third_party/WebKit/Source/wtf/text/UTF8.h

   1 /*
   2  * Copyright (C) 2007 Apple Inc.  All rights reserved.
   3  *
   4  * Redistribution and use in source and binary forms, with or without
   5  * modification, are permitted provided that the following conditions
   6  * are met:
   7  * 1. Redistributions of source code must retain the above copyright
   8  *    notice, this list of conditions and the following disclaimer.
   9  * 2. Redistributions in binary form must reproduce the above copyright
  10  *    notice, this list of conditions and the following disclaimer in the
  11  *    documentation and/or other materials provided with the distribution.
  12  *
  13  * THIS SOFTWARE IS PROVIDED BY APPLE COMPUTER, INC. ``AS IS'' AND ANY
  14  * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  15  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
  16  * PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL APPLE COMPUTER, INC. OR
  17  * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
  18  * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
  19  * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
  20  * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
  21  * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
  22  * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
  23  * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  24  */
  25
  26 #ifndef WTF_UTF8_h
  27 #define WTF_UTF8_h
  28
  29 #include "wtf/WTFExport.h"
  30 #include "wtf/text/Unicode.h"
  31
  32 namespace WTF {
  33 namespace Unicode {
  34
  35     typedef enum {
  36             conversionOK,       // conversion successful
  37             sourceExhausted,    // partial character in source, but hit end
  38             targetExhausted,    // insuff. room in target for conversion
  39             sourceIllegal       // source sequence is illegal/malformed
  40     } ConversionResult;
  41
  42     // These conversion functions take a "strict" argument. When this
  43     // flag is set to strict, both irregular sequences and isolated surrogates
  44     // will cause an error.  When the flag is set to lenient, both irregular
  45     // sequences and isolated surrogates are converted.
  46     //
  47     // Whether the flag is strict or lenient, all illegal sequences will cause
  48     // an error return. This includes sequences such as: <F4 90 80 80>, <C0 80>,
  49     // or <A0> in UTF-8, and values above 0x10FFFF in UTF-32. Conformant code
  50     // must check for illegal sequences.
  51     //
  52     // When the flag is set to lenient, characters over 0x10FFFF are converted
  53     // to the replacement character; otherwise (when the flag is set to strict)
  54     // they constitute an error.
  55
  56     WTF_EXPORT ConversionResult convertUTF8ToUTF16(
  57                     const char** sourceStart, const char* sourceEnd,
  58                     UChar** targetStart, UChar* targetEnd, bool* isSourceAllASCII = 0, bool strict = true);
  59
  60     WTF_EXPORT ConversionResult convertLatin1ToUTF8(
  61                     const LChar** sourceStart, const LChar* sourceEnd,
  62                     char** targetStart, char* targetEnd);
  63
  64     WTF_EXPORT ConversionResult convertUTF16ToUTF8(
  65                     const UChar** sourceStart, const UChar* sourceEnd,
  66                     char** targetStart, char* targetEnd, bool strict = true);
  67
  68     WTF_EXPORT unsigned calculateStringHashAndLengthFromUTF8MaskingTop8Bits(const char* data, const char* dataEnd, unsigned& dataLength, unsigned& utf16Length);
  69
  70     WTF_EXPORT bool equalUTF16WithUTF8(const UChar* a, const UChar* aEnd, const char* b, const char* bEnd);
  71     WTF_EXPORT bool equalLatin1WithUTF8(const LChar* a, const LChar* aEnd, const char* b, const char* bEnd);
  72
  73 } // namespace Unicode
  74 } // namespace WTF
  75
  76 #endif // WTF_UTF8_h