reference, declarationdefinition
definition → references, declarations, derived classes, virtual overrides
reference to multiple definitions → definitions
unreferenced
    1
    2
    3
    4
    5
    6
    7
    8
    9
   10
   11
   12
   13
   14
   15
   16
   17
   18
   19
   20
   21
   22
   23
   24
   25
   26
   27
   28
   29
   30
   31
   32
   33
   34
   35
   36
   37
   38
   39
   40
   41
   42
   43
   44
   45
   46
   47
   48
   49
   50
   51
   52
   53
   54
   55
   56
   57
   58
   59
   60
   61
   62
   63
   64
   65
   66
   67
   68
   69
   70
   71
   72
   73
   74
   75
   76
   77
   78
   79
   80
   81
   82
   83
   84
   85
   86
   87
   88
   89
   90
   91
   92
   93
   94
   95
   96
   97
   98
   99
  100
  101
  102
  103
  104
  105
  106
  107
  108
  109
  110
  111
  112
  113
  114
  115
  116
  117
  118
  119
  120
  121
  122
  123
  124
  125
  126
  127
  128
  129
  130
  131
  132
  133
  134
  135
  136
  137
  138
  139
  140
  141
  142
  143
  144
  145
  146
  147
  148
  149
  150
  151
  152
  153
  154
  155
  156
  157
  158
  159
  160
  161
  162
  163
  164
  165
  166
  167
  168
  169
  170
  171
  172
  173
  174
  175
  176
  177
  178
  179
  180
  181
  182
  183
  184
  185
  186
  187
  188
  189
  190
  191
  192
  193
  194
  195
  196
  197
  198
  199
  200
  201
  202
  203
  204
  205
  206
  207
  208
  209
  210
  211
  212
  213
  214
  215
  216
  217
  218
  219
  220
  221
  222
  223
  224
  225
  226
  227
  228
  229
  230
  231
  232
  233
  234
  235
  236
  237
  238
  239
  240
  241
  242
  243
  244
  245
  246
  247
  248
  249
  250
  251
  252
  253
  254
  255
  256
  257
  258
  259
  260
  261
  262
  263
  264
  265
  266
  267
  268
  269
  270
  271
  272
  273
  274
  275
  276
  277
  278
  279
  280
  281
  282
  283
  284
  285
  286
  287
  288
  289
  290
  291
  292
  293
  294
  295
  296
  297
  298
  299
  300
  301
  302
  303
  304
  305
  306
/*===--- ConvertUTF.h - Universal Character Names conversions ---------------===
 *
 * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 * See https://llvm.org/LICENSE.txt for license information.
 * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *==------------------------------------------------------------------------==*/
/*
 * 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.  Header file.

    Several funtions are included here, forming a complete set of
    conversions between the three formats.  UTF-7 is not included
    here, but is handled in a separate source file.

    Each of these routines takes pointers to input buffers and output
    buffers.  The input buffers are const.

    Each routine converts the text between *sourceStart and sourceEnd,
    putting the result into the buffer between *targetStart and
    targetEnd. Note: the end pointers are *after* the last item: e.g.
    *(sourceEnd - 1) is the last item.

    The return result indicates whether the conversion was successful,
    and if not, whether the problem was in the source or target buffers.
    (Only the first encountered problem is indicated.)

    After the conversion, *sourceStart and *targetStart are both
    updated to point to the end of last text successfully converted in
    the respective buffers.

    Input parameters:
        sourceStart - pointer to a pointer to the source buffer.
                The contents of this are modified on return so that
                it points at the next thing to be converted.
        targetStart - similarly, pointer to pointer to the target buffer.
        sourceEnd, targetEnd - respectively pointers to the ends of the
                two buffers, for overflow checking only.

    These conversion functions take a ConversionFlags argument. When this
    flag is set to strict, both irregular sequences and isolated surrogates
    will cause an error.  When the flag is set to lenient, both irregular
    sequences and isolated surrogates are converted.

    Whether the flag is strict or lenient, all illegal sequences will cause
    an error return. This includes sequences such as: <F4 90 80 80>, <C0 80>,
    or <A0> in UTF-8, and values above 0x10FFFF in UTF-32. Conformant code
    must check for illegal sequences.

    When the flag is set to lenient, characters over 0x10FFFF are converted
    to the replacement character; otherwise (when the flag is set to strict)
    they constitute an error.

    Output parameters:
        The value "sourceIllegal" is returned from some routines if the input
        sequence is malformed.  When "sourceIllegal" is returned, the source
        value will point to the illegal value that caused the problem. E.g.,
        in UTF-8 when a sequence is malformed, it points to the start of the
        malformed sequence.

    Author: Mark E. Davis, 1994.
    Rev History: Rick McGowan, fixes & updates May 2001.
         Fixes & updates, Sept 2001.

------------------------------------------------------------------------ */

#ifndef LLVM_SUPPORT_CONVERTUTF_H
#define LLVM_SUPPORT_CONVERTUTF_H

#include <cstddef>
#include <string>
#include <system_error>

// Wrap everything in namespace llvm so that programs can link with llvm and
// their own version of the unicode libraries.

namespace llvm {

/* ---------------------------------------------------------------------
    The following 4 definitions are compiler-specific.
    The C standard does not guarantee that wchar_t has at least
    16 bits, so wchar_t is no less portable than unsigned short!
    All should be unsigned values to avoid sign extension during
    bit mask & shift operations.
------------------------------------------------------------------------ */

typedef unsigned int    UTF32;  /* at least 32 bits */
typedef unsigned short  UTF16;  /* at least 16 bits */
typedef unsigned char   UTF8;   /* typically 8 bits */
typedef unsigned char   Boolean; /* 0 or 1 */

/* Some fundamental constants */
#define UNI_REPLACEMENT_CHAR (UTF32)0x0000FFFD
#define UNI_MAX_BMP (UTF32)0x0000FFFF
#define UNI_MAX_UTF16 (UTF32)0x0010FFFF
#define UNI_MAX_UTF32 (UTF32)0x7FFFFFFF
#define UNI_MAX_LEGAL_UTF32 (UTF32)0x0010FFFF

#define UNI_MAX_UTF8_BYTES_PER_CODE_POINT 4

#define UNI_UTF16_BYTE_ORDER_MARK_NATIVE  0xFEFF
#define UNI_UTF16_BYTE_ORDER_MARK_SWAPPED 0xFFFE

typedef enum {
  conversionOK,           /* conversion successful */
  sourceExhausted,        /* partial character in source, but hit end */
  targetExhausted,        /* insuff. room in target for conversion */
  sourceIllegal           /* source sequence is illegal/malformed */
} ConversionResult;

typedef enum {
  strictConversion = 0,
  lenientConversion
} ConversionFlags;

ConversionResult ConvertUTF8toUTF16 (
  const UTF8** sourceStart, const UTF8* sourceEnd,
  UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags);

/**
 * Convert a partial UTF8 sequence to UTF32.  If the sequence ends in an
 * incomplete code unit sequence, returns \c sourceExhausted.
 */
ConversionResult ConvertUTF8toUTF32Partial(
  const UTF8** sourceStart, const UTF8* sourceEnd,
  UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags);

/**
 * Convert a partial UTF8 sequence to UTF32.  If the sequence ends in an
 * incomplete code unit sequence, returns \c sourceIllegal.
 */
ConversionResult ConvertUTF8toUTF32(
  const UTF8** sourceStart, const UTF8* sourceEnd,
  UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags);

ConversionResult ConvertUTF16toUTF8 (
  const UTF16** sourceStart, const UTF16* sourceEnd,
  UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags);

ConversionResult ConvertUTF32toUTF8 (
  const UTF32** sourceStart, const UTF32* sourceEnd,
  UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags);

ConversionResult ConvertUTF16toUTF32 (
  const UTF16** sourceStart, const UTF16* sourceEnd,
  UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags);

ConversionResult ConvertUTF32toUTF16 (
  const UTF32** sourceStart, const UTF32* sourceEnd,
  UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags);

Boolean isLegalUTF8Sequence(const UTF8 *source, const UTF8 *sourceEnd);

Boolean isLegalUTF8String(const UTF8 **source, const UTF8 *sourceEnd);

unsigned getNumBytesForUTF8(UTF8 firstByte);

/*************************************************************************/
/* Below are LLVM-specific wrappers of the functions above. */

template <typename T> class ArrayRef;
template <typename T> class SmallVectorImpl;
class StringRef;

/**
 * Convert an UTF8 StringRef to UTF8, UTF16, or UTF32 depending on
 * WideCharWidth. The converted data is written to ResultPtr, which needs to
 * point to at least WideCharWidth * (Source.Size() + 1) bytes. On success,
 * ResultPtr will point one after the end of the copied string. On failure,
 * ResultPtr will not be changed, and ErrorPtr will be set to the location of
 * the first character which could not be converted.
 * \return true on success.
 */
bool ConvertUTF8toWide(unsigned WideCharWidth, llvm::StringRef Source,
                       char *&ResultPtr, const UTF8 *&ErrorPtr);

/**
* Converts a UTF-8 StringRef to a std::wstring.
* \return true on success.
*/
bool ConvertUTF8toWide(llvm::StringRef Source, std::wstring &Result);

/**
* Converts a UTF-8 C-string to a std::wstring.
* \return true on success.
*/
bool ConvertUTF8toWide(const char *Source, std::wstring &Result);

/**
* Converts a std::wstring to a UTF-8 encoded std::string.
* \return true on success.
*/
bool convertWideToUTF8(const std::wstring &Source, std::string &Result);


/**
 * Convert an Unicode code point to UTF8 sequence.
 *
 * \param Source a Unicode code point.
 * \param [in,out] ResultPtr pointer to the output buffer, needs to be at least
 * \c UNI_MAX_UTF8_BYTES_PER_CODE_POINT bytes.  On success \c ResultPtr is
 * updated one past end of the converted sequence.
 *
 * \returns true on success.
 */
bool ConvertCodePointToUTF8(unsigned Source, char *&ResultPtr);

/**
 * Convert the first UTF8 sequence in the given source buffer to a UTF32
 * code point.
 *
 * \param [in,out] source A pointer to the source buffer. If the conversion
 * succeeds, this pointer will be updated to point to the byte just past the
 * end of the converted sequence.
 * \param sourceEnd A pointer just past the end of the source buffer.
 * \param [out] target The converted code
 * \param flags Whether the conversion is strict or lenient.
 *
 * \returns conversionOK on success
 *
 * \sa ConvertUTF8toUTF32
 */
inline ConversionResult convertUTF8Sequence(const UTF8 **source,
                                            const UTF8 *sourceEnd,
                                            UTF32 *target,
                                            ConversionFlags flags) {
  if (*source == sourceEnd)
    return sourceExhausted;
  unsigned size = getNumBytesForUTF8(**source);
  if ((ptrdiff_t)size > sourceEnd - *source)
    return sourceExhausted;
  return ConvertUTF8toUTF32(source, *source + size, &target, target + 1, flags);
}

/**
 * Returns true if a blob of text starts with a UTF-16 big or little endian byte
 * order mark.
 */
bool hasUTF16ByteOrderMark(ArrayRef<char> SrcBytes);

/**
 * Converts a stream of raw bytes assumed to be UTF16 into a UTF8 std::string.
 *
 * \param [in] SrcBytes A buffer of what is assumed to be UTF-16 encoded text.
 * \param [out] Out Converted UTF-8 is stored here on success.
 * \returns true on success
 */
bool convertUTF16ToUTF8String(ArrayRef<char> SrcBytes, std::string &Out);

/**
* Converts a UTF16 string into a UTF8 std::string.
*
* \param [in] Src A buffer of UTF-16 encoded text.
* \param [out] Out Converted UTF-8 is stored here on success.
* \returns true on success
*/
bool convertUTF16ToUTF8String(ArrayRef<UTF16> Src, std::string &Out);

/**
 * Converts a UTF-8 string into a UTF-16 string with native endianness.
 *
 * \returns true on success
 */
bool convertUTF8ToUTF16String(StringRef SrcUTF8,
                              SmallVectorImpl<UTF16> &DstUTF16);

#if defined(_WIN32)
namespace sys {
namespace windows {
std::error_code UTF8ToUTF16(StringRef utf8, SmallVectorImpl<wchar_t> &utf16);
/// Convert to UTF16 from the current code page used in the system
std::error_code CurCPToUTF16(StringRef utf8, SmallVectorImpl<wchar_t> &utf16);
std::error_code UTF16ToUTF8(const wchar_t *utf16, size_t utf16_len,
                            SmallVectorImpl<char> &utf8);
/// Convert from UTF16 to the current code page used in the system
std::error_code UTF16ToCurCP(const wchar_t *utf16, size_t utf16_len,
                             SmallVectorImpl<char> &utf8);
} // namespace windows
} // namespace sys
#endif

} /* end namespace llvm */

#endif