[Scummvm-git-logs] scummvm branch-2-3 -> 84c34e8df49cf864b7db87056f4a24770db09db1
sev-
sev at scummvm.org
Sun Sep 19 14:58:19 UTC 2021
This automated email contains information about 1 new commit which have been
pushed to the 'scummvm' repo located at https://github.com/scummvm/scummvm .
Summary:
84c34e8df4 WINTERMUTE: Replace convert_utf with built-in conversions
Commit: 84c34e8df49cf864b7db87056f4a24770db09db1
https://github.com/scummvm/scummvm/commit/84c34e8df49cf864b7db87056f4a24770db09db1
Author: SupSuper (supsuper at gmail.com)
Date: 2021-09-19T16:58:03+02:00
Commit Message:
WINTERMUTE: Replace convert_utf with built-in conversions
Now that ScummVM supports UTF8 we can just use it
Changed paths:
R engines/wintermute/utils/convert_utf.cpp
R engines/wintermute/utils/convert_utf.h
engines/wintermute/module.mk
engines/wintermute/utils/string_util.cpp
diff --git a/engines/wintermute/module.mk b/engines/wintermute/module.mk
index ed609fe42f..bb8490c4f2 100644
--- a/engines/wintermute/module.mk
+++ b/engines/wintermute/module.mk
@@ -132,7 +132,6 @@ MODULE_OBJS := \
ui/ui_text.o \
ui/ui_tiled_image.o \
ui/ui_window.o \
- utils/convert_utf.o \
utils/crc.o \
utils/path_util.o \
utils/string_util.o \
diff --git a/engines/wintermute/utils/convert_utf.cpp b/engines/wintermute/utils/convert_utf.cpp
deleted file mode 100644
index 0ae63d63a9..0000000000
--- a/engines/wintermute/utils/convert_utf.cpp
+++ /dev/null
@@ -1,644 +0,0 @@
-/*
- * 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 "engines/wintermute/utils/convert_utf.h"
-#ifdef CVTUTF_DEBUG
-#include "common/textconsole.h"
-#endif
-
-namespace Wintermute {
-
-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
-
-/* --------------------------------------------------------------------- */
-
-ConversionResult ConvertUTF32toUTF16(
- const UTF32 **sourceStart, const UTF32 *sourceEnd,
- UTF16 **targetStart, UTF16 *targetEnd, ConversionFlags flags) {
- ConversionResult result = conversionOK;
- const UTF32 *source = *sourceStart;
- UTF16 *target = *targetStart;
- while (source < sourceEnd) {
- UTF32 ch;
- if (target >= targetEnd) {
- result = targetExhausted;
- break;
- }
- ch = *source++;
- if (ch <= UNI_MAX_BMP) { /* Target is a character <= 0xFFFF */
- /* UTF-16 surrogate values are illegal in UTF-32; 0xffff or 0xfffe are both reserved values */
- if (ch >= UNI_SUR_HIGH_START && ch <= UNI_SUR_LOW_END) {
- if (flags == strictConversion) {
- --source; /* 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_LEGAL_UTF32) {
- if (flags == strictConversion) {
- result = sourceIllegal;
- } else {
- *target++ = UNI_REPLACEMENT_CHAR;
- }
- } else {
- /* target is a character in range 0xFFFF - 0x10FFFF. */
- if (target + 1 >= targetEnd) {
- --source; /* 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;
-}
-
-/* --------------------------------------------------------------------- */
-
-ConversionResult ConvertUTF16toUTF32(
- const UTF16 **sourceStart, const UTF16 *sourceEnd,
- UTF32 **targetStart, UTF32 *targetEnd, ConversionFlags flags) {
- ConversionResult result = conversionOK;
- const UTF16 *source = *sourceStart;
- UTF32 *target = *targetStart;
- UTF32 ch, ch2;
- while (source < sourceEnd) {
- 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) {
- /* If the 16 bits following the high surrogate are in the source buffer... */
- if (source < sourceEnd) {
- ch2 = *source;
- /* If it's a low surrogate, convert to UTF32. */
- 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 { /* We don't have the 16 bits following the high surrogate. */
- --source; /* return to the high surrogate */
- result = sourceExhausted;
- break;
- }
- } else if (flags == strictConversion) {
- /* UTF-16 surrogate values are illegal in UTF-32 */
- if (ch >= UNI_SUR_LOW_START && ch <= UNI_SUR_LOW_END) {
- --source; /* return to the illegal value itself */
- result = sourceIllegal;
- break;
- }
- }
- if (target >= targetEnd) {
- source = oldSource; /* Back up source pointer! */
- result = targetExhausted;
- break;
- }
- *target++ = ch;
- }
- *sourceStart = source;
- *targetStart = target;
-#ifdef CVTUTF_DEBUG
- if (result == sourceIllegal) {
- warning("ConvertUTF16toUTF32 illegal seq 0x%04x,%04x\n", ch, ch2);
- }
-#endif
- return result;
-}
-
-/* --------------------------------------------------------------------- */
-
-/*
- * 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 };
-
-/* --------------------------------------------------------------------- */
-
-/* The interface converts a whole buffer to avoid function-call overhead.
- * Constants have been gathered. Loops & conditionals have been removed as
- * much as possible for efficiency, in favor of drop-through switches.
- * (See "Note A" at the bottom of the file for equivalent code.)
- * If your compiler supports it, the "isLegalUTF8" call can be turned
- * into an inline function.
- */
-
-/* --------------------------------------------------------------------- */
-
-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) {
- /* If the 16 bits following the high surrogate are in the source buffer... */
- if (source < sourceEnd) {
- UTF32 ch2 = *source;
- /* If it's a low surrogate, convert to UTF32. */
- 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 { /* We don't have the 16 bits following the high surrogate. */
- --source; /* return to the high surrogate */
- result = sourceExhausted;
- break;
- }
- } else if (flags == strictConversion) {
- /* UTF-16 surrogate values are illegal in UTF-32 */
- if (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)0x110000) {
- bytesToWrite = 4;
- } else {
- bytesToWrite = 3;
- 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 = (UTF8)((ch | byteMark) & byteMask);
- ch >>= 6;
- // fall through
- case 3:
- *--target = (UTF8)((ch | byteMark) & byteMask);
- ch >>= 6;
- // fall through
- case 2:
- *--target = (UTF8)((ch | byteMark) & byteMask);
- ch >>= 6;
- // fall through
- case 1:
- *--target = (UTF8)(ch | firstByteMark[bytesToWrite]);
- // fall through
- default:
- break;
- }
- target += bytesToWrite;
- }
- *sourceStart = source;
- *targetStart = target;
- return result;
-}
-
-/* --------------------------------------------------------------------- */
-
-/*
- * 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 bool 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;
- // fall through
- case 3:
- if ((a = (*--srcptr)) < 0x80 || a > 0xBF) return false;
- // fall through
- 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;
- }
- // fall through
-
- case 1:
- if (*source >= 0x80 && *source < 0xC2) return false;
- }
- if (*source > 0xF4) return false;
- return true;
-}
-
-/* --------------------------------------------------------------------- */
-
-/*
- * Exported function to return whether a UTF-8 sequence is legal or not.
- * This is not used here; it's just exported.
- */
-bool isLegalUTF8Sequence(const UTF8 *source, const UTF8 *sourceEnd) {
- int length = trailingBytesForUTF8[*source] + 1;
- if (source + length > sourceEnd) {
- return false;
- }
- return isLegalUTF8(source, length);
-}
-
-/* --------------------------------------------------------------------- */
-
-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 */
- // fall through
- case 4:
- ch += *source++;
- ch <<= 6; /* remember, illegal UTF-8 */
- // fall through
- case 3:
- ch += *source++;
- ch <<= 6;
- // fall through
- case 2:
- ch += *source++;
- ch <<= 6;
- // fall through
- case 1:
- ch += *source++;
- ch <<= 6;
- // fall through
- case 0:
- ch += *source++;
- break;
- default:
- break;
- }
- ch -= offsetsFromUTF8[extraBytesToRead];
-
- if (target >= targetEnd) {
- source -= (extraBytesToRead + 1); /* Back up source pointer! */
- result = targetExhausted;
- break;
- }
- 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;
-}
-
-/* --------------------------------------------------------------------- */
-
-ConversionResult ConvertUTF32toUTF8(
- const UTF32 **sourceStart, const UTF32 *sourceEnd,
- UTF8 **targetStart, UTF8 *targetEnd, ConversionFlags flags) {
- ConversionResult result = conversionOK;
- const UTF32 *source = *sourceStart;
- UTF8 *target = *targetStart;
- while (source < sourceEnd) {
- UTF32 ch;
- unsigned short bytesToWrite = 0;
- const UTF32 byteMask = 0xBF;
- const UTF32 byteMark = 0x80;
- ch = *source++;
- if (flags == strictConversion) {
- /* UTF-16 surrogate values are illegal in UTF-32 */
- if (ch >= UNI_SUR_HIGH_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. Turn any
- * illegally large UTF32 things (> Plane 17) into replacement chars.
- */
- if (ch < (UTF32)0x80) {
- bytesToWrite = 1;
- } else if (ch < (UTF32)0x800) {
- bytesToWrite = 2;
- } else if (ch < (UTF32)0x10000) {
- bytesToWrite = 3;
- } else if (ch <= UNI_MAX_LEGAL_UTF32) {
- bytesToWrite = 4;
- } else {
- bytesToWrite = 3;
- ch = UNI_REPLACEMENT_CHAR;
- result = sourceIllegal;
- }
-
- target += bytesToWrite;
- if (target > targetEnd) {
- --source; /* Back up source pointer! */
- target -= bytesToWrite;
- result = targetExhausted;
- break;
- }
- switch (bytesToWrite) { /* note: everything falls through. */
- case 4:
- *--target = (UTF8)((ch | byteMark) & byteMask);
- ch >>= 6;
- // fall through
- case 3:
- *--target = (UTF8)((ch | byteMark) & byteMask);
- ch >>= 6;
- // fall through
- case 2:
- *--target = (UTF8)((ch | byteMark) & byteMask);
- ch >>= 6;
- // fall through
- case 1:
- *--target = (UTF8)(ch | firstByteMark[bytesToWrite]);
- break;
- default:
- break;
- }
- target += bytesToWrite;
- }
- *sourceStart = source;
- *targetStart = target;
- return result;
-}
-
-/* --------------------------------------------------------------------- */
-
-ConversionResult ConvertUTF8toUTF32(
- const UTF8 **sourceStart, const UTF8 *sourceEnd,
- UTF32 **targetStart, UTF32 *targetEnd, ConversionFlags flags) {
- ConversionResult result = conversionOK;
- const UTF8 *source = *sourceStart;
- UTF32 *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;
- // fall through
- case 4:
- ch += *source++;
- ch <<= 6;
- // fall through
- case 3:
- ch += *source++;
- ch <<= 6;
- // fall through
- case 2:
- ch += *source++;
- ch <<= 6;
- // fall through
- case 1:
- ch += *source++;
- ch <<= 6;
- // fall through
- case 0:
- ch += *source++;
- break;
- default:
- break;
- }
- ch -= offsetsFromUTF8[extraBytesToRead];
-
- if (target >= targetEnd) {
- source -= (extraBytesToRead + 1); /* Back up the source pointer! */
- result = targetExhausted;
- break;
- }
- if (ch <= UNI_MAX_LEGAL_UTF32) {
- /*
- * UTF-16 surrogate values are illegal in UTF-32, and anything
- * over Plane 17 (> 0x10FFFF) is illegal.
- */
- 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++ = ch;
- }
- } else { /* i.e., ch > UNI_MAX_LEGAL_UTF32 */
- result = sourceIllegal;
- *target++ = UNI_REPLACEMENT_CHAR;
- }
- }
- *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.
-
- --------------------------------------------------------------------- */
-
-} // End of namespace Wintermute
diff --git a/engines/wintermute/utils/convert_utf.h b/engines/wintermute/utils/convert_utf.h
deleted file mode 100644
index d2e54f4af4..0000000000
--- a/engines/wintermute/utils/convert_utf.h
+++ /dev/null
@@ -1,147 +0,0 @@
-/*
- * 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.
- */
-
-// NOTE: Modifications have been made to the code for inclusion
-// into ScummVM.
-
-/* ---------------------------------------------------------------------
-
- 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.
-
------------------------------------------------------------------------- */
-
-/* ---------------------------------------------------------------------
- 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.
------------------------------------------------------------------------- */
-#include "common/system.h"
-
-namespace Wintermute {
-
-typedef uint32 UTF32; /* at least 32 bits */
-typedef uint16 UTF16; /* at least 16 bits */
-typedef uint8 UTF8; /* typically 8 bits */
-
-/* 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
-
-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);
-
-ConversionResult ConvertUTF16toUTF8(
- const UTF16 **sourceStart, const UTF16 *sourceEnd,
- UTF8 **targetStart, UTF8 *targetEnd, ConversionFlags flags);
-
-ConversionResult ConvertUTF8toUTF32(
- const UTF8 **sourceStart, const UTF8 *sourceEnd,
- UTF32 **targetStart, UTF32 *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);
-
-bool isLegalUTF8Sequence(const UTF8 *source, const UTF8 *sourceEnd);
-
-} // End of namespace Wintermute
-
-/* --------------------------------------------------------------------- */
diff --git a/engines/wintermute/utils/string_util.cpp b/engines/wintermute/utils/string_util.cpp
index abf4dee2c8..7afab82963 100644
--- a/engines/wintermute/utils/string_util.cpp
+++ b/engines/wintermute/utils/string_util.cpp
@@ -28,9 +28,9 @@
#include "common/language.h"
#include "common/tokenizer.h"
+#include "common/str-enc.h"
#include "engines/wintermute/base/base_engine.h"
#include "engines/wintermute/utils/string_util.h"
-#include "engines/wintermute/utils/convert_utf.h"
namespace Wintermute {
@@ -52,49 +52,12 @@ bool StringUtil::compareNoCase(const AnsiString &str1, const AnsiString &str2) {
//////////////////////////////////////////////////////////////////////////
WideString StringUtil::utf8ToWide(const Utf8String &Utf8Str) {
- size_t wideSize = Utf8Str.size();
-
- uint32 *wideStringNative = new uint32[wideSize + 1];
-
- const UTF8 *sourceStart = reinterpret_cast<const UTF8 *>(Utf8Str.c_str());
- const UTF8 *sourceEnd = sourceStart + wideSize;
-
- UTF32 *targetStart = reinterpret_cast<UTF32 *>(wideStringNative);
- UTF32 *targetEnd = targetStart + wideSize;
-
- ConversionResult res = ConvertUTF8toUTF32(&sourceStart, sourceEnd, &targetStart, targetEnd, strictConversion);
- if (res != conversionOK) {
- delete[] wideStringNative;
- return WideString();
- }
- *targetStart = 0;
- WideString resultString(wideStringNative);
- delete[] wideStringNative;
- return resultString;
+ return Common::convertToU32String(Utf8Str.c_str(), Common::kUtf8);
}
//////////////////////////////////////////////////////////////////////////
Utf8String StringUtil::wideToUtf8(const WideString &WideStr) {
- size_t wideSize = WideStr.size();
-
- size_t utf8Size = 4 * wideSize + 1;
- char *utf8StringNative = new char[utf8Size];
-
- const UTF32 *sourceStart = reinterpret_cast<const UTF32 *>(WideStr.c_str());
- const UTF32 *sourceEnd = sourceStart + wideSize;
-
- UTF8 *targetStart = reinterpret_cast<UTF8 *>(utf8StringNative);
- UTF8 *targetEnd = targetStart + utf8Size;
-
- ConversionResult res = ConvertUTF32toUTF8(&sourceStart, sourceEnd, &targetStart, targetEnd, strictConversion);
- if (res != conversionOK) {
- delete[] utf8StringNative;
- return Utf8String();
- }
- *targetStart = 0;
- Utf8String resultString(utf8StringNative);
- delete[] utf8StringNative;
- return resultString;
+ return Common::convertFromU32String(WideStr, Common::kUtf8);
}
//////////////////////////////////////////////////////////////////////////
More information about the Scummvm-git-logs
mailing list