length))
- return false;
- *source += length;
- }
- return true;
-}
-
-/* --------------------------------------------------------------------- */
-
-ConversionResult ConvertUTF8toUTF16 (
- const UTF8** sourceStart, const UTF8* sourceEnd,
- UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags) {
- ConversionResult result = conversionOK;
- const UTF8* source = *sourceStart;
- UTF16* target = *targetStart;
- while (source < sourceEnd) {
- UTF32 ch = 0;
- unsigned short extraBytesToRead = trailingBytesForUTF8[*source];
- if (extraBytesToRead >= sourceEnd - source) {
- result = sourceExhausted; break;
- }
- /* Do this check whether lenient or strict */
- if (!isLegalUTF8(source, extraBytesToRead+1)) {
- result = sourceIllegal;
- break;
- }
- /*
- * The cases all fall through. See "Note A" below.
- */
- switch (extraBytesToRead) {
- case 5: ch += *source++; ch <<= 6; /* remember, illegal UTF-8 */
- case 4: ch += *source++; ch <<= 6; /* remember, illegal UTF-8 */
- case 3: ch += *source++; ch <<= 6;
- case 2: ch += *source++; ch <<= 6;
- case 1: ch += *source++; ch <<= 6;
- case 0: ch += *source++;
- }
- ch -= offsetsFromUTF8[extraBytesToRead];
-
- if (target >= targetEnd) {
- source -= (extraBytesToRead+1); /* Back up source pointer! */
- result = targetExhausted; break;
- }
- if (ch <= UNI_MAX_BMP) { /* Target is a character <= 0xFFFF */
- /* UTF-16 surrogate values are illegal in UTF-32 */
- if (ch >= UNI_SUR_HIGH_START && ch <= UNI_SUR_LOW_END) {
- if (flags == strictConversion) {
- source -= (extraBytesToRead+1); /* return to the illegal value itself */
- result = sourceIllegal;
- break;
- } else {
- *target++ = UNI_REPLACEMENT_CHAR;
- }
- } else {
- *target++ = (UTF16)ch; /* normal case */
- }
- } else if (ch > UNI_MAX_UTF16) {
- if (flags == strictConversion) {
- result = sourceIllegal;
- source -= (extraBytesToRead+1); /* return to the start */
- break; /* Bail out; shouldn't continue */
- } else {
- *target++ = UNI_REPLACEMENT_CHAR;
- }
- } else {
- /* target is a character in range 0xFFFF - 0x10FFFF. */
- if (target + 1 >= targetEnd) {
- source -= (extraBytesToRead+1); /* Back up source pointer! */
- result = targetExhausted; break;
- }
- ch -= halfBase;
- *target++ = (UTF16)((ch >> halfShift) + UNI_SUR_HIGH_START);
- *target++ = (UTF16)((ch & halfMask) + UNI_SUR_LOW_START);
- }
- }
- *sourceStart = source;
- *targetStart = target;
- return result;
-}
-
-/* --------------------------------------------------------------------- */
-
-ConversionResult ConvertUTF8toUTF32 (
- const UTF8** sourceStart, const UTF8* sourceEnd,
- UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags) {
- ConversionResult result = conversionOK;
- const UTF8* source = *sourceStart;
- UTF32* target = *targetStart;
- while (source < sourceEnd) {
- UTF32 ch = 0;
- unsigned short extraBytesToRead = trailingBytesForUTF8[*source];
- if (extraBytesToRead >= sourceEnd - source) {
- result = sourceExhausted; break;
- }
- /* Do this check whether lenient or strict */
- if (!isLegalUTF8(source, extraBytesToRead+1)) {
- result = sourceIllegal;
- break;
- }
- /*
- * The cases all fall through. See "Note A" below.
- */
- switch (extraBytesToRead) {
- case 5: ch += *source++; ch <<= 6;
- case 4: ch += *source++; ch <<= 6;
- case 3: ch += *source++; ch <<= 6;
- case 2: ch += *source++; ch <<= 6;
- case 1: ch += *source++; ch <<= 6;
- case 0: ch += *source++;
- }
- ch -= offsetsFromUTF8[extraBytesToRead];
-
- if (target >= targetEnd) {
- source -= (extraBytesToRead+1); /* Back up the source pointer! */
- result = targetExhausted; break;
- }
- if (ch <= UNI_MAX_LEGAL_UTF32) {
- /*
- * UTF-16 surrogate values are illegal in UTF-32, and anything
- * over Plane 17 (> 0x10FFFF) is illegal.
- */
- if (ch >= UNI_SUR_HIGH_START && ch <= UNI_SUR_LOW_END) {
- if (flags == strictConversion) {
- source -= (extraBytesToRead+1); /* return to the illegal value itself */
- result = sourceIllegal;
- break;
- } else {
- *target++ = UNI_REPLACEMENT_CHAR;
- }
- } else {
- *target++ = ch;
- }
- } else { /* i.e., ch > UNI_MAX_LEGAL_UTF32 */
- result = sourceIllegal;
- *target++ = UNI_REPLACEMENT_CHAR;
- }
- }
- *sourceStart = source;
- *targetStart = target;
- return result;
-}
-
-/* ---------------------------------------------------------------------
-
- Note A.
- The fall-through switches in UTF-8 reading code save a
- temp variable, some decrements & conditionals. The switches
- are equivalent to the following loop:
- {
- int tmpBytesToRead = extraBytesToRead+1;
- do {
- ch += *source++;
- --tmpBytesToRead;
- if (tmpBytesToRead) ch <<= 6;
- } while (tmpBytesToRead > 0);
- }
- In UTF-8 writing code, the switches on "bytesToWrite" are
- similarly unrolled loops.
-
- --------------------------------------------------------------------- */
diff --git a/lib/Basic/ConvertUTFWrapper.cpp b/lib/Basic/ConvertUTFWrapper.cpp
deleted file mode 100644
index 6be3828d28..0000000000
--- a/lib/Basic/ConvertUTFWrapper.cpp
+++ /dev/null
@@ -1,76 +0,0 @@
-//===-- ConvertUTFWrapper.cpp - Wrap ConvertUTF.h with clang data types -----===
-//
-// The LLVM Compiler Infrastructure
-//
-// This file is distributed under the University of Illinois Open Source
-// License. See LICENSE.TXT for details.
-//
-//===----------------------------------------------------------------------===//
-
-#include "clang/Basic/ConvertUTF.h"
-#include "clang/Basic/LLVM.h"
-
-namespace clang {
-
-bool ConvertUTF8toWide(unsigned WideCharWidth, llvm::StringRef Source,
- char *&ResultPtr, const UTF8 *&ErrorPtr) {
- assert(WideCharWidth == 1 || WideCharWidth == 2 || WideCharWidth == 4);
- ConversionResult result = conversionOK;
- // Copy the character span over.
- if (WideCharWidth == 1) {
- const UTF8 *Pos = reinterpret_cast<const UTF8*>(Source.begin());
- if (!isLegalUTF8String(&Pos, reinterpret_cast<const UTF8*>(Source.end()))) {
- result = sourceIllegal;
- ErrorPtr = Pos;
- } else {
- memcpy(ResultPtr, Source.data(), Source.size());
- ResultPtr += Source.size();
- }
- } else if (WideCharWidth == 2) {
- const UTF8 *sourceStart = (const UTF8*)Source.data();
- // FIXME: Make the type of the result buffer correct instead of
- // using reinterpret_cast.
- UTF16 *targetStart = reinterpret_cast<UTF16*>(ResultPtr);
- ConversionFlags flags = strictConversion;
- result = ConvertUTF8toUTF16(
- &sourceStart, sourceStart + Source.size(),
- &targetStart, targetStart + 2*Source.size(), flags);
- if (result == conversionOK)
- ResultPtr = reinterpret_cast<char*>(targetStart);
- else
- ErrorPtr = sourceStart;
- } else if (WideCharWidth == 4) {
- const UTF8 *sourceStart = (const UTF8*)Source.data();
- // FIXME: Make the type of the result buffer correct instead of
- // using reinterpret_cast.
- UTF32 *targetStart = reinterpret_cast<UTF32*>(ResultPtr);
- ConversionFlags flags = strictConversion;
- result = ConvertUTF8toUTF32(
- &sourceStart, sourceStart + Source.size(),
- &targetStart, targetStart + 4*Source.size(), flags);
- if (result == conversionOK)
- ResultPtr = reinterpret_cast<char*>(targetStart);
- else
- ErrorPtr = sourceStart;
- }
- assert((result != targetExhausted)
- && "ConvertUTF8toUTFXX exhausted target buffer");
- return result == conversionOK;
-}
-
-bool ConvertCodePointToUTF8(unsigned Source, char *&ResultPtr) {
- const UTF32 *SourceStart = &Source;
- const UTF32 *SourceEnd = SourceStart + 1;
- UTF8 *TargetStart = reinterpret_cast<UTF8 *>(ResultPtr);
- UTF8 *TargetEnd = TargetStart + 4;
- ConversionResult CR = ConvertUTF32toUTF8(&SourceStart, SourceEnd,
- &TargetStart, TargetEnd,
- strictConversion);
- if (CR != conversionOK)
- return false;
-
- ResultPtr = reinterpret_cast<char*>(TargetStart);
- return true;
-}
-
-} // end namespace clang
diff --git a/lib/CodeGen/CGExpr.cpp b/lib/CodeGen/CGExpr.cpp
index aad877134d..71de8fa241 100644
--- a/lib/CodeGen/CGExpr.cpp
+++ b/lib/CodeGen/CGExpr.cpp
@@ -21,13 +21,14 @@
#include "TargetInfo.h"
#include "clang/AST/ASTContext.h"
#include "clang/AST/DeclObjC.h"
-#include "clang/Basic/ConvertUTF.h"
#include "clang/Frontend/CodeGenOptions.h"
#include "llvm/ADT/Hashing.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/Intrinsics.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/IR/MDBuilder.h"
+#include "llvm/Support/ConvertUTF.h"
+
using namespace clang;
using namespace CodeGen;
diff --git a/lib/CodeGen/CodeGenModule.cpp b/lib/CodeGen/CodeGenModule.cpp
index da419dde03..23646b50ba 100644
--- a/lib/CodeGen/CodeGenModule.cpp
+++ b/lib/CodeGen/CodeGenModule.cpp
@@ -30,7 +30,6 @@
#include "clang/AST/RecordLayout.h"
#include "clang/AST/RecursiveASTVisitor.h"
#include "clang/Basic/Builtins.h"
-#include "clang/Basic/ConvertUTF.h"
#include "clang/Basic/Diagnostic.h"
#include "clang/Basic/Module.h"
#include "clang/Basic/SourceManager.h"
@@ -44,8 +43,10 @@
#include "llvm/IR/LLVMContext.h"
#include "llvm/IR/Module.h"
#include "llvm/Support/CallSite.h"
+#include "llvm/Support/ConvertUTF.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Target/Mangler.h"
+
using namespace clang;
using namespace CodeGen;
diff --git a/lib/Frontend/TextDiagnostic.cpp b/lib/Frontend/TextDiagnostic.cpp
index aba90f6046..f7c0d60ae4 100644
--- a/lib/Frontend/TextDiagnostic.cpp
+++ b/lib/Frontend/TextDiagnostic.cpp
@@ -8,13 +8,13 @@
//===----------------------------------------------------------------------===//
#include "clang/Frontend/TextDiagnostic.h"
-#include "clang/Basic/ConvertUTF.h"
#include "clang/Basic/DiagnosticOptions.h"
#include "clang/Basic/FileManager.h"
#include "clang/Basic/SourceManager.h"
#include "clang/Lex/Lexer.h"
#include "llvm/ADT/SmallString.h"
#include "llvm/ADT/StringExtras.h"
+#include "llvm/Support/ConvertUTF.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/Locale.h"
#include "llvm/Support/MemoryBuffer.h"
diff --git a/lib/Lex/Lexer.cpp b/lib/Lex/Lexer.cpp
index 08f406b069..6a918d6a3a 100644
--- a/lib/Lex/Lexer.cpp
+++ b/lib/Lex/Lexer.cpp
@@ -25,7 +25,6 @@
//===----------------------------------------------------------------------===//
#include "clang/Lex/Lexer.h"
-#include "clang/Basic/ConvertUTF.h"
#include "clang/Basic/SourceManager.h"
#include "clang/Lex/CodeCompletionHandler.h"
#include "clang/Lex/LexDiagnostic.h"
@@ -34,6 +33,7 @@
#include "llvm/ADT/StringExtras.h"
#include "llvm/ADT/StringSwitch.h"
#include "llvm/Support/Compiler.h"
+#include "llvm/Support/ConvertUTF.h"
#include "llvm/Support/MemoryBuffer.h"
#include <cstring>
using namespace clang;
@@ -1655,10 +1655,11 @@ FinishIdentifier:
} else if (!isASCII(C)) {
const char *UnicodePtr = CurPtr;
UTF32 CodePoint;
- ConversionResult Result = convertUTF8Sequence((const UTF8 **)&UnicodePtr,
- (const UTF8 *)BufferEnd,
- &CodePoint,
- strictConversion);
+ ConversionResult Result =
+ llvm::convertUTF8Sequence((const UTF8 **)&UnicodePtr,
+ (const UTF8 *)BufferEnd,
+ &CodePoint,
+ strictConversion);
if (Result != conversionOK ||
!isAllowedIDChar(static_cast<uint32_t>(CodePoint)))
goto FinishIdentifier;
@@ -3528,10 +3529,11 @@ LexNextToken:
// We can't just reset CurPtr to BufferPtr because BufferPtr may point to
// an escaped newline.
--CurPtr;
- ConversionResult Status = convertUTF8Sequence((const UTF8 **)&CurPtr,
- (const UTF8 *)BufferEnd,
- &CodePoint,
- strictConversion);
+ ConversionResult Status =
+ llvm::convertUTF8Sequence((const UTF8 **)&CurPtr,
+ (const UTF8 *)BufferEnd,
+ &CodePoint,
+ strictConversion);
if (Status == conversionOK)
return LexUnicode(Result, CodePoint, CurPtr);
diff --git a/lib/Lex/LiteralSupport.cpp b/lib/Lex/LiteralSupport.cpp
index 09a94a1143..b6cc5996fd 100644
--- a/lib/Lex/LiteralSupport.cpp
+++ b/lib/Lex/LiteralSupport.cpp
@@ -13,12 +13,13 @@
//===----------------------------------------------------------------------===//
#include "clang/Lex/LiteralSupport.h"
-#include "clang/Basic/ConvertUTF.h"
#i