1.1 --- /dev/null Thu Jan 01 00:00:00 1970 +0000
1.2 +++ b/toolkit/crashreporter/google-breakpad/src/common/convert_UTF.h Wed Dec 31 06:09:35 2014 +0100
1.3 @@ -0,0 +1,143 @@
1.4 +/*
1.5 + * Copyright 2001-2004 Unicode, Inc.
1.6 + *
1.7 + * Disclaimer
1.8 + *
1.9 + * This source code is provided as is by Unicode, Inc. No claims are
1.10 + * made as to fitness for any particular purpose. No warranties of any
1.11 + * kind are expressed or implied. The recipient agrees to determine
1.12 + * applicability of information provided. If this file has been
1.13 + * purchased on magnetic or optical media from Unicode, Inc., the
1.14 + * sole remedy for any claim will be exchange of defective media
1.15 + * within 90 days of receipt.
1.16 + *
1.17 + * Limitations on Rights to Redistribute This Code
1.18 + *
1.19 + * Unicode, Inc. hereby grants the right to freely use the information
1.20 + * supplied in this file in the creation of products supporting the
1.21 + * Unicode Standard, and to make copies of this file in any form
1.22 + * for internal or external distribution as long as this notice
1.23 + * remains attached.
1.24 + */
1.25 +
1.26 +/* ---------------------------------------------------------------------
1.27 +
1.28 +Conversions between UTF32, UTF-16, and UTF-8. Header file.
1.29 +
1.30 +Several funtions are included here, forming a complete set of
1.31 +conversions between the three formats. UTF-7 is not included
1.32 +here, but is handled in a separate source file.
1.33 +
1.34 +Each of these routines takes pointers to input buffers and output
1.35 +buffers. The input buffers are const.
1.36 +
1.37 +Each routine converts the text between *sourceStart and sourceEnd,
1.38 +putting the result into the buffer between *targetStart and
1.39 +targetEnd. Note: the end pointers are *after* the last item: e.g.
1.40 +*(sourceEnd - 1) is the last item.
1.41 +
1.42 +The return result indicates whether the conversion was successful,
1.43 +and if not, whether the problem was in the source or target buffers.
1.44 +(Only the first encountered problem is indicated.)
1.45 +
1.46 +After the conversion, *sourceStart and *targetStart are both
1.47 +updated to point to the end of last text successfully converted in
1.48 +the respective buffers.
1.49 +
1.50 +Input parameters:
1.51 +sourceStart - pointer to a pointer to the source buffer.
1.52 +The contents of this are modified on return so that
1.53 +it points at the next thing to be converted.
1.54 +targetStart - similarly, pointer to pointer to the target buffer.
1.55 +sourceEnd, targetEnd - respectively pointers to the ends of the
1.56 +two buffers, for overflow checking only.
1.57 +
1.58 +These conversion functions take a ConversionFlags argument. When this
1.59 +flag is set to strict, both irregular sequences and isolated surrogates
1.60 +will cause an error. When the flag is set to lenient, both irregular
1.61 +sequences and isolated surrogates are converted.
1.62 +
1.63 +Whether the flag is strict or lenient, all illegal sequences will cause
1.64 +an error return. This includes sequences such as: <F4 90 80 80>, <C0 80>,
1.65 +or <A0> in UTF-8, and values above 0x10FFFF in UTF-32. Conformant code
1.66 +must check for illegal sequences.
1.67 +
1.68 +When the flag is set to lenient, characters over 0x10FFFF are converted
1.69 +to the replacement character; otherwise (when the flag is set to strict)
1.70 +they constitute an error.
1.71 +
1.72 +Output parameters:
1.73 +The value "sourceIllegal" is returned from some routines if the input
1.74 +sequence is malformed. When "sourceIllegal" is returned, the source
1.75 +value will point to the illegal value that caused the problem. E.g.,
1.76 +in UTF-8 when a sequence is malformed, it points to the start of the
1.77 +malformed sequence.
1.78 +
1.79 +Author: Mark E. Davis, 1994.
1.80 +Rev History: Rick McGowan, fixes & updates May 2001.
1.81 +Fixes & updates, Sept 2001.
1.82 +
1.83 +------------------------------------------------------------------------ */
1.84 +
1.85 +/* ---------------------------------------------------------------------
1.86 +The following 4 definitions are compiler-specific.
1.87 +The C standard does not guarantee that wchar_t has at least
1.88 +16 bits, so wchar_t is no less portable than unsigned short!
1.89 +All should be unsigned values to avoid sign extension during
1.90 +bit mask & shift operations.
1.91 +------------------------------------------------------------------------ */
1.92 +
1.93 +typedef unsigned long UTF32; /* at least 32 bits */
1.94 +typedef unsigned short UTF16; /* at least 16 bits */
1.95 +typedef unsigned char UTF8; /* typically 8 bits */
1.96 +typedef unsigned char Boolean; /* 0 or 1 */
1.97 +
1.98 +/* Some fundamental constants */
1.99 +#define UNI_REPLACEMENT_CHAR (UTF32)0x0000FFFD
1.100 +#define UNI_MAX_BMP (UTF32)0x0000FFFF
1.101 +#define UNI_MAX_UTF16 (UTF32)0x0010FFFF
1.102 +#define UNI_MAX_UTF32 (UTF32)0x7FFFFFFF
1.103 +#define UNI_MAX_LEGAL_UTF32 (UTF32)0x0010FFFF
1.104 +
1.105 +typedef enum {
1.106 + conversionOK, /* conversion successful */
1.107 + sourceExhausted, /* partial character in source, but hit end */
1.108 + targetExhausted, /* insuff. room in target for conversion */
1.109 + sourceIllegal /* source sequence is illegal/malformed */
1.110 +} ConversionResult;
1.111 +
1.112 +typedef enum {
1.113 + strictConversion = 0,
1.114 + lenientConversion
1.115 +} ConversionFlags;
1.116 +
1.117 +/* This is for C++ and does no harm in C */
1.118 +#ifdef __cplusplus
1.119 +extern "C" {
1.120 +#endif
1.121 +
1.122 +ConversionResult ConvertUTF8toUTF16 (const UTF8** sourceStart, const UTF8* sourceEnd,
1.123 + UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags);
1.124 +
1.125 +ConversionResult ConvertUTF16toUTF8 (const UTF16** sourceStart, const UTF16* sourceEnd,
1.126 + UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags);
1.127 +
1.128 +ConversionResult ConvertUTF8toUTF32 (const UTF8** sourceStart, const UTF8* sourceEnd,
1.129 + UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags);
1.130 +
1.131 +ConversionResult ConvertUTF32toUTF8 (const UTF32** sourceStart, const UTF32* sourceEnd,
1.132 + UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags);
1.133 +
1.134 +ConversionResult ConvertUTF16toUTF32 (const UTF16** sourceStart, const UTF16* sourceEnd,
1.135 + UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags);
1.136 +
1.137 +ConversionResult ConvertUTF32toUTF16 (const UTF32** sourceStart, const UTF32* sourceEnd,
1.138 + UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags);
1.139 +
1.140 +Boolean isLegalUTF8Sequence(const UTF8 *source, const UTF8 *sourceEnd);
1.141 +
1.142 +#ifdef __cplusplus
1.143 +}
1.144 +#endif
1.145 +
1.146 +/* --------------------------------------------------------------------- */
