aboutsummaryrefslogtreecommitdiff
path: root/lib/Basic/ConvertUTF.c
diff options
context:
space:
mode:
Diffstat (limited to 'lib/Basic/ConvertUTF.c')
-rw-r--r--lib/Basic/ConvertUTF.c606
1 files changed, 303 insertions, 303 deletions
diff --git a/lib/Basic/ConvertUTF.c b/lib/Basic/ConvertUTF.c
index e5dd3e6bf570..124e386c5526 100644
--- a/lib/Basic/ConvertUTF.c
+++ b/lib/Basic/ConvertUTF.c
@@ -34,10 +34,10 @@
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.
+ 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.
+ 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.
@@ -61,8 +61,8 @@ static const UTF32 halfMask = 0x3FFUL;
#define UNI_SUR_HIGH_END (UTF32)0xDBFF
#define UNI_SUR_LOW_START (UTF32)0xDC00
#define UNI_SUR_LOW_END (UTF32)0xDFFF
-#define false 0
-#define true 1
+#define false 0
+#define true 1
/* --------------------------------------------------------------------- */
@@ -90,7 +90,7 @@ static const char trailingBytesForUTF8[256] = {
* in a UTF-8 sequence.
*/
static const UTF32 offsetsFromUTF8[6] = { 0x00000000UL, 0x00003080UL, 0x000E2080UL,
- 0x03C82080UL, 0xFA082080UL, 0x82082080UL };
+ 0x03C82080UL, 0xFA082080UL, 0x82082080UL };
/*
* Once the bits are split out into bytes of UTF-8, this is a mask OR-ed
@@ -116,46 +116,46 @@ static const UTF8 firstByteMark[7] = { 0x00, 0x00, 0xC0, 0xE0, 0xF0, 0xF8, 0xFC
/* --------------------------------------------------------------------- */
ConversionResult ConvertUTF32toUTF16 (
- const UTF32** sourceStart, const UTF32* sourceEnd,
- UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags) {
+ 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);
- }
+ 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;
@@ -165,48 +165,48 @@ ConversionResult ConvertUTF32toUTF16 (
/* --------------------------------------------------------------------- */
ConversionResult ConvertUTF16toUTF32 (
- const UTF16** sourceStart, const UTF16* sourceEnd,
- UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags) {
+ 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;
+ 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;
@@ -219,67 +219,67 @@ if (result == sourceIllegal) {
return result;
}
ConversionResult ConvertUTF16toUTF8 (
- const UTF16** sourceStart, const UTF16* sourceEnd,
- UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags) {
+ 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;
- case 3: *--target = (UTF8)((ch | byteMark) & byteMask); ch >>= 6;
- case 2: *--target = (UTF8)((ch | byteMark) & byteMask); ch >>= 6;
- case 1: *--target = (UTF8)(ch | firstByteMark[bytesToWrite]);
- }
- target += bytesToWrite;
+ 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;
+ case 3: *--target = (UTF8)((ch | byteMark) & byteMask); ch >>= 6;
+ case 2: *--target = (UTF8)((ch | byteMark) & byteMask); ch >>= 6;
+ case 1: *--target = (UTF8)(ch | firstByteMark[bytesToWrite]);
+ }
+ target += bytesToWrite;
}
*sourceStart = source;
*targetStart = target;
@@ -289,50 +289,50 @@ ConversionResult ConvertUTF16toUTF8 (
/* --------------------------------------------------------------------- */
ConversionResult ConvertUTF32toUTF8 (
- const UTF32** sourceStart, const UTF32* sourceEnd,
- UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags) {
+ 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;
- case 3: *--target = (UTF8)((ch | byteMark) & byteMask); ch >>= 6;
- case 2: *--target = (UTF8)((ch | byteMark) & byteMask); ch >>= 6;
- case 1: *--target = (UTF8) (ch | firstByteMark[bytesToWrite]);
- }
- target += bytesToWrite;
+ 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;
+ case 3: *--target = (UTF8)((ch | byteMark) & byteMask); ch >>= 6;
+ case 2: *--target = (UTF8)((ch | byteMark) & byteMask); ch >>= 6;
+ case 1: *--target = (UTF8) (ch | firstByteMark[bytesToWrite]);
+ }
+ target += bytesToWrite;
}
*sourceStart = source;
*targetStart = target;
@@ -342,59 +342,59 @@ ConversionResult ConvertUTF32toUTF8 (
/* --------------------------------------------------------------------- */
ConversionResult ConvertUTF8toUTF32 (
- const UTF8** sourceStart, const UTF8* sourceEnd,
- UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags) {
+ 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;
- case 4: ch += *source++; ch <<= 6;
- 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];
-
- 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;
- }
+ 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;
+ case 4: ch += *source++; ch <<= 6;
+ 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];
+
+ 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;
@@ -420,19 +420,19 @@ static Boolean isLegalUTF8(const UTF8 *source, int length) {
const UTF8 *srcptr = source+length;
switch (length) {
default: return false;
- /* Everything else falls through when "true"... */
+ /* 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;
- }
+ 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;
}
@@ -449,7 +449,7 @@ static Boolean isLegalUTF8(const UTF8 *source, int length) {
Boolean isLegalUTF8Sequence(const UTF8 *source, const UTF8 *sourceEnd) {
int length = trailingBytesForUTF8[*source]+1;
if (source+length > sourceEnd) {
- return false;
+ return false;
}
return isLegalUTF8(source, length);
}
@@ -457,70 +457,70 @@ Boolean isLegalUTF8Sequence(const UTF8 *source, const UTF8 *sourceEnd) {
/* --------------------------------------------------------------------- */
ConversionResult ConvertUTF8toUTF16 (
- const UTF8** sourceStart, const UTF8* sourceEnd,
- UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags) {
+ 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];
-
- 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);
- }
+ 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];
+
+ 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;
@@ -533,14 +533,14 @@ ConversionResult ConvertUTF8toUTF16 (
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);
- }
+ {
+ 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.
generated by cgit v1.2.3 (git 2.25.1) at 2024-04-18 03:05:50 +0000