diff options
Diffstat (limited to 'Runtime/Misc/UTF8.cpp')
| -rw-r--r-- | Runtime/Misc/UTF8.cpp | 376 |
1 files changed, 376 insertions, 0 deletions
diff --git a/Runtime/Misc/UTF8.cpp b/Runtime/Misc/UTF8.cpp new file mode 100644 index 0000000..defdfea --- /dev/null +++ b/Runtime/Misc/UTF8.cpp @@ -0,0 +1,376 @@ +#include "UnityPrefix.h" + +typedef unsigned long 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 */ + + + +typedef enum { + strictConversion = 0, + lenientConversion +} ConversionFlags; + +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; + +/* 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 + +ConversionResult ConvertUTF8toUTF16 ( + const UTF8** sourceStart, const UTF8* sourceEnd, + UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags); + + +/* + * 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 "UTF8.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 + + +/* --------------------------------------------------------------------- */ + +/* + * 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 }; + + +/* --------------------------------------------------------------------- */ + +/* + * 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)) > 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; +} + + +/* --------------------------------------------------------------------- */ + +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 (source + extraBytesToRead >= sourceEnd) { + 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]; + + DebugAssertIf (target >= targetEnd); + + 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; +} + +/* --------------------------------------------------------------------- + + 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. + + --------------------------------------------------------------------- */ + +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 && source < sourceEnd) { + UTF32 ch2 = *source; + 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 if ((flags == strictConversion) && (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)0x200000) { bytesToWrite = 4; + } else { bytesToWrite = 2; + 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 = (ch | byteMark) & byteMask; ch >>= 6; + case 3: *--target = (ch | byteMark) & byteMask; ch >>= 6; + case 2: *--target = (ch | byteMark) & byteMask; ch >>= 6; + case 1: *--target = ch | firstByteMark[bytesToWrite]; + } + target += bytesToWrite; + } + *sourceStart = source; + *targetStart = target; + return result; +} + + +bool ConvertUTF8toUTF16 (const char* source, int srcLength, UInt16* output, int& outlength) +{ + UInt16* newoutput = output; + const UTF8* src = (UTF8*)source; + if (ConvertUTF8toUTF16(&src, src + srcLength, &newoutput, newoutput + srcLength, lenientConversion) != sourceIllegal) + { + outlength = newoutput - output; + return true; + } + else + { + outlength = 0; + return false; + } +} + +bool ConvertUTF8toUTF16 (const std::string& source, dynamic_array<UInt16>& utf16) +{ + utf16.resize_uninitialized(source.size()); + int length = 0; + bool success = ConvertUTF8toUTF16(source.data(), (int) source.size(), utf16.begin(), length); + utf16.resize_uninitialized(length); + return success; +} + +bool ConvertUTF16toUTF8 (const UInt16* source, int srcLength, char* output, int& outlength) +{ + UTF8* newoutput = (UTF8*)output; + const UTF16* src = (UTF16*)source; + if (ConvertUTF16toUTF8(&src, src + srcLength, &newoutput, newoutput + (srcLength*4), lenientConversion) != sourceIllegal) + { + outlength = newoutput - (UTF8*)output; + return true; + } + else + { + outlength = 0; + return false; + } +} + + +bool ConvertUTF16toUTF8 (const dynamic_array<UnicodeChar>& source, std::string& utf8) +{ + utf8.resize(source.size()*4); + int length = 0; + bool success = ConvertUTF16toUTF8(source.data(), (int) source.size(), &utf8[0], length); + utf8.resize(length); + return success; +} + +bool ConvertUTF16toUTF8 (const UInt16 utf16character, std::string& utf8) +{ + int len; + char character[5]; + if (!ConvertUTF16toUTF8 (&utf16character, 1, character, len)) + return false; + character[len] = 0; + utf8 = std::string(character); + return true; +} |