diff options
| author | hobbs <hobbs> | 2002-11-12 02:25:37 (GMT) |
|---|---|---|
| committer | hobbs <hobbs> | 2002-11-12 02:25:37 (GMT) |
| commit | 10f83aca6f0400e2c03d82df4348c90c81a5c6a0 (patch) | |
| tree | 465c280820c676024a6e78cd9ba6e299a78e9cdc /generic | |
| parent | 11acaadecced9136a82d1e9711ffc7a4d9b7090a (diff) | |
| download | tcl-10f83aca6f0400e2c03d82df4348c90c81a5c6a0.zip tcl-10f83aca6f0400e2c03d82df4348c90c81a5c6a0.tar.gz tcl-10f83aca6f0400e2c03d82df4348c90c81a5c6a0.tar.bz2 | |
* generic/tclEncoding.c (UtfToUtfProc, UtfToUnicodeProc):
(TableFromUtfProc, EscapeFromUtfProc): Use TclUtfToUniChar.
(UnicodeToUtfProc, TableToUtfProc): add 1-byte char optimizations
for Tcl_UniCharToUtf call. These improve encoded channel
conversion speeds by up to 20%.
Diffstat (limited to 'generic')
| -rw-r--r-- | generic/tclEncoding.c | 34 |
1 files changed, 26 insertions, 8 deletions
diff --git a/generic/tclEncoding.c b/generic/tclEncoding.c index ca5bacf..680a990 100644 --- a/generic/tclEncoding.c +++ b/generic/tclEncoding.c @@ -8,7 +8,7 @@ * See the file "license.terms" for information on usage and redistribution * of this file, and for a DISCLAIMER OF ALL WARRANTIES. * - * RCS: @(#) $Id: tclEncoding.c,v 1.13 2002/04/18 01:51:20 hobbs Exp $ + * RCS: @(#) $Id: tclEncoding.c,v 1.14 2002/11/12 02:25:37 hobbs Exp $ */ #include "tclInt.h" @@ -1795,8 +1795,12 @@ UtfToUtfProc(clientData, src, srcLen, flags, statePtr, dst, dstLen, result = TCL_CONVERT_NOSPACE; break; } - src += Tcl_UtfToUniChar(src, &ch); - dst += Tcl_UniCharToUtf(ch, dst); + if (UCHAR(*src) < 0x80) { + *dst++ = *src++; + } else { + src += Tcl_UtfToUniChar(src, &ch); + dst += Tcl_UniCharToUtf(ch, dst); + } } *srcReadPtr = src - srcStart; @@ -1873,7 +1877,14 @@ UnicodeToUtfProc(clientData, src, srcLen, flags, statePtr, dst, dstLen, result = TCL_CONVERT_NOSPACE; break; } - dst += Tcl_UniCharToUtf(*wSrc, dst); + /* + * Special case for 1-byte utf chars for speed. + */ + if (*wSrc && *wSrc < 0x80) { + *dst++ = (char) *wSrc; + } else { + dst += Tcl_UniCharToUtf(*wSrc, dst); + } wSrc++; } @@ -1957,7 +1968,7 @@ UtfToUnicodeProc(clientData, src, srcLen, flags, statePtr, dst, dstLen, result = TCL_CONVERT_NOSPACE; break; } - src += Tcl_UtfToUniChar(src, wDst); + src += TclUtfToUniChar(src, wDst); wDst++; } *srcReadPtr = src - srcStart; @@ -2059,7 +2070,14 @@ TableToUtfProc(clientData, src, srcLen, flags, statePtr, dst, dstLen, } ch = (Tcl_UniChar) byte; } - dst += Tcl_UniCharToUtf(ch, dst); + /* + * Special case for 1-byte utf chars for speed. + */ + if (ch && ch < 0x80) { + *dst++ = (char) ch; + } else { + dst += Tcl_UniCharToUtf(ch, dst); + } src++; } *srcReadPtr = src - srcStart; @@ -2147,7 +2165,7 @@ TableFromUtfProc(clientData, src, srcLen, flags, statePtr, dst, dstLen, result = TCL_CONVERT_MULTIBYTE; break; } - len = Tcl_UtfToUniChar(src, &ch); + len = TclUtfToUniChar(src, &ch); word = fromUnicode[(ch >> 8)][ch & 0xff]; if ((word == 0) && (ch != 0)) { if (flags & TCL_ENCODING_STOPONERROR) { @@ -2531,7 +2549,7 @@ EscapeFromUtfProc(clientData, src, srcLen, flags, statePtr, dst, dstLen, result = TCL_CONVERT_MULTIBYTE; break; } - len = Tcl_UtfToUniChar(src, &ch); + len = TclUtfToUniChar(src, &ch); word = tableFromUnicode[(ch >> 8)][ch & 0xff]; if ((word == 0) && (ch != 0)) { |