fivedev/harbour-core
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

2017-06-26 08:55 UTC+0200 Aleksander Czajczynski (hb fki.pl)

Browse Source 
* contrib/hbexpat/3rd/expat/*
     ! updated to 2.2.1 (from 2.1.0) using 3rdpatch.hb, expat.dif(f) from
       Viktor's 3.4 fork was used - but adapted for DOS 8.3 naming
       scheme. According to issue #157, previous revisions of expat have
       security vulnerabilities, for more information refer to:
       https://github.com/libexpat/libexpat/blob/master/expat/Changes
       Many thanks to Sebastian Pipping for the information.

   * contrib/hbexpat/hbexpat.ch
     + new constant HB_XML_ERROR_INVALID_ARGUMENT added
This commit is contained in:
Aleksander Czajczynski
2017-06-26 08:56:14 +02:00
parent 9581c18aea
commit 0181a0f48f
16 changed files with 1092 additions and 716 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
ChangeLog.txt
View File

@@ -10,6 +10,18 @@
* Change, ! Fix, % Optimization, + Addition, - Removal, ; Comment
*/
2017-06-26 08:55 UTC+0200 Aleksander Czajczynski (hb fki.pl)
* contrib/hbexpat/3rd/expat/*
! updated to 2.2.1 (from 2.1.0) using 3rdpatch.hb, expat.dif(f) from
Viktor's 3.4 fork was used - but adapted for DOS 8.3 naming
scheme. According to issue #157, previous revisions of expat have
security vulnerabilities, for more information refer to:
https://github.com/libexpat/libexpat/blob/master/expat/Changes
Many thanks to Sebastian Pipping for the information.
* contrib/hbexpat/hbexpat.ch
+ new constant HB_XML_ERROR_INVALID_ARGUMENT added
2017-05-20 02:25 UTC Viktor Szakats (vszakats users.noreply.github.com)
* utils/hbmk2/hbmk2.prg
* remove `_HBSHELL_EXEC_PRE` macro

5
contrib/hbexpat/3rd/expat/COPYING
View File

@@ -1,6 +1,5 @@
Copyright (c) 1998, 1999, 2000 Thai Open Source Software Center Ltd
and Clark Cooper
Copyright (c) 2001, 2002, 2003, 2004, 2005, 2006 Expat maintainers.
Copyright (c) 1998-2000 Thai Open Source Software Center Ltd and Clark Cooper
Copyright (c) 2001-2017 Expat maintainers
Permission is hereby granted, free of charge, to any person obtaining
a copy of this software and associated documentation files (the

32
contrib/hbexpat/3rd/expat/amigacon.h
View File

@@ -1,32 +0,0 @@
#ifndef AMIGACONFIG_H
#define AMIGACONFIG_H
/* 1234 = LIL_ENDIAN, 4321 = BIGENDIAN */
#define BYTEORDER 4321
/* Define to 1 if you have the `bcopy' function. */
#define HAVE_BCOPY 1
/* Define to 1 if you have the <check.h> header file. */
#undef HAVE_CHECK_H
/* Define to 1 if you have the `memmove' function. */
#define HAVE_MEMMOVE 1
/* Define to 1 if you have the <unistd.h> header file. */
#define HAVE_UNISTD_H 1
/* whether byteorder is bigendian */
#define WORDS_BIGENDIAN
/* Define to specify how much context to retain around the current parse
point. */
#define XML_CONTEXT_BYTES 1024
/* Define to make parameter entity parsing functionality available. */
#define XML_DTD
/* Define to make XML Namespaces functionality available. */
#define XML_NS
#endif /* AMIGACONFIG_H */

179
contrib/hbexpat/3rd/expat/expat.dif
View File

@@ -1,168 +1,51 @@
diff -urN expat.orig\xmlparse.c expat\xmlparse.c
--- expat.orig\xmlparse.c Wed Sep 12 12:57:25 2012
+++ expat\xmlparse.c Wed Sep 12 12:57:25 2012
@@ -10,7 +10,9 @@
diff -urN expat.orig/xmlparse.c expat/xmlparse.c
--- expat.orig/xmlparse.c 2017-06-26 08:22:50.000000000 +0200
+++ expat/xmlparse.c 2017-06-26 08:22:50.000000000 +0200
@@ -23,7 +23,9 @@
#define XML_BUILDING_EXPAT 1
-#ifdef COMPILED_FROM_DSP
-#ifdef _WIN32
+#ifdef HARBOUR_CONF
+#include "_hbconf.h"
+#elif defined(COMPILED_FROM_DSP)
+#elif defined(_WIN32)
#include "winconfi.h"
#elif defined(MACOS_CLASSIC)
#include "macconfi.h"
diff -urN expat.orig\xmlrole.c expat\xmlrole.c
--- expat.orig\xmlrole.c Wed Sep 12 12:57:25 2012
+++ expat\xmlrole.c Wed Sep 12 12:57:25 2012
#elif defined(HAVE_EXPAT_CONFIG_H)
#include <expat_config.h>
@@ -749,7 +751,7 @@
static int
writeRandomBytes_RtlGenRandom(void * target, size_t count) {
int success = 0; /* full count bytes written? */
- const HMODULE advapi32 = LoadLibrary("ADVAPI32.DLL");
+ const HMODULE advapi32 = LoadLibrary(TEXT("ADVAPI32.DLL"));
if (advapi32) {
const RTLGENRANDOM_FUNC RtlGenRandom
diff -urN expat.orig/xmlrole.c expat/xmlrole.c
--- expat.orig/xmlrole.c 2017-06-26 08:22:50.000000000 +0200
+++ expat/xmlrole.c 2017-06-26 08:22:50.000000000 +0200
@@ -4,7 +4,9 @@
#include <stddef.h>
-#ifdef COMPILED_FROM_DSP
-#ifdef _WIN32
+#ifdef HARBOUR_CONF
+#include "_hbconf.h"
+#elif defined(COMPILED_FROM_DSP)
+#elif defined(_WIN32)
#include "winconfi.h"
#elif defined(MACOS_CLASSIC)
#include "macconfi.h"
diff -urN expat.orig\xmltok.c expat\xmltok.c
--- expat.orig\xmltok.c Wed Sep 12 12:57:25 2012
+++ expat\xmltok.c Wed Sep 12 12:57:25 2012
#else
#ifdef HAVE_EXPAT_CONFIG_H
diff -urN expat.orig/xmltok.c expat/xmltok.c
--- expat.orig/xmltok.c 2017-06-26 08:22:50.000000000 +0200
+++ expat/xmltok.c 2017-06-26 08:22:50.000000000 +0200
@@ -4,7 +4,9 @@
#include <stddef.h>
-#ifdef COMPILED_FROM_DSP
-#ifdef _WIN32
+#ifdef HARBOUR_CONF
+#include "_hbconf.h"
+#elif defined(COMPILED_FROM_DSP)
+#elif defined(_WIN32)
#include "winconfi.h"
#elif defined(MACOS_CLASSIC)
#include "macconfi.h"
@@ -222,6 +224,17 @@
E ## isInvalid3, \
E ## isInvalid4
+#define NULL_VTABLE() \
+ NULL, \
+ NULL, \
+ NULL, \
+ NULL, \
+ NULL, \
+ NULL, \
+ NULL, \
+ NULL, \
+ NULL
+
static int FASTCALL checkCharRefNumber(int);
#include "xmltok_i.h"
@@ -467,7 +480,7 @@
#include "asciitab.h"
#include "latin1ta.h"
},
- STANDARD_VTABLE(sb_)
+ STANDARD_VTABLE(sb_) NULL_VTABLE()
};
#endif
@@ -480,7 +493,7 @@
#undef BT_COLON
#include "latin1ta.h"
},
- STANDARD_VTABLE(sb_)
+ STANDARD_VTABLE(sb_) NULL_VTABLE()
};
static void PTRCALL
@@ -500,7 +513,7 @@
#include "asciitab.h"
/* BT_NONXML == 0 */
},
- STANDARD_VTABLE(sb_)
+ STANDARD_VTABLE(sb_) NULL_VTABLE()
};
#endif
@@ -513,7 +526,7 @@
#undef BT_COLON
/* BT_NONXML == 0 */
},
- STANDARD_VTABLE(sb_)
+ STANDARD_VTABLE(sb_) NULL_VTABLE()
};
static int PTRFASTCALL
@@ -726,7 +739,7 @@
#include "asciitab.h"
#include "latin1ta.h"
},
- STANDARD_VTABLE(little2_)
+ STANDARD_VTABLE(little2_) NULL_VTABLE()
};
#endif
@@ -745,7 +758,7 @@
#undef BT_COLON
#include "latin1ta.h"
},
- STANDARD_VTABLE(little2_)
+ STANDARD_VTABLE(little2_) NULL_VTABLE()
};
#if BYTEORDER != 4321
@@ -758,7 +771,7 @@
#include "iasciita.h"
#include "latin1ta.h"
},
- STANDARD_VTABLE(little2_)
+ STANDARD_VTABLE(little2_) NULL_VTABLE()
};
#endif
@@ -771,7 +784,7 @@
#undef BT_COLON
#include "latin1ta.h"
},
- STANDARD_VTABLE(little2_)
+ STANDARD_VTABLE(little2_) NULL_VTABLE()
};
#endif
@@ -867,7 +880,7 @@
#include "asciitab.h"
#include "latin1ta.h"
},
- STANDARD_VTABLE(big2_)
+ STANDARD_VTABLE(big2_) NULL_VTABLE()
};
#endif
@@ -886,7 +899,7 @@
#undef BT_COLON
#include "latin1ta.h"
},
- STANDARD_VTABLE(big2_)
+ STANDARD_VTABLE(big2_) NULL_VTABLE()
};
#if BYTEORDER != 1234
@@ -899,7 +912,7 @@
#include "iasciita.h"
#include "latin1ta.h"
},
- STANDARD_VTABLE(big2_)
+ STANDARD_VTABLE(big2_) NULL_VTABLE()
};
#endif
@@ -912,7 +925,7 @@
#undef BT_COLON
#include "latin1ta.h"
},
- STANDARD_VTABLE(big2_)
+ STANDARD_VTABLE(big2_) NULL_VTABLE()
};
#endif
#else
#ifdef HAVE_EXPAT_CONFIG_H

35
contrib/hbexpat/3rd/expat/expat.h
View File

@@ -95,7 +95,9 @@ enum XML_Error {
/* Added in 2.0. */
XML_ERROR_RESERVED_PREFIX_XML,
XML_ERROR_RESERVED_PREFIX_XMLNS,
XML_ERROR_RESERVED_NAMESPACE_URI
XML_ERROR_RESERVED_NAMESPACE_URI,
/* Added in 2.2.1. */
XML_ERROR_INVALID_ARGUMENT
};
enum XML_Content_Type {
@@ -342,7 +344,7 @@ XML_SetEntityDeclHandler(XML_Parser parser,
XML_EntityDeclHandler handler);
/* OBSOLETE -- OBSOLETE -- OBSOLETE
This handler has been superceded by the EntityDeclHandler above.
This handler has been superseded by the EntityDeclHandler above.
It is provided here for backward compatibility.
This is called for a declaration of an unparsed (NDATA) entity.
@@ -706,6 +708,7 @@ XML_UseParserAsHandlerArg(XML_Parser parser);
be called, despite an external subset being parsed.
Note: If XML_DTD is not defined when Expat is compiled, returns
XML_ERROR_FEATURE_REQUIRES_XML_DTD.
Note: If parser == NULL, returns XML_ERROR_INVALID_ARGUMENT.
*/
XMLPARSEAPI(enum XML_Error)
XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD);
@@ -729,15 +732,16 @@ XML_GetBase(XML_Parser parser);
to the XML_StartElementHandler that were specified in the start-tag
rather than defaulted. Each attribute/value pair counts as 2; thus
this correspondds to an index into the atts array passed to the
XML_StartElementHandler.
XML_StartElementHandler. Returns -1 if parser == NULL.
*/
XMLPARSEAPI(int)
XML_GetSpecifiedAttributeCount(XML_Parser parser);
/* Returns the index of the ID attribute passed in the last call to
XML_StartElementHandler, or -1 if there is no ID attribute. Each
attribute/value pair counts as 2; thus this correspondds to an
index into the atts array passed to the XML_StartElementHandler.
XML_StartElementHandler, or -1 if there is no ID attribute or
parser == NULL. Each attribute/value pair counts as 2; thus this
correspondds to an index into the atts array passed to the
XML_StartElementHandler.
*/
XMLPARSEAPI(int)
XML_GetIdAttributeIndex(XML_Parser parser);
@@ -901,6 +905,7 @@ enum XML_ParamEntityParsing {
entities is requested; otherwise it will return non-zero.
Note: If XML_SetParamEntityParsing is called after XML_Parse or
XML_ParseBuffer, then it has no effect and will always return 0.
Note: If parser == NULL, the function will do nothing and return 0.
*/
XMLPARSEAPI(int)
XML_SetParamEntityParsing(XML_Parser parser,
@@ -910,6 +915,7 @@ XML_SetParamEntityParsing(XML_Parser parser,
Helps in preventing DoS attacks based on predicting hash
function behavior. This must be called before parsing is started.
Returns 1 if successful, 0 when called after parsing has started.
Note: If parser == NULL, the function will do nothing and return 0.
*/
XMLPARSEAPI(int)
XML_SetHashSalt(XML_Parser parser,
@@ -936,6 +942,10 @@ XML_GetErrorCode(XML_Parser parser);
the location is the location of the character at which the error
was detected; otherwise the location is the location of the last
parse event, as described above.
Note: XML_GetCurrentLineNumber and XML_GetCurrentColumnNumber
return 0 to indicate an error.
Note: XML_GetCurrentByteIndex returns -1 to indicate an error.
*/
XMLPARSEAPI(XML_Size) XML_GetCurrentLineNumber(XML_Parser parser);
XMLPARSEAPI(XML_Size) XML_GetCurrentColumnNumber(XML_Parser parser);
@@ -973,9 +983,12 @@ XML_FreeContentModel(XML_Parser parser, XML_Content *model);
/* Exposing the memory handling functions used in Expat */
XMLPARSEAPI(void *)
XML_ATTR_MALLOC
XML_ATTR_ALLOC_SIZE(2)
XML_MemMalloc(XML_Parser parser, size_t size);
XMLPARSEAPI(void *)
XML_ATTR_ALLOC_SIZE(3)
XML_MemRealloc(XML_Parser parser, void *ptr, size_t size);
XMLPARSEAPI(void)
@@ -1031,14 +1044,12 @@ XMLPARSEAPI(const XML_Feature *)
XML_GetFeatureList(void);
/* Expat follows the GNU/Linux convention of odd number minor version for
beta/development releases and even number minor version for stable
releases. Micro is bumped with each release, and set to 0 with each
change to major or minor version.
/* Expat follows the semantic versioning convention.
See http://semver.org.
*/
#define XML_MAJOR_VERSION 2
#define XML_MINOR_VERSION 1
#define XML_MICRO_VERSION 0
#define XML_MINOR_VERSION 2
#define XML_MICRO_VERSION 1
#ifdef __cplusplus
}

9
contrib/hbexpat/3rd/expat/expat.hbp
View File

@@ -20,9 +20,9 @@ xmltok.c
{bcc}-cflag=-w-8008
{bcc}-cflag=-w-8066
# ORIGIN http://expat.sourceforge.net/
# VER 2.1.0
# URL http://sourceforge.net/projects/expat/files/expat/2.1.0/expat-2.1.0.tar.gz/download
# ORIGIN https://expat.sourceforge.net/
# VER 2.2.1
# URL https://downloads.sourceforge.net/project/expat/expat/2.2.1/expat-2.2.1.tar.bz2
# DIFF expat.dif
#
# MAP COPYING
@@ -31,7 +31,6 @@ xmltok.c
# MAP lib/xmltok.c xmltok.c
# MAP lib/xmltok_impl.c xmltok_i.c
# MAP lib/xmltok_ns.c xmltok_n.c
# MAP lib/amigaconfig.h amigacon.h
# MAP lib/ascii.h ascii.h
# MAP lib/asciitab.h asciitab.h
# MAP lib/expat.h expat.h
@@ -39,8 +38,8 @@ xmltok.c
# MAP lib/iasciitab.h iasciita.h
# MAP lib/internal.h internal.h
# MAP lib/latin1tab.h latin1ta.h
# MAP lib/macconfig.h macconfi.h
# MAP lib/nametab.h nametab.h
# MAP lib/siphash.h siphash.h
# MAP lib/utf8tab.h utf8tab.h
# MAP lib/winconfig.h winconfi.h
# MAP lib/xmlrole.h xmlrole.h

19
contrib/hbexpat/3rd/expat/expat_ex.h
View File

@@ -65,12 +65,26 @@
#endif
#endif /* not defined XML_STATIC */
#if !defined(XMLIMPORT) && defined(__GNUC__) && (__GNUC__ >= 4)
#define XMLIMPORT __attribute__ ((visibility ("default")))
#endif
/* If we didn't define it above, define it away: */
#ifndef XMLIMPORT
#define XMLIMPORT
#endif
#if defined(__GNUC__) && (__GNUC__ > 2 || (__GNUC__ == 2 && __GNUC_MINOR__ >= 96))
#define XML_ATTR_MALLOC __attribute__((__malloc__))
#else
#define XML_ATTR_MALLOC
#endif
#if defined(__GNUC__) && ((__GNUC__ > 4) || (__GNUC__ == 4 && __GNUC_MINOR__ >= 3))
#define XML_ATTR_ALLOC_SIZE(x) __attribute__((__alloc_size__(x)))
#else
#define XML_ATTR_ALLOC_SIZE(x)
#endif
#define XMLPARSEAPI(type) XMLIMPORT type XMLCALL
@@ -79,7 +93,10 @@ extern "C" {
#endif
#ifdef XML_UNICODE_WCHAR_T
#define XML_UNICODE
# define XML_UNICODE
# if defined(__SIZEOF_WCHAR_T__) && (__SIZEOF_WCHAR_T__ != 2)
# error "sizeof(wchar_t) != 2; Need -fshort-wchar for both Expat and libc"
# endif
#endif
#ifdef XML_UNICODE /* Information is UTF-16 encoded. */

22
contrib/hbexpat/3rd/expat/internal.h
View File

@@ -71,3 +71,25 @@
#define inline
#endif
#endif
#ifndef UNUSED_P
# ifdef __GNUC__
# define UNUSED_P(p) UNUSED_ ## p __attribute__((__unused__))
# else
# define UNUSED_P(p) UNUSED_ ## p
# endif
#endif
#ifdef __cplusplus
extern "C" {
#endif
void
align_limit_to_full_utf8_characters(const char * from, const char ** fromLimRef);
#ifdef __cplusplus
}
#endif

53
contrib/hbexpat/3rd/expat/macconfi.h
View File

@@ -1,53 +0,0 @@
/*================================================================
** Copyright 2000, Clark Cooper
** All rights reserved.
**
** This is free software. You are permitted to copy, distribute, or modify
** it under the terms of the MIT/X license (contained in the COPYING file
** with this distribution.)
**
*/
#ifndef MACCONFIG_H
#define MACCONFIG_H
/* 1234 = LIL_ENDIAN, 4321 = BIGENDIAN */
#define BYTEORDER 4321
/* Define to 1 if you have the `bcopy' function. */
#undef HAVE_BCOPY
/* Define to 1 if you have the `memmove' function. */
#define HAVE_MEMMOVE
/* Define to 1 if you have a working `mmap' system call. */
#undef HAVE_MMAP
/* Define to 1 if you have the <unistd.h> header file. */
#undef HAVE_UNISTD_H
/* whether byteorder is bigendian */
#define WORDS_BIGENDIAN
/* Define to specify how much context to retain around the current parse
point. */
#undef XML_CONTEXT_BYTES
/* Define to make parameter entity parsing functionality available. */
#define XML_DTD
/* Define to make XML Namespaces functionality available. */
#define XML_NS
/* Define to empty if `const' does not conform to ANSI C. */
#undef const
/* Define to `long' if <sys/types.h> does not define. */
#define off_t long
/* Define to `unsigned' if <sys/types.h> does not define. */
#undef size_t
#endif /* ifndef MACCONFIG_H */

10
contrib/hbexpat/3rd/expat/winconfi.h
View File

@@ -17,6 +17,12 @@
#include <memory.h>
#include <string.h>
#if defined(HAVE_EXPAT_CONFIG_H) /* e.g. MinGW */
# include <expat_config.h>
#else /* !defined(HAVE_EXPAT_CONFIG_H) */
#define XML_NS 1
#define XML_DTD 1
#define XML_CONTEXT_BYTES 1024
@@ -27,4 +33,8 @@
/* Windows has memmove() available. */
#define HAVE_MEMMOVE
#endif /* !defined(HAVE_EXPAT_CONFIG_H) */
#endif /* ndef WINCONFIG_H */

712
contrib/hbexpat/3rd/expat/xmlparse.c
View File

File diff suppressed because it is too large Load Diff

230
contrib/hbexpat/3rd/expat/xmlrole.c
View File

@@ -6,19 +6,13 @@
#ifdef HARBOUR_CONF
#include "_hbconf.h"
#elif defined(COMPILED_FROM_DSP)
#elif defined(_WIN32)
#include "winconfi.h"
#elif defined(MACOS_CLASSIC)
#include "macconfi.h"
#elif defined(__amigaos__)
#include "amigacon.h"
#elif defined(__WATCOMC__)
#include "watcomconfig.h"
#else
#ifdef HAVE_EXPAT_CONFIG_H
#include <expat_config.h>
#endif
#endif /* ndef COMPILED_FROM_DSP */
#endif /* ndef _WIN32 */
#include "expat_ex.h"
#include "internal.h"
@@ -197,9 +191,9 @@ prolog1(PROLOG_STATE *state,
static int PTRCALL
prolog2(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -218,9 +212,9 @@ prolog2(PROLOG_STATE *state,
static int PTRCALL
doctype0(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -266,9 +260,9 @@ doctype1(PROLOG_STATE *state,
static int PTRCALL
doctype2(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -283,9 +277,9 @@ doctype2(PROLOG_STATE *state,
static int PTRCALL
doctype3(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -300,9 +294,9 @@ doctype3(PROLOG_STATE *state,
static int PTRCALL
doctype4(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -320,9 +314,9 @@ doctype4(PROLOG_STATE *state,
static int PTRCALL
doctype5(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -439,9 +433,9 @@ externalSubset1(PROLOG_STATE *state,
static int PTRCALL
entity0(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -459,9 +453,9 @@ entity0(PROLOG_STATE *state,
static int PTRCALL
entity1(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -504,9 +498,9 @@ entity2(PROLOG_STATE *state,
static int PTRCALL
entity3(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -521,9 +515,9 @@ entity3(PROLOG_STATE *state,
static int PTRCALL
entity4(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -561,9 +555,9 @@ entity5(PROLOG_STATE *state,
static int PTRCALL
entity6(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -607,9 +601,9 @@ entity7(PROLOG_STATE *state,
static int PTRCALL
entity8(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -624,9 +618,9 @@ entity8(PROLOG_STATE *state,
static int PTRCALL
entity9(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -641,9 +635,9 @@ entity9(PROLOG_STATE *state,
static int PTRCALL
entity10(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -658,9 +652,9 @@ entity10(PROLOG_STATE *state,
static int PTRCALL
notation0(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -699,9 +693,9 @@ notation1(PROLOG_STATE *state,
static int PTRCALL
notation2(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -716,9 +710,9 @@ notation2(PROLOG_STATE *state,
static int PTRCALL
notation3(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -734,9 +728,9 @@ notation3(PROLOG_STATE *state,
static int PTRCALL
notation4(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -755,9 +749,9 @@ notation4(PROLOG_STATE *state,
static int PTRCALL
attlist0(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -773,9 +767,9 @@ attlist0(PROLOG_STATE *state,
static int PTRCALL
attlist1(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -835,9 +829,9 @@ attlist2(PROLOG_STATE *state,
static int PTRCALL
attlist3(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -854,9 +848,9 @@ attlist3(PROLOG_STATE *state,
static int PTRCALL
attlist4(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -874,9 +868,9 @@ attlist4(PROLOG_STATE *state,
static int PTRCALL
attlist5(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -891,9 +885,9 @@ attlist5(PROLOG_STATE *state,
static int PTRCALL
attlist6(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -908,9 +902,9 @@ attlist6(PROLOG_STATE *state,
static int PTRCALL
attlist7(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -969,9 +963,9 @@ attlist8(PROLOG_STATE *state,
static int PTRCALL
attlist9(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -986,9 +980,9 @@ attlist9(PROLOG_STATE *state,
static int PTRCALL
element0(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -1074,9 +1068,9 @@ element2(PROLOG_STATE *state,
static int PTRCALL
element3(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -1099,9 +1093,9 @@ element3(PROLOG_STATE *state,
static int PTRCALL
element4(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -1117,9 +1111,9 @@ element4(PROLOG_STATE *state,
static int PTRCALL
element5(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -1138,9 +1132,9 @@ element5(PROLOG_STATE *state,
static int PTRCALL
element6(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -1168,9 +1162,9 @@ element6(PROLOG_STATE *state,
static int PTRCALL
element7(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -1242,9 +1236,9 @@ condSect0(PROLOG_STATE *state,
static int PTRCALL
condSect1(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -1260,9 +1254,9 @@ condSect1(PROLOG_STATE *state,
static int PTRCALL
condSect2(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -1279,9 +1273,9 @@ condSect2(PROLOG_STATE *state,
static int PTRCALL
declClose(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
switch (tok) {
case XML_TOK_PROLOG_S:
@@ -1294,11 +1288,11 @@ declClose(PROLOG_STATE *state,
}
static int PTRCALL
error(PROLOG_STATE *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc)
error(PROLOG_STATE *UNUSED_P(state),
int UNUSED_P(tok),
const char *UNUSED_P(ptr),
const char *UNUSED_P(end),
const ENCODING *UNUSED_P(enc))
{
return XML_ROLE_NONE;
}

253
contrib/hbexpat/3rd/expat/xmltok.c
View File

@@ -6,19 +6,13 @@
#ifdef HARBOUR_CONF
#include "_hbconf.h"
#elif defined(COMPILED_FROM_DSP)
#elif defined(_WIN32)
#include "winconfi.h"
#elif defined(MACOS_CLASSIC)
#include "macconfi.h"
#elif defined(__amigaos__)
#include "amigacon.h"
#elif defined(__WATCOMC__)
#include "watcomconfig.h"
#else
#ifdef HAVE_EXPAT_CONFIG_H
#include <expat_config.h>
#endif
#endif /* ndef COMPILED_FROM_DSP */
#endif /* ndef _WIN32 */
#include "expat_ex.h"
#include "internal.h"
@@ -48,7 +42,7 @@
#define VTABLE VTABLE1, PREFIX(toUtf8), PREFIX(toUtf16)
#define UCS2_GET_NAMING(pages, hi, lo) \
(namingBitmap[(pages[hi] << 3) + ((lo) >> 5)] & (1 << ((lo) & 0x1F)))
(namingBitmap[(pages[hi] << 3) + ((lo) >> 5)] & (1u << ((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
@@ -58,7 +52,7 @@
(namingBitmap[((pages)[(((byte)[0]) >> 2) & 7] << 3) \
+ ((((byte)[0]) & 3) << 1) \
+ ((((byte)[1]) >> 5) & 1)] \
& (1 << (((byte)[1]) & 0x1F)))
& (1u << (((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
@@ -71,7 +65,7 @@
<< 3) \
+ ((((byte)[1]) & 3) << 1) \
+ ((((byte)[2]) >> 5) & 1)] \
& (1 << (((byte)[2]) & 0x1F)))
& (1u << (((byte)[2]) & 0x1F)))
#define UTF8_GET_NAMING(pages, p, n) \
((n) == 2 \
@@ -124,19 +118,19 @@
((*p) == 0xF4 ? (p)[1] > 0x8F : ((p)[1] & 0xC0) == 0xC0)))
static int PTRFASTCALL
isNever(const ENCODING *enc, const char *p)
isNever(const ENCODING *UNUSED_P(enc), const char *UNUSED_P(p))
{
return 0;
}
static int PTRFASTCALL
utf8_isName2(const ENCODING *enc, const char *p)
utf8_isName2(const ENCODING *UNUSED_P(enc), const char *p)
{
return UTF8_GET_NAMING2(namePages, (const unsigned char *)p);
}
static int PTRFASTCALL
utf8_isName3(const ENCODING *enc, const char *p)
utf8_isName3(const ENCODING *UNUSED_P(enc), const char *p)
{
return UTF8_GET_NAMING3(namePages, (const unsigned char *)p);
}
@@ -144,13 +138,13 @@ utf8_isName3(const ENCODING *enc, const char *p)
#define utf8_isName4 isNever
static int PTRFASTCALL
utf8_isNmstrt2(const ENCODING *enc, const char *p)
utf8_isNmstrt2(const ENCODING *UNUSED_P(enc), const char *p)
{
return UTF8_GET_NAMING2(nmstrtPages, (const unsigned char *)p);
}
static int PTRFASTCALL
utf8_isNmstrt3(const ENCODING *enc, const char *p)
utf8_isNmstrt3(const ENCODING *UNUSED_P(enc), const char *p)
{
return UTF8_GET_NAMING3(nmstrtPages, (const unsigned char *)p);
}
@@ -158,19 +152,19 @@ utf8_isNmstrt3(const ENCODING *enc, const char *p)
#define utf8_isNmstrt4 isNever
static int PTRFASTCALL
utf8_isInvalid2(const ENCODING *enc, const char *p)
utf8_isInvalid2(const ENCODING *UNUSED_P(enc), const char *p)
{
return UTF8_INVALID2((const unsigned char *)p);
}
static int PTRFASTCALL
utf8_isInvalid3(const ENCODING *enc, const char *p)
utf8_isInvalid3(const ENCODING *UNUSED_P(enc), const char *p)
{
return UTF8_INVALID3((const unsigned char *)p);
}
static int PTRFASTCALL
utf8_isInvalid4(const ENCODING *enc, const char *p)
utf8_isInvalid4(const ENCODING *UNUSED_P(enc), const char *p)
{
return UTF8_INVALID4((const unsigned char *)p);
}
@@ -224,16 +218,16 @@ struct normal_encoding {
E ## isInvalid3, \
E ## isInvalid4
#define NULL_VTABLE() \
NULL, \
NULL, \
NULL, \
NULL, \
NULL, \
NULL, \
NULL, \
NULL, \
NULL
#define NULL_VTABLE \
/* isName2 */ NULL, \
/* isName3 */ NULL, \
/* isName4 */ NULL, \
/* isNmstrt2 */ NULL, \
/* isNmstrt3 */ NULL, \
/* isNmstrt4 */ NULL, \
/* isInvalid2 */ NULL, \
/* isInvalid3 */ NULL, \
/* isInvalid4 */ NULL
static int FASTCALL checkCharRefNumber(int);
@@ -331,39 +325,89 @@ enum { /* UTF8_cvalN is value of masked first byte of N byte sequence */
UTF8_cval4 = 0xf0
};
static void PTRCALL
utf8_toUtf8(const ENCODING *enc,
void
align_limit_to_full_utf8_characters(const char * from, const char ** fromLimRef)
{
const char * fromLim = *fromLimRef;
size_t walked = 0;
for (; fromLim > from; fromLim--, walked++) {
const unsigned char prev = (unsigned char)fromLim[-1];
if ((prev & 0xf8u) == 0xf0u) { /* 4-byte character, lead by 0b11110xxx byte */
if (walked + 1 >= 4) {
fromLim += 4 - 1;
break;
} else {
walked = 0;
}
} else if ((prev & 0xf0u) == 0xe0u) { /* 3-byte character, lead by 0b1110xxxx byte */
if (walked + 1 >= 3) {
fromLim += 3 - 1;
break;
} else {
walked = 0;
}
} else if ((prev & 0xe0u) == 0xc0u) { /* 2-byte character, lead by 0b110xxxxx byte */
if (walked + 1 >= 2) {
fromLim += 2 - 1;
break;
} else {
walked = 0;
}
} else if ((prev & 0x80u) == 0x00u) { /* 1-byte character, matching 0b0xxxxxxx */
break;
}
}
*fromLimRef = fromLim;
}
static enum XML_Convert_Result PTRCALL
utf8_toUtf8(const ENCODING *UNUSED_P(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++)
const char *fromLimInitial = fromLim;
/* Avoid copying partial characters. */
align_limit_to_full_utf8_characters(*fromP, &fromLim);
for (to = *toP, from = *fromP; (from < fromLim) && (to < toLim); from++, to++)
*to = *from;
*fromP = from;
*toP = to;
if (fromLim < fromLimInitial)
return XML_CONVERT_INPUT_INCOMPLETE;
else if ((to == toLim) && (from < fromLim))
return XML_CONVERT_OUTPUT_EXHAUSTED;
else
return XML_CONVERT_COMPLETED;
}
static void PTRCALL
static enum XML_Convert_Result PTRCALL
utf8_toUtf16(const ENCODING *enc,
const char **fromP, const char *fromLim,
unsigned short **toP, const unsigned short *toLim)
{
enum XML_Convert_Result res = XML_CONVERT_COMPLETED;
unsigned short *to = *toP;
const char *from = *fromP;
while (from != fromLim && to != toLim) {
while (from < fromLim && to < toLim) {
switch (((struct normal_encoding *)enc)->type[(unsigned char)*from]) {
case BT_LEAD2:
if (fromLim - from < 2) {
res = XML_CONVERT_INPUT_INCOMPLETE;
goto after;
}
*to++ = (unsigned short)(((from[0] & 0x1f) << 6) | (from[1] & 0x3f));
from += 2;
break;
case BT_LEAD3:
if (fromLim - from < 3) {
res = XML_CONVERT_INPUT_INCOMPLETE;
goto after;
}
*to++ = (unsigned short)(((from[0] & 0xf) << 12)
| ((from[1] & 0x3f) << 6) | (from[2] & 0x3f));
from += 3;
@@ -371,8 +415,14 @@ utf8_toUtf16(const ENCODING *enc,
case BT_LEAD4:
{
unsigned long n;
if (to + 1 == toLim)
if (toLim - to < 2) {
res = XML_CONVERT_OUTPUT_EXHAUSTED;
goto after;
}
if (fromLim - from < 4) {
res = XML_CONVERT_INPUT_INCOMPLETE;
goto after;
}
n = ((from[0] & 0x7) << 18) | ((from[1] & 0x3f) << 12)
| ((from[2] & 0x3f) << 6) | (from[3] & 0x3f);
n -= 0x10000;
@@ -387,9 +437,12 @@ utf8_toUtf16(const ENCODING *enc,
break;
}
}
if (from < fromLim)
res = XML_CONVERT_OUTPUT_EXHAUSTED;
after:
*fromP = from;
*toP = to;
return res;
}
#ifdef XML_NS
@@ -438,38 +491,43 @@ static const struct normal_encoding internal_utf8_encoding = {
STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_)
};
static void PTRCALL
latin1_toUtf8(const ENCODING *enc,
static enum XML_Convert_Result PTRCALL
latin1_toUtf8(const ENCODING *UNUSED_P(enc),
const char **fromP, const char *fromLim,
char **toP, const char *toLim)
{
for (;;) {
unsigned char c;
if (*fromP == fromLim)
break;
return XML_CONVERT_COMPLETED;
c = (unsigned char)**fromP;
if (c & 0x80) {
if (toLim - *toP < 2)
break;
return XML_CONVERT_OUTPUT_EXHAUSTED;
*(*toP)++ = (char)((c >> 6) | UTF8_cval2);
*(*toP)++ = (char)((c & 0x3f) | 0x80);
(*fromP)++;
}
else {
if (*toP == toLim)
break;
return XML_CONVERT_OUTPUT_EXHAUSTED;
*(*toP)++ = *(*fromP)++;
}
}
}
static void PTRCALL
latin1_toUtf16(const ENCODING *enc,
static enum XML_Convert_Result PTRCALL
latin1_toUtf16(const ENCODING *UNUSED_P(enc),
const char **fromP, const char *fromLim,
unsigned short **toP, const unsigned short *toLim)
{
while (*fromP != fromLim && *toP != toLim)
while (*fromP < fromLim && *toP < toLim)
*(*toP)++ = (unsigned char)*(*fromP)++;
if ((*toP == toLim) && (*fromP < fromLim))
return XML_CONVERT_OUTPUT_EXHAUSTED;
else
return XML_CONVERT_COMPLETED;
}
#ifdef XML_NS
@@ -480,7 +538,7 @@ static const struct normal_encoding latin1_encoding_ns = {
#include "asciitab.h"
#include "latin1ta.h"
},
STANDARD_VTABLE(sb_) NULL_VTABLE()
STANDARD_VTABLE(sb_) NULL_VTABLE
};
#endif
@@ -493,16 +551,21 @@ static const struct normal_encoding latin1_encoding = {
#undef BT_COLON
#include "latin1ta.h"
},
STANDARD_VTABLE(sb_) NULL_VTABLE()
STANDARD_VTABLE(sb_) NULL_VTABLE
};
static void PTRCALL
ascii_toUtf8(const ENCODING *enc,
static enum XML_Convert_Result PTRCALL
ascii_toUtf8(const ENCODING *UNUSED_P(enc),
const char **fromP, const char *fromLim,
char **toP, const char *toLim)
{
while (*fromP != fromLim && *toP != toLim)
while (*fromP < fromLim && *toP < toLim)
*(*toP)++ = *(*fromP)++;
if ((*toP == toLim) && (*fromP < fromLim))
return XML_CONVERT_OUTPUT_EXHAUSTED;
else
return XML_CONVERT_COMPLETED;
}
#ifdef XML_NS
@@ -513,7 +576,7 @@ static const struct normal_encoding ascii_encoding_ns = {
#include "asciitab.h"
/* BT_NONXML == 0 */
},
STANDARD_VTABLE(sb_) NULL_VTABLE()
STANDARD_VTABLE(sb_) NULL_VTABLE
};
#endif
@@ -526,7 +589,7 @@ static const struct normal_encoding ascii_encoding = {
#undef BT_COLON
/* BT_NONXML == 0 */
},
STANDARD_VTABLE(sb_) NULL_VTABLE()
STANDARD_VTABLE(sb_) NULL_VTABLE
};
static int PTRFASTCALL
@@ -549,13 +612,14 @@ unicode_byte_type(char hi, char lo)
}
#define DEFINE_UTF16_TO_UTF8(E) \
static void PTRCALL \
E ## toUtf8(const ENCODING *enc, \
static enum XML_Convert_Result PTRCALL \
E ## toUtf8(const ENCODING *UNUSED_P(enc), \
const char **fromP, const char *fromLim, \
char **toP, const char *toLim) \
{ \
const char *from; \
for (from = *fromP; from != fromLim; from += 2) { \
const char *from = *fromP; \
fromLim = from + (((fromLim - from) >> 1) << 1); /* shrink to even */ \
for (; from < fromLim; from += 2) { \
int plane; \
unsigned char lo2; \
unsigned char lo = GET_LO(from); \
@@ -565,7 +629,7 @@ E ## toUtf8(const ENCODING *enc, \
if (lo < 0x80) { \
if (*toP == toLim) { \
*fromP = from; \
return; \
return XML_CONVERT_OUTPUT_EXHAUSTED; \
} \
*(*toP)++ = lo; \
break; \
@@ -575,7 +639,7 @@ E ## toUtf8(const ENCODING *enc, \
case 0x4: case 0x5: case 0x6: case 0x7: \
if (toLim - *toP < 2) { \
*fromP = from; \
return; \
return XML_CONVERT_OUTPUT_EXHAUSTED; \
} \
*(*toP)++ = ((lo >> 6) | (hi << 2) | UTF8_cval2); \
*(*toP)++ = ((lo & 0x3f) | 0x80); \
@@ -583,7 +647,7 @@ E ## toUtf8(const ENCODING *enc, \
default: \
if (toLim - *toP < 3) { \
*fromP = from; \
return; \
return XML_CONVERT_OUTPUT_EXHAUSTED; \
} \
/* 16 bits divided 4, 6, 6 amongst 3 bytes */ \
*(*toP)++ = ((hi >> 4) | UTF8_cval3); \
@@ -593,7 +657,11 @@ E ## toUtf8(const ENCODING *enc, \
case 0xD8: case 0xD9: case 0xDA: case 0xDB: \
if (toLim - *toP < 4) { \
*fromP = from; \
return; \
return XML_CONVERT_OUTPUT_EXHAUSTED; \
} \
if (fromLim - from < 4) { \
*fromP = from; \
return XML_CONVERT_INPUT_INCOMPLETE; \
} \
plane = (((hi & 0x3) << 2) | ((lo >> 6) & 0x3)) + 1; \
*(*toP)++ = ((plane >> 2) | UTF8_cval4); \
@@ -609,20 +677,32 @@ E ## toUtf8(const ENCODING *enc, \
} \
} \
*fromP = from; \
if (from < fromLim) \
return XML_CONVERT_INPUT_INCOMPLETE; \
else \
return XML_CONVERT_COMPLETED; \
}
#define DEFINE_UTF16_TO_UTF16(E) \
static void PTRCALL \
E ## toUtf16(const ENCODING *enc, \
static enum XML_Convert_Result PTRCALL \
E ## toUtf16(const ENCODING *UNUSED_P(enc), \
const char **fromP, const char *fromLim, \
unsigned short **toP, const unsigned short *toLim) \
{ \
enum XML_Convert_Result res = XML_CONVERT_COMPLETED; \
fromLim = *fromP + (((fromLim - *fromP) >> 1) << 1); /* shrink to even */ \
/* Avoid copying first half only of surrogate */ \
if (fromLim - *fromP > ((toLim - *toP) << 1) \
&& (GET_HI(fromLim - 2) & 0xF8) == 0xD8) \
&& (GET_HI(fromLim - 2) & 0xF8) == 0xD8) { \
fromLim -= 2; \
for (; *fromP != fromLim && *toP != toLim; *fromP += 2) \
res = XML_CONVERT_INPUT_INCOMPLETE; \
} \
for (; *fromP < fromLim && *toP < toLim; *fromP += 2) \
*(*toP)++ = (GET_HI(*fromP) << 8) | GET_LO(*fromP); \
if ((*toP == toLim) && (*fromP < fromLim)) \
return XML_CONVERT_OUTPUT_EXHAUSTED; \
else \
return res; \
}
#define SET2(ptr, ch) \
@@ -739,7 +819,7 @@ static const struct normal_encoding little2_encoding_ns = {
#include "asciitab.h"
#include "latin1ta.h"
},
STANDARD_VTABLE(little2_) NULL_VTABLE()
STANDARD_VTABLE(little2_) NULL_VTABLE
};
#endif
@@ -758,7 +838,7 @@ static const struct normal_encoding little2_encoding = {
#undef BT_COLON
#include "latin1ta.h"
},
STANDARD_VTABLE(little2_) NULL_VTABLE()
STANDARD_VTABLE(little2_) NULL_VTABLE
};
#if BYTEORDER != 4321
@@ -771,7 +851,7 @@ static const struct normal_encoding internal_little2_encoding_ns = {
#include "iasciita.h"
#include "latin1ta.h"
},
STANDARD_VTABLE(little2_) NULL_VTABLE()
STANDARD_VTABLE(little2_) NULL_VTABLE
};
#endif
@@ -784,7 +864,7 @@ static const struct normal_encoding internal_little2_encoding = {
#undef BT_COLON
#include "latin1ta.h"
},
STANDARD_VTABLE(little2_) NULL_VTABLE()
STANDARD_VTABLE(little2_) NULL_VTABLE
};
#endif
@@ -880,7 +960,7 @@ static const struct normal_encoding big2_encoding_ns = {
#include "asciitab.h"
#include "latin1ta.h"
},
STANDARD_VTABLE(big2_) NULL_VTABLE()
STANDARD_VTABLE(big2_) NULL_VTABLE
};
#endif
@@ -899,7 +979,7 @@ static const struct normal_encoding big2_encoding = {
#undef BT_COLON
#include "latin1ta.h"
},
STANDARD_VTABLE(big2_) NULL_VTABLE()
STANDARD_VTABLE(big2_) NULL_VTABLE
};
#if BYTEORDER != 1234
@@ -912,7 +992,7 @@ static const struct normal_encoding internal_big2_encoding_ns = {
#include "iasciita.h"
#include "latin1ta.h"
},
STANDARD_VTABLE(big2_) NULL_VTABLE()
STANDARD_VTABLE(big2_) NULL_VTABLE
};
#endif
@@ -925,7 +1005,7 @@ static const struct normal_encoding internal_big2_encoding = {
#undef BT_COLON
#include "latin1ta.h"
},
STANDARD_VTABLE(big2_) NULL_VTABLE()
STANDARD_VTABLE(big2_) NULL_VTABLE
};
#endif
@@ -951,7 +1031,7 @@ streqci(const char *s1, const char *s2)
}
static void PTRCALL
initUpdatePosition(const ENCODING *enc, const char *ptr,
initUpdatePosition(const ENCODING *UNUSED_P(enc), const char *ptr,
const char *end, POSITION *pos)
{
normal_updatePosition(&utf8_encoding.enc, ptr, end, pos);
@@ -1301,7 +1381,7 @@ unknown_isInvalid(const ENCODING *enc, const char *p)
return (c & ~0xFFFF) || checkCharRefNumber(c) < 0;
}
static void PTRCALL
static enum XML_Convert_Result PTRCALL
unknown_toUtf8(const ENCODING *enc,
const char **fromP, const char *fromLim,
char **toP, const char *toLim)
@@ -1312,21 +1392,21 @@ unknown_toUtf8(const ENCODING *enc,
const char *utf8;
int n;
if (*fromP == fromLim)
break;
return XML_CONVERT_COMPLETED;
utf8 = uenc->utf8[(unsigned char)**fromP];
n = *utf8++;
if (n == 0) {
int c = uenc->convert(uenc->userData, *fromP);
n = XmlUtf8Encode(c, buf);
if (n > toLim - *toP)
break;
return XML_CONVERT_OUTPUT_EXHAUSTED;
utf8 = buf;
*fromP += (AS_NORMAL_ENCODING(enc)->type[(unsigned char)**fromP]
- (BT_LEAD2 - 2));
}
else {
if (n > toLim - *toP)
break;
return XML_CONVERT_OUTPUT_EXHAUSTED;
(*fromP)++;
}
do {
@@ -1335,13 +1415,13 @@ unknown_toUtf8(const ENCODING *enc,
}
}
static void PTRCALL
static enum XML_Convert_Result PTRCALL
unknown_toUtf16(const ENCODING *enc,
const char **fromP, const char *fromLim,
unsigned short **toP, const unsigned short *toLim)
{
const struct unknown_encoding *uenc = AS_UNKNOWN_ENCODING(enc);
while (*fromP != fromLim && *toP != toLim) {
while (*fromP < fromLim && *toP < toLim) {
unsigned short c = uenc->utf16[(unsigned char)**fromP];
if (c == 0) {
c = (unsigned short)
@@ -1353,6 +1433,11 @@ unknown_toUtf16(const ENCODING *enc,
(*fromP)++;
*(*toP)++ = c;
}
if ((*toP == toLim) && (*fromP < fromLim))
return XML_CONVERT_OUTPUT_EXHAUSTED;
else
return XML_CONVERT_COMPLETED;
}
ENCODING *
@@ -1516,7 +1601,7 @@ initScan(const ENCODING * const *encodingTable,
{
const ENCODING **encPtr;
if (ptr == end)
if (ptr >= end)
return XML_TOK_NONE;
encPtr = enc->encPtr;
if (ptr + 1 == end) {

10
contrib/hbexpat/3rd/expat/xmltok.h
View File

@@ -130,6 +130,12 @@ typedef int (PTRCALL *SCANNER)(const ENCODING *,
const char *,
const char **);
enum XML_Convert_Result {
XML_CONVERT_COMPLETED = 0,
XML_CONVERT_INPUT_INCOMPLETE = 1,
XML_CONVERT_OUTPUT_EXHAUSTED = 2 /* and therefore potentially input remaining as well */
};
struct encoding {
SCANNER scanners[XML_N_STATES];
SCANNER literalScanners[XML_N_LITERAL_TYPES];
@@ -158,12 +164,12 @@ struct encoding {
const char *ptr,
const char *end,
const char **badPtr);
void (PTRCALL *utf8Convert)(const ENCODING *enc,
enum XML_Convert_Result (PTRCALL *utf8Convert)(const ENCODING *enc,
const char **fromP,
const char *fromLim,
char **toP,
const char *toLim);
void (PTRCALL *utf16Convert)(const ENCODING *enc,
enum XML_Convert_Result (PTRCALL *utf16Convert)(const ENCODING *enc,
const char **fromP,
const char *fromLim,
unsigned short **toP,

226
contrib/hbexpat/3rd/expat/xmltok_i.c
View File

@@ -87,27 +87,45 @@
#define PREFIX(ident) ident
#endif
#define HAS_CHARS(enc, ptr, end, count) \
(end - ptr >= count * MINBPC(enc))
#define HAS_CHAR(enc, ptr, end) \
HAS_CHARS(enc, ptr, end, 1)
#define REQUIRE_CHARS(enc, ptr, end, count) \
{ \
if (! HAS_CHARS(enc, ptr, end, count)) { \
return XML_TOK_PARTIAL; \
} \
}
#define REQUIRE_CHAR(enc, ptr, end) \
REQUIRE_CHARS(enc, ptr, end, 1)
/* ptr points to character following "<!-" */
static int PTRCALL
PREFIX(scanComment)(const ENCODING *enc, const char *ptr,
const char *end, const char **nextTokPtr)
{
if (ptr != end) {
if (HAS_CHAR(enc, ptr, end)) {
if (!CHAR_MATCHES(enc, ptr, ASCII_MINUS)) {
*nextTokPtr = ptr;
return XML_TOK_INVALID;
}
ptr += MINBPC(enc);
while (ptr != end) {
while (HAS_CHAR(enc, ptr, end)) {
switch (BYTE_TYPE(enc, ptr)) {
INVALID_CASES(ptr, nextTokPtr)
case BT_MINUS:
if ((ptr += MINBPC(enc)) == end)
return XML_TOK_PARTIAL;
ptr += MINBPC(enc);
REQUIRE_CHAR(enc, ptr, end);
if (CHAR_MATCHES(enc, ptr, ASCII_MINUS)) {
if ((ptr += MINBPC(enc)) == end)
return XML_TOK_PARTIAL;
ptr += MINBPC(enc);
REQUIRE_CHAR(enc, ptr, end);
if (!CHAR_MATCHES(enc, ptr, ASCII_GT)) {
*nextTokPtr = ptr;
return XML_TOK_INVALID;
@@ -131,8 +149,7 @@ static int PTRCALL
PREFIX(scanDecl)(const ENCODING *enc, const char *ptr,
const char *end, const char **nextTokPtr)
{
if (ptr == end)
return XML_TOK_PARTIAL;
REQUIRE_CHAR(enc, ptr, end);
switch (BYTE_TYPE(enc, ptr)) {
case BT_MINUS:
return PREFIX(scanComment)(enc, ptr + MINBPC(enc), end, nextTokPtr);
@@ -147,11 +164,10 @@ PREFIX(scanDecl)(const ENCODING *enc, const char *ptr,
*nextTokPtr = ptr;
return XML_TOK_INVALID;
}
while (ptr != end) {
while (HAS_CHAR(enc, ptr, end)) {
switch (BYTE_TYPE(enc, ptr)) {
case BT_PERCNT:
if (ptr + MINBPC(enc) == end)
return XML_TOK_PARTIAL;
REQUIRE_CHARS(enc, ptr, end, 2);
/* 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:
@@ -175,7 +191,7 @@ PREFIX(scanDecl)(const ENCODING *enc, const char *ptr,
}
static int PTRCALL
PREFIX(checkPiTarget)(const ENCODING *enc, const char *ptr,
PREFIX(checkPiTarget)(const ENCODING *UNUSED_P(enc), const char *ptr,
const char *end, int *tokPtr)
{
int upper = 0;
@@ -225,15 +241,14 @@ PREFIX(scanPi)(const ENCODING *enc, const char *ptr,
{
int tok;
const char *target = ptr;
if (ptr == end)
return XML_TOK_PARTIAL;
REQUIRE_CHAR(enc, ptr, end);
switch (BYTE_TYPE(enc, ptr)) {
CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr)
default:
*nextTokPtr = ptr;
return XML_TOK_INVALID;
}
while (ptr != end) {
while (HAS_CHAR(enc, ptr, end)) {
switch (BYTE_TYPE(enc, ptr)) {
CHECK_NAME_CASES(enc, ptr, end, nextTokPtr)
case BT_S: case BT_CR: case BT_LF:
@@ -242,13 +257,12 @@ PREFIX(scanPi)(const ENCODING *enc, const char *ptr,
return XML_TOK_INVALID;
}
ptr += MINBPC(enc);
while (ptr != end) {
while (HAS_CHAR(enc, ptr, end)) {
switch (BYTE_TYPE(enc, ptr)) {
INVALID_CASES(ptr, nextTokPtr)
case BT_QUEST:
ptr += MINBPC(enc);
if (ptr == end)
return XML_TOK_PARTIAL;
REQUIRE_CHAR(enc, ptr, end);
if (CHAR_MATCHES(enc, ptr, ASCII_GT)) {
*nextTokPtr = ptr + MINBPC(enc);
return tok;
@@ -266,8 +280,7 @@ PREFIX(scanPi)(const ENCODING *enc, const char *ptr,
return XML_TOK_INVALID;
}
ptr += MINBPC(enc);
if (ptr == end)
return XML_TOK_PARTIAL;
REQUIRE_CHAR(enc, ptr, end);
if (CHAR_MATCHES(enc, ptr, ASCII_GT)) {
*nextTokPtr = ptr + MINBPC(enc);
return tok;
@@ -282,15 +295,14 @@ PREFIX(scanPi)(const ENCODING *enc, const char *ptr,
}
static int PTRCALL
PREFIX(scanCdataSection)(const ENCODING *enc, const char *ptr,
PREFIX(scanCdataSection)(const ENCODING *UNUSED_P(enc), const char *ptr,
const char *end, const char **nextTokPtr)
{
static const char CDATA_LSQB[] = { ASCII_C, ASCII_D, ASCII_A,
ASCII_T, ASCII_A, ASCII_LSQB };
int i;
/* CDATA[ */
if (end - ptr < 6 * MINBPC(enc))
return XML_TOK_PARTIAL;
REQUIRE_CHARS(enc, ptr, end, 6);
for (i = 0; i < 6; i++, ptr += MINBPC(enc)) {
if (!CHAR_MATCHES(enc, ptr, CDATA_LSQB[i])) {
*nextTokPtr = ptr;
@@ -305,7 +317,7 @@ static int PTRCALL
PREFIX(cdataSectionTok)(const ENCODING *enc, const char *ptr,
const char *end, const char **nextTokPtr)
{
if (ptr == end)
if (ptr >= end)
return XML_TOK_NONE;
if (MINBPC(enc) > 1) {
size_t n = end - ptr;
@@ -319,13 +331,11 @@ PREFIX(cdataSectionTok)(const ENCODING *enc, const char *ptr,
switch (BYTE_TYPE(enc, ptr)) {
case BT_RSQB:
ptr += MINBPC(enc);
if (ptr == end)
return XML_TOK_PARTIAL;
REQUIRE_CHAR(enc, ptr, end);
if (!CHAR_MATCHES(enc, ptr, ASCII_RSQB))
break;
ptr += MINBPC(enc);
if (ptr == end)
return XML_TOK_PARTIAL;
REQUIRE_CHAR(enc, ptr, end);
if (!CHAR_MATCHES(enc, ptr, ASCII_GT)) {
ptr -= MINBPC(enc);
break;
@@ -334,8 +344,7 @@ PREFIX(cdataSectionTok)(const ENCODING *enc, const char *ptr,
return XML_TOK_CDATA_SECT_CLOSE;
case BT_CR:
ptr += MINBPC(enc);
if (ptr == end)
return XML_TOK_PARTIAL;
REQUIRE_CHAR(enc, ptr, end);
if (BYTE_TYPE(enc, ptr) == BT_LF)
ptr += MINBPC(enc);
*nextTokPtr = ptr;
@@ -348,7 +357,7 @@ PREFIX(cdataSectionTok)(const ENCODING *enc, const char *ptr,
ptr += MINBPC(enc);
break;
}
while (ptr != end) {
while (HAS_CHAR(enc, ptr, end)) {
switch (BYTE_TYPE(enc, ptr)) {
#define LEAD_CASE(n) \
case BT_LEAD ## n: \
@@ -383,19 +392,18 @@ static int PTRCALL
PREFIX(scanEndTag)(const ENCODING *enc, const char *ptr,
const char *end, const char **nextTokPtr)
{
if (ptr == end)
return XML_TOK_PARTIAL;
REQUIRE_CHAR(enc, ptr, end);
switch (BYTE_TYPE(enc, ptr)) {
CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr)
default:
*nextTokPtr = ptr;
return XML_TOK_INVALID;
}
while (ptr != end) {
while (HAS_CHAR(enc, 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)) {
for (ptr += MINBPC(enc); HAS_CHAR(enc, ptr, end); ptr += MINBPC(enc)) {
switch (BYTE_TYPE(enc, ptr)) {
case BT_S: case BT_CR: case BT_LF:
break;
@@ -432,7 +440,7 @@ static int PTRCALL
PREFIX(scanHexCharRef)(const ENCODING *enc, const char *ptr,
const char *end, const char **nextTokPtr)
{
if (ptr != end) {
if (HAS_CHAR(enc, ptr, end)) {
switch (BYTE_TYPE(enc, ptr)) {
case BT_DIGIT:
case BT_HEX:
@@ -441,7 +449,7 @@ PREFIX(scanHexCharRef)(const ENCODING *enc, const char *ptr,
*nextTokPtr = ptr;
return XML_TOK_INVALID;
}
for (ptr += MINBPC(enc); ptr != end; ptr += MINBPC(enc)) {
for (ptr += MINBPC(enc); HAS_CHAR(enc, ptr, end); ptr += MINBPC(enc)) {
switch (BYTE_TYPE(enc, ptr)) {
case BT_DIGIT:
case BT_HEX:
@@ -464,7 +472,7 @@ static int PTRCALL
PREFIX(scanCharRef)(const ENCODING *enc, const char *ptr,
const char *end, const char **nextTokPtr)
{
if (ptr != end) {
if (HAS_CHAR(enc, ptr, end)) {
if (CHAR_MATCHES(enc, ptr, ASCII_x))
return PREFIX(scanHexCharRef)(enc, ptr + MINBPC(enc), end, nextTokPtr);
switch (BYTE_TYPE(enc, ptr)) {
@@ -474,7 +482,7 @@ PREFIX(scanCharRef)(const ENCODING *enc, const char *ptr,
*nextTokPtr = ptr;
return XML_TOK_INVALID;
}
for (ptr += MINBPC(enc); ptr != end; ptr += MINBPC(enc)) {
for (ptr += MINBPC(enc); HAS_CHAR(enc, ptr, end); ptr += MINBPC(enc)) {
switch (BYTE_TYPE(enc, ptr)) {
case BT_DIGIT:
break;
@@ -496,8 +504,7 @@ static int PTRCALL
PREFIX(scanRef)(const ENCODING *enc, const char *ptr, const char *end,
const char **nextTokPtr)
{
if (ptr == end)
return XML_TOK_PARTIAL;
REQUIRE_CHAR(enc, ptr, end);
switch (BYTE_TYPE(enc, ptr)) {
CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr)
case BT_NUM:
@@ -506,7 +513,7 @@ PREFIX(scanRef)(const ENCODING *enc, const char *ptr, const char *end,
*nextTokPtr = ptr;
return XML_TOK_INVALID;
}
while (ptr != end) {
while (HAS_CHAR(enc, ptr, end)) {
switch (BYTE_TYPE(enc, ptr)) {
CHECK_NAME_CASES(enc, ptr, end, nextTokPtr)
case BT_SEMI:
@@ -529,7 +536,7 @@ PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end,
#ifdef XML_NS
int hadColon = 0;
#endif
while (ptr != end) {
while (HAS_CHAR(enc, ptr, end)) {
switch (BYTE_TYPE(enc, ptr)) {
CHECK_NAME_CASES(enc, ptr, end, nextTokPtr)
#ifdef XML_NS
@@ -540,8 +547,7 @@ PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end,
}
hadColon = 1;
ptr += MINBPC(enc);
if (ptr == end)
return XML_TOK_PARTIAL;
REQUIRE_CHAR(enc, ptr, end);
switch (BYTE_TYPE(enc, ptr)) {
CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr)
default:
@@ -555,8 +561,7 @@ PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end,
int t;
ptr += MINBPC(enc);
if (ptr == end)
return XML_TOK_PARTIAL;
REQUIRE_CHAR(enc, ptr, end);
t = BYTE_TYPE(enc, ptr);
if (t == BT_EQUALS)
break;
@@ -579,8 +584,7 @@ PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end,
#endif
for (;;) {
ptr += MINBPC(enc);
if (ptr == end)
return XML_TOK_PARTIAL;
REQUIRE_CHAR(enc, ptr, end);
open = BYTE_TYPE(enc, ptr);
if (open == BT_QUOT || open == BT_APOS)
break;
@@ -598,8 +602,7 @@ PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end,
/* in attribute value */
for (;;) {
int t;
if (ptr == end)
return XML_TOK_PARTIAL;
REQUIRE_CHAR(enc, ptr, end);
t = BYTE_TYPE(enc, ptr);
if (t == open)
break;
@@ -624,8 +627,7 @@ PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end,
}
}
ptr += MINBPC(enc);
if (ptr == end)
return XML_TOK_PARTIAL;
REQUIRE_CHAR(enc, ptr, end);
switch (BYTE_TYPE(enc, ptr)) {
case BT_S:
case BT_CR:
@@ -642,8 +644,7 @@ PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end,
/* ptr points to closing quote */
for (;;) {
ptr += MINBPC(enc);
if (ptr == end)
return XML_TOK_PARTIAL;
REQUIRE_CHAR(enc, ptr, end);
switch (BYTE_TYPE(enc, ptr)) {
CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr)
case BT_S: case BT_CR: case BT_LF:
@@ -655,8 +656,7 @@ PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end,
case BT_SOL:
sol:
ptr += MINBPC(enc);
if (ptr == end)
return XML_TOK_PARTIAL;
REQUIRE_CHAR(enc, ptr, end);
if (!CHAR_MATCHES(enc, ptr, ASCII_GT)) {
*nextTokPtr = ptr;
return XML_TOK_INVALID;
@@ -688,13 +688,12 @@ PREFIX(scanLt)(const ENCODING *enc, const char *ptr, const char *end,
#ifdef XML_NS
int hadColon;
#endif
if (ptr == end)
return XML_TOK_PARTIAL;
REQUIRE_CHAR(enc, ptr, end);
switch (BYTE_TYPE(enc, ptr)) {
CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr)
case BT_EXCL:
if ((ptr += MINBPC(enc)) == end)
return XML_TOK_PARTIAL;
ptr += MINBPC(enc);
REQUIRE_CHAR(enc, ptr, end);
switch (BYTE_TYPE(enc, ptr)) {
case BT_MINUS:
return PREFIX(scanComment)(enc, ptr + MINBPC(enc), end, nextTokPtr);
@@ -716,7 +715,7 @@ PREFIX(scanLt)(const ENCODING *enc, const char *ptr, const char *end,
hadColon = 0;
#endif
/* we have a start-tag */
while (ptr != end) {
while (HAS_CHAR(enc, ptr, end)) {
switch (BYTE_TYPE(enc, ptr)) {
CHECK_NAME_CASES(enc, ptr, end, nextTokPtr)
#ifdef XML_NS
@@ -727,8 +726,7 @@ PREFIX(scanLt)(const ENCODING *enc, const char *ptr, const char *end,
}
hadColon = 1;
ptr += MINBPC(enc);
if (ptr == end)
return XML_TOK_PARTIAL;
REQUIRE_CHAR(enc, ptr, end);
switch (BYTE_TYPE(enc, ptr)) {
CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr)
default:
@@ -740,7 +738,7 @@ PREFIX(scanLt)(const ENCODING *enc, const char *ptr, const char *end,
case BT_S: case BT_CR: case BT_LF:
{
ptr += MINBPC(enc);
while (ptr != end) {
while (HAS_CHAR(enc, ptr, end)) {
switch (BYTE_TYPE(enc, ptr)) {
CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr)
case BT_GT:
@@ -765,8 +763,7 @@ PREFIX(scanLt)(const ENCODING *enc, const char *ptr, const char *end,
case BT_SOL:
sol:
ptr += MINBPC(enc);
if (ptr == end)
return XML_TOK_PARTIAL;
REQUIRE_CHAR(enc, ptr, end);
if (!CHAR_MATCHES(enc, ptr, ASCII_GT)) {
*nextTokPtr = ptr;
return XML_TOK_INVALID;
@@ -785,7 +782,7 @@ static int PTRCALL
PREFIX(contentTok)(const ENCODING *enc, const char *ptr, const char *end,
const char **nextTokPtr)
{
if (ptr == end)
if (ptr >= end)
return XML_TOK_NONE;
if (MINBPC(enc) > 1) {
size_t n = end - ptr;
@@ -803,7 +800,7 @@ PREFIX(contentTok)(const ENCODING *enc, const char *ptr, const char *end,
return PREFIX(scanRef)(enc, ptr + MINBPC(enc), end, nextTokPtr);
case BT_CR:
ptr += MINBPC(enc);
if (ptr == end)
if (! HAS_CHAR(enc, ptr, end))
return XML_TOK_TRAILING_CR;
if (BYTE_TYPE(enc, ptr) == BT_LF)
ptr += MINBPC(enc);
@@ -814,12 +811,12 @@ PREFIX(contentTok)(const ENCODING *enc, const char *ptr, const char *end,
return XML_TOK_DATA_NEWLINE;
case BT_RSQB:
ptr += MINBPC(enc);
if (ptr == end)
if (! HAS_CHAR(enc, ptr, end))
return XML_TOK_TRAILING_RSQB;
if (!CHAR_MATCHES(enc, ptr, ASCII_RSQB))
break;
ptr += MINBPC(enc);
if (ptr == end)
if (! HAS_CHAR(enc, ptr, end))
return XML_TOK_TRAILING_RSQB;
if (!CHAR_MATCHES(enc, ptr, ASCII_GT)) {
ptr -= MINBPC(enc);
@@ -832,7 +829,7 @@ PREFIX(contentTok)(const ENCODING *enc, const char *ptr, const char *end,
ptr += MINBPC(enc);
break;
}
while (ptr != end) {
while (HAS_CHAR(enc, ptr, end)) {
switch (BYTE_TYPE(enc, ptr)) {
#define LEAD_CASE(n) \
case BT_LEAD ## n: \
@@ -845,12 +842,12 @@ PREFIX(contentTok)(const ENCODING *enc, const char *ptr, const char *end,
LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4)
#undef LEAD_CASE
case BT_RSQB:
if (ptr + MINBPC(enc) != end) {
if (HAS_CHARS(enc, ptr, end, 2)) {
if (!CHAR_MATCHES(enc, ptr + MINBPC(enc), ASCII_RSQB)) {
ptr += MINBPC(enc);
break;
}
if (ptr + 2*MINBPC(enc) != end) {
if (HAS_CHARS(enc, ptr, end, 3)) {
if (!CHAR_MATCHES(enc, ptr + 2*MINBPC(enc), ASCII_GT)) {
ptr += MINBPC(enc);
break;
@@ -884,8 +881,7 @@ static int PTRCALL
PREFIX(scanPercent)(const ENCODING *enc, const char *ptr, const char *end,
const char **nextTokPtr)
{
if (ptr == end)
return XML_TOK_PARTIAL;
REQUIRE_CHAR(enc, ptr, end);
switch (BYTE_TYPE(enc, ptr)) {
CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr)
case BT_S: case BT_LF: case BT_CR: case BT_PERCNT:
@@ -895,7 +891,7 @@ PREFIX(scanPercent)(const ENCODING *enc, const char *ptr, const char *end,
*nextTokPtr = ptr;
return XML_TOK_INVALID;
}
while (ptr != end) {
while (HAS_CHAR(enc, ptr, end)) {
switch (BYTE_TYPE(enc, ptr)) {
CHECK_NAME_CASES(enc, ptr, end, nextTokPtr)
case BT_SEMI:
@@ -913,15 +909,14 @@ static int PTRCALL
PREFIX(scanPoundName)(const ENCODING *enc, const char *ptr, const char *end,
const char **nextTokPtr)
{
if (ptr == end)
return XML_TOK_PARTIAL;
REQUIRE_CHAR(enc, ptr, end);
switch (BYTE_TYPE(enc, ptr)) {
CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr)
default:
*nextTokPtr = ptr;
return XML_TOK_INVALID;
}
while (ptr != end) {
while (HAS_CHAR(enc, ptr, end)) {
switch (BYTE_TYPE(enc, ptr)) {
CHECK_NAME_CASES(enc, ptr, end, nextTokPtr)
case BT_CR: case BT_LF: case BT_S:
@@ -941,7 +936,7 @@ PREFIX(scanLit)(int open, const ENCODING *enc,
const char *ptr, const char *end,
const char **nextTokPtr)
{
while (ptr != end) {
while (HAS_CHAR(enc, ptr, end)) {
int t = BYTE_TYPE(enc, ptr);
switch (t) {
INVALID_CASES(ptr, nextTokPtr)
@@ -950,7 +945,7 @@ PREFIX(scanLit)(int open, const ENCODING *enc,
ptr += MINBPC(enc);
if (t != open)
break;
if (ptr == end)
if (! HAS_CHAR(enc, ptr, end))
return -XML_TOK_LITERAL;
*nextTokPtr = ptr;
switch (BYTE_TYPE(enc, ptr)) {
@@ -973,7 +968,7 @@ PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end,
const char **nextTokPtr)
{
int tok;
if (ptr == end)
if (ptr >= end)
return XML_TOK_NONE;
if (MINBPC(enc) > 1) {
size_t n = end - ptr;
@@ -992,8 +987,7 @@ PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end,
case BT_LT:
{
ptr += MINBPC(enc);
if (ptr == end)
return XML_TOK_PARTIAL;
REQUIRE_CHAR(enc, ptr, end);
switch (BYTE_TYPE(enc, ptr)) {
case BT_EXCL:
return PREFIX(scanDecl)(enc, ptr + MINBPC(enc), end, nextTokPtr);
@@ -1021,7 +1015,7 @@ PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end,
case BT_S: case BT_LF:
for (;;) {
ptr += MINBPC(enc);
if (ptr == end)
if (! HAS_CHAR(enc, ptr, end))
break;
switch (BYTE_TYPE(enc, ptr)) {
case BT_S: case BT_LF:
@@ -1048,11 +1042,10 @@ PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end,
return XML_TOK_OPEN_BRACKET;
case BT_RSQB:
ptr += MINBPC(enc);
if (ptr == end)
if (! HAS_CHAR(enc, ptr, end))
return -XML_TOK_CLOSE_BRACKET;
if (CHAR_MATCHES(enc, ptr, ASCII_RSQB)) {
if (ptr + MINBPC(enc) == end)
return XML_TOK_PARTIAL;
REQUIRE_CHARS(enc, ptr, end, 2);
if (CHAR_MATCHES(enc, ptr + MINBPC(enc), ASCII_GT)) {
*nextTokPtr = ptr + 2*MINBPC(enc);
return XML_TOK_COND_SECT_CLOSE;
@@ -1065,7 +1058,7 @@ PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end,
return XML_TOK_OPEN_PAREN;
case BT_RPAR:
ptr += MINBPC(enc);
if (ptr == end)
if (! HAS_CHAR(enc, ptr, end))
return -XML_TOK_CLOSE_PAREN;
switch (BYTE_TYPE(enc, ptr)) {
case BT_AST:
@@ -1141,7 +1134,7 @@ PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end,
*nextTokPtr = ptr;
return XML_TOK_INVALID;
}
while (ptr != end) {
while (HAS_CHAR(enc, ptr, end)) {
switch (BYTE_TYPE(enc, ptr)) {
CHECK_NAME_CASES(enc, ptr, end, nextTokPtr)
case BT_GT: case BT_RPAR: case BT_COMMA:
@@ -1154,8 +1147,7 @@ PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end,
ptr += MINBPC(enc);
switch (tok) {
case XML_TOK_NAME:
if (ptr == end)
return XML_TOK_PARTIAL;
REQUIRE_CHAR(enc, ptr, end);
tok = XML_TOK_PREFIXED_NAME;
switch (BYTE_TYPE(enc, ptr)) {
CHECK_NAME_CASES(enc, ptr, end, nextTokPtr)
@@ -1204,10 +1196,12 @@ PREFIX(attributeValueTok)(const ENCODING *enc, const char *ptr,
const char *end, const char **nextTokPtr)
{
const char *start;
if (ptr == end)
if (ptr >= end)
return XML_TOK_NONE;
else if (! HAS_CHAR(enc, ptr, end))
return XML_TOK_PARTIAL;
start = ptr;
while (ptr != end) {
while (HAS_CHAR(enc, ptr, end)) {
switch (BYTE_TYPE(enc, ptr)) {
#define LEAD_CASE(n) \
case BT_LEAD ## n: ptr += n; break;
@@ -1232,7 +1226,7 @@ PREFIX(attributeValueTok)(const ENCODING *enc, const char *ptr,
case BT_CR:
if (ptr == start) {
ptr += MINBPC(enc);
if (ptr == end)
if (! HAS_CHAR(enc, ptr, end))
return XML_TOK_TRAILING_CR;
if (BYTE_TYPE(enc, ptr) == BT_LF)
ptr += MINBPC(enc);
@@ -1262,10 +1256,12 @@ PREFIX(entityValueTok)(const ENCODING *enc, const char *ptr,
const char *end, const char **nextTokPtr)
{
const char *start;
if (ptr == end)
if (ptr >= end)
return XML_TOK_NONE;
else if (! HAS_CHAR(enc, ptr, end))
return XML_TOK_PARTIAL;
start = ptr;
while (ptr != end) {
while (HAS_CHAR(enc, ptr, end)) {
switch (BYTE_TYPE(enc, ptr)) {
#define LEAD_CASE(n) \
case BT_LEAD ## n: ptr += n; break;
@@ -1294,7 +1290,7 @@ PREFIX(entityValueTok)(const ENCODING *enc, const char *ptr,
case BT_CR:
if (ptr == start) {
ptr += MINBPC(enc);
if (ptr == end)
if (! HAS_CHAR(enc, ptr, end))
return XML_TOK_TRAILING_CR;
if (BYTE_TYPE(enc, ptr) == BT_LF)
ptr += MINBPC(enc);
@@ -1326,15 +1322,15 @@ PREFIX(ignoreSectionTok)(const ENCODING *enc, const char *ptr,
end = ptr + n;
}
}
while (ptr != end) {
while (HAS_CHAR(enc, ptr, end)) {
switch (BYTE_TYPE(enc, ptr)) {
INVALID_CASES(ptr, nextTokPtr)
case BT_LT:
if ((ptr += MINBPC(enc)) == end)
return XML_TOK_PARTIAL;
ptr += MINBPC(enc);
REQUIRE_CHAR(enc, ptr, end);
if (CHAR_MATCHES(enc, ptr, ASCII_EXCL)) {
if ((ptr += MINBPC(enc)) == end)
return XML_TOK_PARTIAL;
ptr += MINBPC(enc);
REQUIRE_CHAR(enc, ptr, end);
if (CHAR_MATCHES(enc, ptr, ASCII_LSQB)) {
++level;
ptr += MINBPC(enc);
@@ -1342,11 +1338,11 @@ PREFIX(ignoreSectionTok)(const ENCODING *enc, const char *ptr,
}
break;
case BT_RSQB:
if ((ptr += MINBPC(enc)) == end)
return XML_TOK_PARTIAL;
ptr += MINBPC(enc);
REQUIRE_CHAR(enc, ptr, end);
if (CHAR_MATCHES(enc, ptr, ASCII_RSQB)) {
if ((ptr += MINBPC(enc)) == end)
return XML_TOK_PARTIAL;
ptr += MINBPC(enc);
REQUIRE_CHAR(enc, ptr, end);
if (CHAR_MATCHES(enc, ptr, ASCII_GT)) {
ptr += MINBPC(enc);
if (level == 0) {
@@ -1373,7 +1369,7 @@ PREFIX(isPublicId)(const ENCODING *enc, const char *ptr, const char *end,
{
ptr += MINBPC(enc);
end -= MINBPC(enc);
for (; ptr != end; ptr += MINBPC(enc)) {
for (; HAS_CHAR(enc, ptr, end); ptr += MINBPC(enc)) {
switch (BYTE_TYPE(enc, ptr)) {
case BT_DIGIT:
case BT_HEX:
@@ -1521,7 +1517,7 @@ PREFIX(getAtts)(const ENCODING *enc, const char *ptr,
}
static int PTRFASTCALL
PREFIX(charRefNumber)(const ENCODING *enc, const char *ptr)
PREFIX(charRefNumber)(const ENCODING *UNUSED_P(enc), const char *ptr)
{
int result = 0;
/* skip &# */
@@ -1565,7 +1561,7 @@ PREFIX(charRefNumber)(const ENCODING *enc, const char *ptr)
}
static int PTRCALL
PREFIX(predefinedEntityName)(const ENCODING *enc, const char *ptr,
PREFIX(predefinedEntityName)(const ENCODING *UNUSED_P(enc), const char *ptr,
const char *end)
{
switch ((end - ptr)/MINBPC(enc)) {
@@ -1683,11 +1679,11 @@ PREFIX(sameName)(const ENCODING *enc, const char *ptr1, const char *ptr2)
}
static int PTRCALL
PREFIX(nameMatchesAscii)(const ENCODING *enc, const char *ptr1,
PREFIX(nameMatchesAscii)(const ENCODING *UNUSED_P(enc), const char *ptr1,
const char *end1, const char *ptr2)
{
for (; *ptr2; ptr1 += MINBPC(enc), ptr2++) {
if (ptr1 == end1)
if (end1 - ptr1 < MINBPC(enc))
return 0;
if (!CHAR_MATCHES(enc, ptr1, *ptr2))
return 0;
@@ -1744,7 +1740,7 @@ PREFIX(updatePosition)(const ENCODING *enc,
const char *end,
POSITION *pos)
{
while (ptr < end) {
while (HAS_CHAR(enc, ptr, end)) {
switch (BYTE_TYPE(enc, ptr)) {
#define LEAD_CASE(n) \
case BT_LEAD ## n: \
@@ -1760,7 +1756,7 @@ PREFIX(updatePosition)(const ENCODING *enc,
case BT_CR:
pos->lineNumber++;
ptr += MINBPC(enc);
if (ptr != end && BYTE_TYPE(enc, ptr) == BT_LF)
if (HAS_CHAR(enc, ptr, end) && BYTE_TYPE(enc, ptr) == BT_LF)
ptr += MINBPC(enc);
pos->columnNumber = (XML_Size)-1;
break;

1
contrib/hbexpat/hbexpat.ch
View File

@@ -94,6 +94,7 @@
#define HB_XML_ERROR_RESERVED_PREFIX_XML 38
#define HB_XML_ERROR_RESERVED_PREFIX_XMLNS 39
#define HB_XML_ERROR_RESERVED_NAMESPACE_URI 40
#define HB_XML_ERROR_INVALID_ARGUMENT 41
#define HB_XML_INITIALIZED 0
#define HB_XML_PARSING 1