texlive[42924] Build/source/libs/teckit: remove TECkit SFconv, add
commits+preining at tug.org
commits+preining at tug.org
Wed Jan 11 02:34:07 CET 2017
Revision: 42924
http://tug.org/svn/texlive?view=revision&revision=42924
Author: preining
Date: 2017-01-11 02:34:07 +0100 (Wed, 11 Jan 2017)
Log Message:
-----------
remove TECkit SFconv, add patch to not build it
Modified Paths:
--------------
trunk/Build/source/libs/teckit/TECkit-PATCHES/ChangeLog
trunk/Build/source/libs/teckit/TECkit-PATCHES/TL-Changes
trunk/Build/source/libs/teckit/TECkit-src/bin/Makefile.am
Added Paths:
-----------
trunk/Build/source/libs/teckit/TECkit-PATCHES/patch-06-dont-build-sfconv
Removed Paths:
-------------
trunk/Build/source/libs/teckit/TECkit-src/SFconv/ConvertUTF.c
trunk/Build/source/libs/teckit/TECkit-src/SFconv/ConvertUTF.h
trunk/Build/source/libs/teckit/TECkit-src/SFconv/Debug_Prefix.h
trunk/Build/source/libs/teckit/TECkit-src/SFconv/Final_Prefix.h
trunk/Build/source/libs/teckit/TECkit-src/SFconv/SFconv.cpp
trunk/Build/source/libs/teckit/TECkit-src/SFconv/SFconv.prj
trunk/Build/source/libs/teckit/TECkit-src/SFconv/SFconv_ver.rc
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/expat.html
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlparse/MANIFEST
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlparse/Makefile.in
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlparse/hashtable.c
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlparse/hashtable.h
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlparse/makefile.win
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlparse/xmlparse.c
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlparse/xmlparse.h
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/Makefile.in
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/asciitab.h
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/dllmain.c
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/iasciitab.h
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/latin1tab.h
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/makefile.win
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/nametab.h
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/utf8tab.h
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/xmldef.h
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/xmlrole.c
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/xmlrole.h
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/xmltok.c
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/xmltok.h
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/xmltok_impl.c
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/xmltok_impl.h
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/xmltok_ns.c
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/codepage.c
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/codepage.h
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/filemap.h
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/readfilemap.c
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/unixfilemap.c
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/win32filemap.c
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/xmlfile.c
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/xmlfile.h
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/xmltchar.h
trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/xmlwf.c
trunk/Build/source/libs/teckit/TECkit-src/SFconv/sfReader.h
trunk/Build/source/libs/teckit/TECkit-src/SFconv/ushort_chartraits.h
Modified: trunk/Build/source/libs/teckit/TECkit-PATCHES/ChangeLog
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-PATCHES/ChangeLog 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-PATCHES/ChangeLog 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,3 +1,8 @@
+2017-01-11 Norbert Preining <norbert at preining.info>
+
+ Remove SFconv directory, contains non-free ConvertUTF.{c,h}
+ Add patch patch-06-dont-build-sfconv to not build sfconv.
+
2016-12-30 Akira Kakuto <kakuto at .fuk.kindai.ac.jp>
Imported TECkit-2.5.6 source tree (teckit) from
Modified: trunk/Build/source/libs/teckit/TECkit-PATCHES/TL-Changes
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-PATCHES/TL-Changes 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-PATCHES/TL-Changes 2017-01-11 01:34:07 UTC (rev 42924)
@@ -8,11 +8,7 @@
Removed:
.gitignore
- SFconv/expat/xmlparse/.cvsignore
- SFconv/expat/xmlparse/CVS/
- SFconv/expat/xmltok/.cvsignore
- SFconv/expat/xmltok/CVS/
- SFconv/expat/xmlwf/CVS/
+ SFconv/
TECkit.mcp
build-mac-binaries.sh
build-linux-package.sh
Added: trunk/Build/source/libs/teckit/TECkit-PATCHES/patch-06-dont-build-sfconv
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-PATCHES/patch-06-dont-build-sfconv (rev 0)
+++ trunk/Build/source/libs/teckit/TECkit-PATCHES/patch-06-dont-build-sfconv 2017-01-11 01:34:07 UTC (rev 42924)
@@ -0,0 +1,12 @@
+diff --git a/Build/source/libs/teckit/TECkit-src/bin/Makefile.am b/Build/source/libs/teckit/TECkit-src/bin/Makefile.am
+index 2337f1d851d..1edc61627bd 100644
+--- TECkit-src/bin/Makefile.am
++++ TECkit-src/bin/Makefile.am
+@@ -1,6 +1,6 @@
+ AUTOMAKE_OPTIONS = -Wno-portability
+
+-bin_PROGRAMS = teckit_compile txtconv sfconv
++bin_PROGRAMS = teckit_compile txtconv
+
+ AM_CPPFLAGS = -I$(top_srcdir)/source/Public-headers
+
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/ConvertUTF.c
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/ConvertUTF.c 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/ConvertUTF.c 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,539 +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 "ConvertUTF.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
-#define false 0
-#define true 1
-
-/* --------------------------------------------------------------------- */
-
-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) {
- fprintf(stderr, "ConvertUTF16toUTF32 illegal seq 0x%04x,%04x\n", ch, ch2);
- fflush(stderr);
-}
-#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;
- 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;
- 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 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;
-}
-
-/* --------------------------------------------------------------------- */
-
-/*
- * Exported function to return whether a UTF-8 sequence is legal or not.
- * This is not used here; it's just exported.
- */
-Boolean 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 */
- 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;
- 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;
- 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;
- 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;
- 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;
- 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.
-
- --------------------------------------------------------------------- */
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/ConvertUTF.h
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/ConvertUTF.h 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/ConvertUTF.h 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,149 +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. 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.
------------------------------------------------------------------------- */
-
-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 */
-
-/* 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;
-
-/* This is for C++ and does no harm in C */
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-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);
-
-Boolean isLegalUTF8Sequence(const UTF8 *source, const UTF8 *sourceEnd);
-
-#ifdef __cplusplus
-}
-#endif
-
-/* --------------------------------------------------------------------- */
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/Debug_Prefix.h
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/Debug_Prefix.h 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/Debug_Prefix.h 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,3 +0,0 @@
-#define DEBUG 1
-#define _MSL_NO_LOCALE 1
-#define XML_DTD 1
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/Final_Prefix.h
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/Final_Prefix.h 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/Final_Prefix.h 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,2 +0,0 @@
-#define _MSL_NO_LOCALE 1
-#define XML_DTD 1
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/SFconv.cpp
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/SFconv.cpp 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/SFconv.cpp 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,872 +0,0 @@
-#include <cstring>
-#include <cstdio>
-#include <cstdlib>
-
-#include <string>
-#include <fstream>
-#include <map>
-#include <vector>
-
-using namespace std;
-
-#include "TECkit_Engine.h"
-#include "ConvertUTF.h"
-#include "sfReader.h"
-
-#ifndef platformUTF16
-#ifdef __MWERKS__
-#if __dest_os==__win32_os
-#define platformUTF16 kForm_UTF16LE
-#else
-#define platformUTF16 kForm_UTF16BE
-#endif
-#endif
-#endif
-
-#ifndef platformUTF16
-#ifdef __APPLE__
-#include <TargetConditionals.h>
-#if TARGET_RT_BIG_ENDIAN
-#define platformUTF16 kForm_UTF16BE
-#else
-#define platformUTF16 kForm_UTF16LE
-#endif
-#endif
-#endif
-
-#ifndef platformUTF16
-#include "config.h"
-#if WORDS_BIGENDIAN
-#define platformUTF16 kForm_UTF16BE
-#else
-#define platformUTF16 kForm_UTF16LE
-#endif
-#endif
-
-#if HAVE_LIBEXPAT
-#include <expat.h>
-#else
-#include "expat/xmlparse/xmlparse.h"
-#endif
-
-
-char* gMappingDirectory;
-
-typedef basic_string<UniChar> ustring;
-
-map<string,string> sfmMappings;
-map<string,string> inlineMappings;
-
-map<string,string>* mappings;
-
-string defaultMapping;
-string sfmMapping;
-string inlineMapping;
-
-ustring sfmCharsU;
-ustring inlineCharsU;
-long escapeCharU = 0x5c;
-long inlineEscapeCharU = -1;
-long startInlineU = -1;
-long endInlineU = -1;
-
-const char* defaultMarkerChars = "abcdefghijklmnopqrstuvwxyz_ABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789";
-
-map<string,TECkit_Converter> converters;
-
-enum dir_enum {
- kDirection_Unspecified = 0,
- kDirection_8_U,
- kDirection_U_8
-} direction = kDirection_Unspecified;
-
-int inForm = kForm_Unspecified;
-int outForm = kForm_Unspecified;
-
-static int sDepth;
-static int sError;
-
-static inline bool
-streq(const char* s, const char* t)
-{
- return (strcmp(s, t) == 0);
-}
-
-static ustring
-Utf8ToString(const char* s)
-{
- int len = strlen(s);
- UniChar* buf = new UniChar[len];
- const Byte* sourceStart = (Byte*)s;
- UniChar* targetStart = buf;
- int status = ConvertUTF8toUTF16(&sourceStart, sourceStart + len, &targetStart, targetStart + len, lenientConversion);
- if (status != conversionOK) {
- fprintf(stderr, "error %d converting UTF-8 to UTF-16\n", status);
- exit(1);
- }
- ustring ustr(buf, targetStart - buf);
- delete[] buf;
- return ustr;
-}
-
-static void
-startElement(void* /*userData*/, const XML_Char *name, const XML_Char **atts)
-{
- switch (sDepth) {
- case 0:
- if (streq(name, "sfConversion")) {
- while (*atts) {
- const XML_Char* n = *atts++;
- const XML_Char* v = *atts++;
- if (streq(n, "defaultMapping")) {
- defaultMapping = v;
- }
- else {
- fprintf(stderr, "unrecognized attribute \"%s\" for <sfConversion>\n", n);
- sError = 1;
- break;
- }
- }
- if (defaultMapping.length() == 0) {
- fprintf(stderr, "<sfConversion> requires \"defaultMapping\" attribute\n");
- sError = 1;
- break;
- }
- }
- else {
- fprintf(stderr, "expected <sfConversion>, not <%s>, as top-level element in control file\n", name);
- sError = 1;
- break;
- }
- break;
-
- case 1:
- if (streq(name, "sfMarkers")) {
- while (*atts) {
- const XML_Char* n = *atts++;
- const XML_Char* v = *atts++;
- if (streq(n, "escape")) {
- ustring u = Utf8ToString(v);
- if (u.length() != 1) {
- fprintf(stderr, "\"escape\" attribute of <sfMarkers> must be a single character\n");
- sError = 1;
- break;
- }
- escapeCharU = u[0];
- }
- else if (streq(n, "chars")) {
- sfmCharsU = Utf8ToString(v);
- }
- else if (streq(n, "mapping")) {
- sfmMapping = v;
- }
- else {
- fprintf(stderr, "unrecognized attribute \"%s\" for <sfMarkers>\n", n);
- sError = 1;
- break;
- }
- }
- if (sfmMapping.length() == 0)
- sfmMapping = defaultMapping;
- if (sfmCharsU.length() == 0) {
- sfmCharsU.reserve(96);
- for (const char* cp = defaultMarkerChars; *cp; ++cp)
- sfmCharsU.append(1, *cp);
- }
- mappings = &sfmMappings;
- }
- else if (streq(name, "inlineMarkers")) {
- while (*atts) {
- const XML_Char* n = *atts++;
- const XML_Char* v = *atts++;
- if (streq(n, "escape")) {
- ustring u = Utf8ToString(v);
- if (u.length() != 1) {
- fprintf(stderr, "\"escape\" attribute of <inlineMarkers> must be a single character\n");
- sError = 1;
- break;
- }
- inlineEscapeCharU = u[0];
- }
- else if (streq(n, "start")) {
- ustring u = Utf8ToString(v);
- if (u.length() != 1) {
- fprintf(stderr, "\"start\" attribute of <inlineMarkers> must be a single character\n");
- sError = 1;
- break;
- }
- startInlineU = u[0];
- }
- else if (streq(n, "end")) {
- ustring u = Utf8ToString(v);
- if (u.length() != 1) {
- fprintf(stderr, "\"end\" attribute of <inlineMarkers> must be a single character\n");
- sError = 1;
- break;
- }
- endInlineU = u[0];
- }
- else if (streq(n, "chars")) {
- inlineCharsU = Utf8ToString(v);
- }
- else if (streq(n, "mapping")) {
- inlineMapping = v;
- }
- else {
- fprintf(stderr, "unrecognized attribute \"%s\" for <inlineMarkers>\n", n);
- sError = 1;
- break;
- }
- }
- if (inlineMapping.length() == 0)
- inlineMapping = defaultMapping;
- if (inlineCharsU.length() == 0) {
- inlineCharsU.reserve(96);
- for (const char* cp = defaultMarkerChars; *cp; ++cp)
- inlineCharsU.append(1, *cp);
- }
- mappings = &inlineMappings;
- }
- else {
- fprintf(stderr, "unrecognized element <%s> in <sfConversion>\n", name);
- sError = 1;
- break;
- }
- break;
-
- case 2:
- if (streq(name, "marker")) {
- string marker;
- string mapping;
- while (*atts) {
- const XML_Char* n = *atts++;
- const XML_Char* v = *atts++;
- if (streq(n, "name")) {
- marker = v;
- }
- else if (streq(n, "mapping")) {
- mapping = v;
- }
- else {
- fprintf(stderr, "unrecognized attribute \"%s\" for <marker>\n", n);
- sError = 1;
- break;
- }
- }
- if (marker.length() == 0 || mapping.length() == 0) {
- fprintf(stderr, "<marker> requires \"name\" and \"mapping\" attributes\n");
- sError = 1;
- break;
- }
- if ((*mappings).find(marker) != (*mappings).end()) {
- fprintf(stderr, "duplicate entry for marker \"%s\"\n", marker.c_str());
- sError = 1;
- break;
- }
- (*mappings)[marker] = mapping;
- }
- else {
- fprintf(stderr, "unrecognized element <%s>\n", name);
- sError = 1;
- break;
- }
- break;
-
- default:
- fprintf(stderr, "control file elements nested improperly at <%s>\n", name);
- sError = 1;
- break;
- }
-
- ++sDepth;
-}
-
-static void
-endElement(void* /*userData*/, const XML_Char */*name*/)
-{
- --sDepth;
-}
-
-bool bom = false;
-
-static TECkit_Converter
-makeConverter(const string& mappingName, int direction)
-{
- string mapFileName;
- if (gMappingDirectory)
- mapFileName += gMappingDirectory;
- mapFileName += mappingName;
- mapFileName += ".tec";
-
- FILE* mapFile = fopen(mapFileName.c_str(), "rb");
- if (mapFile == 0) {
- fprintf(stderr, "unable to read mapping file for %s (file %s)\n", mappingName.c_str(), mapFileName.c_str());
- exit(1);
- }
-
- fseek(mapFile, 0, SEEK_END);
- long fileSize = ftell(mapFile);
- fseek(mapFile, 0, SEEK_SET);
-
- unsigned char* buf = (unsigned char*)malloc(fileSize);
- if (buf == 0) {
- fprintf(stderr, "unable to read mapping file for %s (file %s)\n", mappingName.c_str(), mapFileName.c_str());
- exit(1);
- }
- fileSize = fread(buf, 1, fileSize, mapFile);
- fclose(mapFile);
-
- TECkit_Converter converter;
- TECkit_Status status = TECkit_CreateConverter(buf, fileSize,
- (direction == kDirection_8_U),
- (direction == kDirection_8_U) ? kForm_Bytes : platformUTF16,
- (direction == kDirection_8_U) ? outForm : kForm_Bytes,
- &converter);
- if (status != kStatus_NoError) {
- fprintf(stderr, "failed to create converter for %s (file %s)\n", mappingName.c_str(), mapFileName.c_str());
- exit(1);
- }
-
- free(buf);
-
- return converter;
-}
-
-static bool
-read_control_file(const char* controlFile)
-{
- FILE* ctlFile = fopen(controlFile, "r");
- if (ctlFile == 0) {
- fprintf(stderr, "unable to open control file %s\n", controlFile);
- return false;
- }
-
- char buf[BUFSIZ];
- XML_Parser parser = XML_ParserCreate(0);
- int done;
-
- XML_SetElementHandler(parser, startElement, endElement);
-
- int status = 0;
- do {
- size_t len = fread(buf, 1, sizeof(buf), ctlFile);
- done = len < sizeof(buf);
- if (!XML_Parse(parser, buf, len, done)) {
- fprintf(stderr, "XML parse error: %s at line %lu\n", XML_ErrorString(XML_GetErrorCode(parser)), (unsigned long)XML_GetCurrentLineNumber(parser));
- status = 1;
- }
- } while (!status && !done);
-
- fclose(ctlFile);
-
- XML_ParserFree(parser);
-
- if (status != 0)
- return false;
-
- converters[defaultMapping] = makeConverter(defaultMapping, direction);
-
- if (converters.find(sfmMapping) == converters.end())
- converters[sfmMapping] = makeConverter(sfmMapping, direction);
- if (inlineMapping.length() > 0 && converters.find(inlineMapping) == converters.end())
- converters[sfmMapping] = makeConverter(inlineMapping, direction);
-
- for (map<string,string>::const_iterator i = sfmMappings.begin(); i != sfmMappings.end(); ++i) {
- if (converters.find(i->second) == converters.end())
- converters[i->second] = makeConverter(i->second, direction);
- }
- for (map<string,string>::const_iterator i = inlineMappings.begin(); i != inlineMappings.end(); ++i) {
- if (converters.find(i->second) == converters.end())
- converters[i->second] = makeConverter(i->second, direction);
- }
- return true;
-}
-
-static void
-write_converted(const Byte* data, long nBytes, TECkit_Converter converter, FILE* outFile)
-{
-static Byte* convBuffer = 0;
-static UInt32 bufferSize = 0;
-
- UInt32 reqSpace = nBytes * 4 + 256; // probably plenty of space
- UInt32 sourceUsed, destUsed;
- int status;
-
-// do the conversion
-
- while (1) {
- if (bufferSize < reqSpace) {
- if (convBuffer != 0)
- delete[] convBuffer;
- bufferSize = reqSpace;
- convBuffer = new Byte[bufferSize];
- }
- status = TECkit_ConvertBuffer(
- converter,
- const_cast<Byte*>(data),
- nBytes,
- &sourceUsed,
- convBuffer,
- bufferSize,
- &destUsed,
- true);
- if (status == kStatus_OutputBufferFull) {
- reqSpace *= 2; // output didn't fit, enlarge buffer and try again
- continue;
- }
- if (status != kStatus_NoError) {
- fprintf(stderr, "error %d in TECkit_Convert\n", status);
- exit(1);
- }
- UInt32 destUsed2;
- status = TECkit_Flush(
- converter,
- convBuffer + destUsed,
- bufferSize - destUsed,
- &destUsed2);
- if (status == kStatus_OutputBufferFull) {
- reqSpace *= 2;
- continue;
- }
- TECkit_ResetConverter(converter);
- if (status != kStatus_NoError) {
- fprintf(stderr, "error %d in TECkit_Flush\n", status);
- exit(1);
- }
- nBytes = destUsed + destUsed2;
- break;
- }
-
- fwrite(convBuffer, 1, nBytes, outFile);
-}
-
-static void
-convertMarker(const ustring& marker, TECkit_Converter converter, string& cnvMarker)
-{
- int status;
- if (cnvMarker.size() < marker.length() * 4)
- cnvMarker.resize(marker.length() * 4 + 32);
- while (1) {
- UInt32 sourceUsed, destUsed, destUsed2;
- status = TECkit_ConvertBuffer(converter,
- (Byte*)marker.data(),
- marker.size() * 2,
- &sourceUsed,
- (Byte*)cnvMarker.data(),
- cnvMarker.size(),
- &destUsed,
- true);
- if (status == kStatus_OutputBufferFull) {
- cnvMarker.resize(cnvMarker.size() * 2);
- continue;
- }
- status = TECkit_Flush(converter,
- (Byte*)cnvMarker.data() + destUsed,
- cnvMarker.size() - destUsed,
- &destUsed2);
- if (status == kStatus_OutputBufferFull) {
- cnvMarker.resize(cnvMarker.size() * 2);
- continue;
- }
- cnvMarker.resize(destUsed + destUsed2);
- TECkit_ResetConverter(converter);
- if (status != kStatus_NoError) {
- fprintf(stderr, "error %d converting SFM from Unicode\n", status);
- exit(1);
- }
- break;
- }
-}
-
-static long
-convertSingleChar(UniChar inChar, TECkit_Converter converter)
-{
- int status;
- Byte buf[32];
- UInt32 sourceUsed, destUsed, destUsed2;
-
- status = TECkit_ConvertBuffer(converter,
- (Byte*)&inChar,
- 2,
- &sourceUsed,
- &buf[0],
- sizeof(buf),
- &destUsed,
- true);
- if (status == kStatus_OutputBufferFull || destUsed > 1) {
- fprintf(stderr, "marker characters must map to single byte values");
- exit(1);
- }
- status = TECkit_Flush(converter,
- &buf[0] + destUsed,
- sizeof(buf) - destUsed,
- &destUsed2);
- if (status == kStatus_OutputBufferFull || destUsed + destUsed2 != 1) {
- fprintf(stderr, "marker characters must map to single byte values");
- exit(1);
- }
- TECkit_ResetConverter(converter);
-
- if (status != kStatus_NoError) {
- fprintf(stderr, "error %d converting marker characters from Unicode\n", status);
- exit(1);
- }
-
- return buf[0];
-}
-
-static void
-process(const char* inputFile, const char* outputFile)
-{
- TECkit_Converter defaultConverter = converters[defaultMapping];
- TECkit_Converter sfmConverter = converters[sfmMapping];
- TECkit_Converter inlineConverter = converters[inlineMapping];
-
- FILE* outFile = fopen(outputFile, "wb");
- if (!outFile) {
- fprintf(stderr, "unable to open output file %s\n", outputFile);
- exit(1);
- }
-
- FILE* inFile = fopen(inputFile, "rb");
- if (!inFile) {
- fprintf(stderr, "unable to open input file %s\n", inputFile);
- exit(1);
- }
-
- if (direction == kDirection_8_U) {
- // *** Byte to Unicode conversion
- if (outForm == kForm_Unspecified)
- outForm = kForm_UTF8;
-
- if (bom) {
- if (outForm == kForm_UTF8) {
- Byte bom[] = "\xEF\xBB\xBF";
- fwrite(bom, 3, 1, outFile);
- }
- else if (outForm == kForm_UTF16BE) {
- Byte bom[] = "\xFE\xFF";
- fwrite(&bom, 2, 1, outFile);
- }
- else {
- Byte bom[] = "\xFF\xFE";
- fwrite(&bom, 2, 1, outFile);
- }
- }
-
- sfReader<char> reader(inFile);
-
- TECkit_Converter markerMapping = makeConverter(sfmMapping, kDirection_U_8);
-
- reader.escapeChar = convertSingleChar(escapeCharU, markerMapping);
- for (size_t i = 0; i < sfmCharsU.length(); ++i)
- reader.sfmChars.append(1, convertSingleChar(sfmCharsU[i], markerMapping));
-
- if (inlineEscapeCharU != -1) {
- if (inlineMapping != sfmMapping) {
- TECkit_DisposeConverter(markerMapping);
- markerMapping = makeConverter(inlineMapping, kDirection_U_8);
- }
- reader.inlineEscapeChar = convertSingleChar(inlineEscapeCharU, markerMapping);
- reader.startInline = convertSingleChar(startInlineU, markerMapping);
- reader.endInline = convertSingleChar(endInlineU, markerMapping);
- for (size_t i = 0; i < inlineCharsU.length(); ++i)
- reader.inlineChars.append(1, convertSingleChar(inlineCharsU[i], markerMapping));
- }
-
- TECkit_DisposeConverter(markerMapping);
-
- vector<TECkit_Converter> converterStack;
- converterStack.assign(1, defaultConverter);
- int dataType;
- while ((dataType = reader.next(converterStack.size() > 1)) != END_OF_FILE) {
- map<string,string>::const_iterator i;
- switch (dataType) {
- case BODY_TEXT:
- write_converted((Byte*)reader.text.data(), reader.text.length(), converterStack.back(), outFile);
- break;
-
- case SFM:
- i = sfmMappings.find(reader.text);
- if (i == sfmMappings.end())
- converterStack.assign(1, defaultConverter);
- else
- converterStack.assign(1, converters[i->second]);
- reader.text.insert(reader.text.begin(), reader.escapeChar);
- write_converted((Byte*)reader.text.data(), reader.text.length(), sfmConverter, outFile);
- break;
-
- case INLINE_MARKER:
- i = inlineMappings.find(reader.text);
- if (i == inlineMappings.end())
- converterStack.assign(1, converterStack.back());
- else
- converterStack.assign(1, converters[i->second]);
- reader.text.insert(reader.text.begin(), reader.escapeChar);
- write_converted((Byte*)reader.text.data(), reader.text.length(), inlineConverter, outFile);
- break;
-
- case INLINE_START:
- i = inlineMappings.find(reader.text);
- if (i == inlineMappings.end())
- converterStack.push_back(converterStack.back());
- else
- converterStack.push_back(converters[i->second]);
- reader.text.insert(reader.text.begin(), reader.inlineEscapeChar);
- reader.text.insert(reader.text.end(), reader.startInline);
- write_converted((Byte*)reader.text.data(), reader.text.length(), inlineConverter, outFile);
- break;
-
- case INLINE_END:
- reader.text.insert(reader.text.end(), reader.endInline);
- write_converted((Byte*)reader.text.data(), reader.text.length(), inlineConverter, outFile);
- converterStack.pop_back();
- break;
- }
- }
- }
- else {
- // *** Unicode to Byte conversion
- Byte bom[3];
- long pos = ftell(inFile);
- if (fread(bom, 3, 1, inFile) > 0) {
- if (bom[0] == 0xef && bom[1] == 0xbb && bom[2] == 0xbf) {
- inForm = kForm_UTF8;
- }
- else if (bom[0] == 0xfe && bom[1] == 0xff) {
- inForm = kForm_UTF16BE;
- fseek(inFile, pos + 2, SEEK_SET);
- }
- else if (bom[0] == 0xff && bom[1] == 0xfe) {
- inForm = kForm_UTF16LE;
- fseek(inFile, pos + 2, SEEK_SET);
- }
- else {
- if (inForm == kForm_Unspecified) {
- if (bom[0] == 0)
- inForm = kForm_UTF16BE;
- else if (bom[1] == 0)
- inForm = kForm_UTF16LE;
- else
- inForm = kForm_UTF8;
- }
- fseek(inFile, pos, SEEK_SET);
- }
- }
- else
- fseek(inFile, pos, SEEK_SET);
-
- sfReader<UniChar> reader(inFile, inForm);
-
- reader.escapeChar = escapeCharU;
- reader.sfmChars = sfmCharsU;
-
- if (inlineEscapeCharU != -1) {
- reader.inlineEscapeChar = inlineEscapeCharU;
- reader.startInline = startInlineU;
- reader.endInline = endInlineU;
- reader.inlineChars = inlineCharsU;
- }
-
- vector<TECkit_Converter> converterStack;
- converterStack.assign(1, defaultConverter);
- int dataType;
- while ((dataType = reader.next(converterStack.size() > 1)) != END_OF_FILE) {
- map<string,string>::const_iterator i;
- static string cnvMarker;
- switch (dataType) {
- case BODY_TEXT:
- write_converted((Byte*)reader.text.data(), reader.text.length() * 2, converterStack.back(), outFile);
- break;
-
- case SFM:
- convertMarker(reader.text, sfmConverter, cnvMarker);
- i = sfmMappings.find(cnvMarker);
- if (i == sfmMappings.end())
- converterStack.assign(1, defaultConverter);
- else
- converterStack.assign(1, converters[i->second]);
- reader.text.insert(reader.text.begin(), reader.escapeChar);
- write_converted((Byte*)reader.text.data(), reader.text.length() * 2, sfmConverter, outFile);
- break;
-
- case INLINE_MARKER:
- convertMarker(reader.text, inlineConverter, cnvMarker);
- i = inlineMappings.find(cnvMarker);
- if (i == inlineMappings.end())
- converterStack.assign(1, converterStack.back());
- else
- converterStack.assign(1, converters[i->second]);
- reader.text.insert(reader.text.begin(), reader.inlineEscapeChar);
- write_converted((Byte*)reader.text.data(), reader.text.length() * 2, inlineConverter, outFile);
- break;
-
- case INLINE_START:
- convertMarker(reader.text, inlineConverter, cnvMarker);
- i = inlineMappings.find(cnvMarker);
- if (i == inlineMappings.end())
- converterStack.push_back(converterStack.back());
- else
- converterStack.push_back(converters[i->second]);
- reader.text.insert(reader.text.begin(), reader.inlineEscapeChar);
- reader.text.insert(reader.text.end(), reader.startInline);
- write_converted((Byte*)reader.text.data(), reader.text.length() * 2, inlineConverter, outFile);
- break;
-
- case INLINE_END:
- reader.text.insert(reader.text.end(), reader.endInline);
- write_converted((Byte*)reader.text.data(), reader.text.length() * 2, inlineConverter, outFile);
- converterStack.pop_back();
- break;
- }
- }
- }
-
- fclose(inFile);
- fclose(outFile);
-}
-
-#ifdef __MWERKS__
-#if (__dest_os == __mac_os)
-#include <console.h>
-#endif
-#endif
-
-int
-main(
- int argc,
- char** argv)
-{
-#ifdef __MWERKS__
-#if (__dest_os == __mac_os)
- argc = ccommand(&argv);
-#endif
-#endif
-
- char* controlFile = 0;
- char* inputFile = 0;
- char* outputFile = 0;
-
- bool cmdLineErr = (argc < 2);
-
- char unicodeFormat = kForm_UTF8;
-
- int normForm = 0;
-
- while (--argc) {
- char *arg = *++argv;
- if (arg[0] == '-') {
- if (strlen(arg + 1) == 1) {
- switch (arg[1]) {
- case 'c':
- if (controlFile != 0) {
- fprintf(stderr, "repeated argument -c\n");
- cmdLineErr = true;
- continue;
- }
- if (argc == 0) {
- fprintf(stderr, "missing file name after -c\n");
- cmdLineErr = true;
- continue;
- }
- controlFile = *++argv;
- --argc;
- continue;
- case 'd':
- if (gMappingDirectory != 0) {
- fprintf(stderr, "repeated argument -d\n");
- cmdLineErr = true;
- continue;
- }
- if (argc == 0) {
- fprintf(stderr, "missing directory path after -d\n");
- cmdLineErr = true;
- continue;
- }
- gMappingDirectory = *++argv;
- --argc;
- continue;
- case 'i':
- if (inputFile != 0) {
- fprintf(stderr, "repeated argument -i\n");
- cmdLineErr = true;
- continue;
- }
- if (argc == 0) {
- fprintf(stderr, "missing file name after -i\n");
- cmdLineErr = true;
- continue;
- }
- inputFile = *++argv;
- --argc;
- continue;
- case 'o':
- if (outputFile != 0) {
- fprintf(stderr, "repeated argument -o\n");
- cmdLineErr = true;
- continue;
- }
- if (argc == 0) {
- fprintf(stderr, "missing file name after -o\n");
- cmdLineErr = true;
- continue;
- }
- outputFile = *++argv;
- --argc;
- continue;
- case 'h':
- cmdLineErr = true; // to get "usage" message
- continue;
- }
- }
- else if (strcmp(arg + 1, "utf8") == 0)
- unicodeFormat = kForm_UTF8;
- else if (strcmp(arg + 1, "be") == 0)
- unicodeFormat = kForm_UTF16BE;
- else if (strcmp(arg + 1, "le") == 0)
- unicodeFormat = kForm_UTF16LE;
- else if (strcmp(arg + 1, "bom") == 0)
- bom = true;
- else if (strcmp(arg + 1, "u8") == 0)
- direction = kDirection_U_8;
- else if (strcmp(arg + 1, "8u") == 0)
- direction = kDirection_8_U;
- else if (strcmp(arg + 1, "nfc") == 0)
- normForm = kForm_NFC;
- else if (strcmp(arg + 1, "nfd") == 0)
- normForm = kForm_NFD;
- else {
- fprintf(stderr, "Unknown option: %s\n", arg);
- cmdLineErr = true;
- }
- }
- else {
- cmdLineErr = true;
- }
- }
-
- if (cmdLineErr || direction == kDirection_Unspecified || unicodeFormat == kForm_Unspecified) {
- fprintf(stderr, "\
-8-bit to Unicode:\n\
- SFconv -8u [-utf8|-be|-le] [-bom] -c ControlFile [-d MappingDirectory] -i InFile -o OutFile\n\
-Unicode to 8-bit:\n\
- SFconv -u8 [-utf8|-be|-le] -c ControlFile [-d MappingDirectory] -i InFile -o OutFile\n");
- return 1;
- }
-
- if (direction == kDirection_8_U) {
- inForm = kForm_Bytes;
- outForm = unicodeFormat + normForm;
- }
- else {
- inForm = unicodeFormat;
- outForm = kForm_Bytes;
- }
-
- if (!read_control_file(controlFile))
- exit(1);
-
- process(inputFile, outputFile);
-
- return 0;
-}
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/SFconv.prj
===================================================================
(Binary files differ)
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/SFconv_ver.rc
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/SFconv_ver.rc 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/SFconv_ver.rc 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,42 +0,0 @@
-/*------------------------------------------------------------------------
-Copyright (c) 2008-2016 SIL International. All rights reserved.
-
-Distributable under the terms of either the Common Public License or the
-GNU Lesser General Public License, as specified in the LICENSING.txt file.
-------------------------------------------------------------------------*/
-
-//
-// Version
-//
-
-#include "version_defs.h"
-
-VS_VERSION_INFO VERSIONINFO
-FILEVERSION VER_FILEVERSION
-PRODUCTVERSION VER_PRODUCTVERSION
-FILEFLAGSMASK VS_FFI_FILEFLAGSMASK
-FILEFLAGS VER_DEBUG
-FILEOS VOS__WINDOWS32
-FILETYPE VFT_DLL
-FILESUBTYPE VFT2_UNKNOWN
-BEGIN
- BLOCK "StringFileInfo"
- BEGIN
- BLOCK "040904b0"
- BEGIN
- VALUE "Comments", "Standard Format file conversion tool\0"
- VALUE "CompanyName", VER_COMPANY_NAME_STR
- VALUE "FileDescription", "Standard Format file conversion tool\0"
- VALUE "FileVersion", VER_FILEVERSION_STR
- VALUE "InternalName", "sfconv\0"
- VALUE "LegalCopyright", VER_COPYRIGHT_STR
- VALUE "OriginalFilename", "sfconv.exe\0"
- VALUE "ProductName", VER_PRODUCT_NAME_STR
- VALUE "ProductVersion", VER_PRODUCTVERSION_STR
- END
- END
- BLOCK "VarFileInfo"
- BEGIN
- VALUE "Translation", 0x409, 1200
- END
-END
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/expat.html
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/expat.html 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/expat.html 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,67 +0,0 @@
-<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN"
-"http://www.w3.org/TR/REC-html40/loose.dtd">
-
-<HTML>
-
-<TITLE>expat</TITLE>
-
-<BODY>
-
-<H1>expat - XML Parser Toolkit</H1>
-
-<H3>Version 19990307</H3>
-
-<P>Copyright (c) 1998, 1999 James Clark. Expat is subject to the <A
-HREF="MPL-1_0.html">Mozilla Public License Version 1.0</A>. You may
-as a special exception <A href="gplelect.html">elect to use the GNU
-General Public License</A>. Please contact me if you wish to
-negotiate an alternative license.</P>
-
-<P>Expat is an <A
-HREF="http://www.w3.org/TR/1998/REC-xml-19980210">XML 1.0</A> parser
-written in C. It aims to be fully conforming. It is currently not a
-validating XML processor. The current production version of expat can
-be downloaded from <A href = "ftp://ftp.jclark.com/pub/xml/expat.zip"
->ftp://ftp.jclark.com/pub/xml/expat.zip</A>.</P>
-
-<P>The directory <SAMP>xmltok</SAMP> contains a low-level library for
-tokenizing XML. The interface is documented in
-<SAMP>xmltok/xmltok.h</SAMP>.</P>
-
-<P>The directory <SAMP>xmlparse</SAMP> contains an XML parser library
-which is built on top of the <SAMP>xmltok</SAMP> library. The
-interface is documented in <SAMP>xmlparse/xmlparse.h</SAMP>. The
-directory <SAMP>sample</SAMP> contains a simple example program using
-this interface; <SAMP>sample/build.bat</SAMP> is a batch file to build
-the example using Visual C++.</P>
-
-<P>The directory <SAMP>xmlwf</SAMP> contains the <SAMP>xmlwf</SAMP>
-application, which uses the <SAMP>xmlparse</SAMP> library. The
-arguments to <SAMP>xmlwf</SAMP> are one or more files which are each
-to be checked for well-formedness. An option <SAMP>-d
-<VAR>dir</VAR></SAMP> can be specified; for each well-formed input
-file the corresponding <A
-href="http://www.jclark.com/xml/canonxml.html">canonical XML</A> will
-be written to <SAMP>dir/<VAR>f</VAR></SAMP>, where
-<SAMP><VAR>f</VAR></SAMP> is the filename (without any path) of the
-input file. A <CODE>-x</CODE> option will cause references to
-external general entities to be processed.</P>
-
-<P>The <SAMP>bin</SAMP> directory contains Win32 executables. The
-<SAMP>lib</SAMP> directory contains Win32 import libraries.</P>
-
-<P>Answers to some frequently asked questions about expat can be found
-in the <A HREF="http://www.jclark.com/xml/expatfaq.html">expat
-FAQ</A>.</P>
-
-<P></P>
-
-<ADDRESS>
-
-<A HREF="mailto:jjc at jclark.com">James Clark</A>
-
-</ADDRESS>
-
-</BODY>
-
-</HTML>
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlparse/MANIFEST
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlparse/MANIFEST 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlparse/MANIFEST 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,5 +0,0 @@
-#
-# This is a list of local files which get copied to the mozilla:dist directory
-#
-
-xmlparse.h
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlparse/Makefile.in
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlparse/Makefile.in 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlparse/Makefile.in 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,47 +0,0 @@
-#
-# The contents of this file are subject to the Netscape Public
-# License Version 1.1 (the "License"); you may not use this file
-# except in compliance with the License. You may obtain a copy of
-# the License at http://www.mozilla.org/NPL/
-#
-# Software distributed under the License is distributed on an "AS
-# IS" basis, WITHOUT WARRANTY OF ANY KIND, either express or
-# implied. See the License for the specific language governing
-# rights and limitations under the License.
-#
-# The Original Code is mozilla.org code.
-#
-# The Initial Developer of the Original Code is Netscape
-# Communications Corporation. Portions created by Netscape are
-# Copyright (C) 1998 Netscape Communications Corporation. All
-# Rights Reserved.
-#
-# Contributor(s):
-#
-
-DEPTH = ../..
-topsrcdir = @top_srcdir@
-srcdir = @srcdir@
-VPATH = @srcdir@
-
-include $(DEPTH)/config/autoconf.mk
-
-MODULE = expat
-LIBRARY_NAME = expat_s
-
-CSRCS = \
- hashtable.c \
- xmlparse.c \
- $(NULL)
-
-EXPORTS = xmlparse.h
-
-EXPORTS := $(addprefix $(srcdir)/, $(EXPORTS))
-
-LOCAL_INCLUDES = -I$(srcdir)/../xmltok
-
-# We want only the static lib, not the shared lib
-override NO_SHARED_LIB=1
-override NO_STATIC_LIB=
-
-include $(topsrcdir)/config/rules.mk
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlparse/hashtable.c
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlparse/hashtable.c 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlparse/hashtable.c 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,151 +0,0 @@
-/*
-The contents of this file are subject to the Mozilla Public License
-Version 1.1 (the "License"); you may not use this file except in
-csompliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998, 1999
-James Clark. All Rights Reserved.
-
-Contributor(s):
-
-Alternatively, the contents of this file may be used under the terms
-of the GNU General Public License (the "GPL"), in which case the
-provisions of the GPL are applicable instead of those above. If you
-wish to allow use of your version of this file only under the terms of
-the GPL and not to allow others to use your version of this file under
-the MPL, indicate your decision by deleting the provisions above and
-replace them with the notice and other provisions required by the
-GPL. If you do not delete the provisions above, a recipient may use
-your version of this file under either the MPL or the GPL.
-*/
-
-#include "xmldef.h"
-
-#ifdef XML_UNICODE_WCHAR_T
-#ifndef XML_UNICODE
-#define XML_UNICODE
-#endif
-#endif
-
-#include "hashtable.h"
-
-#define INIT_SIZE 64
-
-static
-int keyeq(KEY s1, KEY s2)
-{
- for (; *s1 == *s2; s1++, s2++)
- if (*s1 == 0)
- return 1;
- return 0;
-}
-
-static
-unsigned long hash(KEY s)
-{
- unsigned long h = 0;
- while (*s)
- h = (h << 5) + h + (unsigned char)*s++;
- return h;
-}
-
-NAMED *lookup(HASH_TABLE *table, KEY name, size_t createSize)
-{
- size_t i;
- if (table->size == 0) {
- if (!createSize)
- return 0;
- table->v = calloc(INIT_SIZE, sizeof(NAMED *));
- if (!table->v)
- return 0;
- table->size = INIT_SIZE;
- table->usedLim = INIT_SIZE / 2;
- i = hash(name) & (table->size - 1);
- }
- else {
- unsigned long h = hash(name);
- for (i = h & (table->size - 1);
- table->v[i];
- i == 0 ? i = table->size - 1 : --i) {
- if (keyeq(name, table->v[i]->name))
- return table->v[i];
- }
- if (!createSize)
- return 0;
- if (table->used == table->usedLim) {
- /* check for overflow */
- size_t newSize = table->size * 2;
- NAMED **newV = calloc(newSize, sizeof(NAMED *));
- if (!newV)
- return 0;
- for (i = 0; i < table->size; i++)
- if (table->v[i]) {
- size_t j;
- for (j = hash(table->v[i]->name) & (newSize - 1);
- newV[j];
- j == 0 ? j = newSize - 1 : --j)
- ;
- newV[j] = table->v[i];
- }
- free(table->v);
- table->v = newV;
- table->size = newSize;
- table->usedLim = newSize/2;
- for (i = h & (table->size - 1);
- table->v[i];
- i == 0 ? i = table->size - 1 : --i)
- ;
- }
- }
- table->v[i] = calloc(1, createSize);
- if (!table->v[i])
- return 0;
- table->v[i]->name = name;
- (table->used)++;
- return table->v[i];
-}
-
-void hashTableDestroy(HASH_TABLE *table)
-{
- size_t i;
- for (i = 0; i < table->size; i++) {
- NAMED *p = table->v[i];
- if (p)
- free(p);
- }
- free(table->v);
-}
-
-void hashTableInit(HASH_TABLE *p)
-{
- p->size = 0;
- p->usedLim = 0;
- p->used = 0;
- p->v = 0;
-}
-
-void hashTableIterInit(HASH_TABLE_ITER *iter, const HASH_TABLE *table)
-{
- iter->p = table->v;
- iter->end = iter->p + table->size;
-}
-
-NAMED *hashTableIterNext(HASH_TABLE_ITER *iter)
-{
- while (iter->p != iter->end) {
- NAMED *tem = *(iter->p)++;
- if (tem)
- return tem;
- }
- return 0;
-}
-
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlparse/hashtable.h
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlparse/hashtable.h 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlparse/hashtable.h 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,69 +0,0 @@
-/*
-The contents of this file are subject to the Mozilla Public License
-Version 1.1 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998, 1999
-James Clark. All Rights Reserved.
-
-Contributor(s):
-
-Alternatively, the contents of this file may be used under the terms
-of the GNU General Public License (the "GPL"), in which case the
-provisions of the GPL are applicable instead of those above. If you
-wish to allow use of your version of this file only under the terms of
-the GPL and not to allow others to use your version of this file under
-the MPL, indicate your decision by deleting the provisions above and
-replace them with the notice and other provisions required by the
-GPL. If you do not delete the provisions above, a recipient may use
-your version of this file under either the MPL or the GPL.
-*/
-
-
-#include <stddef.h>
-
-#ifdef XML_UNICODE
-
-#ifdef XML_UNICODE_WCHAR_T
-typedef const wchar_t *KEY;
-#else /* not XML_UNICODE_WCHAR_T */
-typedef const unsigned short *KEY;
-#endif /* not XML_UNICODE_WCHAR_T */
-
-#else /* not XML_UNICODE */
-
-typedef const char *KEY;
-
-#endif /* not XML_UNICODE */
-
-typedef struct {
- KEY name;
-} NAMED;
-
-typedef struct {
- NAMED **v;
- size_t size;
- size_t used;
- size_t usedLim;
-} HASH_TABLE;
-
-NAMED *lookup(HASH_TABLE *table, KEY name, size_t createSize);
-void hashTableInit(HASH_TABLE *);
-void hashTableDestroy(HASH_TABLE *);
-
-typedef struct {
- NAMED **p;
- NAMED **end;
-} HASH_TABLE_ITER;
-
-void hashTableIterInit(HASH_TABLE_ITER *, const HASH_TABLE *);
-NAMED *hashTableIterNext(HASH_TABLE_ITER *);
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlparse/makefile.win
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlparse/makefile.win 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlparse/makefile.win 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,50 +0,0 @@
-#!gmake
-#
-# The contents of this file are subject to the Netscape Public
-# License Version 1.1 (the "License"); you may not use this file
-# except in compliance with the License. You may obtain a copy of
-# the License at http://www.mozilla.org/NPL/
-#
-# Software distributed under the License is distributed on an "AS
-# IS" basis, WITHOUT WARRANTY OF ANY KIND, either express or
-# implied. See the License for the specific language governing
-# rights and limitations under the License.
-#
-# The Original Code is mozilla.org code.
-#
-# The Initial Developer of the Original Code is Netscape
-# Communications Corporation. Portions created by Netscape are
-# Copyright (C) 1998 Netscape Communications Corporation. All
-# Rights Reserved.
-#
-# Contributor(s):
-
-#
-
-DEPTH= ..\..
-MODULE = raptor
-EXPORTS = xmlparse.h
-LIBRARY_NAME=expat
-
-CPPSRCS= \
- xmlparse.c \
- hashtable.c \
- $(NULL)
-
-CPP_OBJS= \
- .\$(OBJDIR)\xmlparse.obj \
- .\$(OBJDIR)\hashtable.obj \
- ..\xmltok\$(OBJDIR)\xmltok.obj \
- ..\xmltok\$(OBJDIR)\xmlrole.obj \
- $(NULL)
-
-LINCS=-I..\xmltok
-
-include <$(DEPTH)\config\rules.mak>
-
-install:: $(OBJDIR) $(OBJS)
-
-install:: $(LIBRARY)
- $(MAKE_INSTALL) $(LIBRARY) $(DIST)\lib
-
-install:: $(LIBRARY)
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlparse/xmlparse.c
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlparse/xmlparse.c 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlparse/xmlparse.c 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,3707 +0,0 @@
-/*
-The contents of this file are subject to the Mozilla Public License
-Version 1.1 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998, 1999
-James Clark. All Rights Reserved.
-
-Contributor(s):
-
-Alternatively, the contents of this file may be used under the terms
-of the GNU General Public License (the "GPL"), in which case the
-provisions of the GPL are applicable instead of those above. If you
-wish to allow use of your version of this file only under the terms of
-the GPL and not to allow others to use your version of this file under
-the MPL, indicate your decision by deleting the provisions above and
-replace them with the notice and other provisions required by the
-GPL. If you do not delete the provisions above, a recipient may use
-your version of this file under either the MPL or the GPL.
-*/
-
-#include "xmldef.h"
-#include "xmlparse.h"
-
-#ifdef XML_UNICODE
-#define XML_ENCODE_MAX XML_UTF16_ENCODE_MAX
-#define XmlConvert XmlUtf16Convert
-#define XmlGetInternalEncoding XmlGetUtf16InternalEncoding
-#define XmlGetInternalEncodingNS XmlGetUtf16InternalEncodingNS
-#define XmlEncode XmlUtf16Encode
-#define MUST_CONVERT(enc, s) (!(enc)->isUtf16 || (((unsigned long)s) & 1))
-typedef unsigned short ICHAR;
-#else
-#define XML_ENCODE_MAX XML_UTF8_ENCODE_MAX
-#define XmlConvert XmlUtf8Convert
-#define XmlGetInternalEncoding XmlGetUtf8InternalEncoding
-#define XmlGetInternalEncodingNS XmlGetUtf8InternalEncodingNS
-#define XmlEncode XmlUtf8Encode
-#define MUST_CONVERT(enc, s) (!(enc)->isUtf8)
-typedef char ICHAR;
-#endif
-
-
-#ifndef XML_NS
-
-#define XmlInitEncodingNS XmlInitEncoding
-#define XmlInitUnknownEncodingNS XmlInitUnknownEncoding
-#undef XmlGetInternalEncodingNS
-#define XmlGetInternalEncodingNS XmlGetInternalEncoding
-#define XmlParseXmlDeclNS XmlParseXmlDecl
-
-#endif
-
-#ifdef XML_UNICODE_WCHAR_T
-#define XML_T(x) L ## x
-#else
-#define XML_T(x) x
-#endif
-
-/* Round up n to be a multiple of sz, where sz is a power of 2. */
-#define ROUND_UP(n, sz) (((n) + ((sz) - 1)) & ~((sz) - 1))
-
-#include "xmltok.h"
-#include "xmlrole.h"
-#include "hashtable.h"
-
-#define INIT_TAG_BUF_SIZE 32 /* must be a multiple of sizeof(XML_Char) */
-#define INIT_DATA_BUF_SIZE 1024
-#define INIT_ATTS_SIZE 16
-#define INIT_BLOCK_SIZE 1024
-#define INIT_BUFFER_SIZE 1024
-
-#define EXPAND_SPARE 24
-
-typedef struct binding {
- struct prefix *prefix;
- struct binding *nextTagBinding;
- struct binding *prevPrefixBinding;
- const struct attribute_id *attId;
- XML_Char *uri;
- int uriLen;
- int uriAlloc;
-} BINDING;
-
-typedef struct prefix {
- const XML_Char *name;
- BINDING *binding;
-} PREFIX;
-
-typedef struct {
- const XML_Char *str;
- const XML_Char *localPart;
- int uriLen;
-} TAG_NAME;
-
-typedef struct tag {
- struct tag *parent;
- const char *rawName;
- int rawNameLength;
- TAG_NAME name;
- char *buf;
- char *bufEnd;
- BINDING *bindings;
-} TAG;
-
-typedef struct {
- const XML_Char *name;
- const XML_Char *textPtr;
- int textLen;
- const XML_Char *systemId;
- const XML_Char *base;
- const XML_Char *publicId;
- const XML_Char *notation;
- char open;
-} ENTITY;
-
-typedef struct block {
- struct block *next;
- int size;
- XML_Char s[1];
-} BLOCK;
-
-typedef struct {
- BLOCK *blocks;
- BLOCK *freeBlocks;
- const XML_Char *end;
- XML_Char *ptr;
- XML_Char *start;
-} STRING_POOL;
-
-/* The XML_Char before the name is used to determine whether
-an attribute has been specified. */
-typedef struct attribute_id {
- XML_Char *name;
- PREFIX *prefix;
- char maybeTokenized;
- char xmlns;
-} ATTRIBUTE_ID;
-
-typedef struct {
- const ATTRIBUTE_ID *id;
- char isCdata;
- const XML_Char *value;
-} DEFAULT_ATTRIBUTE;
-
-typedef struct {
- const XML_Char *name;
- PREFIX *prefix;
- int nDefaultAtts;
- int allocDefaultAtts;
- DEFAULT_ATTRIBUTE *defaultAtts;
-} ELEMENT_TYPE;
-
-typedef struct {
- HASH_TABLE generalEntities;
- HASH_TABLE elementTypes;
- HASH_TABLE attributeIds;
- HASH_TABLE prefixes;
- STRING_POOL pool;
- int complete;
- int standalone;
-#ifdef XML_DTD
- HASH_TABLE paramEntities;
-#endif /* XML_DTD */
- PREFIX defaultPrefix;
-} DTD;
-
-typedef struct open_internal_entity {
- const char *internalEventPtr;
- const char *internalEventEndPtr;
- struct open_internal_entity *next;
- ENTITY *entity;
-} OPEN_INTERNAL_ENTITY;
-
-typedef enum XML_Error Processor(XML_Parser parser,
- const char *start,
- const char *end,
- const char **endPtr);
-
-static Processor prologProcessor;
-static Processor prologInitProcessor;
-static Processor contentProcessor;
-static Processor cdataSectionProcessor;
-#ifdef XML_DTD
-static Processor ignoreSectionProcessor;
-#endif /* XML_DTD */
-static Processor epilogProcessor;
-static Processor errorProcessor;
-static Processor externalEntityInitProcessor;
-static Processor externalEntityInitProcessor2;
-static Processor externalEntityInitProcessor3;
-static Processor externalEntityContentProcessor;
-
-static enum XML_Error
-handleUnknownEncoding(XML_Parser parser, const XML_Char *encodingName);
-static enum XML_Error
-processXmlDecl(XML_Parser parser, int isGeneralTextEntity, const char *, const char *);
-static enum XML_Error
-initializeEncoding(XML_Parser parser);
-static enum XML_Error
-doProlog(XML_Parser parser, const ENCODING *enc, const char *s,
- const char *end, int tok, const char *next, const char **nextPtr);
-static enum XML_Error
-processInternalParamEntity(XML_Parser parser, ENTITY *entity);
-static enum XML_Error
-doContent(XML_Parser parser, int startTagLevel, const ENCODING *enc,
- const char *start, const char *end, const char **endPtr);
-static enum XML_Error
-doCdataSection(XML_Parser parser, const ENCODING *, const char **startPtr, const char *end, const char **nextPtr);
-#ifdef XML_DTD
-static enum XML_Error
-doIgnoreSection(XML_Parser parser, const ENCODING *, const char **startPtr, const char *end, const char **nextPtr);
-#endif /* XML_DTD */
-static enum XML_Error storeAtts(XML_Parser parser, const ENCODING *, const char *s,
- TAG_NAME *tagNamePtr, BINDING **bindingsPtr);
-static
-int addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId, const XML_Char *uri, BINDING **bindingsPtr);
-static int
-defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *, int isCdata, const XML_Char *dfltValue);
-static enum XML_Error
-storeAttributeValue(XML_Parser parser, const ENCODING *, int isCdata, const char *, const char *,
- STRING_POOL *);
-static enum XML_Error
-appendAttributeValue(XML_Parser parser, const ENCODING *, int isCdata, const char *, const char *,
- STRING_POOL *);
-static ATTRIBUTE_ID *
-getAttributeId(XML_Parser parser, const ENCODING *enc, const char *start, const char *end);
-static int setElementTypePrefix(XML_Parser parser, ELEMENT_TYPE *);
-static enum XML_Error
-storeEntityValue(XML_Parser parser, const ENCODING *enc, const char *start, const char *end);
-static int
-reportProcessingInstruction(XML_Parser parser, const ENCODING *enc, const char *start, const char *end);
-static int
-reportComment(XML_Parser parser, const ENCODING *enc, const char *start, const char *end);
-static void
-reportDefault(XML_Parser parser, const ENCODING *enc, const char *start, const char *end);
-
-static const XML_Char *getContext(XML_Parser parser);
-static int setContext(XML_Parser parser, const XML_Char *context);
-static void normalizePublicId(XML_Char *s);
-static int dtdInit(DTD *);
-static void dtdDestroy(DTD *);
-static int dtdCopy(DTD *newDtd, const DTD *oldDtd);
-static int copyEntityTable(HASH_TABLE *, STRING_POOL *, const HASH_TABLE *);
-#ifdef XML_DTD
-static void dtdSwap(DTD *, DTD *);
-#endif /* XML_DTD */
-static void poolInit(STRING_POOL *);
-static void poolClear(STRING_POOL *);
-static void poolDestroy(STRING_POOL *);
-static XML_Char *poolAppend(STRING_POOL *pool, const ENCODING *enc,
- const char *ptr, const char *end);
-static XML_Char *poolStoreString(STRING_POOL *pool, const ENCODING *enc,
- const char *ptr, const char *end);
-static int poolGrow(STRING_POOL *pool);
-static const XML_Char *poolCopyString(STRING_POOL *pool, const XML_Char *s);
-static const XML_Char *poolCopyStringN(STRING_POOL *pool, const XML_Char *s, int n);
-
-#define poolStart(pool) ((pool)->start)
-#define poolEnd(pool) ((pool)->ptr)
-#define poolLength(pool) ((pool)->ptr - (pool)->start)
-#define poolChop(pool) ((void)--(pool->ptr))
-#define poolLastChar(pool) (((pool)->ptr)[-1])
-#define poolDiscard(pool) ((pool)->ptr = (pool)->start)
-#define poolFinish(pool) ((pool)->start = (pool)->ptr)
-#define poolAppendChar(pool, c) \
- (((pool)->ptr == (pool)->end && !poolGrow(pool)) \
- ? 0 \
- : ((*((pool)->ptr)++ = c), 1))
-
-typedef struct {
- /* The first member must be userData so that the XML_GetUserData macro works. */
- void *m_userData;
- void *m_handlerArg;
- char *m_buffer;
- /* first character to be parsed */
- const char *m_bufferPtr;
- /* past last character to be parsed */
- char *m_bufferEnd;
- /* allocated end of buffer */
- const char *m_bufferLim;
- long m_parseEndByteIndex;
- const char *m_parseEndPtr;
- XML_Char *m_dataBuf;
- XML_Char *m_dataBufEnd;
- XML_StartElementHandler m_startElementHandler;
- XML_EndElementHandler m_endElementHandler;
- XML_CharacterDataHandler m_characterDataHandler;
- XML_ProcessingInstructionHandler m_processingInstructionHandler;
- XML_CommentHandler m_commentHandler;
- XML_StartCdataSectionHandler m_startCdataSectionHandler;
- XML_EndCdataSectionHandler m_endCdataSectionHandler;
- XML_DefaultHandler m_defaultHandler;
- XML_StartDoctypeDeclHandler m_startDoctypeDeclHandler;
- XML_EndDoctypeDeclHandler m_endDoctypeDeclHandler;
- XML_UnparsedEntityDeclHandler m_unparsedEntityDeclHandler;
- XML_NotationDeclHandler m_notationDeclHandler;
- XML_StartNamespaceDeclHandler m_startNamespaceDeclHandler;
- XML_EndNamespaceDeclHandler m_endNamespaceDeclHandler;
- XML_NotStandaloneHandler m_notStandaloneHandler;
- XML_ExternalEntityRefHandler m_externalEntityRefHandler;
- void *m_externalEntityRefHandlerArg;
- XML_UnknownEncodingHandler m_unknownEncodingHandler;
- const ENCODING *m_encoding;
- INIT_ENCODING m_initEncoding;
- const ENCODING *m_internalEncoding;
- const XML_Char *m_protocolEncodingName;
- int m_ns;
- void *m_unknownEncodingMem;
- void *m_unknownEncodingData;
- void *m_unknownEncodingHandlerData;
- void (*m_unknownEncodingRelease)(void *);
- PROLOG_STATE m_prologState;
- Processor *m_processor;
- enum XML_Error m_errorCode;
- const char *m_eventPtr;
- const char *m_eventEndPtr;
- const char *m_positionPtr;
- OPEN_INTERNAL_ENTITY *m_openInternalEntities;
- int m_defaultExpandInternalEntities;
- int m_tagLevel;
- ENTITY *m_declEntity;
- const XML_Char *m_declNotationName;
- const XML_Char *m_declNotationPublicId;
- ELEMENT_TYPE *m_declElementType;
- ATTRIBUTE_ID *m_declAttributeId;
- char m_declAttributeIsCdata;
- DTD m_dtd;
- const XML_Char *m_curBase;
- TAG *m_tagStack;
- TAG *m_freeTagList;
- BINDING *m_inheritedBindings;
- BINDING *m_freeBindingList;
- int m_attsSize;
- int m_nSpecifiedAtts;
- ATTRIBUTE *m_atts;
- POSITION m_position;
- STRING_POOL m_tempPool;
- STRING_POOL m_temp2Pool;
- char *m_groupConnector;
- unsigned m_groupSize;
- int m_hadExternalDoctype;
- XML_Char m_namespaceSeparator;
-#ifdef XML_DTD
- enum XML_ParamEntityParsing m_paramEntityParsing;
- XML_Parser m_parentParser;
-#endif
-} Parser;
-
-#define userData (((Parser *)parser)->m_userData)
-#define handlerArg (((Parser *)parser)->m_handlerArg)
-#define startElementHandler (((Parser *)parser)->m_startElementHandler)
-#define endElementHandler (((Parser *)parser)->m_endElementHandler)
-#define characterDataHandler (((Parser *)parser)->m_characterDataHandler)
-#define processingInstructionHandler (((Parser *)parser)->m_processingInstructionHandler)
-#define commentHandler (((Parser *)parser)->m_commentHandler)
-#define startCdataSectionHandler (((Parser *)parser)->m_startCdataSectionHandler)
-#define endCdataSectionHandler (((Parser *)parser)->m_endCdataSectionHandler)
-#define defaultHandler (((Parser *)parser)->m_defaultHandler)
-#define startDoctypeDeclHandler (((Parser *)parser)->m_startDoctypeDeclHandler)
-#define endDoctypeDeclHandler (((Parser *)parser)->m_endDoctypeDeclHandler)
-#define unparsedEntityDeclHandler (((Parser *)parser)->m_unparsedEntityDeclHandler)
-#define notationDeclHandler (((Parser *)parser)->m_notationDeclHandler)
-#define startNamespaceDeclHandler (((Parser *)parser)->m_startNamespaceDeclHandler)
-#define endNamespaceDeclHandler (((Parser *)parser)->m_endNamespaceDeclHandler)
-#define notStandaloneHandler (((Parser *)parser)->m_notStandaloneHandler)
-#define externalEntityRefHandler (((Parser *)parser)->m_externalEntityRefHandler)
-#define externalEntityRefHandlerArg (((Parser *)parser)->m_externalEntityRefHandlerArg)
-#define unknownEncodingHandler (((Parser *)parser)->m_unknownEncodingHandler)
-#define encoding (((Parser *)parser)->m_encoding)
-#define initEncoding (((Parser *)parser)->m_initEncoding)
-#define internalEncoding (((Parser *)parser)->m_internalEncoding)
-#define unknownEncodingMem (((Parser *)parser)->m_unknownEncodingMem)
-#define unknownEncodingData (((Parser *)parser)->m_unknownEncodingData)
-#define unknownEncodingHandlerData \
- (((Parser *)parser)->m_unknownEncodingHandlerData)
-#define unknownEncodingRelease (((Parser *)parser)->m_unknownEncodingRelease)
-#define protocolEncodingName (((Parser *)parser)->m_protocolEncodingName)
-#define ns (((Parser *)parser)->m_ns)
-#define prologState (((Parser *)parser)->m_prologState)
-#define processor (((Parser *)parser)->m_processor)
-#define errorCode (((Parser *)parser)->m_errorCode)
-#define eventPtr (((Parser *)parser)->m_eventPtr)
-#define eventEndPtr (((Parser *)parser)->m_eventEndPtr)
-#define positionPtr (((Parser *)parser)->m_positionPtr)
-#define position (((Parser *)parser)->m_position)
-#define openInternalEntities (((Parser *)parser)->m_openInternalEntities)
-#define defaultExpandInternalEntities (((Parser *)parser)->m_defaultExpandInternalEntities)
-#define tagLevel (((Parser *)parser)->m_tagLevel)
-#define buffer (((Parser *)parser)->m_buffer)
-#define bufferPtr (((Parser *)parser)->m_bufferPtr)
-#define bufferEnd (((Parser *)parser)->m_bufferEnd)
-#define parseEndByteIndex (((Parser *)parser)->m_parseEndByteIndex)
-#define parseEndPtr (((Parser *)parser)->m_parseEndPtr)
-#define bufferLim (((Parser *)parser)->m_bufferLim)
-#define dataBuf (((Parser *)parser)->m_dataBuf)
-#define dataBufEnd (((Parser *)parser)->m_dataBufEnd)
-#define dtd (((Parser *)parser)->m_dtd)
-#define curBase (((Parser *)parser)->m_curBase)
-#define declEntity (((Parser *)parser)->m_declEntity)
-#define declNotationName (((Parser *)parser)->m_declNotationName)
-#define declNotationPublicId (((Parser *)parser)->m_declNotationPublicId)
-#define declElementType (((Parser *)parser)->m_declElementType)
-#define declAttributeId (((Parser *)parser)->m_declAttributeId)
-#define declAttributeIsCdata (((Parser *)parser)->m_declAttributeIsCdata)
-#define freeTagList (((Parser *)parser)->m_freeTagList)
-#define freeBindingList (((Parser *)parser)->m_freeBindingList)
-#define inheritedBindings (((Parser *)parser)->m_inheritedBindings)
-#define tagStack (((Parser *)parser)->m_tagStack)
-#define atts (((Parser *)parser)->m_atts)
-#define attsSize (((Parser *)parser)->m_attsSize)
-#define nSpecifiedAtts (((Parser *)parser)->m_nSpecifiedAtts)
-#define tempPool (((Parser *)parser)->m_tempPool)
-#define temp2Pool (((Parser *)parser)->m_temp2Pool)
-#define groupConnector (((Parser *)parser)->m_groupConnector)
-#define groupSize (((Parser *)parser)->m_groupSize)
-#define hadExternalDoctype (((Parser *)parser)->m_hadExternalDoctype)
-#define namespaceSeparator (((Parser *)parser)->m_namespaceSeparator)
-#ifdef XML_DTD
-#define parentParser (((Parser *)parser)->m_parentParser)
-#define paramEntityParsing (((Parser *)parser)->m_paramEntityParsing)
-#endif /* XML_DTD */
-
-#ifdef _MSC_VER
-#ifdef _DEBUG
-Parser *asParser(XML_Parser parser)
-{
- return parser;
-}
-#endif
-#endif
-
-XML_Parser XML_ParserCreate(const XML_Char *encodingName)
-{
- XML_Parser parser = malloc(sizeof(Parser));
- if (!parser)
- return parser;
- processor = prologInitProcessor;
- XmlPrologStateInit(&prologState);
- userData = 0;
- handlerArg = 0;
- startElementHandler = 0;
- endElementHandler = 0;
- characterDataHandler = 0;
- processingInstructionHandler = 0;
- commentHandler = 0;
- startCdataSectionHandler = 0;
- endCdataSectionHandler = 0;
- defaultHandler = 0;
- startDoctypeDeclHandler = 0;
- endDoctypeDeclHandler = 0;
- unparsedEntityDeclHandler = 0;
- notationDeclHandler = 0;
- startNamespaceDeclHandler = 0;
- endNamespaceDeclHandler = 0;
- notStandaloneHandler = 0;
- externalEntityRefHandler = 0;
- externalEntityRefHandlerArg = parser;
- unknownEncodingHandler = 0;
- buffer = 0;
- bufferPtr = 0;
- bufferEnd = 0;
- parseEndByteIndex = 0;
- parseEndPtr = 0;
- bufferLim = 0;
- declElementType = 0;
- declAttributeId = 0;
- declEntity = 0;
- declNotationName = 0;
- declNotationPublicId = 0;
- memset(&position, 0, sizeof(POSITION));
- errorCode = XML_ERROR_NONE;
- eventPtr = 0;
- eventEndPtr = 0;
- positionPtr = 0;
- openInternalEntities = 0;
- tagLevel = 0;
- tagStack = 0;
- freeTagList = 0;
- freeBindingList = 0;
- inheritedBindings = 0;
- attsSize = INIT_ATTS_SIZE;
- atts = malloc(attsSize * sizeof(ATTRIBUTE));
- nSpecifiedAtts = 0;
- dataBuf = malloc(INIT_DATA_BUF_SIZE * sizeof(XML_Char));
- groupSize = 0;
- groupConnector = 0;
- hadExternalDoctype = 0;
- unknownEncodingMem = 0;
- unknownEncodingRelease = 0;
- unknownEncodingData = 0;
- unknownEncodingHandlerData = 0;
- namespaceSeparator = '!';
-#ifdef XML_DTD
- parentParser = 0;
- paramEntityParsing = XML_PARAM_ENTITY_PARSING_NEVER;
-#endif
- ns = 0;
- poolInit(&tempPool);
- poolInit(&temp2Pool);
- protocolEncodingName = encodingName ? poolCopyString(&tempPool, encodingName) : 0;
- curBase = 0;
- if (!dtdInit(&dtd) || !atts || !dataBuf
- || (encodingName && !protocolEncodingName)) {
- XML_ParserFree(parser);
- return 0;
- }
- dataBufEnd = dataBuf + INIT_DATA_BUF_SIZE;
- XmlInitEncoding(&initEncoding, &encoding, 0);
- internalEncoding = XmlGetInternalEncoding();
- return parser;
-}
-
-XML_Parser XML_ParserCreateNS(const XML_Char *encodingName, XML_Char nsSep)
-{
- static
- const XML_Char implicitContext[] = {
- XML_T('x'), XML_T('m'), XML_T('l'), XML_T('='),
- XML_T('h'), XML_T('t'), XML_T('t'), XML_T('p'), XML_T(':'),
- XML_T('/'), XML_T('/'), XML_T('w'), XML_T('w'), XML_T('w'),
- XML_T('.'), XML_T('w'), XML_T('3'),
- XML_T('.'), XML_T('o'), XML_T('r'), XML_T('g'),
- XML_T('/'), XML_T('X'), XML_T('M'), XML_T('L'),
- XML_T('/'), XML_T('1'), XML_T('9'), XML_T('9'), XML_T('8'),
- XML_T('/'), XML_T('n'), XML_T('a'), XML_T('m'), XML_T('e'),
- XML_T('s'), XML_T('p'), XML_T('a'), XML_T('c'), XML_T('e'),
- XML_T('\0')
- };
-
- XML_Parser parser = XML_ParserCreate(encodingName);
- if (parser) {
- XmlInitEncodingNS(&initEncoding, &encoding, 0);
- ns = 1;
- internalEncoding = XmlGetInternalEncodingNS();
- namespaceSeparator = nsSep;
- }
- if (!setContext(parser, implicitContext)) {
- XML_ParserFree(parser);
- return 0;
- }
- return parser;
-}
-
-int XML_SetEncoding(XML_Parser parser, const XML_Char *encodingName)
-{
- if (!encodingName)
- protocolEncodingName = 0;
- else {
- protocolEncodingName = poolCopyString(&tempPool, encodingName);
- if (!protocolEncodingName)
- return 0;
- }
- return 1;
-}
-
-XML_Parser XML_ExternalEntityParserCreate(XML_Parser oldParser,
- const XML_Char *context,
- const XML_Char *encodingName)
-{
- XML_Parser parser = oldParser;
- DTD *oldDtd = &dtd;
- XML_StartElementHandler oldStartElementHandler = startElementHandler;
- XML_EndElementHandler oldEndElementHandler = endElementHandler;
- XML_CharacterDataHandler oldCharacterDataHandler = characterDataHandler;
- XML_ProcessingInstructionHandler oldProcessingInstructionHandler = processingInstructionHandler;
- XML_CommentHandler oldCommentHandler = commentHandler;
- XML_StartCdataSectionHandler oldStartCdataSectionHandler = startCdataSectionHandler;
- XML_EndCdataSectionHandler oldEndCdataSectionHandler = endCdataSectionHandler;
- XML_DefaultHandler oldDefaultHandler = defaultHandler;
- XML_StartNamespaceDeclHandler oldStartNamespaceDeclHandler = startNamespaceDeclHandler;
- XML_EndNamespaceDeclHandler oldEndNamespaceDeclHandler = endNamespaceDeclHandler;
- XML_NotStandaloneHandler oldNotStandaloneHandler = notStandaloneHandler;
- XML_ExternalEntityRefHandler oldExternalEntityRefHandler = externalEntityRefHandler;
- XML_UnknownEncodingHandler oldUnknownEncodingHandler = unknownEncodingHandler;
- void *oldUserData = userData;
- void *oldHandlerArg = handlerArg;
- int oldDefaultExpandInternalEntities = defaultExpandInternalEntities;
- void *oldExternalEntityRefHandlerArg = externalEntityRefHandlerArg;
-#ifdef XML_DTD
- int oldParamEntityParsing = paramEntityParsing;
-#endif
- parser = (ns
- ? XML_ParserCreateNS(encodingName, namespaceSeparator)
- : XML_ParserCreate(encodingName));
- if (!parser)
- return 0;
- startElementHandler = oldStartElementHandler;
- endElementHandler = oldEndElementHandler;
- characterDataHandler = oldCharacterDataHandler;
- processingInstructionHandler = oldProcessingInstructionHandler;
- commentHandler = oldCommentHandler;
- startCdataSectionHandler = oldStartCdataSectionHandler;
- endCdataSectionHandler = oldEndCdataSectionHandler;
- defaultHandler = oldDefaultHandler;
- startNamespaceDeclHandler = oldStartNamespaceDeclHandler;
- endNamespaceDeclHandler = oldEndNamespaceDeclHandler;
- notStandaloneHandler = oldNotStandaloneHandler;
- externalEntityRefHandler = oldExternalEntityRefHandler;
- unknownEncodingHandler = oldUnknownEncodingHandler;
- userData = oldUserData;
- if (oldUserData == oldHandlerArg)
- handlerArg = userData;
- else
- handlerArg = parser;
- if (oldExternalEntityRefHandlerArg != oldParser)
- externalEntityRefHandlerArg = oldExternalEntityRefHandlerArg;
- defaultExpandInternalEntities = oldDefaultExpandInternalEntities;
-#ifdef XML_DTD
- paramEntityParsing = oldParamEntityParsing;
- if (context) {
-#endif /* XML_DTD */
- if (!dtdCopy(&dtd, oldDtd) || !setContext(parser, context)) {
- XML_ParserFree(parser);
- return 0;
- }
- processor = externalEntityInitProcessor;
-#ifdef XML_DTD
- }
- else {
- dtdSwap(&dtd, oldDtd);
- parentParser = oldParser;
- XmlPrologStateInitExternalEntity(&prologState);
- dtd.complete = 1;
- hadExternalDoctype = 1;
- }
-#endif /* XML_DTD */
- return parser;
-}
-
-static
-void destroyBindings(BINDING *bindings)
-{
- for (;;) {
- BINDING *b = bindings;
- if (!b)
- break;
- bindings = b->nextTagBinding;
- free(b->uri);
- free(b);
- }
-}
-
-void XML_ParserFree(XML_Parser parser)
-{
- for (;;) {
- TAG *p;
- if (tagStack == 0) {
- if (freeTagList == 0)
- break;
- tagStack = freeTagList;
- freeTagList = 0;
- }
- p = tagStack;
- tagStack = tagStack->parent;
- free(p->buf);
- destroyBindings(p->bindings);
- free(p);
- }
- destroyBindings(freeBindingList);
- destroyBindings(inheritedBindings);
- poolDestroy(&tempPool);
- poolDestroy(&temp2Pool);
-#ifdef XML_DTD
- if (parentParser) {
- if (hadExternalDoctype)
- dtd.complete = 0;
- dtdSwap(&dtd, &((Parser *)parentParser)->m_dtd);
- }
-#endif /* XML_DTD */
- dtdDestroy(&dtd);
- free((void *)atts);
- free(groupConnector);
- free(buffer);
- free(dataBuf);
- free(unknownEncodingMem);
- if (unknownEncodingRelease)
- unknownEncodingRelease(unknownEncodingData);
- free(parser);
-}
-
-void XML_UseParserAsHandlerArg(XML_Parser parser)
-{
- handlerArg = parser;
-}
-
-void XML_SetUserData(XML_Parser parser, void *p)
-{
- if (handlerArg == userData)
- handlerArg = userData = p;
- else
- userData = p;
-}
-
-int XML_SetBase(XML_Parser parser, const XML_Char *p)
-{
- if (p) {
- p = poolCopyString(&dtd.pool, p);
- if (!p)
- return 0;
- curBase = p;
- }
- else
- curBase = 0;
- return 1;
-}
-
-const XML_Char *XML_GetBase(XML_Parser parser)
-{
- return curBase;
-}
-
-int XML_GetSpecifiedAttributeCount(XML_Parser parser)
-{
- return nSpecifiedAtts;
-}
-
-void XML_SetElementHandler(XML_Parser parser,
- XML_StartElementHandler start,
- XML_EndElementHandler end)
-{
- startElementHandler = start;
- endElementHandler = end;
-}
-
-void XML_SetCharacterDataHandler(XML_Parser parser,
- XML_CharacterDataHandler handler)
-{
- characterDataHandler = handler;
-}
-
-void XML_SetProcessingInstructionHandler(XML_Parser parser,
- XML_ProcessingInstructionHandler handler)
-{
- processingInstructionHandler = handler;
-}
-
-void XML_SetCommentHandler(XML_Parser parser,
- XML_CommentHandler handler)
-{
- commentHandler = handler;
-}
-
-void XML_SetCdataSectionHandler(XML_Parser parser,
- XML_StartCdataSectionHandler start,
- XML_EndCdataSectionHandler end)
-{
- startCdataSectionHandler = start;
- endCdataSectionHandler = end;
-}
-
-void XML_SetDefaultHandler(XML_Parser parser,
- XML_DefaultHandler handler)
-{
- defaultHandler = handler;
- defaultExpandInternalEntities = 0;
-}
-
-void XML_SetDefaultHandlerExpand(XML_Parser parser,
- XML_DefaultHandler handler)
-{
- defaultHandler = handler;
- defaultExpandInternalEntities = 1;
-}
-
-void XML_SetDoctypeDeclHandler(XML_Parser parser,
- XML_StartDoctypeDeclHandler start,
- XML_EndDoctypeDeclHandler end)
-{
- startDoctypeDeclHandler = start;
- endDoctypeDeclHandler = end;
-}
-
-void XML_SetUnparsedEntityDeclHandler(XML_Parser parser,
- XML_UnparsedEntityDeclHandler handler)
-{
- unparsedEntityDeclHandler = handler;
-}
-
-void XML_SetNotationDeclHandler(XML_Parser parser,
- XML_NotationDeclHandler handler)
-{
- notationDeclHandler = handler;
-}
-
-void XML_SetNamespaceDeclHandler(XML_Parser parser,
- XML_StartNamespaceDeclHandler start,
- XML_EndNamespaceDeclHandler end)
-{
- startNamespaceDeclHandler = start;
- endNamespaceDeclHandler = end;
-}
-
-void XML_SetNotStandaloneHandler(XML_Parser parser,
- XML_NotStandaloneHandler handler)
-{
- notStandaloneHandler = handler;
-}
-
-void XML_SetExternalEntityRefHandler(XML_Parser parser,
- XML_ExternalEntityRefHandler handler)
-{
- externalEntityRefHandler = handler;
-}
-
-void XML_SetExternalEntityRefHandlerArg(XML_Parser parser, void *arg)
-{
- if (arg)
- externalEntityRefHandlerArg = arg;
- else
- externalEntityRefHandlerArg = parser;
-}
-
-void XML_SetUnknownEncodingHandler(XML_Parser parser,
- XML_UnknownEncodingHandler handler,
- void *data)
-{
- unknownEncodingHandler = handler;
- unknownEncodingHandlerData = data;
-}
-
-int XML_SetParamEntityParsing(XML_Parser parser,
- enum XML_ParamEntityParsing parsing)
-{
-#ifdef XML_DTD
- paramEntityParsing = parsing;
- return 1;
-#else
- return parsing == XML_PARAM_ENTITY_PARSING_NEVER;
-#endif
-}
-
-int XML_Parse(XML_Parser parser, const char *s, int len, int isFinal)
-{
- if (len == 0) {
- if (!isFinal)
- return 1;
- positionPtr = bufferPtr;
- errorCode = processor(parser, bufferPtr, parseEndPtr = bufferEnd, 0);
- if (errorCode == XML_ERROR_NONE)
- return 1;
- eventEndPtr = eventPtr;
- processor = errorProcessor;
- return 0;
- }
- else if (bufferPtr == bufferEnd) {
- const char *end;
- int nLeftOver;
- parseEndByteIndex += len;
- positionPtr = s;
- if (isFinal) {
- errorCode = processor(parser, s, parseEndPtr = s + len, 0);
- if (errorCode == XML_ERROR_NONE)
- return 1;
- eventEndPtr = eventPtr;
- processor = errorProcessor;
- return 0;
- }
- errorCode = processor(parser, s, parseEndPtr = s + len, &end);
- if (errorCode != XML_ERROR_NONE) {
- eventEndPtr = eventPtr;
- processor = errorProcessor;
- return 0;
- }
- XmlUpdatePosition(encoding, positionPtr, end, &position);
- nLeftOver = s + len - end;
- if (nLeftOver) {
- if (buffer == 0 || nLeftOver > bufferLim - buffer) {
- /* FIXME avoid integer overflow */
- buffer = buffer == 0 ? malloc(len * 2) : realloc(buffer, len * 2);
- /* FIXME storage leak if realloc fails */
- if (!buffer) {
- errorCode = XML_ERROR_NO_MEMORY;
- eventPtr = eventEndPtr = 0;
- processor = errorProcessor;
- return 0;
- }
- bufferLim = buffer + len * 2;
- }
- memcpy(buffer, end, nLeftOver);
- bufferPtr = buffer;
- bufferEnd = buffer + nLeftOver;
- }
- return 1;
- }
- else {
- memcpy(XML_GetBuffer(parser, len), s, len);
- return XML_ParseBuffer(parser, len, isFinal);
- }
-}
-
-int XML_ParseBuffer(XML_Parser parser, int len, int isFinal)
-{
- const char *start = bufferPtr;
- positionPtr = start;
- bufferEnd += len;
- parseEndByteIndex += len;
- errorCode = processor(parser, start, parseEndPtr = bufferEnd,
- isFinal ? (const char **)0 : &bufferPtr);
- if (errorCode == XML_ERROR_NONE) {
- if (!isFinal)
- XmlUpdatePosition(encoding, positionPtr, bufferPtr, &position);
- return 1;
- }
- else {
- eventEndPtr = eventPtr;
- processor = errorProcessor;
- return 0;
- }
-}
-
-void *XML_GetBuffer(XML_Parser parser, int len)
-{
- if (len > bufferLim - bufferEnd) {
- /* FIXME avoid integer overflow */
- int neededSize = len + (bufferEnd - bufferPtr);
- if (neededSize <= bufferLim - buffer) {
- memmove(buffer, bufferPtr, bufferEnd - bufferPtr);
- bufferEnd = buffer + (bufferEnd - bufferPtr);
- bufferPtr = buffer;
- }
- else {
- char *newBuf;
- int bufferSize = bufferLim - bufferPtr;
- if (bufferSize == 0)
- bufferSize = INIT_BUFFER_SIZE;
- do {
- bufferSize *= 2;
- } while (bufferSize < neededSize);
- newBuf = malloc(bufferSize);
- if (newBuf == 0) {
- errorCode = XML_ERROR_NO_MEMORY;
- return 0;
- }
- bufferLim = newBuf + bufferSize;
- if (bufferPtr) {
- memcpy(newBuf, bufferPtr, bufferEnd - bufferPtr);
- free(buffer);
- }
- bufferEnd = newBuf + (bufferEnd - bufferPtr);
- bufferPtr = buffer = newBuf;
- }
- }
- return bufferEnd;
-}
-
-enum XML_Error XML_GetErrorCode(XML_Parser parser)
-{
- return errorCode;
-}
-
-long XML_GetCurrentByteIndex(XML_Parser parser)
-{
- if (eventPtr)
- return parseEndByteIndex - (parseEndPtr - eventPtr);
- return -1;
-}
-
-int XML_GetCurrentByteCount(XML_Parser parser)
-{
- if (eventEndPtr && eventPtr)
- return eventEndPtr - eventPtr;
- return 0;
-}
-
-int XML_GetCurrentLineNumber(XML_Parser parser)
-{
- if (eventPtr) {
- XmlUpdatePosition(encoding, positionPtr, eventPtr, &position);
- positionPtr = eventPtr;
- }
- return position.lineNumber + 1;
-}
-
-int XML_GetCurrentColumnNumber(XML_Parser parser)
-{
- if (eventPtr) {
- XmlUpdatePosition(encoding, positionPtr, eventPtr, &position);
- positionPtr = eventPtr;
- }
- return position.columnNumber;
-}
-
-void XML_DefaultCurrent(XML_Parser parser)
-{
- if (defaultHandler) {
- if (openInternalEntities)
- reportDefault(parser,
- internalEncoding,
- openInternalEntities->internalEventPtr,
- openInternalEntities->internalEventEndPtr);
- else
- reportDefault(parser, encoding, eventPtr, eventEndPtr);
- }
-}
-
-const XML_LChar *XML_ErrorString(int code)
-{
- static const XML_LChar *message[] = {
- 0,
- XML_T("out of memory"),
- XML_T("syntax error"),
- XML_T("no element found"),
- XML_T("not well-formed"),
- XML_T("unclosed token"),
- XML_T("unclosed token"),
- XML_T("mismatched tag"),
- XML_T("duplicate attribute"),
- XML_T("junk after document element"),
- XML_T("illegal parameter entity reference"),
- XML_T("undefined entity"),
- XML_T("recursive entity reference"),
- XML_T("asynchronous entity"),
- XML_T("reference to invalid character number"),
- XML_T("reference to binary entity"),
- XML_T("reference to external entity in attribute"),
- XML_T("xml processing instruction not at start of external entity"),
- XML_T("unknown encoding"),
- XML_T("encoding specified in XML declaration is incorrect"),
- XML_T("unclosed CDATA section"),
- XML_T("error in processing external entity reference"),
- XML_T("document is not standalone")
- };
- if (code > 0 && code < sizeof(message)/sizeof(message[0]))
- return message[code];
- return 0;
-}
-
-static
-enum XML_Error contentProcessor(XML_Parser parser,
- const char *start,
- const char *end,
- const char **endPtr)
-{
- return doContent(parser, 0, encoding, start, end, endPtr);
-}
-
-static
-enum XML_Error externalEntityInitProcessor(XML_Parser parser,
- const char *start,
- const char *end,
- const char **endPtr)
-{
- enum XML_Error result = initializeEncoding(parser);
- if (result != XML_ERROR_NONE)
- return result;
- processor = externalEntityInitProcessor2;
- return externalEntityInitProcessor2(parser, start, end, endPtr);
-}
-
-static
-enum XML_Error externalEntityInitProcessor2(XML_Parser parser,
- const char *start,
- const char *end,
- const char **endPtr)
-{
- const char *next;
- int tok = XmlContentTok(encoding, start, end, &next);
- switch (tok) {
- case XML_TOK_BOM:
- start = next;
- break;
- case XML_TOK_PARTIAL:
- if (endPtr) {
- *endPtr = start;
- return XML_ERROR_NONE;
- }
- eventPtr = start;
- return XML_ERROR_UNCLOSED_TOKEN;
- case XML_TOK_PARTIAL_CHAR:
- if (endPtr) {
- *endPtr = start;
- return XML_ERROR_NONE;
- }
- eventPtr = start;
- return XML_ERROR_PARTIAL_CHAR;
- }
- processor = externalEntityInitProcessor3;
- return externalEntityInitProcessor3(parser, start, end, endPtr);
-}
-
-static
-enum XML_Error externalEntityInitProcessor3(XML_Parser parser,
- const char *start,
- const char *end,
- const char **endPtr)
-{
- const char *next;
- int tok = XmlContentTok(encoding, start, end, &next);
- switch (tok) {
- case XML_TOK_XML_DECL:
- {
- enum XML_Error result = processXmlDecl(parser, 1, start, next);
- if (result != XML_ERROR_NONE)
- return result;
- start = next;
- }
- break;
- case XML_TOK_PARTIAL:
- if (endPtr) {
- *endPtr = start;
- return XML_ERROR_NONE;
- }
- eventPtr = start;
- return XML_ERROR_UNCLOSED_TOKEN;
- case XML_TOK_PARTIAL_CHAR:
- if (endPtr) {
- *endPtr = start;
- return XML_ERROR_NONE;
- }
- eventPtr = start;
- return XML_ERROR_PARTIAL_CHAR;
- }
- processor = externalEntityContentProcessor;
- tagLevel = 1;
- return doContent(parser, 1, encoding, start, end, endPtr);
-}
-
-static
-enum XML_Error externalEntityContentProcessor(XML_Parser parser,
- const char *start,
- const char *end,
- const char **endPtr)
-{
- return doContent(parser, 1, encoding, start, end, endPtr);
-}
-
-static enum XML_Error
-doContent(XML_Parser parser,
- int startTagLevel,
- const ENCODING *enc,
- const char *s,
- const char *end,
- const char **nextPtr)
-{
- const char **eventPP;
- const char **eventEndPP;
- if (enc == encoding) {
- eventPP = &eventPtr;
- eventEndPP = &eventEndPtr;
- }
- else {
- eventPP = &(openInternalEntities->internalEventPtr);
- eventEndPP = &(openInternalEntities->internalEventEndPtr);
- }
- *eventPP = s;
- for (;;) {
- const char *next = s; /* XmlContentTok doesn't always set the last arg */
- int tok = XmlContentTok(enc, s, end, &next);
- *eventEndPP = next;
- switch (tok) {
- case XML_TOK_TRAILING_CR:
- if (nextPtr) {
- *nextPtr = s;
- return XML_ERROR_NONE;
- }
- *eventEndPP = end;
- if (characterDataHandler) {
- XML_Char c = 0xA;
- characterDataHandler(handlerArg, &c, 1);
- }
- else if (defaultHandler)
- reportDefault(parser, enc, s, end);
- if (startTagLevel == 0)
- return XML_ERROR_NO_ELEMENTS;
- if (tagLevel != startTagLevel)
- return XML_ERROR_ASYNC_ENTITY;
- return XML_ERROR_NONE;
- case XML_TOK_NONE:
- if (nextPtr) {
- *nextPtr = s;
- return XML_ERROR_NONE;
- }
- if (startTagLevel > 0) {
- if (tagLevel != startTagLevel)
- return XML_ERROR_ASYNC_ENTITY;
- return XML_ERROR_NONE;
- }
- return XML_ERROR_NO_ELEMENTS;
- case XML_TOK_INVALID:
- *eventPP = next;
- return XML_ERROR_INVALID_TOKEN;
- case XML_TOK_PARTIAL:
- if (nextPtr) {
- *nextPtr = s;
- return XML_ERROR_NONE;
- }
- return XML_ERROR_UNCLOSED_TOKEN;
- case XML_TOK_PARTIAL_CHAR:
- if (nextPtr) {
- *nextPtr = s;
- return XML_ERROR_NONE;
- }
- return XML_ERROR_PARTIAL_CHAR;
- case XML_TOK_ENTITY_REF:
- {
- const XML_Char *name;
- ENTITY *entity;
- XML_Char ch = XmlPredefinedEntityName(enc,
- s + enc->minBytesPerChar,
- next - enc->minBytesPerChar);
- if (ch) {
- if (characterDataHandler)
- characterDataHandler(handlerArg, &ch, 1);
- else if (defaultHandler)
- reportDefault(parser, enc, s, next);
- break;
- }
- name = poolStoreString(&dtd.pool, enc,
- s + enc->minBytesPerChar,
- next - enc->minBytesPerChar);
- if (!name)
- return XML_ERROR_NO_MEMORY;
- entity = (ENTITY *)lookup(&dtd.generalEntities, name, 0);
- poolDiscard(&dtd.pool);
- if (!entity) {
- if (dtd.complete || dtd.standalone)
- return XML_ERROR_UNDEFINED_ENTITY;
- if (defaultHandler)
- reportDefault(parser, enc, s, next);
- break;
- }
- if (entity->open)
- return XML_ERROR_RECURSIVE_ENTITY_REF;
- if (entity->notation)
- return XML_ERROR_BINARY_ENTITY_REF;
- if (entity) {
- if (entity->textPtr) {
- enum XML_Error result;
- OPEN_INTERNAL_ENTITY openEntity;
- if (defaultHandler && !defaultExpandInternalEntities) {
- reportDefault(parser, enc, s, next);
- break;
- }
- entity->open = 1;
- openEntity.next = openInternalEntities;
- openInternalEntities = &openEntity;
- openEntity.entity = entity;
- openEntity.internalEventPtr = 0;
- openEntity.internalEventEndPtr = 0;
- result = doContent(parser,
- tagLevel,
- internalEncoding,
- (char *)entity->textPtr,
- (char *)(entity->textPtr + entity->textLen),
- 0);
- entity->open = 0;
- openInternalEntities = openEntity.next;
- if (result)
- return result;
- }
- else if (externalEntityRefHandler) {
- const XML_Char *context;
- entity->open = 1;
- context = getContext(parser);
- entity->open = 0;
- if (!context)
- return XML_ERROR_NO_MEMORY;
- if (!externalEntityRefHandler(externalEntityRefHandlerArg,
- context,
- entity->base,
- entity->systemId,
- entity->publicId))
- return XML_ERROR_EXTERNAL_ENTITY_HANDLING;
- poolDiscard(&tempPool);
- }
- else if (defaultHandler)
- reportDefault(parser, enc, s, next);
- }
- break;
- }
- case XML_TOK_START_TAG_WITH_ATTS:
- if (!startElementHandler) {
- enum XML_Error result = storeAtts(parser, enc, s, 0, 0);
- if (result)
- return result;
- }
- /* fall through */
- case XML_TOK_START_TAG_NO_ATTS:
- {
- TAG *tag;
- if (freeTagList) {
- tag = freeTagList;
- freeTagList = freeTagList->parent;
- }
- else {
- tag = malloc(sizeof(TAG));
- if (!tag)
- return XML_ERROR_NO_MEMORY;
- tag->buf = malloc(INIT_TAG_BUF_SIZE);
- if (!tag->buf)
- return XML_ERROR_NO_MEMORY;
- tag->bufEnd = tag->buf + INIT_TAG_BUF_SIZE;
- }
- tag->bindings = 0;
- tag->parent = tagStack;
- tagStack = tag;
- tag->name.localPart = 0;
- tag->rawName = s + enc->minBytesPerChar;
- tag->rawNameLength = XmlNameLength(enc, tag->rawName);
- if (nextPtr) {
- /* Need to guarantee that:
- tag->buf + ROUND_UP(tag->rawNameLength, sizeof(XML_Char)) <= tag->bufEnd - sizeof(XML_Char) */
- if (tag->rawNameLength + (int)(sizeof(XML_Char) - 1) + (int)sizeof(XML_Char) > tag->bufEnd - tag->buf) {
- int bufSize = tag->rawNameLength * 4;
- bufSize = ROUND_UP(bufSize, sizeof(XML_Char));
- tag->buf = realloc(tag->buf, bufSize);
- if (!tag->buf)
- return XML_ERROR_NO_MEMORY;
- tag->bufEnd = tag->buf + bufSize;
- }
- memcpy(tag->buf, tag->rawName, tag->rawNameLength);
- tag->rawName = tag->buf;
- }
- ++tagLevel;
- if (startElementHandler) {
- enum XML_Error result;
- XML_Char *toPtr;
- for (;;) {
- const char *rawNameEnd = tag->rawName + tag->rawNameLength;
- const char *fromPtr = tag->rawName;
- int bufSize;
- if (nextPtr)
- toPtr = (XML_Char *)(tag->buf + ROUND_UP(tag->rawNameLength, sizeof(XML_Char)));
- else
- toPtr = (XML_Char *)tag->buf;
- tag->name.str = toPtr;
- XmlConvert(enc,
- &fromPtr, rawNameEnd,
- (ICHAR **)&toPtr, (ICHAR *)tag->bufEnd - 1);
- if (fromPtr == rawNameEnd)
- break;
- bufSize = (tag->bufEnd - tag->buf) << 1;
- tag->buf = realloc(tag->buf, bufSize);
- if (!tag->buf)
- return XML_ERROR_NO_MEMORY;
- tag->bufEnd = tag->buf + bufSize;
- if (nextPtr)
- tag->rawName = tag->buf;
- }
- *toPtr = XML_T('\0');
- result = storeAtts(parser, enc, s, &(tag->name), &(tag->bindings));
- if (result)
- return result;
- startElementHandler(handlerArg, tag->name.str, (const XML_Char **)atts);
- poolClear(&tempPool);
- }
- else {
- tag->name.str = 0;
- if (defaultHandler)
- reportDefault(parser, enc, s, next);
- }
- break;
- }
- case XML_TOK_EMPTY_ELEMENT_WITH_ATTS:
- if (!startElementHandler) {
- enum XML_Error result = storeAtts(parser, enc, s, 0, 0);
- if (result)
- return result;
- }
- /* fall through */
- case XML_TOK_EMPTY_ELEMENT_NO_ATTS:
- if (startElementHandler || endElementHandler) {
- const char *rawName = s + enc->minBytesPerChar;
- enum XML_Error result;
- BINDING *bindings = 0;
- TAG_NAME name;
- name.str = poolStoreString(&tempPool, enc, rawName,
- rawName + XmlNameLength(enc, rawName));
- if (!name.str)
- return XML_ERROR_NO_MEMORY;
- poolFinish(&tempPool);
- result = storeAtts(parser, enc, s, &name, &bindings);
- if (result)
- return result;
- poolFinish(&tempPool);
- if (startElementHandler)
- startElementHandler(handlerArg, name.str, (const XML_Char **)atts);
- if (endElementHandler) {
- if (startElementHandler)
- *eventPP = *eventEndPP;
- endElementHandler(handlerArg, name.str);
- }
- poolClear(&tempPool);
- while (bindings) {
- BINDING *b = bindings;
- if (endNamespaceDeclHandler)
- endNamespaceDeclHandler(handlerArg, b->prefix->name);
- bindings = bindings->nextTagBinding;
- b->nextTagBinding = freeBindingList;
- freeBindingList = b;
- b->prefix->binding = b->prevPrefixBinding;
- }
- }
- else if (defaultHandler)
- reportDefault(parser, enc, s, next);
- if (tagLevel == 0)
- return epilogProcessor(parser, next, end, nextPtr);
- break;
- case XML_TOK_END_TAG:
- if (tagLevel == startTagLevel)
- return XML_ERROR_ASYNC_ENTITY;
- else {
- int len;
- const char *rawName;
- TAG *tag = tagStack;
- tagStack = tag->parent;
- tag->parent = freeTagList;
- freeTagList = tag;
- rawName = s + enc->minBytesPerChar*2;
- len = XmlNameLength(enc, rawName);
- if (len != tag->rawNameLength
- || memcmp(tag->rawName, rawName, len) != 0) {
- *eventPP = rawName;
- return XML_ERROR_TAG_MISMATCH;
- }
- --tagLevel;
- if (endElementHandler && tag->name.str) {
- if (tag->name.localPart) {
- XML_Char *to = (XML_Char *)tag->name.str + tag->name.uriLen;
- const XML_Char *from = tag->name.localPart;
- while ((*to++ = *from++) != 0)
- ;
- }
- endElementHandler(handlerArg, tag->name.str);
- }
- else if (defaultHandler)
- reportDefault(parser, enc, s, next);
- while (tag->bindings) {
- BINDING *b = tag->bindings;
- if (endNamespaceDeclHandler)
- endNamespaceDeclHandler(handlerArg, b->prefix->name);
- tag->bindings = tag->bindings->nextTagBinding;
- b->nextTagBinding = freeBindingList;
- freeBindingList = b;
- b->prefix->binding = b->prevPrefixBinding;
- }
- if (tagLevel == 0)
- return epilogProcessor(parser, next, end, nextPtr);
- }
- break;
- case XML_TOK_CHAR_REF:
- {
- int n = XmlCharRefNumber(enc, s);
- if (n < 0)
- return XML_ERROR_BAD_CHAR_REF;
- if (characterDataHandler) {
- XML_Char buf[XML_ENCODE_MAX];
- characterDataHandler(handlerArg, buf, XmlEncode(n, (ICHAR *)buf));
- }
- else if (defaultHandler)
- reportDefault(parser, enc, s, next);
- }
- break;
- case XML_TOK_XML_DECL:
- return XML_ERROR_MISPLACED_XML_PI;
- case XML_TOK_DATA_NEWLINE:
- if (characterDataHandler) {
- XML_Char c = 0xA;
- characterDataHandler(handlerArg, &c, 1);
- }
- else if (defaultHandler)
- reportDefault(parser, enc, s, next);
- break;
- case XML_TOK_CDATA_SECT_OPEN:
- {
- enum XML_Error result;
- if (startCdataSectionHandler)
- startCdataSectionHandler(handlerArg);
-#if 0
- /* Suppose you doing a transformation on a document that involves
- changing only the character data. You set up a defaultHandler
- and a characterDataHandler. The defaultHandler simply copies
- characters through. The characterDataHandler does the transformation
- and writes the characters out escaping them as necessary. This case
- will fail to work if we leave out the following two lines (because &
- and < inside CDATA sections will be incorrectly escaped).
-
- However, now we have a start/endCdataSectionHandler, so it seems
- easier to let the user deal with this. */
-
- else if (characterDataHandler)
- characterDataHandler(handlerArg, dataBuf, 0);
-#endif
- else if (defaultHandler)
- reportDefault(parser, enc, s, next);
- result = doCdataSection(parser, enc, &next, end, nextPtr);
- if (!next) {
- processor = cdataSectionProcessor;
- return result;
- }
- }
- break;
- case XML_TOK_TRAILING_RSQB:
- if (nextPtr) {
- *nextPtr = s;
- return XML_ERROR_NONE;
- }
- if (characterDataHandler) {
- if (MUST_CONVERT(enc, s)) {
- ICHAR *dataPtr = (ICHAR *)dataBuf;
- XmlConvert(enc, &s, end, &dataPtr, (ICHAR *)dataBufEnd);
- characterDataHandler(handlerArg, dataBuf, dataPtr - (ICHAR *)dataBuf);
- }
- else
- characterDataHandler(handlerArg,
- (XML_Char *)s,
- (XML_Char *)end - (XML_Char *)s);
- }
- else if (defaultHandler)
- reportDefault(parser, enc, s, end);
- if (startTagLevel == 0) {
- *eventPP = end;
- return XML_ERROR_NO_ELEMENTS;
- }
- if (tagLevel != startTagLevel) {
- *eventPP = end;
- return XML_ERROR_ASYNC_ENTITY;
- }
- return XML_ERROR_NONE;
- case XML_TOK_DATA_CHARS:
- if (characterDataHandler) {
- if (MUST_CONVERT(enc, s)) {
- for (;;) {
- ICHAR *dataPtr = (ICHAR *)dataBuf;
- XmlConvert(enc, &s, next, &dataPtr, (ICHAR *)dataBufEnd);
- *eventEndPP = s;
- characterDataHandler(handlerArg, dataBuf, dataPtr - (ICHAR *)dataBuf);
- if (s == next)
- break;
- *eventPP = s;
- }
- }
- else
- characterDataHandler(handlerArg,
- (XML_Char *)s,
- (XML_Char *)next - (XML_Char *)s);
- }
- else if (defaultHandler)
- reportDefault(parser, enc, s, next);
- break;
- case XML_TOK_PI:
- if (!reportProcessingInstruction(parser, enc, s, next))
- return XML_ERROR_NO_MEMORY;
- break;
- case XML_TOK_COMMENT:
- if (!reportComment(parser, enc, s, next))
- return XML_ERROR_NO_MEMORY;
- break;
- default:
- if (defaultHandler)
- reportDefault(parser, enc, s, next);
- break;
- }
- *eventPP = s = next;
- }
- /* not reached */
-}
-
-/* If tagNamePtr is non-null, build a real list of attributes,
-otherwise just check the attributes for well-formedness. */
-
-static enum XML_Error storeAtts(XML_Parser parser, const ENCODING *enc,
- const char *attStr, TAG_NAME *tagNamePtr,
- BINDING **bindingsPtr)
-{
- ELEMENT_TYPE *elementType = 0;
- int nDefaultAtts = 0;
- const XML_Char **appAtts;
- int attIndex = 0;
- int i;
- int n;
- int nPrefixes = 0;
- BINDING *binding;
- const XML_Char *localPart;
-
- if (tagNamePtr) {
- elementType = (ELEMENT_TYPE *)lookup(&dtd.elementTypes, tagNamePtr->str, 0);
- if (!elementType) {
- tagNamePtr->str = poolCopyString(&dtd.pool, tagNamePtr->str);
- if (!tagNamePtr->str)
- return XML_ERROR_NO_MEMORY;
- elementType = (ELEMENT_TYPE *)lookup(&dtd.elementTypes, tagNamePtr->str, sizeof(ELEMENT_TYPE));
- if (!elementType)
- return XML_ERROR_NO_MEMORY;
- if (ns && !setElementTypePrefix(parser, elementType))
- return XML_ERROR_NO_MEMORY;
- }
- nDefaultAtts = elementType->nDefaultAtts;
- }
- n = XmlGetAttributes(enc, attStr, attsSize, atts);
- if (n + nDefaultAtts > attsSize) {
- int oldAttsSize = attsSize;
- attsSize = n + nDefaultAtts + INIT_ATTS_SIZE;
- atts = realloc((void *)atts, attsSize * sizeof(ATTRIBUTE));
- if (!atts)
- return XML_ERROR_NO_MEMORY;
- if (n > oldAttsSize)
- XmlGetAttributes(enc, attStr, n, atts);
- }
- appAtts = (const XML_Char **)atts;
- for (i = 0; i < n; i++) {
- ATTRIBUTE_ID *attId = getAttributeId(parser, enc, atts[i].name,
- atts[i].name
- + XmlNameLength(enc, atts[i].name));
- if (!attId)
- return XML_ERROR_NO_MEMORY;
- if ((attId->name)[-1]) {
- if (enc == encoding)
- eventPtr = atts[i].name;
- return XML_ERROR_DUPLICATE_ATTRIBUTE;
- }
- (attId->name)[-1] = 1;
- appAtts[attIndex++] = attId->name;
- if (!atts[i].normalized) {
- enum XML_Error result;
- int isCdata = 1;
-
- if (attId->maybeTokenized) {
- int j;
- for (j = 0; j < nDefaultAtts; j++) {
- if (attId == elementType->defaultAtts[j].id) {
- isCdata = elementType->defaultAtts[j].isCdata;
- break;
- }
- }
- }
-
- result = storeAttributeValue(parser, enc, isCdata,
- atts[i].valuePtr, atts[i].valueEnd,
- &tempPool);
- if (result)
- return result;
- if (tagNamePtr) {
- appAtts[attIndex] = poolStart(&tempPool);
- poolFinish(&tempPool);
- }
- else
- poolDiscard(&tempPool);
- }
- else if (tagNamePtr) {
- appAtts[attIndex] = poolStoreString(&tempPool, enc, atts[i].valuePtr, atts[i].valueEnd);
- if (appAtts[attIndex] == 0)
- return XML_ERROR_NO_MEMORY;
- poolFinish(&tempPool);
- }
- if (attId->prefix && tagNamePtr) {
- if (attId->xmlns) {
- if (!addBinding(parser, attId->prefix, attId, appAtts[attIndex], bindingsPtr))
- return XML_ERROR_NO_MEMORY;
- --attIndex;
- }
- else {
- attIndex++;
- nPrefixes++;
- (attId->name)[-1] = 2;
- }
- }
- else
- attIndex++;
- }
- nSpecifiedAtts = attIndex;
- if (tagNamePtr) {
- int j;
- for (j = 0; j < nDefaultAtts; j++) {
- const DEFAULT_ATTRIBUTE *da = elementType->defaultAtts + j;
- if (!(da->id->name)[-1] && da->value) {
- if (da->id->prefix) {
- if (da->id->xmlns) {
- if (!addBinding(parser, da->id->prefix, da->id, da->value, bindingsPtr))
- return XML_ERROR_NO_MEMORY;
- }
- else {
- (da->id->name)[-1] = 2;
- nPrefixes++;
- appAtts[attIndex++] = da->id->name;
- appAtts[attIndex++] = da->value;
- }
- }
- else {
- (da->id->name)[-1] = 1;
- appAtts[attIndex++] = da->id->name;
- appAtts[attIndex++] = da->value;
- }
- }
- }
- appAtts[attIndex] = 0;
- }
- i = 0;
- if (nPrefixes) {
- for (; i < attIndex; i += 2) {
- if (appAtts[i][-1] == 2) {
- ATTRIBUTE_ID *id;
- ((XML_Char *)(appAtts[i]))[-1] = 0;
- id = (ATTRIBUTE_ID *)lookup(&dtd.attributeIds, appAtts[i], 0);
- if (id->prefix->binding) {
- int j;
- const BINDING *b = id->prefix->binding;
- const XML_Char *s = appAtts[i];
- for (j = 0; j < b->uriLen; j++) {
- if (!poolAppendChar(&tempPool, b->uri[j]))
- return XML_ERROR_NO_MEMORY;
- }
- while (*s++ != ':')
- ;
- do {
- if (!poolAppendChar(&tempPool, *s))
- return XML_ERROR_NO_MEMORY;
- } while (*s++);
- appAtts[i] = poolStart(&tempPool);
- poolFinish(&tempPool);
- }
- if (!--nPrefixes)
- break;
- }
- else
- ((XML_Char *)(appAtts[i]))[-1] = 0;
- }
- }
- for (; i < attIndex; i += 2)
- ((XML_Char *)(appAtts[i]))[-1] = 0;
- if (!tagNamePtr)
- return XML_ERROR_NONE;
- for (binding = *bindingsPtr; binding; binding = binding->nextTagBinding)
- binding->attId->name[-1] = 0;
- if (elementType->prefix) {
- binding = elementType->prefix->binding;
- if (!binding)
- return XML_ERROR_NONE;
- localPart = tagNamePtr->str;
- while (*localPart++ != XML_T(':'))
- ;
- }
- else if (dtd.defaultPrefix.binding) {
- binding = dtd.defaultPrefix.binding;
- localPart = tagNamePtr->str;
- }
- else
- return XML_ERROR_NONE;
- tagNamePtr->localPart = localPart;
- tagNamePtr->uriLen = binding->uriLen;
- i = binding->uriLen;
- do {
- if (i == binding->uriAlloc) {
- binding->uri = realloc(binding->uri, binding->uriAlloc *= 2);
- if (!binding->uri)
- return XML_ERROR_NO_MEMORY;
- }
- binding->uri[i++] = *localPart;
- } while (*localPart++);
- tagNamePtr->str = binding->uri;
- return XML_ERROR_NONE;
-}
-
-static
-int addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId, const XML_Char *uri, BINDING **bindingsPtr)
-{
- BINDING *b;
- int len;
- for (len = 0; uri[len]; len++)
- ;
- if (namespaceSeparator)
- len++;
- if (freeBindingList) {
- b = freeBindingList;
- if (len > b->uriAlloc) {
- b->uri = realloc(b->uri, len + EXPAND_SPARE);
- if (!b->uri)
- return 0;
- b->uriAlloc = len + EXPAND_SPARE;
- }
- freeBindingList = b->nextTagBinding;
- }
- else {
- b = malloc(sizeof(BINDING));
- if (!b)
- return 0;
- b->uri = malloc(sizeof(XML_Char) * len + EXPAND_SPARE);
- if (!b->uri) {
- free(b);
- return 0;
- }
- b->uriAlloc = len;
- }
- b->uriLen = len;
- memcpy(b->uri, uri, len * sizeof(XML_Char));
- if (namespaceSeparator)
- b->uri[len - 1] = namespaceSeparator;
- b->prefix = prefix;
- b->attId = attId;
- b->prevPrefixBinding = prefix->binding;
- if (*uri == XML_T('\0') && prefix == &dtd.defaultPrefix)
- prefix->binding = 0;
- else
- prefix->binding = b;
- b->nextTagBinding = *bindingsPtr;
- *bindingsPtr = b;
- if (startNamespaceDeclHandler)
- startNamespaceDeclHandler(handlerArg, prefix->name,
- prefix->binding ? uri : 0);
- return 1;
-}
-
-/* The idea here is to avoid using stack for each CDATA section when
-the whole file is parsed with one call. */
-
-static
-enum XML_Error cdataSectionProcessor(XML_Parser parser,
- const char *start,
- const char *end,
- const char **endPtr)
-{
- enum XML_Error result = doCdataSection(parser, encoding, &start, end, endPtr);
- if (start) {
- processor = contentProcessor;
- return contentProcessor(parser, start, end, endPtr);
- }
- return result;
-}
-
-/* startPtr gets set to non-null is the section is closed, and to null if
-the section is not yet closed. */
-
-static
-enum XML_Error doCdataSection(XML_Parser parser,
- const ENCODING *enc,
- const char **startPtr,
- const char *end,
- const char **nextPtr)
-{
- const char *s = *startPtr;
- const char **eventPP;
- const char **eventEndPP;
- if (enc == encoding) {
- eventPP = &eventPtr;
- *eventPP = s;
- eventEndPP = &eventEndPtr;
- }
- else {
- eventPP = &(openInternalEntities->internalEventPtr);
- eventEndPP = &(openInternalEntities->internalEventEndPtr);
- }
- *eventPP = s;
- *startPtr = 0;
- for (;;) {
- const char *next;
- int tok = XmlCdataSectionTok(enc, s, end, &next);
- *eventEndPP = next;
- switch (tok) {
- case XML_TOK_CDATA_SECT_CLOSE:
- if (endCdataSectionHandler)
- endCdataSectionHandler(handlerArg);
-#if 0
- /* see comment under XML_TOK_CDATA_SECT_OPEN */
- else if (characterDataHandler)
- characterDataHandler(handlerArg, dataBuf, 0);
-#endif
- else if (defaultHandler)
- reportDefault(parser, enc, s, next);
- *startPtr = next;
- return XML_ERROR_NONE;
- case XML_TOK_DATA_NEWLINE:
- if (characterDataHandler) {
- XML_Char c = 0xA;
- characterDataHandler(handlerArg, &c, 1);
- }
- else if (defaultHandler)
- reportDefault(parser, enc, s, next);
- break;
- case XML_TOK_DATA_CHARS:
- if (characterDataHandler) {
- if (MUST_CONVERT(enc, s)) {
- for (;;) {
- ICHAR *dataPtr = (ICHAR *)dataBuf;
- XmlConvert(enc, &s, next, &dataPtr, (ICHAR *)dataBufEnd);
- *eventEndPP = next;
- characterDataHandler(handlerArg, dataBuf, dataPtr - (ICHAR *)dataBuf);
- if (s == next)
- break;
- *eventPP = s;
- }
- }
- else
- characterDataHandler(handlerArg,
- (XML_Char *)s,
- (XML_Char *)next - (XML_Char *)s);
- }
- else if (defaultHandler)
- reportDefault(parser, enc, s, next);
- break;
- case XML_TOK_INVALID:
- *eventPP = next;
- return XML_ERROR_INVALID_TOKEN;
- case XML_TOK_PARTIAL_CHAR:
- if (nextPtr) {
- *nextPtr = s;
- return XML_ERROR_NONE;
- }
- return XML_ERROR_PARTIAL_CHAR;
- case XML_TOK_PARTIAL:
- case XML_TOK_NONE:
- if (nextPtr) {
- *nextPtr = s;
- return XML_ERROR_NONE;
- }
- return XML_ERROR_UNCLOSED_CDATA_SECTION;
- default:
- abort();
- }
- *eventPP = s = next;
- }
- /* not reached */
-}
-
-#ifdef XML_DTD
-
-/* The idea here is to avoid using stack for each IGNORE section when
-the whole file is parsed with one call. */
-
-static
-enum XML_Error ignoreSectionProcessor(XML_Parser parser,
- const char *start,
- const char *end,
- const char **endPtr)
-{
- enum XML_Error result = doIgnoreSection(parser, encoding, &start, end, endPtr);
- if (start) {
- processor = prologProcessor;
- return prologProcessor(parser, start, end, endPtr);
- }
- return result;
-}
-
-/* startPtr gets set to non-null is the section is closed, and to null if
-the section is not yet closed. */
-
-static
-enum XML_Error doIgnoreSection(XML_Parser parser,
- const ENCODING *enc,
- const char **startPtr,
- const char *end,
- const char **nextPtr)
-{
- const char *next;
- int tok;
- const char *s = *startPtr;
- const char **eventPP;
- const char **eventEndPP;
- if (enc == encoding) {
- eventPP = &eventPtr;
- *eventPP = s;
- eventEndPP = &eventEndPtr;
- }
- else {
- eventPP = &(openInternalEntities->internalEventPtr);
- eventEndPP = &(openInternalEntities->internalEventEndPtr);
- }
- *eventPP = s;
- *startPtr = 0;
- tok = XmlIgnoreSectionTok(enc, s, end, &next);
- *eventEndPP = next;
- switch (tok) {
- case XML_TOK_IGNORE_SECT:
- if (defaultHandler)
- reportDefault(parser, enc, s, next);
- *startPtr = next;
- return XML_ERROR_NONE;
- case XML_TOK_INVALID:
- *eventPP = next;
- return XML_ERROR_INVALID_TOKEN;
- case XML_TOK_PARTIAL_CHAR:
- if (nextPtr) {
- *nextPtr = s;
- return XML_ERROR_NONE;
- }
- return XML_ERROR_PARTIAL_CHAR;
- case XML_TOK_PARTIAL:
- case XML_TOK_NONE:
- if (nextPtr) {
- *nextPtr = s;
- return XML_ERROR_NONE;
- }
- return XML_ERROR_SYNTAX; /* XML_ERROR_UNCLOSED_IGNORE_SECTION */
- default:
- abort();
- }
- /* not reached */
-}
-
-#endif /* XML_DTD */
-
-static enum XML_Error
-initializeEncoding(XML_Parser parser)
-{
- const char *s;
-#ifdef XML_UNICODE
- char encodingBuf[128];
- if (!protocolEncodingName)
- s = 0;
- else {
- int i;
- for (i = 0; protocolEncodingName[i]; i++) {
- if (i == sizeof(encodingBuf) - 1
- || (protocolEncodingName[i] & ~0x7f) != 0) {
- encodingBuf[0] = '\0';
- break;
- }
- encodingBuf[i] = (char)protocolEncodingName[i];
- }
- encodingBuf[i] = '\0';
- s = encodingBuf;
- }
-#else
- s = protocolEncodingName;
-#endif
- if ((ns ? XmlInitEncodingNS : XmlInitEncoding)(&initEncoding, &encoding, s))
- return XML_ERROR_NONE;
- return handleUnknownEncoding(parser, protocolEncodingName);
-}
-
-static enum XML_Error
-processXmlDecl(XML_Parser parser, int isGeneralTextEntity,
- const char *s, const char *next)
-{
- const char *encodingName = 0;
- const ENCODING *newEncoding = 0;
- const char *version;
- int standalone = -1;
- if (!(ns
- ? XmlParseXmlDeclNS
- : XmlParseXmlDecl)(isGeneralTextEntity,
- encoding,
- s,
- next,
- &eventPtr,
- &version,
- &encodingName,
- &newEncoding,
- &standalone))
- return XML_ERROR_SYNTAX;
- if (!isGeneralTextEntity && standalone == 1) {
- dtd.standalone = 1;
-#ifdef XML_DTD
- if (paramEntityParsing == XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE)
- paramEntityParsing = XML_PARAM_ENTITY_PARSING_NEVER;
-#endif /* XML_DTD */
- }
- if (defaultHandler)
- reportDefault(parser, encoding, s, next);
- if (!protocolEncodingName) {
- if (newEncoding) {
- if (newEncoding->minBytesPerChar != encoding->minBytesPerChar) {
- eventPtr = encodingName;
- return XML_ERROR_INCORRECT_ENCODING;
- }
- encoding = newEncoding;
- }
- else if (encodingName) {
- enum XML_Error result;
- const XML_Char *str = poolStoreString(&tempPool,
- encoding,
- encodingName,
- encodingName
- + XmlNameLength(encoding, encodingName));
- if (!str)
- return XML_ERROR_NO_MEMORY;
- result = handleUnknownEncoding(parser, str);
- poolDiscard(&tempPool);
- if (result == XML_ERROR_UNKNOWN_ENCODING)
- eventPtr = encodingName;
- return result;
- }
- }
- return XML_ERROR_NONE;
-}
-
-static enum XML_Error
-handleUnknownEncoding(XML_Parser parser, const XML_Char *encodingName)
-{
- if (unknownEncodingHandler) {
- XML_Encoding info;
- int i;
- for (i = 0; i < 256; i++)
- info.map[i] = -1;
- info.convert = 0;
- info.data = 0;
- info.release = 0;
- if (unknownEncodingHandler(unknownEncodingHandlerData, encodingName, &info)) {
- ENCODING *enc;
- unknownEncodingMem = malloc(XmlSizeOfUnknownEncoding());
- if (!unknownEncodingMem) {
- if (info.release)
- info.release(info.data);
- return XML_ERROR_NO_MEMORY;
- }
- enc = (ns
- ? XmlInitUnknownEncodingNS
- : XmlInitUnknownEncoding)(unknownEncodingMem,
- info.map,
- info.convert,
- info.data);
- if (enc) {
- unknownEncodingData = info.data;
- unknownEncodingRelease = info.release;
- encoding = enc;
- return XML_ERROR_NONE;
- }
- }
- if (info.release)
- info.release(info.data);
- }
- return XML_ERROR_UNKNOWN_ENCODING;
-}
-
-static enum XML_Error
-prologInitProcessor(XML_Parser parser,
- const char *s,
- const char *end,
- const char **nextPtr)
-{
- enum XML_Error result = initializeEncoding(parser);
- if (result != XML_ERROR_NONE)
- return result;
- processor = prologProcessor;
- return prologProcessor(parser, s, end, nextPtr);
-}
-
-static enum XML_Error
-prologProcessor(XML_Parser parser,
- const char *s,
- const char *end,
- const char **nextPtr)
-{
- const char *next;
- int tok = XmlPrologTok(encoding, s, end, &next);
- return doProlog(parser, encoding, s, end, tok, next, nextPtr);
-}
-
-static enum XML_Error
-doProlog(XML_Parser parser,
- const ENCODING *enc,
- const char *s,
- const char *end,
- int tok,
- const char *next,
- const char **nextPtr)
-{
-#ifdef XML_DTD
- static const XML_Char externalSubsetName[] = { '#' , '\0' };
-#endif /* XML_DTD */
-
- const char **eventPP;
- const char **eventEndPP;
- if (enc == encoding) {
- eventPP = &eventPtr;
- eventEndPP = &eventEndPtr;
- }
- else {
- eventPP = &(openInternalEntities->internalEventPtr);
- eventEndPP = &(openInternalEntities->internalEventEndPtr);
- }
- for (;;) {
- int role;
- *eventPP = s;
- *eventEndPP = next;
- if (tok <= 0) {
- if (nextPtr != 0 && tok != XML_TOK_INVALID) {
- *nextPtr = s;
- return XML_ERROR_NONE;
- }
- switch (tok) {
- case XML_TOK_INVALID:
- *eventPP = next;
- return XML_ERROR_INVALID_TOKEN;
- case XML_TOK_PARTIAL:
- return XML_ERROR_UNCLOSED_TOKEN;
- case XML_TOK_PARTIAL_CHAR:
- return XML_ERROR_PARTIAL_CHAR;
- case XML_TOK_NONE:
-#ifdef XML_DTD
- if (enc != encoding)
- return XML_ERROR_NONE;
- if (parentParser) {
- if (XmlTokenRole(&prologState, XML_TOK_NONE, end, end, enc)
- == XML_ROLE_ERROR)
- return XML_ERROR_SYNTAX;
- hadExternalDoctype = 0;
- return XML_ERROR_NONE;
- }
-#endif /* XML_DTD */
- return XML_ERROR_NO_ELEMENTS;
- default:
- tok = -tok;
- next = end;
- break;
- }
- }
- role = XmlTokenRole(&prologState, tok, s, next, enc);
- switch (role) {
- case XML_ROLE_XML_DECL:
- {
- enum XML_Error result = processXmlDecl(parser, 0, s, next);
- if (result != XML_ERROR_NONE)
- return result;
- enc = encoding;
- }
- break;
- case XML_ROLE_DOCTYPE_NAME:
- if (startDoctypeDeclHandler) {
- const XML_Char *name = poolStoreString(&tempPool, enc, s, next);
- if (!name)
- return XML_ERROR_NO_MEMORY;
- startDoctypeDeclHandler(handlerArg, name);
- poolClear(&tempPool);
- }
- break;
-#ifdef XML_DTD
- case XML_ROLE_TEXT_DECL:
- {
- enum XML_Error result = processXmlDecl(parser, 1, s, next);
- if (result != XML_ERROR_NONE)
- return result;
- enc = encoding;
- }
- break;
-#endif /* XML_DTD */
- case XML_ROLE_DOCTYPE_PUBLIC_ID:
-#ifdef XML_DTD
- declEntity = (ENTITY *)lookup(&dtd.paramEntities,
- externalSubsetName,
- sizeof(ENTITY));
- if (!declEntity)
- return XML_ERROR_NO_MEMORY;
-#endif /* XML_DTD */
- /* fall through */
- case XML_ROLE_ENTITY_PUBLIC_ID:
- if (!XmlIsPublicId(enc, s, next, eventPP))
- return XML_ERROR_SYNTAX;
- if (declEntity) {
- XML_Char *tem = poolStoreString(&dtd.pool,
- enc,
- s + enc->minBytesPerChar,
- next - enc->minBytesPerChar);
- if (!tem)
- return XML_ERROR_NO_MEMORY;
- normalizePublicId(tem);
- declEntity->publicId = tem;
- poolFinish(&dtd.pool);
- }
- break;
- case XML_ROLE_DOCTYPE_CLOSE:
- if (dtd.complete && hadExternalDoctype) {
- dtd.complete = 0;
-#ifdef XML_DTD
- if (paramEntityParsing && externalEntityRefHandler) {
- ENTITY *entity = (ENTITY *)lookup(&dtd.paramEntities,
- externalSubsetName,
- 0);
- if (!externalEntityRefHandler(externalEntityRefHandlerArg,
- 0,
- entity->base,
- entity->systemId,
- entity->publicId))
- return XML_ERROR_EXTERNAL_ENTITY_HANDLING;
- }
-#endif /* XML_DTD */
- if (!dtd.complete
- && !dtd.standalone
- && notStandaloneHandler
- && !notStandaloneHandler(handlerArg))
- return XML_ERROR_NOT_STANDALONE;
- }
- if (endDoctypeDeclHandler)
- endDoctypeDeclHandler(handlerArg);
- break;
- case XML_ROLE_INSTANCE_START:
- processor = contentProcessor;
- return contentProcessor(parser, s, end, nextPtr);
- case XML_ROLE_ATTLIST_ELEMENT_NAME:
- {
- const XML_Char *name = poolStoreString(&dtd.pool, enc, s, next);
- if (!name)
- return XML_ERROR_NO_MEMORY;
- declElementType = (ELEMENT_TYPE *)lookup(&dtd.elementTypes, name, sizeof(ELEMENT_TYPE));
- if (!declElementType)
- return XML_ERROR_NO_MEMORY;
- if (declElementType->name != name)
- poolDiscard(&dtd.pool);
- else {
- poolFinish(&dtd.pool);
- if (!setElementTypePrefix(parser, declElementType))
- return XML_ERROR_NO_MEMORY;
- }
- break;
- }
- case XML_ROLE_ATTRIBUTE_NAME:
- declAttributeId = getAttributeId(parser, enc, s, next);
- if (!declAttributeId)
- return XML_ERROR_NO_MEMORY;
- declAttributeIsCdata = 0;
- break;
- case XML_ROLE_ATTRIBUTE_TYPE_CDATA:
- declAttributeIsCdata = 1;
- break;
- case XML_ROLE_IMPLIED_ATTRIBUTE_VALUE:
- case XML_ROLE_REQUIRED_ATTRIBUTE_VALUE:
- if (dtd.complete
- && !defineAttribute(declElementType, declAttributeId, declAttributeIsCdata, 0))
- return XML_ERROR_NO_MEMORY;
- break;
- case XML_ROLE_DEFAULT_ATTRIBUTE_VALUE:
- case XML_ROLE_FIXED_ATTRIBUTE_VALUE:
- {
- const XML_Char *attVal;
- enum XML_Error result
- = storeAttributeValue(parser, enc, declAttributeIsCdata,
- s + enc->minBytesPerChar,
- next - enc->minBytesPerChar,
- &dtd.pool);
- if (result)
- return result;
- attVal = poolStart(&dtd.pool);
- poolFinish(&dtd.pool);
- if (dtd.complete
- && !defineAttribute(declElementType, declAttributeId, declAttributeIsCdata, attVal))
- return XML_ERROR_NO_MEMORY;
- break;
- }
- case XML_ROLE_ENTITY_VALUE:
- {
- enum XML_Error result = storeEntityValue(parser, enc,
- s + enc->minBytesPerChar,
- next - enc->minBytesPerChar);
- if (declEntity) {
- declEntity->textPtr = poolStart(&dtd.pool);
- declEntity->textLen = poolLength(&dtd.pool);
- poolFinish(&dtd.pool);
- }
- else
- poolDiscard(&dtd.pool);
- if (result != XML_ERROR_NONE)
- return result;
- }
- break;
- case XML_ROLE_DOCTYPE_SYSTEM_ID:
- if (!dtd.standalone
-#ifdef XML_DTD
- && !paramEntityParsing
-#endif /* XML_DTD */
- && notStandaloneHandler
- && !notStandaloneHandler(handlerArg))
- return XML_ERROR_NOT_STANDALONE;
- hadExternalDoctype = 1;
-#ifndef XML_DTD
- break;
-#else /* XML_DTD */
- if (!declEntity) {
- declEntity = (ENTITY *)lookup(&dtd.paramEntities,
- externalSubsetName,
- sizeof(ENTITY));
- if (!declEntity)
- return XML_ERROR_NO_MEMORY;
- }
- /* fall through */
-#endif /* XML_DTD */
- case XML_ROLE_ENTITY_SYSTEM_ID:
- if (declEntity) {
- declEntity->systemId = poolStoreString(&dtd.pool, enc,
- s + enc->minBytesPerChar,
- next - enc->minBytesPerChar);
- if (!declEntity->systemId)
- return XML_ERROR_NO_MEMORY;
- declEntity->base = curBase;
- poolFinish(&dtd.pool);
- }
- break;
- case XML_ROLE_ENTITY_NOTATION_NAME:
- if (declEntity) {
- declEntity->notation = poolStoreString(&dtd.pool, enc, s, next);
- if (!declEntity->notation)
- return XML_ERROR_NO_MEMORY;
- poolFinish(&dtd.pool);
- if (unparsedEntityDeclHandler) {
- *eventEndPP = s;
- unparsedEntityDeclHandler(handlerArg,
- declEntity->name,
- declEntity->base,
- declEntity->systemId,
- declEntity->publicId,
- declEntity->notation);
- }
-
- }
- break;
- case XML_ROLE_GENERAL_ENTITY_NAME:
- {
- const XML_Char *name;
- if (XmlPredefinedEntityName(enc, s, next)) {
- declEntity = 0;
- break;
- }
- name = poolStoreString(&dtd.pool, enc, s, next);
- if (!name)
- return XML_ERROR_NO_MEMORY;
- if (dtd.complete) {
- declEntity = (ENTITY *)lookup(&dtd.generalEntities, name, sizeof(ENTITY));
- if (!declEntity)
- return XML_ERROR_NO_MEMORY;
- if (declEntity->name != name) {
- poolDiscard(&dtd.pool);
- declEntity = 0;
- }
- else
- poolFinish(&dtd.pool);
- }
- else {
- poolDiscard(&dtd.pool);
- declEntity = 0;
- }
- }
- break;
- case XML_ROLE_PARAM_ENTITY_NAME:
-#ifdef XML_DTD
- if (dtd.complete) {
- const XML_Char *name = poolStoreString(&dtd.pool, enc, s, next);
- if (!name)
- return XML_ERROR_NO_MEMORY;
- declEntity = (ENTITY *)lookup(&dtd.paramEntities, name, sizeof(ENTITY));
- if (!declEntity)
- return XML_ERROR_NO_MEMORY;
- if (declEntity->name != name) {
- poolDiscard(&dtd.pool);
- declEntity = 0;
- }
- else
- poolFinish(&dtd.pool);
- }
-#else /* not XML_DTD */
- declEntity = 0;
-#endif /* not XML_DTD */
- break;
- case XML_ROLE_NOTATION_NAME:
- declNotationPublicId = 0;
- declNotationName = 0;
- if (notationDeclHandler) {
- declNotationName = poolStoreString(&tempPool, enc, s, next);
- if (!declNotationName)
- return XML_ERROR_NO_MEMORY;
- poolFinish(&tempPool);
- }
- break;
- case XML_ROLE_NOTATION_PUBLIC_ID:
- if (!XmlIsPublicId(enc, s, next, eventPP))
- return XML_ERROR_SYNTAX;
- if (declNotationName) {
- XML_Char *tem = poolStoreString(&tempPool,
- enc,
- s + enc->minBytesPerChar,
- next - enc->minBytesPerChar);
- if (!tem)
- return XML_ERROR_NO_MEMORY;
- normalizePublicId(tem);
- declNotationPublicId = tem;
- poolFinish(&tempPool);
- }
- break;
- case XML_ROLE_NOTATION_SYSTEM_ID:
- if (declNotationName && notationDeclHandler) {
- const XML_Char *systemId
- = poolStoreString(&tempPool, enc,
- s + enc->minBytesPerChar,
- next - enc->minBytesPerChar);
- if (!systemId)
- return XML_ERROR_NO_MEMORY;
- *eventEndPP = s;
- notationDeclHandler(handlerArg,
- declNotationName,
- curBase,
- systemId,
- declNotationPublicId);
- }
- poolClear(&tempPool);
- break;
- case XML_ROLE_NOTATION_NO_SYSTEM_ID:
- if (declNotationPublicId && notationDeclHandler) {
- *eventEndPP = s;
- notationDeclHandler(handlerArg,
- declNotationName,
- curBase,
- 0,
- declNotationPublicId);
- }
- poolClear(&tempPool);
- break;
- case XML_ROLE_ERROR:
- switch (tok) {
- case XML_TOK_PARAM_ENTITY_REF:
- return XML_ERROR_PARAM_ENTITY_REF;
- case XML_TOK_XML_DECL:
- return XML_ERROR_MISPLACED_XML_PI;
- default:
- return XML_ERROR_SYNTAX;
- }
-#ifdef XML_DTD
- case XML_ROLE_IGNORE_SECT:
- {
- enum XML_Error result;
- if (defaultHandler)
- reportDefault(parser, enc, s, next);
- result = doIgnoreSection(parser, enc, &next, end, nextPtr);
- if (!next) {
- processor = ignoreSectionProcessor;
- return result;
- }
- }
- break;
-#endif /* XML_DTD */
- case XML_ROLE_GROUP_OPEN:
- if (prologState.level >= groupSize) {
- if (groupSize)
- groupConnector = realloc(groupConnector, groupSize *= 2);
- else
- groupConnector = malloc(groupSize = 32);
- if (!groupConnector)
- return XML_ERROR_NO_MEMORY;
- }
- groupConnector[prologState.level] = 0;
- break;
- case XML_ROLE_GROUP_SEQUENCE:
- if (groupConnector[prologState.level] == '|')
- return XML_ERROR_SYNTAX;
- groupConnector[prologState.level] = ',';
- break;
- case XML_ROLE_GROUP_CHOICE:
- if (groupConnector[prologState.level] == ',')
- return XML_ERROR_SYNTAX;
- groupConnector[prologState.level] = '|';
- break;
- case XML_ROLE_PARAM_ENTITY_REF:
-#ifdef XML_DTD
- case XML_ROLE_INNER_PARAM_ENTITY_REF:
- if (paramEntityParsing
- && (dtd.complete || role == XML_ROLE_INNER_PARAM_ENTITY_REF)) {
- const XML_Char *name;
- ENTITY *entity;
- name = poolStoreString(&dtd.pool, enc,
- s + enc->minBytesPerChar,
- next - enc->minBytesPerChar);
- if (!name)
- return XML_ERROR_NO_MEMORY;
- entity = (ENTITY *)lookup(&dtd.paramEntities, name, 0);
- poolDiscard(&dtd.pool);
- if (!entity) {
- /* FIXME what to do if !dtd.complete? */
- return XML_ERROR_UNDEFINED_ENTITY;
- }
- if (entity->open)
- return XML_ERROR_RECURSIVE_ENTITY_REF;
- if (entity->textPtr) {
- enum XML_Error result;
- result = processInternalParamEntity(parser, entity);
- if (result != XML_ERROR_NONE)
- return result;
- break;
- }
- if (role == XML_ROLE_INNER_PARAM_ENTITY_REF)
- return XML_ERROR_PARAM_ENTITY_REF;
- if (externalEntityRefHandler) {
- dtd.complete = 0;
- entity->open = 1;
- if (!externalEntityRefHandler(externalEntityRefHandlerArg,
- 0,
- entity->base,
- entity->systemId,
- entity->publicId)) {
- entity->open = 0;
- return XML_ERROR_EXTERNAL_ENTITY_HANDLING;
- }
- entity->open = 0;
- if (dtd.complete)
- break;
- }
- }
-#endif /* XML_DTD */
- if (!dtd.standalone
- && notStandaloneHandler
- && !notStandaloneHandler(handlerArg))
- return XML_ERROR_NOT_STANDALONE;
- dtd.complete = 0;
- if (defaultHandler)
- reportDefault(parser, enc, s, next);
- break;
- case XML_ROLE_NONE:
- switch (tok) {
- case XML_TOK_PI:
- if (!reportProcessingInstruction(parser, enc, s, next))
- return XML_ERROR_NO_MEMORY;
- break;
- case XML_TOK_COMMENT:
- if (!reportComment(parser, enc, s, next))
- return XML_ERROR_NO_MEMORY;
- break;
- }
- break;
- }
- if (defaultHandler) {
- switch (tok) {
- case XML_TOK_PI:
- case XML_TOK_COMMENT:
- case XML_TOK_BOM:
- case XML_TOK_XML_DECL:
-#ifdef XML_DTD
- case XML_TOK_IGNORE_SECT:
-#endif /* XML_DTD */
- case XML_TOK_PARAM_ENTITY_REF:
- break;
- default:
- if (role != XML_ROLE_IGNORE_SECT)
- reportDefault(parser, enc, s, next);
- }
- }
- s = next;
- tok = XmlPrologTok(enc, s, end, &next);
- }
- /* not reached */
-}
-
-static
-enum XML_Error epilogProcessor(XML_Parser parser,
- const char *s,
- const char *end,
- const char **nextPtr)
-{
- processor = epilogProcessor;
- eventPtr = s;
- for (;;) {
- const char *next;
- int tok = XmlPrologTok(encoding, s, end, &next);
- eventEndPtr = next;
- switch (tok) {
- case -XML_TOK_PROLOG_S:
- if (defaultHandler) {
- eventEndPtr = end;
- reportDefault(parser, encoding, s, end);
- }
- /* fall through */
- case XML_TOK_NONE:
- if (nextPtr)
- *nextPtr = end;
- return XML_ERROR_NONE;
- case XML_TOK_PROLOG_S:
- if (defaultHandler)
- reportDefault(parser, encoding, s, next);
- break;
- case XML_TOK_PI:
- if (!reportProcessingInstruction(parser, encoding, s, next))
- return XML_ERROR_NO_MEMORY;
- break;
- case XML_TOK_COMMENT:
- if (!reportComment(parser, encoding, s, next))
- return XML_ERROR_NO_MEMORY;
- break;
- case XML_TOK_INVALID:
- eventPtr = next;
- return XML_ERROR_INVALID_TOKEN;
- case XML_TOK_PARTIAL:
- if (nextPtr) {
- *nextPtr = s;
- return XML_ERROR_NONE;
- }
- return XML_ERROR_UNCLOSED_TOKEN;
- case XML_TOK_PARTIAL_CHAR:
- if (nextPtr) {
- *nextPtr = s;
- return XML_ERROR_NONE;
- }
- return XML_ERROR_PARTIAL_CHAR;
- default:
- return XML_ERROR_JUNK_AFTER_DOC_ELEMENT;
- }
- eventPtr = s = next;
- }
-}
-
-#ifdef XML_DTD
-
-static enum XML_Error
-processInternalParamEntity(XML_Parser parser, ENTITY *entity)
-{
- const char *s, *end, *next;
- int tok;
- enum XML_Error result;
- OPEN_INTERNAL_ENTITY openEntity;
- entity->open = 1;
- openEntity.next = openInternalEntities;
- openInternalEntities = &openEntity;
- openEntity.entity = entity;
- openEntity.internalEventPtr = 0;
- openEntity.internalEventEndPtr = 0;
- s = (char *)entity->textPtr;
- end = (char *)(entity->textPtr + entity->textLen);
- tok = XmlPrologTok(internalEncoding, s, end, &next);
- result = doProlog(parser, internalEncoding, s, end, tok, next, 0);
- entity->open = 0;
- openInternalEntities = openEntity.next;
- return result;
-}
-
-#endif /* XML_DTD */
-
-static
-enum XML_Error errorProcessor(XML_Parser parser,
- const char *s,
- const char *end,
- const char **nextPtr)
-{
- return errorCode;
-}
-
-static enum XML_Error
-storeAttributeValue(XML_Parser parser, const ENCODING *enc, int isCdata,
- const char *ptr, const char *end,
- STRING_POOL *pool)
-{
- enum XML_Error result = appendAttributeValue(parser, enc, isCdata, ptr, end, pool);
- if (result)
- return result;
- if (!isCdata && poolLength(pool) && poolLastChar(pool) == 0x20)
- poolChop(pool);
- if (!poolAppendChar(pool, XML_T('\0')))
- return XML_ERROR_NO_MEMORY;
- return XML_ERROR_NONE;
-}
-
-static enum XML_Error
-appendAttributeValue(XML_Parser parser, const ENCODING *enc, int isCdata,
- const char *ptr, const char *end,
- STRING_POOL *pool)
-{
- for (;;) {
- const char *next;
- int tok = XmlAttributeValueTok(enc, ptr, end, &next);
- switch (tok) {
- case XML_TOK_NONE:
- return XML_ERROR_NONE;
- case XML_TOK_INVALID:
- if (enc == encoding)
- eventPtr = next;
- return XML_ERROR_INVALID_TOKEN;
- case XML_TOK_PARTIAL:
- if (enc == encoding)
- eventPtr = ptr;
- return XML_ERROR_INVALID_TOKEN;
- case XML_TOK_CHAR_REF:
- {
- XML_Char buf[XML_ENCODE_MAX];
- int i;
- int n = XmlCharRefNumber(enc, ptr);
- if (n < 0) {
- if (enc == encoding)
- eventPtr = ptr;
- return XML_ERROR_BAD_CHAR_REF;
- }
- if (!isCdata
- && n == 0x20 /* space */
- && (poolLength(pool) == 0 || poolLastChar(pool) == 0x20))
- break;
- n = XmlEncode(n, (ICHAR *)buf);
- if (!n) {
- if (enc == encoding)
- eventPtr = ptr;
- return XML_ERROR_BAD_CHAR_REF;
- }
- for (i = 0; i < n; i++) {
- if (!poolAppendChar(pool, buf[i]))
- return XML_ERROR_NO_MEMORY;
- }
- }
- break;
- case XML_TOK_DATA_CHARS:
- if (!poolAppend(pool, enc, ptr, next))
- return XML_ERROR_NO_MEMORY;
- break;
- break;
- case XML_TOK_TRAILING_CR:
- next = ptr + enc->minBytesPerChar;
- /* fall through */
- case XML_TOK_ATTRIBUTE_VALUE_S:
- case XML_TOK_DATA_NEWLINE:
- if (!isCdata && (poolLength(pool) == 0 || poolLastChar(pool) == 0x20))
- break;
- if (!poolAppendChar(pool, 0x20))
- return XML_ERROR_NO_MEMORY;
- break;
- case XML_TOK_ENTITY_REF:
- {
- const XML_Char *name;
- ENTITY *entity;
- XML_Char ch = XmlPredefinedEntityName(enc,
- ptr + enc->minBytesPerChar,
- next - enc->minBytesPerChar);
- if (ch) {
- if (!poolAppendChar(pool, ch))
- return XML_ERROR_NO_MEMORY;
- break;
- }
- name = poolStoreString(&temp2Pool, enc,
- ptr + enc->minBytesPerChar,
- next - enc->minBytesPerChar);
- if (!name)
- return XML_ERROR_NO_MEMORY;
- entity = (ENTITY *)lookup(&dtd.generalEntities, name, 0);
- poolDiscard(&temp2Pool);
- if (!entity) {
- if (dtd.complete) {
- if (enc == encoding)
- eventPtr = ptr;
- return XML_ERROR_UNDEFINED_ENTITY;
- }
- }
- else if (entity->open) {
- if (enc == encoding)
- eventPtr = ptr;
- return XML_ERROR_RECURSIVE_ENTITY_REF;
- }
- else if (entity->notation) {
- if (enc == encoding)
- eventPtr = ptr;
- return XML_ERROR_BINARY_ENTITY_REF;
- }
- else if (!entity->textPtr) {
- if (enc == encoding)
- eventPtr = ptr;
- return XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF;
- }
- else {
- enum XML_Error result;
- const XML_Char *textEnd = entity->textPtr + entity->textLen;
- entity->open = 1;
- result = appendAttributeValue(parser, internalEncoding, isCdata, (char *)entity->textPtr, (char *)textEnd, pool);
- entity->open = 0;
- if (result)
- return result;
- }
- }
- break;
- default:
- abort();
- }
- ptr = next;
- }
- /* not reached */
-}
-
-static
-enum XML_Error storeEntityValue(XML_Parser parser,
- const ENCODING *enc,
- const char *entityTextPtr,
- const char *entityTextEnd)
-{
- STRING_POOL *pool = &(dtd.pool);
- for (;;) {
- const char *next;
- int tok = XmlEntityValueTok(enc, entityTextPtr, entityTextEnd, &next);
- switch (tok) {
- case XML_TOK_PARAM_ENTITY_REF:
-#ifdef XML_DTD
- if (parentParser || enc != encoding) {
- enum XML_Error result;
- const XML_Char *name;
- ENTITY *entity;
- name = poolStoreString(&tempPool, enc,
- entityTextPtr + enc->minBytesPerChar,
- next - enc->minBytesPerChar);
- if (!name)
- return XML_ERROR_NO_MEMORY;
- entity = (ENTITY *)lookup(&dtd.paramEntities, name, 0);
- poolDiscard(&tempPool);
- if (!entity) {
- if (enc == encoding)
- eventPtr = entityTextPtr;
- return XML_ERROR_UNDEFINED_ENTITY;
- }
- if (entity->open) {
- if (enc == encoding)
- eventPtr = entityTextPtr;
- return XML_ERROR_RECURSIVE_ENTITY_REF;
- }
- if (entity->systemId) {
- if (enc == encoding)
- eventPtr = entityTextPtr;
- return XML_ERROR_PARAM_ENTITY_REF;
- }
- entity->open = 1;
- result = storeEntityValue(parser,
- internalEncoding,
- (char *)entity->textPtr,
- (char *)(entity->textPtr + entity->textLen));
- entity->open = 0;
- if (result)
- return result;
- break;
- }
-#endif /* XML_DTD */
- eventPtr = entityTextPtr;
- return XML_ERROR_SYNTAX;
- case XML_TOK_NONE:
- return XML_ERROR_NONE;
- case XML_TOK_ENTITY_REF:
- case XML_TOK_DATA_CHARS:
- if (!poolAppend(pool, enc, entityTextPtr, next))
- return XML_ERROR_NO_MEMORY;
- break;
- case XML_TOK_TRAILING_CR:
- next = entityTextPtr + enc->minBytesPerChar;
- /* fall through */
- case XML_TOK_DATA_NEWLINE:
- if (pool->end == pool->ptr && !poolGrow(pool))
- return XML_ERROR_NO_MEMORY;
- *(pool->ptr)++ = 0xA;
- break;
- case XML_TOK_CHAR_REF:
- {
- XML_Char buf[XML_ENCODE_MAX];
- int i;
- int n = XmlCharRefNumber(enc, entityTextPtr);
- if (n < 0) {
- if (enc == encoding)
- eventPtr = entityTextPtr;
- return XML_ERROR_BAD_CHAR_REF;
- }
- n = XmlEncode(n, (ICHAR *)buf);
- if (!n) {
- if (enc == encoding)
- eventPtr = entityTextPtr;
- return XML_ERROR_BAD_CHAR_REF;
- }
- for (i = 0; i < n; i++) {
- if (pool->end == pool->ptr && !poolGrow(pool))
- return XML_ERROR_NO_MEMORY;
- *(pool->ptr)++ = buf[i];
- }
- }
- break;
- case XML_TOK_PARTIAL:
- if (enc == encoding)
- eventPtr = entityTextPtr;
- return XML_ERROR_INVALID_TOKEN;
- case XML_TOK_INVALID:
- if (enc == encoding)
- eventPtr = next;
- return XML_ERROR_INVALID_TOKEN;
- default:
- abort();
- }
- entityTextPtr = next;
- }
- /* not reached */
-}
-
-static void
-normalizeLines(XML_Char *s)
-{
- XML_Char *p;
- for (;; s++) {
- if (*s == XML_T('\0'))
- return;
- if (*s == 0xD)
- break;
- }
- p = s;
- do {
- if (*s == 0xD) {
- *p++ = 0xA;
- if (*++s == 0xA)
- s++;
- }
- else
- *p++ = *s++;
- } while (*s);
- *p = XML_T('\0');
-}
-
-static int
-reportProcessingInstruction(XML_Parser parser, const ENCODING *enc, const char *start, const char *end)
-{
- const XML_Char *target;
- XML_Char *data;
- const char *tem;
- if (!processingInstructionHandler) {
- if (defaultHandler)
- reportDefault(parser, enc, start, end);
- return 1;
- }
- start += enc->minBytesPerChar * 2;
- tem = start + XmlNameLength(enc, start);
- target = poolStoreString(&tempPool, enc, start, tem);
- if (!target)
- return 0;
- poolFinish(&tempPool);
- data = poolStoreString(&tempPool, enc,
- XmlSkipS(enc, tem),
- end - enc->minBytesPerChar*2);
- if (!data)
- return 0;
- normalizeLines(data);
- processingInstructionHandler(handlerArg, target, data);
- poolClear(&tempPool);
- return 1;
-}
-
-static int
-reportComment(XML_Parser parser, const ENCODING *enc, const char *start, const char *end)
-{
- XML_Char *data;
- if (!commentHandler) {
- if (defaultHandler)
- reportDefault(parser, enc, start, end);
- return 1;
- }
- data = poolStoreString(&tempPool,
- enc,
- start + enc->minBytesPerChar * 4,
- end - enc->minBytesPerChar * 3);
- if (!data)
- return 0;
- normalizeLines(data);
- commentHandler(handlerArg, data);
- poolClear(&tempPool);
- return 1;
-}
-
-static void
-reportDefault(XML_Parser parser, const ENCODING *enc, const char *s, const char *end)
-{
- if (MUST_CONVERT(enc, s)) {
- const char **eventPP;
- const char **eventEndPP;
- if (enc == encoding) {
- eventPP = &eventPtr;
- eventEndPP = &eventEndPtr;
- }
- else {
- eventPP = &(openInternalEntities->internalEventPtr);
- eventEndPP = &(openInternalEntities->internalEventEndPtr);
- }
- do {
- ICHAR *dataPtr = (ICHAR *)dataBuf;
- XmlConvert(enc, &s, end, &dataPtr, (ICHAR *)dataBufEnd);
- *eventEndPP = s;
- defaultHandler(handlerArg, dataBuf, dataPtr - (ICHAR *)dataBuf);
- *eventPP = s;
- } while (s != end);
- }
- else
- defaultHandler(handlerArg, (XML_Char *)s, (XML_Char *)end - (XML_Char *)s);
-}
-
-
-static int
-defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *attId, int isCdata, const XML_Char *value)
-{
- DEFAULT_ATTRIBUTE *att;
- if (value) {
- /* The handling of default attributes gets messed up if we have
- a default which duplicates a non-default. */
- int i;
- for (i = 0; i < type->nDefaultAtts; i++)
- if (attId == type->defaultAtts[i].id)
- return 1;
- }
- if (type->nDefaultAtts == type->allocDefaultAtts) {
- if (type->allocDefaultAtts == 0) {
- type->allocDefaultAtts = 8;
- type->defaultAtts = malloc(type->allocDefaultAtts*sizeof(DEFAULT_ATTRIBUTE));
- }
- else {
- type->allocDefaultAtts *= 2;
- type->defaultAtts = realloc(type->defaultAtts,
- type->allocDefaultAtts*sizeof(DEFAULT_ATTRIBUTE));
- }
- if (!type->defaultAtts)
- return 0;
- }
- att = type->defaultAtts + type->nDefaultAtts;
- att->id = attId;
- att->value = value;
- att->isCdata = isCdata;
- if (!isCdata)
- attId->maybeTokenized = 1;
- type->nDefaultAtts += 1;
- return 1;
-}
-
-static int setElementTypePrefix(XML_Parser parser, ELEMENT_TYPE *elementType)
-{
- const XML_Char *name;
- for (name = elementType->name; *name; name++) {
- if (*name == XML_T(':')) {
- PREFIX *prefix;
- const XML_Char *s;
- for (s = elementType->name; s != name; s++) {
- if (!poolAppendChar(&dtd.pool, *s))
- return 0;
- }
- if (!poolAppendChar(&dtd.pool, XML_T('\0')))
- return 0;
- prefix = (PREFIX *)lookup(&dtd.prefixes, poolStart(&dtd.pool), sizeof(PREFIX));
- if (!prefix)
- return 0;
- if (prefix->name == poolStart(&dtd.pool))
- poolFinish(&dtd.pool);
- else
- poolDiscard(&dtd.pool);
- elementType->prefix = prefix;
-
- }
- }
- return 1;
-}
-
-static ATTRIBUTE_ID *
-getAttributeId(XML_Parser parser, const ENCODING *enc, const char *start, const char *end)
-{
- ATTRIBUTE_ID *id;
- const XML_Char *name;
- if (!poolAppendChar(&dtd.pool, XML_T('\0')))
- return 0;
- name = poolStoreString(&dtd.pool, enc, start, end);
- if (!name)
- return 0;
- ++name;
- id = (ATTRIBUTE_ID *)lookup(&dtd.attributeIds, name, sizeof(ATTRIBUTE_ID));
- if (!id)
- return 0;
- if (id->name != name)
- poolDiscard(&dtd.pool);
- else {
- poolFinish(&dtd.pool);
- if (!ns)
- ;
- else if (name[0] == 'x'
- && name[1] == 'm'
- && name[2] == 'l'
- && name[3] == 'n'
- && name[4] == 's'
- && (name[5] == XML_T('\0') || name[5] == XML_T(':'))) {
- if (name[5] == '\0')
- id->prefix = &dtd.defaultPrefix;
- else
- id->prefix = (PREFIX *)lookup(&dtd.prefixes, name + 6, sizeof(PREFIX));
- id->xmlns = 1;
- }
- else {
- int i;
- for (i = 0; name[i]; i++) {
- if (name[i] == XML_T(':')) {
- int j;
- for (j = 0; j < i; j++) {
- if (!poolAppendChar(&dtd.pool, name[j]))
- return 0;
- }
- if (!poolAppendChar(&dtd.pool, XML_T('\0')))
- return 0;
- id->prefix = (PREFIX *)lookup(&dtd.prefixes, poolStart(&dtd.pool), sizeof(PREFIX));
- if (id->prefix->name == poolStart(&dtd.pool))
- poolFinish(&dtd.pool);
- else
- poolDiscard(&dtd.pool);
- break;
- }
- }
- }
- }
- return id;
-}
-
-#define CONTEXT_SEP XML_T('\f')
-
-static
-const XML_Char *getContext(XML_Parser parser)
-{
- HASH_TABLE_ITER iter;
- int needSep = 0;
-
- if (dtd.defaultPrefix.binding) {
- int i;
- int len;
- if (!poolAppendChar(&tempPool, XML_T('=')))
- return 0;
- len = dtd.defaultPrefix.binding->uriLen;
- if (namespaceSeparator != XML_T('\0'))
- len--;
- for (i = 0; i < len; i++)
- if (!poolAppendChar(&tempPool, dtd.defaultPrefix.binding->uri[i]))
- return 0;
- needSep = 1;
- }
-
- hashTableIterInit(&iter, &(dtd.prefixes));
- for (;;) {
- int i;
- int len;
- const XML_Char *s;
- PREFIX *prefix = (PREFIX *)hashTableIterNext(&iter);
- if (!prefix)
- break;
- if (!prefix->binding)
- continue;
- if (needSep && !poolAppendChar(&tempPool, CONTEXT_SEP))
- return 0;
- for (s = prefix->name; *s; s++)
- if (!poolAppendChar(&tempPool, *s))
- return 0;
- if (!poolAppendChar(&tempPool, XML_T('=')))
- return 0;
- len = prefix->binding->uriLen;
- if (namespaceSeparator != XML_T('\0'))
- len--;
- for (i = 0; i < len; i++)
- if (!poolAppendChar(&tempPool, prefix->binding->uri[i]))
- return 0;
- needSep = 1;
- }
-
-
- hashTableIterInit(&iter, &(dtd.generalEntities));
- for (;;) {
- const XML_Char *s;
- ENTITY *e = (ENTITY *)hashTableIterNext(&iter);
- if (!e)
- break;
- if (!e->open)
- continue;
- if (needSep && !poolAppendChar(&tempPool, CONTEXT_SEP))
- return 0;
- for (s = e->name; *s; s++)
- if (!poolAppendChar(&tempPool, *s))
- return 0;
- needSep = 1;
- }
-
- if (!poolAppendChar(&tempPool, XML_T('\0')))
- return 0;
- return tempPool.start;
-}
-
-static
-int setContext(XML_Parser parser, const XML_Char *context)
-{
- const XML_Char *s = context;
-
- while (*context != XML_T('\0')) {
- if (*s == CONTEXT_SEP || *s == XML_T('\0')) {
- ENTITY *e;
- if (!poolAppendChar(&tempPool, XML_T('\0')))
- return 0;
- e = (ENTITY *)lookup(&dtd.generalEntities, poolStart(&tempPool), 0);
- if (e)
- e->open = 1;
- if (*s != XML_T('\0'))
- s++;
- context = s;
- poolDiscard(&tempPool);
- }
- else if (*s == '=') {
- PREFIX *prefix;
- if (poolLength(&tempPool) == 0)
- prefix = &dtd.defaultPrefix;
- else {
- if (!poolAppendChar(&tempPool, XML_T('\0')))
- return 0;
- prefix = (PREFIX *)lookup(&dtd.prefixes, poolStart(&tempPool), sizeof(PREFIX));
- if (!prefix)
- return 0;
- if (prefix->name == poolStart(&tempPool))
- poolFinish(&tempPool);
- else
- poolDiscard(&tempPool);
- }
- for (context = s + 1; *context != CONTEXT_SEP && *context != XML_T('\0'); context++)
- if (!poolAppendChar(&tempPool, *context))
- return 0;
- if (!poolAppendChar(&tempPool, XML_T('\0')))
- return 0;
- if (!addBinding(parser, prefix, 0, poolStart(&tempPool), &inheritedBindings))
- return 0;
- poolDiscard(&tempPool);
- if (*context != XML_T('\0'))
- ++context;
- s = context;
- }
- else {
- if (!poolAppendChar(&tempPool, *s))
- return 0;
- s++;
- }
- }
- return 1;
-}
-
-
-static
-void normalizePublicId(XML_Char *publicId)
-{
- XML_Char *p = publicId;
- XML_Char *s;
- for (s = publicId; *s; s++) {
- switch (*s) {
- case 0x20:
- case 0xD:
- case 0xA:
- if (p != publicId && p[-1] != 0x20)
- *p++ = 0x20;
- break;
- default:
- *p++ = *s;
- }
- }
- if (p != publicId && p[-1] == 0x20)
- --p;
- *p = XML_T('\0');
-}
-
-static int dtdInit(DTD *p)
-{
- poolInit(&(p->pool));
- hashTableInit(&(p->generalEntities));
- hashTableInit(&(p->elementTypes));
- hashTableInit(&(p->attributeIds));
- hashTableInit(&(p->prefixes));
- p->complete = 1;
- p->standalone = 0;
-#ifdef XML_DTD
- hashTableInit(&(p->paramEntities));
-#endif /* XML_DTD */
- p->defaultPrefix.name = 0;
- p->defaultPrefix.binding = 0;
- return 1;
-}
-
-#ifdef XML_DTD
-
-static void dtdSwap(DTD *p1, DTD *p2)
-{
- DTD tem;
- memcpy(&tem, p1, sizeof(DTD));
- memcpy(p1, p2, sizeof(DTD));
- memcpy(p2, &tem, sizeof(DTD));
-}
-
-#endif /* XML_DTD */
-
-static void dtdDestroy(DTD *p)
-{
- HASH_TABLE_ITER iter;
- hashTableIterInit(&iter, &(p->elementTypes));
- for (;;) {
- ELEMENT_TYPE *e = (ELEMENT_TYPE *)hashTableIterNext(&iter);
- if (!e)
- break;
- if (e->allocDefaultAtts != 0)
- free(e->defaultAtts);
- }
- hashTableDestroy(&(p->generalEntities));
-#ifdef XML_DTD
- hashTableDestroy(&(p->paramEntities));
-#endif /* XML_DTD */
- hashTableDestroy(&(p->elementTypes));
- hashTableDestroy(&(p->attributeIds));
- hashTableDestroy(&(p->prefixes));
- poolDestroy(&(p->pool));
-}
-
-/* Do a deep copy of the DTD. Return 0 for out of memory; non-zero otherwise.
-The new DTD has already been initialized. */
-
-static int dtdCopy(DTD *newDtd, const DTD *oldDtd)
-{
- HASH_TABLE_ITER iter;
-
- /* Copy the prefix table. */
-
- hashTableIterInit(&iter, &(oldDtd->prefixes));
- for (;;) {
- const XML_Char *name;
- const PREFIX *oldP = (PREFIX *)hashTableIterNext(&iter);
- if (!oldP)
- break;
- name = poolCopyString(&(newDtd->pool), oldP->name);
- if (!name)
- return 0;
- if (!lookup(&(newDtd->prefixes), name, sizeof(PREFIX)))
- return 0;
- }
-
- hashTableIterInit(&iter, &(oldDtd->attributeIds));
-
- /* Copy the attribute id table. */
-
- for (;;) {
- ATTRIBUTE_ID *newA;
- const XML_Char *name;
- const ATTRIBUTE_ID *oldA = (ATTRIBUTE_ID *)hashTableIterNext(&iter);
-
- if (!oldA)
- break;
- /* Remember to allocate the scratch byte before the name. */
- if (!poolAppendChar(&(newDtd->pool), XML_T('\0')))
- return 0;
- name = poolCopyString(&(newDtd->pool), oldA->name);
- if (!name)
- return 0;
- ++name;
- newA = (ATTRIBUTE_ID *)lookup(&(newDtd->attributeIds), name, sizeof(ATTRIBUTE_ID));
- if (!newA)
- return 0;
- newA->maybeTokenized = oldA->maybeTokenized;
- if (oldA->prefix) {
- newA->xmlns = oldA->xmlns;
- if (oldA->prefix == &oldDtd->defaultPrefix)
- newA->prefix = &newDtd->defaultPrefix;
- else
- newA->prefix = (PREFIX *)lookup(&(newDtd->prefixes), oldA->prefix->name, 0);
- }
- }
-
- /* Copy the element type table. */
-
- hashTableIterInit(&iter, &(oldDtd->elementTypes));
-
- for (;;) {
- int i;
- ELEMENT_TYPE *newE;
- const XML_Char *name;
- const ELEMENT_TYPE *oldE = (ELEMENT_TYPE *)hashTableIterNext(&iter);
- if (!oldE)
- break;
- name = poolCopyString(&(newDtd->pool), oldE->name);
- if (!name)
- return 0;
- newE = (ELEMENT_TYPE *)lookup(&(newDtd->elementTypes), name, sizeof(ELEMENT_TYPE));
- if (!newE)
- return 0;
- if (oldE->nDefaultAtts) {
- newE->defaultAtts = (DEFAULT_ATTRIBUTE *)malloc(oldE->nDefaultAtts * sizeof(DEFAULT_ATTRIBUTE));
- if (!newE->defaultAtts)
- return 0;
- }
- newE->allocDefaultAtts = newE->nDefaultAtts = oldE->nDefaultAtts;
- if (oldE->prefix)
- newE->prefix = (PREFIX *)lookup(&(newDtd->prefixes), oldE->prefix->name, 0);
- for (i = 0; i < newE->nDefaultAtts; i++) {
- newE->defaultAtts[i].id = (ATTRIBUTE_ID *)lookup(&(newDtd->attributeIds), oldE->defaultAtts[i].id->name, 0);
- newE->defaultAtts[i].isCdata = oldE->defaultAtts[i].isCdata;
- if (oldE->defaultAtts[i].value) {
- newE->defaultAtts[i].value = poolCopyString(&(newDtd->pool), oldE->defaultAtts[i].value);
- if (!newE->defaultAtts[i].value)
- return 0;
- }
- else
- newE->defaultAtts[i].value = 0;
- }
- }
-
- /* Copy the entity tables. */
- if (!copyEntityTable(&(newDtd->generalEntities),
- &(newDtd->pool),
- &(oldDtd->generalEntities)))
- return 0;
-
-#ifdef XML_DTD
- if (!copyEntityTable(&(newDtd->paramEntities),
- &(newDtd->pool),
- &(oldDtd->paramEntities)))
- return 0;
-#endif /* XML_DTD */
-
- newDtd->complete = oldDtd->complete;
- newDtd->standalone = oldDtd->standalone;
- return 1;
-}
-
-static int copyEntityTable(HASH_TABLE *newTable,
- STRING_POOL *newPool,
- const HASH_TABLE *oldTable)
-{
- HASH_TABLE_ITER iter;
- const XML_Char *cachedOldBase = 0;
- const XML_Char *cachedNewBase = 0;
-
- hashTableIterInit(&iter, oldTable);
-
- for (;;) {
- ENTITY *newE;
- const XML_Char *name;
- const ENTITY *oldE = (ENTITY *)hashTableIterNext(&iter);
- if (!oldE)
- break;
- name = poolCopyString(newPool, oldE->name);
- if (!name)
- return 0;
- newE = (ENTITY *)lookup(newTable, name, sizeof(ENTITY));
- if (!newE)
- return 0;
- if (oldE->systemId) {
- const XML_Char *tem = poolCopyString(newPool, oldE->systemId);
- if (!tem)
- return 0;
- newE->systemId = tem;
- if (oldE->base) {
- if (oldE->base == cachedOldBase)
- newE->base = cachedNewBase;
- else {
- cachedOldBase = oldE->base;
- tem = poolCopyString(newPool, cachedOldBase);
- if (!tem)
- return 0;
- cachedNewBase = newE->base = tem;
- }
- }
- }
- else {
- const XML_Char *tem = poolCopyStringN(newPool, oldE->textPtr, oldE->textLen);
- if (!tem)
- return 0;
- newE->textPtr = tem;
- newE->textLen = oldE->textLen;
- }
- if (oldE->notation) {
- const XML_Char *tem = poolCopyString(newPool, oldE->notation);
- if (!tem)
- return 0;
- newE->notation = tem;
- }
- }
- return 1;
-}
-
-static
-void poolInit(STRING_POOL *pool)
-{
- pool->blocks = 0;
- pool->freeBlocks = 0;
- pool->start = 0;
- pool->ptr = 0;
- pool->end = 0;
-}
-
-static
-void poolClear(STRING_POOL *pool)
-{
- if (!pool->freeBlocks)
- pool->freeBlocks = pool->blocks;
- else {
- BLOCK *p = pool->blocks;
- while (p) {
- BLOCK *tem = p->next;
- p->next = pool->freeBlocks;
- pool->freeBlocks = p;
- p = tem;
- }
- }
- pool->blocks = 0;
- pool->start = 0;
- pool->ptr = 0;
- pool->end = 0;
-}
-
-static
-void poolDestroy(STRING_POOL *pool)
-{
- BLOCK *p = pool->blocks;
- while (p) {
- BLOCK *tem = p->next;
- free(p);
- p = tem;
- }
- pool->blocks = 0;
- p = pool->freeBlocks;
- while (p) {
- BLOCK *tem = p->next;
- free(p);
- p = tem;
- }
- pool->freeBlocks = 0;
- pool->ptr = 0;
- pool->start = 0;
- pool->end = 0;
-}
-
-static
-XML_Char *poolAppend(STRING_POOL *pool, const ENCODING *enc,
- const char *ptr, const char *end)
-{
- if (!pool->ptr && !poolGrow(pool))
- return 0;
- for (;;) {
- XmlConvert(enc, &ptr, end, (ICHAR **)&(pool->ptr), (ICHAR *)pool->end);
- if (ptr == end)
- break;
- if (!poolGrow(pool))
- return 0;
- }
- return pool->start;
-}
-
-static const XML_Char *poolCopyString(STRING_POOL *pool, const XML_Char *s)
-{
- do {
- if (!poolAppendChar(pool, *s))
- return 0;
- } while (*s++);
- s = pool->start;
- poolFinish(pool);
- return s;
-}
-
-static const XML_Char *poolCopyStringN(STRING_POOL *pool, const XML_Char *s, int n)
-{
- if (!pool->ptr && !poolGrow(pool))
- return 0;
- for (; n > 0; --n, s++) {
- if (!poolAppendChar(pool, *s))
- return 0;
-
- }
- s = pool->start;
- poolFinish(pool);
- return s;
-}
-
-static
-XML_Char *poolStoreString(STRING_POOL *pool, const ENCODING *enc,
- const char *ptr, const char *end)
-{
- if (!poolAppend(pool, enc, ptr, end))
- return 0;
- if (pool->ptr == pool->end && !poolGrow(pool))
- return 0;
- *(pool->ptr)++ = 0;
- return pool->start;
-}
-
-static
-int poolGrow(STRING_POOL *pool)
-{
- if (pool->freeBlocks) {
- if (pool->start == 0) {
- pool->blocks = pool->freeBlocks;
- pool->freeBlocks = pool->freeBlocks->next;
- pool->blocks->next = 0;
- pool->start = pool->blocks->s;
- pool->end = pool->start + pool->blocks->size;
- pool->ptr = pool->start;
- return 1;
- }
- if (pool->end - pool->start < pool->freeBlocks->size) {
- BLOCK *tem = pool->freeBlocks->next;
- pool->freeBlocks->next = pool->blocks;
- pool->blocks = pool->freeBlocks;
- pool->freeBlocks = tem;
- memcpy(pool->blocks->s, pool->start, (pool->end - pool->start) * sizeof(XML_Char));
- pool->ptr = pool->blocks->s + (pool->ptr - pool->start);
- pool->start = pool->blocks->s;
- pool->end = pool->start + pool->blocks->size;
- return 1;
- }
- }
- if (pool->blocks && pool->start == pool->blocks->s) {
- int blockSize = (pool->end - pool->start)*2;
- pool->blocks = realloc(pool->blocks, offsetof(BLOCK, s) + blockSize * sizeof(XML_Char));
- if (!pool->blocks)
- return 0;
- pool->blocks->size = blockSize;
- pool->ptr = pool->blocks->s + (pool->ptr - pool->start);
- pool->start = pool->blocks->s;
- pool->end = pool->start + blockSize;
- }
- else {
- BLOCK *tem;
- int blockSize = pool->end - pool->start;
- if (blockSize < INIT_BLOCK_SIZE)
- blockSize = INIT_BLOCK_SIZE;
- else
- blockSize *= 2;
- tem = malloc(offsetof(BLOCK, s) + blockSize * sizeof(XML_Char));
- if (!tem)
- return 0;
- tem->size = blockSize;
- tem->next = pool->blocks;
- pool->blocks = tem;
- memcpy(tem->s, pool->start, (pool->ptr - pool->start) * sizeof(XML_Char));
- pool->ptr = tem->s + (pool->ptr - pool->start);
- pool->start = tem->s;
- pool->end = tem->s + blockSize;
- }
- return 1;
-}
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlparse/xmlparse.h
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlparse/xmlparse.h 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlparse/xmlparse.h 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,525 +0,0 @@
-/*
-The contents of this file are subject to the Mozilla Public License
-Version 1.1 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998, 1999
-James Clark. All Rights Reserved.
-
-Contributor(s):
-
-Alternatively, the contents of this file may be used under the terms
-of the GNU General Public License (the "GPL"), in which case the
-provisions of the GPL are applicable instead of those above. If you
-wish to allow use of your version of this file only under the terms of
-the GPL and not to allow others to use your version of this file under
-the MPL, indicate your decision by deleting the provisions above and
-replace them with the notice and other provisions required by the
-GPL. If you do not delete the provisions above, a recipient may use
-your version of this file under either the MPL or the GPL.
-*/
-
-#ifndef XmlParse_INCLUDED
-#define XmlParse_INCLUDED 1
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-#ifndef XMLPARSEAPI
-#define XMLPARSEAPI /* as nothing */
-#endif
-
-typedef void *XML_Parser;
-
-#ifdef XML_UNICODE_WCHAR_T
-
-/* XML_UNICODE_WCHAR_T will work only if sizeof(wchar_t) == 2 and wchar_t
-uses Unicode. */
-/* Information is UTF-16 encoded as wchar_ts */
-
-#ifndef XML_UNICODE
-#define XML_UNICODE
-#endif
-
-#include <stddef.h>
-typedef wchar_t XML_Char;
-typedef wchar_t XML_LChar;
-
-#else /* not XML_UNICODE_WCHAR_T */
-
-#ifdef XML_UNICODE
-
-/* Information is UTF-16 encoded as unsigned shorts */
-typedef unsigned short XML_Char;
-typedef char XML_LChar;
-
-#else /* not XML_UNICODE */
-
-/* Information is UTF-8 encoded. */
-typedef char XML_Char;
-typedef char XML_LChar;
-
-#endif /* not XML_UNICODE */
-
-#endif /* not XML_UNICODE_WCHAR_T */
-
-
-/* Constructs a new parser; encoding is the encoding specified by the external
-protocol or null if there is none specified. */
-
-XML_Parser XMLPARSEAPI
-XML_ParserCreate(const XML_Char *encoding);
-
-/* Constructs a new parser and namespace processor. Element type names
-and attribute names that belong to a namespace will be expanded;
-unprefixed attribute names are never expanded; unprefixed element type
-names are expanded only if there is a default namespace. The expanded
-name is the concatenation of the namespace URI, the namespace separator character,
-and the local part of the name. If the namespace separator is '\0' then
-the namespace URI and the local part will be concatenated without any
-separator. When a namespace is not declared, the name and prefix will be
-passed through without expansion. */
-
-XML_Parser XMLPARSEAPI
-XML_ParserCreateNS(const XML_Char *encoding, XML_Char namespaceSeparator);
-
-
-/* atts is array of name/value pairs, terminated by 0;
- names and values are 0 terminated. */
-
-typedef void (*XML_StartElementHandler)(void *userData,
- const XML_Char *name,
- const XML_Char **atts);
-
-typedef void (*XML_EndElementHandler)(void *userData,
- const XML_Char *name);
-
-/* s is not 0 terminated. */
-typedef void (*XML_CharacterDataHandler)(void *userData,
- const XML_Char *s,
- int len);
-
-/* target and data are 0 terminated */
-typedef void (*XML_ProcessingInstructionHandler)(void *userData,
- const XML_Char *target,
- const XML_Char *data);
-
-/* data is 0 terminated */
-typedef void (*XML_CommentHandler)(void *userData, const XML_Char *data);
-
-typedef void (*XML_StartCdataSectionHandler)(void *userData);
-typedef void (*XML_EndCdataSectionHandler)(void *userData);
-
-/* This is called for any characters in the XML document for
-which there is no applicable handler. This includes both
-characters that are part of markup which is of a kind that is
-not reported (comments, markup declarations), or characters
-that are part of a construct which could be reported but
-for which no handler has been supplied. The characters are passed
-exactly as they were in the XML document except that
-they will be encoded in UTF-8. Line boundaries are not normalized.
-Note that a byte order mark character is not passed to the default handler.
-There are no guarantees about how characters are divided between calls
-to the default handler: for example, a comment might be split between
-multiple calls. */
-
-typedef void (*XML_DefaultHandler)(void *userData,
- const XML_Char *s,
- int len);
-
-/* This is called for the start of the DOCTYPE declaration when the
-name of the DOCTYPE is encountered. */
-typedef void (*XML_StartDoctypeDeclHandler)(void *userData,
- const XML_Char *doctypeName);
-
-/* This is called for the start of the DOCTYPE declaration when the
-closing > is encountered, but after processing any external subset. */
-typedef void (*XML_EndDoctypeDeclHandler)(void *userData);
-
-/* This is called for a declaration of an unparsed (NDATA)
-entity. The base argument is whatever was set by XML_SetBase.
-The entityName, systemId and notationName arguments will never be null.
-The other arguments may be. */
-
-typedef void (*XML_UnparsedEntityDeclHandler)(void *userData,
- const XML_Char *entityName,
- const XML_Char *base,
- const XML_Char *systemId,
- const XML_Char *publicId,
- const XML_Char *notationName);
-
-/* This is called for a declaration of notation.
-The base argument is whatever was set by XML_SetBase.
-The notationName will never be null. The other arguments can be. */
-
-typedef void (*XML_NotationDeclHandler)(void *userData,
- const XML_Char *notationName,
- const XML_Char *base,
- const XML_Char *systemId,
- const XML_Char *publicId);
-
-/* When namespace processing is enabled, these are called once for
-each namespace declaration. The call to the start and end element
-handlers occur between the calls to the start and end namespace
-declaration handlers. For an xmlns attribute, prefix will be null.
-For an xmlns="" attribute, uri will be null. */
-
-typedef void (*XML_StartNamespaceDeclHandler)(void *userData,
- const XML_Char *prefix,
- const XML_Char *uri);
-
-typedef void (*XML_EndNamespaceDeclHandler)(void *userData,
- const XML_Char *prefix);
-
-/* This is called if the document is not standalone (it has an
-external subset or a reference to a parameter entity, but does not
-have standalone="yes"). If this handler returns 0, then processing
-will not continue, and the parser will return a
-XML_ERROR_NOT_STANDALONE error. */
-
-typedef int (*XML_NotStandaloneHandler)(void *userData);
-
-/* This is called for a reference to an external parsed general entity.
-The referenced entity is not automatically parsed.
-The application can parse it immediately or later using
-XML_ExternalEntityParserCreate.
-The parser argument is the parser parsing the entity containing the reference;
-it can be passed as the parser argument to XML_ExternalEntityParserCreate.
-The systemId argument is the system identifier as specified in the entity declaration;
-it will not be null.
-The base argument is the system identifier that should be used as the base for
-resolving systemId if systemId was relative; this is set by XML_SetBase;
-it may be null.
-The publicId argument is the public identifier as specified in the entity declaration,
-or null if none was specified; the whitespace in the public identifier
-will have been normalized as required by the XML spec.
-The context argument specifies the parsing context in the format
-expected by the context argument to
-XML_ExternalEntityParserCreate; context is valid only until the handler
-returns, so if the referenced entity is to be parsed later, it must be copied.
-The handler should return 0 if processing should not continue because of
-a fatal error in the handling of the external entity.
-In this case the calling parser will return an XML_ERROR_EXTERNAL_ENTITY_HANDLING
-error.
-Note that unlike other handlers the first argument is the parser, not userData. */
-
-typedef int (*XML_ExternalEntityRefHandler)(XML_Parser parser,
- const XML_Char *context,
- const XML_Char *base,
- const XML_Char *systemId,
- const XML_Char *publicId);
-
-/* This structure is filled in by the XML_UnknownEncodingHandler
-to provide information to the parser about encodings that are unknown
-to the parser.
-The map[b] member gives information about byte sequences
-whose first byte is b.
-If map[b] is c where c is >= 0, then b by itself encodes the Unicode scalar value c.
-If map[b] is -1, then the byte sequence is malformed.
-If map[b] is -n, where n >= 2, then b is the first byte of an n-byte
-sequence that encodes a single Unicode scalar value.
-The data member will be passed as the first argument to the convert function.
-The convert function is used to convert multibyte sequences;
-s will point to a n-byte sequence where map[(unsigned char)*s] == -n.
-The convert function must return the Unicode scalar value
-represented by this byte sequence or -1 if the byte sequence is malformed.
-The convert function may be null if the encoding is a single-byte encoding,
-that is if map[b] >= -1 for all bytes b.
-When the parser is finished with the encoding, then if release is not null,
-it will call release passing it the data member;
-once release has been called, the convert function will not be called again.
-
-Expat places certain restrictions on the encodings that are supported
-using this mechanism.
-
-1. Every ASCII character that can appear in a well-formed XML document,
-other than the characters
-
- $@\^`{}~
-
-must be represented by a single byte, and that byte must be the
-same byte that represents that character in ASCII.
-
-2. No character may require more than 4 bytes to encode.
-
-3. All characters encoded must have Unicode scalar values <= 0xFFFF,
-(ie characters that would be encoded by surrogates in UTF-16
-are not allowed). Note that this restriction doesn't apply to
-the built-in support for UTF-8 and UTF-16.
-
-4. No Unicode character may be encoded by more than one distinct sequence
-of bytes. */
-
-typedef struct {
- int map[256];
- void *data;
- int (*convert)(void *data, const char *s);
- void (*release)(void *data);
-} XML_Encoding;
-
-/* This is called for an encoding that is unknown to the parser.
-The encodingHandlerData argument is that which was passed as the
-second argument to XML_SetUnknownEncodingHandler.
-The name argument gives the name of the encoding as specified in
-the encoding declaration.
-If the callback can provide information about the encoding,
-it must fill in the XML_Encoding structure, and return 1.
-Otherwise it must return 0.
-If info does not describe a suitable encoding,
-then the parser will return an XML_UNKNOWN_ENCODING error. */
-
-typedef int (*XML_UnknownEncodingHandler)(void *encodingHandlerData,
- const XML_Char *name,
- XML_Encoding *info);
-
-void XMLPARSEAPI
-XML_SetElementHandler(XML_Parser parser,
- XML_StartElementHandler start,
- XML_EndElementHandler end);
-
-void XMLPARSEAPI
-XML_SetCharacterDataHandler(XML_Parser parser,
- XML_CharacterDataHandler handler);
-
-void XMLPARSEAPI
-XML_SetProcessingInstructionHandler(XML_Parser parser,
- XML_ProcessingInstructionHandler handler);
-void XMLPARSEAPI
-XML_SetCommentHandler(XML_Parser parser,
- XML_CommentHandler handler);
-
-void XMLPARSEAPI
-XML_SetCdataSectionHandler(XML_Parser parser,
- XML_StartCdataSectionHandler start,
- XML_EndCdataSectionHandler end);
-
-/* This sets the default handler and also inhibits expansion of internal entities.
-The entity reference will be passed to the default handler. */
-
-void XMLPARSEAPI
-XML_SetDefaultHandler(XML_Parser parser,
- XML_DefaultHandler handler);
-
-/* This sets the default handler but does not inhibit expansion of internal entities.
-The entity reference will not be passed to the default handler. */
-
-void XMLPARSEAPI
-XML_SetDefaultHandlerExpand(XML_Parser parser,
- XML_DefaultHandler handler);
-
-void XMLPARSEAPI
-XML_SetDoctypeDeclHandler(XML_Parser parser,
- XML_StartDoctypeDeclHandler start,
- XML_EndDoctypeDeclHandler end);
-
-void XMLPARSEAPI
-XML_SetUnparsedEntityDeclHandler(XML_Parser parser,
- XML_UnparsedEntityDeclHandler handler);
-
-void XMLPARSEAPI
-XML_SetNotationDeclHandler(XML_Parser parser,
- XML_NotationDeclHandler handler);
-
-void XMLPARSEAPI
-XML_SetNamespaceDeclHandler(XML_Parser parser,
- XML_StartNamespaceDeclHandler start,
- XML_EndNamespaceDeclHandler end);
-
-void XMLPARSEAPI
-XML_SetNotStandaloneHandler(XML_Parser parser,
- XML_NotStandaloneHandler handler);
-
-void XMLPARSEAPI
-XML_SetExternalEntityRefHandler(XML_Parser parser,
- XML_ExternalEntityRefHandler handler);
-
-/* If a non-null value for arg is specified here, then it will be passed
-as the first argument to the external entity ref handler instead
-of the parser object. */
-void XMLPARSEAPI
-XML_SetExternalEntityRefHandlerArg(XML_Parser, void *arg);
-
-void XMLPARSEAPI
-XML_SetUnknownEncodingHandler(XML_Parser parser,
- XML_UnknownEncodingHandler handler,
- void *encodingHandlerData);
-
-/* This can be called within a handler for a start element, end element,
-processing instruction or character data. It causes the corresponding
-markup to be passed to the default handler. */
-void XMLPARSEAPI XML_DefaultCurrent(XML_Parser parser);
-
-/* This value is passed as the userData argument to callbacks. */
-void XMLPARSEAPI
-XML_SetUserData(XML_Parser parser, void *userData);
-
-/* Returns the last value set by XML_SetUserData or null. */
-#define XML_GetUserData(parser) (*(void **)(parser))
-
-/* This is equivalent to supplying an encoding argument
-to XML_CreateParser. It must not be called after XML_Parse
-or XML_ParseBuffer. */
-
-int XMLPARSEAPI
-XML_SetEncoding(XML_Parser parser, const XML_Char *encoding);
-
-/* If this function is called, then the parser will be passed
-as the first argument to callbacks instead of userData.
-The userData will still be accessible using XML_GetUserData. */
-
-void XMLPARSEAPI
-XML_UseParserAsHandlerArg(XML_Parser parser);
-
-/* Sets the base to be used for resolving relative URIs in system identifiers in
-declarations. Resolving relative identifiers is left to the application:
-this value will be passed through as the base argument to the
-XML_ExternalEntityRefHandler, XML_NotationDeclHandler
-and XML_UnparsedEntityDeclHandler. The base argument will be copied.
-Returns zero if out of memory, non-zero otherwise. */
-
-int XMLPARSEAPI
-XML_SetBase(XML_Parser parser, const XML_Char *base);
-
-const XML_Char XMLPARSEAPI *
-XML_GetBase(XML_Parser parser);
-
-/* Returns the number of the attributes passed in last call to the
-XML_StartElementHandler that were specified in the start-tag rather
-than defaulted. */
-
-int XMLPARSEAPI XML_GetSpecifiedAttributeCount(XML_Parser parser);
-
-/* Parses some input. Returns 0 if a fatal error is detected.
-The last call to XML_Parse must have isFinal true;
-len may be zero for this call (or any other). */
-int XMLPARSEAPI
-XML_Parse(XML_Parser parser, const char *s, int len, int isFinal);
-
-void XMLPARSEAPI *
-XML_GetBuffer(XML_Parser parser, int len);
-
-int XMLPARSEAPI
-XML_ParseBuffer(XML_Parser parser, int len, int isFinal);
-
-/* Creates an XML_Parser object that can parse an external general entity;
-context is a '\0'-terminated string specifying the parse context;
-encoding is a '\0'-terminated string giving the name of the externally specified encoding,
-or null if there is no externally specified encoding.
-The context string consists of a sequence of tokens separated by formfeeds (\f);
-a token consisting of a name specifies that the general entity of the name
-is open; a token of the form prefix=uri specifies the namespace for a particular
-prefix; a token of the form =uri specifies the default namespace.
-This can be called at any point after the first call to an ExternalEntityRefHandler
-so longer as the parser has not yet been freed.
-The new parser is completely independent and may safely be used in a separate thread.
-The handlers and userData are initialized from the parser argument.
-Returns 0 if out of memory. Otherwise returns a new XML_Parser object. */
-XML_Parser XMLPARSEAPI
-XML_ExternalEntityParserCreate(XML_Parser parser,
- const XML_Char *context,
- const XML_Char *encoding);
-
-enum XML_ParamEntityParsing {
- XML_PARAM_ENTITY_PARSING_NEVER,
- XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE,
- XML_PARAM_ENTITY_PARSING_ALWAYS
-};
-
-/* Controls parsing of parameter entities (including the external DTD
-subset). If parsing of parameter entities is enabled, then references
-to external parameter entities (including the external DTD subset)
-will be passed to the handler set with
-XML_SetExternalEntityRefHandler. The context passed will be 0.
-Unlike external general entities, external parameter entities can only
-be parsed synchronously. If the external parameter entity is to be
-parsed, it must be parsed during the call to the external entity ref
-handler: the complete sequence of XML_ExternalEntityParserCreate,
-XML_Parse/XML_ParseBuffer and XML_ParserFree calls must be made during
-this call. After XML_ExternalEntityParserCreate has been called to
-create the parser for the external parameter entity (context must be 0
-for this call), it is illegal to make any calls on the old parser
-until XML_ParserFree has been called on the newly created parser. If
-the library has been compiled without support for parameter entity
-parsing (ie without XML_DTD being defined), then
-XML_SetParamEntityParsing will return 0 if parsing of parameter
-entities is requested; otherwise it will return non-zero. */
-
-int XMLPARSEAPI
-XML_SetParamEntityParsing(XML_Parser parser,
- enum XML_ParamEntityParsing parsing);
-
-enum XML_Error {
- XML_ERROR_NONE,
- XML_ERROR_NO_MEMORY,
- XML_ERROR_SYNTAX,
- XML_ERROR_NO_ELEMENTS,
- XML_ERROR_INVALID_TOKEN,
- XML_ERROR_UNCLOSED_TOKEN,
- XML_ERROR_PARTIAL_CHAR,
- XML_ERROR_TAG_MISMATCH,
- XML_ERROR_DUPLICATE_ATTRIBUTE,
- XML_ERROR_JUNK_AFTER_DOC_ELEMENT,
- XML_ERROR_PARAM_ENTITY_REF,
- XML_ERROR_UNDEFINED_ENTITY,
- XML_ERROR_RECURSIVE_ENTITY_REF,
- XML_ERROR_ASYNC_ENTITY,
- XML_ERROR_BAD_CHAR_REF,
- XML_ERROR_BINARY_ENTITY_REF,
- XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF,
- XML_ERROR_MISPLACED_XML_PI,
- XML_ERROR_UNKNOWN_ENCODING,
- XML_ERROR_INCORRECT_ENCODING,
- XML_ERROR_UNCLOSED_CDATA_SECTION,
- XML_ERROR_EXTERNAL_ENTITY_HANDLING,
- XML_ERROR_NOT_STANDALONE
-};
-
-/* If XML_Parse or XML_ParseBuffer have returned 0, then XML_GetErrorCode
-returns information about the error. */
-
-enum XML_Error XMLPARSEAPI XML_GetErrorCode(XML_Parser parser);
-
-/* These functions return information about the current parse location.
-They may be called when XML_Parse or XML_ParseBuffer return 0;
-in this case the location is the location of the character at which
-the error was detected.
-They may also be called from any other callback called to report
-some parse event; in this the location is the location of the first
-of the sequence of characters that generated the event. */
-
-int XMLPARSEAPI XML_GetCurrentLineNumber(XML_Parser parser);
-int XMLPARSEAPI XML_GetCurrentColumnNumber(XML_Parser parser);
-long XMLPARSEAPI XML_GetCurrentByteIndex(XML_Parser parser);
-
-/* Return the number of bytes in the current event.
-Returns 0 if the event is in an internal entity. */
-
-int XMLPARSEAPI XML_GetCurrentByteCount(XML_Parser parser);
-
-/* For backwards compatibility with previous versions. */
-#define XML_GetErrorLineNumber XML_GetCurrentLineNumber
-#define XML_GetErrorColumnNumber XML_GetCurrentColumnNumber
-#define XML_GetErrorByteIndex XML_GetCurrentByteIndex
-
-/* Frees memory used by the parser. */
-void XMLPARSEAPI
-XML_ParserFree(XML_Parser parser);
-
-/* Returns a string describing the error. */
-const XML_LChar XMLPARSEAPI *XML_ErrorString(int code);
-
-#ifdef __cplusplus
-}
-#endif
-
-#endif /* not XmlParse_INCLUDED */
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/Makefile.in
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/Makefile.in 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/Makefile.in 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,41 +0,0 @@
-#
-# The contents of this file are subject to the Netscape Public
-# License Version 1.1 (the "License"); you may not use this file
-# except in compliance with the License. You may obtain a copy of
-# the License at http://www.mozilla.org/NPL/
-#
-# Software distributed under the License is distributed on an "AS
-# IS" basis, WITHOUT WARRANTY OF ANY KIND, either express or
-# implied. See the License for the specific language governing
-# rights and limitations under the License.
-#
-# The Original Code is mozilla.org code.
-#
-# The Initial Developer of the Original Code is Netscape
-# Communications Corporation. Portions created by Netscape are
-# Copyright (C) 1998 Netscape Communications Corporation. All
-# Rights Reserved.
-#
-# Contributor(s):
-#
-
-DEPTH = ../..
-topsrcdir = @top_srcdir@
-srcdir = @srcdir@
-VPATH = @srcdir@
-
-include $(DEPTH)/config/autoconf.mk
-
-MODULE = expat
-LIBRARY_NAME = xmltok_s
-
-CSRCS = \
- xmltok.c \
- xmlrole.c \
- $(NULL)
-
-# We want only the static lib, not the shared lib
-override NO_SHARED_LIB=1
-override NO_STATIC_LIB=
-
-include $(topsrcdir)/config/rules.mk
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/asciitab.h
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/asciitab.h 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/asciitab.h 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,62 +0,0 @@
-/*
-The contents of this file are subject to the Mozilla Public License
-Version 1.1 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998, 1999
-James Clark. All Rights Reserved.
-
-Contributor(s):
-
-Alternatively, the contents of this file may be used under the terms
-of the GNU General Public License (the "GPL"), in which case the
-provisions of the GPL are applicable instead of those above. If you
-wish to allow use of your version of this file only under the terms of
-the GPL and not to allow others to use your version of this file under
-the MPL, indicate your decision by deleting the provisions above and
-replace them with the notice and other provisions required by the
-GPL. If you do not delete the provisions above, a recipient may use
-your version of this file under either the MPL or the GPL.
-*/
-
-/* 0x00 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
-/* 0x04 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
-/* 0x08 */ BT_NONXML, BT_S, BT_LF, BT_NONXML,
-/* 0x0C */ BT_NONXML, BT_CR, BT_NONXML, BT_NONXML,
-/* 0x10 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
-/* 0x14 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
-/* 0x18 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
-/* 0x1C */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
-/* 0x20 */ BT_S, BT_EXCL, BT_QUOT, BT_NUM,
-/* 0x24 */ BT_OTHER, BT_PERCNT, BT_AMP, BT_APOS,
-/* 0x28 */ BT_LPAR, BT_RPAR, BT_AST, BT_PLUS,
-/* 0x2C */ BT_COMMA, BT_MINUS, BT_NAME, BT_SOL,
-/* 0x30 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT,
-/* 0x34 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT,
-/* 0x38 */ BT_DIGIT, BT_DIGIT, BT_COLON, BT_SEMI,
-/* 0x3C */ BT_LT, BT_EQUALS, BT_GT, BT_QUEST,
-/* 0x40 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX,
-/* 0x44 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT,
-/* 0x48 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
-/* 0x4C */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
-/* 0x50 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
-/* 0x54 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
-/* 0x58 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_LSQB,
-/* 0x5C */ BT_OTHER, BT_RSQB, BT_OTHER, BT_NMSTRT,
-/* 0x60 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX,
-/* 0x64 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT,
-/* 0x68 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
-/* 0x6C */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
-/* 0x70 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
-/* 0x74 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
-/* 0x78 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_OTHER,
-/* 0x7C */ BT_VERBAR, BT_OTHER, BT_OTHER, BT_OTHER,
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/dllmain.c
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/dllmain.c 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/dllmain.c 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,40 +0,0 @@
-/*
-The contents of this file are subject to the Mozilla Public License
-Version 1.1 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998, 1999
-James Clark. All Rights Reserved.
-
-Contributor(s):
-
-Alternatively, the contents of this file may be used under the terms
-of the GNU General Public License (the "GPL"), in which case the
-provisions of the GPL are applicable instead of those above. If you
-wish to allow use of your version of this file only under the terms of
-the GPL and not to allow others to use your version of this file under
-the MPL, indicate your decision by deleting the provisions above and
-replace them with the notice and other provisions required by the
-GPL. If you do not delete the provisions above, a recipient may use
-your version of this file under either the MPL or the GPL.
-*/
-
-#define STRICT 1
-#define WIN32_LEAN_AND_MEAN 1
-
-#include <windows.h>
-
-BOOL WINAPI DllMain(HANDLE hInst, ULONG ul_reason_for_call, LPVOID lpReserved)
-{
- return TRUE;
-}
-
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/iasciitab.h
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/iasciitab.h 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/iasciitab.h 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,63 +0,0 @@
-/*
-The contents of this file are subject to the Mozilla Public License
-Version 1.1 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998, 1999
-James Clark. All Rights Reserved.
-
-Contributor(s):
-
-Alternatively, the contents of this file may be used under the terms
-of the GNU General Public License (the "GPL"), in which case the
-provisions of the GPL are applicable instead of those above. If you
-wish to allow use of your version of this file only under the terms of
-the GPL and not to allow others to use your version of this file under
-the MPL, indicate your decision by deleting the provisions above and
-replace them with the notice and other provisions required by the
-GPL. If you do not delete the provisions above, a recipient may use
-your version of this file under either the MPL or the GPL.
-*/
-
-/* Like asciitab.h, except that 0xD has code BT_S rather than BT_CR */
-/* 0x00 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
-/* 0x04 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
-/* 0x08 */ BT_NONXML, BT_S, BT_LF, BT_NONXML,
-/* 0x0C */ BT_NONXML, BT_S, BT_NONXML, BT_NONXML,
-/* 0x10 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
-/* 0x14 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
-/* 0x18 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
-/* 0x1C */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
-/* 0x20 */ BT_S, BT_EXCL, BT_QUOT, BT_NUM,
-/* 0x24 */ BT_OTHER, BT_PERCNT, BT_AMP, BT_APOS,
-/* 0x28 */ BT_LPAR, BT_RPAR, BT_AST, BT_PLUS,
-/* 0x2C */ BT_COMMA, BT_MINUS, BT_NAME, BT_SOL,
-/* 0x30 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT,
-/* 0x34 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT,
-/* 0x38 */ BT_DIGIT, BT_DIGIT, BT_COLON, BT_SEMI,
-/* 0x3C */ BT_LT, BT_EQUALS, BT_GT, BT_QUEST,
-/* 0x40 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX,
-/* 0x44 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT,
-/* 0x48 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
-/* 0x4C */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
-/* 0x50 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
-/* 0x54 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
-/* 0x58 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_LSQB,
-/* 0x5C */ BT_OTHER, BT_RSQB, BT_OTHER, BT_NMSTRT,
-/* 0x60 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX,
-/* 0x64 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT,
-/* 0x68 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
-/* 0x6C */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
-/* 0x70 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
-/* 0x74 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
-/* 0x78 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_OTHER,
-/* 0x7C */ BT_VERBAR, BT_OTHER, BT_OTHER, BT_OTHER,
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/latin1tab.h
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/latin1tab.h 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/latin1tab.h 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,62 +0,0 @@
-/*
-The contents of this file are subject to the Mozilla Public License
-Version 1.1 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998, 1999
-James Clark. All Rights Reserved.
-
-Contributor(s):
-
-Alternatively, the contents of this file may be used under the terms
-of the GNU General Public License (the "GPL"), in which case the
-provisions of the GPL are applicable instead of those above. If you
-wish to allow use of your version of this file only under the terms of
-the GPL and not to allow others to use your version of this file under
-the MPL, indicate your decision by deleting the provisions above and
-replace them with the notice and other provisions required by the
-GPL. If you do not delete the provisions above, a recipient may use
-your version of this file under either the MPL or the GPL.
-*/
-
-/* 0x80 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
-/* 0x84 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
-/* 0x88 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
-/* 0x8C */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
-/* 0x90 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
-/* 0x94 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
-/* 0x98 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
-/* 0x9C */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
-/* 0xA0 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
-/* 0xA4 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
-/* 0xA8 */ BT_OTHER, BT_OTHER, BT_NMSTRT, BT_OTHER,
-/* 0xAC */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
-/* 0xB0 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
-/* 0xB4 */ BT_OTHER, BT_NMSTRT, BT_OTHER, BT_NAME,
-/* 0xB8 */ BT_OTHER, BT_OTHER, BT_NMSTRT, BT_OTHER,
-/* 0xBC */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
-/* 0xC0 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
-/* 0xC4 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
-/* 0xC8 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
-/* 0xCC */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
-/* 0xD0 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
-/* 0xD4 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_OTHER,
-/* 0xD8 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
-/* 0xDC */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
-/* 0xE0 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
-/* 0xE4 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
-/* 0xE8 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
-/* 0xEC */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
-/* 0xF0 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
-/* 0xF4 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_OTHER,
-/* 0xF8 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
-/* 0xFC */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/makefile.win
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/makefile.win 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/makefile.win 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,38 +0,0 @@
-#!gmake
-#
-# The contents of this file are subject to the Netscape Public
-# License Version 1.1 (the "License"); you may not use this file
-# except in compliance with the License. You may obtain a copy of
-# the License at http://www.mozilla.org/NPL/
-#
-# Software distributed under the License is distributed on an "AS
-# IS" basis, WITHOUT WARRANTY OF ANY KIND, either express or
-# implied. See the License for the specific language governing
-# rights and limitations under the License.
-#
-# The Original Code is mozilla.org code.
-#
-# The Initial Developer of the Original Code is Netscape
-# Communications Corporation. Portions created by Netscape are
-# Copyright (C) 1998 Netscape Communications Corporation. All
-# Rights Reserved.
-#
-# Contributor(s):
-
-#
-
-DEPTH= ..\..
-
-CPPSRCS= \
- xmltok.c \
- xmlrole.c \
- $(NULL)
-
-CPP_OBJS= \
- .\$(OBJDIR)\xmltok.obj \
- .\$(OBJDIR)\xmlrole.obj \
- $(NULL)
-
-include <$(DEPTH)\config\rules.mak>
-
-install:: $(OBJDIR) $(OBJS)
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/nametab.h
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/nametab.h 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/nametab.h 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,150 +0,0 @@
-static const unsigned namingBitmap[] = {
-0x00000000, 0x00000000, 0x00000000, 0x00000000,
-0x00000000, 0x00000000, 0x00000000, 0x00000000,
-0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF,
-0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF,
-0x00000000, 0x04000000, 0x87FFFFFE, 0x07FFFFFE,
-0x00000000, 0x00000000, 0xFF7FFFFF, 0xFF7FFFFF,
-0xFFFFFFFF, 0x7FF3FFFF, 0xFFFFFDFE, 0x7FFFFFFF,
-0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFE00F, 0xFC31FFFF,
-0x00FFFFFF, 0x00000000, 0xFFFF0000, 0xFFFFFFFF,
-0xFFFFFFFF, 0xF80001FF, 0x00000003, 0x00000000,
-0x00000000, 0x00000000, 0x00000000, 0x00000000,
-0xFFFFD740, 0xFFFFFFFB, 0x547F7FFF, 0x000FFFFD,
-0xFFFFDFFE, 0xFFFFFFFF, 0xDFFEFFFF, 0xFFFFFFFF,
-0xFFFF0003, 0xFFFFFFFF, 0xFFFF199F, 0x033FCFFF,
-0x00000000, 0xFFFE0000, 0x027FFFFF, 0xFFFFFFFE,
-0x0000007F, 0x00000000, 0xFFFF0000, 0x000707FF,
-0x00000000, 0x07FFFFFE, 0x000007FE, 0xFFFE0000,
-0xFFFFFFFF, 0x7CFFFFFF, 0x002F7FFF, 0x00000060,
-0xFFFFFFE0, 0x23FFFFFF, 0xFF000000, 0x00000003,
-0xFFF99FE0, 0x03C5FDFF, 0xB0000000, 0x00030003,
-0xFFF987E0, 0x036DFDFF, 0x5E000000, 0x001C0000,
-0xFFFBAFE0, 0x23EDFDFF, 0x00000000, 0x00000001,
-0xFFF99FE0, 0x23CDFDFF, 0xB0000000, 0x00000003,
-0xD63DC7E0, 0x03BFC718, 0x00000000, 0x00000000,
-0xFFFDDFE0, 0x03EFFDFF, 0x00000000, 0x00000003,
-0xFFFDDFE0, 0x03EFFDFF, 0x40000000, 0x00000003,
-0xFFFDDFE0, 0x03FFFDFF, 0x00000000, 0x00000003,
-0x00000000, 0x00000000, 0x00000000, 0x00000000,
-0xFFFFFFFE, 0x000D7FFF, 0x0000003F, 0x00000000,
-0xFEF02596, 0x200D6CAE, 0x0000001F, 0x00000000,
-0x00000000, 0x00000000, 0xFFFFFEFF, 0x000003FF,
-0x00000000, 0x00000000, 0x00000000, 0x00000000,
-0x00000000, 0x00000000, 0x00000000, 0x00000000,
-0x00000000, 0xFFFFFFFF, 0xFFFF003F, 0x007FFFFF,
-0x0007DAED, 0x50000000, 0x82315001, 0x002C62AB,
-0x40000000, 0xF580C900, 0x00000007, 0x02010800,
-0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF,
-0x0FFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x03FFFFFF,
-0x3F3FFFFF, 0xFFFFFFFF, 0xAAFF3F3F, 0x3FFFFFFF,
-0xFFFFFFFF, 0x5FDFFFFF, 0x0FCF1FDC, 0x1FDC1FFF,
-0x00000000, 0x00004C40, 0x00000000, 0x00000000,
-0x00000007, 0x00000000, 0x00000000, 0x00000000,
-0x00000080, 0x000003FE, 0xFFFFFFFE, 0xFFFFFFFF,
-0x001FFFFF, 0xFFFFFFFE, 0xFFFFFFFF, 0x07FFFFFF,
-0xFFFFFFE0, 0x00001FFF, 0x00000000, 0x00000000,
-0x00000000, 0x00000000, 0x00000000, 0x00000000,
-0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF,
-0xFFFFFFFF, 0x0000003F, 0x00000000, 0x00000000,
-0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF,
-0xFFFFFFFF, 0x0000000F, 0x00000000, 0x00000000,
-0x00000000, 0x07FF6000, 0x87FFFFFE, 0x07FFFFFE,
-0x00000000, 0x00800000, 0xFF7FFFFF, 0xFF7FFFFF,
-0x00FFFFFF, 0x00000000, 0xFFFF0000, 0xFFFFFFFF,
-0xFFFFFFFF, 0xF80001FF, 0x00030003, 0x00000000,
-0xFFFFFFFF, 0xFFFFFFFF, 0x0000003F, 0x00000003,
-0xFFFFD7C0, 0xFFFFFFFB, 0x547F7FFF, 0x000FFFFD,
-0xFFFFDFFE, 0xFFFFFFFF, 0xDFFEFFFF, 0xFFFFFFFF,
-0xFFFF007B, 0xFFFFFFFF, 0xFFFF199F, 0x033FCFFF,
-0x00000000, 0xFFFE0000, 0x027FFFFF, 0xFFFFFFFE,
-0xFFFE007F, 0xBBFFFFFB, 0xFFFF0016, 0x000707FF,
-0x00000000, 0x07FFFFFE, 0x0007FFFF, 0xFFFF03FF,
-0xFFFFFFFF, 0x7CFFFFFF, 0xFFEF7FFF, 0x03FF3DFF,
-0xFFFFFFEE, 0xF3FFFFFF, 0xFF1E3FFF, 0x0000FFCF,
-0xFFF99FEE, 0xD3C5FDFF, 0xB080399F, 0x0003FFCF,
-0xFFF987E4, 0xD36DFDFF, 0x5E003987, 0x001FFFC0,
-0xFFFBAFEE, 0xF3EDFDFF, 0x00003BBF, 0x0000FFC1,
-0xFFF99FEE, 0xF3CDFDFF, 0xB0C0398F, 0x0000FFC3,
-0xD63DC7EC, 0xC3BFC718, 0x00803DC7, 0x0000FF80,
-0xFFFDDFEE, 0xC3EFFDFF, 0x00603DDF, 0x0000FFC3,
-0xFFFDDFEC, 0xC3EFFDFF, 0x40603DDF, 0x0000FFC3,
-0xFFFDDFEC, 0xC3FFFDFF, 0x00803DCF, 0x0000FFC3,
-0x00000000, 0x00000000, 0x00000000, 0x00000000,
-0xFFFFFFFE, 0x07FF7FFF, 0x03FF7FFF, 0x00000000,
-0xFEF02596, 0x3BFF6CAE, 0x03FF3F5F, 0x00000000,
-0x03000000, 0xC2A003FF, 0xFFFFFEFF, 0xFFFE03FF,
-0xFEBF0FDF, 0x02FE3FFF, 0x00000000, 0x00000000,
-0x00000000, 0x00000000, 0x00000000, 0x00000000,
-0x00000000, 0x00000000, 0x1FFF0000, 0x00000002,
-0x000000A0, 0x003EFFFE, 0xFFFFFFFE, 0xFFFFFFFF,
-0x661FFFFF, 0xFFFFFFFE, 0xFFFFFFFF, 0x77FFFFFF,
-};
-static const unsigned char nmstrtPages[] = {
-0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x00,
-0x00, 0x09, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
-0x10, 0x11, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x12, 0x13,
-0x00, 0x14, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x15, 0x16, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x17,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x18,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-};
-static const unsigned char namePages[] = {
-0x19, 0x03, 0x1A, 0x1B, 0x1C, 0x1D, 0x1E, 0x00,
-0x00, 0x1F, 0x20, 0x21, 0x22, 0x23, 0x24, 0x25,
-0x10, 0x11, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x12, 0x13,
-0x26, 0x14, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x27, 0x16, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x17,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x18,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-};
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/utf8tab.h
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/utf8tab.h 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/utf8tab.h 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,63 +0,0 @@
-/*
-The contents of this file are subject to the Mozilla Public License
-Version 1.1 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998, 1999
-James Clark. All Rights Reserved.
-
-Contributor(s):
-
-Alternatively, the contents of this file may be used under the terms
-of the GNU General Public License (the "GPL"), in which case the
-provisions of the GPL are applicable instead of those above. If you
-wish to allow use of your version of this file only under the terms of
-the GPL and not to allow others to use your version of this file under
-the MPL, indicate your decision by deleting the provisions above and
-replace them with the notice and other provisions required by the
-GPL. If you do not delete the provisions above, a recipient may use
-your version of this file under either the MPL or the GPL.
-*/
-
-
-/* 0x80 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
-/* 0x84 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
-/* 0x88 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
-/* 0x8C */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
-/* 0x90 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
-/* 0x94 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
-/* 0x98 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
-/* 0x9C */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
-/* 0xA0 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
-/* 0xA4 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
-/* 0xA8 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
-/* 0xAC */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
-/* 0xB0 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
-/* 0xB4 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
-/* 0xB8 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
-/* 0xBC */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
-/* 0xC0 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2,
-/* 0xC4 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2,
-/* 0xC8 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2,
-/* 0xCC */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2,
-/* 0xD0 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2,
-/* 0xD4 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2,
-/* 0xD8 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2,
-/* 0xDC */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2,
-/* 0xE0 */ BT_LEAD3, BT_LEAD3, BT_LEAD3, BT_LEAD3,
-/* 0xE4 */ BT_LEAD3, BT_LEAD3, BT_LEAD3, BT_LEAD3,
-/* 0xE8 */ BT_LEAD3, BT_LEAD3, BT_LEAD3, BT_LEAD3,
-/* 0xEC */ BT_LEAD3, BT_LEAD3, BT_LEAD3, BT_LEAD3,
-/* 0xF0 */ BT_LEAD4, BT_LEAD4, BT_LEAD4, BT_LEAD4,
-/* 0xF4 */ BT_LEAD4, BT_NONXML, BT_NONXML, BT_NONXML,
-/* 0xF8 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
-/* 0xFC */ BT_NONXML, BT_NONXML, BT_MALFORM, BT_MALFORM,
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/xmldef.h
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/xmldef.h 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/xmldef.h 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,78 +0,0 @@
-/*
-The contents of this file are subject to the Mozilla Public License
-Version 1.1 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998, 1999
-James Clark. All Rights Reserved.
-
-Contributor(s):
-
-Alternatively, the contents of this file may be used under the terms
-of the GNU General Public License (the "GPL"), in which case the
-provisions of the GPL are applicable instead of those above. If you
-wish to allow use of your version of this file only under the terms of
-the GPL and not to allow others to use your version of this file under
-the MPL, indicate your decision by deleting the provisions above and
-replace them with the notice and other provisions required by the
-GPL. If you do not delete the provisions above, a recipient may use
-your version of this file under either the MPL or the GPL.
-*/
-
-#include <string.h>
-
-#ifdef XML_WINLIB
-
-#define WIN32_LEAN_AND_MEAN
-#define STRICT
-#include <windows.h>
-
-#define malloc(x) HeapAlloc(GetProcessHeap(), 0, (x))
-#define calloc(x, y) HeapAlloc(GetProcessHeap(), HEAP_ZERO_MEMORY, (x)*(y))
-#define free(x) HeapFree(GetProcessHeap(), 0, (x))
-#define realloc(x, y) HeapReAlloc(GetProcessHeap(), 0, x, y)
-#define abort() /* as nothing */
-
-#else /* not XML_WINLIB */
-
-#include <stdlib.h>
-
-#endif /* not XML_WINLIB */
-
-/* This file can be used for any definitions needed in
-particular environments. */
-
-/***
- * Mozilla specific defines listed below
- */
-/*#ifdef MOZILLA_CLIENT
-
-#include "nspr.h"
-#define malloc(x) PR_Malloc((size_t)(x))
-#define realloc(x, y) PR_Realloc((x), (size_t)(y))
-#define calloc(x, y) PR_Calloc((x),(y))
-#define free(x) PR_Free(x)
-
-#if PR_BYTES_PER_INT != 4
-typedef PRInt32 int;
-#endif
-
-// Enable Unicode string processing in expat
-#define XML_UNICODE
-
-// Enable external paramter entity parsing in expat
-#ifndef XML_DTD
-#define XML_DTD 1
-#endif
-
-#endif
-*/
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/xmlrole.c
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/xmlrole.c 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/xmlrole.c 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,1265 +0,0 @@
-/*
-The contents of this file are subject to the Mozilla Public License
-Version 1.1 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998, 1999
-James Clark. All Rights Reserved.
-
-Contributor(s):
-
-Alternatively, the contents of this file may be used under the terms
-of the GNU General Public License (the "GPL"), in which case the
-provisions of the GPL are applicable instead of those above. If you
-wish to allow use of your version of this file only under the terms of
-the GPL and not to allow others to use your version of this file under
-the MPL, indicate your decision by deleting the provisions above and
-replace them with the notice and other provisions required by the
-GPL. If you do not delete the provisions above, a recipient may use
-your version of this file under either the MPL or the GPL.
-*/
-
-#include "xmldef.h"
-#include "xmlrole.h"
-
-/* Doesn't check:
-
- that ,| are not mixed in a model group
- content of literals
-
-*/
-
-#ifndef MIN_BYTES_PER_CHAR
-#define MIN_BYTES_PER_CHAR(enc) ((enc)->minBytesPerChar)
-#endif
-
-#ifdef XML_DTD
-#define setTopLevel(state) \
- ((state)->handler = ((state)->documentEntity \
- ? internalSubset \
- : externalSubset1))
-#else /* not XML_DTD */
-#define setTopLevel(state) ((state)->handler = internalSubset)
-#endif /* not XML_DTD */
-
-typedef int PROLOG_HANDLER(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc);
-
-static PROLOG_HANDLER
- prolog0, prolog1, prolog2,
- doctype0, doctype1, doctype2, doctype3, doctype4, doctype5,
- internalSubset,
- entity0, entity1, entity2, entity3, entity4, entity5, entity6,
- entity7, entity8, entity9,
- notation0, notation1, notation2, notation3, notation4,
- attlist0, attlist1, attlist2, attlist3, attlist4, attlist5, attlist6,
- attlist7, attlist8, attlist9,
- element0, element1, element2, element3, element4, element5, element6,
- element7,
-#ifdef XML_DTD
- externalSubset0, externalSubset1,
- condSect0, condSect1, condSect2,
-#endif /* XML_DTD */
- declClose,
- error;
-
-static
-int common(PROLOG_STATE *state, int tok);
-
-static
-int prolog0(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- state->handler = prolog1;
- return XML_ROLE_NONE;
- case XML_TOK_XML_DECL:
- state->handler = prolog1;
- return XML_ROLE_XML_DECL;
- case XML_TOK_PI:
- state->handler = prolog1;
- return XML_ROLE_NONE;
- case XML_TOK_COMMENT:
- state->handler = prolog1;
- case XML_TOK_BOM:
- return XML_ROLE_NONE;
- case XML_TOK_DECL_OPEN:
- if (!XmlNameMatchesAscii(enc,
- ptr + 2 * MIN_BYTES_PER_CHAR(enc),
- end,
- "DOCTYPE"))
- break;
- state->handler = doctype0;
- return XML_ROLE_NONE;
- case XML_TOK_INSTANCE_START:
- state->handler = error;
- return XML_ROLE_INSTANCE_START;
- }
- return common(state, tok);
-}
-
-static
-int prolog1(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_PI:
- case XML_TOK_COMMENT:
- case XML_TOK_BOM:
- return XML_ROLE_NONE;
- case XML_TOK_DECL_OPEN:
- if (!XmlNameMatchesAscii(enc,
- ptr + 2 * MIN_BYTES_PER_CHAR(enc),
- end,
- "DOCTYPE"))
- break;
- state->handler = doctype0;
- return XML_ROLE_NONE;
- case XML_TOK_INSTANCE_START:
- state->handler = error;
- return XML_ROLE_INSTANCE_START;
- }
- return common(state, tok);
-}
-
-static
-int prolog2(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_PI:
- case XML_TOK_COMMENT:
- return XML_ROLE_NONE;
- case XML_TOK_INSTANCE_START:
- state->handler = error;
- return XML_ROLE_INSTANCE_START;
- }
- return common(state, tok);
-}
-
-static
-int doctype0(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_NAME:
- case XML_TOK_PREFIXED_NAME:
- state->handler = doctype1;
- return XML_ROLE_DOCTYPE_NAME;
- }
- return common(state, tok);
-}
-
-static
-int doctype1(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_OPEN_BRACKET:
- state->handler = internalSubset;
- return XML_ROLE_NONE;
- case XML_TOK_DECL_CLOSE:
- state->handler = prolog2;
- return XML_ROLE_DOCTYPE_CLOSE;
- case XML_TOK_NAME:
- if (XmlNameMatchesAscii(enc, ptr, end, "SYSTEM")) {
- state->handler = doctype3;
- return XML_ROLE_NONE;
- }
- if (XmlNameMatchesAscii(enc, ptr, end, "PUBLIC")) {
- state->handler = doctype2;
- return XML_ROLE_NONE;
- }
- break;
- }
- return common(state, tok);
-}
-
-static
-int doctype2(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_LITERAL:
- state->handler = doctype3;
- return XML_ROLE_DOCTYPE_PUBLIC_ID;
- }
- return common(state, tok);
-}
-
-static
-int doctype3(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_LITERAL:
- state->handler = doctype4;
- return XML_ROLE_DOCTYPE_SYSTEM_ID;
- }
- return common(state, tok);
-}
-
-static
-int doctype4(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_OPEN_BRACKET:
- state->handler = internalSubset;
- return XML_ROLE_NONE;
- case XML_TOK_DECL_CLOSE:
- state->handler = prolog2;
- return XML_ROLE_DOCTYPE_CLOSE;
- }
- return common(state, tok);
-}
-
-static
-int doctype5(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_DECL_CLOSE:
- state->handler = prolog2;
- return XML_ROLE_DOCTYPE_CLOSE;
- }
- return common(state, tok);
-}
-
-static
-int internalSubset(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_DECL_OPEN:
- if (XmlNameMatchesAscii(enc,
- ptr + 2 * MIN_BYTES_PER_CHAR(enc),
- end,
- "ENTITY")) {
- state->handler = entity0;
- return XML_ROLE_NONE;
- }
- if (XmlNameMatchesAscii(enc,
- ptr + 2 * MIN_BYTES_PER_CHAR(enc),
- end,
- "ATTLIST")) {
- state->handler = attlist0;
- return XML_ROLE_NONE;
- }
- if (XmlNameMatchesAscii(enc,
- ptr + 2 * MIN_BYTES_PER_CHAR(enc),
- end,
- "ELEMENT")) {
- state->handler = element0;
- return XML_ROLE_NONE;
- }
- if (XmlNameMatchesAscii(enc,
- ptr + 2 * MIN_BYTES_PER_CHAR(enc),
- end,
- "NOTATION")) {
- state->handler = notation0;
- return XML_ROLE_NONE;
- }
- break;
- case XML_TOK_PI:
- case XML_TOK_COMMENT:
- return XML_ROLE_NONE;
- case XML_TOK_PARAM_ENTITY_REF:
- return XML_ROLE_PARAM_ENTITY_REF;
- case XML_TOK_CLOSE_BRACKET:
- state->handler = doctype5;
- return XML_ROLE_NONE;
- }
- return common(state, tok);
-}
-
-#ifdef XML_DTD
-
-static
-int externalSubset0(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- state->handler = externalSubset1;
- if (tok == XML_TOK_XML_DECL)
- return XML_ROLE_TEXT_DECL;
- return externalSubset1(state, tok, ptr, end, enc);
-}
-
-static
-int externalSubset1(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_COND_SECT_OPEN:
- state->handler = condSect0;
- return XML_ROLE_NONE;
- case XML_TOK_COND_SECT_CLOSE:
- if (state->includeLevel == 0)
- break;
- state->includeLevel -= 1;
- return XML_ROLE_NONE;
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_CLOSE_BRACKET:
- break;
- case XML_TOK_NONE:
- if (state->includeLevel)
- break;
- return XML_ROLE_NONE;
- default:
- return internalSubset(state, tok, ptr, end, enc);
- }
- return common(state, tok);
-}
-
-#endif /* XML_DTD */
-
-static
-int entity0(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_PERCENT:
- state->handler = entity1;
- return XML_ROLE_NONE;
- case XML_TOK_NAME:
- state->handler = entity2;
- return XML_ROLE_GENERAL_ENTITY_NAME;
- }
- return common(state, tok);
-}
-
-static
-int entity1(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_NAME:
- state->handler = entity7;
- return XML_ROLE_PARAM_ENTITY_NAME;
- }
- return common(state, tok);
-}
-
-static
-int entity2(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_NAME:
- if (XmlNameMatchesAscii(enc, ptr, end, "SYSTEM")) {
- state->handler = entity4;
- return XML_ROLE_NONE;
- }
- if (XmlNameMatchesAscii(enc, ptr, end, "PUBLIC")) {
- state->handler = entity3;
- return XML_ROLE_NONE;
- }
- break;
- case XML_TOK_LITERAL:
- state->handler = declClose;
- return XML_ROLE_ENTITY_VALUE;
- }
- return common(state, tok);
-}
-
-static
-int entity3(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_LITERAL:
- state->handler = entity4;
- return XML_ROLE_ENTITY_PUBLIC_ID;
- }
- return common(state, tok);
-}
-
-
-static
-int entity4(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_LITERAL:
- state->handler = entity5;
- return XML_ROLE_ENTITY_SYSTEM_ID;
- }
- return common(state, tok);
-}
-
-static
-int entity5(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_DECL_CLOSE:
- setTopLevel(state);
- return XML_ROLE_NONE;
- case XML_TOK_NAME:
- if (XmlNameMatchesAscii(enc, ptr, end, "NDATA")) {
- state->handler = entity6;
- return XML_ROLE_NONE;
- }
- break;
- }
- return common(state, tok);
-}
-
-static
-int entity6(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_NAME:
- state->handler = declClose;
- return XML_ROLE_ENTITY_NOTATION_NAME;
- }
- return common(state, tok);
-}
-
-static
-int entity7(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_NAME:
- if (XmlNameMatchesAscii(enc, ptr, end, "SYSTEM")) {
- state->handler = entity9;
- return XML_ROLE_NONE;
- }
- if (XmlNameMatchesAscii(enc, ptr, end, "PUBLIC")) {
- state->handler = entity8;
- return XML_ROLE_NONE;
- }
- break;
- case XML_TOK_LITERAL:
- state->handler = declClose;
- return XML_ROLE_ENTITY_VALUE;
- }
- return common(state, tok);
-}
-
-static
-int entity8(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_LITERAL:
- state->handler = entity9;
- return XML_ROLE_ENTITY_PUBLIC_ID;
- }
- return common(state, tok);
-}
-
-static
-int entity9(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_LITERAL:
- state->handler = declClose;
- return XML_ROLE_ENTITY_SYSTEM_ID;
- }
- return common(state, tok);
-}
-
-static
-int notation0(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_NAME:
- state->handler = notation1;
- return XML_ROLE_NOTATION_NAME;
- }
- return common(state, tok);
-}
-
-static
-int notation1(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_NAME:
- if (XmlNameMatchesAscii(enc, ptr, end, "SYSTEM")) {
- state->handler = notation3;
- return XML_ROLE_NONE;
- }
- if (XmlNameMatchesAscii(enc, ptr, end, "PUBLIC")) {
- state->handler = notation2;
- return XML_ROLE_NONE;
- }
- break;
- }
- return common(state, tok);
-}
-
-static
-int notation2(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_LITERAL:
- state->handler = notation4;
- return XML_ROLE_NOTATION_PUBLIC_ID;
- }
- return common(state, tok);
-}
-
-static
-int notation3(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_LITERAL:
- state->handler = declClose;
- return XML_ROLE_NOTATION_SYSTEM_ID;
- }
- return common(state, tok);
-}
-
-static
-int notation4(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_LITERAL:
- state->handler = declClose;
- return XML_ROLE_NOTATION_SYSTEM_ID;
- case XML_TOK_DECL_CLOSE:
- setTopLevel(state);
- return XML_ROLE_NOTATION_NO_SYSTEM_ID;
- }
- return common(state, tok);
-}
-
-static
-int attlist0(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_NAME:
- case XML_TOK_PREFIXED_NAME:
- state->handler = attlist1;
- return XML_ROLE_ATTLIST_ELEMENT_NAME;
- }
- return common(state, tok);
-}
-
-static
-int attlist1(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_DECL_CLOSE:
- setTopLevel(state);
- return XML_ROLE_NONE;
- case XML_TOK_NAME:
- case XML_TOK_PREFIXED_NAME:
- state->handler = attlist2;
- return XML_ROLE_ATTRIBUTE_NAME;
- }
- return common(state, tok);
-}
-
-static
-int attlist2(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_NAME:
- {
- static const char *types[] = {
- "CDATA",
- "ID",
- "IDREF",
- "IDREFS",
- "ENTITY",
- "ENTITIES",
- "NMTOKEN",
- "NMTOKENS",
- };
- int i;
- for (i = 0; i < (int)(sizeof(types)/sizeof(types[0])); i++)
- if (XmlNameMatchesAscii(enc, ptr, end, types[i])) {
- state->handler = attlist8;
- return XML_ROLE_ATTRIBUTE_TYPE_CDATA + i;
- }
- }
- if (XmlNameMatchesAscii(enc, ptr, end, "NOTATION")) {
- state->handler = attlist5;
- return XML_ROLE_NONE;
- }
- break;
- case XML_TOK_OPEN_PAREN:
- state->handler = attlist3;
- return XML_ROLE_NONE;
- }
- return common(state, tok);
-}
-
-static
-int attlist3(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_NMTOKEN:
- case XML_TOK_NAME:
- case XML_TOK_PREFIXED_NAME:
- state->handler = attlist4;
- return XML_ROLE_ATTRIBUTE_ENUM_VALUE;
- }
- return common(state, tok);
-}
-
-static
-int attlist4(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_CLOSE_PAREN:
- state->handler = attlist8;
- return XML_ROLE_NONE;
- case XML_TOK_OR:
- state->handler = attlist3;
- return XML_ROLE_NONE;
- }
- return common(state, tok);
-}
-
-static
-int attlist5(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_OPEN_PAREN:
- state->handler = attlist6;
- return XML_ROLE_NONE;
- }
- return common(state, tok);
-}
-
-
-static
-int attlist6(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_NAME:
- state->handler = attlist7;
- return XML_ROLE_ATTRIBUTE_NOTATION_VALUE;
- }
- return common(state, tok);
-}
-
-static
-int attlist7(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_CLOSE_PAREN:
- state->handler = attlist8;
- return XML_ROLE_NONE;
- case XML_TOK_OR:
- state->handler = attlist6;
- return XML_ROLE_NONE;
- }
- return common(state, tok);
-}
-
-/* default value */
-static
-int attlist8(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_POUND_NAME:
- if (XmlNameMatchesAscii(enc,
- ptr + MIN_BYTES_PER_CHAR(enc),
- end,
- "IMPLIED")) {
- state->handler = attlist1;
- return XML_ROLE_IMPLIED_ATTRIBUTE_VALUE;
- }
- if (XmlNameMatchesAscii(enc,
- ptr + MIN_BYTES_PER_CHAR(enc),
- end,
- "REQUIRED")) {
- state->handler = attlist1;
- return XML_ROLE_REQUIRED_ATTRIBUTE_VALUE;
- }
- if (XmlNameMatchesAscii(enc,
- ptr + MIN_BYTES_PER_CHAR(enc),
- end,
- "FIXED")) {
- state->handler = attlist9;
- return XML_ROLE_NONE;
- }
- break;
- case XML_TOK_LITERAL:
- state->handler = attlist1;
- return XML_ROLE_DEFAULT_ATTRIBUTE_VALUE;
- }
- return common(state, tok);
-}
-
-static
-int attlist9(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_LITERAL:
- state->handler = attlist1;
- return XML_ROLE_FIXED_ATTRIBUTE_VALUE;
- }
- return common(state, tok);
-}
-
-static
-int element0(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_NAME:
- case XML_TOK_PREFIXED_NAME:
- state->handler = element1;
- return XML_ROLE_ELEMENT_NAME;
- }
- return common(state, tok);
-}
-
-static
-int element1(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_NAME:
- if (XmlNameMatchesAscii(enc, ptr, end, "EMPTY")) {
- state->handler = declClose;
- return XML_ROLE_CONTENT_EMPTY;
- }
- if (XmlNameMatchesAscii(enc, ptr, end, "ANY")) {
- state->handler = declClose;
- return XML_ROLE_CONTENT_ANY;
- }
- break;
- case XML_TOK_OPEN_PAREN:
- state->handler = element2;
- state->level = 1;
- return XML_ROLE_GROUP_OPEN;
- }
- return common(state, tok);
-}
-
-static
-int element2(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_POUND_NAME:
- if (XmlNameMatchesAscii(enc,
- ptr + MIN_BYTES_PER_CHAR(enc),
- end,
- "PCDATA")) {
- state->handler = element3;
- return XML_ROLE_CONTENT_PCDATA;
- }
- break;
- case XML_TOK_OPEN_PAREN:
- state->level = 2;
- state->handler = element6;
- return XML_ROLE_GROUP_OPEN;
- case XML_TOK_NAME:
- case XML_TOK_PREFIXED_NAME:
- state->handler = element7;
- return XML_ROLE_CONTENT_ELEMENT;
- case XML_TOK_NAME_QUESTION:
- state->handler = element7;
- return XML_ROLE_CONTENT_ELEMENT_OPT;
- case XML_TOK_NAME_ASTERISK:
- state->handler = element7;
- return XML_ROLE_CONTENT_ELEMENT_REP;
- case XML_TOK_NAME_PLUS:
- state->handler = element7;
- return XML_ROLE_CONTENT_ELEMENT_PLUS;
- }
- return common(state, tok);
-}
-
-static
-int element3(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_CLOSE_PAREN:
- case XML_TOK_CLOSE_PAREN_ASTERISK:
- state->handler = declClose;
- return XML_ROLE_GROUP_CLOSE_REP;
- case XML_TOK_OR:
- state->handler = element4;
- return XML_ROLE_NONE;
- }
- return common(state, tok);
-}
-
-static
-int element4(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_NAME:
- case XML_TOK_PREFIXED_NAME:
- state->handler = element5;
- return XML_ROLE_CONTENT_ELEMENT;
- }
- return common(state, tok);
-}
-
-static
-int element5(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_CLOSE_PAREN_ASTERISK:
- state->handler = declClose;
- return XML_ROLE_GROUP_CLOSE_REP;
- case XML_TOK_OR:
- state->handler = element4;
- return XML_ROLE_NONE;
- }
- return common(state, tok);
-}
-
-static
-int element6(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_OPEN_PAREN:
- state->level += 1;
- return XML_ROLE_GROUP_OPEN;
- case XML_TOK_NAME:
- case XML_TOK_PREFIXED_NAME:
- state->handler = element7;
- return XML_ROLE_CONTENT_ELEMENT;
- case XML_TOK_NAME_QUESTION:
- state->handler = element7;
- return XML_ROLE_CONTENT_ELEMENT_OPT;
- case XML_TOK_NAME_ASTERISK:
- state->handler = element7;
- return XML_ROLE_CONTENT_ELEMENT_REP;
- case XML_TOK_NAME_PLUS:
- state->handler = element7;
- return XML_ROLE_CONTENT_ELEMENT_PLUS;
- }
- return common(state, tok);
-}
-
-static
-int element7(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_CLOSE_PAREN:
- state->level -= 1;
- if (state->level == 0)
- state->handler = declClose;
- return XML_ROLE_GROUP_CLOSE;
- case XML_TOK_CLOSE_PAREN_ASTERISK:
- state->level -= 1;
- if (state->level == 0)
- state->handler = declClose;
- return XML_ROLE_GROUP_CLOSE_REP;
- case XML_TOK_CLOSE_PAREN_QUESTION:
- state->level -= 1;
- if (state->level == 0)
- state->handler = declClose;
- return XML_ROLE_GROUP_CLOSE_OPT;
- case XML_TOK_CLOSE_PAREN_PLUS:
- state->level -= 1;
- if (state->level == 0)
- state->handler = declClose;
- return XML_ROLE_GROUP_CLOSE_PLUS;
- case XML_TOK_COMMA:
- state->handler = element6;
- return XML_ROLE_GROUP_SEQUENCE;
- case XML_TOK_OR:
- state->handler = element6;
- return XML_ROLE_GROUP_CHOICE;
- }
- return common(state, tok);
-}
-
-#ifdef XML_DTD
-
-static
-int condSect0(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_NAME:
- if (XmlNameMatchesAscii(enc, ptr, end, "INCLUDE")) {
- state->handler = condSect1;
- return XML_ROLE_NONE;
- }
- if (XmlNameMatchesAscii(enc, ptr, end, "IGNORE")) {
- state->handler = condSect2;
- return XML_ROLE_NONE;
- }
- break;
- }
- return common(state, tok);
-}
-
-static
-int condSect1(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_OPEN_BRACKET:
- state->handler = externalSubset1;
- state->includeLevel += 1;
- return XML_ROLE_NONE;
- }
- return common(state, tok);
-}
-
-static
-int condSect2(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_OPEN_BRACKET:
- state->handler = externalSubset1;
- return XML_ROLE_IGNORE_SECT;
- }
- return common(state, tok);
-}
-
-#endif /* XML_DTD */
-
-static
-int declClose(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_PROLOG_S:
- return XML_ROLE_NONE;
- case XML_TOK_DECL_CLOSE:
- setTopLevel(state);
- return XML_ROLE_NONE;
- }
- return common(state, tok);
-}
-
-#if 0
-
-static
-int ignore(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- switch (tok) {
- case XML_TOK_DECL_CLOSE:
- state->handler = internalSubset;
- return 0;
- default:
- return XML_ROLE_NONE;
- }
- return common(state, tok);
-}
-#endif
-
-static
-int error(PROLOG_STATE *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc)
-{
- return XML_ROLE_NONE;
-}
-
-static
-int common(PROLOG_STATE *state, int tok)
-{
-#ifdef XML_DTD
- if (!state->documentEntity && tok == XML_TOK_PARAM_ENTITY_REF)
- return XML_ROLE_INNER_PARAM_ENTITY_REF;
-#endif
- state->handler = error;
- return XML_ROLE_ERROR;
-}
-
-void XmlPrologStateInit(PROLOG_STATE *state)
-{
- state->handler = prolog0;
-#ifdef XML_DTD
- state->documentEntity = 1;
- state->includeLevel = 0;
-#endif /* XML_DTD */
-}
-
-#ifdef XML_DTD
-
-void XmlPrologStateInitExternalEntity(PROLOG_STATE *state)
-{
- state->handler = externalSubset0;
- state->documentEntity = 0;
- state->includeLevel = 0;
-}
-
-#endif /* XML_DTD */
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/xmlrole.h
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/xmlrole.h 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/xmlrole.h 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,123 +0,0 @@
-/*
-The contents of this file are subject to the Mozilla Public License
-Version 1.1 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998, 1999
-James Clark. All Rights Reserved.
-
-Contributor(s):
-
-Alternatively, the contents of this file may be used under the terms
-of the GNU General Public License (the "GPL"), in which case the
-provisions of the GPL are applicable instead of those above. If you
-wish to allow use of your version of this file only under the terms of
-the GPL and not to allow others to use your version of this file under
-the MPL, indicate your decision by deleting the provisions above and
-replace them with the notice and other provisions required by the
-GPL. If you do not delete the provisions above, a recipient may use
-your version of this file under either the MPL or the GPL.
-*/
-
-#ifndef XmlRole_INCLUDED
-#define XmlRole_INCLUDED 1
-
-#include "xmltok.h"
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-enum {
- XML_ROLE_ERROR = -1,
- XML_ROLE_NONE = 0,
- XML_ROLE_XML_DECL,
- XML_ROLE_INSTANCE_START,
- XML_ROLE_DOCTYPE_NAME,
- XML_ROLE_DOCTYPE_SYSTEM_ID,
- XML_ROLE_DOCTYPE_PUBLIC_ID,
- XML_ROLE_DOCTYPE_CLOSE,
- XML_ROLE_GENERAL_ENTITY_NAME,
- XML_ROLE_PARAM_ENTITY_NAME,
- XML_ROLE_ENTITY_VALUE,
- XML_ROLE_ENTITY_SYSTEM_ID,
- XML_ROLE_ENTITY_PUBLIC_ID,
- XML_ROLE_ENTITY_NOTATION_NAME,
- XML_ROLE_NOTATION_NAME,
- XML_ROLE_NOTATION_SYSTEM_ID,
- XML_ROLE_NOTATION_NO_SYSTEM_ID,
- XML_ROLE_NOTATION_PUBLIC_ID,
- XML_ROLE_ATTRIBUTE_NAME,
- XML_ROLE_ATTRIBUTE_TYPE_CDATA,
- XML_ROLE_ATTRIBUTE_TYPE_ID,
- XML_ROLE_ATTRIBUTE_TYPE_IDREF,
- XML_ROLE_ATTRIBUTE_TYPE_IDREFS,
- XML_ROLE_ATTRIBUTE_TYPE_ENTITY,
- XML_ROLE_ATTRIBUTE_TYPE_ENTITIES,
- XML_ROLE_ATTRIBUTE_TYPE_NMTOKEN,
- XML_ROLE_ATTRIBUTE_TYPE_NMTOKENS,
- XML_ROLE_ATTRIBUTE_ENUM_VALUE,
- XML_ROLE_ATTRIBUTE_NOTATION_VALUE,
- XML_ROLE_ATTLIST_ELEMENT_NAME,
- XML_ROLE_IMPLIED_ATTRIBUTE_VALUE,
- XML_ROLE_REQUIRED_ATTRIBUTE_VALUE,
- XML_ROLE_DEFAULT_ATTRIBUTE_VALUE,
- XML_ROLE_FIXED_ATTRIBUTE_VALUE,
- XML_ROLE_ELEMENT_NAME,
- XML_ROLE_CONTENT_ANY,
- XML_ROLE_CONTENT_EMPTY,
- XML_ROLE_CONTENT_PCDATA,
- XML_ROLE_GROUP_OPEN,
- XML_ROLE_GROUP_CLOSE,
- XML_ROLE_GROUP_CLOSE_REP,
- XML_ROLE_GROUP_CLOSE_OPT,
- XML_ROLE_GROUP_CLOSE_PLUS,
- XML_ROLE_GROUP_CHOICE,
- XML_ROLE_GROUP_SEQUENCE,
- XML_ROLE_CONTENT_ELEMENT,
- XML_ROLE_CONTENT_ELEMENT_REP,
- XML_ROLE_CONTENT_ELEMENT_OPT,
- XML_ROLE_CONTENT_ELEMENT_PLUS,
-#ifdef XML_DTD
- XML_ROLE_TEXT_DECL,
- XML_ROLE_IGNORE_SECT,
- XML_ROLE_INNER_PARAM_ENTITY_REF,
-#endif /* XML_DTD */
- XML_ROLE_PARAM_ENTITY_REF
-};
-
-typedef struct prolog_state {
- int (*handler)(struct prolog_state *state,
- int tok,
- const char *ptr,
- const char *end,
- const ENCODING *enc);
- unsigned level;
-#ifdef XML_DTD
- unsigned includeLevel;
- int documentEntity;
-#endif /* XML_DTD */
-} PROLOG_STATE;
-
-void XMLTOKAPI XmlPrologStateInit(PROLOG_STATE *);
-#ifdef XML_DTD
-void XMLTOKAPI XmlPrologStateInitExternalEntity(PROLOG_STATE *);
-#endif /* XML_DTD */
-
-#define XmlTokenRole(state, tok, ptr, end, enc) \
- (((state)->handler)(state, tok, ptr, end, enc))
-
-#ifdef __cplusplus
-}
-#endif
-
-#endif /* not XmlRole_INCLUDED */
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/xmltok.c
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/xmltok.c 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/xmltok.c 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,1542 +0,0 @@
-/*
-The contents of this file are subject to the Mozilla Public License
-Version 1.1 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998, 1999
-James Clark. All Rights Reserved.
-
-Contributor(s):
-
-Alternatively, the contents of this file may be used under the terms
-of the GNU General Public License (the "GPL"), in which case the
-provisions of the GPL are applicable instead of those above. If you
-wish to allow use of your version of this file only under the terms of
-the GPL and not to allow others to use your version of this file under
-the MPL, indicate your decision by deleting the provisions above and
-replace them with the notice and other provisions required by the
-GPL. If you do not delete the provisions above, a recipient may use
-your version of this file under either the MPL or the GPL.
-*/
-
-#include "xmldef.h"
-#include "xmltok.h"
-#include "nametab.h"
-
-#ifdef XML_DTD
-#define IGNORE_SECTION_TOK_VTABLE , PREFIX(ignoreSectionTok)
-#else
-#define IGNORE_SECTION_TOK_VTABLE /* as nothing */
-#endif
-
-#define VTABLE1 \
- { PREFIX(prologTok), PREFIX(contentTok), \
- PREFIX(cdataSectionTok) IGNORE_SECTION_TOK_VTABLE }, \
- { PREFIX(attributeValueTok), PREFIX(entityValueTok) }, \
- PREFIX(sameName), \
- PREFIX(nameMatchesAscii), \
- PREFIX(nameLength), \
- PREFIX(skipS), \
- PREFIX(getAtts), \
- PREFIX(charRefNumber), \
- PREFIX(predefinedEntityName), \
- PREFIX(updatePosition), \
- PREFIX(isPublicId)
-
-#define VTABLE VTABLE1, PREFIX(toUtf8), PREFIX(toUtf16)
-
-#define UCS2_GET_NAMING(pages, hi, lo) \
- (namingBitmap[(pages[hi] << 3) + ((lo) >> 5)] & (1 << ((lo) & 0x1F)))
-
-/* A 2 byte UTF-8 representation splits the characters 11 bits
-between the bottom 5 and 6 bits of the bytes.
-We need 8 bits to index into pages, 3 bits to add to that index and
-5 bits to generate the mask. */
-#define UTF8_GET_NAMING2(pages, byte) \
- (namingBitmap[((pages)[(((byte)[0]) >> 2) & 7] << 3) \
- + ((((byte)[0]) & 3) << 1) \
- + ((((byte)[1]) >> 5) & 1)] \
- & (1 << (((byte)[1]) & 0x1F)))
-
-/* A 3 byte UTF-8 representation splits the characters 16 bits
-between the bottom 4, 6 and 6 bits of the bytes.
-We need 8 bits to index into pages, 3 bits to add to that index and
-5 bits to generate the mask. */
-#define UTF8_GET_NAMING3(pages, byte) \
- (namingBitmap[((pages)[((((byte)[0]) & 0xF) << 4) \
- + ((((byte)[1]) >> 2) & 0xF)] \
- << 3) \
- + ((((byte)[1]) & 3) << 1) \
- + ((((byte)[2]) >> 5) & 1)] \
- & (1 << (((byte)[2]) & 0x1F)))
-
-#define UTF8_GET_NAMING(pages, p, n) \
- ((n) == 2 \
- ? UTF8_GET_NAMING2(pages, (const unsigned char *)(p)) \
- : ((n) == 3 \
- ? UTF8_GET_NAMING3(pages, (const unsigned char *)(p)) \
- : 0))
-
-#define UTF8_INVALID3(p) \
- ((*p) == 0xED \
- ? (((p)[1] & 0x20) != 0) \
- : ((*p) == 0xEF \
- ? ((p)[1] == 0xBF && ((p)[2] == 0xBF || (p)[2] == 0xBE)) \
- : 0))
-
-#define UTF8_INVALID4(p) ((*p) == 0xF4 && ((p)[1] & 0x30) != 0)
-
-static
-int isNever(const ENCODING *enc, const char *p)
-{
- return 0;
-}
-
-static
-int utf8_isName2(const ENCODING *enc, const char *p)
-{
- return UTF8_GET_NAMING2(namePages, (const unsigned char *)p);
-}
-
-static
-int utf8_isName3(const ENCODING *enc, const char *p)
-{
- return UTF8_GET_NAMING3(namePages, (const unsigned char *)p);
-}
-
-#define utf8_isName4 isNever
-
-static
-int utf8_isNmstrt2(const ENCODING *enc, const char *p)
-{
- return UTF8_GET_NAMING2(nmstrtPages, (const unsigned char *)p);
-}
-
-static
-int utf8_isNmstrt3(const ENCODING *enc, const char *p)
-{
- return UTF8_GET_NAMING3(nmstrtPages, (const unsigned char *)p);
-}
-
-#define utf8_isNmstrt4 isNever
-
-#define utf8_isInvalid2 isNever
-
-static
-int utf8_isInvalid3(const ENCODING *enc, const char *p)
-{
- return UTF8_INVALID3((const unsigned char *)p);
-}
-
-static
-int utf8_isInvalid4(const ENCODING *enc, const char *p)
-{
- return UTF8_INVALID4((const unsigned char *)p);
-}
-
-struct normal_encoding {
- ENCODING enc;
- unsigned char type[256];
-#ifdef XML_MIN_SIZE
- int (*byteType)(const ENCODING *, const char *);
- int (*isNameMin)(const ENCODING *, const char *);
- int (*isNmstrtMin)(const ENCODING *, const char *);
- int (*byteToAscii)(const ENCODING *, const char *);
- int (*charMatches)(const ENCODING *, const char *, int);
-#endif /* XML_MIN_SIZE */
- int (*isName2)(const ENCODING *, const char *);
- int (*isName3)(const ENCODING *, const char *);
- int (*isName4)(const ENCODING *, const char *);
- int (*isNmstrt2)(const ENCODING *, const char *);
- int (*isNmstrt3)(const ENCODING *, const char *);
- int (*isNmstrt4)(const ENCODING *, const char *);
- int (*isInvalid2)(const ENCODING *, const char *);
- int (*isInvalid3)(const ENCODING *, const char *);
- int (*isInvalid4)(const ENCODING *, const char *);
-};
-
-#ifdef XML_MIN_SIZE
-
-#define STANDARD_VTABLE(E) \
- E ## byteType, \
- E ## isNameMin, \
- E ## isNmstrtMin, \
- E ## byteToAscii, \
- E ## charMatches,
-
-#else
-
-#define STANDARD_VTABLE(E) /* as nothing */
-
-#endif
-
-#define NORMAL_VTABLE(E) \
- E ## isName2, \
- E ## isName3, \
- E ## isName4, \
- E ## isNmstrt2, \
- E ## isNmstrt3, \
- E ## isNmstrt4, \
- E ## isInvalid2, \
- E ## isInvalid3, \
- E ## isInvalid4
-
-static int checkCharRefNumber(int);
-
-#include "xmltok_impl.h"
-
-#ifdef XML_MIN_SIZE
-#define sb_isNameMin isNever
-#define sb_isNmstrtMin isNever
-#endif
-
-#ifdef XML_MIN_SIZE
-#define MINBPC(enc) ((enc)->minBytesPerChar)
-#else
-/* minimum bytes per character */
-#define MINBPC(enc) 1
-#endif
-
-#define SB_BYTE_TYPE(enc, p) \
- (((struct normal_encoding *)(enc))->type[(unsigned char)*(p)])
-
-#ifdef XML_MIN_SIZE
-static
-int sb_byteType(const ENCODING *enc, const char *p)
-{
- return SB_BYTE_TYPE(enc, p);
-}
-#define BYTE_TYPE(enc, p) \
- (((const struct normal_encoding *)(enc))->byteType(enc, p))
-#else
-#define BYTE_TYPE(enc, p) SB_BYTE_TYPE(enc, p)
-#endif
-
-#ifdef XML_MIN_SIZE
-#define BYTE_TO_ASCII(enc, p) \
- (((const struct normal_encoding *)(enc))->byteToAscii(enc, p))
-static
-int sb_byteToAscii(const ENCODING *enc, const char *p)
-{
- return *p;
-}
-#else
-#define BYTE_TO_ASCII(enc, p) (*p)
-#endif
-
-#define IS_NAME_CHAR(enc, p, n) \
- (((const struct normal_encoding *)(enc))->isName ## n(enc, p))
-#define IS_NMSTRT_CHAR(enc, p, n) \
- (((const struct normal_encoding *)(enc))->isNmstrt ## n(enc, p))
-#define IS_INVALID_CHAR(enc, p, n) \
- (((const struct normal_encoding *)(enc))->isInvalid ## n(enc, p))
-
-#ifdef XML_MIN_SIZE
-#define IS_NAME_CHAR_MINBPC(enc, p) \
- (((const struct normal_encoding *)(enc))->isNameMin(enc, p))
-#define IS_NMSTRT_CHAR_MINBPC(enc, p) \
- (((const struct normal_encoding *)(enc))->isNmstrtMin(enc, p))
-#else
-#define IS_NAME_CHAR_MINBPC(enc, p) (0)
-#define IS_NMSTRT_CHAR_MINBPC(enc, p) (0)
-#endif
-
-#ifdef XML_MIN_SIZE
-#define CHAR_MATCHES(enc, p, c) \
- (((const struct normal_encoding *)(enc))->charMatches(enc, p, c))
-static
-int sb_charMatches(const ENCODING *enc, const char *p, int c)
-{
- return *p == c;
-}
-#else
-/* c is an ASCII character */
-#define CHAR_MATCHES(enc, p, c) (*(p) == c)
-#endif
-
-#define PREFIX(ident) normal_ ## ident
-#include "xmltok_impl.c"
-
-#undef MINBPC
-#undef BYTE_TYPE
-#undef BYTE_TO_ASCII
-#undef CHAR_MATCHES
-#undef IS_NAME_CHAR
-#undef IS_NAME_CHAR_MINBPC
-#undef IS_NMSTRT_CHAR
-#undef IS_NMSTRT_CHAR_MINBPC
-#undef IS_INVALID_CHAR
-
-enum { /* UTF8_cvalN is value of masked first byte of N byte sequence */
- UTF8_cval1 = 0x00,
- UTF8_cval2 = 0xc0,
- UTF8_cval3 = 0xe0,
- UTF8_cval4 = 0xf0
-};
-
-static
-void utf8_toUtf8(const ENCODING *enc,
- const char **fromP, const char *fromLim,
- char **toP, const char *toLim)
-{
- char *to;
- const char *from;
- if (fromLim - *fromP > toLim - *toP) {
- /* Avoid copying partial characters. */
- for (fromLim = *fromP + (toLim - *toP); fromLim > *fromP; fromLim--)
- if (((unsigned char)fromLim[-1] & 0xc0) != 0x80)
- break;
- }
- for (to = *toP, from = *fromP; from != fromLim; from++, to++)
- *to = *from;
- *fromP = from;
- *toP = to;
-}
-
-static
-void utf8_toUtf16(const ENCODING *enc,
- const char **fromP, const char *fromLim,
- unsigned short **toP, const unsigned short *toLim)
-{
- unsigned short *to = *toP;
- const char *from = *fromP;
- while (from != fromLim && to != toLim) {
- switch (((struct normal_encoding *)enc)->type[(unsigned char)*from]) {
- case BT_LEAD2:
- *to++ = ((from[0] & 0x1f) << 6) | (from[1] & 0x3f);
- from += 2;
- break;
- case BT_LEAD3:
- *to++ = ((from[0] & 0xf) << 12) | ((from[1] & 0x3f) << 6) | (from[2] & 0x3f);
- from += 3;
- break;
- case BT_LEAD4:
- {
- unsigned long n;
- if (to + 1 == toLim)
- break;
- n = ((from[0] & 0x7) << 18) | ((from[1] & 0x3f) << 12) | ((from[2] & 0x3f) << 6) | (from[3] & 0x3f);
- n -= 0x10000;
- to[0] = (unsigned short)((n >> 10) | 0xD800);
- to[1] = (unsigned short)((n & 0x3FF) | 0xDC00);
- to += 2;
- from += 4;
- }
- break;
- default:
- *to++ = *from++;
- break;
- }
- }
- *fromP = from;
- *toP = to;
-}
-
-#ifdef XML_NS
-static const struct normal_encoding utf8_encoding_ns = {
- { VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0 },
- {
-#include "asciitab.h"
-#include "utf8tab.h"
- },
- STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_)
-};
-#endif
-
-static const struct normal_encoding utf8_encoding = {
- { VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0 },
- {
-#define BT_COLON BT_NMSTRT
-#include "asciitab.h"
-#undef BT_COLON
-#include "utf8tab.h"
- },
- STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_)
-};
-
-#ifdef XML_NS
-
-static const struct normal_encoding internal_utf8_encoding_ns = {
- { VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0 },
- {
-#include "iasciitab.h"
-#include "utf8tab.h"
- },
- STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_)
-};
-
-#endif
-
-static const struct normal_encoding internal_utf8_encoding = {
- { VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0 },
- {
-#define BT_COLON BT_NMSTRT
-#include "iasciitab.h"
-#undef BT_COLON
-#include "utf8tab.h"
- },
- STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_)
-};
-
-static
-void latin1_toUtf8(const ENCODING *enc,
- const char **fromP, const char *fromLim,
- char **toP, const char *toLim)
-{
- for (;;) {
- unsigned char c;
- if (*fromP == fromLim)
- break;
- c = (unsigned char)**fromP;
- if (c & 0x80) {
- if (toLim - *toP < 2)
- break;
- *(*toP)++ = ((c >> 6) | UTF8_cval2);
- *(*toP)++ = ((c & 0x3f) | 0x80);
- (*fromP)++;
- }
- else {
- if (*toP == toLim)
- break;
- *(*toP)++ = *(*fromP)++;
- }
- }
-}
-
-static
-void latin1_toUtf16(const ENCODING *enc,
- const char **fromP, const char *fromLim,
- unsigned short **toP, const unsigned short *toLim)
-{
- while (*fromP != fromLim && *toP != toLim)
- *(*toP)++ = (unsigned char)*(*fromP)++;
-}
-
-#ifdef XML_NS
-
-static const struct normal_encoding latin1_encoding_ns = {
- { VTABLE1, latin1_toUtf8, latin1_toUtf16, 1, 0, 0 },
- {
-#include "asciitab.h"
-#include "latin1tab.h"
- },
- STANDARD_VTABLE(sb_)
-};
-
-#endif
-
-static const struct normal_encoding latin1_encoding = {
- { VTABLE1, latin1_toUtf8, latin1_toUtf16, 1, 0, 0 },
- {
-#define BT_COLON BT_NMSTRT
-#include "asciitab.h"
-#undef BT_COLON
-#include "latin1tab.h"
- },
- STANDARD_VTABLE(sb_)
-};
-
-static
-void ascii_toUtf8(const ENCODING *enc,
- const char **fromP, const char *fromLim,
- char **toP, const char *toLim)
-{
- while (*fromP != fromLim && *toP != toLim)
- *(*toP)++ = *(*fromP)++;
-}
-
-#ifdef XML_NS
-
-static const struct normal_encoding ascii_encoding_ns = {
- { VTABLE1, ascii_toUtf8, latin1_toUtf16, 1, 1, 0 },
- {
-#include "asciitab.h"
-/* BT_NONXML == 0 */
- },
- STANDARD_VTABLE(sb_)
-};
-
-#endif
-
-static const struct normal_encoding ascii_encoding = {
- { VTABLE1, ascii_toUtf8, latin1_toUtf16, 1, 1, 0 },
- {
-#define BT_COLON BT_NMSTRT
-#include "asciitab.h"
-#undef BT_COLON
-/* BT_NONXML == 0 */
- },
- STANDARD_VTABLE(sb_)
-};
-
-static int unicode_byte_type(char hi, char lo)
-{
- switch ((unsigned char)hi) {
- case 0xD8: case 0xD9: case 0xDA: case 0xDB:
- return BT_LEAD4;
- case 0xDC: case 0xDD: case 0xDE: case 0xDF:
- return BT_TRAIL;
- case 0xFF:
- switch ((unsigned char)lo) {
- case 0xFF:
- case 0xFE:
- return BT_NONXML;
- }
- break;
- }
- return BT_NONASCII;
-}
-
-#define DEFINE_UTF16_TO_UTF8(E) \
-static \
-void E ## toUtf8(const ENCODING *enc, \
- const char **fromP, const char *fromLim, \
- char **toP, const char *toLim) \
-{ \
- const char *from; \
- for (from = *fromP; from != fromLim; from += 2) { \
- int plane; \
- unsigned char lo2; \
- unsigned char lo = GET_LO(from); \
- unsigned char hi = GET_HI(from); \
- switch (hi) { \
- case 0: \
- if (lo < 0x80) { \
- if (*toP == toLim) { \
- *fromP = from; \
- return; \
- } \
- *(*toP)++ = lo; \
- break; \
- } \
- /* fall through */ \
- case 0x1: case 0x2: case 0x3: \
- case 0x4: case 0x5: case 0x6: case 0x7: \
- if (toLim - *toP < 2) { \
- *fromP = from; \
- return; \
- } \
- *(*toP)++ = ((lo >> 6) | (hi << 2) | UTF8_cval2); \
- *(*toP)++ = ((lo & 0x3f) | 0x80); \
- break; \
- default: \
- if (toLim - *toP < 3) { \
- *fromP = from; \
- return; \
- } \
- /* 16 bits divided 4, 6, 6 amongst 3 bytes */ \
- *(*toP)++ = ((hi >> 4) | UTF8_cval3); \
- *(*toP)++ = (((hi & 0xf) << 2) | (lo >> 6) | 0x80); \
- *(*toP)++ = ((lo & 0x3f) | 0x80); \
- break; \
- case 0xD8: case 0xD9: case 0xDA: case 0xDB: \
- if (toLim - *toP < 4) { \
- *fromP = from; \
- return; \
- } \
- plane = (((hi & 0x3) << 2) | ((lo >> 6) & 0x3)) + 1; \
- *(*toP)++ = ((plane >> 2) | UTF8_cval4); \
- *(*toP)++ = (((lo >> 2) & 0xF) | ((plane & 0x3) << 4) | 0x80); \
- from += 2; \
- lo2 = GET_LO(from); \
- *(*toP)++ = (((lo & 0x3) << 4) \
- | ((GET_HI(from) & 0x3) << 2) \
- | (lo2 >> 6) \
- | 0x80); \
- *(*toP)++ = ((lo2 & 0x3f) | 0x80); \
- break; \
- } \
- } \
- *fromP = from; \
-}
-
-#define DEFINE_UTF16_TO_UTF16(E) \
-static \
-void E ## toUtf16(const ENCODING *enc, \
- const char **fromP, const char *fromLim, \
- unsigned short **toP, const unsigned short *toLim) \
-{ \
- /* Avoid copying first half only of surrogate */ \
- if (fromLim - *fromP > ((toLim - *toP) << 1) \
- && (GET_HI(fromLim - 2) & 0xF8) == 0xD8) \
- fromLim -= 2; \
- for (; *fromP != fromLim && *toP != toLim; *fromP += 2) \
- *(*toP)++ = (GET_HI(*fromP) << 8) | GET_LO(*fromP); \
-}
-
-#define SET2(ptr, ch) \
- (((ptr)[0] = ((ch) & 0xff)), ((ptr)[1] = ((ch) >> 8)))
-#define GET_LO(ptr) ((unsigned char)(ptr)[0])
-#define GET_HI(ptr) ((unsigned char)(ptr)[1])
-
-DEFINE_UTF16_TO_UTF8(little2_)
-DEFINE_UTF16_TO_UTF16(little2_)
-
-#undef SET2
-#undef GET_LO
-#undef GET_HI
-
-#define SET2(ptr, ch) \
- (((ptr)[0] = ((ch) >> 8)), ((ptr)[1] = ((ch) & 0xFF)))
-#define GET_LO(ptr) ((unsigned char)(ptr)[1])
-#define GET_HI(ptr) ((unsigned char)(ptr)[0])
-
-DEFINE_UTF16_TO_UTF8(big2_)
-DEFINE_UTF16_TO_UTF16(big2_)
-
-#undef SET2
-#undef GET_LO
-#undef GET_HI
-
-#define LITTLE2_BYTE_TYPE(enc, p) \
- ((p)[1] == 0 \
- ? ((struct normal_encoding *)(enc))->type[(unsigned char)*(p)] \
- : unicode_byte_type((p)[1], (p)[0]))
-#define LITTLE2_BYTE_TO_ASCII(enc, p) ((p)[1] == 0 ? (p)[0] : -1)
-#define LITTLE2_CHAR_MATCHES(enc, p, c) ((p)[1] == 0 && (p)[0] == c)
-#define LITTLE2_IS_NAME_CHAR_MINBPC(enc, p) \
- UCS2_GET_NAMING(namePages, (unsigned char)p[1], (unsigned char)p[0])
-#define LITTLE2_IS_NMSTRT_CHAR_MINBPC(enc, p) \
- UCS2_GET_NAMING(nmstrtPages, (unsigned char)p[1], (unsigned char)p[0])
-
-#ifdef XML_MIN_SIZE
-
-static
-int little2_byteType(const ENCODING *enc, const char *p)
-{
- return LITTLE2_BYTE_TYPE(enc, p);
-}
-
-static
-int little2_byteToAscii(const ENCODING *enc, const char *p)
-{
- return LITTLE2_BYTE_TO_ASCII(enc, p);
-}
-
-static
-int little2_charMatches(const ENCODING *enc, const char *p, int c)
-{
- return LITTLE2_CHAR_MATCHES(enc, p, c);
-}
-
-static
-int little2_isNameMin(const ENCODING *enc, const char *p)
-{
- return LITTLE2_IS_NAME_CHAR_MINBPC(enc, p);
-}
-
-static
-int little2_isNmstrtMin(const ENCODING *enc, const char *p)
-{
- return LITTLE2_IS_NMSTRT_CHAR_MINBPC(enc, p);
-}
-
-#undef VTABLE
-#define VTABLE VTABLE1, little2_toUtf8, little2_toUtf16
-
-#else /* not XML_MIN_SIZE */
-
-#undef PREFIX
-#define PREFIX(ident) little2_ ## ident
-#define MINBPC(enc) 2
-/* CHAR_MATCHES is guaranteed to have MINBPC bytes available. */
-#define BYTE_TYPE(enc, p) LITTLE2_BYTE_TYPE(enc, p)
-#define BYTE_TO_ASCII(enc, p) LITTLE2_BYTE_TO_ASCII(enc, p)
-#define CHAR_MATCHES(enc, p, c) LITTLE2_CHAR_MATCHES(enc, p, c)
-#define IS_NAME_CHAR(enc, p, n) 0
-#define IS_NAME_CHAR_MINBPC(enc, p) LITTLE2_IS_NAME_CHAR_MINBPC(enc, p)
-#define IS_NMSTRT_CHAR(enc, p, n) (0)
-#define IS_NMSTRT_CHAR_MINBPC(enc, p) LITTLE2_IS_NMSTRT_CHAR_MINBPC(enc, p)
-
-#include "xmltok_impl.c"
-
-#undef MINBPC
-#undef BYTE_TYPE
-#undef BYTE_TO_ASCII
-#undef CHAR_MATCHES
-#undef IS_NAME_CHAR
-#undef IS_NAME_CHAR_MINBPC
-#undef IS_NMSTRT_CHAR
-#undef IS_NMSTRT_CHAR_MINBPC
-#undef IS_INVALID_CHAR
-
-#endif /* not XML_MIN_SIZE */
-
-#ifdef XML_NS
-
-static const struct normal_encoding little2_encoding_ns = {
- { VTABLE, 2, 0,
-#if XML_BYTE_ORDER == 12
- 1
-#else
- 0
-#endif
- },
- {
-#include "asciitab.h"
-#include "latin1tab.h"
- },
- STANDARD_VTABLE(little2_)
-};
-
-#endif
-
-static const struct normal_encoding little2_encoding = {
- { VTABLE, 2, 0,
-#if XML_BYTE_ORDER == 12
- 1
-#else
- 0
-#endif
- },
- {
-#define BT_COLON BT_NMSTRT
-#include "asciitab.h"
-#undef BT_COLON
-#include "latin1tab.h"
- },
- STANDARD_VTABLE(little2_)
-};
-
-#if XML_BYTE_ORDER != 21
-
-#ifdef XML_NS
-
-static const struct normal_encoding internal_little2_encoding_ns = {
- { VTABLE, 2, 0, 1 },
- {
-#include "iasciitab.h"
-#include "latin1tab.h"
- },
- STANDARD_VTABLE(little2_)
-};
-
-#endif
-
-static const struct normal_encoding internal_little2_encoding = {
- { VTABLE, 2, 0, 1 },
- {
-#define BT_COLON BT_NMSTRT
-#include "iasciitab.h"
-#undef BT_COLON
-#include "latin1tab.h"
- },
- STANDARD_VTABLE(little2_)
-};
-
-#endif
-
-
-#define BIG2_BYTE_TYPE(enc, p) \
- ((p)[0] == 0 \
- ? ((struct normal_encoding *)(enc))->type[(unsigned char)(p)[1]] \
- : unicode_byte_type((p)[0], (p)[1]))
-#define BIG2_BYTE_TO_ASCII(enc, p) ((p)[0] == 0 ? (p)[1] : -1)
-#define BIG2_CHAR_MATCHES(enc, p, c) ((p)[0] == 0 && (p)[1] == c)
-#define BIG2_IS_NAME_CHAR_MINBPC(enc, p) \
- UCS2_GET_NAMING(namePages, (unsigned char)p[0], (unsigned char)p[1])
-#define BIG2_IS_NMSTRT_CHAR_MINBPC(enc, p) \
- UCS2_GET_NAMING(nmstrtPages, (unsigned char)p[0], (unsigned char)p[1])
-
-#ifdef XML_MIN_SIZE
-
-static
-int big2_byteType(const ENCODING *enc, const char *p)
-{
- return BIG2_BYTE_TYPE(enc, p);
-}
-
-static
-int big2_byteToAscii(const ENCODING *enc, const char *p)
-{
- return BIG2_BYTE_TO_ASCII(enc, p);
-}
-
-static
-int big2_charMatches(const ENCODING *enc, const char *p, int c)
-{
- return BIG2_CHAR_MATCHES(enc, p, c);
-}
-
-static
-int big2_isNameMin(const ENCODING *enc, const char *p)
-{
- return BIG2_IS_NAME_CHAR_MINBPC(enc, p);
-}
-
-static
-int big2_isNmstrtMin(const ENCODING *enc, const char *p)
-{
- return BIG2_IS_NMSTRT_CHAR_MINBPC(enc, p);
-}
-
-#undef VTABLE
-#define VTABLE VTABLE1, big2_toUtf8, big2_toUtf16
-
-#else /* not XML_MIN_SIZE */
-
-#undef PREFIX
-#define PREFIX(ident) big2_ ## ident
-#define MINBPC(enc) 2
-/* CHAR_MATCHES is guaranteed to have MINBPC bytes available. */
-#define BYTE_TYPE(enc, p) BIG2_BYTE_TYPE(enc, p)
-#define BYTE_TO_ASCII(enc, p) BIG2_BYTE_TO_ASCII(enc, p)
-#define CHAR_MATCHES(enc, p, c) BIG2_CHAR_MATCHES(enc, p, c)
-#define IS_NAME_CHAR(enc, p, n) 0
-#define IS_NAME_CHAR_MINBPC(enc, p) BIG2_IS_NAME_CHAR_MINBPC(enc, p)
-#define IS_NMSTRT_CHAR(enc, p, n) (0)
-#define IS_NMSTRT_CHAR_MINBPC(enc, p) BIG2_IS_NMSTRT_CHAR_MINBPC(enc, p)
-
-#include "xmltok_impl.c"
-
-#undef MINBPC
-#undef BYTE_TYPE
-#undef BYTE_TO_ASCII
-#undef CHAR_MATCHES
-#undef IS_NAME_CHAR
-#undef IS_NAME_CHAR_MINBPC
-#undef IS_NMSTRT_CHAR
-#undef IS_NMSTRT_CHAR_MINBPC
-#undef IS_INVALID_CHAR
-
-#endif /* not XML_MIN_SIZE */
-
-#ifdef XML_NS
-
-static const struct normal_encoding big2_encoding_ns = {
- { VTABLE, 2, 0,
-#if XML_BYTE_ORDER == 21
- 1
-#else
- 0
-#endif
- },
- {
-#include "asciitab.h"
-#include "latin1tab.h"
- },
- STANDARD_VTABLE(big2_)
-};
-
-#endif
-
-static const struct normal_encoding big2_encoding = {
- { VTABLE, 2, 0,
-#if XML_BYTE_ORDER == 21
- 1
-#else
- 0
-#endif
- },
- {
-#define BT_COLON BT_NMSTRT
-#include "asciitab.h"
-#undef BT_COLON
-#include "latin1tab.h"
- },
- STANDARD_VTABLE(big2_)
-};
-
-#if XML_BYTE_ORDER != 12
-
-#ifdef XML_NS
-
-static const struct normal_encoding internal_big2_encoding_ns = {
- { VTABLE, 2, 0, 1 },
- {
-#include "iasciitab.h"
-#include "latin1tab.h"
- },
- STANDARD_VTABLE(big2_)
-};
-
-#endif
-
-static const struct normal_encoding internal_big2_encoding = {
- { VTABLE, 2, 0, 1 },
- {
-#define BT_COLON BT_NMSTRT
-#include "iasciitab.h"
-#undef BT_COLON
-#include "latin1tab.h"
- },
- STANDARD_VTABLE(big2_)
-};
-
-#endif
-
-#undef PREFIX
-
-static
-int streqci(const char *s1, const char *s2)
-{
- for (;;) {
- char c1 = *s1++;
- char c2 = *s2++;
- if ('a' <= c1 && c1 <= 'z')
- c1 += 'A' - 'a';
- if ('a' <= c2 && c2 <= 'z')
- c2 += 'A' - 'a';
- if (c1 != c2)
- return 0;
- if (!c1)
- break;
- }
- return 1;
-}
-
-static
-void initUpdatePosition(const ENCODING *enc, const char *ptr,
- const char *end, POSITION *pos)
-{
- normal_updatePosition(&utf8_encoding.enc, ptr, end, pos);
-}
-
-static
-int toAscii(const ENCODING *enc, const char *ptr, const char *end)
-{
- char buf[1];
- char *p = buf;
- XmlUtf8Convert(enc, &ptr, end, &p, p + 1);
- if (p == buf)
- return -1;
- else
- return buf[0];
-}
-
-static
-int isSpace(int c)
-{
- switch (c) {
- case 0x20:
- case 0xD:
- case 0xA:
- case 0x9:
- return 1;
- }
- return 0;
-}
-
-/* Return 1 if there's just optional white space
-or there's an S followed by name=val. */
-static
-int parsePseudoAttribute(const ENCODING *enc,
- const char *ptr,
- const char *end,
- const char **namePtr,
- const char **nameEndPtr,
- const char **valPtr,
- const char **nextTokPtr)
-{
- int c;
- char open;
- if (ptr == end) {
- *namePtr = 0;
- return 1;
- }
- if (!isSpace(toAscii(enc, ptr, end))) {
- *nextTokPtr = ptr;
- return 0;
- }
- do {
- ptr += enc->minBytesPerChar;
- } while (isSpace(toAscii(enc, ptr, end)));
- if (ptr == end) {
- *namePtr = 0;
- return 1;
- }
- *namePtr = ptr;
- for (;;) {
- c = toAscii(enc, ptr, end);
- if (c == -1) {
- *nextTokPtr = ptr;
- return 0;
- }
- if (c == '=') {
- *nameEndPtr = ptr;
- break;
- }
- if (isSpace(c)) {
- *nameEndPtr = ptr;
- do {
- ptr += enc->minBytesPerChar;
- } while (isSpace(c = toAscii(enc, ptr, end)));
- if (c != '=') {
- *nextTokPtr = ptr;
- return 0;
- }
- break;
- }
- ptr += enc->minBytesPerChar;
- }
- if (ptr == *namePtr) {
- *nextTokPtr = ptr;
- return 0;
- }
- ptr += enc->minBytesPerChar;
- c = toAscii(enc, ptr, end);
- while (isSpace(c)) {
- ptr += enc->minBytesPerChar;
- c = toAscii(enc, ptr, end);
- }
- if (c != '"' && c != '\'') {
- *nextTokPtr = ptr;
- return 0;
- }
- open = c;
- ptr += enc->minBytesPerChar;
- *valPtr = ptr;
- for (;; ptr += enc->minBytesPerChar) {
- c = toAscii(enc, ptr, end);
- if (c == open)
- break;
- if (!('a' <= c && c <= 'z')
- && !('A' <= c && c <= 'Z')
- && !('0' <= c && c <= '9')
- && c != '.'
- && c != '-'
- && c != '_') {
- *nextTokPtr = ptr;
- return 0;
- }
- }
- *nextTokPtr = ptr + enc->minBytesPerChar;
- return 1;
-}
-
-static
-int doParseXmlDecl(const ENCODING *(*encodingFinder)(const ENCODING *,
- const char *,
- const char *),
- int isGeneralTextEntity,
- const ENCODING *enc,
- const char *ptr,
- const char *end,
- const char **badPtr,
- const char **versionPtr,
- const char **encodingName,
- const ENCODING **encoding,
- int *standalone)
-{
- const char *val = 0;
- const char *name = 0;
- const char *nameEnd = 0;
- ptr += 5 * enc->minBytesPerChar;
- end -= 2 * enc->minBytesPerChar;
- if (!parsePseudoAttribute(enc, ptr, end, &name, &nameEnd, &val, &ptr) || !name) {
- *badPtr = ptr;
- return 0;
- }
- if (!XmlNameMatchesAscii(enc, name, nameEnd, "version")) {
- if (!isGeneralTextEntity) {
- *badPtr = name;
- return 0;
- }
- }
- else {
- if (versionPtr)
- *versionPtr = val;
- if (!parsePseudoAttribute(enc, ptr, end, &name, &nameEnd, &val, &ptr)) {
- *badPtr = ptr;
- return 0;
- }
- if (!name) {
- if (isGeneralTextEntity) {
- /* a TextDecl must have an EncodingDecl */
- *badPtr = ptr;
- return 0;
- }
- return 1;
- }
- }
- if (XmlNameMatchesAscii(enc, name, nameEnd, "encoding")) {
- int c = toAscii(enc, val, end);
- if (!('a' <= c && c <= 'z') && !('A' <= c && c <= 'Z')) {
- *badPtr = val;
- return 0;
- }
- if (encodingName)
- *encodingName = val;
- if (encoding)
- *encoding = encodingFinder(enc, val, ptr - enc->minBytesPerChar);
- if (!parsePseudoAttribute(enc, ptr, end, &name, &nameEnd, &val, &ptr)) {
- *badPtr = ptr;
- return 0;
- }
- if (!name)
- return 1;
- }
- if (!XmlNameMatchesAscii(enc, name, nameEnd, "standalone") || isGeneralTextEntity) {
- *badPtr = name;
- return 0;
- }
- if (XmlNameMatchesAscii(enc, val, ptr - enc->minBytesPerChar, "yes")) {
- if (standalone)
- *standalone = 1;
- }
- else if (XmlNameMatchesAscii(enc, val, ptr - enc->minBytesPerChar, "no")) {
- if (standalone)
- *standalone = 0;
- }
- else {
- *badPtr = val;
- return 0;
- }
- while (isSpace(toAscii(enc, ptr, end)))
- ptr += enc->minBytesPerChar;
- if (ptr != end) {
- *badPtr = ptr;
- return 0;
- }
- return 1;
-}
-
-static
-int checkCharRefNumber(int result)
-{
- switch (result >> 8) {
- case 0xD8: case 0xD9: case 0xDA: case 0xDB:
- case 0xDC: case 0xDD: case 0xDE: case 0xDF:
- return -1;
- case 0:
- if (latin1_encoding.type[result] == BT_NONXML)
- return -1;
- break;
- case 0xFF:
- if (result == 0xFFFE || result == 0xFFFF)
- return -1;
- break;
- }
- return result;
-}
-
-int XmlUtf8Encode(int c, char *buf)
-{
- enum {
- /* minN is minimum legal resulting value for N byte sequence */
- min2 = 0x80,
- min3 = 0x800,
- min4 = 0x10000
- };
-
- if (c < 0)
- return 0;
- if (c < min2) {
- buf[0] = (c | UTF8_cval1);
- return 1;
- }
- if (c < min3) {
- buf[0] = ((c >> 6) | UTF8_cval2);
- buf[1] = ((c & 0x3f) | 0x80);
- return 2;
- }
- if (c < min4) {
- buf[0] = ((c >> 12) | UTF8_cval3);
- buf[1] = (((c >> 6) & 0x3f) | 0x80);
- buf[2] = ((c & 0x3f) | 0x80);
- return 3;
- }
- if (c < 0x110000) {
- buf[0] = ((c >> 18) | UTF8_cval4);
- buf[1] = (((c >> 12) & 0x3f) | 0x80);
- buf[2] = (((c >> 6) & 0x3f) | 0x80);
- buf[3] = ((c & 0x3f) | 0x80);
- return 4;
- }
- return 0;
-}
-
-int XmlUtf16Encode(int charNum, unsigned short *buf)
-{
- if (charNum < 0)
- return 0;
- if (charNum < 0x10000) {
- buf[0] = charNum;
- return 1;
- }
- if (charNum < 0x110000) {
- charNum -= 0x10000;
- buf[0] = (charNum >> 10) + 0xD800;
- buf[1] = (charNum & 0x3FF) + 0xDC00;
- return 2;
- }
- return 0;
-}
-
-struct unknown_encoding {
- struct normal_encoding normal;
- int (*convert)(void *userData, const char *p);
- void *userData;
- unsigned short utf16[256];
- char utf8[256][4];
-};
-
-int XmlSizeOfUnknownEncoding(void)
-{
- return sizeof(struct unknown_encoding);
-}
-
-static
-int unknown_isName(const ENCODING *enc, const char *p)
-{
- int c = ((const struct unknown_encoding *)enc)
- ->convert(((const struct unknown_encoding *)enc)->userData, p);
- if (c & ~0xFFFF)
- return 0;
- return UCS2_GET_NAMING(namePages, c >> 8, c & 0xFF);
-}
-
-static
-int unknown_isNmstrt(const ENCODING *enc, const char *p)
-{
- int c = ((const struct unknown_encoding *)enc)
- ->convert(((const struct unknown_encoding *)enc)->userData, p);
- if (c & ~0xFFFF)
- return 0;
- return UCS2_GET_NAMING(nmstrtPages, c >> 8, c & 0xFF);
-}
-
-static
-int unknown_isInvalid(const ENCODING *enc, const char *p)
-{
- int c = ((const struct unknown_encoding *)enc)
- ->convert(((const struct unknown_encoding *)enc)->userData, p);
- return (c & ~0xFFFF) || checkCharRefNumber(c) < 0;
-}
-
-static
-void unknown_toUtf8(const ENCODING *enc,
- const char **fromP, const char *fromLim,
- char **toP, const char *toLim)
-{
- char buf[XML_UTF8_ENCODE_MAX];
- for (;;) {
- const char *utf8;
- int n;
- if (*fromP == fromLim)
- break;
- utf8 = ((const struct unknown_encoding *)enc)->utf8[(unsigned char)**fromP];
- n = *utf8++;
- if (n == 0) {
- int c = ((const struct unknown_encoding *)enc)
- ->convert(((const struct unknown_encoding *)enc)->userData, *fromP);
- n = XmlUtf8Encode(c, buf);
- if (n > toLim - *toP)
- break;
- utf8 = buf;
- *fromP += ((const struct normal_encoding *)enc)->type[(unsigned char)**fromP]
- - (BT_LEAD2 - 2);
- }
- else {
- if (n > toLim - *toP)
- break;
- (*fromP)++;
- }
- do {
- *(*toP)++ = *utf8++;
- } while (--n != 0);
- }
-}
-
-static
-void unknown_toUtf16(const ENCODING *enc,
- const char **fromP, const char *fromLim,
- unsigned short **toP, const unsigned short *toLim)
-{
- while (*fromP != fromLim && *toP != toLim) {
- unsigned short c
- = ((const struct unknown_encoding *)enc)->utf16[(unsigned char)**fromP];
- if (c == 0) {
- c = (unsigned short)((const struct unknown_encoding *)enc)
- ->convert(((const struct unknown_encoding *)enc)->userData, *fromP);
- *fromP += ((const struct normal_encoding *)enc)->type[(unsigned char)**fromP]
- - (BT_LEAD2 - 2);
- }
- else
- (*fromP)++;
- *(*toP)++ = c;
- }
-}
-
-ENCODING *
-XmlInitUnknownEncoding(void *mem,
- int *table,
- int (*convert)(void *userData, const char *p),
- void *userData)
-{
- unsigned int i;
- struct unknown_encoding *e = mem;
- for (i = 0; i < sizeof(struct normal_encoding); i++)
- ((char *)mem)[i] = ((char *)&latin1_encoding)[i];
- for (i = 0; i < 128; i++)
- if (latin1_encoding.type[i] != BT_OTHER
- && latin1_encoding.type[i] != BT_NONXML
- && table[i] != (int)i)
- return 0;
- for (i = 0; i < 256; i++) {
- int c = table[i];
- if (c == -1) {
- e->normal.type[i] = BT_MALFORM;
- /* This shouldn't really get used. */
- e->utf16[i] = 0xFFFF;
- e->utf8[i][0] = 1;
- e->utf8[i][1] = 0;
- }
- else if (c < 0) {
- if (c < -4)
- return 0;
- e->normal.type[i] = BT_LEAD2 - (c + 2);
- e->utf8[i][0] = 0;
- e->utf16[i] = 0;
- }
- else if (c < 0x80) {
- if (latin1_encoding.type[c] != BT_OTHER
- && latin1_encoding.type[c] != BT_NONXML
- && c != i)
- return 0;
- e->normal.type[i] = latin1_encoding.type[c];
- e->utf8[i][0] = 1;
- e->utf8[i][1] = (char)c;
- e->utf16[i] = c == 0 ? 0xFFFF : c;
- }
- else if (checkCharRefNumber(c) < 0) {
- e->normal.type[i] = BT_NONXML;
- /* This shouldn't really get used. */
- e->utf16[i] = 0xFFFF;
- e->utf8[i][0] = 1;
- e->utf8[i][1] = 0;
- }
- else {
- if (c > 0xFFFF)
- return 0;
- if (UCS2_GET_NAMING(nmstrtPages, c >> 8, c & 0xff))
- e->normal.type[i] = BT_NMSTRT;
- else if (UCS2_GET_NAMING(namePages, c >> 8, c & 0xff))
- e->normal.type[i] = BT_NAME;
- else
- e->normal.type[i] = BT_OTHER;
- e->utf8[i][0] = (char)XmlUtf8Encode(c, e->utf8[i] + 1);
- e->utf16[i] = c;
- }
- }
- e->userData = userData;
- e->convert = convert;
- if (convert) {
- e->normal.isName2 = unknown_isName;
- e->normal.isName3 = unknown_isName;
- e->normal.isName4 = unknown_isName;
- e->normal.isNmstrt2 = unknown_isNmstrt;
- e->normal.isNmstrt3 = unknown_isNmstrt;
- e->normal.isNmstrt4 = unknown_isNmstrt;
- e->normal.isInvalid2 = unknown_isInvalid;
- e->normal.isInvalid3 = unknown_isInvalid;
- e->normal.isInvalid4 = unknown_isInvalid;
- }
- e->normal.enc.utf8Convert = unknown_toUtf8;
- e->normal.enc.utf16Convert = unknown_toUtf16;
- return &(e->normal.enc);
-}
-
-/* If this enumeration is changed, getEncodingIndex and encodings
-must also be changed. */
-enum {
- UNKNOWN_ENC = -1,
- ISO_8859_1_ENC = 0,
- US_ASCII_ENC,
- UTF_8_ENC,
- UTF_16_ENC,
- UTF_16BE_ENC,
- UTF_16LE_ENC,
- /* must match encodingNames up to here */
- NO_ENC
-};
-
-static
-int getEncodingIndex(const char *name)
-{
- static const char *encodingNames[] = {
- "ISO-8859-1",
- "US-ASCII",
- "UTF-8",
- "UTF-16",
- "UTF-16BE"
- "UTF-16LE",
- };
- int i;
- if (name == 0)
- return NO_ENC;
- for (i = 0; i < sizeof(encodingNames)/sizeof(encodingNames[0]); i++)
- if (streqci(name, encodingNames[i]))
- return i;
- return UNKNOWN_ENC;
-}
-
-/* For binary compatibility, we store the index of the encoding specified
-at initialization in the isUtf16 member. */
-
-#define INIT_ENC_INDEX(enc) ((int)(enc)->initEnc.isUtf16)
-#define SET_INIT_ENC_INDEX(enc, i) ((enc)->initEnc.isUtf16 = (char)i)
-
-/* This is what detects the encoding.
-encodingTable maps from encoding indices to encodings;
-INIT_ENC_INDEX(enc) is the index of the external (protocol) specified encoding;
-state is XML_CONTENT_STATE if we're parsing an external text entity,
-and XML_PROLOG_STATE otherwise.
-*/
-
-
-static
-int initScan(const ENCODING **encodingTable,
- const INIT_ENCODING *enc,
- int state,
- const char *ptr,
- const char *end,
- const char **nextTokPtr)
-{
- const ENCODING **encPtr;
-
- if (ptr == end)
- return XML_TOK_NONE;
- encPtr = enc->encPtr;
- if (ptr + 1 == end) {
- /* only a single byte available for auto-detection */
-#ifndef XML_DTD /* FIXME */
- /* a well-formed document entity must have more than one byte */
- if (state != XML_CONTENT_STATE)
- return XML_TOK_PARTIAL;
-#endif
- /* so we're parsing an external text entity... */
- /* if UTF-16 was externally specified, then we need at least 2 bytes */
- switch (INIT_ENC_INDEX(enc)) {
- case UTF_16_ENC:
- case UTF_16LE_ENC:
- case UTF_16BE_ENC:
- return XML_TOK_PARTIAL;
- }
- switch ((unsigned char)*ptr) {
- case 0xFE:
- case 0xFF:
- case 0xEF: /* possibly first byte of UTF-8 BOM */
- if (INIT_ENC_INDEX(enc) == ISO_8859_1_ENC
- && state == XML_CONTENT_STATE)
- break;
- /* fall through */
- case 0x00:
- case 0x3C:
- return XML_TOK_PARTIAL;
- }
- }
- else {
- switch (((unsigned char)ptr[0] << 8) | (unsigned char)ptr[1]) {
- case 0xFEFF:
- if (INIT_ENC_INDEX(enc) == ISO_8859_1_ENC
- && state == XML_CONTENT_STATE)
- break;
- *nextTokPtr = ptr + 2;
- *encPtr = encodingTable[UTF_16BE_ENC];
- return XML_TOK_BOM;
- /* 00 3C is handled in the default case */
- case 0x3C00:
- if ((INIT_ENC_INDEX(enc) == UTF_16BE_ENC
- || INIT_ENC_INDEX(enc) == UTF_16_ENC)
- && state == XML_CONTENT_STATE)
- break;
- *encPtr = encodingTable[UTF_16LE_ENC];
- return XmlTok(*encPtr, state, ptr, end, nextTokPtr);
- case 0xFFFE:
- if (INIT_ENC_INDEX(enc) == ISO_8859_1_ENC
- && state == XML_CONTENT_STATE)
- break;
- *nextTokPtr = ptr + 2;
- *encPtr = encodingTable[UTF_16LE_ENC];
- return XML_TOK_BOM;
- case 0xEFBB:
- /* Maybe a UTF-8 BOM (EF BB BF) */
- /* If there's an explicitly specified (external) encoding
- of ISO-8859-1 or some flavour of UTF-16
- and this is an external text entity,
- don't look for the BOM,
- because it might be a legal data. */
- if (state == XML_CONTENT_STATE) {
- int e = INIT_ENC_INDEX(enc);
- if (e == ISO_8859_1_ENC || e == UTF_16BE_ENC || e == UTF_16LE_ENC || e == UTF_16_ENC)
- break;
- }
- if (ptr + 2 == end)
- return XML_TOK_PARTIAL;
- if ((unsigned char)ptr[2] == 0xBF) {
- *encPtr = encodingTable[UTF_8_ENC];
- return XML_TOK_BOM;
- }
- break;
- default:
- if (ptr[0] == '\0') {
- /* 0 isn't a legal data character. Furthermore a document entity can only
- start with ASCII characters. So the only way this can fail to be big-endian
- UTF-16 if it it's an external parsed general entity that's labelled as
- UTF-16LE. */
- if (state == XML_CONTENT_STATE && INIT_ENC_INDEX(enc) == UTF_16LE_ENC)
- break;
- *encPtr = encodingTable[UTF_16BE_ENC];
- return XmlTok(*encPtr, state, ptr, end, nextTokPtr);
- }
- else if (ptr[1] == '\0') {
- /* We could recover here in the case:
- - parsing an external entity
- - second byte is 0
- - no externally specified encoding
- - no encoding declaration
- by assuming UTF-16LE. But we don't, because this would mean when
- presented just with a single byte, we couldn't reliably determine
- whether we needed further bytes. */
- if (state == XML_CONTENT_STATE)
- break;
- *encPtr = encodingTable[UTF_16LE_ENC];
- return XmlTok(*encPtr, state, ptr, end, nextTokPtr);
- }
- break;
- }
- }
- *encPtr = encodingTable[INIT_ENC_INDEX(enc)];
- return XmlTok(*encPtr, state, ptr, end, nextTokPtr);
-}
-
-
-#define NS(x) x
-#define ns(x) x
-#include "xmltok_ns.c"
-#undef NS
-#undef ns
-
-#ifdef XML_NS
-
-#define NS(x) x ## NS
-#define ns(x) x ## _ns
-
-#include "xmltok_ns.c"
-
-#undef NS
-#undef ns
-
-ENCODING *
-XmlInitUnknownEncodingNS(void *mem,
- int *table,
- int (*convert)(void *userData, const char *p),
- void *userData)
-{
- ENCODING *enc = XmlInitUnknownEncoding(mem, table, convert, userData);
- if (enc)
- ((struct normal_encoding *)enc)->type[':'] = BT_COLON;
- return enc;
-}
-
-#endif /* XML_NS */
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/xmltok.h
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/xmltok.h 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/xmltok.h 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,326 +0,0 @@
-/*
-The contents of this file are subject to the Mozilla Public License
-Version 1.1 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998, 1999
-James Clark. All Rights Reserved.
-
-Contributor(s):
-
-Alternatively, the contents of this file may be used under the terms
-of the GNU General Public License (the "GPL"), in which case the
-provisions of the GPL are applicable instead of those above. If you
-wish to allow use of your version of this file only under the terms of
-the GPL and not to allow others to use your version of this file under
-the MPL, indicate your decision by deleting the provisions above and
-replace them with the notice and other provisions required by the
-GPL. If you do not delete the provisions above, a recipient may use
-your version of this file under either the MPL or the GPL.
-*/
-
-#ifndef XmlTok_INCLUDED
-#define XmlTok_INCLUDED 1
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-#ifndef XMLTOKAPI
-#define XMLTOKAPI /* as nothing */
-#endif
-
-/* The following token may be returned by XmlContentTok */
-#define XML_TOK_TRAILING_RSQB -5 /* ] or ]] at the end of the scan; might be start of
- illegal ]]> sequence */
-/* The following tokens may be returned by both XmlPrologTok and XmlContentTok */
-#define XML_TOK_NONE -4 /* The string to be scanned is empty */
-#define XML_TOK_TRAILING_CR -3 /* A CR at the end of the scan;
- might be part of CRLF sequence */
-#define XML_TOK_PARTIAL_CHAR -2 /* only part of a multibyte sequence */
-#define XML_TOK_PARTIAL -1 /* only part of a token */
-#define XML_TOK_INVALID 0
-
-/* The following tokens are returned by XmlContentTok; some are also
- returned by XmlAttributeValueTok, XmlEntityTok, XmlCdataSectionTok */
-
-#define XML_TOK_START_TAG_WITH_ATTS 1
-#define XML_TOK_START_TAG_NO_ATTS 2
-#define XML_TOK_EMPTY_ELEMENT_WITH_ATTS 3 /* empty element tag <e/> */
-#define XML_TOK_EMPTY_ELEMENT_NO_ATTS 4
-#define XML_TOK_END_TAG 5
-#define XML_TOK_DATA_CHARS 6
-#define XML_TOK_DATA_NEWLINE 7
-#define XML_TOK_CDATA_SECT_OPEN 8
-#define XML_TOK_ENTITY_REF 9
-#define XML_TOK_CHAR_REF 10 /* numeric character reference */
-
-/* The following tokens may be returned by both XmlPrologTok and XmlContentTok */
-#define XML_TOK_PI 11 /* processing instruction */
-#define XML_TOK_XML_DECL 12 /* XML decl or text decl */
-#define XML_TOK_COMMENT 13
-#define XML_TOK_BOM 14 /* Byte order mark */
-
-/* The following tokens are returned only by XmlPrologTok */
-#define XML_TOK_PROLOG_S 15
-#define XML_TOK_DECL_OPEN 16 /* <!foo */
-#define XML_TOK_DECL_CLOSE 17 /* > */
-#define XML_TOK_NAME 18
-#define XML_TOK_NMTOKEN 19
-#define XML_TOK_POUND_NAME 20 /* #name */
-#define XML_TOK_OR 21 /* | */
-#define XML_TOK_PERCENT 22
-#define XML_TOK_OPEN_PAREN 23
-#define XML_TOK_CLOSE_PAREN 24
-#define XML_TOK_OPEN_BRACKET 25
-#define XML_TOK_CLOSE_BRACKET 26
-#define XML_TOK_LITERAL 27
-#define XML_TOK_PARAM_ENTITY_REF 28
-#define XML_TOK_INSTANCE_START 29
-
-/* The following occur only in element type declarations */
-#define XML_TOK_NAME_QUESTION 30 /* name? */
-#define XML_TOK_NAME_ASTERISK 31 /* name* */
-#define XML_TOK_NAME_PLUS 32 /* name+ */
-#define XML_TOK_COND_SECT_OPEN 33 /* <![ */
-#define XML_TOK_COND_SECT_CLOSE 34 /* ]]> */
-#define XML_TOK_CLOSE_PAREN_QUESTION 35 /* )? */
-#define XML_TOK_CLOSE_PAREN_ASTERISK 36 /* )* */
-#define XML_TOK_CLOSE_PAREN_PLUS 37 /* )+ */
-#define XML_TOK_COMMA 38
-
-/* The following token is returned only by XmlAttributeValueTok */
-#define XML_TOK_ATTRIBUTE_VALUE_S 39
-
-/* The following token is returned only by XmlCdataSectionTok */
-#define XML_TOK_CDATA_SECT_CLOSE 40
-
-/* With namespace processing this is returned by XmlPrologTok
- for a name with a colon. */
-#define XML_TOK_PREFIXED_NAME 41
-
-#ifdef XML_DTD
-#define XML_TOK_IGNORE_SECT 42
-#endif /* XML_DTD */
-
-#ifdef XML_DTD
-#define XML_N_STATES 4
-#else /* not XML_DTD */
-#define XML_N_STATES 3
-#endif /* not XML_DTD */
-
-#define XML_PROLOG_STATE 0
-#define XML_CONTENT_STATE 1
-#define XML_CDATA_SECTION_STATE 2
-#ifdef XML_DTD
-#define XML_IGNORE_SECTION_STATE 3
-#endif /* XML_DTD */
-
-#define XML_N_LITERAL_TYPES 2
-#define XML_ATTRIBUTE_VALUE_LITERAL 0
-#define XML_ENTITY_VALUE_LITERAL 1
-
-/* The size of the buffer passed to XmlUtf8Encode must be at least this. */
-#define XML_UTF8_ENCODE_MAX 4
-/* The size of the buffer passed to XmlUtf16Encode must be at least this. */
-#define XML_UTF16_ENCODE_MAX 2
-
-typedef struct position {
- /* first line and first column are 0 not 1 */
- unsigned long lineNumber;
- unsigned long columnNumber;
-} POSITION;
-
-typedef struct {
- const char *name;
- const char *valuePtr;
- const char *valueEnd;
- char normalized;
-} ATTRIBUTE;
-
-struct encoding;
-typedef struct encoding ENCODING;
-
-struct encoding {
- int (*scanners[XML_N_STATES])(const ENCODING *,
- const char *,
- const char *,
- const char **);
- int (*literalScanners[XML_N_LITERAL_TYPES])(const ENCODING *,
- const char *,
- const char *,
- const char **);
- int (*sameName)(const ENCODING *,
- const char *, const char *);
- int (*nameMatchesAscii)(const ENCODING *,
- const char *, const char *, const char *);
- int (*nameLength)(const ENCODING *, const char *);
- const char *(*skipS)(const ENCODING *, const char *);
- int (*getAtts)(const ENCODING *enc, const char *ptr,
- int attsMax, ATTRIBUTE *atts);
- int (*charRefNumber)(const ENCODING *enc, const char *ptr);
- int (*predefinedEntityName)(const ENCODING *, const char *, const char *);
- void (*updatePosition)(const ENCODING *,
- const char *ptr,
- const char *end,
- POSITION *);
- int (*isPublicId)(const ENCODING *enc, const char *ptr, const char *end,
- const char **badPtr);
- void (*utf8Convert)(const ENCODING *enc,
- const char **fromP,
- const char *fromLim,
- char **toP,
- const char *toLim);
- void (*utf16Convert)(const ENCODING *enc,
- const char **fromP,
- const char *fromLim,
- unsigned short **toP,
- const unsigned short *toLim);
- int minBytesPerChar;
- char isUtf8;
- char isUtf16;
-};
-
-/*
-Scan the string starting at ptr until the end of the next complete token,
-but do not scan past eptr. Return an integer giving the type of token.
-
-Return XML_TOK_NONE when ptr == eptr; nextTokPtr will not be set.
-
-Return XML_TOK_PARTIAL when the string does not contain a complete token;
-nextTokPtr will not be set.
-
-Return XML_TOK_INVALID when the string does not start a valid token; nextTokPtr
-will be set to point to the character which made the token invalid.
-
-Otherwise the string starts with a valid token; nextTokPtr will be set to point
-to the character following the end of that token.
-
-Each data character counts as a single token, but adjacent data characters
-may be returned together. Similarly for characters in the prolog outside
-literals, comments and processing instructions.
-*/
-
-
-#define XmlTok(enc, state, ptr, end, nextTokPtr) \
- (((enc)->scanners[state])(enc, ptr, end, nextTokPtr))
-
-#define XmlPrologTok(enc, ptr, end, nextTokPtr) \
- XmlTok(enc, XML_PROLOG_STATE, ptr, end, nextTokPtr)
-
-#define XmlContentTok(enc, ptr, end, nextTokPtr) \
- XmlTok(enc, XML_CONTENT_STATE, ptr, end, nextTokPtr)
-
-#define XmlCdataSectionTok(enc, ptr, end, nextTokPtr) \
- XmlTok(enc, XML_CDATA_SECTION_STATE, ptr, end, nextTokPtr)
-
-#ifdef XML_DTD
-
-#define XmlIgnoreSectionTok(enc, ptr, end, nextTokPtr) \
- XmlTok(enc, XML_IGNORE_SECTION_STATE, ptr, end, nextTokPtr)
-
-#endif /* XML_DTD */
-
-/* This is used for performing a 2nd-level tokenization on
-the content of a literal that has already been returned by XmlTok. */
-
-#define XmlLiteralTok(enc, literalType, ptr, end, nextTokPtr) \
- (((enc)->literalScanners[literalType])(enc, ptr, end, nextTokPtr))
-
-#define XmlAttributeValueTok(enc, ptr, end, nextTokPtr) \
- XmlLiteralTok(enc, XML_ATTRIBUTE_VALUE_LITERAL, ptr, end, nextTokPtr)
-
-#define XmlEntityValueTok(enc, ptr, end, nextTokPtr) \
- XmlLiteralTok(enc, XML_ENTITY_VALUE_LITERAL, ptr, end, nextTokPtr)
-
-#define XmlSameName(enc, ptr1, ptr2) (((enc)->sameName)(enc, ptr1, ptr2))
-
-#define XmlNameMatchesAscii(enc, ptr1, end1, ptr2) \
- (((enc)->nameMatchesAscii)(enc, ptr1, end1, ptr2))
-
-#define XmlNameLength(enc, ptr) \
- (((enc)->nameLength)(enc, ptr))
-
-#define XmlSkipS(enc, ptr) \
- (((enc)->skipS)(enc, ptr))
-
-#define XmlGetAttributes(enc, ptr, attsMax, atts) \
- (((enc)->getAtts)(enc, ptr, attsMax, atts))
-
-#define XmlCharRefNumber(enc, ptr) \
- (((enc)->charRefNumber)(enc, ptr))
-
-#define XmlPredefinedEntityName(enc, ptr, end) \
- (((enc)->predefinedEntityName)(enc, ptr, end))
-
-#define XmlUpdatePosition(enc, ptr, end, pos) \
- (((enc)->updatePosition)(enc, ptr, end, pos))
-
-#define XmlIsPublicId(enc, ptr, end, badPtr) \
- (((enc)->isPublicId)(enc, ptr, end, badPtr))
-
-#define XmlUtf8Convert(enc, fromP, fromLim, toP, toLim) \
- (((enc)->utf8Convert)(enc, fromP, fromLim, toP, toLim))
-
-#define XmlUtf16Convert(enc, fromP, fromLim, toP, toLim) \
- (((enc)->utf16Convert)(enc, fromP, fromLim, toP, toLim))
-
-typedef struct {
- ENCODING initEnc;
- const ENCODING **encPtr;
-} INIT_ENCODING;
-
-int XMLTOKAPI XmlParseXmlDecl(int isGeneralTextEntity,
- const ENCODING *enc,
- const char *ptr,
- const char *end,
- const char **badPtr,
- const char **versionPtr,
- const char **encodingNamePtr,
- const ENCODING **namedEncodingPtr,
- int *standalonePtr);
-
-int XMLTOKAPI XmlInitEncoding(INIT_ENCODING *, const ENCODING **, const char *name);
-const ENCODING XMLTOKAPI *XmlGetUtf8InternalEncoding(void);
-const ENCODING XMLTOKAPI *XmlGetUtf16InternalEncoding(void);
-int XMLTOKAPI XmlUtf8Encode(int charNumber, char *buf);
-int XMLTOKAPI XmlUtf16Encode(int charNumber, unsigned short *buf);
-
-int XMLTOKAPI XmlSizeOfUnknownEncoding(void);
-ENCODING XMLTOKAPI *
-XmlInitUnknownEncoding(void *mem,
- int *table,
- int (*conv)(void *userData, const char *p),
- void *userData);
-
-int XMLTOKAPI XmlParseXmlDeclNS(int isGeneralTextEntity,
- const ENCODING *enc,
- const char *ptr,
- const char *end,
- const char **badPtr,
- const char **versionPtr,
- const char **encodingNamePtr,
- const ENCODING **namedEncodingPtr,
- int *standalonePtr);
-int XMLTOKAPI XmlInitEncodingNS(INIT_ENCODING *, const ENCODING **, const char *name);
-const ENCODING XMLTOKAPI *XmlGetUtf8InternalEncodingNS();
-const ENCODING XMLTOKAPI *XmlGetUtf16InternalEncodingNS();
-ENCODING XMLTOKAPI *
-XmlInitUnknownEncodingNS(void *mem,
- int *table,
- int (*conv)(void *userData, const char *p),
- void *userData);
-#ifdef __cplusplus
-}
-#endif
-
-#endif /* not XmlTok_INCLUDED */
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/xmltok_impl.c
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/xmltok_impl.c 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/xmltok_impl.c 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,1789 +0,0 @@
-/*
-The contents of this file are subject to the Mozilla Public License
-Version 1.1 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998, 1999
-James Clark. All Rights Reserved.
-
-Contributor(s):
-
-Alternatively, the contents of this file may be used under the terms
-of the GNU General Public License (the "GPL"), in which case the
-provisions of the GPL are applicable instead of those above. If you
-wish to allow use of your version of this file only under the terms of
-the GPL and not to allow others to use your version of this file under
-the MPL, indicate your decision by deleting the provisions above and
-replace them with the notice and other provisions required by the
-GPL. If you do not delete the provisions above, a recipient may use
-your version of this file under either the MPL or the GPL.
-*/
-
-#ifndef IS_INVALID_CHAR
-#define IS_INVALID_CHAR(enc, ptr, n) (0)
-#endif
-
-#define INVALID_LEAD_CASE(n, ptr, nextTokPtr) \
- case BT_LEAD ## n: \
- if (end - ptr < n) \
- return XML_TOK_PARTIAL_CHAR; \
- if (IS_INVALID_CHAR(enc, ptr, n)) { \
- *(nextTokPtr) = (ptr); \
- return XML_TOK_INVALID; \
- } \
- ptr += n; \
- break;
-
-#define INVALID_CASES(ptr, nextTokPtr) \
- INVALID_LEAD_CASE(2, ptr, nextTokPtr) \
- INVALID_LEAD_CASE(3, ptr, nextTokPtr) \
- INVALID_LEAD_CASE(4, ptr, nextTokPtr) \
- case BT_NONXML: \
- case BT_MALFORM: \
- case BT_TRAIL: \
- *(nextTokPtr) = (ptr); \
- return XML_TOK_INVALID;
-
-#define CHECK_NAME_CASE(n, enc, ptr, end, nextTokPtr) \
- case BT_LEAD ## n: \
- if (end - ptr < n) \
- return XML_TOK_PARTIAL_CHAR; \
- if (!IS_NAME_CHAR(enc, ptr, n)) { \
- *nextTokPtr = ptr; \
- return XML_TOK_INVALID; \
- } \
- ptr += n; \
- break;
-
-#define CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) \
- case BT_NONASCII: \
- if (!IS_NAME_CHAR_MINBPC(enc, ptr)) { \
- *nextTokPtr = ptr; \
- return XML_TOK_INVALID; \
- } \
- case BT_NMSTRT: \
- case BT_HEX: \
- case BT_DIGIT: \
- case BT_NAME: \
- case BT_MINUS: \
- ptr += MINBPC(enc); \
- break; \
- CHECK_NAME_CASE(2, enc, ptr, end, nextTokPtr) \
- CHECK_NAME_CASE(3, enc, ptr, end, nextTokPtr) \
- CHECK_NAME_CASE(4, enc, ptr, end, nextTokPtr)
-
-#define CHECK_NMSTRT_CASE(n, enc, ptr, end, nextTokPtr) \
- case BT_LEAD ## n: \
- if (end - ptr < n) \
- return XML_TOK_PARTIAL_CHAR; \
- if (!IS_NMSTRT_CHAR(enc, ptr, n)) { \
- *nextTokPtr = ptr; \
- return XML_TOK_INVALID; \
- } \
- ptr += n; \
- break;
-
-#define CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) \
- case BT_NONASCII: \
- if (!IS_NMSTRT_CHAR_MINBPC(enc, ptr)) { \
- *nextTokPtr = ptr; \
- return XML_TOK_INVALID; \
- } \
- case BT_NMSTRT: \
- case BT_HEX: \
- ptr += MINBPC(enc); \
- break; \
- CHECK_NMSTRT_CASE(2, enc, ptr, end, nextTokPtr) \
- CHECK_NMSTRT_CASE(3, enc, ptr, end, nextTokPtr) \
- CHECK_NMSTRT_CASE(4, enc, ptr, end, nextTokPtr)
-
-#ifndef PREFIX
-#define PREFIX(ident) ident
-#endif
-
-/* ptr points to character following "<!-" */
-
-static
-int PREFIX(scanComment)(const ENCODING *enc, const char *ptr, const char *end,
- const char **nextTokPtr)
-{
- if (ptr != end) {
- if (!CHAR_MATCHES(enc, ptr, '-')) {
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- ptr += MINBPC(enc);
- while (ptr != end) {
- switch (BYTE_TYPE(enc, ptr)) {
- INVALID_CASES(ptr, nextTokPtr)
- case BT_MINUS:
- if ((ptr += MINBPC(enc)) == end)
- return XML_TOK_PARTIAL;
- if (CHAR_MATCHES(enc, ptr, '-')) {
- if ((ptr += MINBPC(enc)) == end)
- return XML_TOK_PARTIAL;
- if (!CHAR_MATCHES(enc, ptr, '>')) {
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- *nextTokPtr = ptr + MINBPC(enc);
- return XML_TOK_COMMENT;
- }
- break;
- default:
- ptr += MINBPC(enc);
- break;
- }
- }
- }
- return XML_TOK_PARTIAL;
-}
-
-/* ptr points to character following "<!" */
-
-static
-int PREFIX(scanDecl)(const ENCODING *enc, const char *ptr, const char *end,
- const char **nextTokPtr)
-{
- if (ptr == end)
- return XML_TOK_PARTIAL;
- switch (BYTE_TYPE(enc, ptr)) {
- case BT_MINUS:
- return PREFIX(scanComment)(enc, ptr + MINBPC(enc), end, nextTokPtr);
- case BT_LSQB:
- *nextTokPtr = ptr + MINBPC(enc);
- return XML_TOK_COND_SECT_OPEN;
- case BT_NMSTRT:
- case BT_HEX:
- ptr += MINBPC(enc);
- break;
- default:
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- while (ptr != end) {
- switch (BYTE_TYPE(enc, ptr)) {
- case BT_PERCNT:
- if (ptr + MINBPC(enc) == end)
- return XML_TOK_PARTIAL;
- /* don't allow <!ENTITY% foo "whatever"> */
- switch (BYTE_TYPE(enc, ptr + MINBPC(enc))) {
- case BT_S: case BT_CR: case BT_LF: case BT_PERCNT:
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- /* fall through */
- case BT_S: case BT_CR: case BT_LF:
- *nextTokPtr = ptr;
- return XML_TOK_DECL_OPEN;
- case BT_NMSTRT:
- case BT_HEX:
- ptr += MINBPC(enc);
- break;
- default:
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- }
- return XML_TOK_PARTIAL;
-}
-
-static
-int PREFIX(checkPiTarget)(const ENCODING *enc, const char *ptr, const char *end, int *tokPtr)
-{
- int upper = 0;
- *tokPtr = XML_TOK_PI;
- if (end - ptr != MINBPC(enc)*3)
- return 1;
- switch (BYTE_TO_ASCII(enc, ptr)) {
- case 'x':
- break;
- case 'X':
- upper = 1;
- break;
- default:
- return 1;
- }
- ptr += MINBPC(enc);
- switch (BYTE_TO_ASCII(enc, ptr)) {
- case 'm':
- break;
- case 'M':
- upper = 1;
- break;
- default:
- return 1;
- }
- ptr += MINBPC(enc);
- switch (BYTE_TO_ASCII(enc, ptr)) {
- case 'l':
- break;
- case 'L':
- upper = 1;
- break;
- default:
- return 1;
- }
- if (upper)
- return 0;
- *tokPtr = XML_TOK_XML_DECL;
- return 1;
-}
-
-/* ptr points to character following "<?" */
-
-static
-int PREFIX(scanPi)(const ENCODING *enc, const char *ptr, const char *end,
- const char **nextTokPtr)
-{
- int tok;
- const char *target = ptr;
- if (ptr == end)
- return XML_TOK_PARTIAL;
- switch (BYTE_TYPE(enc, ptr)) {
- CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr)
- default:
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- while (ptr != end) {
- switch (BYTE_TYPE(enc, ptr)) {
- CHECK_NAME_CASES(enc, ptr, end, nextTokPtr)
- case BT_S: case BT_CR: case BT_LF:
- if (!PREFIX(checkPiTarget)(enc, target, ptr, &tok)) {
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- ptr += MINBPC(enc);
- while (ptr != end) {
- switch (BYTE_TYPE(enc, ptr)) {
- INVALID_CASES(ptr, nextTokPtr)
- case BT_QUEST:
- ptr += MINBPC(enc);
- if (ptr == end)
- return XML_TOK_PARTIAL;
- if (CHAR_MATCHES(enc, ptr, '>')) {
- *nextTokPtr = ptr + MINBPC(enc);
- return tok;
- }
- break;
- default:
- ptr += MINBPC(enc);
- break;
- }
- }
- return XML_TOK_PARTIAL;
- case BT_QUEST:
- if (!PREFIX(checkPiTarget)(enc, target, ptr, &tok)) {
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- ptr += MINBPC(enc);
- if (ptr == end)
- return XML_TOK_PARTIAL;
- if (CHAR_MATCHES(enc, ptr, '>')) {
- *nextTokPtr = ptr + MINBPC(enc);
- return tok;
- }
- /* fall through */
- default:
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- }
- return XML_TOK_PARTIAL;
-}
-
-
-static
-int PREFIX(scanCdataSection)(const ENCODING *enc, const char *ptr, const char *end,
- const char **nextTokPtr)
-{
- int i;
- /* CDATA[ */
- if (end - ptr < 6 * MINBPC(enc))
- return XML_TOK_PARTIAL;
- for (i = 0; i < 6; i++, ptr += MINBPC(enc)) {
- if (!CHAR_MATCHES(enc, ptr, "CDATA["[i])) {
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- }
- *nextTokPtr = ptr;
- return XML_TOK_CDATA_SECT_OPEN;
-}
-
-static
-int PREFIX(cdataSectionTok)(const ENCODING *enc, const char *ptr, const char *end,
- const char **nextTokPtr)
-{
- if (ptr == end)
- return XML_TOK_NONE;
- if (MINBPC(enc) > 1) {
- size_t n = end - ptr;
- if (n & (MINBPC(enc) - 1)) {
- n &= ~(MINBPC(enc) - 1);
- if (n == 0)
- return XML_TOK_PARTIAL;
- end = ptr + n;
- }
- }
- switch (BYTE_TYPE(enc, ptr)) {
- case BT_RSQB:
- ptr += MINBPC(enc);
- if (ptr == end)
- return XML_TOK_PARTIAL;
- if (!CHAR_MATCHES(enc, ptr, ']'))
- break;
- ptr += MINBPC(enc);
- if (ptr == end)
- return XML_TOK_PARTIAL;
- if (!CHAR_MATCHES(enc, ptr, '>')) {
- ptr -= MINBPC(enc);
- break;
- }
- *nextTokPtr = ptr + MINBPC(enc);
- return XML_TOK_CDATA_SECT_CLOSE;
- case BT_CR:
- ptr += MINBPC(enc);
- if (ptr == end)
- return XML_TOK_PARTIAL;
- if (BYTE_TYPE(enc, ptr) == BT_LF)
- ptr += MINBPC(enc);
- *nextTokPtr = ptr;
- return XML_TOK_DATA_NEWLINE;
- case BT_LF:
- *nextTokPtr = ptr + MINBPC(enc);
- return XML_TOK_DATA_NEWLINE;
- INVALID_CASES(ptr, nextTokPtr)
- default:
- ptr += MINBPC(enc);
- break;
- }
- while (ptr != end) {
- switch (BYTE_TYPE(enc, ptr)) {
-#define LEAD_CASE(n) \
- case BT_LEAD ## n: \
- if (end - ptr < n || IS_INVALID_CHAR(enc, ptr, n)) { \
- *nextTokPtr = ptr; \
- return XML_TOK_DATA_CHARS; \
- } \
- ptr += n; \
- break;
- LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4)
-#undef LEAD_CASE
- case BT_NONXML:
- case BT_MALFORM:
- case BT_TRAIL:
- case BT_CR:
- case BT_LF:
- case BT_RSQB:
- *nextTokPtr = ptr;
- return XML_TOK_DATA_CHARS;
- default:
- ptr += MINBPC(enc);
- break;
- }
- }
- *nextTokPtr = ptr;
- return XML_TOK_DATA_CHARS;
-}
-
-/* ptr points to character following "</" */
-
-static
-int PREFIX(scanEndTag)(const ENCODING *enc, const char *ptr, const char *end,
- const char **nextTokPtr)
-{
- if (ptr == end)
- return XML_TOK_PARTIAL;
- switch (BYTE_TYPE(enc, ptr)) {
- CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr)
- default:
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- while (ptr != end) {
- switch (BYTE_TYPE(enc, ptr)) {
- CHECK_NAME_CASES(enc, ptr, end, nextTokPtr)
- case BT_S: case BT_CR: case BT_LF:
- for (ptr += MINBPC(enc); ptr != end; ptr += MINBPC(enc)) {
- switch (BYTE_TYPE(enc, ptr)) {
- case BT_S: case BT_CR: case BT_LF:
- break;
- case BT_GT:
- *nextTokPtr = ptr + MINBPC(enc);
- return XML_TOK_END_TAG;
- default:
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- }
- return XML_TOK_PARTIAL;
-#ifdef XML_NS
- case BT_COLON:
- /* no need to check qname syntax here, since end-tag must match exactly */
- ptr += MINBPC(enc);
- break;
-#endif
- case BT_GT:
- *nextTokPtr = ptr + MINBPC(enc);
- return XML_TOK_END_TAG;
- default:
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- }
- return XML_TOK_PARTIAL;
-}
-
-/* ptr points to character following "&#X" */
-
-static
-int PREFIX(scanHexCharRef)(const ENCODING *enc, const char *ptr, const char *end,
- const char **nextTokPtr)
-{
- if (ptr != end) {
- switch (BYTE_TYPE(enc, ptr)) {
- case BT_DIGIT:
- case BT_HEX:
- break;
- default:
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- for (ptr += MINBPC(enc); ptr != end; ptr += MINBPC(enc)) {
- switch (BYTE_TYPE(enc, ptr)) {
- case BT_DIGIT:
- case BT_HEX:
- break;
- case BT_SEMI:
- *nextTokPtr = ptr + MINBPC(enc);
- return XML_TOK_CHAR_REF;
- default:
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- }
- }
- return XML_TOK_PARTIAL;
-}
-
-/* ptr points to character following "&#" */
-
-static
-int PREFIX(scanCharRef)(const ENCODING *enc, const char *ptr, const char *end,
- const char **nextTokPtr)
-{
- if (ptr != end) {
- if (CHAR_MATCHES(enc, ptr, 'x'))
- return PREFIX(scanHexCharRef)(enc, ptr + MINBPC(enc), end, nextTokPtr);
- switch (BYTE_TYPE(enc, ptr)) {
- case BT_DIGIT:
- break;
- default:
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- for (ptr += MINBPC(enc); ptr != end; ptr += MINBPC(enc)) {
- switch (BYTE_TYPE(enc, ptr)) {
- case BT_DIGIT:
- break;
- case BT_SEMI:
- *nextTokPtr = ptr + MINBPC(enc);
- return XML_TOK_CHAR_REF;
- default:
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- }
- }
- return XML_TOK_PARTIAL;
-}
-
-/* ptr points to character following "&" */
-
-static
-int PREFIX(scanRef)(const ENCODING *enc, const char *ptr, const char *end,
- const char **nextTokPtr)
-{
- if (ptr == end)
- return XML_TOK_PARTIAL;
- switch (BYTE_TYPE(enc, ptr)) {
- CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr)
- case BT_NUM:
- return PREFIX(scanCharRef)(enc, ptr + MINBPC(enc), end, nextTokPtr);
- default:
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- while (ptr != end) {
- switch (BYTE_TYPE(enc, ptr)) {
- CHECK_NAME_CASES(enc, ptr, end, nextTokPtr)
- case BT_SEMI:
- *nextTokPtr = ptr + MINBPC(enc);
- return XML_TOK_ENTITY_REF;
- default:
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- }
- return XML_TOK_PARTIAL;
-}
-
-/* ptr points to character following first character of attribute name */
-
-static
-int PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end,
- const char **nextTokPtr)
-{
-#ifdef XML_NS
- int hadColon = 0;
-#endif
- while (ptr != end) {
- switch (BYTE_TYPE(enc, ptr)) {
- CHECK_NAME_CASES(enc, ptr, end, nextTokPtr)
-#ifdef XML_NS
- case BT_COLON:
- if (hadColon) {
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- hadColon = 1;
- ptr += MINBPC(enc);
- if (ptr == end)
- return XML_TOK_PARTIAL;
- switch (BYTE_TYPE(enc, ptr)) {
- CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr)
- default:
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- break;
-#endif
- case BT_S: case BT_CR: case BT_LF:
- for (;;) {
- int t;
-
- ptr += MINBPC(enc);
- if (ptr == end)
- return XML_TOK_PARTIAL;
- t = BYTE_TYPE(enc, ptr);
- if (t == BT_EQUALS)
- break;
- switch (t) {
- case BT_S:
- case BT_LF:
- case BT_CR:
- break;
- default:
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- }
- /* fall through */
- case BT_EQUALS:
- {
- int open;
-#ifdef XML_NS
- hadColon = 0;
-#endif
- for (;;) {
-
- ptr += MINBPC(enc);
- if (ptr == end)
- return XML_TOK_PARTIAL;
- open = BYTE_TYPE(enc, ptr);
- if (open == BT_QUOT || open == BT_APOS)
- break;
- switch (open) {
- case BT_S:
- case BT_LF:
- case BT_CR:
- break;
- default:
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- }
- ptr += MINBPC(enc);
- /* in attribute value */
- for (;;) {
- int t;
- if (ptr == end)
- return XML_TOK_PARTIAL;
- t = BYTE_TYPE(enc, ptr);
- if (t == open)
- break;
- switch (t) {
- INVALID_CASES(ptr, nextTokPtr)
- case BT_AMP:
- {
- int tok = PREFIX(scanRef)(enc, ptr + MINBPC(enc), end, &ptr);
- if (tok <= 0) {
- if (tok == XML_TOK_INVALID)
- *nextTokPtr = ptr;
- return tok;
- }
- break;
- }
- case BT_LT:
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- default:
- ptr += MINBPC(enc);
- break;
- }
- }
- ptr += MINBPC(enc);
- if (ptr == end)
- return XML_TOK_PARTIAL;
- switch (BYTE_TYPE(enc, ptr)) {
- case BT_S:
- case BT_CR:
- case BT_LF:
- break;
- case BT_SOL:
- goto sol;
- case BT_GT:
- goto gt;
- default:
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- /* ptr points to closing quote */
- for (;;) {
- ptr += MINBPC(enc);
- if (ptr == end)
- return XML_TOK_PARTIAL;
- switch (BYTE_TYPE(enc, ptr)) {
- CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr)
- case BT_S: case BT_CR: case BT_LF:
- continue;
- case BT_GT:
- gt:
- *nextTokPtr = ptr + MINBPC(enc);
- return XML_TOK_START_TAG_WITH_ATTS;
- case BT_SOL:
- sol:
- ptr += MINBPC(enc);
- if (ptr == end)
- return XML_TOK_PARTIAL;
- if (!CHAR_MATCHES(enc, ptr, '>')) {
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- *nextTokPtr = ptr + MINBPC(enc);
- return XML_TOK_EMPTY_ELEMENT_WITH_ATTS;
- default:
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- break;
- }
- break;
- }
- default:
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- }
- return XML_TOK_PARTIAL;
-}
-
-/* ptr points to character following "<" */
-
-static
-int PREFIX(scanLt)(const ENCODING *enc, const char *ptr, const char *end,
- const char **nextTokPtr)
-{
-#ifdef XML_NS
- int hadColon;
-#endif
- if (ptr == end)
- return XML_TOK_PARTIAL;
- switch (BYTE_TYPE(enc, ptr)) {
- CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr)
- case BT_EXCL:
- if ((ptr += MINBPC(enc)) == end)
- return XML_TOK_PARTIAL;
- switch (BYTE_TYPE(enc, ptr)) {
- case BT_MINUS:
- return PREFIX(scanComment)(enc, ptr + MINBPC(enc), end, nextTokPtr);
- case BT_LSQB:
- return PREFIX(scanCdataSection)(enc, ptr + MINBPC(enc), end, nextTokPtr);
- }
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- case BT_QUEST:
- return PREFIX(scanPi)(enc, ptr + MINBPC(enc), end, nextTokPtr);
- case BT_SOL:
- return PREFIX(scanEndTag)(enc, ptr + MINBPC(enc), end, nextTokPtr);
- default:
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
-#ifdef XML_NS
- hadColon = 0;
-#endif
- /* we have a start-tag */
- while (ptr != end) {
- switch (BYTE_TYPE(enc, ptr)) {
- CHECK_NAME_CASES(enc, ptr, end, nextTokPtr)
-#ifdef XML_NS
- case BT_COLON:
- if (hadColon) {
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- hadColon = 1;
- ptr += MINBPC(enc);
- if (ptr == end)
- return XML_TOK_PARTIAL;
- switch (BYTE_TYPE(enc, ptr)) {
- CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr)
- default:
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- break;
-#endif
- case BT_S: case BT_CR: case BT_LF:
- {
- ptr += MINBPC(enc);
- while (ptr != end) {
- switch (BYTE_TYPE(enc, ptr)) {
- CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr)
- case BT_GT:
- goto gt;
- case BT_SOL:
- goto sol;
- case BT_S: case BT_CR: case BT_LF:
- ptr += MINBPC(enc);
- continue;
- default:
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- return PREFIX(scanAtts)(enc, ptr, end, nextTokPtr);
- }
- return XML_TOK_PARTIAL;
- }
- case BT_GT:
- gt:
- *nextTokPtr = ptr + MINBPC(enc);
- return XML_TOK_START_TAG_NO_ATTS;
- case BT_SOL:
- sol:
- ptr += MINBPC(enc);
- if (ptr == end)
- return XML_TOK_PARTIAL;
- if (!CHAR_MATCHES(enc, ptr, '>')) {
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- *nextTokPtr = ptr + MINBPC(enc);
- return XML_TOK_EMPTY_ELEMENT_NO_ATTS;
- default:
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- }
- return XML_TOK_PARTIAL;
-}
-
-static
-int PREFIX(contentTok)(const ENCODING *enc, const char *ptr, const char *end,
- const char **nextTokPtr)
-{
- if (ptr == end)
- return XML_TOK_NONE;
- if (MINBPC(enc) > 1) {
- size_t n = end - ptr;
- if (n & (MINBPC(enc) - 1)) {
- n &= ~(MINBPC(enc) - 1);
- if (n == 0)
- return XML_TOK_PARTIAL;
- end = ptr + n;
- }
- }
- switch (BYTE_TYPE(enc, ptr)) {
- case BT_LT:
- return PREFIX(scanLt)(enc, ptr + MINBPC(enc), end, nextTokPtr);
- case BT_AMP:
- return PREFIX(scanRef)(enc, ptr + MINBPC(enc), end, nextTokPtr);
- case BT_CR:
- ptr += MINBPC(enc);
- if (ptr == end)
- return XML_TOK_TRAILING_CR;
- if (BYTE_TYPE(enc, ptr) == BT_LF)
- ptr += MINBPC(enc);
- *nextTokPtr = ptr;
- return XML_TOK_DATA_NEWLINE;
- case BT_LF:
- *nextTokPtr = ptr + MINBPC(enc);
- return XML_TOK_DATA_NEWLINE;
- case BT_RSQB:
- ptr += MINBPC(enc);
- if (ptr == end)
- return XML_TOK_TRAILING_RSQB;
- if (!CHAR_MATCHES(enc, ptr, ']'))
- break;
- ptr += MINBPC(enc);
- if (ptr == end)
- return XML_TOK_TRAILING_RSQB;
- if (!CHAR_MATCHES(enc, ptr, '>')) {
- ptr -= MINBPC(enc);
- break;
- }
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- INVALID_CASES(ptr, nextTokPtr)
- default:
- ptr += MINBPC(enc);
- break;
- }
- while (ptr != end) {
- switch (BYTE_TYPE(enc, ptr)) {
-#define LEAD_CASE(n) \
- case BT_LEAD ## n: \
- if (end - ptr < n || IS_INVALID_CHAR(enc, ptr, n)) { \
- *nextTokPtr = ptr; \
- return XML_TOK_DATA_CHARS; \
- } \
- ptr += n; \
- break;
- LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4)
-#undef LEAD_CASE
- case BT_RSQB:
- if (ptr + MINBPC(enc) != end) {
- if (!CHAR_MATCHES(enc, ptr + MINBPC(enc), ']')) {
- ptr += MINBPC(enc);
- break;
- }
- if (ptr + 2*MINBPC(enc) != end) {
- if (!CHAR_MATCHES(enc, ptr + 2*MINBPC(enc), '>')) {
- ptr += MINBPC(enc);
- break;
- }
- *nextTokPtr = ptr + 2*MINBPC(enc);
- return XML_TOK_INVALID;
- }
- }
- /* fall through */
- case BT_AMP:
- case BT_LT:
- case BT_NONXML:
- case BT_MALFORM:
- case BT_TRAIL:
- case BT_CR:
- case BT_LF:
- *nextTokPtr = ptr;
- return XML_TOK_DATA_CHARS;
- default:
- ptr += MINBPC(enc);
- break;
- }
- }
- *nextTokPtr = ptr;
- return XML_TOK_DATA_CHARS;
-}
-
-/* ptr points to character following "%" */
-
-static
-int PREFIX(scanPercent)(const ENCODING *enc, const char *ptr, const char *end,
- const char **nextTokPtr)
-{
- if (ptr == end)
- return XML_TOK_PARTIAL;
- switch (BYTE_TYPE(enc, ptr)) {
- CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr)
- case BT_S: case BT_LF: case BT_CR: case BT_PERCNT:
- *nextTokPtr = ptr;
- return XML_TOK_PERCENT;
- default:
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- while (ptr != end) {
- switch (BYTE_TYPE(enc, ptr)) {
- CHECK_NAME_CASES(enc, ptr, end, nextTokPtr)
- case BT_SEMI:
- *nextTokPtr = ptr + MINBPC(enc);
- return XML_TOK_PARAM_ENTITY_REF;
- default:
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- }
- return XML_TOK_PARTIAL;
-}
-
-static
-int PREFIX(scanPoundName)(const ENCODING *enc, const char *ptr, const char *end,
- const char **nextTokPtr)
-{
- if (ptr == end)
- return XML_TOK_PARTIAL;
- switch (BYTE_TYPE(enc, ptr)) {
- CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr)
- default:
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- while (ptr != end) {
- switch (BYTE_TYPE(enc, ptr)) {
- CHECK_NAME_CASES(enc, ptr, end, nextTokPtr)
- case BT_CR: case BT_LF: case BT_S:
- case BT_RPAR: case BT_GT: case BT_PERCNT: case BT_VERBAR:
- *nextTokPtr = ptr;
- return XML_TOK_POUND_NAME;
- default:
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- }
- return -XML_TOK_POUND_NAME;
-}
-
-static
-int PREFIX(scanLit)(int open, const ENCODING *enc,
- const char *ptr, const char *end,
- const char **nextTokPtr)
-{
- while (ptr != end) {
- int t = BYTE_TYPE(enc, ptr);
- switch (t) {
- INVALID_CASES(ptr, nextTokPtr)
- case BT_QUOT:
- case BT_APOS:
- ptr += MINBPC(enc);
- if (t != open)
- break;
- if (ptr == end)
- return -XML_TOK_LITERAL;
- *nextTokPtr = ptr;
- switch (BYTE_TYPE(enc, ptr)) {
- case BT_S: case BT_CR: case BT_LF:
- case BT_GT: case BT_PERCNT: case BT_LSQB:
- return XML_TOK_LITERAL;
- default:
- return XML_TOK_INVALID;
- }
- default:
- ptr += MINBPC(enc);
- break;
- }
- }
- return XML_TOK_PARTIAL;
-}
-
-static
-int PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end,
- const char **nextTokPtr)
-{
- int tok;
- if (ptr == end)
- return XML_TOK_NONE;
- if (MINBPC(enc) > 1) {
- size_t n = end - ptr;
- if (n & (MINBPC(enc) - 1)) {
- n &= ~(MINBPC(enc) - 1);
- if (n == 0)
- return XML_TOK_PARTIAL;
- end = ptr + n;
- }
- }
- switch (BYTE_TYPE(enc, ptr)) {
- case BT_QUOT:
- return PREFIX(scanLit)(BT_QUOT, enc, ptr + MINBPC(enc), end, nextTokPtr);
- case BT_APOS:
- return PREFIX(scanLit)(BT_APOS, enc, ptr + MINBPC(enc), end, nextTokPtr);
- case BT_LT:
- {
- ptr += MINBPC(enc);
- if (ptr == end)
- return XML_TOK_PARTIAL;
- switch (BYTE_TYPE(enc, ptr)) {
- case BT_EXCL:
- return PREFIX(scanDecl)(enc, ptr + MINBPC(enc), end, nextTokPtr);
- case BT_QUEST:
- return PREFIX(scanPi)(enc, ptr + MINBPC(enc), end, nextTokPtr);
- case BT_NMSTRT:
- case BT_HEX:
- case BT_NONASCII:
- case BT_LEAD2:
- case BT_LEAD3:
- case BT_LEAD4:
- *nextTokPtr = ptr - MINBPC(enc);
- return XML_TOK_INSTANCE_START;
- }
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- case BT_CR:
- if (ptr + MINBPC(enc) == end)
- return -XML_TOK_PROLOG_S;
- /* fall through */
- case BT_S: case BT_LF:
- for (;;) {
- ptr += MINBPC(enc);
- if (ptr == end)
- break;
- switch (BYTE_TYPE(enc, ptr)) {
- case BT_S: case BT_LF:
- break;
- case BT_CR:
- /* don't split CR/LF pair */
- if (ptr + MINBPC(enc) != end)
- break;
- /* fall through */
- default:
- *nextTokPtr = ptr;
- return XML_TOK_PROLOG_S;
- }
- }
- *nextTokPtr = ptr;
- return XML_TOK_PROLOG_S;
- case BT_PERCNT:
- return PREFIX(scanPercent)(enc, ptr + MINBPC(enc), end, nextTokPtr);
- case BT_COMMA:
- *nextTokPtr = ptr + MINBPC(enc);
- return XML_TOK_COMMA;
- case BT_LSQB:
- *nextTokPtr = ptr + MINBPC(enc);
- return XML_TOK_OPEN_BRACKET;
- case BT_RSQB:
- ptr += MINBPC(enc);
- if (ptr == end)
- return -XML_TOK_CLOSE_BRACKET;
- if (CHAR_MATCHES(enc, ptr, ']')) {
- if (ptr + MINBPC(enc) == end)
- return XML_TOK_PARTIAL;
- if (CHAR_MATCHES(enc, ptr + MINBPC(enc), '>')) {
- *nextTokPtr = ptr + 2*MINBPC(enc);
- return XML_TOK_COND_SECT_CLOSE;
- }
- }
- *nextTokPtr = ptr;
- return XML_TOK_CLOSE_BRACKET;
- case BT_LPAR:
- *nextTokPtr = ptr + MINBPC(enc);
- return XML_TOK_OPEN_PAREN;
- case BT_RPAR:
- ptr += MINBPC(enc);
- if (ptr == end)
- return -XML_TOK_CLOSE_PAREN;
- switch (BYTE_TYPE(enc, ptr)) {
- case BT_AST:
- *nextTokPtr = ptr + MINBPC(enc);
- return XML_TOK_CLOSE_PAREN_ASTERISK;
- case BT_QUEST:
- *nextTokPtr = ptr + MINBPC(enc);
- return XML_TOK_CLOSE_PAREN_QUESTION;
- case BT_PLUS:
- *nextTokPtr = ptr + MINBPC(enc);
- return XML_TOK_CLOSE_PAREN_PLUS;
- case BT_CR: case BT_LF: case BT_S:
- case BT_GT: case BT_COMMA: case BT_VERBAR:
- case BT_RPAR:
- *nextTokPtr = ptr;
- return XML_TOK_CLOSE_PAREN;
- }
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- case BT_VERBAR:
- *nextTokPtr = ptr + MINBPC(enc);
- return XML_TOK_OR;
- case BT_GT:
- *nextTokPtr = ptr + MINBPC(enc);
- return XML_TOK_DECL_CLOSE;
- case BT_NUM:
- return PREFIX(scanPoundName)(enc, ptr + MINBPC(enc), end, nextTokPtr);
-#define LEAD_CASE(n) \
- case BT_LEAD ## n: \
- if (end - ptr < n) \
- return XML_TOK_PARTIAL_CHAR; \
- if (IS_NMSTRT_CHAR(enc, ptr, n)) { \
- ptr += n; \
- tok = XML_TOK_NAME; \
- break; \
- } \
- if (IS_NAME_CHAR(enc, ptr, n)) { \
- ptr += n; \
- tok = XML_TOK_NMTOKEN; \
- break; \
- } \
- *nextTokPtr = ptr; \
- return XML_TOK_INVALID;
- LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4)
-#undef LEAD_CASE
- case BT_NMSTRT:
- case BT_HEX:
- tok = XML_TOK_NAME;
- ptr += MINBPC(enc);
- break;
- case BT_DIGIT:
- case BT_NAME:
- case BT_MINUS:
-#ifdef XML_NS
- case BT_COLON:
-#endif
- tok = XML_TOK_NMTOKEN;
- ptr += MINBPC(enc);
- break;
- case BT_NONASCII:
- if (IS_NMSTRT_CHAR_MINBPC(enc, ptr)) {
- ptr += MINBPC(enc);
- tok = XML_TOK_NAME;
- break;
- }
- if (IS_NAME_CHAR_MINBPC(enc, ptr)) {
- ptr += MINBPC(enc);
- tok = XML_TOK_NMTOKEN;
- break;
- }
- /* fall through */
- default:
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- while (ptr != end) {
- switch (BYTE_TYPE(enc, ptr)) {
- CHECK_NAME_CASES(enc, ptr, end, nextTokPtr)
- case BT_GT: case BT_RPAR: case BT_COMMA:
- case BT_VERBAR: case BT_LSQB: case BT_PERCNT:
- case BT_S: case BT_CR: case BT_LF:
- *nextTokPtr = ptr;
- return tok;
-#ifdef XML_NS
- case BT_COLON:
- ptr += MINBPC(enc);
- switch (tok) {
- case XML_TOK_NAME:
- if (ptr == end)
- return XML_TOK_PARTIAL;
- tok = XML_TOK_PREFIXED_NAME;
- switch (BYTE_TYPE(enc, ptr)) {
- CHECK_NAME_CASES(enc, ptr, end, nextTokPtr)
- default:
- tok = XML_TOK_NMTOKEN;
- break;
- }
- break;
- case XML_TOK_PREFIXED_NAME:
- tok = XML_TOK_NMTOKEN;
- break;
- }
- break;
-#endif
- case BT_PLUS:
- if (tok == XML_TOK_NMTOKEN) {
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- *nextTokPtr = ptr + MINBPC(enc);
- return XML_TOK_NAME_PLUS;
- case BT_AST:
- if (tok == XML_TOK_NMTOKEN) {
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- *nextTokPtr = ptr + MINBPC(enc);
- return XML_TOK_NAME_ASTERISK;
- case BT_QUEST:
- if (tok == XML_TOK_NMTOKEN) {
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- *nextTokPtr = ptr + MINBPC(enc);
- return XML_TOK_NAME_QUESTION;
- default:
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- }
- }
- return -tok;
-}
-
-static
-int PREFIX(attributeValueTok)(const ENCODING *enc, const char *ptr, const char *end,
- const char **nextTokPtr)
-{
- const char *start;
- if (ptr == end)
- return XML_TOK_NONE;
- start = ptr;
- while (ptr != end) {
- switch (BYTE_TYPE(enc, ptr)) {
-#define LEAD_CASE(n) \
- case BT_LEAD ## n: ptr += n; break;
- LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4)
-#undef LEAD_CASE
- case BT_AMP:
- if (ptr == start)
- return PREFIX(scanRef)(enc, ptr + MINBPC(enc), end, nextTokPtr);
- *nextTokPtr = ptr;
- return XML_TOK_DATA_CHARS;
- case BT_LT:
- /* this is for inside entity references */
- *nextTokPtr = ptr;
- return XML_TOK_INVALID;
- case BT_LF:
- if (ptr == start) {
- *nextTokPtr = ptr + MINBPC(enc);
- return XML_TOK_DATA_NEWLINE;
- }
- *nextTokPtr = ptr;
- return XML_TOK_DATA_CHARS;
- case BT_CR:
- if (ptr == start) {
- ptr += MINBPC(enc);
- if (ptr == end)
- return XML_TOK_TRAILING_CR;
- if (BYTE_TYPE(enc, ptr) == BT_LF)
- ptr += MINBPC(enc);
- *nextTokPtr = ptr;
- return XML_TOK_DATA_NEWLINE;
- }
- *nextTokPtr = ptr;
- return XML_TOK_DATA_CHARS;
- case BT_S:
- if (ptr == start) {
- *nextTokPtr = ptr + MINBPC(enc);
- return XML_TOK_ATTRIBUTE_VALUE_S;
- }
- *nextTokPtr = ptr;
- return XML_TOK_DATA_CHARS;
- default:
- ptr += MINBPC(enc);
- break;
- }
- }
- *nextTokPtr = ptr;
- return XML_TOK_DATA_CHARS;
-}
-
-static
-int PREFIX(entityValueTok)(const ENCODING *enc, const char *ptr, const char *end,
- const char **nextTokPtr)
-{
- const char *start;
- if (ptr == end)
- return XML_TOK_NONE;
- start = ptr;
- while (ptr != end) {
- switch (BYTE_TYPE(enc, ptr)) {
-#define LEAD_CASE(n) \
- case BT_LEAD ## n: ptr += n; break;
- LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4)
-#undef LEAD_CASE
- case BT_AMP:
- if (ptr == start)
- return PREFIX(scanRef)(enc, ptr + MINBPC(enc), end, nextTokPtr);
- *nextTokPtr = ptr;
- return XML_TOK_DATA_CHARS;
- case BT_PERCNT:
- if (ptr == start)
- return PREFIX(scanPercent)(enc, ptr + MINBPC(enc), end, nextTokPtr);
- *nextTokPtr = ptr;
- return XML_TOK_DATA_CHARS;
- case BT_LF:
- if (ptr == start) {
- *nextTokPtr = ptr + MINBPC(enc);
- return XML_TOK_DATA_NEWLINE;
- }
- *nextTokPtr = ptr;
- return XML_TOK_DATA_CHARS;
- case BT_CR:
- if (ptr == start) {
- ptr += MINBPC(enc);
- if (ptr == end)
- return XML_TOK_TRAILING_CR;
- if (BYTE_TYPE(enc, ptr) == BT_LF)
- ptr += MINBPC(enc);
- *nextTokPtr = ptr;
- return XML_TOK_DATA_NEWLINE;
- }
- *nextTokPtr = ptr;
- return XML_TOK_DATA_CHARS;
- default:
- ptr += MINBPC(enc);
- break;
- }
- }
- *nextTokPtr = ptr;
- return XML_TOK_DATA_CHARS;
-}
-
-#ifdef XML_DTD
-
-static
-int PREFIX(ignoreSectionTok)(const ENCODING *enc, const char *ptr, const char *end,
- const char **nextTokPtr)
-{
- int level = 0;
- if (MINBPC(enc) > 1) {
- size_t n = end - ptr;
- if (n & (MINBPC(enc) - 1)) {
- n &= ~(MINBPC(enc) - 1);
- end = ptr + n;
- }
- }
- while (ptr != end) {
- switch (BYTE_TYPE(enc, ptr)) {
- INVALID_CASES(ptr, nextTokPtr)
- case BT_LT:
- if ((ptr += MINBPC(enc)) == end)
- return XML_TOK_PARTIAL;
- if (CHAR_MATCHES(enc, ptr, '!')) {
- if ((ptr += MINBPC(enc)) == end)
- return XML_TOK_PARTIAL;
- if (CHAR_MATCHES(enc, ptr, '[')) {
- ++level;
- ptr += MINBPC(enc);
- }
- }
- break;
- case BT_RSQB:
- if ((ptr += MINBPC(enc)) == end)
- return XML_TOK_PARTIAL;
- if (CHAR_MATCHES(enc, ptr, ']')) {
- if ((ptr += MINBPC(enc)) == end)
- return XML_TOK_PARTIAL;
- if (CHAR_MATCHES(enc, ptr, '>')) {
- ptr += MINBPC(enc);
- if (level == 0) {
- *nextTokPtr = ptr;
- return XML_TOK_IGNORE_SECT;
- }
- --level;
- }
- }
- break;
- default:
- ptr += MINBPC(enc);
- break;
- }
- }
- return XML_TOK_PARTIAL;
-}
-
-#endif /* XML_DTD */
-
-static
-int PREFIX(isPublicId)(const ENCODING *enc, const char *ptr, const char *end,
- const char **badPtr)
-{
- ptr += MINBPC(enc);
- end -= MINBPC(enc);
- for (; ptr != end; ptr += MINBPC(enc)) {
- switch (BYTE_TYPE(enc, ptr)) {
- case BT_DIGIT:
- case BT_HEX:
- case BT_MINUS:
- case BT_APOS:
- case BT_LPAR:
- case BT_RPAR:
- case BT_PLUS:
- case BT_COMMA:
- case BT_SOL:
- case BT_EQUALS:
- case BT_QUEST:
- case BT_CR:
- case BT_LF:
- case BT_SEMI:
- case BT_EXCL:
- case BT_AST:
- case BT_PERCNT:
- case BT_NUM:
-#ifdef XML_NS
- case BT_COLON:
-#endif
- break;
- case BT_S:
- if (CHAR_MATCHES(enc, ptr, '\t')) {
- *badPtr = ptr;
- return 0;
- }
- break;
- case BT_NAME:
- case BT_NMSTRT:
- if (!(BYTE_TO_ASCII(enc, ptr) & ~0x7f))
- break;
- default:
- switch (BYTE_TO_ASCII(enc, ptr)) {
- case 0x24: /* $ */
- case 0x40: /* @ */
- break;
- default:
- *badPtr = ptr;
- return 0;
- }
- break;
- }
- }
- return 1;
-}
-
-/* This must only be called for a well-formed start-tag or empty element tag.
-Returns the number of attributes. Pointers to the first attsMax attributes
-are stored in atts. */
-
-static
-int PREFIX(getAtts)(const ENCODING *enc, const char *ptr,
- int attsMax, ATTRIBUTE *atts)
-{
- enum { other, inName, inValue } state = inName;
- int nAtts = 0;
- int open = 0; /* defined when state == inValue;
- initialization just to shut up compilers */
-
- for (ptr += MINBPC(enc);; ptr += MINBPC(enc)) {
- switch (BYTE_TYPE(enc, ptr)) {
-#define START_NAME \
- if (state == other) { \
- if (nAtts < attsMax) { \
- atts[nAtts].name = ptr; \
- atts[nAtts].normalized = 1; \
- } \
- state = inName; \
- }
-#define LEAD_CASE(n) \
- case BT_LEAD ## n: START_NAME ptr += (n - MINBPC(enc)); break;
- LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4)
-#undef LEAD_CASE
- case BT_NONASCII:
- case BT_NMSTRT:
- case BT_HEX:
- START_NAME
- break;
-#undef START_NAME
- case BT_QUOT:
- if (state != inValue) {
- if (nAtts < attsMax)
- atts[nAtts].valuePtr = ptr + MINBPC(enc);
- state = inValue;
- open = BT_QUOT;
- }
- else if (open == BT_QUOT) {
- state = other;
- if (nAtts < attsMax)
- atts[nAtts].valueEnd = ptr;
- nAtts++;
- }
- break;
- case BT_APOS:
- if (state != inValue) {
- if (nAtts < attsMax)
- atts[nAtts].valuePtr = ptr + MINBPC(enc);
- state = inValue;
- open = BT_APOS;
- }
- else if (open == BT_APOS) {
- state = other;
- if (nAtts < attsMax)
- atts[nAtts].valueEnd = ptr;
- nAtts++;
- }
- break;
- case BT_AMP:
- if (nAtts < attsMax)
- atts[nAtts].normalized = 0;
- break;
- case BT_S:
- if (state == inName)
- state = other;
- else if (state == inValue
- && nAtts < attsMax
- && atts[nAtts].normalized
- && (ptr == atts[nAtts].valuePtr
- || BYTE_TO_ASCII(enc, ptr) != ' '
- || BYTE_TO_ASCII(enc, ptr + MINBPC(enc)) == ' '
- || BYTE_TYPE(enc, ptr + MINBPC(enc)) == open))
- atts[nAtts].normalized = 0;
- break;
- case BT_CR: case BT_LF:
- /* This case ensures that the first attribute name is counted
- Apart from that we could just change state on the quote. */
- if (state == inName)
- state = other;
- else if (state == inValue && nAtts < attsMax)
- atts[nAtts].normalized = 0;
- break;
- case BT_GT:
- case BT_SOL:
- if (state != inValue)
- return nAtts;
- break;
- default:
- break;
- }
- }
- /* not reached */
-}
-
-static
-int PREFIX(charRefNumber)(const ENCODING *enc, const char *ptr)
-{
- int result = 0;
- /* skip &# */
- ptr += 2*MINBPC(enc);
- if (CHAR_MATCHES(enc, ptr, 'x')) {
- for (ptr += MINBPC(enc); !CHAR_MATCHES(enc, ptr, ';'); ptr += MINBPC(enc)) {
- int c = BYTE_TO_ASCII(enc, ptr);
- switch (c) {
- case '0': case '1': case '2': case '3': case '4':
- case '5': case '6': case '7': case '8': case '9':
- result <<= 4;
- result |= (c - '0');
- break;
- case 'A': case 'B': case 'C': case 'D': case 'E': case 'F':
- result <<= 4;
- result += 10 + (c - 'A');
- break;
- case 'a': case 'b': case 'c': case 'd': case 'e': case 'f':
- result <<= 4;
- result += 10 + (c - 'a');
- break;
- }
- if (result >= 0x110000)
- return -1;
- }
- }
- else {
- for (; !CHAR_MATCHES(enc, ptr, ';'); ptr += MINBPC(enc)) {
- int c = BYTE_TO_ASCII(enc, ptr);
- result *= 10;
- result += (c - '0');
- if (result >= 0x110000)
- return -1;
- }
- }
- return checkCharRefNumber(result);
-}
-
-static
-int PREFIX(predefinedEntityName)(const ENCODING *enc, const char *ptr, const char *end)
-{
- switch ((end - ptr)/MINBPC(enc)) {
- case 2:
- if (CHAR_MATCHES(enc, ptr + MINBPC(enc), 't')) {
- switch (BYTE_TO_ASCII(enc, ptr)) {
- case 'l':
- return '<';
- case 'g':
- return '>';
- }
- }
- break;
- case 3:
- if (CHAR_MATCHES(enc, ptr, 'a')) {
- ptr += MINBPC(enc);
- if (CHAR_MATCHES(enc, ptr, 'm')) {
- ptr += MINBPC(enc);
- if (CHAR_MATCHES(enc, ptr, 'p'))
- return '&';
- }
- }
- break;
- case 4:
- switch (BYTE_TO_ASCII(enc, ptr)) {
- case 'q':
- ptr += MINBPC(enc);
- if (CHAR_MATCHES(enc, ptr, 'u')) {
- ptr += MINBPC(enc);
- if (CHAR_MATCHES(enc, ptr, 'o')) {
- ptr += MINBPC(enc);
- if (CHAR_MATCHES(enc, ptr, 't'))
- return '"';
- }
- }
- break;
- case 'a':
- ptr += MINBPC(enc);
- if (CHAR_MATCHES(enc, ptr, 'p')) {
- ptr += MINBPC(enc);
- if (CHAR_MATCHES(enc, ptr, 'o')) {
- ptr += MINBPC(enc);
- if (CHAR_MATCHES(enc, ptr, 's'))
- return '\'';
- }
- }
- break;
- }
- }
- return 0;
-}
-
-static
-int PREFIX(sameName)(const ENCODING *enc, const char *ptr1, const char *ptr2)
-{
- for (;;) {
- switch (BYTE_TYPE(enc, ptr1)) {
-#define LEAD_CASE(n) \
- case BT_LEAD ## n: \
- if (*ptr1++ != *ptr2++) \
- return 0;
- LEAD_CASE(4) LEAD_CASE(3) LEAD_CASE(2)
-#undef LEAD_CASE
- /* fall through */
- if (*ptr1++ != *ptr2++)
- return 0;
- break;
- case BT_NONASCII:
- case BT_NMSTRT:
-#ifdef XML_NS
- case BT_COLON:
-#endif
- case BT_HEX:
- case BT_DIGIT:
- case BT_NAME:
- case BT_MINUS:
- if (*ptr2++ != *ptr1++)
- return 0;
- if (MINBPC(enc) > 1) {
- if (*ptr2++ != *ptr1++)
- return 0;
- if (MINBPC(enc) > 2) {
- if (*ptr2++ != *ptr1++)
- return 0;
- if (MINBPC(enc) > 3) {
- if (*ptr2++ != *ptr1++)
- return 0;
- }
- }
- }
- break;
- default:
- if (MINBPC(enc) == 1 && *ptr1 == *ptr2)
- return 1;
- switch (BYTE_TYPE(enc, ptr2)) {
- case BT_LEAD2:
- case BT_LEAD3:
- case BT_LEAD4:
- case BT_NONASCII:
- case BT_NMSTRT:
-#ifdef XML_NS
- case BT_COLON:
-#endif
- case BT_HEX:
- case BT_DIGIT:
- case BT_NAME:
- case BT_MINUS:
- return 0;
- default:
- return 1;
- }
- }
- }
- /* not reached */
-}
-
-static
-int PREFIX(nameMatchesAscii)(const ENCODING *enc, const char *ptr1,
- const char *end1, const char *ptr2)
-{
- for (; *ptr2; ptr1 += MINBPC(enc), ptr2++) {
- if (ptr1 == end1)
- return 0;
- if (!CHAR_MATCHES(enc, ptr1, *ptr2))
- return 0;
- }
- return ptr1 == end1;
-}
-
-static
-int PREFIX(nameLength)(const ENCODING *enc, const char *ptr)
-{
- const char *start = ptr;
- for (;;) {
- switch (BYTE_TYPE(enc, ptr)) {
-#define LEAD_CASE(n) \
- case BT_LEAD ## n: ptr += n; break;
- LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4)
-#undef LEAD_CASE
- case BT_NONASCII:
- case BT_NMSTRT:
-#ifdef XML_NS
- case BT_COLON:
-#endif
- case BT_HEX:
- case BT_DIGIT:
- case BT_NAME:
- case BT_MINUS:
- ptr += MINBPC(enc);
- break;
- default:
- return ptr - start;
- }
- }
-}
-
-static
-const char *PREFIX(skipS)(const ENCODING *enc, const char *ptr)
-{
- for (;;) {
- switch (BYTE_TYPE(enc, ptr)) {
- case BT_LF:
- case BT_CR:
- case BT_S:
- ptr += MINBPC(enc);
- break;
- default:
- return ptr;
- }
- }
-}
-
-static
-void PREFIX(updatePosition)(const ENCODING *enc,
- const char *ptr,
- const char *end,
- POSITION *pos)
-{
- while (ptr != end) {
- switch (BYTE_TYPE(enc, ptr)) {
-#define LEAD_CASE(n) \
- case BT_LEAD ## n: \
- ptr += n; \
- break;
- LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4)
-#undef LEAD_CASE
- case BT_LF:
- pos->columnNumber = (unsigned)-1;
- pos->lineNumber++;
- ptr += MINBPC(enc);
- break;
- case BT_CR:
- pos->lineNumber++;
- ptr += MINBPC(enc);
- if (ptr != end && BYTE_TYPE(enc, ptr) == BT_LF)
- ptr += MINBPC(enc);
- pos->columnNumber = (unsigned)-1;
- break;
- default:
- ptr += MINBPC(enc);
- break;
- }
- pos->columnNumber++;
- }
-}
-
-#undef DO_LEAD_CASE
-#undef MULTIBYTE_CASES
-#undef INVALID_CASES
-#undef CHECK_NAME_CASE
-#undef CHECK_NAME_CASES
-#undef CHECK_NMSTRT_CASE
-#undef CHECK_NMSTRT_CASES
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/xmltok_impl.h
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/xmltok_impl.h 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/xmltok_impl.h 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,71 +0,0 @@
-/*
-The contents of this file are subject to the Mozilla Public License
-Version 1.1 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998, 1999
-James Clark. All Rights Reserved.
-
-Contributor(s):
-
-Alternatively, the contents of this file may be used under the terms
-of the GNU General Public License (the "GPL"), in which case the
-provisions of the GPL are applicable instead of those above. If you
-wish to allow use of your version of this file only under the terms of
-the GPL and not to allow others to use your version of this file under
-the MPL, indicate your decision by deleting the provisions above and
-replace them with the notice and other provisions required by the
-GPL. If you do not delete the provisions above, a recipient may use
-your version of this file under either the MPL or the GPL.
-*/
-
-enum {
- BT_NONXML,
- BT_MALFORM,
- BT_LT,
- BT_AMP,
- BT_RSQB,
- BT_LEAD2,
- BT_LEAD3,
- BT_LEAD4,
- BT_TRAIL,
- BT_CR,
- BT_LF,
- BT_GT,
- BT_QUOT,
- BT_APOS,
- BT_EQUALS,
- BT_QUEST,
- BT_EXCL,
- BT_SOL,
- BT_SEMI,
- BT_NUM,
- BT_LSQB,
- BT_S,
- BT_NMSTRT,
- BT_COLON,
- BT_HEX,
- BT_DIGIT,
- BT_NAME,
- BT_MINUS,
- BT_OTHER, /* known not to be a name or name start character */
- BT_NONASCII, /* might be a name or name start character */
- BT_PERCNT,
- BT_LPAR,
- BT_RPAR,
- BT_AST,
- BT_PLUS,
- BT_COMMA,
- BT_VERBAR
-};
-
-#include <stddef.h>
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/xmltok_ns.c
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/xmltok_ns.c 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmltok/xmltok_ns.c 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,96 +0,0 @@
-const ENCODING *NS(XmlGetUtf8InternalEncoding)(void)
-{
- return &ns(internal_utf8_encoding).enc;
-}
-
-const ENCODING *NS(XmlGetUtf16InternalEncoding)(void)
-{
-#if XML_BYTE_ORDER == 12
- return &ns(internal_little2_encoding).enc;
-#elif XML_BYTE_ORDER == 21
- return &ns(internal_big2_encoding).enc;
-#else
- const short n = 1;
- return *(const char *)&n ? &ns(internal_little2_encoding).enc : &ns(internal_big2_encoding).enc;
-#endif
-}
-
-static
-const ENCODING *NS(encodings)[] = {
- &ns(latin1_encoding).enc,
- &ns(ascii_encoding).enc,
- &ns(utf8_encoding).enc,
- &ns(big2_encoding).enc,
- &ns(big2_encoding).enc,
- &ns(little2_encoding).enc,
- &ns(utf8_encoding).enc /* NO_ENC */
-};
-
-static
-int NS(initScanProlog)(const ENCODING *enc, const char *ptr, const char *end,
- const char **nextTokPtr)
-{
- return initScan(NS(encodings), (const INIT_ENCODING *)enc, XML_PROLOG_STATE, ptr, end, nextTokPtr);
-}
-
-static
-int NS(initScanContent)(const ENCODING *enc, const char *ptr, const char *end,
- const char **nextTokPtr)
-{
- return initScan(NS(encodings), (const INIT_ENCODING *)enc, XML_CONTENT_STATE, ptr, end, nextTokPtr);
-}
-
-int NS(XmlInitEncoding)(INIT_ENCODING *p, const ENCODING **encPtr, const char *name)
-{
- int i = getEncodingIndex(name);
- if (i == UNKNOWN_ENC)
- return 0;
- SET_INIT_ENC_INDEX(p, i);
- p->initEnc.scanners[XML_PROLOG_STATE] = NS(initScanProlog);
- p->initEnc.scanners[XML_CONTENT_STATE] = NS(initScanContent);
- p->initEnc.updatePosition = initUpdatePosition;
- p->encPtr = encPtr;
- *encPtr = &(p->initEnc);
- return 1;
-}
-
-static
-const ENCODING *NS(findEncoding)(const ENCODING *enc, const char *ptr, const char *end)
-{
-#define ENCODING_MAX 128
- char buf[ENCODING_MAX];
- char *p = buf;
- int i;
- XmlUtf8Convert(enc, &ptr, end, &p, p + ENCODING_MAX - 1);
- if (ptr != end)
- return 0;
- *p = 0;
- if (streqci(buf, "UTF-16") && enc->minBytesPerChar == 2)
- return enc;
- i = getEncodingIndex(buf);
- if (i == UNKNOWN_ENC)
- return 0;
- return NS(encodings)[i];
-}
-
-int NS(XmlParseXmlDecl)(int isGeneralTextEntity,
- const ENCODING *enc,
- const char *ptr,
- const char *end,
- const char **badPtr,
- const char **versionPtr,
- const char **encodingName,
- const ENCODING **encoding,
- int *standalone)
-{
- return doParseXmlDecl(NS(findEncoding),
- isGeneralTextEntity,
- enc,
- ptr,
- end,
- badPtr,
- versionPtr,
- encodingName,
- encoding,
- standalone);
-}
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/codepage.c
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/codepage.c 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/codepage.c 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,90 +0,0 @@
-/*
-The contents of this file are subject to the Mozilla Public License
-Version 1.1 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998, 1999
-James Clark. All Rights Reserved.
-
-Contributor(s):
-
-Alternatively, the contents of this file may be used under the terms
-of the GNU General Public License (the "GPL"), in which case the
-provisions of the GPL are applicable instead of those above. If you
-wish to allow use of your version of this file only under the terms of
-the GPL and not to allow others to use your version of this file under
-the MPL, indicate your decision by deleting the provisions above and
-replace them with the notice and other provisions required by the
-GPL. If you do not delete the provisions above, a recipient may use
-your version of this file under either the MPL or the GPL.
-*/
-
-#include "codepage.h"
-
-#ifdef WIN32
-#define STRICT 1
-#define WIN32_LEAN_AND_MEAN 1
-
-#include <windows.h>
-
-int codepageMap(int cp, int *map)
-{
- int i;
- CPINFO info;
- if (!GetCPInfo(cp, &info) || info.MaxCharSize > 2)
- return 0;
- for (i = 0; i < 256; i++)
- map[i] = -1;
- if (info.MaxCharSize > 1) {
- for (i = 0; i < MAX_LEADBYTES; i++) {
- int j, lim;
- if (info.LeadByte[i] == 0 && info.LeadByte[i + 1] == 0)
- break;
- lim = info.LeadByte[i + 1];
- for (j = info.LeadByte[i]; j < lim; j++)
- map[j] = -2;
- }
- }
- for (i = 0; i < 256; i++) {
- if (map[i] == -1) {
- char c = i;
- unsigned short n;
- if (MultiByteToWideChar(cp, MB_PRECOMPOSED|MB_ERR_INVALID_CHARS,
- &c, 1, &n, 1) == 1)
- map[i] = n;
- }
- }
- return 1;
-}
-
-int codepageConvert(int cp, const char *p)
-{
- unsigned short c;
- if (MultiByteToWideChar(cp, MB_PRECOMPOSED|MB_ERR_INVALID_CHARS,
- p, 2, &c, 1) == 1)
- return c;
- return -1;
-}
-
-#else /* not WIN32 */
-
-int codepageMap(int cp, int *map)
-{
- return 0;
-}
-
-int codepageConvert(int cp, const char *p)
-{
- return -1;
-}
-
-#endif /* not WIN32 */
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/codepage.h
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/codepage.h 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/codepage.h 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,32 +0,0 @@
-/*
-The contents of this file are subject to the Mozilla Public License
-Version 1.1 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998, 1999
-James Clark. All Rights Reserved.
-
-Contributor(s):
-
-Alternatively, the contents of this file may be used under the terms
-of the GNU General Public License (the "GPL"), in which case the
-provisions of the GPL are applicable instead of those above. If you
-wish to allow use of your version of this file only under the terms of
-the GPL and not to allow others to use your version of this file under
-the MPL, indicate your decision by deleting the provisions above and
-replace them with the notice and other provisions required by the
-GPL. If you do not delete the provisions above, a recipient may use
-your version of this file under either the MPL or the GPL.
-*/
-
-int codepageMap(int cp, int *map);
-int codepageConvert(int cp, const char *p);
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/filemap.h
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/filemap.h 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/filemap.h 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,42 +0,0 @@
-/*
-The contents of this file are subject to the Mozilla Public License
-Version 1.1 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998, 1999
-James Clark. All Rights Reserved.
-
-Contributor(s):
-
-Alternatively, the contents of this file may be used under the terms
-of the GNU General Public License (the "GPL"), in which case the
-provisions of the GPL are applicable instead of those above. If you
-wish to allow use of your version of this file only under the terms of
-the GPL and not to allow others to use your version of this file under
-the MPL, indicate your decision by deleting the provisions above and
-replace them with the notice and other provisions required by the
-GPL. If you do not delete the provisions above, a recipient may use
-your version of this file under either the MPL or the GPL.
-*/
-
-
-#include <stddef.h>
-
-#ifdef XML_UNICODE
-int filemap(const wchar_t *name,
- void (*processor)(const void *, size_t, const wchar_t *, void *arg),
- void *arg);
-#else
-int filemap(const char *name,
- void (*processor)(const void *, size_t, const char *, void *arg),
- void *arg);
-#endif
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/readfilemap.c
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/readfilemap.c 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/readfilemap.c 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,99 +0,0 @@
-/*
-The contents of this file are subject to the Mozilla Public License
-Version 1.1 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998, 1999
-James Clark. All Rights Reserved.
-
-Contributor(s):
-
-Alternatively, the contents of this file may be used under the terms
-of the GNU General Public License (the "GPL"), in which case the
-provisions of the GPL are applicable instead of those above. If you
-wish to allow use of your version of this file only under the terms of
-the GPL and not to allow others to use your version of this file under
-the MPL, indicate your decision by deleting the provisions above and
-replace them with the notice and other provisions required by the
-GPL. If you do not delete the provisions above, a recipient may use
-your version of this file under either the MPL or the GPL.
-*/
-
-#include <sys/types.h>
-#include <sys/stat.h>
-#include <fcntl.h>
-#include <stdlib.h>
-#include <stdio.h>
-
-#ifndef S_ISREG
-#ifndef S_IFREG
-#define S_IFREG _S_IFREG
-#endif
-#ifndef S_IFMT
-#define S_IFMT _S_IFMT
-#endif
-#define S_ISREG(m) (((m) & S_IFMT) == S_IFREG)
-#endif /* not S_ISREG */
-
-#ifndef O_BINARY
-#ifdef _O_BINARY
-#define O_BINARY _O_BINARY
-#else
-#define O_BINARY 0
-#endif
-#endif
-
-int filemap(const char *name,
- void (*processor)(const void *, size_t, const char *, void *arg),
- void *arg)
-{
- size_t nbytes;
- int fd;
- int n;
- struct stat sb;
- void *p;
-
- fd = open(name, O_RDONLY|O_BINARY);
- if (fd < 0) {
- perror(name);
- return 0;
- }
- if (fstat(fd, &sb) < 0) {
- perror(name);
- return 0;
- }
- if (!S_ISREG(sb.st_mode)) {
- fprintf(stderr, "%s: not a regular file\n", name);
- return 0;
- }
- nbytes = sb.st_size;
- p = malloc(nbytes);
- if (!p) {
- fprintf(stderr, "%s: out of memory\n", name);
- return 0;
- }
- n = read(fd, p, nbytes);
- if (n < 0) {
- perror(name);
- close(fd);
- return 0;
- }
- if (n != nbytes) {
- fprintf(stderr, "%s: read unexpected number of bytes\n", name);
- close(fd);
- return 0;
- }
- processor(p, nbytes, name, arg);
- free(p);
- close(fd);
- return 1;
-}
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/unixfilemap.c
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/unixfilemap.c 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/unixfilemap.c 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,82 +0,0 @@
-/*
-The contents of this file are subject to the Mozilla Public License
-Version 1.1 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998, 1999
-James Clark. All Rights Reserved.
-
-Contributor(s):
-
-Alternatively, the contents of this file may be used under the terms
-of the GNU General Public License (the "GPL"), in which case the
-provisions of the GPL are applicable instead of those above. If you
-wish to allow use of your version of this file only under the terms of
-the GPL and not to allow others to use your version of this file under
-the MPL, indicate your decision by deleting the provisions above and
-replace them with the notice and other provisions required by the
-GPL. If you do not delete the provisions above, a recipient may use
-your version of this file under either the MPL or the GPL.
-*/
-
-#include <sys/types.h>
-#include <sys/mman.h>
-#include <sys/stat.h>
-#include <fcntl.h>
-#include <errno.h>
-#include <string.h>
-#include <stdio.h>
-
-#ifndef MAP_FILE
-#define MAP_FILE 0
-#endif
-
-#include "filemap.h"
-
-int filemap(const char *name,
- void (*processor)(const void *, size_t, const char *, void *arg),
- void *arg)
-{
- int fd;
- size_t nbytes;
- struct stat sb;
- void *p;
-
- fd = open(name, O_RDONLY);
- if (fd < 0) {
- perror(name);
- return 0;
- }
- if (fstat(fd, &sb) < 0) {
- perror(name);
- close(fd);
- return 0;
- }
- if (!S_ISREG(sb.st_mode)) {
- close(fd);
- fprintf(stderr, "%s: not a regular file\n", name);
- return 0;
- }
-
- nbytes = sb.st_size;
- p = (void *)mmap((caddr_t)0, (size_t)nbytes, PROT_READ,
- MAP_FILE|MAP_PRIVATE, fd, (off_t)0);
- if (p == (void *)-1) {
- perror(name);
- close(fd);
- return 0;
- }
- processor(p, nbytes, name, arg);
- munmap((caddr_t)p, nbytes);
- close(fd);
- return 1;
-}
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/win32filemap.c
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/win32filemap.c 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/win32filemap.c 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,120 +0,0 @@
-/*
-The contents of this file are subject to the Mozilla Public License
-Version 1.1 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998, 1999
-James Clark. All Rights Reserved.
-
-Contributor(s):
-
-Alternatively, the contents of this file may be used under the terms
-of the GNU General Public License (the "GPL"), in which case the
-provisions of the GPL are applicable instead of those above. If you
-wish to allow use of your version of this file only under the terms of
-the GPL and not to allow others to use your version of this file under
-the MPL, indicate your decision by deleting the provisions above and
-replace them with the notice and other provisions required by the
-GPL. If you do not delete the provisions above, a recipient may use
-your version of this file under either the MPL or the GPL.
-*/
-
-#define STRICT 1
-#define WIN32_LEAN_AND_MEAN 1
-
-#ifdef XML_UNICODE_WCHAR_T
-#ifndef XML_UNICODE
-#define XML_UNICODE
-#endif
-#endif
-
-#ifdef XML_UNICODE
-#define UNICODE
-#define _UNICODE
-#endif /* XML_UNICODE */
-#include <windows.h>
-#include <stdio.h>
-#include <tchar.h>
-#include "filemap.h"
-
-static void win32perror(const TCHAR *);
-
-int filemap(const TCHAR *name,
- void (*processor)(const void *, size_t, const TCHAR *, void *arg),
- void *arg)
-{
- HANDLE f;
- HANDLE m;
- DWORD size;
- DWORD sizeHi;
- void *p;
-
- f = CreateFile(name, GENERIC_READ, FILE_SHARE_READ, NULL, OPEN_EXISTING,
- FILE_FLAG_SEQUENTIAL_SCAN, NULL);
- if (f == INVALID_HANDLE_VALUE) {
- win32perror(name);
- return 0;
- }
- size = GetFileSize(f, &sizeHi);
- if (size == (DWORD)-1) {
- win32perror(name);
- return 0;
- }
- if (sizeHi) {
- _ftprintf(stderr, _T("%s: bigger than 2Gb\n"), name);
- return 0;
- }
- /* CreateFileMapping barfs on zero length files */
- if (size == 0) {
- static const char c = '\0';
- processor(&c, 0, name, arg);
- CloseHandle(f);
- return 1;
- }
- m = CreateFileMapping(f, NULL, PAGE_READONLY, 0, 0, NULL);
- if (m == NULL) {
- win32perror(name);
- CloseHandle(f);
- return 0;
- }
- p = MapViewOfFile(m, FILE_MAP_READ, 0, 0, 0);
- if (p == NULL) {
- win32perror(name);
- CloseHandle(m);
- CloseHandle(f);
- return 0;
- }
- processor(p, size, name, arg);
- UnmapViewOfFile(p);
- CloseHandle(m);
- CloseHandle(f);
- return 1;
-}
-
-static
-void win32perror(const TCHAR *s)
-{
- LPVOID buf;
- if (FormatMessage(FORMAT_MESSAGE_ALLOCATE_BUFFER | FORMAT_MESSAGE_FROM_SYSTEM,
- NULL,
- GetLastError(),
- MAKELANGID(LANG_NEUTRAL, SUBLANG_DEFAULT),
- (LPTSTR) &buf,
- 0,
- NULL)) {
- _ftprintf(stderr, _T("%s: %s"), s, buf);
- fflush(stderr);
- LocalFree(buf);
- }
- else
- _ftprintf(stderr, _T("%s: unknown Windows error\n"), s);
-}
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/xmlfile.c
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/xmlfile.c 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/xmlfile.c 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,238 +0,0 @@
-/*
-The contents of this file are subject to the Mozilla Public License
-Version 1.1 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998, 1999
-James Clark. All Rights Reserved.
-
-Contributor(s):
-
-Alternatively, the contents of this file may be used under the terms
-of the GNU General Public License (the "GPL"), in which case the
-provisions of the GPL are applicable instead of those above. If you
-wish to allow use of your version of this file only under the terms of
-the GPL and not to allow others to use your version of this file under
-the MPL, indicate your decision by deleting the provisions above and
-replace them with the notice and other provisions required by the
-GPL. If you do not delete the provisions above, a recipient may use
-your version of this file under either the MPL or the GPL.
-*/
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <stddef.h>
-#include <string.h>
-#include <fcntl.h>
-#include "xmlparse.h"
-#include "xmlfile.h"
-#include "xmltchar.h"
-#include "filemap.h"
-
-#ifdef _MSC_VER
-#include <io.h>
-#endif
-
-#ifdef _POSIX_SOURCE
-#include <unistd.h>
-#endif
-
-#ifndef O_BINARY
-#ifdef _O_BINARY
-#define O_BINARY _O_BINARY
-#else
-#define O_BINARY 0
-#endif
-#endif
-
-#ifdef _DEBUG
-#define READ_SIZE 16
-#else
-#define READ_SIZE (1024*8)
-#endif
-
-
-
-typedef struct {
- XML_Parser parser;
- int *retPtr;
-} PROCESS_ARGS;
-
-static
-void reportError(XML_Parser parser, const XML_Char *filename)
-{
- int code = XML_GetErrorCode(parser);
- const XML_Char *message = XML_ErrorString(code);
- if (message)
- ftprintf(stdout, T("%s:%d:%ld: %s\n"),
- filename,
- XML_GetErrorLineNumber(parser),
- XML_GetErrorColumnNumber(parser),
- message);
- else
- ftprintf(stderr, T("%s: (unknown message %d)\n"), filename, code);
-}
-
-static
-void processFile(const void *data,
- size_t size,
- const XML_Char *filename,
- void *args)
-{
- XML_Parser parser = ((PROCESS_ARGS *)args)->parser;
- int *retPtr = ((PROCESS_ARGS *)args)->retPtr;
- if (!XML_Parse(parser, data, size, 1)) {
- reportError(parser, filename);
- *retPtr = 0;
- }
- else
- *retPtr = 1;
-}
-
-static
-int isAsciiLetter(XML_Char c)
-{
- return (T('a') <= c && c <= T('z')) || (T('A') <= c && c <= T('Z'));
-}
-
-static
-const XML_Char *resolveSystemId(const XML_Char *base, const XML_Char *systemId, XML_Char **toFree)
-{
- XML_Char *s;
- *toFree = 0;
- if (!base
- || *systemId == T('/')
-#ifdef WIN32
- || *systemId == T('\\')
- || (isAsciiLetter(systemId[0]) && systemId[1] == T(':'))
-#endif
- )
- return systemId;
- *toFree = (XML_Char *)malloc((tcslen(base) + tcslen(systemId) + 2)*sizeof(XML_Char));
- if (!*toFree)
- return systemId;
- tcscpy(*toFree, base);
- s = *toFree;
- if (tcsrchr(s, T('/')))
- s = tcsrchr(s, T('/')) + 1;
-#ifdef WIN32
- if (tcsrchr(s, T('\\')))
- s = tcsrchr(s, T('\\')) + 1;
-#endif
- tcscpy(s, systemId);
- return *toFree;
-}
-
-static
-int externalEntityRefFilemap(XML_Parser parser,
- const XML_Char *context,
- const XML_Char *base,
- const XML_Char *systemId,
- const XML_Char *publicId)
-{
- int result;
- XML_Char *s;
- const XML_Char *filename;
- XML_Parser entParser = XML_ExternalEntityParserCreate(parser, context, 0);
- PROCESS_ARGS args;
- args.retPtr = &result;
- args.parser = entParser;
- filename = resolveSystemId(base, systemId, &s);
- XML_SetBase(entParser, filename);
- if (!filemap(filename, processFile, &args))
- result = 0;
- free(s);
- XML_ParserFree(entParser);
- return result;
-}
-
-static
-int processStream(const XML_Char *filename, XML_Parser parser)
-{
- int fd = topen(filename, O_BINARY|O_RDONLY);
- if (fd < 0) {
- tperror(filename);
- return 0;
- }
- for (;;) {
- int nread;
- char *buf = XML_GetBuffer(parser, READ_SIZE);
- if (!buf) {
- close(fd);
- ftprintf(stderr, T("%s: out of memory\n"), filename);
- return 0;
- }
- nread = read(fd, buf, READ_SIZE);
- if (nread < 0) {
- tperror(filename);
- close(fd);
- return 0;
- }
- if (!XML_ParseBuffer(parser, nread, nread == 0)) {
- reportError(parser, filename);
- close(fd);
- return 0;
- }
- if (nread == 0) {
- close(fd);
- break;;
- }
- }
- return 1;
-}
-
-static
-int externalEntityRefStream(XML_Parser parser,
- const XML_Char *context,
- const XML_Char *base,
- const XML_Char *systemId,
- const XML_Char *publicId)
-{
- XML_Char *s;
- const XML_Char *filename;
- int ret;
- XML_Parser entParser = XML_ExternalEntityParserCreate(parser, context, 0);
- filename = resolveSystemId(base, systemId, &s);
- XML_SetBase(entParser, filename);
- ret = processStream(filename, entParser);
- free(s);
- XML_ParserFree(entParser);
- return ret;
-}
-
-int XML_ProcessFile(XML_Parser parser,
- const XML_Char *filename,
- unsigned flags)
-{
- int result;
-
- if (!XML_SetBase(parser, filename)) {
- ftprintf(stderr, T("%s: out of memory"), filename);
- exit(1);
- }
-
- if (flags & XML_EXTERNAL_ENTITIES)
- XML_SetExternalEntityRefHandler(parser,
- (flags & XML_MAP_FILE)
- ? externalEntityRefFilemap
- : externalEntityRefStream);
- if (flags & XML_MAP_FILE) {
- PROCESS_ARGS args;
- args.retPtr = &result;
- args.parser = parser;
- if (!filemap(filename, processFile, &args))
- result = 0;
- }
- else
- result = processStream(filename, parser);
- return result;
-}
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/xmlfile.h
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/xmlfile.h 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/xmlfile.h 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,36 +0,0 @@
-/*
-The contents of this file are subject to the Mozilla Public License
-Version 1.1 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998, 1999
-James Clark. All Rights Reserved.
-
-Contributor(s):
-
-Alternatively, the contents of this file may be used under the terms
-of the GNU General Public License (the "GPL"), in which case the
-provisions of the GPL are applicable instead of those above. If you
-wish to allow use of your version of this file only under the terms of
-the GPL and not to allow others to use your version of this file under
-the MPL, indicate your decision by deleting the provisions above and
-replace them with the notice and other provisions required by the
-GPL. If you do not delete the provisions above, a recipient may use
-your version of this file under either the MPL or the GPL.
-*/
-
-#define XML_MAP_FILE 01
-#define XML_EXTERNAL_ENTITIES 02
-
-extern int XML_ProcessFile(XML_Parser parser,
- const XML_Char *filename,
- unsigned flags);
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/xmltchar.h
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/xmltchar.h 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/xmltchar.h 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,36 +0,0 @@
-#ifdef XML_UNICODE
-#ifndef XML_UNICODE_WCHAR_T
-#error xmlwf requires a 16-bit Unicode-compatible wchar_t
-#endif
-#define T(x) L ## x
-#define ftprintf fwprintf
-#define tfopen _wfopen
-#define fputts fputws
-#define puttc putwc
-#define tcscmp wcscmp
-#define tcscpy wcscpy
-#define tcscat wcscat
-#define tcschr wcschr
-#define tcsrchr wcsrchr
-#define tcslen wcslen
-#define tperror _wperror
-#define topen _wopen
-#define tmain wmain
-#define tremove _wremove
-#else /* not XML_UNICODE */
-#define T(x) x
-#define ftprintf fprintf
-#define tfopen fopen
-#define fputts fputs
-#define puttc putc
-#define tcscmp strcmp
-#define tcscpy strcpy
-#define tcscat strcat
-#define tcschr strchr
-#define tcsrchr strrchr
-#define tcslen strlen
-#define tperror perror
-#define topen open
-#define tmain main
-#define tremove remove
-#endif /* not XML_UNICODE */
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/xmlwf.c
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/xmlwf.c 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/expat/xmlwf/xmlwf.c 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,747 +0,0 @@
-/*
-The contents of this file are subject to the Mozilla Public License
-Version 1.1 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998, 1999
-James Clark. All Rights Reserved.
-
-Contributor(s):
-
-Alternatively, the contents of this file may be used under the terms
-of the GNU General Public License (the "GPL"), in which case the
-provisions of the GPL are applicable instead of those above. If you
-wish to allow use of your version of this file only under the terms of
-the GPL and not to allow others to use your version of this file under
-the MPL, indicate your decision by deleting the provisions above and
-replace them with the notice and other provisions required by the
-GPL. If you do not delete the provisions above, a recipient may use
-your version of this file under either the MPL or the GPL.
-*/
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <stddef.h>
-#include <string.h>
-
-#include "xmlparse.h"
-#include "codepage.h"
-#include "xmlfile.h"
-#include "xmltchar.h"
-
-#ifdef _MSC_VER
-#include <crtdbg.h>
-#endif
-
-/* This ensures proper sorting. */
-
-#define NSSEP T('\001')
-
-static void characterData(void *userData, const XML_Char *s, int len)
-{
- FILE *fp = userData;
- for (; len > 0; --len, ++s) {
- switch (*s) {
- case T('&'):
- fputts(T("&"), fp);
- break;
- case T('<'):
- fputts(T("<"), fp);
- break;
- case T('>'):
- fputts(T(">"), fp);
- break;
-#ifdef W3C14N
- case 13:
- fputts(T("
"), fp);
- break;
-#else
- case T('"'):
- fputts(T("""), fp);
- break;
- case 9:
- case 10:
- case 13:
- ftprintf(fp, T("&#%d;"), *s);
- break;
-#endif
- default:
- puttc(*s, fp);
- break;
- }
- }
-}
-
-static void attributeValue(FILE *fp, const XML_Char *s)
-{
- puttc(T('='), fp);
- puttc(T('"'), fp);
- for (;;) {
- switch (*s) {
- case 0:
- case NSSEP:
- puttc(T('"'), fp);
- return;
- case T('&'):
- fputts(T("&"), fp);
- break;
- case T('<'):
- fputts(T("<"), fp);
- break;
- case T('"'):
- fputts(T("""), fp);
- break;
-#ifdef W3C14N
- case 9:
- fputts(T("	"), fp);
- break;
- case 10:
- fputts(T("
"), fp);
- break;
- case 13:
- fputts(T("
"), fp);
- break;
-#else
- case T('>'):
- fputts(T(">"), fp);
- break;
- case 9:
- case 10:
- case 13:
- ftprintf(fp, T("&#%d;"), *s);
- break;
-#endif
- default:
- puttc(*s, fp);
- break;
- }
- s++;
- }
-}
-
-/* Lexicographically comparing UTF-8 encoded attribute values,
-is equivalent to lexicographically comparing based on the character number. */
-
-static int attcmp(const void *att1, const void *att2)
-{
- return tcscmp(*(const XML_Char **)att1, *(const XML_Char **)att2);
-}
-
-static void startElement(void *userData, const XML_Char *name, const XML_Char **atts)
-{
- int nAtts;
- const XML_Char **p;
- FILE *fp = userData;
- puttc(T('<'), fp);
- fputts(name, fp);
-
- p = atts;
- while (*p)
- ++p;
- nAtts = (p - atts) >> 1;
- if (nAtts > 1)
- qsort((void *)atts, nAtts, sizeof(XML_Char *) * 2, attcmp);
- while (*atts) {
- puttc(T(' '), fp);
- fputts(*atts++, fp);
- attributeValue(fp, *atts);
- atts++;
- }
- puttc(T('>'), fp);
-}
-
-static void endElement(void *userData, const XML_Char *name)
-{
- FILE *fp = userData;
- puttc(T('<'), fp);
- puttc(T('/'), fp);
- fputts(name, fp);
- puttc(T('>'), fp);
-}
-
-static int nsattcmp(const void *p1, const void *p2)
-{
- const XML_Char *att1 = *(const XML_Char **)p1;
- const XML_Char *att2 = *(const XML_Char **)p2;
- int sep1 = (tcsrchr(att1, NSSEP) != 0);
- int sep2 = (tcsrchr(att1, NSSEP) != 0);
- if (sep1 != sep2)
- return sep1 - sep2;
- return tcscmp(att1, att2);
-}
-
-static void startElementNS(void *userData, const XML_Char *name, const XML_Char **atts)
-{
- int nAtts;
- int nsi;
- const XML_Char **p;
- FILE *fp = userData;
- const XML_Char *sep;
- puttc(T('<'), fp);
-
- sep = tcsrchr(name, NSSEP);
- if (sep) {
- fputts(T("n1:"), fp);
- fputts(sep + 1, fp);
- fputts(T(" xmlns:n1"), fp);
- attributeValue(fp, name);
- nsi = 2;
- }
- else {
- fputts(name, fp);
- nsi = 1;
- }
-
- p = atts;
- while (*p)
- ++p;
- nAtts = (p - atts) >> 1;
- if (nAtts > 1)
- qsort((void *)atts, nAtts, sizeof(XML_Char *) * 2, nsattcmp);
- while (*atts) {
- name = *atts++;
- sep = tcsrchr(name, NSSEP);
- puttc(T(' '), fp);
- if (sep) {
- ftprintf(fp, T("n%d:"), nsi);
- fputts(sep + 1, fp);
- }
- else
- fputts(name, fp);
- attributeValue(fp, *atts);
- if (sep) {
- ftprintf(fp, T(" xmlns:n%d"), nsi++);
- attributeValue(fp, name);
- }
- atts++;
- }
- puttc(T('>'), fp);
-}
-
-static void endElementNS(void *userData, const XML_Char *name)
-{
- FILE *fp = userData;
- const XML_Char *sep;
- puttc(T('<'), fp);
- puttc(T('/'), fp);
- sep = tcsrchr(name, NSSEP);
- if (sep) {
- fputts(T("n1:"), fp);
- fputts(sep + 1, fp);
- }
- else
- fputts(name, fp);
- puttc(T('>'), fp);
-}
-
-#ifndef W3C14N
-
-static void processingInstruction(void *userData, const XML_Char *target, const XML_Char *data)
-{
- FILE *fp = userData;
- puttc(T('<'), fp);
- puttc(T('?'), fp);
- fputts(target, fp);
- puttc(T(' '), fp);
- fputts(data, fp);
- puttc(T('?'), fp);
- puttc(T('>'), fp);
-}
-
-#endif /* not W3C14N */
-
-static void defaultCharacterData(XML_Parser parser, const XML_Char *s, int len)
-{
- XML_DefaultCurrent(parser);
-}
-
-static void defaultStartElement(XML_Parser parser, const XML_Char *name, const XML_Char **atts)
-{
- XML_DefaultCurrent(parser);
-}
-
-static void defaultEndElement(XML_Parser parser, const XML_Char *name)
-{
- XML_DefaultCurrent(parser);
-}
-
-static void defaultProcessingInstruction(XML_Parser parser, const XML_Char *target, const XML_Char *data)
-{
- XML_DefaultCurrent(parser);
-}
-
-static void nopCharacterData(XML_Parser parser, const XML_Char *s, int len)
-{
-}
-
-static void nopStartElement(XML_Parser parser, const XML_Char *name, const XML_Char **atts)
-{
-}
-
-static void nopEndElement(XML_Parser parser, const XML_Char *name)
-{
-}
-
-static void nopProcessingInstruction(XML_Parser parser, const XML_Char *target, const XML_Char *data)
-{
-}
-
-static void markup(XML_Parser parser, const XML_Char *s, int len)
-{
- FILE *fp = XML_GetUserData(parser);
- for (; len > 0; --len, ++s)
- puttc(*s, fp);
-}
-
-static
-void metaLocation(XML_Parser parser)
-{
- const XML_Char *uri = XML_GetBase(parser);
- if (uri)
- ftprintf(XML_GetUserData(parser), T(" uri=\"%s\""), uri);
- ftprintf(XML_GetUserData(parser),
- T(" byte=\"%ld\" nbytes=\"%d\" line=\"%d\" col=\"%d\""),
- XML_GetCurrentByteIndex(parser),
- XML_GetCurrentByteCount(parser),
- XML_GetCurrentLineNumber(parser),
- XML_GetCurrentColumnNumber(parser));
-}
-
-static
-void metaStartDocument(XML_Parser parser)
-{
- fputts(T("<document>\n"), XML_GetUserData(parser));
-}
-
-static
-void metaEndDocument(XML_Parser parser)
-{
- fputts(T("</document>\n"), XML_GetUserData(parser));
-}
-
-static
-void metaStartElement(XML_Parser parser, const XML_Char *name, const XML_Char **atts)
-{
- FILE *fp = XML_GetUserData(parser);
- const XML_Char **specifiedAttsEnd
- = atts + 2*XML_GetSpecifiedAttributeCount(parser);
- ftprintf(fp, T("<starttag name=\"%s\""), name);
- metaLocation(parser);
- if (*atts) {
- fputts(T(">\n"), fp);
- do {
- ftprintf(fp, T("<attribute name=\"%s\" value=\""), atts[0]);
- characterData(fp, atts[1], tcslen(atts[1]));
- if (atts >= specifiedAttsEnd)
- fputts(T("\" defaulted=\"yes\"/>\n"), fp);
- else
- fputts(T("\"/>\n"), fp);
- } while (*(atts += 2));
- fputts(T("</starttag>\n"), fp);
- }
- else
- fputts(T("/>\n"), fp);
-}
-
-static
-void metaEndElement(XML_Parser parser, const XML_Char *name)
-{
- FILE *fp = XML_GetUserData(parser);
- ftprintf(fp, T("<endtag name=\"%s\""), name);
- metaLocation(parser);
- fputts(T("/>\n"), fp);
-}
-
-static
-void metaProcessingInstruction(XML_Parser parser, const XML_Char *target, const XML_Char *data)
-{
- FILE *fp = XML_GetUserData(parser);
- ftprintf(fp, T("<pi target=\"%s\" data=\""), target);
- characterData(fp, data, tcslen(data));
- puttc(T('"'), fp);
- metaLocation(parser);
- fputts(T("/>\n"), fp);
-}
-
-static
-void metaComment(XML_Parser parser, const XML_Char *data)
-{
- FILE *fp = XML_GetUserData(parser);
- fputts(T("<comment data=\""), fp);
- characterData(fp, data, tcslen(data));
- puttc(T('"'), fp);
- metaLocation(parser);
- fputts(T("/>\n"), fp);
-}
-
-static
-void metaStartCdataSection(XML_Parser parser)
-{
- FILE *fp = XML_GetUserData(parser);
- fputts(T("<startcdata"), fp);
- metaLocation(parser);
- fputts(T("/>\n"), fp);
-}
-
-static
-void metaEndCdataSection(XML_Parser parser)
-{
- FILE *fp = XML_GetUserData(parser);
- fputts(T("<endcdata"), fp);
- metaLocation(parser);
- fputts(T("/>\n"), fp);
-}
-
-static
-void metaCharacterData(XML_Parser parser, const XML_Char *s, int len)
-{
- FILE *fp = XML_GetUserData(parser);
- fputts(T("<chars str=\""), fp);
- characterData(fp, s, len);
- puttc(T('"'), fp);
- metaLocation(parser);
- fputts(T("/>\n"), fp);
-}
-
-static
-void metaStartDoctypeDecl(XML_Parser parser, const XML_Char *doctypeName)
-{
- FILE *fp = XML_GetUserData(parser);
- ftprintf(fp, T("<startdoctype name=\"%s\""), doctypeName);
- metaLocation(parser);
- fputts(T("/>\n"), fp);
-}
-
-static
-void metaEndDoctypeDecl(XML_Parser parser)
-{
- FILE *fp = XML_GetUserData(parser);
- fputts(T("<enddoctype"), fp);
- metaLocation(parser);
- fputts(T("/>\n"), fp);
-}
-
-static
-void metaUnparsedEntityDecl(XML_Parser parser,
- const XML_Char *entityName,
- const XML_Char *base,
- const XML_Char *systemId,
- const XML_Char *publicId,
- const XML_Char *notationName)
-{
- FILE *fp = XML_GetUserData(parser);
- ftprintf(fp, T("<entity name=\"%s\""), entityName);
- if (publicId)
- ftprintf(fp, T(" public=\"%s\""), publicId);
- fputts(T(" system=\""), fp);
- characterData(fp, systemId, tcslen(systemId));
- puttc(T('"'), fp);
- ftprintf(fp, T(" notation=\"%s\""), notationName);
- metaLocation(parser);
- fputts(T("/>\n"), fp);
-}
-
-static
-void metaNotationDecl(XML_Parser parser,
- const XML_Char *notationName,
- const XML_Char *base,
- const XML_Char *systemId,
- const XML_Char *publicId)
-{
- FILE *fp = XML_GetUserData(parser);
- ftprintf(fp, T("<notation name=\"%s\""), notationName);
- if (publicId)
- ftprintf(fp, T(" public=\"%s\""), publicId);
- if (systemId) {
- fputts(T(" system=\""), fp);
- characterData(fp, systemId, tcslen(systemId));
- puttc(T('"'), fp);
- }
- metaLocation(parser);
- fputts(T("/>\n"), fp);
-}
-
-static
-void metaStartNamespaceDecl(XML_Parser parser,
- const XML_Char *prefix,
- const XML_Char *uri)
-{
- FILE *fp = XML_GetUserData(parser);
- fputts(T("<startns"), fp);
- if (prefix)
- ftprintf(fp, T(" prefix=\"%s\""), prefix);
- if (uri) {
- fputts(T(" ns=\""), fp);
- characterData(fp, uri, tcslen(uri));
- fputts(T("\"/>\n"), fp);
- }
- else
- fputts(T("/>\n"), fp);
-}
-
-static
-void metaEndNamespaceDecl(XML_Parser parser, const XML_Char *prefix)
-{
- FILE *fp = XML_GetUserData(parser);
- if (!prefix)
- fputts(T("<endns/>\n"), fp);
- else
- ftprintf(fp, T("<endns prefix=\"%s\"/>\n"), prefix);
-}
-
-static
-int unknownEncodingConvert(void *data, const char *p)
-{
- return codepageConvert(*(int *)data, p);
-}
-
-static
-int unknownEncoding(void *userData,
- const XML_Char *name,
- XML_Encoding *info)
-{
- int cp;
- static const XML_Char prefixL[] = T("windows-");
- static const XML_Char prefixU[] = T("WINDOWS-");
- int i;
-
- for (i = 0; prefixU[i]; i++)
- if (name[i] != prefixU[i] && name[i] != prefixL[i])
- return 0;
-
- cp = 0;
- for (; name[i]; i++) {
- static const XML_Char digits[] = T("0123456789");
- const XML_Char *s = tcschr(digits, name[i]);
- if (!s)
- return 0;
- cp *= 10;
- cp += s - digits;
- if (cp >= 0x10000)
- return 0;
- }
- if (!codepageMap(cp, info->map))
- return 0;
- info->convert = unknownEncodingConvert;
- /* We could just cast the code page integer to a void *,
- and avoid the use of release. */
- info->release = free;
- info->data = malloc(sizeof(int));
- if (!info->data)
- return 0;
- *(int *)info->data = cp;
- return 1;
-}
-
-static
-int notStandalone(void *userData)
-{
- return 0;
-}
-
-static
-void usage(const XML_Char *prog)
-{
- ftprintf(stderr, T("usage: %s [-n] [-p] [-r] [-s] [-w] [-x] [-d output-dir] [-e encoding] file ...\n"), prog);
- exit(1);
-}
-
-int tmain(int argc, XML_Char **argv)
-{
- int i, j;
- const XML_Char *outputDir = 0;
- const XML_Char *encoding = 0;
- unsigned processFlags = XML_MAP_FILE;
- int windowsCodePages = 0;
- int outputType = 0;
- int useNamespaces = 0;
- int requireStandalone = 0;
- int paramEntityParsing = XML_PARAM_ENTITY_PARSING_NEVER;
-
-#ifdef _MSC_VER
- _CrtSetDbgFlag(_CRTDBG_ALLOC_MEM_DF|_CRTDBG_LEAK_CHECK_DF);
-#endif
-
- i = 1;
- j = 0;
- while (i < argc) {
- if (j == 0) {
- if (argv[i][0] != T('-'))
- break;
- if (argv[i][1] == T('-') && argv[i][2] == T('\0')) {
- i++;
- break;
- }
- j++;
- }
- switch (argv[i][j]) {
- case T('r'):
- processFlags &= ~XML_MAP_FILE;
- j++;
- break;
- case T('s'):
- requireStandalone = 1;
- j++;
- break;
- case T('n'):
- useNamespaces = 1;
- j++;
- break;
- case T('p'):
- paramEntityParsing = XML_PARAM_ENTITY_PARSING_ALWAYS;
- /* fall through */
- case T('x'):
- processFlags |= XML_EXTERNAL_ENTITIES;
- j++;
- break;
- case T('w'):
- windowsCodePages = 1;
- j++;
- break;
- case T('m'):
- outputType = 'm';
- j++;
- break;
- case T('c'):
- outputType = 'c';
- useNamespaces = 0;
- j++;
- break;
- case T('t'):
- outputType = 't';
- j++;
- break;
- case T('d'):
- if (argv[i][j + 1] == T('\0')) {
- if (++i == argc)
- usage(argv[0]);
- outputDir = argv[i];
- }
- else
- outputDir = argv[i] + j + 1;
- i++;
- j = 0;
- break;
- case T('e'):
- if (argv[i][j + 1] == T('\0')) {
- if (++i == argc)
- usage(argv[0]);
- encoding = argv[i];
- }
- else
- encoding = argv[i] + j + 1;
- i++;
- j = 0;
- break;
- case T('\0'):
- if (j > 1) {
- i++;
- j = 0;
- break;
- }
- /* fall through */
- default:
- usage(argv[0]);
- }
- }
- if (i == argc)
- usage(argv[0]);
- for (; i < argc; i++) {
- FILE *fp = 0;
- XML_Char *outName = 0;
- int result;
- XML_Parser parser;
- if (useNamespaces)
- parser = XML_ParserCreateNS(encoding, NSSEP);
- else
- parser = XML_ParserCreate(encoding);
- if (requireStandalone)
- XML_SetNotStandaloneHandler(parser, notStandalone);
- XML_SetParamEntityParsing(parser, paramEntityParsing);
- if (outputType == 't') {
- /* This is for doing timings; this gives a more realistic estimate of
- the parsing time. */
- outputDir = 0;
- XML_SetElementHandler(parser, nopStartElement, nopEndElement);
- XML_SetCharacterDataHandler(parser, nopCharacterData);
- XML_SetProcessingInstructionHandler(parser, nopProcessingInstruction);
- }
- else if (outputDir) {
- const XML_Char *file = argv[i];
- if (tcsrchr(file, T('/')))
- file = tcsrchr(file, T('/')) + 1;
-#ifdef WIN32
- if (tcsrchr(file, T('\\')))
- file = tcsrchr(file, T('\\')) + 1;
-#endif
- outName = malloc((tcslen(outputDir) + tcslen(file) + 2) * sizeof(XML_Char));
- tcscpy(outName, outputDir);
- tcscat(outName, T("/"));
- tcscat(outName, file);
- fp = tfopen(outName, T("wb"));
- if (!fp) {
- tperror(outName);
- exit(1);
- }
- setvbuf(fp, NULL, _IOFBF, 16384);
-#ifdef XML_UNICODE
- puttc(0xFEFF, fp);
-#endif
- XML_SetUserData(parser, fp);
- switch (outputType) {
- case 'm':
- XML_UseParserAsHandlerArg(parser);
- XML_SetElementHandler(parser, metaStartElement, metaEndElement);
- XML_SetProcessingInstructionHandler(parser, metaProcessingInstruction);
- XML_SetCommentHandler(parser, metaComment);
- XML_SetCdataSectionHandler(parser, metaStartCdataSection, metaEndCdataSection);
- XML_SetCharacterDataHandler(parser, metaCharacterData);
- XML_SetDoctypeDeclHandler(parser, metaStartDoctypeDecl, metaEndDoctypeDecl);
- XML_SetUnparsedEntityDeclHandler(parser, metaUnparsedEntityDecl);
- XML_SetNotationDeclHandler(parser, metaNotationDecl);
- XML_SetNamespaceDeclHandler(parser, metaStartNamespaceDecl, metaEndNamespaceDecl);
- metaStartDocument(parser);
- break;
- case 'c':
- XML_UseParserAsHandlerArg(parser);
- XML_SetDefaultHandler(parser, markup);
- XML_SetElementHandler(parser, defaultStartElement, defaultEndElement);
- XML_SetCharacterDataHandler(parser, defaultCharacterData);
- XML_SetProcessingInstructionHandler(parser, defaultProcessingInstruction);
- break;
- default:
- if (useNamespaces)
- XML_SetElementHandler(parser, startElementNS, endElementNS);
- else
- XML_SetElementHandler(parser, startElement, endElement);
- XML_SetCharacterDataHandler(parser, characterData);
-#ifndef W3C14N
- XML_SetProcessingInstructionHandler(parser, processingInstruction);
-#endif /* not W3C14N */
- break;
- }
- }
- if (windowsCodePages)
- XML_SetUnknownEncodingHandler(parser, unknownEncoding, 0);
- result = XML_ProcessFile(parser, argv[i], processFlags);
- if (outputDir) {
- if (outputType == 'm')
- metaEndDocument(parser);
- fclose(fp);
- if (!result)
- tremove(outName);
- free(outName);
- }
- XML_ParserFree(parser);
- }
- return 0;
-}
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/sfReader.h
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/sfReader.h 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/sfReader.h 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,234 +0,0 @@
-#include <string>
-#include <cstdio>
-
-#include "ushort_chartraits.h"
-
-#define END_OF_FILE -1
-#define BODY_TEXT 0
-#define SFM 1
-#define INLINE_START 2
-#define INLINE_END 3
-#define INLINE_MARKER 4
-
-template<class C>
-class sfReader
-{
-public:
- typedef std::basic_string<C> stringT;
- typedef std::char_traits<C> traitsT;
-
- sfReader(std::FILE* inFile, char inForm = kForm_Bytes);
- ~sfReader();
-
- long escapeChar;
- long inlineEscapeChar;
- long startInline;
- long endInline;
-
- stringT sfmChars;
- stringT inlineChars;
-
- int next(bool checkInlineEnd);
-
- stringT text;
-
-protected:
- long get();
- void putback(long c);
-
- long fSavedChar;
-
- char inForm;
-
- std::FILE* inFile;
-};
-
-template<class C>
-sfReader<C>::sfReader(std::FILE* f, char i)
- : inForm(i)
- , inFile(f)
-{
- escapeChar = '\\';
- inlineEscapeChar = -1;
- startInline = -1;
- endInline = -1;
-
- text.reserve(10000);
- fSavedChar = -1;
-}
-
-template<class C>
-sfReader<C>::~sfReader()
-{
-}
-
-template<> long
-sfReader<char>::get()
-{
- long rval = fSavedChar;
- if (rval == -1)
- rval = getc(inFile);
- else
- fSavedChar = -1;
- return rval;
-}
-
-static char bytesFromUTF8[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};
-static unsigned long offsetsFromUTF8[6] =
- {0x00000000UL, 0x00003080UL, 0x000E2080UL,
- 0x03C82080UL, 0xFA082080UL, 0x82082080UL};
-/*
-const unsigned long kReplacementCharacter = 0x0000FFFDUL;
-const unsigned long kMaximumUCS2 = 0x0000FFFFUL;
-const unsigned long kMaximumUTF16 = 0x0010FFFFUL;
-const unsigned long kMaximumUCS4 = 0x7FFFFFFFUL;
-*/
-const int halfShift = 10;
-const unsigned long halfBase = 0x0010000UL;
-const unsigned long halfMask = 0x3FFUL;
-const unsigned long kSurrogateHighStart = 0xD800UL;
-const unsigned long kSurrogateHighEnd = 0xDBFFUL;
-const unsigned long kSurrogateLowStart = 0xDC00UL;
-const unsigned long kSurrogateLowEnd = 0xDFFFUL;
-
-template<> long
-sfReader<UniChar>::get()
-{
- if (fSavedChar != -1) {
- long rval = fSavedChar;
- fSavedChar = -1;
- return rval;
- }
- long c1 = getc(inFile);
- if (c1 == -1)
- return -1;
- else {
- if (inForm == kForm_UTF8) {
- long t1, t2 = -1;
- unsigned long ch = c1;
- unsigned short extraBytes = bytesFromUTF8[c1];
- long c2;
- switch(extraBytes) { /* note: code falls through cases! */
- case 5: c2 = getc(inFile); if (c2 == -1) return -1; ch <<= 6; ch += c2;
- case 4: c2 = getc(inFile); if (c2 == -1) return -1; ch <<= 6; ch += c2;
- case 3: c2 = getc(inFile); if (c2 == -1) return -1; ch <<= 6; ch += c2;
- case 2: c2 = getc(inFile); if (c2 == -1) return -1; ch <<= 6; ch += c2;
- case 1: c2 = getc(inFile); if (c2 == -1) return -1; ch <<= 6; ch += c2;
- case 0: ;
- };
- ch -= offsetsFromUTF8[extraBytes];
- if (ch <= UNI_MAX_BMP) {
- t1 = ch;
- } else if (ch > UNI_MAX_UTF16) {
- t1 = UNI_REPLACEMENT_CHAR;
- } else {
- ch -= halfBase;
- t1 = (ch >> halfShift) + kSurrogateHighStart;
- t2 = (ch & halfMask) + kSurrogateLowStart;
- }
- fSavedChar = t2;
- return t1;
- }
- else {
- long c2 = getc(inFile);
- if (c2 == -1)
- return -1;
- if (inForm == kForm_UTF16BE)
- return (c1 << 8) + c2;
- else
- return (c2 << 8) + c1;
- }
- }
-}
-
-template<class C>
-void
-sfReader<C>::putback(long c)
-{
- fSavedChar = c;
-}
-
-template<class C>
-int
-sfReader<C>::next(bool checkInlineEnd)
-{
- const long eof = traitsT::eof();
- long c = get();
- if (c == eof)
- return END_OF_FILE;
-
- text.clear();
-
- if (c == escapeChar) {
- while (1) {
- c = get();
- if (c == eof) {
- return SFM;
- }
- if (sfmChars.find(c, 0) != stringT::npos) {
- text.append(1, c);
- }
- else if (text.length() == 0) {
- text.append(1, c);
- return SFM;
- }
- else {
- putback(c);
- return SFM;
- }
- }
- }
-
- if (c == inlineEscapeChar) {
- while (1) {
- c = get();
- if (c == eof) {
- return INLINE_MARKER;
- }
- if (inlineChars.find(c, 0) != stringT::npos)
- text.append(1, c);
- else if (text.length() == 0) {
- text.append(1, c);
- c = get();
- if (c == startInline)
- return INLINE_START;
- else {
- putback(c);
- return INLINE_MARKER;
- }
- }
- else {
- if (c == startInline)
- return INLINE_START;
- else {
- putback(c);
- return INLINE_MARKER;
- }
- }
- }
- }
-
- if (checkInlineEnd && c == endInline) {
- return INLINE_END;
- }
-
- // must be "junk" before the first SFM
- text.append(1, c);
-
- while (1) {
- c = get();
- if (c == eof || c == escapeChar || c == inlineEscapeChar || (checkInlineEnd && c == endInline)) {
- putback(c);
- return BODY_TEXT;
- }
- text.append(1, c);
- }
-}
Deleted: trunk/Build/source/libs/teckit/TECkit-src/SFconv/ushort_chartraits.h
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/SFconv/ushort_chartraits.h 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/SFconv/ushort_chartraits.h 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,102 +0,0 @@
-#ifndef __ushort_chartraits_h__
-#define __ushort_chartraits_h__
-
-#include <iostream>
-#include <string>
-#include <locale>
-
-// Provide std::char_traits specialization for unsigned short.
-
-// BEWARE:
-// This is adequate for SFconv but may not work for all purposes
-
-namespace std
-{
- template<>
- struct char_traits<unsigned short>
- {
- typedef unsigned short char_type;
-
- // NB: this type should be bigger than char_type, so as to
- // properly hold EOF values in addition to the full range of
- // char_type values.
- typedef unsigned long int_type;
-
- typedef streampos pos_type;
- typedef streamoff off_type;
- typedef mbstate_t state_type;
-
- static void
- assign(char_type& __c1, const char_type& __c2)
- { __c1 = __c2; }
-
- static bool
- eq(const char_type& __c1, const char_type& __c2)
- { return __c1 == __c2; }
-
- static bool
- lt(const char_type& __c1, const char_type& __c2)
- { return __c1 < __c2; }
-
- static int
- compare(const char_type* __s1, const char_type* __s2, size_t __n)
- {
- for (size_t __i = 0; __i < __n; ++__i)
- if (!eq(__s1[__i], __s2[__i]))
- return lt(__s1[__i], __s2[__i]) ? -1 : 1;
- return 0;
- }
-
- static size_t
- length(const char_type* __s)
- {
- const char_type* __p = __s;
- while (*__p) ++__p;
- return (__p - __s);
- }
-
- static const char_type*
- find(const char_type* __s, size_t __n, const char_type& __a)
- {
- for (const char_type* __p = __s; size_t(__p - __s) < __n; ++__p)
- if (*__p == __a) return __p;
- return 0;
- }
-
- static char_type*
- move(char_type* __s1, const char_type* __s2, size_t __n)
- { return (char_type*) memmove(__s1, __s2, __n * sizeof(char_type)); }
-
- static char_type*
- copy(char_type* __s1, const char_type* __s2, size_t __n)
- { return (char_type*) memcpy(__s1, __s2, __n * sizeof(char_type)); }
-
- static char_type*
- assign(char_type* __s, size_t __n, char_type __a)
- {
- for (char_type* __p = __s; __p < __s + __n; ++__p)
- assign(*__p, __a);
- return __s;
- }
-
- static char_type
- to_char_type(const int_type& __c)
- { return char_type(__c); }
-
- static int_type
- to_int_type(const char_type& __c) { return int_type(__c); }
-
- static bool
- eq_int_type(const int_type& __c1, const int_type& __c2)
- { return __c1 == __c2; }
-
- static int_type
- eof() { return static_cast<int_type>(-1); }
-
- static int_type
- not_eof(const int_type& __c)
- { return eq_int_type(__c, eof()) ? int_type(0) : __c; }
- };
-}
-
-#endif
Modified: trunk/Build/source/libs/teckit/TECkit-src/bin/Makefile.am
===================================================================
--- trunk/Build/source/libs/teckit/TECkit-src/bin/Makefile.am 2017-01-11 01:02:40 UTC (rev 42923)
+++ trunk/Build/source/libs/teckit/TECkit-src/bin/Makefile.am 2017-01-11 01:34:07 UTC (rev 42924)
@@ -1,6 +1,6 @@
AUTOMAKE_OPTIONS = -Wno-portability
-bin_PROGRAMS = teckit_compile txtconv sfconv
+bin_PROGRAMS = teckit_compile txtconv
AM_CPPFLAGS = -I$(top_srcdir)/source/Public-headers
More information about the tex-live-commits
mailing list