wtf/unicode/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 "Unicode.h"
  30
  31 namespace WTF {
  32   namespace Unicode {
  33
  34     // Given a first byte, gives the length of the UTF-8 sequence it begins.
  35     // Returns 0 for bytes that are not legal starts of UTF-8 sequences.
  36     // Only allows sequences of up to 4 bytes, since that works for all Unicode characters (U-00000000 to U-0010FFFF).
  37     int UTF8SequenceLength(char);
  38
  39     // Takes a null-terminated C-style string with a UTF-8 sequence in it and converts it to a character.
  40     // Only allows Unicode characters (U-00000000 to U-0010FFFF).
  41     // Returns -1 if the sequence is not valid (including presence of extra bytes).
  42     int decodeUTF8Sequence(const char*);
  43
  44     typedef enum {
  45             conversionOK,       // conversion successful
  46             sourceExhausted,    // partial character in source, but hit end
  47             targetExhausted,    // insuff. room in target for conversion
  48             sourceIllegal       // source sequence is illegal/malformed
  49     } ConversionResult;
  50
  51     // These conversion functions take a "strict" argument. When this
  52     // flag is set to strict, both irregular sequences and isolated surrogates
  53     // will cause an error.  When the flag is set to lenient, both irregular
  54     // sequences and isolated surrogates are converted.
  55     //
  56     // Whether the flag is strict or lenient, all illegal sequences will cause
  57     // an error return. This includes sequences such as: <F4 90 80 80>, <C0 80>,
  58     // or <A0> in UTF-8, and values above 0x10FFFF in UTF-32. Conformant code
  59     // must check for illegal sequences.
  60     //
  61     // When the flag is set to lenient, characters over 0x10FFFF are converted
  62     // to the replacement character; otherwise (when the flag is set to strict)
  63     // they constitute an error.
  64
  65     ConversionResult convertUTF8ToUTF16(
  66                     const char** sourceStart, const char* sourceEnd,
  67                     UChar** targetStart, UChar* targetEnd, bool strict = true);
  68
  69     ConversionResult convertUTF16ToUTF8(
  70                     const UChar** sourceStart, const UChar* sourceEnd,
  71                     char** targetStart, char* targetEnd, bool strict = true);
  72   }
  73 }
  74
  75 #endif // WTF_UTF8_h