diff options
author | dgp <dgp@users.sourceforge.net> | 2016-06-16 16:27:01 (GMT) |
---|---|---|
committer | dgp <dgp@users.sourceforge.net> | 2016-06-16 16:27:01 (GMT) |
commit | 3cbd3b2bede59c6fd03330ac014e626a0a776522 (patch) | |
tree | 8e125264e32e68a389be074bfb8795cd212b9114 /generic/tclEncoding.c | |
parent | 95fb48bf07be37ad0717475514d2c444602a0a6c (diff) | |
parent | 4fac9b8d0fb5648943635cf4c956c9518e610921 (diff) | |
download | tcl-bug_16828b3744.zip tcl-bug_16828b3744.tar.gz tcl-bug_16828b3744.tar.bz2 |
Merge tip of core-8-6-branchbug_16828b3744
Diffstat (limited to 'generic/tclEncoding.c')
-rw-r--r-- | generic/tclEncoding.c | 119 |
1 files changed, 91 insertions, 28 deletions
diff --git a/generic/tclEncoding.c b/generic/tclEncoding.c index 2cc55d6..4edebcf 100644 --- a/generic/tclEncoding.c +++ b/generic/tclEncoding.c @@ -180,8 +180,9 @@ TCL_DECLARE_MUTEX(encodingMutex) * the system encoding will be used to perform the conversion. */ -static Tcl_Encoding defaultEncoding; -static Tcl_Encoding systemEncoding; +static Tcl_Encoding defaultEncoding = NULL; +static Tcl_Encoding systemEncoding = NULL; +Tcl_Encoding tclIdentityEncoding = NULL; /* * The following variable is used in the sparse matrix code for a @@ -567,7 +568,7 @@ TclInitEncodingSubsystem(void) type.freeProc = NULL; type.nullSize = 1; type.clientData = NULL; - Tcl_CreateEncoding(&type); + tclIdentityEncoding = Tcl_CreateEncoding(&type); type.encodingName = "utf-8"; type.toUtfProc = UtfExtToUtfIntProc; @@ -651,6 +652,10 @@ TclFinalizeEncodingSubsystem(void) Tcl_MutexLock(&encodingMutex); encodingsInitialized = 0; FreeEncoding(systemEncoding); + systemEncoding = NULL; + defaultEncoding = NULL; + FreeEncoding(tclIdentityEncoding); + tclIdentityEncoding = NULL; hPtr = Tcl_FirstHashEntry(&encodingTable, &search); while (hPtr != NULL) { @@ -1201,7 +1206,10 @@ Tcl_ExternalToUtf( * output buffer. */ { const Encoding *encodingPtr; - int result, srcRead, dstWrote, dstChars; + int result, srcRead, dstWrote, dstChars = 0; + int noTerminate = flags & TCL_ENCODING_NO_TERMINATE; + int charLimited = (flags & TCL_ENCODING_CHAR_LIMIT) && dstCharsPtr; + int maxChars = INT_MAX; Tcl_EncodingState state; if (encoding == NULL) { @@ -1226,19 +1234,40 @@ Tcl_ExternalToUtf( } if (dstCharsPtr == NULL) { dstCharsPtr = &dstChars; + flags &= ~TCL_ENCODING_CHAR_LIMIT; + } else if (charLimited) { + maxChars = *dstCharsPtr; } - /* - * If there are any null characters in the middle of the buffer, they will - * converted to the UTF-8 null character (\xC080). To get the actual \0 at - * the end of the destination buffer, we need to append it manually. - */ + if (!noTerminate) { + /* + * If there are any null characters in the middle of the buffer, + * they will converted to the UTF-8 null character (\xC080). To get + * the actual \0 at the end of the destination buffer, we need to + * append it manually. First make room for it... + */ - dstLen--; - result = encodingPtr->toUtfProc(encodingPtr->clientData, src, srcLen, - flags, statePtr, dst, dstLen, srcReadPtr, dstWrotePtr, - dstCharsPtr); - dst[*dstWrotePtr] = '\0'; + dstLen--; + } + do { + int savedFlags = flags; + Tcl_EncodingState savedState = *statePtr; + + result = encodingPtr->toUtfProc(encodingPtr->clientData, src, srcLen, + flags, statePtr, dst, dstLen, srcReadPtr, dstWrotePtr, + dstCharsPtr); + if (*dstCharsPtr <= maxChars) { + break; + } + dstLen = Tcl_UtfAtIndex(dst, maxChars) - 1 - dst + TCL_UTF_MAX; + flags = savedFlags; + *statePtr = savedState; + } while (1); + if (!noTerminate) { + /* ...and then append it */ + + dst[*dstWrotePtr] = '\0'; + } return result; } @@ -1421,7 +1450,7 @@ Tcl_UtfToExternal( * * Side effects: * The absolute pathname for the application is computed and stored to be - * returned later be [info nameofexecutable]. + * returned later by [info nameofexecutable]. * *--------------------------------------------------------------------------- */ @@ -2102,6 +2131,9 @@ BinaryProc( if (dstLen < 0) { dstLen = 0; } + if ((flags & TCL_ENCODING_CHAR_LIMIT) && srcLen > *dstCharsPtr) { + srcLen = *dstCharsPtr; + } if (srcLen > dstLen) { srcLen = dstLen; result = TCL_CONVERT_NOSPACE; @@ -2262,7 +2294,7 @@ UtfToUtfProc( { const char *srcStart, *srcEnd, *srcClose; const char *dstStart, *dstEnd; - int result, numChars; + int result, numChars, charLimit = INT_MAX; Tcl_UniChar ch; result = TCL_OK; @@ -2273,11 +2305,14 @@ UtfToUtfProc( if ((flags & TCL_ENCODING_END) == 0) { srcClose -= TCL_UTF_MAX; } + if (flags & TCL_ENCODING_CHAR_LIMIT) { + charLimit = *dstCharsPtr; + } dstStart = dst; dstEnd = dst + dstLen - TCL_UTF_MAX; - for (numChars = 0; src < srcEnd; numChars++) { + for (numChars = 0; src < srcEnd && numChars <= charLimit; numChars++) { if ((src > srcClose) && (!Tcl_UtfCharComplete(src, srcEnd - src))) { /* * If there is more string to follow, this will ensure that the @@ -2299,7 +2334,7 @@ UtfToUtfProc( *dst++ = *src++; } else if (pureNullMode == 1 && UCHAR(*src) == 0xc0 && - UCHAR(*(src+1)) == 0x80) { + (src + 1 < srcEnd) && UCHAR(*(src+1)) == 0x80) { /* * Convert 0xc080 to real nulls when we are in output mode. */ @@ -2373,9 +2408,12 @@ UnicodeToUtfProc( { const char *srcStart, *srcEnd; const char *dstEnd, *dstStart; - int result, numChars; + int result, numChars, charLimit = INT_MAX; Tcl_UniChar ch; + if (flags & TCL_ENCODING_CHAR_LIMIT) { + charLimit = *dstCharsPtr; + } result = TCL_OK; if ((srcLen % sizeof(Tcl_UniChar)) != 0) { result = TCL_CONVERT_MULTIBYTE; @@ -2389,7 +2427,7 @@ UnicodeToUtfProc( dstStart = dst; dstEnd = dst + dstLen - TCL_UTF_MAX; - for (numChars = 0; src < srcEnd; numChars++) { + for (numChars = 0; src < srcEnd && numChars <= charLimit; numChars++) { if (dst > dstEnd) { result = TCL_CONVERT_NOSPACE; break; @@ -2487,22 +2525,35 @@ UtfToUnicodeProc( if (dst > dstEnd) { result = TCL_CONVERT_NOSPACE; break; - } + } src += TclUtfToUniChar(src, &ch); /* * Need to handle this in a way that won't cause misalignment by * casting dst to a Tcl_UniChar. [Bug 1122671] - * XXX: This hard-codes the assumed size of Tcl_UniChar as 2. */ #ifdef WORDS_BIGENDIAN +#if TCL_UTF_MAX > 4 + *dst++ = (ch >> 24); + *dst++ = ((ch >> 16) & 0xFF); + *dst++ = ((ch >> 8) & 0xFF); + *dst++ = (ch & 0xFF); +#else *dst++ = (ch >> 8); *dst++ = (ch & 0xFF); +#endif +#else +#if TCL_UTF_MAX > 4 + *dst++ = (ch & 0xFF); + *dst++ = ((ch >> 8) & 0xFF); + *dst++ = ((ch >> 16) & 0xFF); + *dst++ = (ch >> 24); #else *dst++ = (ch & 0xFF); *dst++ = (ch >> 8); #endif +#endif } *srcReadPtr = src - srcStart; *dstWrotePtr = dst - dstStart; @@ -2557,12 +2608,15 @@ TableToUtfProc( { const char *srcStart, *srcEnd; const char *dstEnd, *dstStart, *prefixBytes; - int result, byte, numChars; + int result, byte, numChars, charLimit = INT_MAX; Tcl_UniChar ch; const unsigned short *const *toUnicode; const unsigned short *pageZero; TableEncodingData *dataPtr = clientData; + if (flags & TCL_ENCODING_CHAR_LIMIT) { + charLimit = *dstCharsPtr; + } srcStart = src; srcEnd = src + srcLen; @@ -2574,7 +2628,7 @@ TableToUtfProc( pageZero = toUnicode[0]; result = TCL_OK; - for (numChars = 0; src < srcEnd; numChars++) { + for (numChars = 0; src < srcEnd && numChars <= charLimit; numChars++) { if (dst > dstEnd) { result = TCL_CONVERT_NOSPACE; break; @@ -2788,8 +2842,11 @@ Iso88591ToUtfProc( { const char *srcStart, *srcEnd; const char *dstEnd, *dstStart; - int result, numChars; + int result, numChars, charLimit = INT_MAX; + if (flags & TCL_ENCODING_CHAR_LIMIT) { + charLimit = *dstCharsPtr; + } srcStart = src; srcEnd = src + srcLen; @@ -2797,7 +2854,7 @@ Iso88591ToUtfProc( dstEnd = dst + dstLen - TCL_UTF_MAX; result = TCL_OK; - for (numChars = 0; src < srcEnd; numChars++) { + for (numChars = 0; src < srcEnd && numChars <= charLimit; numChars++) { Tcl_UniChar ch; if (dst > dstEnd) { @@ -2958,7 +3015,9 @@ TableFreeProc( */ ckfree(dataPtr->toUnicode); + dataPtr->toUnicode = NULL; ckfree(dataPtr->fromUnicode); + dataPtr->fromUnicode = NULL; ckfree(dataPtr); } @@ -3011,9 +3070,12 @@ EscapeToUtfProc( const char *prefixBytes, *tablePrefixBytes, *srcStart, *srcEnd; const unsigned short *const *tableToUnicode; const Encoding *encodingPtr; - int state, result, numChars; + int state, result, numChars, charLimit = INT_MAX; const char *dstStart, *dstEnd; + if (flags & TCL_ENCODING_CHAR_LIMIT) { + charLimit = *dstCharsPtr; + } result = TCL_OK; tablePrefixBytes = NULL; /* lint. */ tableToUnicode = NULL; /* lint. */ @@ -3031,7 +3093,7 @@ EscapeToUtfProc( state = 0; } - for (numChars = 0; src < srcEnd; ) { + for (numChars = 0; src < srcEnd && numChars <= charLimit; ) { int byte, hi, lo, ch; if (dst > dstEnd) { @@ -3431,6 +3493,7 @@ EscapeFreeProc( subTablePtr = dataPtr->subTables; for (i = 0; i < dataPtr->numSubTables; i++) { FreeEncoding((Tcl_Encoding) subTablePtr->encodingPtr); + subTablePtr->encodingPtr = NULL; subTablePtr++; } } |