aboutsummaryrefslogtreecommitdiff
path: root/libstudxml
diff options
context:
space:
mode:
Diffstat (limited to 'libstudxml')
-rw-r--r--libstudxml/buildfile74
-rw-r--r--libstudxml/details/config-vc.h2
-rw-r--r--libstudxml/details/config.h2
-rw-r--r--libstudxml/details/config.hxx27
-rw-r--r--libstudxml/details/expat/config.h24
-rw-r--r--libstudxml/details/expat/expat.h31
-rw-r--r--libstudxml/details/expat/xmlparse.c3176
-rw-r--r--libstudxml/details/expat/xmltok.c117
-rw-r--r--libstudxml/details/expat/xmltok.h10
-rw-r--r--libstudxml/details/expat/xmltok_impl.c77
-rw-r--r--libstudxml/details/genx/LICENSE35
-rw-r--r--libstudxml/details/genx/genx.c70
-rw-r--r--libstudxml/details/genx/genx.h75
-rw-r--r--libstudxml/parser.hxx7
-rw-r--r--libstudxml/serializer.hxx6
15 files changed, 2196 insertions, 1537 deletions
diff --git a/libstudxml/buildfile b/libstudxml/buildfile
index 6d3869d..e004fca 100644
--- a/libstudxml/buildfile
+++ b/libstudxml/buildfile
@@ -1,29 +1,37 @@
# file : libstudxml/buildfile
# license : MIT; see accompanying LICENSE file
+int_expat = (!$config.libstudxml.external_expat)
+
+intf_libs = # Interface dependencies.
+
+if! $int_expat
+ import intf_libs += libexpat%lib{expat}
+
lib{studxml}: {hxx ixx txx cxx}{** -version} {hxx}{version} \
details/{h}{config*}
-# Expat. Note that we treat a whole bunch of its sources as files since they
-# are private and #include's (including .c file).
+# Expat.
#
-lib{studxml}: details/expat/{ \
- h{expat expat_external} \
- c{xmlparse xmlrole xmltok} \
-file{ascii.h asciitab.h config.h iasciitab.h internal.h latin1tab.h nametab.h \
- utf8tab.h xmlrole.h xmltok.h xmltok_impl.h xmltok_impl.c xmltok_ns.c} \
- doc{COPYING README} \
+# Note that we treat some of its source files as ad hoc since they are
+# #include'd.
+#
+details/expat/
+{
+ ../../lib{studxml}: h{*}: include = $int_expat
+ ../../lib{studxml}: c{xmlparse xmlrole xmltok}: include = $int_expat
+ ../../lib{studxml}: c{xmltok_impl xmltok_ns}: include = ($int_expat ? adhoc : false)
+ ../../lib{studxml}: doc{COPYING README}
}
-details/expat/doc{README}@./: install = false
-details/expat/doc{COPYING}@./: install = doc/EXPAT-LICENSE
-
# Genx.
#
-lib{studxml}: details/genx/{h{*} c{*} doc{LICENSE README}}
+details/genx/
+{
+ ../../lib{studxml}: h{*} c{*} doc{LICENSE README}
+}
-details/genx/doc{README}@./: install = false
-details/genx/doc{LICENSE}@./: install = doc/GENX-LICENSE
+lib{studxml}: $intf_libs
# Include the generated version header into the distribution (so that we don't
# pick up an installed one) and don't remove it when cleaning in src (so that
@@ -52,15 +60,25 @@ if ($c.class == 'gcc')
#
cc.poptions =+ "-I$out_root" "-I$src_root"
+if! $int_expat
+ cc.poptions += -DLIBSTUDXML_EXTERNAL_EXPAT
+
obja{*}: cc.poptions += -DLIBSTUDXML_STATIC_BUILD
objs{*}: cc.poptions += -DLIBSTUDXML_SHARED_BUILD
# Export options.
#
-lib{studxml}: cc.export.poptions = "-I$out_root" "-I$src_root"
+lib{studxml}:
+{
+ cxx.export.poptions = "-I$out_root" "-I$src_root"
+ cxx.export.libs = $intf_libs
+}
-liba{studxml}: cc.export.poptions += -DLIBSTUDXML_STATIC
-libs{studxml}: cc.export.poptions += -DLIBSTUDXML_SHARED
+if! $int_expat
+ lib{studxml}: cxx.export.poptions += -DLIBSTUDXML_EXTERNAL_EXPAT
+
+liba{studxml}: cxx.export.poptions += -DLIBSTUDXML_STATIC
+libs{studxml}: cxx.export.poptions += -DLIBSTUDXML_SHARED
# For pre-releases use the complete version to make sure they cannot be used
# in place of another pre-release or the final version. See the version module
@@ -79,3 +97,25 @@ else
install = include/libstudxml/
install.subdirs = true
}
+
+# Most of the Expat headers are private.
+#
+details/expat/
+{
+ h{*}: install = false
+
+ h{expat}@./ h{expat_external.h}@./:
+ {
+ install = ($int_expat ? include/libstudxml/details/expat/ : false)
+ install.subdirs = false
+ }
+
+ doc{README}@./: install = false
+ doc{COPYING}@./: install = ($int_expat ? doc/EXPAT-LICENSE : false)
+}
+
+details/genx/
+{
+ doc{README}@./: install = false
+ doc{LICENSE}@./: install = doc/GENX-LICENSE
+}
diff --git a/libstudxml/details/config-vc.h b/libstudxml/details/config-vc.h
index 5d8f79e..0ff1240 100644
--- a/libstudxml/details/config-vc.h
+++ b/libstudxml/details/config-vc.h
@@ -7,7 +7,7 @@
#ifndef LIBSTUDXML_DETAILS_CONFIG_VC_H
#define LIBSTUDXML_DETAILS_CONFIG_VC_H
-// Always little-endian, at least on i686 and x86_64.
+// Always little-endian, at least on i686, x86_64, and ARM.
//
#define LIBSTUDXML_BYTEORDER 1234
diff --git a/libstudxml/details/config.h b/libstudxml/details/config.h
index 3030a76..7d7c292 100644
--- a/libstudxml/details/config.h
+++ b/libstudxml/details/config.h
@@ -7,6 +7,8 @@
#ifndef LIBSTUDXML_DETAILS_CONFIG_H
#define LIBSTUDXML_DETAILS_CONFIG_H
+/* Endianess.
+ */
#ifdef __FreeBSD__
# include <sys/endian.h> /* BYTE_ORDER */
#else
diff --git a/libstudxml/details/config.hxx b/libstudxml/details/config.hxx
index 6a466d6..8e8cf95 100644
--- a/libstudxml/details/config.hxx
+++ b/libstudxml/details/config.hxx
@@ -4,32 +4,15 @@
#ifndef LIBSTUDXML_DETAILS_CONFIG_HXX
#define LIBSTUDXML_DETAILS_CONFIG_HXX
-// C++11 support.
+// Note that MSVC 14.3 (1900) does not define suitable __cplusplus but
+// supports C++11.
//
-#ifdef _MSC_VER
-# if _MSC_VER >= 1900
-# define STUDXML_CXX11_NOEXCEPT
-# endif
-#else
-# if defined(__GXX_EXPERIMENTAL_CXX0X__) || __cplusplus >= 201103L
-# ifdef __clang__ // Pretends to be a really old __GNUC__ on some platforms.
-# define STUDXML_CXX11_NOEXCEPT
-# elif defined(__GNUC__)
-# if (__GNUC__ == 4 && __GNUC_MINOR__ >= 6) || __GNUC__ > 4
-# define STUDXML_CXX11_NOEXCEPT
-# endif
-# else
-# define STUDXML_CXX11_NOEXCEPT
-# endif
+#if !defined(__cplusplus) || __cplusplus < 201103L
+# if !defined(_MSC_VER) || _MSC_VER < 1900
+# error C++11 is required
# endif
#endif
-#ifdef STUDXML_CXX11_NOEXCEPT
-# define STUDXML_NOTHROW_NOEXCEPT noexcept
-#else
-# define STUDXML_NOTHROW_NOEXCEPT throw()
-#endif
-
#ifdef _MSC_VER
# include <libstudxml/details/config-vc.h>
#else
diff --git a/libstudxml/details/expat/config.h b/libstudxml/details/expat/config.h
index 99fa673..ea0245a 100644
--- a/libstudxml/details/expat/config.h
+++ b/libstudxml/details/expat/config.h
@@ -9,27 +9,25 @@
#define BYTEORDER LIBSTUDXML_BYTEORDER
-#define XML_NS 1
-#define XML_DTD 1
+#define XML_NS 1
+#define XML_DTD 1
#define XML_CONTEXT_BYTES 1024
+/* #define XML_FREESTANDING 1 */
#define UNUSED(x) (void)x;
-#ifdef _WIN32
-/* Windows
- *
+/* Specific for Windows.
*/
-#define WIN32_LEAN_AND_MEAN
-#include <windows.h>
-#undef WIN32_LEAN_AND_MEAN
+#ifdef _WIN32
+# define WIN32_LEAN_AND_MEAN
+# include <windows.h>
+# undef WIN32_LEAN_AND_MEAN
-#define HAVE_MEMMOVE 1
+# define COMPILED_FROM_DSP 1
+#endif
-#else
-/* POSIX
- *
+/* Common for all supported OSes/compilers.
*/
#define HAVE_MEMMOVE 1
-#endif
#endif /* EXPAT_CONFIG_H */
diff --git a/libstudxml/details/expat/expat.h b/libstudxml/details/expat/expat.h
index 9671b73..24a2669 100644
--- a/libstudxml/details/expat/expat.h
+++ b/libstudxml/details/expat/expat.h
@@ -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 {
@@ -215,6 +217,17 @@ XML_ParserCreate(const XML_Char *encoding);
and the local part will be concatenated without any separator.
It is a programming error to use the separator '\0' with namespace
triplets (see XML_SetReturnNSTriplet).
+ If a namespace separator is chosen that can be part of a URI or
+ part of an XML name, splitting an expanded name back into its
+ 1, 2 or 3 original parts on application level in the element handler
+ may end up vulnerable, so these are advised against; sane choices for
+ a namespace separator are e.g. '\n' (line feed) and '|' (pipe).
+
+ Note that Expat does not validate namespace URIs (beyond encoding)
+ against RFC 3986 today (and is not required to do so with regard to
+ the XML 1.0 namespaces specification) but it may start doing that
+ in future releases. Before that, an application using Expat must
+ be ready to receive namespace URIs containing non-URI characters.
*/
XMLPARSEAPI(XML_Parser)
XML_ParserCreateNS(const XML_Char *encoding, XML_Char namespaceSeparator);
@@ -788,20 +801,20 @@ XML_ParseBuffer(XML_Parser parser, int len, int isFinal);
(resumable = 0) an already suspended parser. Some call-backs may
still follow because they would otherwise get lost. Examples:
- endElementHandler() for empty elements when stopped in
- startElementHandler(),
- - endNameSpaceDeclHandler() when stopped in endElementHandler(),
+ startElementHandler(),
+ - endNameSpaceDeclHandler() when stopped in endElementHandler(),
and possibly others.
Can be called from most handlers, including DTD related call-backs,
except when parsing an external parameter entity and resumable != 0.
Returns XML_STATUS_OK when successful, XML_STATUS_ERROR otherwise.
- Possible error codes:
+ Possible error codes:
- XML_ERROR_SUSPENDED: when suspending an already suspended parser.
- XML_ERROR_FINISHED: when the parser has already finished.
- XML_ERROR_SUSPEND_PE: when suspending while parsing an external PE.
- When resumable != 0 (true) then parsing is suspended, that is,
- XML_Parse() and XML_ParseBuffer() return XML_STATUS_SUSPENDED.
+ When resumable != 0 (true) then parsing is suspended, that is,
+ XML_Parse() and XML_ParseBuffer() return XML_STATUS_SUSPENDED.
Otherwise, parsing is aborted, that is, XML_Parse() and XML_ParseBuffer()
return XML_STATUS_ERROR with error code XML_ERROR_ABORTED.
@@ -812,7 +825,7 @@ XML_ParseBuffer(XML_Parser parser, int len, int isFinal);
the externalEntityRefHandler() to call XML_StopParser() on the parent
parser (recursively), if one wants to stop parsing altogether.
- When suspended, parsing can be resumed by calling XML_ResumeParser().
+ When suspended, parsing can be resumed by calling XML_ResumeParser().
*/
XMLPARSEAPI(enum XML_Status)
XML_StopParser(XML_Parser parser, XML_Bool resumable);
@@ -820,7 +833,7 @@ XML_StopParser(XML_Parser parser, XML_Bool resumable);
/* Resumes parsing after it has been suspended with XML_StopParser().
Must not be called from within a handler call-back. Returns same
status codes as XML_Parse() or XML_ParseBuffer().
- Additional error code XML_ERROR_NOT_SUSPENDED possible.
+ Additional error code XML_ERROR_NOT_SUSPENDED possible.
*Note*:
This must be called on the most deeply nested child parser instance
@@ -930,7 +943,7 @@ XML_GetErrorCode(XML_Parser parser);
be within the relevant markup. When called outside of the callback
functions, the position indicated will be just past the last parse
event (regardless of whether there was an associated callback).
-
+
They may also be called after returning from a call to XML_Parse
or XML_ParseBuffer. If the return value is XML_STATUS_ERROR then
the location is the location of the character at which the error
diff --git a/libstudxml/details/expat/xmlparse.c b/libstudxml/details/expat/xmlparse.c
index 5bc6373..ba2e6fc 100644
--- a/libstudxml/details/expat/xmlparse.c
+++ b/libstudxml/details/expat/xmlparse.c
@@ -6,12 +6,20 @@
#include <string.h> /* memset(), memcpy() */
#include <assert.h>
#include <limits.h> /* UINT_MAX */
-#include <time.h> /* time() */
+#include <stdint.h> /* SIZE_MAX */
#define XML_BUILDING_EXPAT 1
#include <libstudxml/details/expat/config.h>
+#ifdef COMPILED_FROM_DSP
+#define getpid GetCurrentProcessId
+#else
+#include <sys/time.h> /* gettimeofday() */
+#include <sys/types.h> /* getpid() */
+#include <unistd.h> /* getpid() */
+#endif
+
#include <libstudxml/details/expat/ascii.h>
#include <libstudxml/details/expat/expat.h>
@@ -236,7 +244,7 @@ typedef struct {
typedef struct {
unsigned long version;
- unsigned long hash;
+ size_t hash;
const XML_Char *uriName;
} NS_ATT;
@@ -321,7 +329,7 @@ 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,
- XML_Bool haveMore);
+ XML_Bool haveMore, XML_Bool allowClosingDoctype);
static enum XML_Error
processInternalEntity(XML_Parser parser, ENTITY *entity,
XML_Bool betweenDecl);
@@ -378,7 +386,7 @@ setContext(XML_Parser parser, const XML_Char *context);
static void FASTCALL normalizePublicId(XML_Char *s);
static DTD * dtdCreate(const XML_Memory_Handling_Suite *ms);
-/* do not call if parentParser != NULL */
+/* do not call if m_parentParser != NULL */
static void dtdReset(DTD *p, const XML_Memory_Handling_Suite *ms);
static void
dtdDestroy(DTD *p, XML_Bool isDocEntity, const XML_Memory_Handling_Suite *ms);
@@ -422,7 +430,10 @@ static ELEMENT_TYPE *
getElementType(XML_Parser parser, const ENCODING *enc,
const char *ptr, const char *end);
-static unsigned long generate_hash_secret_salt(void);
+static XML_Char *copyString(const XML_Char *s,
+ const XML_Memory_Handling_Suite *memsuite);
+
+static size_t generate_hash_secret_salt(XML_Parser parser);
static XML_Bool startParsing(XML_Parser parser);
static XML_Parser
@@ -447,7 +458,7 @@ parserInit(XML_Parser parser, const XML_Char *encodingName);
: ((*((pool)->ptr)++ = c), 1))
struct XML_ParserStruct {
- /* The first member must be userData so that the XML_GetUserData
+ /* The first member must be m_userData so that the XML_GetUserData
macro works. */
void *m_userData;
void *m_handlerArg;
@@ -457,7 +468,7 @@ struct XML_ParserStruct {
const char *m_bufferPtr;
/* past last character to be parsed */
char *m_bufferEnd;
- /* allocated end of buffer */
+ /* allocated end of m_buffer */
const char *m_bufferLim;
XML_Index m_parseEndByteIndex;
const char *m_parseEndPtr;
@@ -546,116 +557,12 @@ struct XML_ParserStruct {
XML_Bool m_useForeignDTD;
enum XML_ParamEntityParsing m_paramEntityParsing;
#endif
- unsigned long m_hash_secret_salt;
+ size_t m_hash_secret_salt;
};
-#define MALLOC(s) (parser->m_mem.malloc_fcn((s)))
-#define REALLOC(p,s) (parser->m_mem.realloc_fcn((p),(s)))
-#define FREE(p) (parser->m_mem.free_fcn((p)))
-
-#define userData (parser->m_userData)
-#define handlerArg (parser->m_handlerArg)
-#define startElementHandler (parser->m_startElementHandler)
-#define endElementHandler (parser->m_endElementHandler)
-#define characterDataHandler (parser->m_characterDataHandler)
-#define processingInstructionHandler \
- (parser->m_processingInstructionHandler)
-#define commentHandler (parser->m_commentHandler)
-#define startCdataSectionHandler \
- (parser->m_startCdataSectionHandler)
-#define endCdataSectionHandler (parser->m_endCdataSectionHandler)
-#define defaultHandler (parser->m_defaultHandler)
-#define startDoctypeDeclHandler (parser->m_startDoctypeDeclHandler)
-#define endDoctypeDeclHandler (parser->m_endDoctypeDeclHandler)
-#define unparsedEntityDeclHandler \
- (parser->m_unparsedEntityDeclHandler)
-#define notationDeclHandler (parser->m_notationDeclHandler)
-#define startNamespaceDeclHandler \
- (parser->m_startNamespaceDeclHandler)
-#define endNamespaceDeclHandler (parser->m_endNamespaceDeclHandler)
-#define notStandaloneHandler (parser->m_notStandaloneHandler)
-#define externalEntityRefHandler \
- (parser->m_externalEntityRefHandler)
-#define externalEntityRefHandlerArg \
- (parser->m_externalEntityRefHandlerArg)
-#define internalEntityRefHandler \
- (parser->m_internalEntityRefHandler)
-#define skippedEntityHandler (parser->m_skippedEntityHandler)
-#define unknownEncodingHandler (parser->m_unknownEncodingHandler)
-#define elementDeclHandler (parser->m_elementDeclHandler)
-#define attlistDeclHandler (parser->m_attlistDeclHandler)
-#define entityDeclHandler (parser->m_entityDeclHandler)
-#define xmlDeclHandler (parser->m_xmlDeclHandler)
-#define encoding (parser->m_encoding)
-#define initEncoding (parser->m_initEncoding)
-#define internalEncoding (parser->m_internalEncoding)
-#define unknownEncodingMem (parser->m_unknownEncodingMem)
-#define unknownEncodingData (parser->m_unknownEncodingData)
-#define unknownEncodingHandlerData \
- (parser->m_unknownEncodingHandlerData)
-#define unknownEncodingRelease (parser->m_unknownEncodingRelease)
-#define protocolEncodingName (parser->m_protocolEncodingName)
-#define ns (parser->m_ns)
-#define ns_triplets (parser->m_ns_triplets)
-#define prologState (parser->m_prologState)
-#define processor (parser->m_processor)
-#define errorCode (parser->m_errorCode)
-#define eventPtr (parser->m_eventPtr)
-#define eventEndPtr (parser->m_eventEndPtr)
-#define positionPtr (parser->m_positionPtr)
-#define position (parser->m_position)
-#define openInternalEntities (parser->m_openInternalEntities)
-#define freeInternalEntities (parser->m_freeInternalEntities)
-#define defaultExpandInternalEntities \
- (parser->m_defaultExpandInternalEntities)
-#define tagLevel (parser->m_tagLevel)
-#define buffer (parser->m_buffer)
-#define bufferPtr (parser->m_bufferPtr)
-#define bufferEnd (parser->m_bufferEnd)
-#define parseEndByteIndex (parser->m_parseEndByteIndex)
-#define parseEndPtr (parser->m_parseEndPtr)
-#define bufferLim (parser->m_bufferLim)
-#define dataBuf (parser->m_dataBuf)
-#define dataBufEnd (parser->m_dataBufEnd)
-#define _dtd (parser->m_dtd)
-#define curBase (parser->m_curBase)
-#define declEntity (parser->m_declEntity)
-#define doctypeName (parser->m_doctypeName)
-#define doctypeSysid (parser->m_doctypeSysid)
-#define doctypePubid (parser->m_doctypePubid)
-#define declAttributeType (parser->m_declAttributeType)
-#define declNotationName (parser->m_declNotationName)
-#define declNotationPublicId (parser->m_declNotationPublicId)
-#define declElementType (parser->m_declElementType)
-#define declAttributeId (parser->m_declAttributeId)
-#define declAttributeIsCdata (parser->m_declAttributeIsCdata)
-#define declAttributeIsId (parser->m_declAttributeIsId)
-#define freeTagList (parser->m_freeTagList)
-#define freeBindingList (parser->m_freeBindingList)
-#define inheritedBindings (parser->m_inheritedBindings)
-#define tagStack (parser->m_tagStack)
-#define atts (parser->m_atts)
-#define attsSize (parser->m_attsSize)
-#define nSpecifiedAtts (parser->m_nSpecifiedAtts)
-#define idAttIndex (parser->m_idAttIndex)
-#define nsAtts (parser->m_nsAtts)
-#define nsAttsVersion (parser->m_nsAttsVersion)
-#define nsAttsPower (parser->m_nsAttsPower)
-#define attInfo (parser->m_attInfo)
-#define tempPool (parser->m_tempPool)
-#define temp2Pool (parser->m_temp2Pool)
-#define groupConnector (parser->m_groupConnector)
-#define groupSize (parser->m_groupSize)
-#define namespaceSeparator (parser->m_namespaceSeparator)
-#define parentParser (parser->m_parentParser)
-#define ps_parsing (parser->m_parsingStatus.parsing)
-#define ps_finalBuffer (parser->m_parsingStatus.finalBuffer)
-#ifdef XML_DTD
-#define isParamEntity (parser->m_isParamEntity)
-#define useForeignDTD (parser->m_useForeignDTD)
-#define paramEntityParsing (parser->m_paramEntityParsing)
-#endif /* XML_DTD */
-#define hash_secret_salt (parser->m_hash_secret_salt)
+#define MALLOC(parser, s) (parser->m_mem.malloc_fcn((s)))
+#define REALLOC(parser, p, s) (parser->m_mem.realloc_fcn((p),(s)))
+#define FREE(parser, p) (parser->m_mem.free_fcn((p)))
XML_Parser XMLCALL
XML_ParserCreate(const XML_Char *encodingName)
@@ -680,21 +587,54 @@ static const XML_Char implicitContext[] = {
ASCII_s, ASCII_p, ASCII_a, ASCII_c, ASCII_e, '\0'
};
-static unsigned long
-generate_hash_secret_salt(void)
+#ifndef XML_FREESTANDING
+static size_t
+gather_time_entropy(void)
+{
+#ifdef COMPILED_FROM_DSP
+ FILETIME ft;
+ GetSystemTimeAsFileTime(&ft); /* never fails */
+ return ft.dwHighDateTime ^ ft.dwLowDateTime;
+#else
+ struct timeval tv;
+ int gettimeofday_res;
+
+ gettimeofday_res = gettimeofday(&tv, NULL);
+ assert (gettimeofday_res == 0);
+
+ /* Microseconds time is <20 bits entropy */
+ return tv.tv_usec;
+#endif
+}
+#endif
+
+static size_t
+generate_hash_secret_salt(XML_Parser parser)
{
- unsigned int seed = time(NULL) % UINT_MAX;
- srand(seed);
- return rand();
+#ifdef XML_FREESTANDING
+ const size_t entropy = (size_t)&parser ^ (size_t)parser;
+#else
+ /* Process ID is 0 bits entropy if attacker has local access
+ * XML_Parser address is few bits of entropy if attacker has local access */
+ const size_t entropy =
+ gather_time_entropy() ^ getpid() ^ (size_t)parser;
+#endif
+
+ /* Factors are 2^31-1 and 2^61-1 (Mersenne primes M31 and M61) */
+ if (sizeof(size_t) == 4) {
+ return entropy * (size_t)2147483647;
+ } else {
+ return entropy * (size_t)2305843009213693951;
+ }
}
static XML_Bool /* only valid for root parser */
startParsing(XML_Parser parser)
{
/* hash functions must be initialized before setContext() is called */
- if (hash_secret_salt == 0)
- hash_secret_salt = generate_hash_secret_salt();
- if (ns) {
+ if (parser->m_hash_secret_salt == 0)
+ parser->m_hash_secret_salt = generate_hash_secret_salt(parser);
+ if (parser->m_ns) {
/* implicit context only set for root parser, since child
parsers (i.e. external entity parsers) will inherit it
*/
@@ -744,83 +684,93 @@ parserCreate(const XML_Char *encodingName,
if (!parser)
return parser;
- buffer = NULL;
- bufferLim = NULL;
+ parser->m_buffer = NULL;
+ parser->m_bufferLim = NULL;
- attsSize = INIT_ATTS_SIZE;
- atts = (ATTRIBUTE *)MALLOC(attsSize * sizeof(ATTRIBUTE));
- if (atts == NULL) {
- FREE(parser);
+ parser->m_attsSize = INIT_ATTS_SIZE;
+ parser->m_atts = (ATTRIBUTE *)MALLOC(parser, parser->m_attsSize * sizeof(ATTRIBUTE));
+ if (parser->m_atts == NULL) {
+ FREE(parser, parser);
return NULL;
}
#ifdef XML_ATTR_INFO
- attInfo = (XML_AttrInfo*)MALLOC(attsSize * sizeof(XML_AttrInfo));
- if (attInfo == NULL) {
- FREE(atts);
- FREE(parser);
+ parser->m_attInfo = (XML_AttrInfo*)MALLOC(parser, parser->m_attsSize * sizeof(XML_AttrInfo));
+ if (parser->m_attInfo == NULL) {
+ FREE(parser, parser->m_atts);
+ FREE(parser, parser);
return NULL;
}
#endif
- dataBuf = (XML_Char *)MALLOC(INIT_DATA_BUF_SIZE * sizeof(XML_Char));
- if (dataBuf == NULL) {
- FREE(atts);
+ parser->m_dataBuf = (XML_Char *)MALLOC(parser, INIT_DATA_BUF_SIZE * sizeof(XML_Char));
+ if (parser->m_dataBuf == NULL) {
+ FREE(parser, parser->m_atts);
#ifdef XML_ATTR_INFO
- FREE(attInfo);
+ FREE(parser, parser->m_attInfo);
#endif
- FREE(parser);
+ FREE(parser, parser);
return NULL;
}
- dataBufEnd = dataBuf + INIT_DATA_BUF_SIZE;
+ parser->m_dataBufEnd = parser->m_dataBuf + INIT_DATA_BUF_SIZE;
if (dtd)
- _dtd = dtd;
+ parser->m_dtd = dtd;
else {
- _dtd = dtdCreate(&parser->m_mem);
- if (_dtd == NULL) {
- FREE(dataBuf);
- FREE(atts);
+ parser->m_dtd = dtdCreate(&parser->m_mem);
+ if (parser->m_dtd == NULL) {
+ FREE(parser, parser->m_dataBuf);
+ FREE(parser, parser->m_atts);
#ifdef XML_ATTR_INFO
- FREE(attInfo);
+ FREE(parser, parser->m_attInfo);
#endif
- FREE(parser);
+ FREE(parser, parser);
return NULL;
}
}
- freeBindingList = NULL;
- freeTagList = NULL;
- freeInternalEntities = NULL;
+ parser->m_freeBindingList = NULL;
+ parser->m_freeTagList = NULL;
+ parser->m_freeInternalEntities = NULL;
- groupSize = 0;
- groupConnector = NULL;
+ parser->m_groupSize = 0;
+ parser->m_groupConnector = NULL;
- unknownEncodingHandler = NULL;
- unknownEncodingHandlerData = NULL;
+ parser->m_unknownEncodingHandler = NULL;
+ parser->m_unknownEncodingHandlerData = NULL;
- namespaceSeparator = ASCII_EXCL;
- ns = XML_FALSE;
- ns_triplets = XML_FALSE;
+ parser->m_namespaceSeparator = ASCII_EXCL;
+ parser->m_ns = XML_FALSE;
+ parser->m_ns_triplets = XML_FALSE;
- nsAtts = NULL;
- nsAttsVersion = 0;
- nsAttsPower = 0;
+ parser->m_nsAtts = NULL;
+ parser->m_nsAttsVersion = 0;
+ parser->m_nsAttsPower = 0;
- poolInit(&tempPool, &(parser->m_mem));
- poolInit(&temp2Pool, &(parser->m_mem));
+ parser->m_protocolEncodingName = NULL;
+
+ poolInit(&parser->m_tempPool, &(parser->m_mem));
+ poolInit(&parser->m_temp2Pool, &(parser->m_mem));
parserInit(parser, encodingName);
- if (encodingName && !protocolEncodingName) {
+ if (encodingName && !parser->m_protocolEncodingName) {
+ if (dtd) {
+ // We need to stop the upcoming call to XML_ParserFree from happily
+ // destroying parser->m_dtd because the DTD is shared with the parent
+ // parser and the only guard that keeps XML_ParserFree from destroying
+ // parser->m_dtd is parser->m_isParamEntity but it will be set to
+ // XML_TRUE only later in XML_ExternalEntityParserCreate (or not at all).
+ parser->m_dtd = NULL;
+ }
XML_ParserFree(parser);
return NULL;
}
if (nameSep) {
- ns = XML_TRUE;
- internalEncoding = XmlGetInternalEncodingNS();
- namespaceSeparator = *nameSep;
+ parser->m_ns = XML_TRUE;
+ parser->m_internalEncoding = XmlGetInternalEncodingNS();
+ parser->m_namespaceSeparator = *nameSep;
}
else {
- internalEncoding = XmlGetInternalEncoding();
+ parser->m_internalEncoding = XmlGetInternalEncoding();
}
return parser;
@@ -829,85 +779,85 @@ parserCreate(const XML_Char *encodingName,
static void
parserInit(XML_Parser parser, const XML_Char *encodingName)
{
- processor = prologInitProcessor;
- XmlPrologStateInit(&prologState);
- protocolEncodingName = (encodingName != NULL
- ? poolCopyString(&tempPool, encodingName)
- : NULL);
- curBase = NULL;
- XmlInitEncoding(&initEncoding, &encoding, 0);
- userData = NULL;
- handlerArg = NULL;
- startElementHandler = NULL;
- endElementHandler = NULL;
- characterDataHandler = NULL;
- processingInstructionHandler = NULL;
- commentHandler = NULL;
- startCdataSectionHandler = NULL;
- endCdataSectionHandler = NULL;
- defaultHandler = NULL;
- startDoctypeDeclHandler = NULL;
- endDoctypeDeclHandler = NULL;
- unparsedEntityDeclHandler = NULL;
- notationDeclHandler = NULL;
- startNamespaceDeclHandler = NULL;
- endNamespaceDeclHandler = NULL;
- notStandaloneHandler = NULL;
- externalEntityRefHandler = NULL;
- externalEntityRefHandlerArg = parser;
- skippedEntityHandler = NULL;
- elementDeclHandler = NULL;
- attlistDeclHandler = NULL;
- entityDeclHandler = NULL;
- xmlDeclHandler = NULL;
- bufferPtr = buffer;
- bufferEnd = buffer;
- parseEndByteIndex = 0;
- parseEndPtr = NULL;
- declElementType = NULL;
- declAttributeId = NULL;
- declEntity = NULL;
- doctypeName = NULL;
- doctypeSysid = NULL;
- doctypePubid = NULL;
- declAttributeType = NULL;
- declNotationName = NULL;
- declNotationPublicId = NULL;
- declAttributeIsCdata = XML_FALSE;
- declAttributeIsId = XML_FALSE;
- memset(&position, 0, sizeof(POSITION));
- errorCode = XML_ERROR_NONE;
- eventPtr = NULL;
- eventEndPtr = NULL;
- positionPtr = NULL;
- openInternalEntities = NULL;
- defaultExpandInternalEntities = XML_TRUE;
- tagLevel = 0;
- tagStack = NULL;
- inheritedBindings = NULL;
- nSpecifiedAtts = 0;
- unknownEncodingMem = NULL;
- unknownEncodingRelease = NULL;
- unknownEncodingData = NULL;
- parentParser = NULL;
- ps_parsing = XML_INITIALIZED;
+ parser->m_processor = prologInitProcessor;
+ XmlPrologStateInit(&parser->m_prologState);
+ if (encodingName != NULL) {
+ parser->m_protocolEncodingName = copyString(encodingName, &(parser->m_mem));
+ }
+ parser->m_curBase = NULL;
+ XmlInitEncoding(&parser->m_initEncoding, &parser->m_encoding, 0);
+ parser->m_userData = NULL;
+ parser->m_handlerArg = NULL;
+ parser->m_startElementHandler = NULL;
+ parser->m_endElementHandler = NULL;
+ parser->m_characterDataHandler = NULL;
+ parser->m_processingInstructionHandler = NULL;
+ parser->m_commentHandler = NULL;
+ parser->m_startCdataSectionHandler = NULL;
+ parser->m_endCdataSectionHandler = NULL;
+ parser->m_defaultHandler = NULL;
+ parser->m_startDoctypeDeclHandler = NULL;
+ parser->m_endDoctypeDeclHandler = NULL;
+ parser->m_unparsedEntityDeclHandler = NULL;
+ parser->m_notationDeclHandler = NULL;
+ parser->m_startNamespaceDeclHandler = NULL;
+ parser->m_endNamespaceDeclHandler = NULL;
+ parser->m_notStandaloneHandler = NULL;
+ parser->m_externalEntityRefHandler = NULL;
+ parser->m_externalEntityRefHandlerArg = parser;
+ parser->m_skippedEntityHandler = NULL;
+ parser->m_elementDeclHandler = NULL;
+ parser->m_attlistDeclHandler = NULL;
+ parser->m_entityDeclHandler = NULL;
+ parser->m_xmlDeclHandler = NULL;
+ parser->m_bufferPtr = parser->m_buffer;
+ parser->m_bufferEnd = parser->m_buffer;
+ parser->m_parseEndByteIndex = 0;
+ parser->m_parseEndPtr = NULL;
+ parser->m_declElementType = NULL;
+ parser->m_declAttributeId = NULL;
+ parser->m_declEntity = NULL;
+ parser->m_doctypeName = NULL;
+ parser->m_doctypeSysid = NULL;
+ parser->m_doctypePubid = NULL;
+ parser->m_declAttributeType = NULL;
+ parser->m_declNotationName = NULL;
+ parser->m_declNotationPublicId = NULL;
+ parser->m_declAttributeIsCdata = XML_FALSE;
+ parser->m_declAttributeIsId = XML_FALSE;
+ memset(&parser->m_position, 0, sizeof(POSITION));
+ parser->m_errorCode = XML_ERROR_NONE;
+ parser->m_eventPtr = NULL;
+ parser->m_eventEndPtr = NULL;
+ parser->m_positionPtr = NULL;
+ parser->m_openInternalEntities = NULL;
+ parser->m_defaultExpandInternalEntities = XML_TRUE;
+ parser->m_tagLevel = 0;
+ parser->m_tagStack = NULL;
+ parser->m_inheritedBindings = NULL;
+ parser->m_nSpecifiedAtts = 0;
+ parser->m_unknownEncodingMem = NULL;
+ parser->m_unknownEncodingRelease = NULL;
+ parser->m_unknownEncodingData = NULL;
+ parser->m_parentParser = NULL;
+ parser->m_parsingStatus.parsing = XML_INITIALIZED;
#ifdef XML_DTD
- isParamEntity = XML_FALSE;
- useForeignDTD = XML_FALSE;
- paramEntityParsing = XML_PARAM_ENTITY_PARSING_NEVER;
+ parser->m_isParamEntity = XML_FALSE;
+ parser->m_useForeignDTD = XML_FALSE;
+ parser->m_paramEntityParsing = XML_PARAM_ENTITY_PARSING_NEVER;
#endif
- hash_secret_salt = 0;
+ parser->m_hash_secret_salt = 0;
}
-/* moves list of bindings to freeBindingList */
+/* moves list of bindings to m_freeBindingList */
static void FASTCALL
moveToFreeBindingList(XML_Parser parser, BINDING *bindings)
{
while (bindings) {
BINDING *b = bindings;
bindings = bindings->nextTagBinding;
- b->nextTagBinding = freeBindingList;
- freeBindingList = b;
+ b->nextTagBinding = parser->m_freeBindingList;
+ parser->m_freeBindingList = b;
}
}
@@ -916,34 +866,36 @@ XML_ParserReset(XML_Parser parser, const XML_Char *encodingName)
{
TAG *tStk;
OPEN_INTERNAL_ENTITY *openEntityList;
- if (parentParser)
+ if (parser->m_parentParser)
return XML_FALSE;
- /* move tagStack to freeTagList */
- tStk = tagStack;
+ /* move m_tagStack to m_freeTagList */
+ tStk = parser->m_tagStack;
while (tStk) {
TAG *tag = tStk;
tStk = tStk->parent;
- tag->parent = freeTagList;
+ tag->parent = parser->m_freeTagList;
moveToFreeBindingList(parser, tag->bindings);
tag->bindings = NULL;
- freeTagList = tag;
+ parser->m_freeTagList = tag;
}
- /* move openInternalEntities to freeInternalEntities */
- openEntityList = openInternalEntities;
+ /* move m_openInternalEntities to m_freeInternalEntities */
+ openEntityList = parser->m_openInternalEntities;
while (openEntityList) {
OPEN_INTERNAL_ENTITY *openEntity = openEntityList;
openEntityList = openEntity->next;
- openEntity->next = freeInternalEntities;
- freeInternalEntities = openEntity;
- }
- moveToFreeBindingList(parser, inheritedBindings);
- FREE(unknownEncodingMem);
- if (unknownEncodingRelease)
- unknownEncodingRelease(unknownEncodingData);
- poolClear(&tempPool);
- poolClear(&temp2Pool);
+ openEntity->next = parser->m_freeInternalEntities;
+ parser->m_freeInternalEntities = openEntity;
+ }
+ moveToFreeBindingList(parser, parser->m_inheritedBindings);
+ FREE(parser, parser->m_unknownEncodingMem);
+ if (parser->m_unknownEncodingRelease)
+ parser->m_unknownEncodingRelease(parser->m_unknownEncodingData);
+ poolClear(&parser->m_tempPool);
+ poolClear(&parser->m_temp2Pool);
+ FREE(parser, (void *)parser->m_protocolEncodingName);
+ parser->m_protocolEncodingName = NULL;
parserInit(parser, encodingName);
- dtdReset(_dtd, &parser->m_mem);
+ dtdReset(parser->m_dtd, &parser->m_mem);
return XML_TRUE;
}
@@ -954,13 +906,20 @@ XML_SetEncoding(XML_Parser parser, const XML_Char *encodingName)
XXX There's no way for the caller to determine which of the
XXX possible error cases caused the XML_STATUS_ERROR return.
*/
- if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED)
+ if (parser->m_parsingStatus.parsing == XML_PARSING
+ || parser->m_parsingStatus.parsing == XML_SUSPENDED)
return XML_STATUS_ERROR;
+
+ /* Get rid of any previous encoding name */
+ FREE(parser, (void *)parser->m_protocolEncodingName);
+
if (encodingName == NULL)
- protocolEncodingName = NULL;
+ /* No new encoding name */
+ parser->m_protocolEncodingName = NULL;
else {
- protocolEncodingName = poolCopyString(&tempPool, encodingName);
- if (!protocolEncodingName)
+ /* Copy the new encoding name into allocated memory */
+ parser->m_protocolEncodingName = copyString(encodingName, &(parser->m_mem));
+ if (!parser->m_protocolEncodingName)
return XML_STATUS_ERROR;
}
return XML_STATUS_OK;
@@ -973,52 +932,44 @@ XML_ExternalEntityParserCreate(XML_Parser oldParser,
{
XML_Parser parser = oldParser;
DTD *newDtd = NULL;
- 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_UnparsedEntityDeclHandler oldUnparsedEntityDeclHandler
- = unparsedEntityDeclHandler;
- XML_NotationDeclHandler oldNotationDeclHandler = notationDeclHandler;
- XML_StartNamespaceDeclHandler oldStartNamespaceDeclHandler
- = startNamespaceDeclHandler;
- XML_EndNamespaceDeclHandler oldEndNamespaceDeclHandler
- = endNamespaceDeclHandler;
- XML_NotStandaloneHandler oldNotStandaloneHandler = notStandaloneHandler;
- XML_ExternalEntityRefHandler oldExternalEntityRefHandler
- = externalEntityRefHandler;
- XML_SkippedEntityHandler oldSkippedEntityHandler = skippedEntityHandler;
- XML_UnknownEncodingHandler oldUnknownEncodingHandler
- = unknownEncodingHandler;
- XML_ElementDeclHandler oldElementDeclHandler = elementDeclHandler;
- XML_AttlistDeclHandler oldAttlistDeclHandler = attlistDeclHandler;
- XML_EntityDeclHandler oldEntityDeclHandler = entityDeclHandler;
- XML_XmlDeclHandler oldXmlDeclHandler = xmlDeclHandler;
- ELEMENT_TYPE * oldDeclElementType = declElementType;
-
- void *oldUserData = userData;
- void *oldHandlerArg = handlerArg;
- XML_Bool oldDefaultExpandInternalEntities = defaultExpandInternalEntities;
- XML_Parser oldExternalEntityRefHandlerArg = externalEntityRefHandlerArg;
+ DTD *oldDtd = parser->m_dtd;
+ XML_StartElementHandler oldStartElementHandler = parser->m_startElementHandler;
+ XML_EndElementHandler oldEndElementHandler = parser->m_endElementHandler;
+ XML_CharacterDataHandler oldCharacterDataHandler = parser->m_characterDataHandler;
+ XML_ProcessingInstructionHandler oldProcessingInstructionHandler = parser->m_processingInstructionHandler;
+ XML_CommentHandler oldCommentHandler = parser->m_commentHandler;
+ XML_StartCdataSectionHandler oldStartCdataSectionHandler = parser->m_startCdataSectionHandler;
+ XML_EndCdataSectionHandler oldEndCdataSectionHandler = parser->m_endCdataSectionHandler;
+ XML_DefaultHandler oldDefaultHandler = parser->m_defaultHandler;
+ XML_UnparsedEntityDeclHandler oldUnparsedEntityDeclHandler = parser->m_unparsedEntityDeclHandler;
+ XML_NotationDeclHandler oldNotationDeclHandler = parser->m_notationDeclHandler;
+ XML_StartNamespaceDeclHandler oldStartNamespaceDeclHandler = parser->m_startNamespaceDeclHandler;
+ XML_EndNamespaceDeclHandler oldEndNamespaceDeclHandler = parser->m_endNamespaceDeclHandler;
+ XML_NotStandaloneHandler oldNotStandaloneHandler = parser->m_notStandaloneHandler;
+ XML_ExternalEntityRefHandler oldExternalEntityRefHandler = parser->m_externalEntityRefHandler;
+ XML_SkippedEntityHandler oldSkippedEntityHandler = parser->m_skippedEntityHandler;
+ XML_UnknownEncodingHandler oldUnknownEncodingHandler = parser->m_unknownEncodingHandler;
+ XML_ElementDeclHandler oldElementDeclHandler = parser->m_elementDeclHandler;
+ XML_AttlistDeclHandler oldAttlistDeclHandler = parser->m_attlistDeclHandler;
+ XML_EntityDeclHandler oldEntityDeclHandler = parser->m_entityDeclHandler;
+ XML_XmlDeclHandler oldXmlDeclHandler = parser->m_xmlDeclHandler;
+ ELEMENT_TYPE * oldDeclElementType = parser->m_declElementType;
+
+ void *oldUserData = parser->m_userData;
+ void *oldHandlerArg = parser->m_handlerArg;
+ XML_Bool oldDefaultExpandInternalEntities = parser->m_defaultExpandInternalEntities;
+ XML_Parser oldExternalEntityRefHandlerArg = parser->m_externalEntityRefHandlerArg;
#ifdef XML_DTD
- enum XML_ParamEntityParsing oldParamEntityParsing = paramEntityParsing;
- int oldInEntityValue = prologState.inEntityValue;
+ enum XML_ParamEntityParsing oldParamEntityParsing = parser->m_paramEntityParsing;
+ int oldInEntityValue = parser->m_prologState.inEntityValue;
#endif
- XML_Bool oldns_triplets = ns_triplets;
+ XML_Bool oldns_triplets = parser->m_ns_triplets;
/* Note that the new parser shares the same hash secret as the old
parser, so that dtdCopy and copyEntityTable can lookup values
from hash tables associated with either parser without us having
to worry which hash secrets each table has.
*/
- unsigned long oldhash_secret_salt = hash_secret_salt;
+ size_t oldhash_secret_salt = parser->m_hash_secret_salt;
#ifdef XML_DTD
if (!context)
@@ -1030,9 +981,9 @@ XML_ExternalEntityParserCreate(XML_Parser oldParser,
here. This makes this function more painful to follow than it
would be otherwise.
*/
- if (ns) {
+ if (parser->m_ns) {
XML_Char tmp[2];
- *tmp = namespaceSeparator;
+ *tmp = parser->m_namespaceSeparator;
parser = parserCreate(encodingName, &parser->m_mem, tmp, newDtd);
}
else {
@@ -1042,62 +993,62 @@ XML_ExternalEntityParserCreate(XML_Parser oldParser,
if (!parser)
return NULL;
- startElementHandler = oldStartElementHandler;
- endElementHandler = oldEndElementHandler;
- characterDataHandler = oldCharacterDataHandler;
- processingInstructionHandler = oldProcessingInstructionHandler;
- commentHandler = oldCommentHandler;
- startCdataSectionHandler = oldStartCdataSectionHandler;
- endCdataSectionHandler = oldEndCdataSectionHandler;
- defaultHandler = oldDefaultHandler;
- unparsedEntityDeclHandler = oldUnparsedEntityDeclHandler;
- notationDeclHandler = oldNotationDeclHandler;
- startNamespaceDeclHandler = oldStartNamespaceDeclHandler;
- endNamespaceDeclHandler = oldEndNamespaceDeclHandler;
- notStandaloneHandler = oldNotStandaloneHandler;
- externalEntityRefHandler = oldExternalEntityRefHandler;
- skippedEntityHandler = oldSkippedEntityHandler;
- unknownEncodingHandler = oldUnknownEncodingHandler;
- elementDeclHandler = oldElementDeclHandler;
- attlistDeclHandler = oldAttlistDeclHandler;
- entityDeclHandler = oldEntityDeclHandler;
- xmlDeclHandler = oldXmlDeclHandler;
- declElementType = oldDeclElementType;
- userData = oldUserData;
+ parser->m_startElementHandler = oldStartElementHandler;
+ parser->m_endElementHandler = oldEndElementHandler;
+ parser->m_characterDataHandler = oldCharacterDataHandler;
+ parser->m_processingInstructionHandler = oldProcessingInstructionHandler;
+ parser->m_commentHandler = oldCommentHandler;
+ parser->m_startCdataSectionHandler = oldStartCdataSectionHandler;
+ parser->m_endCdataSectionHandler = oldEndCdataSectionHandler;
+ parser->m_defaultHandler = oldDefaultHandler;
+ parser->m_unparsedEntityDeclHandler = oldUnparsedEntityDeclHandler;
+ parser->m_notationDeclHandler = oldNotationDeclHandler;
+ parser->m_startNamespaceDeclHandler = oldStartNamespaceDeclHandler;
+ parser->m_endNamespaceDeclHandler = oldEndNamespaceDeclHandler;
+ parser->m_notStandaloneHandler = oldNotStandaloneHandler;
+ parser->m_externalEntityRefHandler = oldExternalEntityRefHandler;
+ parser->m_skippedEntityHandler = oldSkippedEntityHandler;
+ parser->m_unknownEncodingHandler = oldUnknownEncodingHandler;
+ parser->m_elementDeclHandler = oldElementDeclHandler;
+ parser->m_attlistDeclHandler = oldAttlistDeclHandler;
+ parser->m_entityDeclHandler = oldEntityDeclHandler;
+ parser->m_xmlDeclHandler = oldXmlDeclHandler;
+ parser->m_declElementType = oldDeclElementType;
+ parser->m_userData = oldUserData;
if (oldUserData == oldHandlerArg)
- handlerArg = userData;
+ parser->m_handlerArg = parser->m_userData;
else
- handlerArg = parser;
+ parser->m_handlerArg = parser;
if (oldExternalEntityRefHandlerArg != oldParser)
- externalEntityRefHandlerArg = oldExternalEntityRefHandlerArg;
- defaultExpandInternalEntities = oldDefaultExpandInternalEntities;
- ns_triplets = oldns_triplets;
- hash_secret_salt = oldhash_secret_salt;
- parentParser = oldParser;
+ parser->m_externalEntityRefHandlerArg = oldExternalEntityRefHandlerArg;
+ parser->m_defaultExpandInternalEntities = oldDefaultExpandInternalEntities;
+ parser->m_ns_triplets = oldns_triplets;
+ parser->m_hash_secret_salt = oldhash_secret_salt;
+ parser->m_parentParser = oldParser;
#ifdef XML_DTD
- paramEntityParsing = oldParamEntityParsing;
- prologState.inEntityValue = oldInEntityValue;
+ parser->m_paramEntityParsing = oldParamEntityParsing;
+ parser->m_prologState.inEntityValue = oldInEntityValue;
if (context) {
#endif /* XML_DTD */
- if (!dtdCopy(oldParser, _dtd, oldDtd, &parser->m_mem)
+ if (!dtdCopy(oldParser, parser->m_dtd, oldDtd, &parser->m_mem)
|| !setContext(parser, context)) {
XML_ParserFree(parser);
return NULL;
}
- processor = externalEntityInitProcessor;
+ parser->m_processor = externalEntityInitProcessor;
#ifdef XML_DTD
}
else {
- /* The DTD instance referenced by _dtd is shared between the document's
+ /* The DTD instance referenced by parser->m_dtd is shared between the document's
root parser and external PE parsers, therefore one does not need to
call setContext. In addition, one also *must* not call setContext,
because this would overwrite existing prefix->binding pointers in
- _dtd with ones that get destroyed with the external PE parser.
+ parser->m_dtd with ones that get destroyed with the external PE parser.
This would leave those prefixes with dangling pointers.
*/
- isParamEntity = XML_TRUE;
- XmlPrologStateInitExternalEntity(&prologState);
- processor = externalParEntInitProcessor;
+ parser->m_isParamEntity = XML_TRUE;
+ XmlPrologStateInitExternalEntity(&parser->m_prologState);
+ parser->m_processor = externalParEntInitProcessor;
}
#endif /* XML_DTD */
return parser;
@@ -1111,8 +1062,8 @@ destroyBindings(BINDING *bindings, XML_Parser parser)
if (!b)
break;
bindings = b->nextTagBinding;
- FREE(b->uri);
- FREE(b);
+ FREE(parser, b->uri);
+ FREE(parser, b);
}
}
@@ -1123,68 +1074,69 @@ XML_ParserFree(XML_Parser parser)
OPEN_INTERNAL_ENTITY *entityList;
if (parser == NULL)
return;
- /* free tagStack and freeTagList */
- tagList = tagStack;
+ /* free m_tagStack and m_freeTagList */
+ tagList = parser->m_tagStack;
for (;;) {
TAG *p;
if (tagList == NULL) {
- if (freeTagList == NULL)
+ if (parser->m_freeTagList == NULL)
break;
- tagList = freeTagList;
- freeTagList = NULL;
+ tagList = parser->m_freeTagList;
+ parser->m_freeTagList = NULL;
}
p = tagList;
tagList = tagList->parent;
- FREE(p->buf);
+ FREE(parser, p->buf);
destroyBindings(p->bindings, parser);
- FREE(p);
+ FREE(parser, p);
}
- /* free openInternalEntities and freeInternalEntities */
- entityList = openInternalEntities;
+ /* free m_openInternalEntities and m_freeInternalEntities */
+ entityList = parser->m_openInternalEntities;
for (;;) {
OPEN_INTERNAL_ENTITY *openEntity;
if (entityList == NULL) {
- if (freeInternalEntities == NULL)
+ if (parser->m_freeInternalEntities == NULL)
break;
- entityList = freeInternalEntities;
- freeInternalEntities = NULL;
+ entityList = parser->m_freeInternalEntities;
+ parser->m_freeInternalEntities = NULL;
}
openEntity = entityList;
entityList = entityList->next;
- FREE(openEntity);
+ FREE(parser, openEntity);
}
- destroyBindings(freeBindingList, parser);
- destroyBindings(inheritedBindings, parser);
- poolDestroy(&tempPool);
- poolDestroy(&temp2Pool);
+ destroyBindings(parser->m_freeBindingList, parser);
+ destroyBindings(parser->m_inheritedBindings, parser);
+ poolDestroy(&parser->m_tempPool);
+ poolDestroy(&parser->m_temp2Pool);
+ FREE(parser, (void *)parser->m_protocolEncodingName);
#ifdef XML_DTD
/* external parameter entity parsers share the DTD structure
parser->m_dtd with the root parser, so we must not destroy it
*/
- if (!isParamEntity && _dtd)
+ if (!parser->m_isParamEntity && parser->m_dtd)
#else
- if (_dtd)
+ if (parser->m_dtd)
#endif /* XML_DTD */
- dtdDestroy(_dtd, (XML_Bool)!parentParser, &parser->m_mem);
- FREE((void *)atts);
+ dtdDestroy(parser->m_dtd, (XML_Bool)!parser->m_parentParser, &parser->m_mem);
+ FREE(parser, (void *)parser->m_atts);
#ifdef XML_ATTR_INFO
- FREE((void *)attInfo);
+ FREE(parser, (void *)parser->m_attInfo);
#endif
- FREE(groupConnector);
- FREE(buffer);
- FREE(dataBuf);
- FREE(nsAtts);
- FREE(unknownEncodingMem);
- if (unknownEncodingRelease)
- unknownEncodingRelease(unknownEncodingData);
- FREE(parser);
+ FREE(parser, parser->m_groupConnector);
+ FREE(parser, parser->m_buffer);
+ FREE(parser, parser->m_dataBuf);
+ FREE(parser, parser->m_nsAtts);
+ FREE(parser, parser->m_unknownEncodingMem);
+ if (parser->m_unknownEncodingRelease)
+ parser->m_unknownEncodingRelease(parser->m_unknownEncodingData);
+ FREE(parser, parser);
}
void XMLCALL
XML_UseParserAsHandlerArg(XML_Parser parser)
{
- handlerArg = parser;
+ parser->m_handlerArg = parser;
}
enum XML_Error XMLCALL
@@ -1192,9 +1144,9 @@ XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD)
{
#ifdef XML_DTD
/* block after XML_Parse()/XML_ParseBuffer() has been called */
- if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED)
+ if (parser->m_parsingStatus.parsing == XML_PARSING || parser->m_parsingStatus.parsing == XML_SUSPENDED)
return XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING;
- useForeignDTD = useDTD;
+ parser->m_useForeignDTD = useDTD;
return XML_ERROR_NONE;
#else
return XML_ERROR_FEATURE_REQUIRES_XML_DTD;
@@ -1205,57 +1157,57 @@ void XMLCALL
XML_SetReturnNSTriplet(XML_Parser parser, int do_nst)
{
/* block after XML_Parse()/XML_ParseBuffer() has been called */
- if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED)
+ if (parser->m_parsingStatus.parsing == XML_PARSING || parser->m_parsingStatus.parsing == XML_SUSPENDED)
return;
- ns_triplets = do_nst ? XML_TRUE : XML_FALSE;
+ parser->m_ns_triplets = do_nst ? XML_TRUE : XML_FALSE;
}
void XMLCALL
XML_SetUserData(XML_Parser parser, void *p)
{
- if (handlerArg == userData)
- handlerArg = userData = p;
+ if (parser->m_handlerArg == parser->m_userData)
+ parser->m_handlerArg = parser->m_userData = p;
else
- userData = p;
+ parser->m_userData = p;
}
enum XML_Status XMLCALL
XML_SetBase(XML_Parser parser, const XML_Char *p)
{
if (p) {
- p = poolCopyString(&_dtd->pool, p);
+ p = poolCopyString(&parser->m_dtd->pool, p);
if (!p)
return XML_STATUS_ERROR;
- curBase = p;
+ parser->m_curBase = p;
}
else
- curBase = NULL;
+ parser->m_curBase = NULL;
return XML_STATUS_OK;
}
const XML_Char * XMLCALL
XML_GetBase(XML_Parser parser)
{
- return curBase;
+ return parser->m_curBase;
}
int XMLCALL
XML_GetSpecifiedAttributeCount(XML_Parser parser)
{
- return nSpecifiedAtts;
+ return parser->m_nSpecifiedAtts;
}
int XMLCALL
XML_GetIdAttributeIndex(XML_Parser parser)
{
- return idAttIndex;
+ return parser->m_idAttIndex;
}
#ifdef XML_ATTR_INFO
const XML_AttrInfo * XMLCALL
XML_GetAttributeInfo(XML_Parser parser)
{
- return attInfo;
+ return parser->m_attInfo;
}
#endif
@@ -1264,41 +1216,41 @@ XML_SetElementHandler(XML_Parser parser,
XML_StartElementHandler start,
XML_EndElementHandler end)
{
- startElementHandler = start;
- endElementHandler = end;
+ parser->m_startElementHandler = start;
+ parser->m_endElementHandler = end;
}
void XMLCALL
XML_SetStartElementHandler(XML_Parser parser,
XML_StartElementHandler start) {
- startElementHandler = start;
+ parser->m_startElementHandler = start;
}
void XMLCALL
XML_SetEndElementHandler(XML_Parser parser,
XML_EndElementHandler end) {
- endElementHandler = end;
+ parser->m_endElementHandler = end;
}
void XMLCALL
XML_SetCharacterDataHandler(XML_Parser parser,
XML_CharacterDataHandler handler)
{
- characterDataHandler = handler;
+ parser->m_characterDataHandler = handler;
}
void XMLCALL
XML_SetProcessingInstructionHandler(XML_Parser parser,
XML_ProcessingInstructionHandler handler)
{
- processingInstructionHandler = handler;
+ parser->m_processingInstructionHandler = handler;
}
void XMLCALL
XML_SetCommentHandler(XML_Parser parser,
XML_CommentHandler handler)
{
- commentHandler = handler;
+ parser->m_commentHandler = handler;
}
void XMLCALL
@@ -1306,36 +1258,36 @@ XML_SetCdataSectionHandler(XML_Parser parser,
XML_StartCdataSectionHandler start,
XML_EndCdataSectionHandler end)
{
- startCdataSectionHandler = start;
- endCdataSectionHandler = end;
+ parser->m_startCdataSectionHandler = start;
+ parser->m_endCdataSectionHandler = end;
}
void XMLCALL
XML_SetStartCdataSectionHandler(XML_Parser parser,
XML_StartCdataSectionHandler start) {
- startCdataSectionHandler = start;
+ parser->m_startCdataSectionHandler = start;
}
void XMLCALL
XML_SetEndCdataSectionHandler(XML_Parser parser,
XML_EndCdataSectionHandler end) {
- endCdataSectionHandler = end;
+ parser->m_endCdataSectionHandler = end;
}
void XMLCALL
XML_SetDefaultHandler(XML_Parser parser,
XML_DefaultHandler handler)
{
- defaultHandler = handler;
- defaultExpandInternalEntities = XML_FALSE;
+ parser->m_defaultHandler = handler;
+ parser->m_defaultExpandInternalEntities = XML_FALSE;
}
void XMLCALL
XML_SetDefaultHandlerExpand(XML_Parser parser,
XML_DefaultHandler handler)
{
- defaultHandler = handler;
- defaultExpandInternalEntities = XML_TRUE;
+ parser->m_defaultHandler = handler;
+ parser->m_defaultExpandInternalEntities = XML_TRUE;
}
void XMLCALL
@@ -1343,34 +1295,34 @@ XML_SetDoctypeDeclHandler(XML_Parser parser,
XML_StartDoctypeDeclHandler start,
XML_EndDoctypeDeclHandler end)
{
- startDoctypeDeclHandler = start;
- endDoctypeDeclHandler = end;
+ parser->m_startDoctypeDeclHandler = start;
+ parser->m_endDoctypeDeclHandler = end;
}
void XMLCALL
XML_SetStartDoctypeDeclHandler(XML_Parser parser,
XML_StartDoctypeDeclHandler start) {
- startDoctypeDeclHandler = start;
+ parser->m_startDoctypeDeclHandler = start;
}
void XMLCALL
XML_SetEndDoctypeDeclHandler(XML_Parser parser,
XML_EndDoctypeDeclHandler end) {
- endDoctypeDeclHandler = end;
+ parser->m_endDoctypeDeclHandler = end;
}
void XMLCALL
XML_SetUnparsedEntityDeclHandler(XML_Parser parser,
XML_UnparsedEntityDeclHandler handler)
{
- unparsedEntityDeclHandler = handler;
+ parser->m_unparsedEntityDeclHandler = handler;
}
void XMLCALL
XML_SetNotationDeclHandler(XML_Parser parser,
XML_NotationDeclHandler handler)
{
- notationDeclHandler = handler;
+ parser->m_notationDeclHandler = handler;
}
void XMLCALL
@@ -1378,50 +1330,50 @@ XML_SetNamespaceDeclHandler(XML_Parser parser,
XML_StartNamespaceDeclHandler start,
XML_EndNamespaceDeclHandler end)
{
- startNamespaceDeclHandler = start;
- endNamespaceDeclHandler = end;
+ parser->m_startNamespaceDeclHandler = start;
+ parser->m_endNamespaceDeclHandler = end;
}
void XMLCALL
XML_SetStartNamespaceDeclHandler(XML_Parser parser,
XML_StartNamespaceDeclHandler start) {
- startNamespaceDeclHandler = start;
+ parser->m_startNamespaceDeclHandler = start;
}
void XMLCALL
XML_SetEndNamespaceDeclHandler(XML_Parser parser,
XML_EndNamespaceDeclHandler end) {
- endNamespaceDeclHandler = end;
+ parser->m_endNamespaceDeclHandler = end;
}
void XMLCALL
XML_SetNotStandaloneHandler(XML_Parser parser,
XML_NotStandaloneHandler handler)
{
- notStandaloneHandler = handler;
+ parser->m_notStandaloneHandler = handler;
}
void XMLCALL
XML_SetExternalEntityRefHandler(XML_Parser parser,
XML_ExternalEntityRefHandler handler)
{
- externalEntityRefHandler = handler;
+ parser->m_externalEntityRefHandler = handler;
}
void XMLCALL
XML_SetExternalEntityRefHandlerArg(XML_Parser parser, void *arg)
{
if (arg)
- externalEntityRefHandlerArg = (XML_Parser)arg;
+ parser->m_externalEntityRefHandlerArg = (XML_Parser)arg;
else
- externalEntityRefHandlerArg = parser;
+ parser->m_externalEntityRefHandlerArg = parser;
}
void XMLCALL
XML_SetSkippedEntityHandler(XML_Parser parser,
XML_SkippedEntityHandler handler)
{
- skippedEntityHandler = handler;
+ parser->m_skippedEntityHandler = handler;
}
void XMLCALL
@@ -1429,35 +1381,35 @@ XML_SetUnknownEncodingHandler(XML_Parser parser,
XML_UnknownEncodingHandler handler,
void *data)
{
- unknownEncodingHandler = handler;
- unknownEncodingHandlerData = data;
+ parser->m_unknownEncodingHandler = handler;
+ parser->m_unknownEncodingHandlerData = data;
}
void XMLCALL
XML_SetElementDeclHandler(XML_Parser parser,
XML_ElementDeclHandler eldecl)
{
- elementDeclHandler = eldecl;
+ parser->m_elementDeclHandler = eldecl;
}
void XMLCALL
XML_SetAttlistDeclHandler(XML_Parser parser,
XML_AttlistDeclHandler attdecl)
{
- attlistDeclHandler = attdecl;
+ parser->m_attlistDeclHandler = attdecl;
}
void XMLCALL
XML_SetEntityDeclHandler(XML_Parser parser,
XML_EntityDeclHandler handler)
{
- entityDeclHandler = handler;
+ parser->m_entityDeclHandler = handler;
}
void XMLCALL
XML_SetXmlDeclHandler(XML_Parser parser,
XML_XmlDeclHandler handler) {
- xmlDeclHandler = handler;
+ parser->m_xmlDeclHandler = handler;
}
int XMLCALL
@@ -1465,10 +1417,10 @@ XML_SetParamEntityParsing(XML_Parser parser,
enum XML_ParamEntityParsing peParsing)
{
/* block after XML_Parse()/XML_ParseBuffer() has been called */
- if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED)
+ if (parser->m_parsingStatus.parsing == XML_PARSING || parser->m_parsingStatus.parsing == XML_SUSPENDED)
return 0;
#ifdef XML_DTD
- paramEntityParsing = peParsing;
+ parser->m_paramEntityParsing = peParsing;
return 1;
#else
return peParsing == XML_PARAM_ENTITY_PARSING_NEVER;
@@ -1477,90 +1429,90 @@ XML_SetParamEntityParsing(XML_Parser parser,
int XMLCALL
XML_SetHashSalt(XML_Parser parser,
- unsigned long hash_salt)
+ unsigned long hash_salt) /* should be size_t */
{
/* block after XML_Parse()/XML_ParseBuffer() has been called */
- if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED)
+ if (parser->m_parsingStatus.parsing == XML_PARSING || parser->m_parsingStatus.parsing == XML_SUSPENDED)
return 0;
- hash_secret_salt = hash_salt;
+ parser->m_hash_secret_salt = hash_salt;
return 1;
}
enum XML_Status XMLCALL
XML_Parse(XML_Parser parser, const char *s, int len, int isFinal)
{
- switch (ps_parsing) {
+ switch (parser->m_parsingStatus.parsing) {
case XML_SUSPENDED:
- errorCode = XML_ERROR_SUSPENDED;
+ parser->m_errorCode = XML_ERROR_SUSPENDED;
return XML_STATUS_ERROR;
case XML_FINISHED:
- errorCode = XML_ERROR_FINISHED;
+ parser->m_errorCode = XML_ERROR_FINISHED;
return XML_STATUS_ERROR;
case XML_INITIALIZED:
- if (parentParser == NULL && !startParsing(parser)) {
- errorCode = XML_ERROR_NO_MEMORY;
+ if (parser->m_parentParser == NULL && !startParsing(parser)) {
+ parser->m_errorCode = XML_ERROR_NO_MEMORY;
return XML_STATUS_ERROR;
}
default:
- ps_parsing = XML_PARSING;
+ parser->m_parsingStatus.parsing = XML_PARSING;
}
if (len == 0) {
- ps_finalBuffer = (XML_Bool)isFinal;
+ parser->m_parsingStatus.finalBuffer = (XML_Bool)isFinal;
if (!isFinal)
return XML_STATUS_OK;
- positionPtr = bufferPtr;
- parseEndPtr = bufferEnd;
+ parser->m_positionPtr = parser->m_bufferPtr;
+ parser->m_parseEndPtr = parser->m_bufferEnd;
/* If data are left over from last buffer, and we now know that these
data are the final chunk of input, then we have to check them again
to detect errors based on that fact.
*/
- errorCode = processor(parser, bufferPtr, parseEndPtr, &bufferPtr);
+ parser->m_errorCode = parser->m_processor(parser, parser->m_bufferPtr, parser->m_parseEndPtr, &parser->m_bufferPtr);
- if (errorCode == XML_ERROR_NONE) {
- switch (ps_parsing) {
+ if (parser->m_errorCode == XML_ERROR_NONE) {
+ switch (parser->m_parsingStatus.parsing) {
case XML_SUSPENDED:
- XmlUpdatePosition(encoding, positionPtr, bufferPtr, &position);
- positionPtr = bufferPtr;
+ XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, parser->m_bufferPtr, &parser->m_position);
+ parser->m_positionPtr = parser->m_bufferPtr;
return XML_STATUS_SUSPENDED;
case XML_INITIALIZED:
case XML_PARSING:
- ps_parsing = XML_FINISHED;
+ parser->m_parsingStatus.parsing = XML_FINISHED;
/* fall through */
default:
return XML_STATUS_OK;
}
}
- eventEndPtr = eventPtr;
- processor = errorProcessor;
+ parser->m_eventEndPtr = parser->m_eventPtr;
+ parser->m_processor = errorProcessor;
return XML_STATUS_ERROR;
}
#ifndef XML_CONTEXT_BYTES
- else if (bufferPtr == bufferEnd) {
+ else if (parser->m_bufferPtr == parser->m_bufferEnd) {
const char *end;
int nLeftOver;
enum XML_Error result;
- parseEndByteIndex += len;
- positionPtr = s;
- ps_finalBuffer = (XML_Bool)isFinal;
+ parser->m_parseEndByteIndex += len;
+ parser->m_positionPtr = s;
+ parser->m_parsingStatus.finalBuffer = (XML_Bool)isFinal;
- errorCode = processor(parser, s, parseEndPtr = s + len, &end);
+ parser->m_errorCode = parser->m_processor(parser, s, parser->m_parseEndPtr = s + len, &end);
- if (errorCode != XML_ERROR_NONE) {
- eventEndPtr = eventPtr;
- processor = errorProcessor;
+ if (parser->m_errorCode != XML_ERROR_NONE) {
+ parser->m_eventEndPtr = parser->m_eventPtr;
+ parser->m_processor = errorProcessor;
return XML_STATUS_ERROR;
}
else {
- switch (ps_parsing) {
+ switch (parser->m_parsingStatus.parsing) {
case XML_SUSPENDED:
result = XML_STATUS_SUSPENDED;
break;
case XML_INITIALIZED:
case XML_PARSING:
if (isFinal) {
- ps_parsing = XML_FINISHED;
+ parser->m_parsingStatus.parsing = XML_FINISHED;
return XML_STATUS_OK;
}
/* fall through */
@@ -1569,32 +1521,35 @@ XML_Parse(XML_Parser parser, const char *s, int len, int isFinal)
}
}
- XmlUpdatePosition(encoding, positionPtr, end, &position);
+ XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, end, &parser->m_position);
nLeftOver = s + len - end;
if (nLeftOver) {
- if (buffer == NULL || nLeftOver > bufferLim - buffer) {
- /* FIXME avoid integer overflow */
- char *temp;
- temp = (buffer == NULL
- ? (char *)MALLOC(len * 2)
- : (char *)REALLOC(buffer, len * 2));
+ if (parser->m_buffer == NULL || nLeftOver > parser->m_bufferLim - parser->m_buffer) {
+ /* avoid _signed_ integer overflow */
+ char *temp = NULL;
+ const int bytesToAllocate = (int)((unsigned)len * 2U);
+ if (bytesToAllocate > 0) {
+ temp = (parser->m_buffer == NULL
+ ? (char *)MALLOC(parser, bytesToAllocate)
+ : (char *)REALLOC(parser, parser->m_buffer, bytesToAllocate));
+ }
if (temp == NULL) {
- errorCode = XML_ERROR_NO_MEMORY;
- eventPtr = eventEndPtr = NULL;
- processor = errorProcessor;
+ parser->m_errorCode = XML_ERROR_NO_MEMORY;
+ parser->m_eventPtr = parser->m_eventEndPtr = NULL;
+ parser->m_processor = errorProcessor;
return XML_STATUS_ERROR;
}
- buffer = temp;
- bufferLim = buffer + len * 2;
+ parser->m_buffer = temp;
+ parser->m_bufferLim = parser->m_buffer + bytesToAllocate;
}
- memcpy(buffer, end, nLeftOver);
+ memcpy(parser->m_buffer, end, nLeftOver);
}
- bufferPtr = buffer;
- bufferEnd = buffer + nLeftOver;
- positionPtr = bufferPtr;
- parseEndPtr = bufferEnd;
- eventPtr = bufferPtr;
- eventEndPtr = bufferPtr;
+ parser->m_bufferPtr = parser->m_buffer;
+ parser->m_bufferEnd = parser->m_buffer + nLeftOver;
+ parser->m_positionPtr = parser->m_bufferPtr;
+ parser->m_parseEndPtr = parser->m_bufferEnd;
+ parser->m_eventPtr = parser->m_bufferPtr;
+ parser->m_eventEndPtr = parser->m_bufferPtr;
return result;
}
#endif /* not defined XML_CONTEXT_BYTES */
@@ -1615,163 +1570,194 @@ XML_ParseBuffer(XML_Parser parser, int len, int isFinal)
const char *start;
enum XML_Status result = XML_STATUS_OK;
- switch (ps_parsing) {
+ if (len < 0) {
+ parser->m_errorCode = XML_ERROR_INVALID_ARGUMENT;
+ return XML_STATUS_ERROR;
+ }
+
+ switch (parser->m_parsingStatus.parsing) {
case XML_SUSPENDED:
- errorCode = XML_ERROR_SUSPENDED;
+ parser->m_errorCode = XML_ERROR_SUSPENDED;
return XML_STATUS_ERROR;
case XML_FINISHED:
- errorCode = XML_ERROR_FINISHED;
+ parser->m_errorCode = XML_ERROR_FINISHED;
return XML_STATUS_ERROR;
case XML_INITIALIZED:
- if (parentParser == NULL && !startParsing(parser)) {
- errorCode = XML_ERROR_NO_MEMORY;
+ if (parser->m_parentParser == NULL && !startParsing(parser)) {
+ parser->m_errorCode = XML_ERROR_NO_MEMORY;
return XML_STATUS_ERROR;
}
default:
- ps_parsing = XML_PARSING;
+ parser->m_parsingStatus.parsing = XML_PARSING;
}
- start = bufferPtr;
- positionPtr = start;
- bufferEnd += len;
- parseEndPtr = bufferEnd;
- parseEndByteIndex += len;
- ps_finalBuffer = (XML_Bool)isFinal;
+ start = parser->m_bufferPtr;
+ parser->m_positionPtr = start;
+ parser->m_bufferEnd += len;
+ parser->m_parseEndPtr = parser->m_bufferEnd;
+ parser->m_parseEndByteIndex += len;
+ parser->m_parsingStatus.finalBuffer = (XML_Bool)isFinal;
- errorCode = processor(parser, start, parseEndPtr, &bufferPtr);
+ parser->m_errorCode = parser->m_processor(parser, start, parser->m_parseEndPtr, &parser->m_bufferPtr);
- if (errorCode != XML_ERROR_NONE) {
- eventEndPtr = eventPtr;
- processor = errorProcessor;
+ if (parser->m_errorCode != XML_ERROR_NONE) {
+ parser->m_eventEndPtr = parser->m_eventPtr;
+ parser->m_processor = errorProcessor;
return XML_STATUS_ERROR;
}
else {
- switch (ps_parsing) {
+ switch (parser->m_parsingStatus.parsing) {
case XML_SUSPENDED:
result = XML_STATUS_SUSPENDED;
break;
case XML_INITIALIZED:
case XML_PARSING:
if (isFinal) {
- ps_parsing = XML_FINISHED;
+ parser->m_parsingStatus.parsing = XML_FINISHED;
return result;
}
default: ; /* should not happen */
}
}
- XmlUpdatePosition(encoding, positionPtr, bufferPtr, &position);
- positionPtr = bufferPtr;
+ XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, parser->m_bufferPtr, &parser->m_position);
+ parser->m_positionPtr = parser->m_bufferPtr;
return result;
}
void * XMLCALL
XML_GetBuffer(XML_Parser parser, int len)
{
- switch (ps_parsing) {
+/* BEGIN MOZILLA CHANGE (sanity check len) */
+ if (len < 0) {
+ parser->m_errorCode = XML_ERROR_NO_MEMORY;
+ return NULL;
+ }
+/* END MOZILLA CHANGE */
+ switch (parser->m_parsingStatus.parsing) {
case XML_SUSPENDED:
- errorCode = XML_ERROR_SUSPENDED;
+ parser->m_errorCode = XML_ERROR_SUSPENDED;
return NULL;
case XML_FINISHED:
- errorCode = XML_ERROR_FINISHED;
+ parser->m_errorCode = XML_ERROR_FINISHED;
return NULL;
default: ;
}
- if (len > bufferLim - bufferEnd) {
- /* FIXME avoid integer overflow */
- int neededSize = len + (int)(bufferEnd - bufferPtr);
+ if (len > parser->m_bufferLim - parser->m_bufferEnd) {
+ /* Do not invoke signed arithmetic overflow: */
+ int neededSize = (int) ((unsigned)len + (unsigned)(parser->m_bufferEnd - parser->m_bufferPtr));
+/* BEGIN MOZILLA CHANGE (sanity check neededSize) */
+ if (neededSize < 0) {
+ parser->m_errorCode = XML_ERROR_NO_MEMORY;
+ return NULL;
+ }
+/* END MOZILLA CHANGE */
#ifdef XML_CONTEXT_BYTES
- int keep = (int)(bufferPtr - buffer);
+ int keep = (int)(parser->m_bufferPtr - parser->m_buffer);
if (keep > XML_CONTEXT_BYTES)
keep = XML_CONTEXT_BYTES;
+ /* Detect and prevent integer overflow */
+ if (keep > INT_MAX - neededSize) {
+ parser->m_errorCode = XML_ERROR_NO_MEMORY;
+ return NULL;
+ }
neededSize += keep;
#endif /* defined XML_CONTEXT_BYTES */
- if (neededSize <= bufferLim - buffer) {
+ if (neededSize <= parser->m_bufferLim - parser->m_buffer) {
#ifdef XML_CONTEXT_BYTES
- if (keep < bufferPtr - buffer) {
- int offset = (int)(bufferPtr - buffer) - keep;
- memmove(buffer, &buffer[offset], bufferEnd - bufferPtr + keep);
- bufferEnd -= offset;
- bufferPtr -= offset;
+ if (keep < parser->m_bufferPtr - parser->m_buffer) {
+ int offset = (int)(parser->m_bufferPtr - parser->m_buffer) - keep;
+ memmove(parser->m_buffer, &parser->m_buffer[offset], parser->m_bufferEnd - parser->m_bufferPtr + keep);
+ parser->m_bufferEnd -= offset;
+ parser->m_bufferPtr -= offset;
}
#else
- memmove(buffer, bufferPtr, bufferEnd - bufferPtr);
- bufferEnd = buffer + (bufferEnd - bufferPtr);
- bufferPtr = buffer;
+ memmove(parser->m_buffer, parser->m_bufferPtr, parser->m_bufferEnd - parser->m_bufferPtr);
+ parser->m_bufferEnd = parser->m_buffer + (parser->m_bufferEnd - parser->m_bufferPtr);
+ parser->m_bufferPtr = parser->m_buffer;
#endif /* not defined XML_CONTEXT_BYTES */
}
else {
char *newBuf;
- int bufferSize = (int)(bufferLim - bufferPtr);
+ int bufferSize = (int)(parser->m_bufferLim - parser->m_bufferPtr);
if (bufferSize == 0)
bufferSize = INIT_BUFFER_SIZE;
do {
- bufferSize *= 2;
- } while (bufferSize < neededSize);
- newBuf = (char *)MALLOC(bufferSize);
+ /* Do not invoke signed arithmetic overflow: */
+ bufferSize = (int) (2U * (unsigned) bufferSize);
+/* BEGIN MOZILLA CHANGE (prevent infinite loop on overflow) */
+ } while (bufferSize < neededSize && bufferSize > 0);
+/* END MOZILLA CHANGE */
+/* BEGIN MOZILLA CHANGE (sanity check bufferSize) */
+ if (bufferSize <= 0) {
+ parser->m_errorCode = XML_ERROR_NO_MEMORY;
+ return NULL;
+ }
+/* END MOZILLA CHANGE */
+ newBuf = (char *)MALLOC(parser, bufferSize);
if (newBuf == 0) {
- errorCode = XML_ERROR_NO_MEMORY;
+ parser->m_errorCode = XML_ERROR_NO_MEMORY;
return NULL;
}
- bufferLim = newBuf + bufferSize;
+ parser->m_bufferLim = newBuf + bufferSize;
#ifdef XML_CONTEXT_BYTES
- if (bufferPtr) {
- int keep = (int)(bufferPtr - buffer);
+ if (parser->m_bufferPtr) {
+ int keep = (int)(parser->m_bufferPtr - parser->m_buffer);
if (keep > XML_CONTEXT_BYTES)
keep = XML_CONTEXT_BYTES;
- memcpy(newBuf, &bufferPtr[-keep], bufferEnd - bufferPtr + keep);
- FREE(buffer);
- buffer = newBuf;
- bufferEnd = buffer + (bufferEnd - bufferPtr) + keep;
- bufferPtr = buffer + keep;
+ memcpy(newBuf, &parser->m_bufferPtr[-keep], parser->m_bufferEnd - parser->m_bufferPtr + keep);
+ FREE(parser, parser->m_buffer);
+ parser->m_buffer = newBuf;
+ parser->m_bufferEnd = parser->m_buffer + (parser->m_bufferEnd - parser->m_bufferPtr) + keep;
+ parser->m_bufferPtr = parser->m_buffer + keep;
}
else {
- bufferEnd = newBuf + (bufferEnd - bufferPtr);
- bufferPtr = buffer = newBuf;
+ parser->m_bufferEnd = newBuf + (parser->m_bufferEnd - parser->m_bufferPtr);
+ parser->m_bufferPtr = parser->m_buffer = newBuf;
}
#else
- if (bufferPtr) {
- memcpy(newBuf, bufferPtr, bufferEnd - bufferPtr);
- FREE(buffer);
+ if (parser->m_bufferPtr) {
+ memcpy(newBuf, parser->m_bufferPtr, parser->m_bufferEnd - parser->m_bufferPtr);
+ FREE(parser, parser->m_buffer);
}
- bufferEnd = newBuf + (bufferEnd - bufferPtr);
- bufferPtr = buffer = newBuf;
+ parser->m_bufferEnd = newBuf + (parser->m_bufferEnd - parser->m_bufferPtr);
+ parser->m_bufferPtr = parser->m_buffer = newBuf;
#endif /* not defined XML_CONTEXT_BYTES */
}
- eventPtr = eventEndPtr = NULL;
- positionPtr = NULL;
+ parser->m_eventPtr = parser->m_eventEndPtr = NULL;
+ parser->m_positionPtr = NULL;
}
- return bufferEnd;
+ return parser->m_bufferEnd;
}
enum XML_Status XMLCALL
XML_StopParser(XML_Parser parser, XML_Bool resumable)
{
- switch (ps_parsing) {
+ switch (parser->m_parsingStatus.parsing) {
case XML_SUSPENDED:
if (resumable) {
- errorCode = XML_ERROR_SUSPENDED;
+ parser->m_errorCode = XML_ERROR_SUSPENDED;
return XML_STATUS_ERROR;
}
- ps_parsing = XML_FINISHED;
+ parser->m_parsingStatus.parsing = XML_FINISHED;
break;
case XML_FINISHED:
- errorCode = XML_ERROR_FINISHED;
+ parser->m_errorCode = XML_ERROR_FINISHED;
return XML_STATUS_ERROR;
default:
if (resumable) {
#ifdef XML_DTD
- if (isParamEntity) {
- errorCode = XML_ERROR_SUSPEND_PE;
+ if (parser->m_isParamEntity) {
+ parser->m_errorCode = XML_ERROR_SUSPEND_PE;
return XML_STATUS_ERROR;
}
#endif
- ps_parsing = XML_SUSPENDED;
+ parser->m_parsingStatus.parsing = XML_SUSPENDED;
}
else
- ps_parsing = XML_FINISHED;
+ parser->m_parsingStatus.parsing = XML_FINISHED;
}
return XML_STATUS_OK;
}
@@ -1781,36 +1767,36 @@ XML_ResumeParser(XML_Parser parser)
{
enum XML_Status result = XML_STATUS_OK;
- if (ps_parsing != XML_SUSPENDED) {
- errorCode = XML_ERROR_NOT_SUSPENDED;
+ if (parser->m_parsingStatus.parsing != XML_SUSPENDED) {
+ parser->m_errorCode = XML_ERROR_NOT_SUSPENDED;
return XML_STATUS_ERROR;
}
- ps_parsing = XML_PARSING;
+ parser->m_parsingStatus.parsing = XML_PARSING;
- errorCode = processor(parser, bufferPtr, parseEndPtr, &bufferPtr);
+ parser->m_errorCode = parser->m_processor(parser, parser->m_bufferPtr, parser->m_parseEndPtr, &parser->m_bufferPtr);
- if (errorCode != XML_ERROR_NONE) {
- eventEndPtr = eventPtr;
- processor = errorProcessor;
+ if (parser->m_errorCode != XML_ERROR_NONE) {
+ parser->m_eventEndPtr = parser->m_eventPtr;
+ parser->m_processor = errorProcessor;
return XML_STATUS_ERROR;
}
else {
- switch (ps_parsing) {
+ switch (parser->m_parsingStatus.parsing) {
case XML_SUSPENDED:
result = XML_STATUS_SUSPENDED;
break;
case XML_INITIALIZED:
case XML_PARSING:
- if (ps_finalBuffer) {
- ps_parsing = XML_FINISHED;
+ if (parser->m_parsingStatus.finalBuffer) {
+ parser->m_parsingStatus.parsing = XML_FINISHED;
return result;
}
default: ;
}
}
- XmlUpdatePosition(encoding, positionPtr, bufferPtr, &position);
- positionPtr = bufferPtr;
+ XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, parser->m_bufferPtr, &parser->m_position);
+ parser->m_positionPtr = parser->m_bufferPtr;
return result;
}
@@ -1824,22 +1810,22 @@ XML_GetParsingStatus(XML_Parser parser, XML_ParsingStatus *status)
enum XML_Error XMLCALL
XML_GetErrorCode(XML_Parser parser)
{
- return errorCode;
+ return parser->m_errorCode;
}
XML_Index XMLCALL
XML_GetCurrentByteIndex(XML_Parser parser)
{
- if (eventPtr)
- return (XML_Index) (parseEndByteIndex - (parseEndPtr - eventPtr));
+ if (parser->m_eventPtr)
+ return (XML_Index) (parser->m_parseEndByteIndex - (parser->m_parseEndPtr - parser->m_eventPtr));
return -1;
}
int XMLCALL
XML_GetCurrentByteCount(XML_Parser parser)
{
- if (eventEndPtr && eventPtr)
- return (int)(eventEndPtr - eventPtr);
+ if (parser->m_eventEndPtr && parser->m_eventPtr)
+ return (int)(parser->m_eventEndPtr - parser->m_eventPtr);
return 0;
}
@@ -1847,10 +1833,10 @@ const char * XMLCALL
XML_GetInputContext(XML_Parser parser, int *offset, int *size)
{
#ifdef XML_CONTEXT_BYTES
- if (eventPtr && buffer) {
- *offset = (int)(eventPtr - buffer);
- *size = (int)(bufferEnd - buffer);
- return buffer;
+ if (parser->m_eventPtr && parser->m_buffer) {
+ *offset = (int)(parser->m_eventPtr - parser->m_buffer);
+ *size = (int)(parser->m_bufferEnd - parser->m_buffer);
+ return parser->m_buffer;
}
#endif /* defined XML_CONTEXT_BYTES */
return (char *) 0;
@@ -1859,58 +1845,58 @@ XML_GetInputContext(XML_Parser parser, int *offset, int *size)
XML_Size XMLCALL
XML_GetCurrentLineNumber(XML_Parser parser)
{
- if (eventPtr && eventPtr >= positionPtr) {
- XmlUpdatePosition(encoding, positionPtr, eventPtr, &position);
- positionPtr = eventPtr;
+ if (parser->m_eventPtr && parser->m_eventPtr >= parser->m_positionPtr) {
+ XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, parser->m_eventPtr, &parser->m_position);
+ parser->m_positionPtr = parser->m_eventPtr;
}
- return position.lineNumber + 1;
+ return parser->m_position.lineNumber + 1;
}
XML_Size XMLCALL
XML_GetCurrentColumnNumber(XML_Parser parser)
{
- if (eventPtr && eventPtr >= positionPtr) {
- XmlUpdatePosition(encoding, positionPtr, eventPtr, &position);
- positionPtr = eventPtr;
+ if (parser->m_eventPtr && parser->m_eventPtr >= parser->m_positionPtr) {
+ XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, parser->m_eventPtr, &parser->m_position);
+ parser->m_positionPtr = parser->m_eventPtr;
}
- return position.columnNumber;
+ return parser->m_position.columnNumber;
}
void XMLCALL
XML_FreeContentModel(XML_Parser parser, XML_Content *model)
{
- FREE(model);
+ FREE(parser, model);
}
void * XMLCALL
XML_MemMalloc(XML_Parser parser, size_t size)
{
- return MALLOC(size);
+ return MALLOC(parser, size);
}
void * XMLCALL
XML_MemRealloc(XML_Parser parser, void *ptr, size_t size)
{
- return REALLOC(ptr, size);
+ return REALLOC(parser, ptr, size);
}
void XMLCALL
XML_MemFree(XML_Parser parser, void *ptr)
{
- FREE(ptr);
+ FREE(parser, ptr);
}
void XMLCALL
XML_DefaultCurrent(XML_Parser parser)
{
- if (defaultHandler) {
- if (openInternalEntities)
+ if (parser->m_defaultHandler) {
+ if (parser->m_openInternalEntities)
reportDefault(parser,
- internalEncoding,
- openInternalEntities->internalEventPtr,
- openInternalEntities->internalEventEndPtr);
+ parser->m_internalEncoding,
+ parser->m_openInternalEntities->internalEventPtr,
+ parser->m_openInternalEntities->internalEventEndPtr);
else
- reportDefault(parser, encoding, eventPtr, eventEndPtr);
+ reportDefault(parser, parser->m_encoding, parser->m_eventPtr, parser->m_eventEndPtr);
}
}
@@ -1958,7 +1944,8 @@ XML_ErrorString(enum XML_Error code)
XML_L("cannot suspend in external parameter entity"),
XML_L("reserved prefix (xml) must not be undeclared or bound to another namespace name"),
XML_L("reserved prefix (xmlns) must not be declared or undeclared"),
- XML_L("prefix must not be bound to one of the reserved namespace names")
+ XML_L("prefix must not be bound to one of the reserved namespace names"),
+ XML_L("invalid argument")
};
if (code > 0 && code < sizeof(message)/sizeof(message[0]))
return message[code];
@@ -2044,12 +2031,13 @@ XML_GetFeatureList(void)
static XML_Bool
storeRawNames(XML_Parser parser)
{
- TAG *tag = tagStack;
+ TAG *tag = parser->m_tagStack;
while (tag) {
int bufSize;
int nameLen = sizeof(XML_Char) * (tag->name.strLen + 1);
+ size_t rawNameLen;
char *rawNameBuf = tag->buf + nameLen;
- /* Stop if already stored. Since tagStack is a stack, we can stop
+ /* Stop if already stored. Since m_tagStack is a stack, we can stop
at the first entry that has already been copied; everything
below it in the stack is already been accounted for in a
previous call to this function.
@@ -2059,9 +2047,13 @@ storeRawNames(XML_Parser parser)
/* For re-use purposes we need to ensure that the
size of tag->buf is a multiple of sizeof(XML_Char).
*/
- bufSize = nameLen + ROUND_UP(tag->rawNameLength, sizeof(XML_Char));
+ rawNameLen = ROUND_UP(tag->rawNameLength, sizeof(XML_Char));
+ /* Detect and prevent integer overflow. */
+ if (rawNameLen > (size_t)INT_MAX - nameLen)
+ return XML_FALSE;
+ bufSize = nameLen + (int)rawNameLen;
if (bufSize > tag->bufEnd - tag->buf) {
- char *temp = (char *)REALLOC(tag->buf, bufSize);
+ char *temp = (char *)REALLOC(parser, tag->buf, bufSize);
if (temp == NULL)
return XML_FALSE;
/* if tag->name.str points to tag->buf (only when namespace
@@ -2092,8 +2084,8 @@ contentProcessor(XML_Parser parser,
const char *end,
const char **endPtr)
{
- enum XML_Error result = doContent(parser, 0, encoding, start, end,
- endPtr, (XML_Bool)!ps_finalBuffer);
+ enum XML_Error result = doContent(parser, 0, parser->m_encoding, start, end,
+ endPtr, (XML_Bool)!parser->m_parsingStatus.finalBuffer);
if (result == XML_ERROR_NONE) {
if (!storeRawNames(parser))
return XML_ERROR_NO_MEMORY;
@@ -2110,7 +2102,7 @@ externalEntityInitProcessor(XML_Parser parser,
enum XML_Error result = initializeEncoding(parser);
if (result != XML_ERROR_NONE)
return result;
- processor = externalEntityInitProcessor2;
+ parser->m_processor = externalEntityInitProcessor2;
return externalEntityInitProcessor2(parser, start, end, endPtr);
}
@@ -2121,7 +2113,7 @@ externalEntityInitProcessor2(XML_Parser parser,
const char **endPtr)
{
const char *next = start; /* XmlContentTok doesn't always set the last arg */
- int tok = XmlContentTok(encoding, start, end, &next);
+ int tok = XmlContentTok(parser->m_encoding, start, end, &next);
switch (tok) {
case XML_TOK_BOM:
/* If we are at the end of the buffer, this would cause the next stage,
@@ -2129,28 +2121,28 @@ externalEntityInitProcessor2(XML_Parser parser,
doContent (by detecting XML_TOK_NONE) without processing any xml text
declaration - causing the error XML_ERROR_MISPLACED_XML_PI in doContent.
*/
- if (next == end && !ps_finalBuffer) {
+ if (next == end && !parser->m_parsingStatus.finalBuffer) {
*endPtr = next;
return XML_ERROR_NONE;
}
start = next;
break;
case XML_TOK_PARTIAL:
- if (!ps_finalBuffer) {
+ if (!parser->m_parsingStatus.finalBuffer) {
*endPtr = start;
return XML_ERROR_NONE;
}
- eventPtr = start;
+ parser->m_eventPtr = start;
return XML_ERROR_UNCLOSED_TOKEN;
case XML_TOK_PARTIAL_CHAR:
- if (!ps_finalBuffer) {
+ if (!parser->m_parsingStatus.finalBuffer) {
*endPtr = start;
return XML_ERROR_NONE;
}
- eventPtr = start;
+ parser->m_eventPtr = start;
return XML_ERROR_PARTIAL_CHAR;
}
- processor = externalEntityInitProcessor3;
+ parser->m_processor = externalEntityInitProcessor3;
return externalEntityInitProcessor3(parser, start, end, endPtr);
}
@@ -2162,9 +2154,9 @@ externalEntityInitProcessor3(XML_Parser parser,
{
int tok;
const char *next = start; /* XmlContentTok doesn't always set the last arg */
- eventPtr = start;
- tok = XmlContentTok(encoding, start, end, &next);
- eventEndPtr = next;
+ parser->m_eventPtr = start;
+ tok = XmlContentTok(parser->m_encoding, start, end, &next);
+ parser->m_eventEndPtr = next;
switch (tok) {
case XML_TOK_XML_DECL:
@@ -2173,7 +2165,7 @@ externalEntityInitProcessor3(XML_Parser parser,
result = processXmlDecl(parser, 1, start, next);
if (result != XML_ERROR_NONE)
return result;
- switch (ps_parsing) {
+ switch (parser->m_parsingStatus.parsing) {
case XML_SUSPENDED:
*endPtr = next;
return XML_ERROR_NONE;
@@ -2185,20 +2177,20 @@ externalEntityInitProcessor3(XML_Parser parser,
}
break;
case XML_TOK_PARTIAL:
- if (!ps_finalBuffer) {
+ if (!parser->m_parsingStatus.finalBuffer) {
*endPtr = start;
return XML_ERROR_NONE;
}
return XML_ERROR_UNCLOSED_TOKEN;
case XML_TOK_PARTIAL_CHAR:
- if (!ps_finalBuffer) {
+ if (!parser->m_parsingStatus.finalBuffer) {
*endPtr = start;
return XML_ERROR_NONE;
}
return XML_ERROR_PARTIAL_CHAR;
}
- processor = externalEntityContentProcessor;
- tagLevel = 1;
+ parser->m_processor = externalEntityContentProcessor;
+ parser->m_tagLevel = 1;
return externalEntityContentProcessor(parser, start, end, endPtr);
}
@@ -2208,8 +2200,8 @@ externalEntityContentProcessor(XML_Parser parser,
const char *end,
const char **endPtr)
{
- enum XML_Error result = doContent(parser, 1, encoding, start, end,
- endPtr, (XML_Bool)!ps_finalBuffer);
+ enum XML_Error result = doContent(parser, 1, parser->m_encoding, start, end,
+ endPtr, (XML_Bool)!parser->m_parsingStatus.finalBuffer);
if (result == XML_ERROR_NONE) {
if (!storeRawNames(parser))
return XML_ERROR_NO_MEMORY;
@@ -2227,17 +2219,17 @@ doContent(XML_Parser parser,
XML_Bool haveMore)
{
/* save one level of indirection */
- DTD * const dtd = _dtd;
+ DTD * const dtd = parser->m_dtd;
const char **eventPP;
const char **eventEndPP;
- if (enc == encoding) {
- eventPP = &eventPtr;
- eventEndPP = &eventEndPtr;
+ if (enc == parser->m_encoding) {
+ eventPP = &parser->m_eventPtr;
+ eventEndPP = &parser->m_eventEndPtr;
}
else {
- eventPP = &(openInternalEntities->internalEventPtr);
- eventEndPP = &(openInternalEntities->internalEventEndPtr);
+ eventPP = &(parser->m_openInternalEntities->internalEventPtr);
+ eventEndPP = &(parser->m_openInternalEntities->internalEventEndPtr);
}
*eventPP = s;
@@ -2252,18 +2244,18 @@ doContent(XML_Parser parser,
return XML_ERROR_NONE;
}
*eventEndPP = end;
- if (characterDataHandler) {
+ if (parser->m_characterDataHandler) {
XML_Char c = 0xA;
- characterDataHandler(handlerArg, &c, 1);
+ parser->m_characterDataHandler(parser->m_handlerArg, &c, 1);
}
- else if (defaultHandler)
+ else if (parser->m_defaultHandler)
reportDefault(parser, enc, s, end);
/* We are at the end of the final buffer, should we check for
XML_SUSPENDED, XML_FINISHED?
*/
if (startTagLevel == 0)
return XML_ERROR_NO_ELEMENTS;
- if (tagLevel != startTagLevel)
+ if (parser->m_tagLevel != startTagLevel)
return XML_ERROR_ASYNC_ENTITY;
*nextPtr = end;
return XML_ERROR_NONE;
@@ -2273,7 +2265,7 @@ doContent(XML_Parser parser,
return XML_ERROR_NONE;
}
if (startTagLevel > 0) {
- if (tagLevel != startTagLevel)
+ if (parser->m_tagLevel != startTagLevel)
return XML_ERROR_ASYNC_ENTITY;
*nextPtr = s;
return XML_ERROR_NONE;
@@ -2302,9 +2294,9 @@ doContent(XML_Parser parser,
s + enc->minBytesPerChar,
next - enc->minBytesPerChar);
if (ch) {
- if (characterDataHandler)
- characterDataHandler(handlerArg, &ch, 1);
- else if (defaultHandler)
+ if (parser->m_characterDataHandler)
+ parser->m_characterDataHandler(parser->m_handlerArg, &ch, 1);
+ else if (parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
break;
}
@@ -2326,9 +2318,9 @@ doContent(XML_Parser parser,
return XML_ERROR_ENTITY_DECLARED_IN_PE;
}
else if (!entity) {
- if (skippedEntityHandler)
- skippedEntityHandler(handlerArg, name, 0);
- else if (defaultHandler)
+ if (parser->m_skippedEntityHandler)
+ parser->m_skippedEntityHandler(parser->m_handlerArg, name, 0);
+ else if (parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
break;
}
@@ -2338,10 +2330,10 @@ doContent(XML_Parser parser,
return XML_ERROR_BINARY_ENTITY_REF;
if (entity->textPtr) {
enum XML_Error result;
- if (!defaultExpandInternalEntities) {
- if (skippedEntityHandler)
- skippedEntityHandler(handlerArg, entity->name, 0);
- else if (defaultHandler)
+ if (!parser->m_defaultExpandInternalEntities) {
+ if (parser->m_skippedEntityHandler)
+ parser->m_skippedEntityHandler(parser->m_handlerArg, entity->name, 0);
+ else if (parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
break;
}
@@ -2349,22 +2341,22 @@ doContent(XML_Parser parser,
if (result != XML_ERROR_NONE)
return result;
}
- else if (externalEntityRefHandler) {
+ else if (parser->m_externalEntityRefHandler) {
const XML_Char *context;
entity->open = XML_TRUE;
context = getContext(parser);
entity->open = XML_FALSE;
if (!context)
return XML_ERROR_NO_MEMORY;
- if (!externalEntityRefHandler(externalEntityRefHandlerArg,
+ if (!parser->m_externalEntityRefHandler(parser->m_externalEntityRefHandlerArg,
context,
entity->base,
entity->systemId,
entity->publicId))
return XML_ERROR_EXTERNAL_ENTITY_HANDLING;
- poolDiscard(&tempPool);
+ poolDiscard(&parser->m_tempPool);
}
- else if (defaultHandler)
+ else if (parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
break;
}
@@ -2375,29 +2367,29 @@ doContent(XML_Parser parser,
TAG *tag;
enum XML_Error result;
XML_Char *toPtr;
- if (freeTagList) {
- tag = freeTagList;
- freeTagList = freeTagList->parent;
+ if (parser->m_freeTagList) {
+ tag = parser->m_freeTagList;
+ parser->m_freeTagList = parser->m_freeTagList->parent;
}
else {
- tag = (TAG *)MALLOC(sizeof(TAG));
+ tag = (TAG *)MALLOC(parser, sizeof(TAG));
if (!tag)
return XML_ERROR_NO_MEMORY;
- tag->buf = (char *)MALLOC(INIT_TAG_BUF_SIZE);
+ tag->buf = (char *)MALLOC(parser, INIT_TAG_BUF_SIZE);
if (!tag->buf) {
- FREE(tag);
+ FREE(parser, tag);
return XML_ERROR_NO_MEMORY;
}
tag->bufEnd = tag->buf + INIT_TAG_BUF_SIZE;
}
tag->bindings = NULL;
- tag->parent = tagStack;
- tagStack = tag;
+ tag->parent = parser->m_tagStack;
+ parser->m_tagStack = tag;
tag->name.localPart = NULL;
tag->name.prefix = NULL;
tag->rawName = s + enc->minBytesPerChar;
tag->rawNameLength = XmlNameLength(enc, tag->rawName);
- ++tagLevel;
+ ++parser->m_tagLevel;
{
const char *rawNameEnd = tag->rawName + tag->rawNameLength;
const char *fromPtr = tag->rawName;
@@ -2405,17 +2397,17 @@ doContent(XML_Parser parser,
for (;;) {
int bufSize;
int convLen;
- XmlConvert(enc,
+ const enum XML_Convert_Result convert_res = XmlConvert(enc,
&fromPtr, rawNameEnd,
(ICHAR **)&toPtr, (ICHAR *)tag->bufEnd - 1);
convLen = (int)(toPtr - (XML_Char *)tag->buf);
- if (fromPtr == rawNameEnd) {
+ if ((convert_res == XML_CONVERT_COMPLETED) || (convert_res == XML_CONVERT_INPUT_INCOMPLETE)) {
tag->name.strLen = convLen;
break;
}
bufSize = (int)(tag->bufEnd - tag->buf) << 1;
{
- char *temp = (char *)REALLOC(tag->buf, bufSize);
+ char *temp = (char *)REALLOC(parser, tag->buf, bufSize);
if (temp == NULL)
return XML_ERROR_NO_MEMORY;
tag->buf = temp;
@@ -2429,12 +2421,12 @@ doContent(XML_Parser parser,
result = storeAtts(parser, enc, s, &(tag->name), &(tag->bindings));
if (result)
return result;
- if (startElementHandler)
- startElementHandler(handlerArg, tag->name.str,
- (const XML_Char **)atts);
- else if (defaultHandler)
+ if (parser->m_startElementHandler)
+ parser->m_startElementHandler(parser->m_handlerArg, tag->name.str,
+ (const XML_Char **)parser->m_atts);
+ else if (parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
- poolClear(&tempPool);
+ poolClear(&parser->m_tempPool);
break;
}
case XML_TOK_EMPTY_ELEMENT_NO_ATTS:
@@ -2446,51 +2438,48 @@ doContent(XML_Parser parser,
BINDING *bindings = NULL;
XML_Bool noElmHandlers = XML_TRUE;
TAG_NAME name;
- name.str = poolStoreString(&tempPool, enc, rawName,
+ name.str = poolStoreString(&parser->m_tempPool, enc, rawName,
rawName + XmlNameLength(enc, rawName));
if (!name.str)
return XML_ERROR_NO_MEMORY;
- poolFinish(&tempPool);
+ poolFinish(&parser->m_tempPool);
result = storeAtts(parser, enc, s, &name, &bindings);
if (result)
return result;
- poolFinish(&tempPool);
- if (startElementHandler) {
- startElementHandler(handlerArg, name.str, (const XML_Char **)atts);
+ poolFinish(&parser->m_tempPool);
+ if (parser->m_startElementHandler) {
+ parser->m_startElementHandler(parser->m_handlerArg, name.str, (const XML_Char **)parser->m_atts);
noElmHandlers = XML_FALSE;
}
- if (endElementHandler) {
- if (startElementHandler)
+ if (parser->m_endElementHandler) {
+ if (parser->m_startElementHandler)
*eventPP = *eventEndPP;
- endElementHandler(handlerArg, name.str);
+ parser->m_endElementHandler(parser->m_handlerArg, name.str);
noElmHandlers = XML_FALSE;
}
- if (noElmHandlers && defaultHandler)
+ if (noElmHandlers && parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
- poolClear(&tempPool);
+ poolClear(&parser->m_tempPool);
while (bindings) {
BINDING *b = bindings;
- if (endNamespaceDeclHandler)
- endNamespaceDeclHandler(handlerArg, b->prefix->name);
+ if (parser->m_endNamespaceDeclHandler)
+ parser->m_endNamespaceDeclHandler(parser->m_handlerArg, b->prefix->name);
bindings = bindings->nextTagBinding;
- b->nextTagBinding = freeBindingList;
- freeBindingList = b;
+ b->nextTagBinding = parser->m_freeBindingList;
+ parser->m_freeBindingList = b;
b->prefix->binding = b->prevPrefixBinding;
}
}
- if (tagLevel == 0)
+ if (parser->m_tagLevel == 0)
return epilogProcessor(parser, next, end, nextPtr);
break;
case XML_TOK_END_TAG:
- if (tagLevel == startTagLevel)
+ if (parser->m_tagLevel == startTagLevel)
return XML_ERROR_ASYNC_ENTITY;
else {
int len;
const char *rawName;
- TAG *tag = tagStack;
- tagStack = tag->parent;
- tag->parent = freeTagList;
- freeTagList = tag;
+ TAG *tag = parser->m_tagStack;
rawName = s + enc->minBytesPerChar*2;
len = XmlNameLength(enc, rawName);
if (len != tag->rawNameLength
@@ -2498,13 +2487,16 @@ doContent(XML_Parser parser,
*eventPP = rawName;
return XML_ERROR_TAG_MISMATCH;
}
- --tagLevel;
- if (endElementHandler) {
+ parser->m_tagStack = tag->parent;
+ tag->parent = parser->m_freeTagList;
+ parser->m_freeTagList = tag;
+ --parser->m_tagLevel;
+ if (parser->m_endElementHandler) {
const XML_Char *localPart;
const XML_Char *prefix;
XML_Char *uri;
localPart = tag->name.localPart;
- if (ns && localPart) {
+ if (parser->m_ns && localPart) {
/* localPart and prefix may have been overwritten in
tag->name.str, since this points to the binding->uri
buffer which gets re-used; so we have to add them again
@@ -2513,26 +2505,26 @@ doContent(XML_Parser parser,
/* don't need to check for space - already done in storeAtts() */
while (*localPart) *uri++ = *localPart++;
prefix = (XML_Char *)tag->name.prefix;
- if (ns_triplets && prefix) {
- *uri++ = namespaceSeparator;
+ if (parser->m_ns_triplets && prefix) {
+ *uri++ = parser->m_namespaceSeparator;
while (*prefix) *uri++ = *prefix++;
}
*uri = XML_T('\0');
}
- endElementHandler(handlerArg, tag->name.str);
+ parser->m_endElementHandler(parser->m_handlerArg, tag->name.str);
}
- else if (defaultHandler)
+ else if (parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
while (tag->bindings) {
BINDING *b = tag->bindings;
- if (endNamespaceDeclHandler)
- endNamespaceDeclHandler(handlerArg, b->prefix->name);
+ if (parser->m_endNamespaceDeclHandler)
+ parser->m_endNamespaceDeclHandler(parser->m_handlerArg, b->prefix->name);
tag->bindings = tag->bindings->nextTagBinding;
- b->nextTagBinding = freeBindingList;
- freeBindingList = b;
+ b->nextTagBinding = parser->m_freeBindingList;
+ parser->m_freeBindingList = b;
b->prefix->binding = b->prevPrefixBinding;
}
- if (tagLevel == 0)
+ if (parser->m_tagLevel == 0)
return epilogProcessor(parser, next, end, nextPtr);
}
break;
@@ -2541,29 +2533,29 @@ doContent(XML_Parser parser,
int n = XmlCharRefNumber(enc, s);
if (n < 0)
return XML_ERROR_BAD_CHAR_REF;
- if (characterDataHandler) {
+ if (parser->m_characterDataHandler) {
XML_Char buf[XML_ENCODE_MAX];
- characterDataHandler(handlerArg, buf, XmlEncode(n, (ICHAR *)buf));
+ parser->m_characterDataHandler(parser->m_handlerArg, buf, XmlEncode(n, (ICHAR *)buf));
}
- else if (defaultHandler)
+ else if (parser->m_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) {
+ if (parser->m_characterDataHandler) {
XML_Char c = 0xA;
- characterDataHandler(handlerArg, &c, 1);
+ parser->m_characterDataHandler(parser->m_handlerArg, &c, 1);
}
- else if (defaultHandler)
+ else if (parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
break;
case XML_TOK_CDATA_SECT_OPEN:
{
enum XML_Error result;
- if (startCdataSectionHandler)
- startCdataSectionHandler(handlerArg);
+ if (parser->m_startCdataSectionHandler)
+ parser->m_startCdataSectionHandler(parser->m_handlerArg);
#if 0
/* Suppose you doing a transformation on a document that involves
changing only the character data. You set up a defaultHandler
@@ -2577,16 +2569,16 @@ doContent(XML_Parser parser,
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);
+ else if (parser->m_characterDataHandler)
+ parser->m_characterDataHandler(parser->m_handlerArg, parser->m_dataBuf, 0);
#endif
- else if (defaultHandler)
+ else if (parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
result = doCdataSection(parser, enc, &next, end, nextPtr, haveMore);
if (result != XML_ERROR_NONE)
return result;
else if (!next) {
- processor = cdataSectionProcessor;
+ parser->m_processor = cdataSectionProcessor;
return result;
}
}
@@ -2596,19 +2588,19 @@ doContent(XML_Parser parser,
*nextPtr = s;
return XML_ERROR_NONE;
}
- if (characterDataHandler) {
+ if (parser->m_characterDataHandler) {
if (MUST_CONVERT(enc, s)) {
- ICHAR *dataPtr = (ICHAR *)dataBuf;
- XmlConvert(enc, &s, end, &dataPtr, (ICHAR *)dataBufEnd);
- characterDataHandler(handlerArg, dataBuf,
- (int)(dataPtr - (ICHAR *)dataBuf));
+ ICHAR *dataPtr = (ICHAR *)parser->m_dataBuf;
+ XmlConvert(enc, &s, end, &dataPtr, (ICHAR *)parser->m_dataBufEnd);
+ parser->m_characterDataHandler(parser->m_handlerArg, parser->m_dataBuf,
+ (int)(dataPtr - (ICHAR *)parser->m_dataBuf));
}
else
- characterDataHandler(handlerArg,
+ parser->m_characterDataHandler(parser->m_handlerArg,
(XML_Char *)s,
(int)((XML_Char *)end - (XML_Char *)s));
}
- else if (defaultHandler)
+ else if (parser->m_defaultHandler)
reportDefault(parser, enc, s, end);
/* We are at the end of the final buffer, should we check for
XML_SUSPENDED, XML_FINISHED?
@@ -2617,7 +2609,7 @@ doContent(XML_Parser parser,
*eventPP = end;
return XML_ERROR_NO_ELEMENTS;
}
- if (tagLevel != startTagLevel) {
+ if (parser->m_tagLevel != startTagLevel) {
*eventPP = end;
return XML_ERROR_ASYNC_ENTITY;
}
@@ -2625,26 +2617,26 @@ doContent(XML_Parser parser,
return XML_ERROR_NONE;
case XML_TOK_DATA_CHARS:
{
- XML_CharacterDataHandler charDataHandler = characterDataHandler;
+ XML_CharacterDataHandler charDataHandler = parser->m_characterDataHandler;
if (charDataHandler) {
if (MUST_CONVERT(enc, s)) {
for (;;) {
- ICHAR *dataPtr = (ICHAR *)dataBuf;
- XmlConvert(enc, &s, next, &dataPtr, (ICHAR *)dataBufEnd);
+ ICHAR *dataPtr = (ICHAR *)parser->m_dataBuf;
+ const enum XML_Convert_Result convert_res = XmlConvert(enc, &s, next, &dataPtr, (ICHAR *)parser->m_dataBufEnd);
*eventEndPP = s;
- charDataHandler(handlerArg, dataBuf,
- (int)(dataPtr - (ICHAR *)dataBuf));
- if (s == next)
+ charDataHandler(parser->m_handlerArg, parser->m_dataBuf,
+ (int)(dataPtr - (ICHAR *)parser->m_dataBuf));
+ if ((convert_res == XML_CONVERT_COMPLETED) || (convert_res == XML_CONVERT_INPUT_INCOMPLETE))
break;
*eventPP = s;
}
}
else
- charDataHandler(handlerArg,
+ charDataHandler(parser->m_handlerArg,
(XML_Char *)s,
(int)((XML_Char *)next - (XML_Char *)s));
}
- else if (defaultHandler)
+ else if (parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
}
break;
@@ -2657,12 +2649,12 @@ doContent(XML_Parser parser,
return XML_ERROR_NO_MEMORY;
break;
default:
- if (defaultHandler)
+ if (parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
break;
}
*eventPP = s = next;
- switch (ps_parsing) {
+ switch (parser->m_parsingStatus.parsing) {
case XML_SUSPENDED:
*nextPtr = next;
return XML_ERROR_NONE;
@@ -2689,7 +2681,7 @@ storeAtts(XML_Parser parser, const ENCODING *enc,
const char *attStr, TAG_NAME *tagNamePtr,
BINDING **bindingsPtr)
{
- DTD * const dtd = _dtd; /* save one level of indirection */
+ DTD * const dtd = parser->m_dtd; /* save one level of indirection */
ELEMENT_TYPE *elementType;
int nDefaultAtts;
const XML_Char **appAtts; /* the attribute list for the application */
@@ -2712,39 +2704,75 @@ storeAtts(XML_Parser parser, const ENCODING *enc,
sizeof(ELEMENT_TYPE));
if (!elementType)
return XML_ERROR_NO_MEMORY;
- if (ns && !setElementTypePrefix(parser, elementType))
+ if (parser->m_ns && !setElementTypePrefix(parser, elementType))
return XML_ERROR_NO_MEMORY;
}
nDefaultAtts = elementType->nDefaultAtts;
/* get the attributes from the tokenizer */
- n = XmlGetAttributes(enc, attStr, attsSize, atts);
- if (n + nDefaultAtts > attsSize) {
- int oldAttsSize = attsSize;
+ n = XmlGetAttributes(enc, attStr, parser->m_attsSize, parser->m_atts);
+
+ /* Detect and prevent integer overflow */
+ if (n > INT_MAX - nDefaultAtts) {
+ return XML_ERROR_NO_MEMORY;
+ }
+
+ if (n + nDefaultAtts > parser->m_attsSize) {
+ int oldAttsSize = parser->m_attsSize;
ATTRIBUTE *temp;
#ifdef XML_ATTR_INFO
XML_AttrInfo *temp2;
#endif
- attsSize = n + nDefaultAtts + INIT_ATTS_SIZE;
- temp = (ATTRIBUTE *)REALLOC((void *)atts, attsSize * sizeof(ATTRIBUTE));
+
+ /* Detect and prevent integer overflow */
+ if ((nDefaultAtts > INT_MAX - INIT_ATTS_SIZE)
+ || (n > INT_MAX - (nDefaultAtts + INIT_ATTS_SIZE))) {
+ return XML_ERROR_NO_MEMORY;
+ }
+
+ parser->m_attsSize = n + nDefaultAtts + INIT_ATTS_SIZE;
+
+ /* Detect and prevent integer overflow.
+ * The preprocessor guard addresses the "always false" warning
+ * from -Wtype-limits on platforms where
+ * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */
+#if UINT_MAX >= SIZE_MAX
+ if ((unsigned)parser->m_attsSize > (size_t)(-1) / sizeof(ATTRIBUTE)) {
+ parser->m_attsSize = oldAttsSize;
+ return XML_ERROR_NO_MEMORY;
+ }
+#endif
+
+ temp = (ATTRIBUTE *)REALLOC(parser, (void *)parser->m_atts, parser->m_attsSize * sizeof(ATTRIBUTE));
if (temp == NULL)
return XML_ERROR_NO_MEMORY;
- atts = temp;
+ parser->m_atts = temp;
#ifdef XML_ATTR_INFO
- temp2 = (XML_AttrInfo *)REALLOC((void *)attInfo, attsSize * sizeof(XML_AttrInfo));
+ /* Detect and prevent integer overflow.
+ * The preprocessor guard addresses the "always false" warning
+ * from -Wtype-limits on platforms where
+ * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */
+# if UINT_MAX >= SIZE_MAX
+ if ((unsigned)parser->m_attsSize > (size_t)(-1) / sizeof(XML_AttrInfo)) {
+ parser->m_attsSize = oldAttsSize;
+ return XML_ERROR_NO_MEMORY;
+ }
+# endif
+
+ temp2 = (XML_AttrInfo *)REALLOC(parser, (void *)parser->m_attInfo, parser->m_attsSize * sizeof(XML_AttrInfo));
if (temp2 == NULL)
return XML_ERROR_NO_MEMORY;
- attInfo = temp2;
+ parser->m_attInfo = temp2;
#endif
if (n > oldAttsSize)
- XmlGetAttributes(enc, attStr, n, atts);
+ XmlGetAttributes(enc, attStr, n, parser->m_atts);
}
- appAtts = (const XML_Char **)atts;
+ appAtts = (const XML_Char **)parser->m_atts;
for (i = 0; i < n; i++) {
- ATTRIBUTE *currAtt = &atts[i];
+ ATTRIBUTE *currAtt = &parser->m_atts[i];
#ifdef XML_ATTR_INFO
- XML_AttrInfo *currAttInfo = &attInfo[i];
+ XML_AttrInfo *currAttInfo = &parser->m_attInfo[i];
#endif
/* add the name and value to the attribute list */
ATTRIBUTE_ID *attId = getAttributeId(parser, enc, currAtt->name,
@@ -2753,25 +2781,25 @@ storeAtts(XML_Parser parser, const ENCODING *enc,
if (!attId)
return XML_ERROR_NO_MEMORY;
#ifdef XML_ATTR_INFO
- currAttInfo->nameStart = parseEndByteIndex - (parseEndPtr - currAtt->name);
+ currAttInfo->nameStart = parser->m_parseEndByteIndex - (parser->m_parseEndPtr - currAtt->name);
currAttInfo->nameEnd = currAttInfo->nameStart +
XmlNameLength(enc, currAtt->name);
- currAttInfo->valueStart = parseEndByteIndex -
- (parseEndPtr - currAtt->valuePtr);
- currAttInfo->valueEnd = parseEndByteIndex - (parseEndPtr - currAtt->valueEnd);
+ currAttInfo->valueStart = parser->m_parseEndByteIndex -
+ (parser->m_parseEndPtr - currAtt->valuePtr);
+ currAttInfo->valueEnd = parser->m_parseEndByteIndex - (parser->m_parseEndPtr - currAtt->valueEnd);
#endif
/* Detect duplicate attributes by their QNames. This does not work when
namespace processing is turned on and different prefixes for the same
namespace are used. For this case we have a check further down.
*/
if ((attId->name)[-1]) {
- if (enc == encoding)
- eventPtr = atts[i].name;
+ if (enc == parser->m_encoding)
+ parser->m_eventPtr = parser->m_atts[i].name;
return XML_ERROR_DUPLICATE_ATTRIBUTE;
}
(attId->name)[-1] = 1;
appAtts[attIndex++] = attId->name;
- if (!atts[i].normalized) {
+ if (!parser->m_atts[i].normalized) {
enum XML_Error result;
XML_Bool isCdata = XML_TRUE;
@@ -2788,20 +2816,20 @@ storeAtts(XML_Parser parser, const ENCODING *enc,
/* normalize the attribute value */
result = storeAttributeValue(parser, enc, isCdata,
- atts[i].valuePtr, atts[i].valueEnd,
- &tempPool);
+ parser->m_atts[i].valuePtr, parser->m_atts[i].valueEnd,
+ &parser->m_tempPool);
if (result)
return result;
- appAtts[attIndex] = poolStart(&tempPool);
- poolFinish(&tempPool);
+ appAtts[attIndex] = poolStart(&parser->m_tempPool);
+ poolFinish(&parser->m_tempPool);
}
else {
/* the value did not need normalizing */
- appAtts[attIndex] = poolStoreString(&tempPool, enc, atts[i].valuePtr,
- atts[i].valueEnd);
+ appAtts[attIndex] = poolStoreString(&parser->m_tempPool, enc, parser->m_atts[i].valuePtr,
+ parser->m_atts[i].valueEnd);
if (appAtts[attIndex] == 0)
return XML_ERROR_NO_MEMORY;
- poolFinish(&tempPool);
+ poolFinish(&parser->m_tempPool);
}
/* handle prefixed attribute names */
if (attId->prefix) {
@@ -2825,16 +2853,16 @@ storeAtts(XML_Parser parser, const ENCODING *enc,
}
/* set-up for XML_GetSpecifiedAttributeCount and XML_GetIdAttributeIndex */
- nSpecifiedAtts = attIndex;
+ parser->m_nSpecifiedAtts = attIndex;
if (elementType->idAtt && (elementType->idAtt->name)[-1]) {
for (i = 0; i < attIndex; i += 2)
if (appAtts[i] == elementType->idAtt->name) {
- idAttIndex = i;
+ parser->m_idAttIndex = i;
break;
}
}
else
- idAttIndex = -1;
+ parser->m_idAttIndex = -1;
/* do attribute defaulting */
for (i = 0; i < nDefaultAtts; i++) {
@@ -2867,30 +2895,58 @@ storeAtts(XML_Parser parser, const ENCODING *enc,
and clear flags that say whether attributes were specified */
i = 0;
if (nPrefixes) {
- int j; /* hash table index */
- unsigned long version = nsAttsVersion;
- int nsAttsSize = (int)1 << nsAttsPower;
+ size_t j; /* hash table index */
+ unsigned long version = parser->m_nsAttsVersion;
+
+ /* Detect and prevent invalid shift */
+ if (parser->m_nsAttsPower >= sizeof(unsigned int) * 8 /* bits per byte */) {
+ return XML_ERROR_NO_MEMORY;
+ }
+
+ unsigned int nsAttsSize = 1u << parser->m_nsAttsPower;
+ unsigned char oldNsAttsPower = parser->m_nsAttsPower;
/* size of hash table must be at least 2 * (# of prefixed attributes) */
- if ((nPrefixes << 1) >> nsAttsPower) { /* true for nsAttsPower = 0 */
+ if ((nPrefixes << 1) >> parser->m_nsAttsPower) { /* true for m_nsAttsPower = 0 */
NS_ATT *temp;
/* hash table size must also be a power of 2 and >= 8 */
- while (nPrefixes >> nsAttsPower++);
- if (nsAttsPower < 3)
- nsAttsPower = 3;
- nsAttsSize = (int)1 << nsAttsPower;
- temp = (NS_ATT *)REALLOC(nsAtts, nsAttsSize * sizeof(NS_ATT));
+ while (nPrefixes >> parser->m_nsAttsPower++);
+ if (parser->m_nsAttsPower < 3)
+ parser->m_nsAttsPower = 3;
+
+ /* Detect and prevent invalid shift */
+ if (parser->m_nsAttsPower >= sizeof(nsAttsSize) * 8 /* bits per byte */) {
+ /* Restore actual size of memory in m_nsAtts */
+ parser->m_nsAttsPower = oldNsAttsPower;
+ return XML_ERROR_NO_MEMORY;
+ }
+
+ nsAttsSize = 1u << parser->m_nsAttsPower;
+
+ /* Detect and prevent integer overflow.
+ * The preprocessor guard addresses the "always false" warning
+ * from -Wtype-limits on platforms where
+ * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */
+#if UINT_MAX >= SIZE_MAX
+ if (nsAttsSize > (size_t)(-1) / sizeof(NS_ATT)) {
+ /* Restore actual size of memory in m_nsAtts */
+ parser->m_nsAttsPower = oldNsAttsPower;
+ return XML_ERROR_NO_MEMORY;
+ }
+#endif
+
+ temp = (NS_ATT *)REALLOC(parser, parser->m_nsAtts, nsAttsSize * sizeof(NS_ATT));
if (!temp)
return XML_ERROR_NO_MEMORY;
- nsAtts = temp;
- version = 0; /* force re-initialization of nsAtts hash table */
+ parser->m_nsAtts = temp;
+ version = 0; /* force re-initialization of m_nsAtts hash table */
}
- /* using a version flag saves us from initializing nsAtts every time */
+ /* using a version flag saves us from initializing m_nsAtts every time */
if (!version) { /* initialize version flags when version wraps around */
version = INIT_ATTS_VERSION;
for (j = nsAttsSize; j != 0; )
- nsAtts[--j].version = version;
+ parser->m_nsAtts[--j].version = version;
}
- nsAttsVersion = --version;
+ parser->m_nsAttsVersion = --version;
/* expand prefixed names and check for duplicates */
for (; i < attIndex; i += 2) {
@@ -2898,17 +2954,33 @@ storeAtts(XML_Parser parser, const ENCODING *enc,
if (s[-1] == 2) { /* prefixed */
ATTRIBUTE_ID *id;
const BINDING *b;
- unsigned long uriHash = hash_secret_salt;
+ size_t uriHash = parser->m_hash_secret_salt;
((XML_Char *)s)[-1] = 0; /* clear flag */
id = (ATTRIBUTE_ID *)lookup(parser, &dtd->attributeIds, s, 0);
+ if (!id || !id->prefix) {
+ /* This code is walking through the appAtts array, dealing
+ * with (in this case) a prefixed attribute name. To be in
+ * the array, the attribute must have already been bound, so
+ * has to have passed through the hash table lookup once
+ * already. That implies that an entry for it already
+ * exists, so the lookup above will return a pointer to
+ * already allocated memory. There is no opportunaity for
+ * the allocator to fail, so the condition above cannot be
+ * fulfilled.
+ *
+ * Since it is difficult to be certain that the above
+ * analysis is complete, we retain the test.
+ */
+ return XML_ERROR_NO_MEMORY;
+ }
b = id->prefix->binding;
if (!b)
return XML_ERROR_UNBOUND_PREFIX;
/* as we expand the name we also calculate its hash value */
- for (j = 0; j < b->uriLen; j++) {
+ for (j = 0; j < (size_t)b->uriLen; j++) {
const XML_Char c = b->uri[j];
- if (!poolAppendChar(&tempPool, c))
+ if (!poolAppendChar(&parser->m_tempPool, c))
return XML_ERROR_NO_MEMORY;
uriHash = CHAR_HASH(uriHash, c);
}
@@ -2916,7 +2988,7 @@ storeAtts(XML_Parser parser, const ENCODING *enc,
;
do { /* copies null terminator */
const XML_Char c = *s;
- if (!poolAppendChar(&tempPool, *s))
+ if (!poolAppendChar(&parser->m_tempPool, *s))
return XML_ERROR_NO_MEMORY;
uriHash = CHAR_HASH(uriHash, c);
} while (*s++);
@@ -2925,42 +2997,42 @@ storeAtts(XML_Parser parser, const ENCODING *enc,
Derived from code in lookup(parser, HASH_TABLE *table, ...).
*/
unsigned char step = 0;
- unsigned long mask = nsAttsSize - 1;
+ size_t mask = nsAttsSize - 1;
j = uriHash & mask; /* index into hash table */
- while (nsAtts[j].version == version) {
+ while (parser->m_nsAtts[j].version == version) {
/* for speed we compare stored hash values first */
- if (uriHash == nsAtts[j].hash) {
- const XML_Char *s1 = poolStart(&tempPool);
- const XML_Char *s2 = nsAtts[j].uriName;
+ if (uriHash == parser->m_nsAtts[j].hash) {
+ const XML_Char *s1 = poolStart(&parser->m_tempPool);
+ const XML_Char *s2 = parser->m_nsAtts[j].uriName;
/* s1 is null terminated, but not s2 */
for (; *s1 == *s2 && *s1 != 0; s1++, s2++);
if (*s1 == 0)
return XML_ERROR_DUPLICATE_ATTRIBUTE;
}
if (!step)
- step = PROBE_STEP(uriHash, mask, nsAttsPower);
+ step = PROBE_STEP(uriHash, mask, parser->m_nsAttsPower);
j < step ? (j += nsAttsSize - step) : (j -= step);
}
}
- if (ns_triplets) { /* append namespace separator and prefix */
- tempPool.ptr[-1] = namespaceSeparator;
+ if (parser->m_ns_triplets) { /* append namespace separator and prefix */
+ parser->m_tempPool.ptr[-1] = parser->m_namespaceSeparator;
s = b->prefix->name;
do {
- if (!poolAppendChar(&tempPool, *s))
+ if (!poolAppendChar(&parser->m_tempPool, *s))
return XML_ERROR_NO_MEMORY;
} while (*s++);
}
/* store expanded name in attribute list */
- s = poolStart(&tempPool);
- poolFinish(&tempPool);
+ s = poolStart(&parser->m_tempPool);
+ poolFinish(&parser->m_tempPool);
appAtts[i] = s;
/* fill empty slot with new version, uriName and hash value */
- nsAtts[j].version = version;
- nsAtts[j].hash = uriHash;
- nsAtts[j].uriName = s;
+ parser->m_nsAtts[j].version = version;
+ parser->m_nsAtts[j].hash = uriHash;
+ parser->m_nsAtts[j].uriName = s;
if (!--nPrefixes) {
i += 2;
@@ -2977,7 +3049,7 @@ storeAtts(XML_Parser parser, const ENCODING *enc,
for (binding = *bindingsPtr; binding; binding = binding->nextTagBinding)
binding->attId->name[-1] = 0;
- if (!ns)
+ if (!parser->m_ns)
return XML_ERROR_NONE;
/* expand the element type name */
@@ -2996,7 +3068,7 @@ storeAtts(XML_Parser parser, const ENCODING *enc,
else
return XML_ERROR_NONE;
prefixLen = 0;
- if (ns_triplets && binding->prefix->name) {
+ if (parser->m_ns_triplets && binding->prefix->name) {
for (; binding->prefix->name[prefixLen++];)
; /* prefixLen includes null terminator */
}
@@ -3006,33 +3078,166 @@ storeAtts(XML_Parser parser, const ENCODING *enc,
tagNamePtr->prefixLen = prefixLen;
for (i = 0; localPart[i++];)
; /* i includes null terminator */
+
+ /* Detect and prevent integer overflow */
+ if (binding->uriLen > INT_MAX - prefixLen
+ || i > INT_MAX - (binding->uriLen + prefixLen)) {
+ return XML_ERROR_NO_MEMORY;
+ }
+
n = i + binding->uriLen + prefixLen;
if (n > binding->uriAlloc) {
TAG *p;
- uri = (XML_Char *)MALLOC((n + EXPAND_SPARE) * sizeof(XML_Char));
+
+ /* Detect and prevent integer overflow */
+ if (n > INT_MAX - EXPAND_SPARE) {
+ return XML_ERROR_NO_MEMORY;
+ }
+ /* Detect and prevent integer overflow.
+ * The preprocessor guard addresses the "always false" warning
+ * from -Wtype-limits on platforms where
+ * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */
+#if UINT_MAX >= SIZE_MAX
+ if ((unsigned)(n + EXPAND_SPARE) > (size_t)(-1) / sizeof(XML_Char)) {
+ return XML_ERROR_NO_MEMORY;
+ }
+#endif
+
+ uri = (XML_Char *)MALLOC(parser, (n + EXPAND_SPARE) * sizeof(XML_Char));
if (!uri)
return XML_ERROR_NO_MEMORY;
binding->uriAlloc = n + EXPAND_SPARE;
memcpy(uri, binding->uri, binding->uriLen * sizeof(XML_Char));
- for (p = tagStack; p; p = p->parent)
+ for (p = parser->m_tagStack; p; p = p->parent)
if (p->name.str == binding->uri)
p->name.str = uri;
- FREE(binding->uri);
+ FREE(parser, binding->uri);
binding->uri = uri;
}
- /* if namespaceSeparator != '\0' then uri includes it already */
+ /* if m_namespaceSeparator != '\0' then uri includes it already */
uri = binding->uri + binding->uriLen;
memcpy(uri, localPart, i * sizeof(XML_Char));
/* we always have a namespace separator between localPart and prefix */
if (prefixLen) {
uri += i - 1;
- *uri = namespaceSeparator; /* replace null terminator */
+ *uri = parser->m_namespaceSeparator; /* replace null terminator */
memcpy(uri + 1, binding->prefix->name, prefixLen * sizeof(XML_Char));
}
tagNamePtr->str = binding->uri;
return XML_ERROR_NONE;
}
+static XML_Bool
+is_rfc3986_uri_char(XML_Char candidate) {
+ // For the RFC 3986 ANBF grammar see
+ // https://datatracker.ietf.org/doc/html/rfc3986#appendix-A
+
+ switch (candidate) {
+ // From rule "ALPHA" (uppercase half)
+ case 'A':
+ case 'B':
+ case 'C':
+ case 'D':
+ case 'E':
+ case 'F':
+ case 'G':
+ case 'H':
+ case 'I':
+ case 'J':
+ case 'K':
+ case 'L':
+ case 'M':
+ case 'N':
+ case 'O':
+ case 'P':
+ case 'Q':
+ case 'R':
+ case 'S':
+ case 'T':
+ case 'U':
+ case 'V':
+ case 'W':
+ case 'X':
+ case 'Y':
+ case 'Z':
+
+ // From rule "ALPHA" (lowercase half)
+ case 'a':
+ case 'b':
+ case 'c':
+ case 'd':
+ case 'e':
+ case 'f':
+ case 'g':
+ case 'h':
+ case 'i':
+ case 'j':
+ case 'k':
+ case 'l':
+ case 'm':
+ case 'n':
+ case 'o':
+ case 'p':
+ case 'q':
+ case 'r':
+ case 's':
+ case 't':
+ case 'u':
+ case 'v':
+ case 'w':
+ case 'x':
+ case 'y':
+ case 'z':
+
+ // From rule "DIGIT"
+ case '0':
+ case '1':
+ case '2':
+ case '3':
+ case '4':
+ case '5':
+ case '6':
+ case '7':
+ case '8':
+ case '9':
+
+ // From rule "pct-encoded"
+ case '%':
+
+ // From rule "unreserved"
+ case '-':
+ case '.':
+ case '_':
+ case '~':
+
+ // From rule "gen-delims"
+ case ':':
+ case '/':
+ case '?':
+ case '#':
+ case '[':
+ case ']':
+ case '@':
+
+ // From rule "sub-delims"
+ case '!':
+ case '$':
+ case '&':
+ case '\'':
+ case '(':
+ case ')':
+ case '*':
+ case '+':
+ case ',':
+ case ';':
+ case '=':
+ return XML_TRUE;
+
+ default:
+ return XML_FALSE;
+ }
+}
+
/* addBinding() overwrites the value of prefix->binding without checking.
Therefore one must keep track of the old value outside of addBinding().
*/
@@ -3093,6 +3298,29 @@ addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId,
if (!mustBeXML && isXMLNS
&& (len > xmlnsLen || uri[len] != xmlnsNamespace[len]))
isXMLNS = XML_FALSE;
+
+ // NOTE: While Expat does not validate namespace URIs against RFC 3986
+ // today (and is not REQUIRED to do so with regard to the XML 1.0
+ // namespaces specification) we have to at least make sure, that
+ // the application on top of Expat (that is likely splitting expanded
+ // element names ("qualified names") of form
+ // "[uri sep] local [sep prefix] '\0'" back into 1, 2 or 3 pieces
+ // in its element handler code) cannot be confused by an attacker
+ // putting additional namespace separator characters into namespace
+ // declarations. That would be ambiguous and not to be expected.
+ //
+ // While the HTML API docs of function XML_ParserCreateNS have been
+ // advising against use of a namespace separator character that can
+ // appear in a URI for >20 years now, some widespread applications
+ // are using URI characters (':' (colon) in particular) for a
+ // namespace separator, in practice. To keep these applications
+ // functional, we only reject namespaces URIs containing the
+ // application-chosen namespace separator if the chosen separator
+ // is a non-URI character with regard to RFC 3986.
+ if (parser->m_ns && (uri[len] == parser->m_namespaceSeparator)
+ && ! is_rfc3986_uri_char(uri[len])) {
+ return XML_ERROR_SYNTAX;
+ }
}
isXML = isXML && len == xmlLen;
isXMLNS = isXMLNS && len == xmlnsLen;
@@ -3104,48 +3332,78 @@ addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId,
if (isXMLNS)
return XML_ERROR_RESERVED_NAMESPACE_URI;
- if (namespaceSeparator)
+ if (parser->m_namespaceSeparator)
len++;
- if (freeBindingList) {
- b = freeBindingList;
+ if (parser->m_freeBindingList) {
+ b = parser->m_freeBindingList;
if (len > b->uriAlloc) {
- XML_Char *temp = (XML_Char *)REALLOC(b->uri,
+ /* Detect and prevent integer overflow */
+ if (len > INT_MAX - EXPAND_SPARE) {
+ return XML_ERROR_NO_MEMORY;
+ }
+
+ /* Detect and prevent integer overflow.
+ * The preprocessor guard addresses the "always false" warning
+ * from -Wtype-limits on platforms where
+ * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */
+#if UINT_MAX >= SIZE_MAX
+ if ((unsigned)(len + EXPAND_SPARE) > (size_t)(-1) / sizeof(XML_Char)) {
+ return XML_ERROR_NO_MEMORY;
+ }
+#endif
+
+ XML_Char *temp = (XML_Char *)REALLOC(parser, b->uri,
sizeof(XML_Char) * (len + EXPAND_SPARE));
if (temp == NULL)
return XML_ERROR_NO_MEMORY;
b->uri = temp;
b->uriAlloc = len + EXPAND_SPARE;
}
- freeBindingList = b->nextTagBinding;
+ parser->m_freeBindingList = b->nextTagBinding;
}
else {
- b = (BINDING *)MALLOC(sizeof(BINDING));
+ b = (BINDING *)MALLOC(parser, sizeof(BINDING));
if (!b)
return XML_ERROR_NO_MEMORY;
- b->uri = (XML_Char *)MALLOC(sizeof(XML_Char) * (len + EXPAND_SPARE));
+
+ /* Detect and prevent integer overflow */
+ if (len > INT_MAX - EXPAND_SPARE) {
+ return XML_ERROR_NO_MEMORY;
+ }
+ /* Detect and prevent integer overflow.
+ * The preprocessor guard addresses the "always false" warning
+ * from -Wtype-limits on platforms where
+ * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */
+#if UINT_MAX >= SIZE_MAX
+ if ((unsigned)(len + EXPAND_SPARE) > (size_t)(-1) / sizeof(XML_Char)) {
+ return XML_ERROR_NO_MEMORY;
+ }
+#endif
+
+ b->uri = (XML_Char *)MALLOC(parser, sizeof(XML_Char) * (len + EXPAND_SPARE));
if (!b->uri) {
- FREE(b);
+ FREE(parser, b);
return XML_ERROR_NO_MEMORY;
}
b->uriAlloc = len + EXPAND_SPARE;
}
b->uriLen = len;
memcpy(b->uri, uri, len * sizeof(XML_Char));
- if (namespaceSeparator)
- b->uri[len - 1] = namespaceSeparator;
+ if (parser->m_namespaceSeparator)
+ b->uri[len - 1] = parser->m_namespaceSeparator;
b->prefix = prefix;
b->attId = attId;
b->prevPrefixBinding = prefix->binding;
/* NULL binding when default namespace undeclared */
- if (*uri == XML_T('\0') && prefix == &_dtd->defaultPrefix)
+ if (*uri == XML_T('\0') && prefix == &parser->m_dtd->defaultPrefix)
prefix->binding = NULL;
else
prefix->binding = b;
b->nextTagBinding = *bindingsPtr;
*bindingsPtr = b;
/* if attId == NULL then we are not starting a namespace scope */
- if (attId && startNamespaceDeclHandler)
- startNamespaceDeclHandler(handlerArg, prefix->name,
+ if (attId && parser->m_startNamespaceDeclHandler)
+ parser->m_startNamespaceDeclHandler(parser->m_handlerArg, prefix->name,
prefix->binding ? uri : 0);
return XML_ERROR_NONE;
}
@@ -3159,17 +3417,17 @@ cdataSectionProcessor(XML_Parser parser,
const char *end,
const char **endPtr)
{
- enum XML_Error result = doCdataSection(parser, encoding, &start, end,
- endPtr, (XML_Bool)!ps_finalBuffer);
+ enum XML_Error result = doCdataSection(parser, parser->m_encoding, &start, end,
+ endPtr, (XML_Bool)!parser->m_parsingStatus.finalBuffer);
if (result != XML_ERROR_NONE)
return result;
if (start) {
- if (parentParser) { /* we are parsing an external entity */
- processor = externalEntityContentProcessor;
+ if (parser->m_parentParser) { /* we are parsing an external entity */
+ parser->m_processor = externalEntityContentProcessor;
return externalEntityContentProcessor(parser, start, end, endPtr);
}
else {
- processor = contentProcessor;
+ parser->m_processor = contentProcessor;
return contentProcessor(parser, start, end, endPtr);
}
}
@@ -3190,14 +3448,14 @@ doCdataSection(XML_Parser parser,
const char *s = *startPtr;
const char **eventPP;
const char **eventEndPP;
- if (enc == encoding) {
- eventPP = &eventPtr;
+ if (enc == parser->m_encoding) {
+ eventPP = &parser->m_eventPtr;
*eventPP = s;
- eventEndPP = &eventEndPtr;
+ eventEndPP = &parser->m_eventEndPtr;
}
else {
- eventPP = &(openInternalEntities->internalEventPtr);
- eventEndPP = &(openInternalEntities->internalEventEndPtr);
+ eventPP = &(parser->m_openInternalEntities->internalEventPtr);
+ eventEndPP = &(parser->m_openInternalEntities->internalEventEndPtr);
}
*eventPP = s;
*startPtr = NULL;
@@ -3208,51 +3466,51 @@ doCdataSection(XML_Parser parser,
*eventEndPP = next;
switch (tok) {
case XML_TOK_CDATA_SECT_CLOSE:
- if (endCdataSectionHandler)
- endCdataSectionHandler(handlerArg);
+ if (parser->m_endCdataSectionHandler)
+ parser->m_endCdataSectionHandler(parser->m_handlerArg);
#if 0
/* see comment under XML_TOK_CDATA_SECT_OPEN */
- else if (characterDataHandler)
- characterDataHandler(handlerArg, dataBuf, 0);
+ else if (parser->m_characterDataHandler)
+ parser->m_characterDataHandler(parser->m_handlerArg, parser->m_dataBuf, 0);
#endif
- else if (defaultHandler)
+ else if (parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
*startPtr = next;
*nextPtr = next;
- if (ps_parsing == XML_FINISHED)
+ if (parser->m_parsingStatus.parsing == XML_FINISHED)
return XML_ERROR_ABORTED;
else
return XML_ERROR_NONE;
case XML_TOK_DATA_NEWLINE:
- if (characterDataHandler) {
+ if (parser->m_characterDataHandler) {
XML_Char c = 0xA;
- characterDataHandler(handlerArg, &c, 1);
+ parser->m_characterDataHandler(parser->m_handlerArg, &c, 1);
}
- else if (defaultHandler)
+ else if (parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
break;
case XML_TOK_DATA_CHARS:
{
- XML_CharacterDataHandler charDataHandler = characterDataHandler;
+ XML_CharacterDataHandler charDataHandler = parser->m_characterDataHandler;
if (charDataHandler) {
if (MUST_CONVERT(enc, s)) {
for (;;) {
- ICHAR *dataPtr = (ICHAR *)dataBuf;
- XmlConvert(enc, &s, next, &dataPtr, (ICHAR *)dataBufEnd);
+ ICHAR *dataPtr = (ICHAR *)parser->m_dataBuf;
+ const enum XML_Convert_Result convert_res = XmlConvert(enc, &s, next, &dataPtr, (ICHAR *)parser->m_dataBufEnd);
*eventEndPP = next;
- charDataHandler(handlerArg, dataBuf,
- (int)(dataPtr - (ICHAR *)dataBuf));
- if (s == next)
+ charDataHandler(parser->m_handlerArg, parser->m_dataBuf,
+ (int)(dataPtr - (ICHAR *)parser->m_dataBuf));
+ if ((convert_res == XML_CONVERT_COMPLETED) || (convert_res == XML_CONVERT_INPUT_INCOMPLETE))
break;
*eventPP = s;
}
}
else
- charDataHandler(handlerArg,
+ charDataHandler(parser->m_handlerArg,
(XML_Char *)s,
(int)((XML_Char *)next - (XML_Char *)s));
}
- else if (defaultHandler)
+ else if (parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
}
break;
@@ -3278,7 +3536,7 @@ doCdataSection(XML_Parser parser,
}
*eventPP = s = next;
- switch (ps_parsing) {
+ switch (parser->m_parsingStatus.parsing) {
case XML_SUSPENDED:
*nextPtr = next;
return XML_ERROR_NONE;
@@ -3301,12 +3559,12 @@ ignoreSectionProcessor(XML_Parser parser,
const char *end,
const char **endPtr)
{
- enum XML_Error result = doIgnoreSection(parser, encoding, &start, end,
- endPtr, (XML_Bool)!ps_finalBuffer);
+ enum XML_Error result = doIgnoreSection(parser, parser->m_encoding, &start, end,
+ endPtr, (XML_Bool)!parser->m_parsingStatus.finalBuffer);
if (result != XML_ERROR_NONE)
return result;
if (start) {
- processor = prologProcessor;
+ parser->m_processor = prologProcessor;
return prologProcessor(parser, start, end, endPtr);
}
return result;
@@ -3328,14 +3586,14 @@ doIgnoreSection(XML_Parser parser,
const char *s = *startPtr;
const char **eventPP;
const char **eventEndPP;
- if (enc == encoding) {
- eventPP = &eventPtr;
+ if (enc == parser->m_encoding) {
+ eventPP = &parser->m_eventPtr;
*eventPP = s;
- eventEndPP = &eventEndPtr;
+ eventEndPP = &parser->m_eventEndPtr;
}
else {
- eventPP = &(openInternalEntities->internalEventPtr);
- eventEndPP = &(openInternalEntities->internalEventEndPtr);
+ eventPP = &(parser->m_openInternalEntities->internalEventPtr);
+ eventEndPP = &(parser->m_openInternalEntities->internalEventEndPtr);
}
*eventPP = s;
*startPtr = NULL;
@@ -3343,11 +3601,11 @@ doIgnoreSection(XML_Parser parser,
*eventEndPP = next;
switch (tok) {
case XML_TOK_IGNORE_SECT:
- if (defaultHandler)
+ if (parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
*startPtr = next;
*nextPtr = next;
- if (ps_parsing == XML_FINISHED)
+ if (parser->m_parsingStatus.parsing == XML_FINISHED)
return XML_ERROR_ABORTED;
else
return XML_ERROR_NONE;
@@ -3382,27 +3640,28 @@ initializeEncoding(XML_Parser parser)
const char *s;
#ifdef XML_UNICODE
char encodingBuf[128];
- if (!protocolEncodingName)
+ /* See comments about `protocolEncodingName` in parserInit() */
+ if (!parser->m_protocolEncodingName)
s = NULL;
else {
int i;
- for (i = 0; protocolEncodingName[i]; i++) {
+ for (i = 0; parser->m_protocolEncodingName[i]; i++) {
if (i == sizeof(encodingBuf) - 1
- || (protocolEncodingName[i] & ~0x7f) != 0) {
+ || (parser->m_protocolEncodingName[i] & ~0x7f) != 0) {
encodingBuf[0] = '\0';
break;
}
- encodingBuf[i] = (char)protocolEncodingName[i];
+ encodingBuf[i] = (char)parser->m_protocolEncodingName[i];
}
encodingBuf[i] = '\0';
s = encodingBuf;
}
#else
- s = protocolEncodingName;
+ s = parser->m_protocolEncodingName;
#endif
- if ((ns ? XmlInitEncodingNS : XmlInitEncoding)(&initEncoding, &encoding, s))
+ if ((parser->m_ns ? XmlInitEncodingNS : XmlInitEncoding)(&parser->m_initEncoding, &parser->m_encoding, s))
return XML_ERROR_NONE;
- return handleUnknownEncoding(parser, protocolEncodingName);
+ return handleUnknownEncoding(parser, parser->m_protocolEncodingName);
}
static enum XML_Error
@@ -3416,13 +3675,13 @@ processXmlDecl(XML_Parser parser, int isGeneralTextEntity,
const char *versionend;
const XML_Char *storedversion = NULL;
int standalone = -1;
- if (!(ns
+ if (!(parser->m_ns
? XmlParseXmlDeclNS
: XmlParseXmlDecl)(isGeneralTextEntity,
- encoding,
+ parser->m_encoding,
s,
next,
- &eventPtr,
+ &parser->m_eventPtr,
&version,
&versionend,
&encodingName,
@@ -3434,62 +3693,62 @@ processXmlDecl(XML_Parser parser, int isGeneralTextEntity,
return XML_ERROR_XML_DECL;
}
if (!isGeneralTextEntity && standalone == 1) {
- _dtd->standalone = XML_TRUE;
+ parser->m_dtd->standalone = XML_TRUE;
#ifdef XML_DTD
- if (paramEntityParsing == XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE)
- paramEntityParsing = XML_PARAM_ENTITY_PARSING_NEVER;
+ if (parser->m_paramEntityParsing == XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE)
+ parser->m_paramEntityParsing = XML_PARAM_ENTITY_PARSING_NEVER;
#endif /* XML_DTD */
}
- if (xmlDeclHandler) {
+ if (parser->m_xmlDeclHandler) {
if (encodingName != NULL) {
- storedEncName = poolStoreString(&temp2Pool,
- encoding,
+ storedEncName = poolStoreString(&parser->m_temp2Pool,
+ parser->m_encoding,
encodingName,
encodingName
- + XmlNameLength(encoding, encodingName));
+ + XmlNameLength(parser->m_encoding, encodingName));
if (!storedEncName)
return XML_ERROR_NO_MEMORY;
- poolFinish(&temp2Pool);
+ poolFinish(&parser->m_temp2Pool);
}
if (version) {
- storedversion = poolStoreString(&temp2Pool,
- encoding,
+ storedversion = poolStoreString(&parser->m_temp2Pool,
+ parser->m_encoding,
version,
- versionend - encoding->minBytesPerChar);
+ versionend - parser->m_encoding->minBytesPerChar);
if (!storedversion)
return XML_ERROR_NO_MEMORY;
}
- xmlDeclHandler(handlerArg, storedversion, storedEncName, standalone);
+ parser->m_xmlDeclHandler(parser->m_handlerArg, storedversion, storedEncName, standalone);
}
- else if (defaultHandler)
- reportDefault(parser, encoding, s, next);
- if (protocolEncodingName == NULL) {
+ else if (parser->m_defaultHandler)
+ reportDefault(parser, parser->m_encoding, s, next);
+ if (parser->m_protocolEncodingName == NULL) {
if (newEncoding) {
- if (newEncoding->minBytesPerChar != encoding->minBytesPerChar) {
- eventPtr = encodingName;
+ if (newEncoding->minBytesPerChar != parser->m_encoding->minBytesPerChar) {
+ parser->m_eventPtr = encodingName;
return XML_ERROR_INCORRECT_ENCODING;
}
- encoding = newEncoding;
+ parser->m_encoding = newEncoding;
}
else if (encodingName) {
enum XML_Error result;
if (!storedEncName) {
storedEncName = poolStoreString(
- &temp2Pool, encoding, encodingName,
- encodingName + XmlNameLength(encoding, encodingName));
+ &parser->m_temp2Pool, parser->m_encoding, encodingName,
+ encodingName + XmlNameLength(parser->m_encoding, encodingName));
if (!storedEncName)
return XML_ERROR_NO_MEMORY;
}
result = handleUnknownEncoding(parser, storedEncName);
- poolClear(&temp2Pool);
+ poolClear(&parser->m_temp2Pool);
if (result == XML_ERROR_UNKNOWN_ENCODING)
- eventPtr = encodingName;
+ parser->m_eventPtr = encodingName;
return result;
}
}
if (storedEncName || storedversion)
- poolClear(&temp2Pool);
+ poolClear(&parser->m_temp2Pool);
return XML_ERROR_NONE;
}
@@ -3497,7 +3756,7 @@ processXmlDecl(XML_Parser parser, int isGeneralTextEntity,
static enum XML_Error
handleUnknownEncoding(XML_Parser parser, const XML_Char *encodingName)
{
- if (unknownEncodingHandler) {
+ if (parser->m_unknownEncodingHandler) {
XML_Encoding info;
int i;
for (i = 0; i < 256; i++)
@@ -3505,25 +3764,25 @@ handleUnknownEncoding(XML_Parser parser, const XML_Char *encodingName)
info.convert = NULL;
info.data = NULL;
info.release = NULL;
- if (unknownEncodingHandler(unknownEncodingHandlerData, encodingName,
+ if (parser->m_unknownEncodingHandler(parser->m_unknownEncodingHandlerData, encodingName,
&info)) {
ENCODING *enc;
- unknownEncodingMem = MALLOC(XmlSizeOfUnknownEncoding());
- if (!unknownEncodingMem) {
+ parser->m_unknownEncodingMem = MALLOC(parser, XmlSizeOfUnknownEncoding());
+ if (!parser->m_unknownEncodingMem) {
if (info.release)
info.release(info.data);
return XML_ERROR_NO_MEMORY;
}
- enc = (ns
+ enc = (parser->m_ns
? XmlInitUnknownEncodingNS
- : XmlInitUnknownEncoding)(unknownEncodingMem,
+ : XmlInitUnknownEncoding)(parser->m_unknownEncodingMem,
info.map,
info.convert,
info.data);
if (enc) {
- unknownEncodingData = info.data;
- unknownEncodingRelease = info.release;
- encoding = enc;
+ parser->m_unknownEncodingData = info.data;
+ parser->m_unknownEncodingRelease = info.release;
+ parser->m_encoding = enc;
return XML_ERROR_NONE;
}
}
@@ -3542,7 +3801,7 @@ prologInitProcessor(XML_Parser parser,
enum XML_Error result = initializeEncoding(parser);
if (result != XML_ERROR_NONE)
return result;
- processor = prologProcessor;
+ parser->m_processor = prologProcessor;
return prologProcessor(parser, s, end, nextPtr);
}
@@ -3560,14 +3819,14 @@ externalParEntInitProcessor(XML_Parser parser,
/* we know now that XML_Parse(Buffer) has been called,
so we consider the external parameter entity read */
- _dtd->paramEntityRead = XML_TRUE;
+ parser->m_dtd->paramEntityRead = XML_TRUE;
- if (prologState.inEntityValue) {
- processor = entityValueInitProcessor;
+ if (parser->m_prologState.inEntityValue) {
+ parser->m_processor = entityValueInitProcessor;
return entityValueInitProcessor(parser, s, end, nextPtr);
}
else {
- processor = externalParEntProcessor;
+ parser->m_processor = externalParEntProcessor;
return externalParEntProcessor(parser, s, end, nextPtr);
}
}
@@ -3581,13 +3840,13 @@ entityValueInitProcessor(XML_Parser parser,
int tok;
const char *start = s;
const char *next = start;
- eventPtr = start;
+ parser->m_eventPtr = start;
for (;;) {
- tok = XmlPrologTok(encoding, start, end, &next);
- eventEndPtr = next;
+ tok = XmlPrologTok(parser->m_encoding, start, end, &next);
+ parser->m_eventEndPtr = next;
if (tok <= 0) {
- if (!ps_finalBuffer && tok != XML_TOK_INVALID) {
+ if (!parser->m_parsingStatus.finalBuffer && tok != XML_TOK_INVALID) {
*nextPtr = s;
return XML_ERROR_NONE;
}
@@ -3603,14 +3862,14 @@ entityValueInitProcessor(XML_Parser parser,
break;
}
/* found end of entity value - can store it now */
- return storeEntityValue(parser, encoding, s, end);
+ return storeEntityValue(parser, parser->m_encoding, s, end);
}
else if (tok == XML_TOK_XML_DECL) {
enum XML_Error result;
result = processXmlDecl(parser, 0, start, next);
if (result != XML_ERROR_NONE)
return result;
- switch (ps_parsing) {
+ switch (parser->m_parsingStatus.parsing) {
case XML_SUSPENDED:
*nextPtr = next;
return XML_ERROR_NONE;
@@ -3620,7 +3879,7 @@ entityValueInitProcessor(XML_Parser parser,
*nextPtr = next;
}
/* stop scanning for text declaration - we found one */
- processor = entityValueProcessor;
+ parser->m_processor = entityValueProcessor;
return entityValueProcessor(parser, next, end, nextPtr);
}
/* If we are at the end of the buffer, this would cause XmlPrologTok to
@@ -3630,12 +3889,20 @@ entityValueInitProcessor(XML_Parser parser,
then, when this routine is entered the next time, XmlPrologTok will
return XML_TOK_INVALID, since the BOM is still in the buffer
*/
- else if (tok == XML_TOK_BOM && next == end && !ps_finalBuffer) {
+ else if (tok == XML_TOK_BOM && next == end && !parser->m_parsingStatus.finalBuffer) {
*nextPtr = next;
return XML_ERROR_NONE;
}
+ /* If we get this token, we have the start of what might be a
+ normal tag, but not a declaration (i.e. it doesn't begin with
+ "<!"). In a DTD context, that isn't legal.
+ */
+ else if (tok == XML_TOK_INSTANCE_START) {
+ *nextPtr = next;
+ return XML_ERROR_SYNTAX;
+ }
start = next;
- eventPtr = start;
+ parser->m_eventPtr = start;
}
}
@@ -3648,9 +3915,9 @@ externalParEntProcessor(XML_Parser parser,
const char *next = s;
int tok;
- tok = XmlPrologTok(encoding, s, end, &next);
+ tok = XmlPrologTok(parser->m_encoding, s, end, &next);
if (tok <= 0) {
- if (!ps_finalBuffer && tok != XML_TOK_INVALID) {
+ if (!parser->m_parsingStatus.finalBuffer && tok != XML_TOK_INVALID) {
*nextPtr = s;
return XML_ERROR_NONE;
}
@@ -3672,12 +3939,12 @@ externalParEntProcessor(XML_Parser parser,
*/
else if (tok == XML_TOK_BOM) {
s = next;
- tok = XmlPrologTok(encoding, s, end, &next);
+ tok = XmlPrologTok(parser->m_encoding, s, end, &next);
}
- processor = prologProcessor;
- return doProlog(parser, encoding, s, end, tok, next,
- nextPtr, (XML_Bool)!ps_finalBuffer);
+ parser->m_processor = prologProcessor;
+ return doProlog(parser, parser->m_encoding, s, end, tok, next,
+ nextPtr, (XML_Bool)!parser->m_parsingStatus.finalBuffer, XML_TRUE);
}
static enum XML_Error PTRCALL
@@ -3688,13 +3955,13 @@ entityValueProcessor(XML_Parser parser,
{
const char *start = s;
const char *next = s;
- const ENCODING *enc = encoding;
+ const ENCODING *enc = parser->m_encoding;
int tok;
for (;;) {
tok = XmlPrologTok(enc, start, end, &next);
if (tok <= 0) {
- if (!ps_finalBuffer && tok != XML_TOK_INVALID) {
+ if (!parser->m_parsingStatus.finalBuffer && tok != XML_TOK_INVALID) {
*nextPtr = s;
return XML_ERROR_NONE;
}
@@ -3725,9 +3992,9 @@ prologProcessor(XML_Parser parser,
const char **nextPtr)
{
const char *next = s;
- int tok = XmlPrologTok(encoding, s, end, &next);
- return doProlog(parser, encoding, s, end, tok, next,
- nextPtr, (XML_Bool)!ps_finalBuffer);
+ int tok = XmlPrologTok(parser->m_encoding, s, end, &next);
+ return doProlog(parser, parser->m_encoding, s, end, tok, next,
+ nextPtr, (XML_Bool)!parser->m_parsingStatus.finalBuffer, XML_TRUE);
}
static enum XML_Error
@@ -3738,7 +4005,8 @@ doProlog(XML_Parser parser,
int tok,
const char *next,
const char **nextPtr,
- XML_Bool haveMore)
+ XML_Bool haveMore,
+ XML_Bool allowClosingDoctype)
{
#ifdef XML_DTD
static const XML_Char externalSubsetName[] = { ASCII_HASH , '\0' };
@@ -3764,19 +4032,19 @@ doProlog(XML_Parser parser,
static const XML_Char enumValueStart[] = { ASCII_LPAREN, '\0' };
/* save one level of indirection */
- DTD * const dtd = _dtd;
+ DTD * const dtd = parser->m_dtd;
const char **eventPP;
const char **eventEndPP;
enum XML_Content_Quant quant;
- if (enc == encoding) {
- eventPP = &eventPtr;
- eventEndPP = &eventEndPtr;
+ if (enc == parser->m_encoding) {
+ eventPP = &parser->m_eventPtr;
+ eventEndPP = &parser->m_eventEndPtr;
}
else {
- eventPP = &(openInternalEntities->internalEventPtr);
- eventEndPP = &(openInternalEntities->internalEventEndPtr);
+ eventPP = &(parser->m_openInternalEntities->internalEventPtr);
+ eventEndPP = &(parser->m_openInternalEntities->internalEventEndPtr);
}
for (;;) {
@@ -3803,7 +4071,7 @@ doProlog(XML_Parser parser,
case XML_TOK_NONE:
#ifdef XML_DTD
/* for internal PE NOT referenced between declarations */
- if (enc != encoding && !openInternalEntities->betweenDecl) {
+ if (enc != parser->m_encoding && !parser->m_openInternalEntities->betweenDecl) {
*nextPtr = s;
return XML_ERROR_NONE;
}
@@ -3811,8 +4079,8 @@ doProlog(XML_Parser parser,
complete markup, not only for external PEs, but also for
internal PEs if the reference occurs between declarations.
*/
- if (isParamEntity || enc != encoding) {
- if (XmlTokenRole(&prologState, XML_TOK_NONE, end, end, enc)
+ if (parser->m_isParamEntity || enc != parser->m_encoding) {
+ if (XmlTokenRole(&parser->m_prologState, XML_TOK_NONE, end, end, enc)
== XML_ROLE_ERROR)
return XML_ERROR_INCOMPLETE_PE;
*nextPtr = s;
@@ -3826,34 +4094,34 @@ doProlog(XML_Parser parser,
break;
}
}
- role = XmlTokenRole(&prologState, tok, s, next, enc);
+ role = XmlTokenRole(&parser->m_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;
+ enc = parser->m_encoding;
handleDefault = XML_FALSE;
}
break;
case XML_ROLE_DOCTYPE_NAME:
- if (startDoctypeDeclHandler) {
- doctypeName = poolStoreString(&tempPool, enc, s, next);
- if (!doctypeName)
+ if (parser->m_startDoctypeDeclHandler) {
+ parser->m_doctypeName = poolStoreString(&parser->m_tempPool, enc, s, next);
+ if (!parser->m_doctypeName)
return XML_ERROR_NO_MEMORY;
- poolFinish(&tempPool);
- doctypePubid = NULL;
+ poolFinish(&parser->m_tempPool);
+ parser->m_doctypePubid = NULL;
handleDefault = XML_FALSE;
}
- doctypeSysid = NULL; /* always initialize to NULL */
+ parser->m_doctypeSysid = NULL; /* always initialize to NULL */
break;
case XML_ROLE_DOCTYPE_INTERNAL_SUBSET:
- if (startDoctypeDeclHandler) {
- startDoctypeDeclHandler(handlerArg, doctypeName, doctypeSysid,
- doctypePubid, 1);
- doctypeName = NULL;
- poolClear(&tempPool);
+ if (parser->m_startDoctypeDeclHandler) {
+ parser->m_startDoctypeDeclHandler(parser->m_handlerArg, parser->m_doctypeName, parser->m_doctypeSysid,
+ parser->m_doctypePubid, 1);
+ parser->m_doctypeName = NULL;
+ poolClear(&parser->m_tempPool);
handleDefault = XML_FALSE;
}
break;
@@ -3863,34 +4131,34 @@ doProlog(XML_Parser parser,
enum XML_Error result = processXmlDecl(parser, 1, s, next);
if (result != XML_ERROR_NONE)
return result;
- enc = encoding;
+ enc = parser->m_encoding;
handleDefault = XML_FALSE;
}
break;
#endif /* XML_DTD */
case XML_ROLE_DOCTYPE_PUBLIC_ID:
#ifdef XML_DTD
- useForeignDTD = XML_FALSE;
- declEntity = (ENTITY *)lookup(parser,
+ parser->m_useForeignDTD = XML_FALSE;
+ parser->m_declEntity = (ENTITY *)lookup(parser,
&dtd->paramEntities,
externalSubsetName,
sizeof(ENTITY));
- if (!declEntity)
+ if (!parser->m_declEntity)
return XML_ERROR_NO_MEMORY;
#endif /* XML_DTD */
dtd->hasParamEntityRefs = XML_TRUE;
- if (startDoctypeDeclHandler) {
+ if (parser->m_startDoctypeDeclHandler) {
XML_Char *pubId;
if (!XmlIsPublicId(enc, s, next, eventPP))
return XML_ERROR_PUBLICID;
- pubId = poolStoreString(&tempPool, enc,
+ pubId = poolStoreString(&parser->m_tempPool, enc,
s + enc->minBytesPerChar,
next - enc->minBytesPerChar);
if (!pubId)
return XML_ERROR_NO_MEMORY;
normalizePublicId(pubId);
- poolFinish(&tempPool);
- doctypePubid = pubId;
+ poolFinish(&parser->m_tempPool);
+ parser->m_doctypePubid = pubId;
handleDefault = XML_FALSE;
goto alreadyChecked;
}
@@ -3899,7 +4167,7 @@ doProlog(XML_Parser parser,
if (!XmlIsPublicId(enc, s, next, eventPP))
return XML_ERROR_PUBLICID;
alreadyChecked:
- if (dtd->keepProcessing && declEntity) {
+ if (dtd->keepProcessing && parser->m_declEntity) {
XML_Char *tem = poolStoreString(&dtd->pool,
enc,
s + enc->minBytesPerChar,
@@ -3907,38 +4175,43 @@ doProlog(XML_Parser parser,
if (!tem)
return XML_ERROR_NO_MEMORY;
normalizePublicId(tem);
- declEntity->publicId = tem;
+ parser->m_declEntity->publicId = tem;
poolFinish(&dtd->pool);
- if (entityDeclHandler)
+ if (parser->m_entityDeclHandler)
handleDefault = XML_FALSE;
}
break;
case XML_ROLE_DOCTYPE_CLOSE:
- if (doctypeName) {
- startDoctypeDeclHandler(handlerArg, doctypeName,
- doctypeSysid, doctypePubid, 0);
- poolClear(&tempPool);
+ if (allowClosingDoctype != XML_TRUE) {
+ /* Must not close doctype from within expanded parameter entities */
+ return XML_ERROR_INVALID_TOKEN;
+ }
+
+ if (parser->m_doctypeName) {
+ parser->m_startDoctypeDeclHandler(parser->m_handlerArg, parser->m_doctypeName,
+ parser->m_doctypeSysid, parser->m_doctypePubid, 0);
+ poolClear(&parser->m_tempPool);
handleDefault = XML_FALSE;
}
- /* doctypeSysid will be non-NULL in the case of a previous
- XML_ROLE_DOCTYPE_SYSTEM_ID, even if startDoctypeDeclHandler
+ /* parser->m_doctypeSysid will be non-NULL in the case of a previous
+ XML_ROLE_DOCTYPE_SYSTEM_ID, even if parser->m_startDoctypeDeclHandler
was not set, indicating an external subset
*/
#ifdef XML_DTD
- if (doctypeSysid || useForeignDTD) {
+ if (parser->m_doctypeSysid || parser->m_useForeignDTD) {
XML_Bool hadParamEntityRefs = dtd->hasParamEntityRefs;
dtd->hasParamEntityRefs = XML_TRUE;
- if (paramEntityParsing && externalEntityRefHandler) {
+ if (parser->m_paramEntityParsing && parser->m_externalEntityRefHandler) {
ENTITY *entity = (ENTITY *)lookup(parser,
&dtd->paramEntities,
externalSubsetName,
sizeof(ENTITY));
if (!entity)
return XML_ERROR_NO_MEMORY;
- if (useForeignDTD)
- entity->base = curBase;
+ if (parser->m_useForeignDTD)
+ entity->base = parser->m_curBase;
dtd->paramEntityRead = XML_FALSE;
- if (!externalEntityRefHandler(externalEntityRefHandlerArg,
+ if (!parser->m_externalEntityRefHandler(parser->m_externalEntityRefHandlerArg,
0,
entity->base,
entity->systemId,
@@ -3946,22 +4219,22 @@ doProlog(XML_Parser parser,
return XML_ERROR_EXTERNAL_ENTITY_HANDLING;
if (dtd->paramEntityRead) {
if (!dtd->standalone &&
- notStandaloneHandler &&
- !notStandaloneHandler(handlerArg))
+ parser->m_notStandaloneHandler &&
+ !parser->m_notStandaloneHandler(parser->m_handlerArg))
return XML_ERROR_NOT_STANDALONE;
}
/* if we didn't read the foreign DTD then this means that there
is no external subset and we must reset dtd->hasParamEntityRefs
*/
- else if (!doctypeSysid)
+ else if (!parser->m_doctypeSysid)
dtd->hasParamEntityRefs = hadParamEntityRefs;
/* end of DTD - no need to update dtd->keepProcessing */
}
- useForeignDTD = XML_FALSE;
+ parser->m_useForeignDTD = XML_FALSE;
}
#endif /* XML_DTD */
- if (endDoctypeDeclHandler) {
- endDoctypeDeclHandler(handlerArg);
+ if (parser->m_endDoctypeDeclHandler) {
+ parser->m_endDoctypeDeclHandler(parser->m_handlerArg);
handleDefault = XML_FALSE;
}
break;
@@ -3970,18 +4243,18 @@ doProlog(XML_Parser parser,
/* if there is no DOCTYPE declaration then now is the
last chance to read the foreign DTD
*/
- if (useForeignDTD) {
+ if (parser->m_useForeignDTD) {
XML_Bool hadParamEntityRefs = dtd->hasParamEntityRefs;
dtd->hasParamEntityRefs = XML_TRUE;
- if (paramEntityParsing && externalEntityRefHandler) {
+ if (parser->m_paramEntityParsing && parser->m_externalEntityRefHandler) {
ENTITY *entity = (ENTITY *)lookup(parser, &dtd->paramEntities,
externalSubsetName,
sizeof(ENTITY));
if (!entity)
return XML_ERROR_NO_MEMORY;
- entity->base = curBase;
+ entity->base = parser->m_curBase;
dtd->paramEntityRead = XML_FALSE;
- if (!externalEntityRefHandler(externalEntityRefHandlerArg,
+ if (!parser->m_externalEntityRefHandler(parser->m_externalEntityRefHandlerArg,
0,
entity->base,
entity->systemId,
@@ -3989,8 +4262,8 @@ doProlog(XML_Parser parser,
return XML_ERROR_EXTERNAL_ENTITY_HANDLING;
if (dtd->paramEntityRead) {
if (!dtd->standalone &&
- notStandaloneHandler &&
- !notStandaloneHandler(handlerArg))
+ parser->m_notStandaloneHandler &&
+ !parser->m_notStandaloneHandler(parser->m_handlerArg))
return XML_ERROR_NOT_STANDALONE;
}
/* if we didn't read the foreign DTD then this means that there
@@ -4002,55 +4275,55 @@ doProlog(XML_Parser parser,
}
}
#endif /* XML_DTD */
- processor = contentProcessor;
+ parser->m_processor = contentProcessor;
return contentProcessor(parser, s, end, nextPtr);
case XML_ROLE_ATTLIST_ELEMENT_NAME:
- declElementType = getElementType(parser, enc, s, next);
- if (!declElementType)
+ parser->m_declElementType = getElementType(parser, enc, s, next);
+ if (!parser->m_declElementType)
return XML_ERROR_NO_MEMORY;
goto checkAttListDeclHandler;
case XML_ROLE_ATTRIBUTE_NAME:
- declAttributeId = getAttributeId(parser, enc, s, next);
- if (!declAttributeId)
+ parser->m_declAttributeId = getAttributeId(parser, enc, s, next);
+ if (!parser->m_declAttributeId)
return XML_ERROR_NO_MEMORY;
- declAttributeIsCdata = XML_FALSE;
- declAttributeType = NULL;
- declAttributeIsId = XML_FALSE;
+ parser->m_declAttributeIsCdata = XML_FALSE;
+ parser->m_declAttributeType = NULL;
+ parser->m_declAttributeIsId = XML_FALSE;
goto checkAttListDeclHandler;
case XML_ROLE_ATTRIBUTE_TYPE_CDATA:
- declAttributeIsCdata = XML_TRUE;
- declAttributeType = atypeCDATA;
+ parser->m_declAttributeIsCdata = XML_TRUE;
+ parser->m_declAttributeType = atypeCDATA;
goto checkAttListDeclHandler;
case XML_ROLE_ATTRIBUTE_TYPE_ID:
- declAttributeIsId = XML_TRUE;
- declAttributeType = atypeID;
+ parser->m_declAttributeIsId = XML_TRUE;
+ parser->m_declAttributeType = atypeID;
goto checkAttListDeclHandler;
case XML_ROLE_ATTRIBUTE_TYPE_IDREF:
- declAttributeType = atypeIDREF;
+ parser->m_declAttributeType = atypeIDREF;
goto checkAttListDeclHandler;
case XML_ROLE_ATTRIBUTE_TYPE_IDREFS:
- declAttributeType = atypeIDREFS;
+ parser->m_declAttributeType = atypeIDREFS;
goto checkAttListDeclHandler;
case XML_ROLE_ATTRIBUTE_TYPE_ENTITY:
- declAttributeType = atypeENTITY;
+ parser->m_declAttributeType = atypeENTITY;
goto checkAttListDeclHandler;
case XML_ROLE_ATTRIBUTE_TYPE_ENTITIES:
- declAttributeType = atypeENTITIES;
+ parser->m_declAttributeType = atypeENTITIES;
goto checkAttListDeclHandler;
case XML_ROLE_ATTRIBUTE_TYPE_NMTOKEN:
- declAttributeType = atypeNMTOKEN;
+ parser->m_declAttributeType = atypeNMTOKEN;
goto checkAttListDeclHandler;
case XML_ROLE_ATTRIBUTE_TYPE_NMTOKENS:
- declAttributeType = atypeNMTOKENS;
+ parser->m_declAttributeType = atypeNMTOKENS;
checkAttListDeclHandler:
- if (dtd->keepProcessing && attlistDeclHandler)
+ if (dtd->keepProcessing && parser->m_attlistDeclHandler)
handleDefault = XML_FALSE;
break;
case XML_ROLE_ATTRIBUTE_ENUM_VALUE:
case XML_ROLE_ATTRIBUTE_NOTATION_VALUE:
- if (dtd->keepProcessing && attlistDeclHandler) {
+ if (dtd->keepProcessing && parser->m_attlistDeclHandler) {
const XML_Char *prefix;
- if (declAttributeType) {
+ if (parser->m_declAttributeType) {
prefix = enumValueSep;
}
else {
@@ -4058,37 +4331,37 @@ doProlog(XML_Parser parser,
? notationPrefix
: enumValueStart);
}
- if (!poolAppendString(&tempPool, prefix))
+ if (!poolAppendString(&parser->m_tempPool, prefix))
return XML_ERROR_NO_MEMORY;
- if (!poolAppend(&tempPool, enc, s, next))
+ if (!poolAppend(&parser->m_tempPool, enc, s, next))
return XML_ERROR_NO_MEMORY;
- declAttributeType = tempPool.start;
+ parser->m_declAttributeType = parser->m_tempPool.start;
handleDefault = XML_FALSE;
}
break;
case XML_ROLE_IMPLIED_ATTRIBUTE_VALUE:
case XML_ROLE_REQUIRED_ATTRIBUTE_VALUE:
if (dtd->keepProcessing) {
- if (!defineAttribute(declElementType, declAttributeId,
- declAttributeIsCdata, declAttributeIsId,
+ if (!defineAttribute(parser->m_declElementType, parser->m_declAttributeId,
+ parser->m_declAttributeIsCdata, parser->m_declAttributeIsId,
0, parser))
return XML_ERROR_NO_MEMORY;
- if (attlistDeclHandler && declAttributeType) {
- if (*declAttributeType == XML_T(ASCII_LPAREN)
- || (*declAttributeType == XML_T(ASCII_N)
- && declAttributeType[1] == XML_T(ASCII_O))) {
+ if (parser->m_attlistDeclHandler && parser->m_declAttributeType) {
+ if (*parser->m_declAttributeType == XML_T(ASCII_LPAREN)
+ || (*parser->m_declAttributeType == XML_T(ASCII_N)
+ && parser->m_declAttributeType[1] == XML_T(ASCII_O))) {
/* Enumerated or Notation type */
- if (!poolAppendChar(&tempPool, XML_T(ASCII_RPAREN))
- || !poolAppendChar(&tempPool, XML_T('\0')))
+ if (!poolAppendChar(&parser->m_tempPool, XML_T(ASCII_RPAREN))
+ || !poolAppendChar(&parser->m_tempPool, XML_T('\0')))
return XML_ERROR_NO_MEMORY;
- declAttributeType = tempPool.start;
- poolFinish(&tempPool);
+ parser->m_declAttributeType = parser->m_tempPool.start;
+ poolFinish(&parser->m_tempPool);
}
*eventEndPP = s;
- attlistDeclHandler(handlerArg, declElementType->name,
- declAttributeId->name, declAttributeType,
+ parser->m_attlistDeclHandler(parser->m_handlerArg, parser->m_declElementType->name,
+ parser->m_declAttributeId->name, parser->m_declAttributeType,
0, role == XML_ROLE_REQUIRED_ATTRIBUTE_VALUE);
- poolClear(&tempPool);
+ poolClear(&parser->m_tempPool);
handleDefault = XML_FALSE;
}
}
@@ -4098,7 +4371,7 @@ doProlog(XML_Parser parser,
if (dtd->keepProcessing) {
const XML_Char *attVal;
enum XML_Error result =
- storeAttributeValue(parser, enc, declAttributeIsCdata,
+ storeAttributeValue(parser, enc, parser->m_declAttributeIsCdata,
s + enc->minBytesPerChar,
next - enc->minBytesPerChar,
&dtd->pool);
@@ -4107,26 +4380,26 @@ doProlog(XML_Parser parser,
attVal = poolStart(&dtd->pool);
poolFinish(&dtd->pool);
/* ID attributes aren't allowed to have a default */
- if (!defineAttribute(declElementType, declAttributeId,
- declAttributeIsCdata, XML_FALSE, attVal, parser))
+ if (!defineAttribute(parser->m_declElementType, parser->m_declAttributeId,
+ parser->m_declAttributeIsCdata, XML_FALSE, attVal, parser))
return XML_ERROR_NO_MEMORY;
- if (attlistDeclHandler && declAttributeType) {
- if (*declAttributeType == XML_T(ASCII_LPAREN)
- || (*declAttributeType == XML_T(ASCII_N)
- && declAttributeType[1] == XML_T(ASCII_O))) {
+ if (parser->m_attlistDeclHandler && parser->m_declAttributeType) {
+ if (*parser->m_declAttributeType == XML_T(ASCII_LPAREN)
+ || (*parser->m_declAttributeType == XML_T(ASCII_N)
+ && parser->m_declAttributeType[1] == XML_T(ASCII_O))) {
/* Enumerated or Notation type */
- if (!poolAppendChar(&tempPool, XML_T(ASCII_RPAREN))
- || !poolAppendChar(&tempPool, XML_T('\0')))
+ if (!poolAppendChar(&parser->m_tempPool, XML_T(ASCII_RPAREN))
+ || !poolAppendChar(&parser->m_tempPool, XML_T('\0')))
return XML_ERROR_NO_MEMORY;
- declAttributeType = tempPool.start;
- poolFinish(&tempPool);
+ parser->m_declAttributeType = parser->m_tempPool.start;
+ poolFinish(&parser->m_tempPool);
}
*eventEndPP = s;
- attlistDeclHandler(handlerArg, declElementType->name,
- declAttributeId->name, declAttributeType,
+ parser->m_attlistDeclHandler(parser->m_handlerArg, parser->m_declElementType->name,
+ parser->m_declAttributeId->name, parser->m_declAttributeType,
attVal,
role == XML_ROLE_FIXED_ATTRIBUTE_VALUE);
- poolClear(&tempPool);
+ poolClear(&parser->m_tempPool);
handleDefault = XML_FALSE;
}
}
@@ -4136,18 +4409,18 @@ doProlog(XML_Parser parser,
enum XML_Error result = storeEntityValue(parser, enc,
s + enc->minBytesPerChar,
next - enc->minBytesPerChar);
- if (declEntity) {
- declEntity->textPtr = poolStart(&dtd->entityValuePool);
- declEntity->textLen = (int)(poolLength(&dtd->entityValuePool));
+ if (parser->m_declEntity) {
+ parser->m_declEntity->textPtr = poolStart(&dtd->entityValuePool);
+ parser->m_declEntity->textLen = (int)(poolLength(&dtd->entityValuePool));
poolFinish(&dtd->entityValuePool);
- if (entityDeclHandler) {
+ if (parser->m_entityDeclHandler) {
*eventEndPP = s;
- entityDeclHandler(handlerArg,
- declEntity->name,
- declEntity->is_param,
- declEntity->textPtr,
- declEntity->textLen,
- curBase, 0, 0, 0);
+ parser->m_entityDeclHandler(parser->m_handlerArg,
+ parser->m_declEntity->name,
+ parser->m_declEntity->is_param,
+ parser->m_declEntity->textPtr,
+ parser->m_declEntity->textLen,
+ parser->m_curBase, 0, 0, 0);
handleDefault = XML_FALSE;
}
}
@@ -4159,97 +4432,97 @@ doProlog(XML_Parser parser,
break;
case XML_ROLE_DOCTYPE_SYSTEM_ID:
#ifdef XML_DTD
- useForeignDTD = XML_FALSE;
+ parser->m_useForeignDTD = XML_FALSE;
#endif /* XML_DTD */
dtd->hasParamEntityRefs = XML_TRUE;
- if (startDoctypeDeclHandler) {
- doctypeSysid = poolStoreString(&tempPool, enc,
+ if (parser->m_startDoctypeDeclHandler) {
+ parser->m_doctypeSysid = poolStoreString(&parser->m_tempPool, enc,
s + enc->minBytesPerChar,
next - enc->minBytesPerChar);
- if (doctypeSysid == NULL)
+ if (parser->m_doctypeSysid == NULL)
return XML_ERROR_NO_MEMORY;
- poolFinish(&tempPool);
+ poolFinish(&parser->m_tempPool);
handleDefault = XML_FALSE;
}
#ifdef XML_DTD
else
- /* use externalSubsetName to make doctypeSysid non-NULL
- for the case where no startDoctypeDeclHandler is set */
- doctypeSysid = externalSubsetName;
+ /* use externalSubsetName to make parser->m_doctypeSysid non-NULL
+ for the case where no parser->m_startDoctypeDeclHandler is set */
+ parser->m_doctypeSysid = externalSubsetName;
#endif /* XML_DTD */
if (!dtd->standalone
#ifdef XML_DTD
- && !paramEntityParsing
+ && !parser->m_paramEntityParsing
#endif /* XML_DTD */
- && notStandaloneHandler
- && !notStandaloneHandler(handlerArg))
+ && parser->m_notStandaloneHandler
+ && !parser->m_notStandaloneHandler(parser->m_handlerArg))
return XML_ERROR_NOT_STANDALONE;
#ifndef XML_DTD
break;
#else /* XML_DTD */
- if (!declEntity) {
- declEntity = (ENTITY *)lookup(parser,
+ if (!parser->m_declEntity) {
+ parser->m_declEntity = (ENTITY *)lookup(parser,
&dtd->paramEntities,
externalSubsetName,
sizeof(ENTITY));
- if (!declEntity)
+ if (!parser->m_declEntity)
return XML_ERROR_NO_MEMORY;
- declEntity->publicId = NULL;
+ parser->m_declEntity->publicId = NULL;
}
/* fall through */
#endif /* XML_DTD */
case XML_ROLE_ENTITY_SYSTEM_ID:
- if (dtd->keepProcessing && declEntity) {
- declEntity->systemId = poolStoreString(&dtd->pool, enc,
+ if (dtd->keepProcessing && parser->m_declEntity) {
+ parser->m_declEntity->systemId = poolStoreString(&dtd->pool, enc,
s + enc->minBytesPerChar,
next - enc->minBytesPerChar);
- if (!declEntity->systemId)
+ if (!parser->m_declEntity->systemId)
return XML_ERROR_NO_MEMORY;
- declEntity->base = curBase;
+ parser->m_declEntity->base = parser->m_curBase;
poolFinish(&dtd->pool);
- if (entityDeclHandler)
+ if (parser->m_entityDeclHandler)
handleDefault = XML_FALSE;
}
break;
case XML_ROLE_ENTITY_COMPLETE:
- if (dtd->keepProcessing && declEntity && entityDeclHandler) {
+ if (dtd->keepProcessing && parser->m_declEntity && parser->m_entityDeclHandler) {
*eventEndPP = s;
- entityDeclHandler(handlerArg,
- declEntity->name,
- declEntity->is_param,
+ parser->m_entityDeclHandler(parser->m_handlerArg,
+ parser->m_declEntity->name,
+ parser->m_declEntity->is_param,
0,0,
- declEntity->base,
- declEntity->systemId,
- declEntity->publicId,
+ parser->m_declEntity->base,
+ parser->m_declEntity->systemId,
+ parser->m_declEntity->publicId,
0);
handleDefault = XML_FALSE;
}
break;
case XML_ROLE_ENTITY_NOTATION_NAME:
- if (dtd->keepProcessing && declEntity) {
- declEntity->notation = poolStoreString(&dtd->pool, enc, s, next);
- if (!declEntity->notation)
+ if (dtd->keepProcessing && parser->m_declEntity) {
+ parser->m_declEntity->notation = poolStoreString(&dtd->pool, enc, s, next);
+ if (!parser->m_declEntity->notation)
return XML_ERROR_NO_MEMORY;
poolFinish(&dtd->pool);
- if (unparsedEntityDeclHandler) {
+ if (parser->m_unparsedEntityDeclHandler) {
*eventEndPP = s;
- unparsedEntityDeclHandler(handlerArg,
- declEntity->name,
- declEntity->base,
- declEntity->systemId,
- declEntity->publicId,
- declEntity->notation);
+ parser->m_unparsedEntityDeclHandler(parser->m_handlerArg,
+ parser->m_declEntity->name,
+ parser->m_declEntity->base,
+ parser->m_declEntity->systemId,
+ parser->m_declEntity->publicId,
+ parser->m_declEntity->notation);
handleDefault = XML_FALSE;
}
- else if (entityDeclHandler) {
+ else if (parser->m_entityDeclHandler) {
*eventEndPP = s;
- entityDeclHandler(handlerArg,
- declEntity->name,
+ parser->m_entityDeclHandler(parser->m_handlerArg,
+ parser->m_declEntity->name,
0,0,0,
- declEntity->base,
- declEntity->systemId,
- declEntity->publicId,
- declEntity->notation);
+ parser->m_declEntity->base,
+ parser->m_declEntity->systemId,
+ parser->m_declEntity->publicId,
+ parser->m_declEntity->notation);
handleDefault = XML_FALSE;
}
}
@@ -4257,36 +4530,36 @@ doProlog(XML_Parser parser,
case XML_ROLE_GENERAL_ENTITY_NAME:
{
if (XmlPredefinedEntityName(enc, s, next)) {
- declEntity = NULL;
+ parser->m_declEntity = NULL;
break;
}
if (dtd->keepProcessing) {
const XML_Char *name = poolStoreString(&dtd->pool, enc, s, next);
if (!name)
return XML_ERROR_NO_MEMORY;
- declEntity = (ENTITY *)lookup(parser, &dtd->generalEntities, name,
+ parser->m_declEntity = (ENTITY *)lookup(parser, &dtd->generalEntities, name,
sizeof(ENTITY));
- if (!declEntity)
+ if (!parser->m_declEntity)
return XML_ERROR_NO_MEMORY;
- if (declEntity->name != name) {
+ if (parser->m_declEntity->name != name) {
poolDiscard(&dtd->pool);
- declEntity = NULL;
+ parser->m_declEntity = NULL;
}
else {
poolFinish(&dtd->pool);
- declEntity->publicId = NULL;
- declEntity->is_param = XML_FALSE;
+ parser->m_declEntity->publicId = NULL;
+ parser->m_declEntity->is_param = XML_FALSE;
/* if we have a parent parser or are reading an internal parameter
entity, then the entity declaration is not considered "internal"
*/
- declEntity->is_internal = !(parentParser || openInternalEntities);
- if (entityDeclHandler)
+ parser->m_declEntity->is_internal = !(parser->m_parentParser || parser->m_openInternalEntities);
+ if (parser->m_entityDeclHandler)
handleDefault = XML_FALSE;
}
}
else {
poolDiscard(&dtd->pool);
- declEntity = NULL;
+ parser->m_declEntity = NULL;
}
}
break;
@@ -4296,90 +4569,90 @@ doProlog(XML_Parser parser,
const XML_Char *name = poolStoreString(&dtd->pool, enc, s, next);
if (!name)
return XML_ERROR_NO_MEMORY;
- declEntity = (ENTITY *)lookup(parser, &dtd->paramEntities,
+ parser->m_declEntity = (ENTITY *)lookup(parser, &dtd->paramEntities,
name, sizeof(ENTITY));
- if (!declEntity)
+ if (!parser->m_declEntity)
return XML_ERROR_NO_MEMORY;
- if (declEntity->name != name) {
+ if (parser->m_declEntity->name != name) {
poolDiscard(&dtd->pool);
- declEntity = NULL;
+ parser->m_declEntity = NULL;
}
else {
poolFinish(&dtd->pool);
- declEntity->publicId = NULL;
- declEntity->is_param = XML_TRUE;
+ parser->m_declEntity->publicId = NULL;
+ parser->m_declEntity->is_param = XML_TRUE;
/* if we have a parent parser or are reading an internal parameter
entity, then the entity declaration is not considered "internal"
*/
- declEntity->is_internal = !(parentParser || openInternalEntities);
- if (entityDeclHandler)
+ parser->m_declEntity->is_internal = !(parser->m_parentParser || parser->m_openInternalEntities);
+ if (parser->m_entityDeclHandler)
handleDefault = XML_FALSE;
}
}
else {
poolDiscard(&dtd->pool);
- declEntity = NULL;
+ parser->m_declEntity = NULL;
}
#else /* not XML_DTD */
- declEntity = NULL;
+ parser->m_declEntity = NULL;
#endif /* XML_DTD */
break;
case XML_ROLE_NOTATION_NAME:
- declNotationPublicId = NULL;
- declNotationName = NULL;
- if (notationDeclHandler) {
- declNotationName = poolStoreString(&tempPool, enc, s, next);
- if (!declNotationName)
+ parser->m_declNotationPublicId = NULL;
+ parser->m_declNotationName = NULL;
+ if (parser->m_notationDeclHandler) {
+ parser->m_declNotationName = poolStoreString(&parser->m_tempPool, enc, s, next);
+ if (!parser->m_declNotationName)
return XML_ERROR_NO_MEMORY;
- poolFinish(&tempPool);
+ poolFinish(&parser->m_tempPool);
handleDefault = XML_FALSE;
}
break;
case XML_ROLE_NOTATION_PUBLIC_ID:
if (!XmlIsPublicId(enc, s, next, eventPP))
return XML_ERROR_PUBLICID;
- if (declNotationName) { /* means notationDeclHandler != NULL */
- XML_Char *tem = poolStoreString(&tempPool,
+ if (parser->m_declNotationName) { /* means m_notationDeclHandler != NULL */
+ XML_Char *tem = poolStoreString(&parser->m_tempPool,
enc,
s + enc->minBytesPerChar,
next - enc->minBytesPerChar);
if (!tem)
return XML_ERROR_NO_MEMORY;
normalizePublicId(tem);
- declNotationPublicId = tem;
- poolFinish(&tempPool);
+ parser->m_declNotationPublicId = tem;
+ poolFinish(&parser->m_tempPool);
handleDefault = XML_FALSE;
}
break;
case XML_ROLE_NOTATION_SYSTEM_ID:
- if (declNotationName && notationDeclHandler) {
+ if (parser->m_declNotationName && parser->m_notationDeclHandler) {
const XML_Char *systemId
- = poolStoreString(&tempPool, enc,
+ = poolStoreString(&parser->m_tempPool, enc,
s + enc->minBytesPerChar,
next - enc->minBytesPerChar);
if (!systemId)
return XML_ERROR_NO_MEMORY;
*eventEndPP = s;
- notationDeclHandler(handlerArg,
- declNotationName,
- curBase,
+ parser->m_notationDeclHandler(parser->m_handlerArg,
+ parser->m_declNotationName,
+ parser->m_curBase,
systemId,
- declNotationPublicId);
+ parser->m_declNotationPublicId);
handleDefault = XML_FALSE;
}
- poolClear(&tempPool);
+ poolClear(&parser->m_tempPool);
break;
case XML_ROLE_NOTATION_NO_SYSTEM_ID:
- if (declNotationPublicId && notationDeclHandler) {
+ if (parser->m_declNotationPublicId && parser->m_notationDeclHandler) {
*eventEndPP = s;
- notationDeclHandler(handlerArg,
- declNotationName,
- curBase,
+ parser->m_notationDeclHandler(parser->m_handlerArg,
+ parser->m_declNotationName,
+ parser->m_curBase,
0,
- declNotationPublicId);
+ parser->m_declNotationPublicId);
handleDefault = XML_FALSE;
}
- poolClear(&tempPool);
+ poolClear(&parser->m_tempPool);
break;
case XML_ROLE_ERROR:
switch (tok) {
@@ -4396,41 +4669,56 @@ doProlog(XML_Parser parser,
case XML_ROLE_IGNORE_SECT:
{
enum XML_Error result;
- if (defaultHandler)
+ if (parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
handleDefault = XML_FALSE;
result = doIgnoreSection(parser, enc, &next, end, nextPtr, haveMore);
if (result != XML_ERROR_NONE)
return result;
else if (!next) {
- processor = ignoreSectionProcessor;
+ parser->m_processor = ignoreSectionProcessor;
return result;
}
}
break;
#endif /* XML_DTD */
case XML_ROLE_GROUP_OPEN:
- if (prologState.level >= groupSize) {
- if (groupSize) {
- char *temp = (char *)REALLOC(groupConnector, groupSize *= 2);
+ if (parser->m_prologState.level >= parser->m_groupSize) {
+ if (parser->m_groupSize) {
+ /* Detect and prevent integer overflow */
+ if (parser->m_groupSize > (unsigned int)(-1) / 2u) {
+ return XML_ERROR_NO_MEMORY;
+ }
+
+ char *temp = (char *)REALLOC(parser, parser->m_groupConnector, parser->m_groupSize *= 2);
if (temp == NULL)
return XML_ERROR_NO_MEMORY;
- groupConnector = temp;
+ parser->m_groupConnector = temp;
if (dtd->scaffIndex) {
- int *temp = (int *)REALLOC(dtd->scaffIndex,
- groupSize * sizeof(int));
+ /* Detect and prevent integer overflow.
+ * The preprocessor guard addresses the "always false" warning
+ * from -Wtype-limits on platforms where
+ * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */
+#if UINT_MAX >= SIZE_MAX
+ if (parser->m_groupSize > (size_t)(-1) / sizeof(int)) {
+ return XML_ERROR_NO_MEMORY;
+ }
+#endif
+
+ int *temp = (int *)REALLOC(parser, dtd->scaffIndex,
+ parser->m_groupSize * sizeof(int));
if (temp == NULL)
return XML_ERROR_NO_MEMORY;
dtd->scaffIndex = temp;
}
}
else {
- groupConnector = (char *)MALLOC(groupSize = 32);
- if (!groupConnector)
+ parser->m_groupConnector = (char *)MALLOC(parser, parser->m_groupSize = 32);
+ if (!parser->m_groupConnector)
return XML_ERROR_NO_MEMORY;
}
}
- groupConnector[prologState.level] = 0;
+ parser->m_groupConnector[parser->m_prologState.level] = 0;
if (dtd->in_eldecl) {
int myindex = nextScaffoldPart(parser);
if (myindex < 0)
@@ -4438,37 +4726,37 @@ doProlog(XML_Parser parser,
dtd->scaffIndex[dtd->scaffLevel] = myindex;
dtd->scaffLevel++;
dtd->scaffold[myindex].type = XML_CTYPE_SEQ;
- if (elementDeclHandler)
+ if (parser->m_elementDeclHandler)
handleDefault = XML_FALSE;
}
break;
case XML_ROLE_GROUP_SEQUENCE:
- if (groupConnector[prologState.level] == ASCII_PIPE)
+ if (parser->m_groupConnector[parser->m_prologState.level] == ASCII_PIPE)
return XML_ERROR_SYNTAX;
- groupConnector[prologState.level] = ASCII_COMMA;
- if (dtd->in_eldecl && elementDeclHandler)
+ parser->m_groupConnector[parser->m_prologState.level] = ASCII_COMMA;
+ if (dtd->in_eldecl && parser->m_elementDeclHandler)
handleDefault = XML_FALSE;
break;
case XML_ROLE_GROUP_CHOICE:
- if (groupConnector[prologState.level] == ASCII_COMMA)
+ if (parser->m_groupConnector[parser->m_prologState.level] == ASCII_COMMA)
return XML_ERROR_SYNTAX;
if (dtd->in_eldecl
- && !groupConnector[prologState.level]
+ && !parser->m_groupConnector[parser->m_prologState.level]
&& (dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel - 1]].type
!= XML_CTYPE_MIXED)
) {
dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel - 1]].type
= XML_CTYPE_CHOICE;
- if (elementDeclHandler)
+ if (parser->m_elementDeclHandler)
handleDefault = XML_FALSE;
}
- groupConnector[prologState.level] = ASCII_PIPE;
+ parser->m_groupConnector[parser->m_prologState.level] = ASCII_PIPE;
break;
case XML_ROLE_PARAM_ENTITY_REF:
#ifdef XML_DTD
case XML_ROLE_INNER_PARAM_ENTITY_REF:
dtd->hasParamEntityRefs = XML_TRUE;
- if (!paramEntityParsing)
+ if (!parser->m_paramEntityParsing)
dtd->keepProcessing = dtd->standalone;
else {
const XML_Char *name;
@@ -4484,9 +4772,9 @@ doProlog(XML_Parser parser,
if yes, check that the entity exists, and that it is internal,
otherwise call the skipped entity handler
*/
- if (prologState.documentEntity &&
+ if (parser->m_prologState.documentEntity &&
(dtd->standalone
- ? !openInternalEntities
+ ? !parser->m_openInternalEntities
: !dtd->hasParamEntityRefs)) {
if (!entity)
return XML_ERROR_UNDEFINED_ENTITY;
@@ -4496,8 +4784,8 @@ doProlog(XML_Parser parser,
else if (!entity) {
dtd->keepProcessing = dtd->standalone;
/* cannot report skipped entities in declarations */
- if ((role == XML_ROLE_PARAM_ENTITY_REF) && skippedEntityHandler) {
- skippedEntityHandler(handlerArg, name, 1);
+ if ((role == XML_ROLE_PARAM_ENTITY_REF) && parser->m_skippedEntityHandler) {
+ parser->m_skippedEntityHandler(parser->m_handlerArg, name, 1);
handleDefault = XML_FALSE;
}
break;
@@ -4514,10 +4802,10 @@ doProlog(XML_Parser parser,
handleDefault = XML_FALSE;
break;
}
- if (externalEntityRefHandler) {
+ if (parser->m_externalEntityRefHandler) {
dtd->paramEntityRead = XML_FALSE;
entity->open = XML_TRUE;
- if (!externalEntityRefHandler(externalEntityRefHandlerArg,
+ if (!parser->m_externalEntityRefHandler(parser->m_externalEntityRefHandlerArg,
0,
entity->base,
entity->systemId,
@@ -4539,17 +4827,17 @@ doProlog(XML_Parser parser,
}
#endif /* XML_DTD */
if (!dtd->standalone &&
- notStandaloneHandler &&
- !notStandaloneHandler(handlerArg))
+ parser->m_notStandaloneHandler &&
+ !parser->m_notStandaloneHandler(parser->m_handlerArg))
return XML_ERROR_NOT_STANDALONE;
break;
/* Element declaration stuff */
case XML_ROLE_ELEMENT_NAME:
- if (elementDeclHandler) {
- declElementType = getElementType(parser, enc, s, next);
- if (!declElementType)
+ if (parser->m_elementDeclHandler) {
+ parser->m_declElementType = getElementType(parser, enc, s, next);
+ if (!parser->m_declElementType)
return XML_ERROR_NO_MEMORY;
dtd->scaffLevel = 0;
dtd->scaffCount = 0;
@@ -4561,8 +4849,8 @@ doProlog(XML_Parser parser,
case XML_ROLE_CONTENT_ANY:
case XML_ROLE_CONTENT_EMPTY:
if (dtd->in_eldecl) {
- if (elementDeclHandler) {
- XML_Content * content = (XML_Content *) MALLOC(sizeof(XML_Content));
+ if (parser->m_elementDeclHandler) {
+ XML_Content * content = (XML_Content *) MALLOC(parser, sizeof(XML_Content));
if (!content)
return XML_ERROR_NO_MEMORY;
content->quant = XML_CQUANT_NONE;
@@ -4573,7 +4861,7 @@ doProlog(XML_Parser parser,
XML_CTYPE_ANY :
XML_CTYPE_EMPTY);
*eventEndPP = s;
- elementDeclHandler(handlerArg, declElementType->name, content);
+ parser->m_elementDeclHandler(parser->m_handlerArg, parser->m_declElementType->name, content);
handleDefault = XML_FALSE;
}
dtd->in_eldecl = XML_FALSE;
@@ -4584,7 +4872,7 @@ doProlog(XML_Parser parser,
if (dtd->in_eldecl) {
dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel - 1]].type
= XML_CTYPE_MIXED;
- if (elementDeclHandler)
+ if (parser->m_elementDeclHandler)
handleDefault = XML_FALSE;
}
break;
@@ -4604,7 +4892,7 @@ doProlog(XML_Parser parser,
if (dtd->in_eldecl) {
ELEMENT_TYPE *el;
const XML_Char *name;
- int nameLen;
+ size_t nameLen;
const char *nxt = (quant == XML_CQUANT_NONE
? next
: next - enc->minBytesPerChar);
@@ -4620,8 +4908,14 @@ doProlog(XML_Parser parser,
dtd->scaffold[myindex].name = name;
nameLen = 0;
for (; name[nameLen++]; );
- dtd->contentStringLen += nameLen;
- if (elementDeclHandler)
+
+ /* Detect and prevent integer overflow */
+ if (nameLen > UINT_MAX - dtd->contentStringLen) {
+ return XML_ERROR_NO_MEMORY;
+ }
+
+ dtd->contentStringLen += (unsigned)nameLen;
+ if (parser->m_elementDeclHandler)
handleDefault = XML_FALSE;
}
break;
@@ -4639,7 +4933,7 @@ doProlog(XML_Parser parser,
quant = XML_CQUANT_PLUS;
closeGroup:
if (dtd->in_eldecl) {
- if (elementDeclHandler)
+ if (parser->m_elementDeclHandler)
handleDefault = XML_FALSE;
dtd->scaffLevel--;
dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel]].quant = quant;
@@ -4649,7 +4943,7 @@ doProlog(XML_Parser parser,
if (!model)
return XML_ERROR_NO_MEMORY;
*eventEndPP = s;
- elementDeclHandler(handlerArg, declElementType->name, model);
+ parser->m_elementDeclHandler(parser->m_handlerArg, parser->m_declElementType->name, model);
}
dtd->in_eldecl = XML_FALSE;
dtd->contentStringLen = 0;
@@ -4676,31 +4970,31 @@ doProlog(XML_Parser parser,
}
break;
case XML_ROLE_DOCTYPE_NONE:
- if (startDoctypeDeclHandler)
+ if (parser->m_startDoctypeDeclHandler)
handleDefault = XML_FALSE;
break;
case XML_ROLE_ENTITY_NONE:
- if (dtd->keepProcessing && entityDeclHandler)
+ if (dtd->keepProcessing && parser->m_entityDeclHandler)
handleDefault = XML_FALSE;
break;
case XML_ROLE_NOTATION_NONE:
- if (notationDeclHandler)
+ if (parser->m_notationDeclHandler)
handleDefault = XML_FALSE;
break;
case XML_ROLE_ATTLIST_NONE:
- if (dtd->keepProcessing && attlistDeclHandler)
+ if (dtd->keepProcessing && parser->m_attlistDeclHandler)
handleDefault = XML_FALSE;
break;
case XML_ROLE_ELEMENT_NONE:
- if (elementDeclHandler)
+ if (parser->m_elementDeclHandler)
handleDefault = XML_FALSE;
break;
} /* end of big switch */
- if (handleDefault && defaultHandler)
+ if (handleDefault && parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
- switch (ps_parsing) {
+ switch (parser->m_parsingStatus.parsing) {
case XML_SUSPENDED:
*nextPtr = next;
return XML_ERROR_NONE;
@@ -4720,18 +5014,18 @@ epilogProcessor(XML_Parser parser,
const char *end,
const char **nextPtr)
{
- processor = epilogProcessor;
- eventPtr = s;
+ parser->m_processor = epilogProcessor;
+ parser->m_eventPtr = s;
for (;;) {
const char *next = NULL;
- int tok = XmlPrologTok(encoding, s, end, &next);
- eventEndPtr = next;
+ int tok = XmlPrologTok(parser->m_encoding, s, end, &next);
+ parser->m_eventEndPtr = next;
switch (tok) {
/* report partial linebreak - it might be the last token */
case -XML_TOK_PROLOG_S:
- if (defaultHandler) {
- reportDefault(parser, encoding, s, next);
- if (ps_parsing == XML_FINISHED)
+ if (parser->m_defaultHandler) {
+ reportDefault(parser, parser->m_encoding, s, next);
+ if (parser->m_parsingStatus.parsing == XML_FINISHED)
return XML_ERROR_ABORTED;
}
*nextPtr = next;
@@ -4740,28 +5034,28 @@ epilogProcessor(XML_Parser parser,
*nextPtr = s;
return XML_ERROR_NONE;
case XML_TOK_PROLOG_S:
- if (defaultHandler)
- reportDefault(parser, encoding, s, next);
+ if (parser->m_defaultHandler)
+ reportDefault(parser, parser->m_encoding, s, next);
break;
case XML_TOK_PI:
- if (!reportProcessingInstruction(parser, encoding, s, next))
+ if (!reportProcessingInstruction(parser, parser->m_encoding, s, next))
return XML_ERROR_NO_MEMORY;
break;
case XML_TOK_COMMENT:
- if (!reportComment(parser, encoding, s, next))
+ if (!reportComment(parser, parser->m_encoding, s, next))
return XML_ERROR_NO_MEMORY;
break;
case XML_TOK_INVALID:
- eventPtr = next;
+ parser->m_eventPtr = next;
return XML_ERROR_INVALID_TOKEN;
case XML_TOK_PARTIAL:
- if (!ps_finalBuffer) {
+ if (!parser->m_parsingStatus.finalBuffer) {
*nextPtr = s;
return XML_ERROR_NONE;
}
return XML_ERROR_UNCLOSED_TOKEN;
case XML_TOK_PARTIAL_CHAR:
- if (!ps_finalBuffer) {
+ if (!parser->m_parsingStatus.finalBuffer) {
*nextPtr = s;
return XML_ERROR_NONE;
}
@@ -4769,8 +5063,8 @@ epilogProcessor(XML_Parser parser,
default:
return XML_ERROR_JUNK_AFTER_DOC_ELEMENT;
}
- eventPtr = s = next;
- switch (ps_parsing) {
+ parser->m_eventPtr = s = next;
+ switch (parser->m_parsingStatus.parsing) {
case XML_SUSPENDED:
*nextPtr = next;
return XML_ERROR_NONE;
@@ -4790,21 +5084,21 @@ processInternalEntity(XML_Parser parser, ENTITY *entity,
enum XML_Error result;
OPEN_INTERNAL_ENTITY *openEntity;
- if (freeInternalEntities) {
- openEntity = freeInternalEntities;
- freeInternalEntities = openEntity->next;
+ if (parser->m_freeInternalEntities) {
+ openEntity = parser->m_freeInternalEntities;
+ parser->m_freeInternalEntities = openEntity->next;
}
else {
- openEntity = (OPEN_INTERNAL_ENTITY *)MALLOC(sizeof(OPEN_INTERNAL_ENTITY));
+ openEntity = (OPEN_INTERNAL_ENTITY *)MALLOC(parser, sizeof(OPEN_INTERNAL_ENTITY));
if (!openEntity)
return XML_ERROR_NO_MEMORY;
}
entity->open = XML_TRUE;
entity->processed = 0;
- openEntity->next = openInternalEntities;
- openInternalEntities = openEntity;
+ openEntity->next = parser->m_openInternalEntities;
+ parser->m_openInternalEntities = openEntity;
openEntity->entity = entity;
- openEntity->startTagLevel = tagLevel;
+ openEntity->startTagLevel = parser->m_tagLevel;
openEntity->betweenDecl = betweenDecl;
openEntity->internalEventPtr = NULL;
openEntity->internalEventEndPtr = NULL;
@@ -4813,26 +5107,26 @@ processInternalEntity(XML_Parser parser, ENTITY *entity,
#ifdef XML_DTD
if (entity->is_param) {
- int tok = XmlPrologTok(internalEncoding, textStart, textEnd, &next);
- result = doProlog(parser, internalEncoding, textStart, textEnd, tok,
- next, &next, XML_FALSE);
+ int tok = XmlPrologTok(parser->m_internalEncoding, textStart, textEnd, &next);
+ result = doProlog(parser, parser->m_internalEncoding, textStart, textEnd, tok,
+ next, &next, XML_FALSE, XML_FALSE);
}
else
#endif /* XML_DTD */
- result = doContent(parser, tagLevel, internalEncoding, textStart,
+ result = doContent(parser, parser->m_tagLevel, parser->m_internalEncoding, textStart,
textEnd, &next, XML_FALSE);
if (result == XML_ERROR_NONE) {
- if (textEnd != next && ps_parsing == XML_SUSPENDED) {
+ if (textEnd != next && parser->m_parsingStatus.parsing == XML_SUSPENDED) {
entity->processed = (int)(next - textStart);
- processor = internalEntityProcessor;
+ parser->m_processor = internalEntityProcessor;
}
else {
entity->open = XML_FALSE;
- openInternalEntities = openEntity->next;
+ parser->m_openInternalEntities = openEntity->next;
/* put openEntity back in list of free instances */
- openEntity->next = freeInternalEntities;
- freeInternalEntities = openEntity;
+ openEntity->next = parser->m_freeInternalEntities;
+ parser->m_freeInternalEntities = openEntity;
}
}
return result;
@@ -4848,7 +5142,7 @@ internalEntityProcessor(XML_Parser parser,
const char *textStart, *textEnd;
const char *next;
enum XML_Error result;
- OPEN_INTERNAL_ENTITY *openEntity = openInternalEntities;
+ OPEN_INTERNAL_ENTITY *openEntity = parser->m_openInternalEntities;
if (!openEntity)
return XML_ERROR_UNEXPECTED_STATE;
@@ -4858,44 +5152,50 @@ internalEntityProcessor(XML_Parser parser,
#ifdef XML_DTD
if (entity->is_param) {
- int tok = XmlPrologTok(internalEncoding, textStart, textEnd, &next);
- result = doProlog(parser, internalEncoding, textStart, textEnd, tok,
- next, &next, XML_FALSE);
+ int tok = XmlPrologTok(parser->m_internalEncoding, textStart, textEnd, &next);
+ result = doProlog(parser, parser->m_internalEncoding, textStart, textEnd, tok,
+ next, &next, XML_FALSE, XML_TRUE);
}
else
#endif /* XML_DTD */
- result = doContent(parser, openEntity->startTagLevel, internalEncoding,
+ result = doContent(parser, openEntity->startTagLevel, parser->m_internalEncoding,
textStart, textEnd, &next, XML_FALSE);
if (result != XML_ERROR_NONE)
return result;
- else if (textEnd != next && ps_parsing == XML_SUSPENDED) {
+ else if (textEnd != next && parser->m_parsingStatus.parsing == XML_SUSPENDED) {
entity->processed = (int)(next - (char *)entity->textPtr);
return result;
}
else {
entity->open = XML_FALSE;
- openInternalEntities = openEntity->next;
+ parser->m_openInternalEntities = openEntity->next;
/* put openEntity back in list of free instances */
- openEntity->next = freeInternalEntities;
- freeInternalEntities = openEntity;
+ openEntity->next = parser->m_freeInternalEntities;
+ parser->m_freeInternalEntities = openEntity;
}
#ifdef XML_DTD
if (entity->is_param) {
int tok;
- processor = prologProcessor;
- tok = XmlPrologTok(encoding, s, end, &next);
- return doProlog(parser, encoding, s, end, tok, next, nextPtr,
- (XML_Bool)!ps_finalBuffer);
+ parser->m_processor = prologProcessor;
+ tok = XmlPrologTok(parser->m_encoding, s, end, &next);
+ return doProlog(parser, parser->m_encoding, s, end, tok, next, nextPtr,
+ (XML_Bool)!parser->m_parsingStatus.finalBuffer, XML_TRUE);
}
else
#endif /* XML_DTD */
{
- processor = contentProcessor;
+ parser->m_processor = contentProcessor;
/* see externalEntityContentProcessor vs contentProcessor */
- return doContent(parser, parentParser ? 1 : 0, encoding, s, end,
- nextPtr, (XML_Bool)!ps_finalBuffer);
+ result = doContent(parser, parser->m_parentParser ? 1 : 0,
+ parser->m_encoding, s, end, nextPtr,
+ (XML_Bool)!parser->m_parsingStatus.finalBuffer);
+ if (result == XML_ERROR_NONE) {
+ if (! storeRawNames(parser))
+ return XML_ERROR_NO_MEMORY;
+ }
+ return result;
}
}
@@ -4909,7 +5209,7 @@ errorProcessor(XML_Parser parser,
UNUSED(end);
UNUSED(nextPtr);
- return errorCode;
+ return parser->m_errorCode;
}
static enum XML_Error
@@ -4933,7 +5233,7 @@ appendAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata,
const char *ptr, const char *end,
STRING_POOL *pool)
{
- DTD * const dtd = _dtd; /* save one level of indirection */
+ DTD * const dtd = parser->m_dtd; /* save one level of indirection */
for (;;) {
const char *next;
int tok = XmlAttributeValueTok(enc, ptr, end, &next);
@@ -4941,12 +5241,12 @@ appendAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata,
case XML_TOK_NONE:
return XML_ERROR_NONE;
case XML_TOK_INVALID:
- if (enc == encoding)
- eventPtr = next;
+ if (enc == parser->m_encoding)
+ parser->m_eventPtr = next;
return XML_ERROR_INVALID_TOKEN;
case XML_TOK_PARTIAL:
- if (enc == encoding)
- eventPtr = ptr;
+ if (enc == parser->m_encoding)
+ parser->m_eventPtr = ptr;
return XML_ERROR_INVALID_TOKEN;
case XML_TOK_CHAR_REF:
{
@@ -4954,8 +5254,8 @@ appendAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata,
int i;
int n = XmlCharRefNumber(enc, ptr);
if (n < 0) {
- if (enc == encoding)
- eventPtr = ptr;
+ if (enc == parser->m_encoding)
+ parser->m_eventPtr = ptr;
return XML_ERROR_BAD_CHAR_REF;
}
if (!isCdata
@@ -4964,8 +5264,8 @@ appendAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata,
break;
n = XmlEncode(n, (ICHAR *)buf);
if (!n) {
- if (enc == encoding)
- eventPtr = ptr;
+ if (enc == parser->m_encoding)
+ parser->m_eventPtr = ptr;
return XML_ERROR_BAD_CHAR_REF;
}
for (i = 0; i < n; i++) {
@@ -5001,25 +5301,25 @@ appendAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata,
return XML_ERROR_NO_MEMORY;
break;
}
- name = poolStoreString(&temp2Pool, enc,
+ name = poolStoreString(&parser->m_temp2Pool, enc,
ptr + enc->minBytesPerChar,
next - enc->minBytesPerChar);
if (!name)
return XML_ERROR_NO_MEMORY;
entity = (ENTITY *)lookup(parser, &dtd->generalEntities, name, 0);
- poolDiscard(&temp2Pool);
+ poolDiscard(&parser->m_temp2Pool);
/* First, determine if a check for an existing declaration is needed;
if yes, check that the entity exists, and that it is internal.
*/
if (pool == &dtd->pool) /* are we called from prolog? */
checkEntityDecl =
#ifdef XML_DTD
- prologState.documentEntity &&
+ parser->m_prologState.documentEntity &&
#endif /* XML_DTD */
(dtd->standalone
- ? !openInternalEntities
+ ? !parser->m_openInternalEntities
: !dtd->hasParamEntityRefs);
- else /* if (pool == &tempPool): we are called from content */
+ else /* if (pool == &parser->m_tempPool): we are called from content */
checkEntityDecl = !dtd->hasParamEntityRefs || dtd->standalone;
if (checkEntityDecl) {
if (!entity)
@@ -5029,37 +5329,37 @@ appendAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata,
}
else if (!entity) {
/* Cannot report skipped entity here - see comments on
- skippedEntityHandler.
- if (skippedEntityHandler)
- skippedEntityHandler(handlerArg, name, 0);
+ parser->m_skippedEntityHandler.
+ if (parser->m_skippedEntityHandler)
+ parser->m_skippedEntityHandler(parser->m_handlerArg, name, 0);
*/
/* Cannot call the default handler because this would be
out of sync with the call to the startElementHandler.
- if ((pool == &tempPool) && defaultHandler)
+ if ((pool == &parser->m_tempPool) && parser->m_defaultHandler)
reportDefault(parser, enc, ptr, next);
*/
break;
}
if (entity->open) {
- if (enc == encoding)
- eventPtr = ptr;
+ if (enc == parser->m_encoding)
+ parser->m_eventPtr = ptr;
return XML_ERROR_RECURSIVE_ENTITY_REF;
}
if (entity->notation) {
- if (enc == encoding)
- eventPtr = ptr;
+ if (enc == parser->m_encoding)
+ parser->m_eventPtr = ptr;
return XML_ERROR_BINARY_ENTITY_REF;
}
if (!entity->textPtr) {
- if (enc == encoding)
- eventPtr = ptr;
+ if (enc == parser->m_encoding)
+ parser->m_eventPtr = ptr;
return XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF;
}
else {
enum XML_Error result;
const XML_Char *textEnd = entity->textPtr + entity->textLen;
entity->open = XML_TRUE;
- result = appendAttributeValue(parser, internalEncoding, isCdata,
+ result = appendAttributeValue(parser, parser->m_internalEncoding, isCdata,
(char *)entity->textPtr,
(char *)textEnd, pool);
entity->open = XML_FALSE;
@@ -5069,8 +5369,8 @@ appendAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata,
}
break;
default:
- if (enc == encoding)
- eventPtr = ptr;
+ if (enc == parser->m_encoding)
+ parser->m_eventPtr = ptr;
return XML_ERROR_UNEXPECTED_STATE;
}
ptr = next;
@@ -5084,12 +5384,12 @@ storeEntityValue(XML_Parser parser,
const char *entityTextPtr,
const char *entityTextEnd)
{
- DTD * const dtd = _dtd; /* save one level of indirection */
+ DTD * const dtd = parser->m_dtd; /* save one level of indirection */
STRING_POOL *pool = &(dtd->entityValuePool);
enum XML_Error result = XML_ERROR_NONE;
#ifdef XML_DTD
- int oldInEntityValue = prologState.inEntityValue;
- prologState.inEntityValue = 1;
+ int oldInEntityValue = parser->m_prologState.inEntityValue;
+ parser->m_prologState.inEntityValue = 1;
#endif /* XML_DTD */
/* never return Null for the value argument in EntityDeclHandler,
since this would indicate an external entity; therefore we
@@ -5105,10 +5405,10 @@ storeEntityValue(XML_Parser parser,
switch (tok) {
case XML_TOK_PARAM_ENTITY_REF:
#ifdef XML_DTD
- if (isParamEntity || enc != encoding) {
+ if (parser->m_isParamEntity || enc != parser->m_encoding) {
const XML_Char *name;
ENTITY *entity;
- name = poolStoreString(&tempPool, enc,
+ name = poolStoreString(&parser->m_tempPool, enc,
entityTextPtr + enc->minBytesPerChar,
next - enc->minBytesPerChar);
if (!name) {
@@ -5116,28 +5416,28 @@ storeEntityValue(XML_Parser parser,
goto endEntityValue;
}
entity = (ENTITY *)lookup(parser, &dtd->paramEntities, name, 0);
- poolDiscard(&tempPool);
+ poolDiscard(&parser->m_tempPool);
if (!entity) {
/* not a well-formedness error - see XML 1.0: WFC Entity Declared */
/* cannot report skipped entity here - see comments on
- skippedEntityHandler
- if (skippedEntityHandler)
- skippedEntityHandler(handlerArg, name, 0);
+ parser->m_skippedEntityHandler
+ if (parser->m_skippedEntityHandler)
+ parser->m_skippedEntityHandler(parser->m_handlerArg, name, 0);
*/
dtd->keepProcessing = dtd->standalone;
goto endEntityValue;
}
if (entity->open) {
- if (enc == encoding)
- eventPtr = entityTextPtr;
+ if (enc == parser->m_encoding)
+ parser->m_eventPtr = entityTextPtr;
result = XML_ERROR_RECURSIVE_ENTITY_REF;
goto endEntityValue;
}
if (entity->systemId) {
- if (externalEntityRefHandler) {
+ if (parser->m_externalEntityRefHandler) {
dtd->paramEntityRead = XML_FALSE;
entity->open = XML_TRUE;
- if (!externalEntityRefHandler(externalEntityRefHandlerArg,
+ if (!parser->m_externalEntityRefHandler(parser->m_externalEntityRefHandlerArg,
0,
entity->base,
entity->systemId,
@@ -5156,7 +5456,7 @@ storeEntityValue(XML_Parser parser,
else {
entity->open = XML_TRUE;
result = storeEntityValue(parser,
- internalEncoding,
+ parser->m_internalEncoding,
(char *)entity->textPtr,
(char *)(entity->textPtr
+ entity->textLen));
@@ -5169,7 +5469,7 @@ storeEntityValue(XML_Parser parser,
#endif /* XML_DTD */
/* In the internal subset, PE references are not legal
within markup declarations, e.g entity values in this case. */
- eventPtr = entityTextPtr;
+ parser->m_eventPtr = entityTextPtr;
result = XML_ERROR_PARAM_ENTITY_REF;
goto endEntityValue;
case XML_TOK_NONE:
@@ -5198,15 +5498,15 @@ storeEntityValue(XML_Parser parser,
int i;
int n = XmlCharRefNumber(enc, entityTextPtr);
if (n < 0) {
- if (enc == encoding)
- eventPtr = entityTextPtr;
+ if (enc == parser->m_encoding)
+ parser->m_eventPtr = entityTextPtr;
result = XML_ERROR_BAD_CHAR_REF;
goto endEntityValue;
}
n = XmlEncode(n, (ICHAR *)buf);
if (!n) {
- if (enc == encoding)
- eventPtr = entityTextPtr;
+ if (enc == parser->m_encoding)
+ parser->m_eventPtr = entityTextPtr;
result = XML_ERROR_BAD_CHAR_REF;
goto endEntityValue;
}
@@ -5220,18 +5520,18 @@ storeEntityValue(XML_Parser parser,
}
break;
case XML_TOK_PARTIAL:
- if (enc == encoding)
- eventPtr = entityTextPtr;
+ if (enc == parser->m_encoding)
+ parser->m_eventPtr = entityTextPtr;
result = XML_ERROR_INVALID_TOKEN;
goto endEntityValue;
case XML_TOK_INVALID:
- if (enc == encoding)
- eventPtr = next;
+ if (enc == parser->m_encoding)
+ parser->m_eventPtr = next;
result = XML_ERROR_INVALID_TOKEN;
goto endEntityValue;
default:
- if (enc == encoding)
- eventPtr = entityTextPtr;
+ if (enc == parser->m_encoding)
+ parser->m_eventPtr = entityTextPtr;
result = XML_ERROR_UNEXPECTED_STATE;
goto endEntityValue;
}
@@ -5239,7 +5539,7 @@ storeEntityValue(XML_Parser parser,
}
endEntityValue:
#ifdef XML_DTD
- prologState.inEntityValue = oldInEntityValue;
+ parser->m_prologState.inEntityValue = oldInEntityValue;
#endif /* XML_DTD */
return result;
}
@@ -5274,25 +5574,25 @@ reportProcessingInstruction(XML_Parser parser, const ENCODING *enc,
const XML_Char *target;
XML_Char *data;
const char *tem;
- if (!processingInstructionHandler) {
- if (defaultHandler)
+ if (!parser->m_processingInstructionHandler) {
+ if (parser->m_defaultHandler)
reportDefault(parser, enc, start, end);
return 1;
}
start += enc->minBytesPerChar * 2;
tem = start + XmlNameLength(enc, start);
- target = poolStoreString(&tempPool, enc, start, tem);
+ target = poolStoreString(&parser->m_tempPool, enc, start, tem);
if (!target)
return 0;
- poolFinish(&tempPool);
- data = poolStoreString(&tempPool, enc,
+ poolFinish(&parser->m_tempPool);
+ data = poolStoreString(&parser->m_tempPool, enc,
XmlSkipS(enc, tem),
end - enc->minBytesPerChar*2);
if (!data)
return 0;
normalizeLines(data);
- processingInstructionHandler(handlerArg, target, data);
- poolClear(&tempPool);
+ parser->m_processingInstructionHandler(parser->m_handlerArg, target, data);
+ poolClear(&parser->m_tempPool);
return 1;
}
@@ -5301,20 +5601,20 @@ reportComment(XML_Parser parser, const ENCODING *enc,
const char *start, const char *end)
{
XML_Char *data;
- if (!commentHandler) {
- if (defaultHandler)
+ if (!parser->m_commentHandler) {
+ if (parser->m_defaultHandler)
reportDefault(parser, enc, start, end);
return 1;
}
- data = poolStoreString(&tempPool,
+ data = poolStoreString(&parser->m_tempPool,
enc,
start + enc->minBytesPerChar * 4,
end - enc->minBytesPerChar * 3);
if (!data)
return 0;
normalizeLines(data);
- commentHandler(handlerArg, data);
- poolClear(&tempPool);
+ parser->m_commentHandler(parser->m_handlerArg, data);
+ poolClear(&parser->m_tempPool);
return 1;
}
@@ -5323,26 +5623,27 @@ reportDefault(XML_Parser parser, const ENCODING *enc,
const char *s, const char *end)
{
if (MUST_CONVERT(enc, s)) {
+ enum XML_Convert_Result convert_res;
const char **eventPP;
const char **eventEndPP;
- if (enc == encoding) {
- eventPP = &eventPtr;
- eventEndPP = &eventEndPtr;
+ if (enc == parser->m_encoding) {
+ eventPP = &parser->m_eventPtr;
+ eventEndPP = &parser->m_eventEndPtr;
}
else {
- eventPP = &(openInternalEntities->internalEventPtr);
- eventEndPP = &(openInternalEntities->internalEventEndPtr);
+ eventPP = &(parser->m_openInternalEntities->internalEventPtr);
+ eventEndPP = &(parser->m_openInternalEntities->internalEventEndPtr);
}
do {
- ICHAR *dataPtr = (ICHAR *)dataBuf;
- XmlConvert(enc, &s, end, &dataPtr, (ICHAR *)dataBufEnd);
+ ICHAR *dataPtr = (ICHAR *)parser->m_dataBuf;
+ convert_res = XmlConvert(enc, &s, end, &dataPtr, (ICHAR *)parser->m_dataBufEnd);
*eventEndPP = s;
- defaultHandler(handlerArg, dataBuf, (int)(dataPtr - (ICHAR *)dataBuf));
+ parser->m_defaultHandler(parser->m_handlerArg, parser->m_dataBuf, (int)(dataPtr - (ICHAR *)parser->m_dataBuf));
*eventPP = s;
- } while (s != end);
+ } while ((convert_res != XML_CONVERT_COMPLETED) && (convert_res != XML_CONVERT_INPUT_INCOMPLETE));
}
else
- defaultHandler(handlerArg, (XML_Char *)s, (int)((XML_Char *)end - (XML_Char *)s));
+ parser->m_defaultHandler(parser->m_handlerArg, (XML_Char *)s, (int)((XML_Char *)end - (XML_Char *)s));
}
@@ -5364,16 +5665,33 @@ defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *attId, XML_Bool isCdata,
if (type->nDefaultAtts == type->allocDefaultAtts) {
if (type->allocDefaultAtts == 0) {
type->allocDefaultAtts = 8;
- type->defaultAtts = (DEFAULT_ATTRIBUTE *)MALLOC(type->allocDefaultAtts
+ type->defaultAtts = (DEFAULT_ATTRIBUTE *)MALLOC(parser, type->allocDefaultAtts
* sizeof(DEFAULT_ATTRIBUTE));
if (!type->defaultAtts)
return 0;
}
else {
DEFAULT_ATTRIBUTE *temp;
+
+ /* Detect and prevent integer overflow */
+ if (type->allocDefaultAtts > INT_MAX / 2) {
+ return 0;
+ }
+
int count = type->allocDefaultAtts * 2;
+
+ /* Detect and prevent integer overflow.
+ * The preprocessor guard addresses the "always false" warning
+ * from -Wtype-limits on platforms where
+ * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */
+#if UINT_MAX >= SIZE_MAX
+ if ((unsigned)count > (size_t)(-1) / sizeof(DEFAULT_ATTRIBUTE)) {
+ return 0;
+ }
+#endif
+
temp = (DEFAULT_ATTRIBUTE *)
- REALLOC(type->defaultAtts, (count * sizeof(DEFAULT_ATTRIBUTE)));
+ REALLOC(parser, type->defaultAtts, (count * sizeof(DEFAULT_ATTRIBUTE)));
if (temp == NULL)
return 0;
type->allocDefaultAtts = count;
@@ -5393,7 +5711,7 @@ defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *attId, XML_Bool isCdata,
static int
setElementTypePrefix(XML_Parser parser, ELEMENT_TYPE *elementType)
{
- DTD * const dtd = _dtd; /* save one level of indirection */
+ DTD * const dtd = parser->m_dtd; /* save one level of indirection */
const XML_Char *name;
for (name = elementType->name; *name; name++) {
if (*name == XML_T(ASCII_COLON)) {
@@ -5414,6 +5732,7 @@ setElementTypePrefix(XML_Parser parser, ELEMENT_TYPE *elementType)
else
poolDiscard(&dtd->pool);
elementType->prefix = prefix;
+ break;
}
}
@@ -5424,7 +5743,7 @@ static ATTRIBUTE_ID *
getAttributeId(XML_Parser parser, const ENCODING *enc,
const char *start, const char *end)
{
- DTD * const dtd = _dtd; /* save one level of indirection */
+ DTD * const dtd = parser->m_dtd; /* save one level of indirection */
ATTRIBUTE_ID *id;
const XML_Char *name;
if (!poolAppendChar(&dtd->pool, XML_T('\0')))
@@ -5441,7 +5760,7 @@ getAttributeId(XML_Parser parser, const ENCODING *enc,
poolDiscard(&dtd->pool);
else {
poolFinish(&dtd->pool);
- if (!ns)
+ if (!parser->m_ns)
;
else if (name[0] == XML_T(ASCII_x)
&& name[1] == XML_T(ASCII_m)
@@ -5469,6 +5788,8 @@ getAttributeId(XML_Parser parser, const ENCODING *enc,
return NULL;
id->prefix = (PREFIX *)lookup(parser, &dtd->prefixes, poolStart(&dtd->pool),
sizeof(PREFIX));
+ if (!id->prefix)
+ return NULL;
if (id->prefix->name == poolStart(&dtd->pool))
poolFinish(&dtd->pool);
else
@@ -5486,20 +5807,20 @@ getAttributeId(XML_Parser parser, const ENCODING *enc,
static const XML_Char *
getContext(XML_Parser parser)
{
- DTD * const dtd = _dtd; /* save one level of indirection */
+ DTD * const dtd = parser->m_dtd; /* save one level of indirection */
HASH_TABLE_ITER iter;
XML_Bool needSep = XML_FALSE;
if (dtd->defaultPrefix.binding) {
int i;
int len;
- if (!poolAppendChar(&tempPool, XML_T(ASCII_EQUALS)))
+ if (!poolAppendChar(&parser->m_tempPool, XML_T(ASCII_EQUALS)))
return NULL;
len = dtd->defaultPrefix.binding->uriLen;
- if (namespaceSeparator)
+ if (parser->m_namespaceSeparator)
len--;
for (i = 0; i < len; i++)
- if (!poolAppendChar(&tempPool, dtd->defaultPrefix.binding->uri[i]))
+ if (!poolAppendChar(&parser->m_tempPool, dtd->defaultPrefix.binding->uri[i]))
return NULL;
needSep = XML_TRUE;
}
@@ -5514,18 +5835,18 @@ getContext(XML_Parser parser)
break;
if (!prefix->binding)
continue;
- if (needSep && !poolAppendChar(&tempPool, CONTEXT_SEP))
+ if (needSep && !poolAppendChar(&parser->m_tempPool, CONTEXT_SEP))
return NULL;
for (s = prefix->name; *s; s++)
- if (!poolAppendChar(&tempPool, *s))
+ if (!poolAppendChar(&parser->m_tempPool, *s))
return NULL;
- if (!poolAppendChar(&tempPool, XML_T(ASCII_EQUALS)))
+ if (!poolAppendChar(&parser->m_tempPool, XML_T(ASCII_EQUALS)))
return NULL;
len = prefix->binding->uriLen;
- if (namespaceSeparator)
+ if (parser->m_namespaceSeparator)
len--;
for (i = 0; i < len; i++)
- if (!poolAppendChar(&tempPool, prefix->binding->uri[i]))
+ if (!poolAppendChar(&parser->m_tempPool, prefix->binding->uri[i]))
return NULL;
needSep = XML_TRUE;
}
@@ -5539,73 +5860,73 @@ getContext(XML_Parser parser)
break;
if (!e->open)
continue;
- if (needSep && !poolAppendChar(&tempPool, CONTEXT_SEP))
+ if (needSep && !poolAppendChar(&parser->m_tempPool, CONTEXT_SEP))
return NULL;
for (s = e->name; *s; s++)
- if (!poolAppendChar(&tempPool, *s))
+ if (!poolAppendChar(&parser->m_tempPool, *s))
return 0;
needSep = XML_TRUE;
}
- if (!poolAppendChar(&tempPool, XML_T('\0')))
+ if (!poolAppendChar(&parser->m_tempPool, XML_T('\0')))
return NULL;
- return tempPool.start;
+ return parser->m_tempPool.start;
}
static XML_Bool
setContext(XML_Parser parser, const XML_Char *context)
{
- DTD * const dtd = _dtd; /* save one level of indirection */
+ DTD * const dtd = parser->m_dtd; /* save one level of indirection */
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')))
+ if (!poolAppendChar(&parser->m_tempPool, XML_T('\0')))
return XML_FALSE;
- e = (ENTITY *)lookup(parser, &dtd->generalEntities, poolStart(&tempPool), 0);
+ e = (ENTITY *)lookup(parser, &dtd->generalEntities, poolStart(&parser->m_tempPool), 0);
if (e)
e->open = XML_TRUE;
if (*s != XML_T('\0'))
s++;
context = s;
- poolDiscard(&tempPool);
+ poolDiscard(&parser->m_tempPool);
}
else if (*s == XML_T(ASCII_EQUALS)) {
PREFIX *prefix;
- if (poolLength(&tempPool) == 0)
+ if (poolLength(&parser->m_tempPool) == 0)
prefix = &dtd->defaultPrefix;
else {
- if (!poolAppendChar(&tempPool, XML_T('\0')))
+ if (!poolAppendChar(&parser->m_tempPool, XML_T('\0')))
return XML_FALSE;
- prefix = (PREFIX *)lookup(parser, &dtd->prefixes, poolStart(&tempPool),
+ prefix = (PREFIX *)lookup(parser, &dtd->prefixes, poolStart(&parser->m_tempPool),
sizeof(PREFIX));
if (!prefix)
return XML_FALSE;
- if (prefix->name == poolStart(&tempPool)) {
+ if (prefix->name == poolStart(&parser->m_tempPool)) {
prefix->name = poolCopyString(&dtd->pool, prefix->name);
if (!prefix->name)
return XML_FALSE;
}
- poolDiscard(&tempPool);
+ poolDiscard(&parser->m_tempPool);
}
for (context = s + 1;
*context != CONTEXT_SEP && *context != XML_T('\0');
context++)
- if (!poolAppendChar(&tempPool, *context))
+ if (!poolAppendChar(&parser->m_tempPool, *context))
return XML_FALSE;
- if (!poolAppendChar(&tempPool, XML_T('\0')))
+ if (!poolAppendChar(&parser->m_tempPool, XML_T('\0')))
return XML_FALSE;
- if (addBinding(parser, prefix, NULL, poolStart(&tempPool),
- &inheritedBindings) != XML_ERROR_NONE)
+ if (addBinding(parser, prefix, NULL, poolStart(&parser->m_tempPool),
+ &parser->m_inheritedBindings) != XML_ERROR_NONE)
return XML_FALSE;
- poolDiscard(&tempPool);
+ poolDiscard(&parser->m_tempPool);
if (*context != XML_T('\0'))
++context;
s = context;
}
else {
- if (!poolAppendChar(&tempPool, *s))
+ if (!poolAppendChar(&parser->m_tempPool, *s))
return XML_FALSE;
s++;
}
@@ -5813,6 +6134,16 @@ dtdCopy(XML_Parser oldParser, DTD *newDtd, const DTD *oldDtd, const XML_Memory_H
if (!newE)
return 0;
if (oldE->nDefaultAtts) {
+ /* Detect and prevent integer overflow.
+ * The preprocessor guard addresses the "always false" warning
+ * from -Wtype-limits on platforms where
+ * sizeof(int) < sizeof(size_t), e.g. on x86_64. */
+#if UINT_MAX >= SIZE_MAX
+ if ((size_t)oldE->nDefaultAtts
+ > ((size_t)(-1) / sizeof(DEFAULT_ATTRIBUTE))) {
+ return 0;
+ }
+#endif
newE->defaultAtts = (DEFAULT_ATTRIBUTE *)
ms->malloc_fcn(oldE->nDefaultAtts * sizeof(DEFAULT_ATTRIBUTE));
if (!newE->defaultAtts) {
@@ -5951,10 +6282,10 @@ keyeq(KEY s1, KEY s2)
return XML_FALSE;
}
-static unsigned long FASTCALL
+static size_t FASTCALL
hash(XML_Parser parser, KEY s)
{
- unsigned long h = hash_secret_salt;
+ size_t h = parser->m_hash_secret_salt;
while (*s)
h = CHAR_HASH(h, *s++);
return h;
@@ -5981,8 +6312,8 @@ lookup(XML_Parser parser, HASH_TABLE *table, KEY name, size_t createSize)
i = hash(parser, name) & ((unsigned long)table->size - 1);
}
else {
- unsigned long h = hash(parser, name);
- unsigned long mask = (unsigned long)table->size - 1;
+ size_t h = hash(parser, name);
+ size_t mask = table->size - 1;
unsigned char step = 0;
i = h & mask;
while (table->v[i]) {
@@ -5998,8 +6329,20 @@ lookup(XML_Parser parser, HASH_TABLE *table, KEY name, size_t createSize)
/* check for overflow (table is half full) */
if (table->used >> (table->power - 1)) {
unsigned char newPower = table->power + 1;
+
+ /* Detect and prevent invalid shift */
+ if (newPower >= sizeof(unsigned long) * 8 /* bits per byte */) {
+ return NULL;
+ }
+
size_t newSize = (size_t)1 << newPower;
- unsigned long newMask = (unsigned long)newSize - 1;
+ size_t newMask = newSize - 1;
+
+ /* Detect and prevent integer overflow */
+ if (newSize > (size_t)(-1) / sizeof(NAMED *)) {
+ return NULL;
+ }
+
size_t tsize = newSize * sizeof(NAMED *);
NAMED **newV = (NAMED **)table->mem->malloc_fcn(tsize);
if (!newV)
@@ -6007,7 +6350,7 @@ lookup(XML_Parser parser, HASH_TABLE *table, KEY name, size_t createSize)
memset(newV, 0, tsize);
for (i = 0; i < table->size; i++)
if (table->v[i]) {
- unsigned long newHash = hash(parser, table->v[i]->name);
+ size_t newHash = hash(parser, table->v[i]->name);
size_t j = newHash & newMask;
step = 0;
while (newV[j]) {
@@ -6142,8 +6485,8 @@ poolAppend(STRING_POOL *pool, const ENCODING *enc,
if (!pool->ptr && !poolGrow(pool))
return NULL;
for (;;) {
- XmlConvert(enc, &ptr, end, (ICHAR **)&(pool->ptr), (ICHAR *)pool->end);
- if (ptr == end)
+ const enum XML_Convert_Result convert_res = XmlConvert(enc, &ptr, end, (ICHAR **)&(pool->ptr), (ICHAR *)pool->end);
+ if ((convert_res == XML_CONVERT_COMPLETED) || (convert_res == XML_CONVERT_INPUT_INCOMPLETE))
break;
if (!poolGrow(pool))
return NULL;
@@ -6227,8 +6570,13 @@ poolGrow(STRING_POOL *pool)
}
}
if (pool->blocks && pool->start == pool->blocks->s) {
- int blockSize = (int)(pool->end - pool->start)*2;
- BLOCK *temp = (BLOCK *)
+ BLOCK *temp;
+ int blockSize = (int)((unsigned)(pool->end - pool->start)*2U);
+
+ if (blockSize < 0)
+ return XML_FALSE;
+
+ temp = (BLOCK *)
pool->mem->realloc_fcn(pool->blocks,
(offsetof(BLOCK, s)
+ blockSize * sizeof(XML_Char)));
@@ -6243,6 +6591,10 @@ poolGrow(STRING_POOL *pool)
else {
BLOCK *tem;
int blockSize = (int)(pool->end - pool->start);
+
+ if (blockSize < 0)
+ return XML_FALSE;
+
if (blockSize < INIT_BLOCK_SIZE)
blockSize = INIT_BLOCK_SIZE;
else
@@ -6267,12 +6619,21 @@ poolGrow(STRING_POOL *pool)
static int FASTCALL
nextScaffoldPart(XML_Parser parser)
{
- DTD * const dtd = _dtd; /* save one level of indirection */
+ DTD * const dtd = parser->m_dtd; /* save one level of indirection */
CONTENT_SCAFFOLD * me;
int next;
if (!dtd->scaffIndex) {
- dtd->scaffIndex = (int *)MALLOC(groupSize * sizeof(int));
+ /* Detect and prevent integer overflow.
+ * The preprocessor guard addresses the "always false" warning
+ * from -Wtype-limits on platforms where
+ * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */
+#if UINT_MAX >= SIZE_MAX
+ if (parser->m_groupSize > ((size_t)(-1) / sizeof(int))) {
+ return -1;
+ }
+#endif
+ dtd->scaffIndex = (int *)MALLOC(parser, parser->m_groupSize * sizeof(int));
if (!dtd->scaffIndex)
return -1;
dtd->scaffIndex[0] = 0;
@@ -6281,14 +6642,28 @@ nextScaffoldPart(XML_Parser parser)
if (dtd->scaffCount >= dtd->scaffSize) {
CONTENT_SCAFFOLD *temp;
if (dtd->scaffold) {
+ /* Detect and prevent integer overflow */
+ if (dtd->scaffSize > UINT_MAX / 2u) {
+ return -1;
+ }
+ /* Detect and prevent integer overflow.
+ * The preprocessor guard addresses the "always false" warning
+ * from -Wtype-limits on platforms where
+ * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */
+#if UINT_MAX >= SIZE_MAX
+ if (dtd->scaffSize > (size_t)(-1) / 2u / sizeof(CONTENT_SCAFFOLD)) {
+ return -1;
+ }
+#endif
+
temp = (CONTENT_SCAFFOLD *)
- REALLOC(dtd->scaffold, dtd->scaffSize * 2 * sizeof(CONTENT_SCAFFOLD));
+ REALLOC(parser, dtd->scaffold, dtd->scaffSize * 2 * sizeof(CONTENT_SCAFFOLD));
if (temp == NULL)
return -1;
dtd->scaffSize *= 2;
}
else {
- temp = (CONTENT_SCAFFOLD *)MALLOC(INIT_SCAFFOLD_ELEMENTS
+ temp = (CONTENT_SCAFFOLD *)MALLOC(parser, INIT_SCAFFOLD_ELEMENTS
* sizeof(CONTENT_SCAFFOLD));
if (temp == NULL)
return -1;
@@ -6312,62 +6687,116 @@ nextScaffoldPart(XML_Parser parser)
return next;
}
-static void
-build_node(XML_Parser parser,
- int src_node,
- XML_Content *dest,
- XML_Content **contpos,
- XML_Char **strpos)
-{
- DTD * const dtd = _dtd; /* save one level of indirection */
- dest->type = dtd->scaffold[src_node].type;
- dest->quant = dtd->scaffold[src_node].quant;
- if (dest->type == XML_CTYPE_NAME) {
- const XML_Char *src;
- dest->name = *strpos;
- src = dtd->scaffold[src_node].name;
- for (;;) {
- *(*strpos)++ = *src;
- if (!*src)
- break;
- src++;
- }
- dest->numchildren = 0;
- dest->children = NULL;
- }
- else {
- unsigned int i;
- int cn;
- dest->numchildren = dtd->scaffold[src_node].childcnt;
- dest->children = *contpos;
- *contpos += dest->numchildren;
- for (i = 0, cn = dtd->scaffold[src_node].firstchild;
- i < dest->numchildren;
- i++, cn = dtd->scaffold[cn].nextsib) {
- build_node(parser, cn, &(dest->children[i]), contpos, strpos);
- }
- dest->name = NULL;
- }
-}
-
static XML_Content *
build_model (XML_Parser parser)
{
- DTD * const dtd = _dtd; /* save one level of indirection */
+ /* Function build_model transforms the existing parser->m_dtd->scaffold
+ * array of CONTENT_SCAFFOLD tree nodes into a new array of
+ * XML_Content tree nodes followed by a gapless list of zero-terminated
+ * strings. */
+ DTD * const dtd = parser->m_dtd; /* save one level of indirection */
XML_Content *ret;
- XML_Content *cpos;
- XML_Char * str;
- int allocsize = (dtd->scaffCount * sizeof(XML_Content)
- + (dtd->contentStringLen * sizeof(XML_Char)));
+ XML_Char * str; /* the current string writing location */
+
+ /* Detect and prevent integer overflow.
+ * The preprocessor guard addresses the "always false" warning
+ * from -Wtype-limits on platforms where
+ * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */
+#if UINT_MAX >= SIZE_MAX
+ if (dtd->scaffCount > (size_t)(-1) / sizeof(XML_Content)) {
+ return NULL;
+ }
+ if (dtd->contentStringLen > (size_t)(-1) / sizeof(XML_Char)) {
+ return NULL;
+ }
+#endif
+ if (dtd->scaffCount * sizeof(XML_Content)
+ > (size_t)(-1) - dtd->contentStringLen * sizeof(XML_Char)) {
+ return NULL;
+ }
- ret = (XML_Content *)MALLOC(allocsize);
+ const size_t allocsize = (dtd->scaffCount * sizeof(XML_Content)
+ + (dtd->contentStringLen * sizeof(XML_Char)));
+
+ ret = (XML_Content *)MALLOC(parser, allocsize);
if (!ret)
return NULL;
- str = (XML_Char *) (&ret[dtd->scaffCount]);
- cpos = &ret[1];
+ /* What follows is an iterative implementation (of what was previously done
+ * recursively in a dedicated function called "build_node". The old recursive
+ * build_node could be forced into stack exhaustion from input as small as a
+ * few megabyte, and so that was a security issue. Hence, a function call
+ * stack is avoided now by resolving recursion.)
+ *
+ * The iterative approach works as follows:
+ *
+ * - We use space in the target array for building a temporary stack structure
+ * while that space is still unused.
+ * The stack grows from the array's end downwards and the "actual data"
+ * grows from the start upwards, sequentially.
+ * (Because stack grows downwards, pushing onto the stack is a decrement
+ * while popping off the stack is an increment.)
+ *
+ * - A stack element appears as a regular XML_Content node on the outside,
+ * but only uses a single field -- numchildren -- to store the source
+ * tree node array index. These are the breadcrumbs leading the way back
+ * during pre-order (node first) depth-first traversal.
+ *
+ * - The reason we know the stack will never grow into (or overlap with)
+ * the area with data of value at the start of the array is because
+ * the overall number of elements to process matches the size of the array,
+ * and the sum of fully processed nodes and yet-to-be processed nodes
+ * on the stack, cannot be more than the total number of nodes.
+ * It is possible for the top of the stack and the about-to-write node
+ * to meet, but that is safe because we get the source index out
+ * before doing any writes on that node.
+ */
+ XML_Content *dest = ret; /* tree node writing location, moves upwards */
+ XML_Content *const destLimit = &ret[dtd->scaffCount];
+ XML_Content *const stackBottom = &ret[dtd->scaffCount];
+ XML_Content *stackTop = stackBottom; /* i.e. stack is initially empty */
+ str = (XML_Char *)&ret[dtd->scaffCount];
+
+ /* Push source tree root node index onto the stack */
+ (--stackTop)->numchildren = 0;
+
+ for (; dest < destLimit; dest++) {
+ /* Pop source tree node index off the stack */
+ const int src_node = (int)(stackTop++)->numchildren;
+
+ /* Convert item */
+ dest->type = dtd->scaffold[src_node].type;
+ dest->quant = dtd->scaffold[src_node].quant;
+ if (dest->type == XML_CTYPE_NAME) {
+ const XML_Char *src;
+ dest->name = str;
+ src = dtd->scaffold[src_node].name;
+ for (;;) {
+ *str++ = *src;
+ if (! *src)
+ break;
+ src++;
+ }
+ dest->numchildren = 0;
+ dest->children = NULL;
+ } else {
+ unsigned int i;
+ int cn;
+ dest->name = NULL;
+ dest->numchildren = dtd->scaffold[src_node].childcnt;
+ dest->children = &dest[1];
+
+ /* Push children to the stack
+ * in a way where the first child ends up at the top of the
+ * (downwards growing) stack, in order to be processed first. */
+ stackTop -= dest->numchildren;
+ for (i = 0, cn = dtd->scaffold[src_node].firstchild;
+ i < dest->numchildren; i++, cn = dtd->scaffold[cn].nextsib) {
+ (stackTop + i)->numchildren = (unsigned int)cn;
+ }
+ }
+ }
- build_node(parser, 0, ret, &cpos, &str);
return ret;
}
@@ -6377,7 +6806,7 @@ getElementType(XML_Parser parser,
const char *ptr,
const char *end)
{
- DTD * const dtd = _dtd; /* save one level of indirection */
+ DTD * const dtd = parser->m_dtd; /* save one level of indirection */
const XML_Char *name = poolStoreString(&dtd->pool, enc, ptr, end);
ELEMENT_TYPE *ret;
@@ -6395,3 +6824,24 @@ getElementType(XML_Parser parser,
}
return ret;
}
+
+static XML_Char *
+copyString(const XML_Char *s, const XML_Memory_Handling_Suite *memsuite) {
+ size_t charsRequired = 0;
+ XML_Char *result;
+
+ /* First determine how long the string is */
+ while (s[charsRequired] != 0) {
+ charsRequired++;
+ }
+ /* Include the terminator */
+ charsRequired++;
+
+ /* Now allocate space for the copy */
+ result = memsuite->malloc_fcn(charsRequired * sizeof(XML_Char));
+ if (result == NULL)
+ return NULL;
+ /* Copy the original into place */
+ memcpy(result, s, charsRequired * sizeof(XML_Char));
+ return result;
+}
diff --git a/libstudxml/details/expat/xmltok.c b/libstudxml/details/expat/xmltok.c
index 5a8f36f..a36735c 100644
--- a/libstudxml/details/expat/xmltok.c
+++ b/libstudxml/details/expat/xmltok.c
@@ -336,11 +336,12 @@ enum { /* UTF8_cvalN is value of masked first byte of N byte sequence */
UTF8_cval4 = 0xf0
};
-static void PTRCALL
+static enum XML_Convert_Result PTRCALL
utf8_toUtf8(const ENCODING *enc,
const char **fromP, const char *fromLim,
char **toP, const char *toLim)
{
+ enum XML_Convert_Result res = XML_CONVERT_COMPLETED;
char *to;
const char *from;
@@ -348,30 +349,45 @@ utf8_toUtf8(const ENCODING *enc,
if (fromLim - *fromP > toLim - *toP) {
/* Avoid copying partial characters. */
+ res = XML_CONVERT_OUTPUT_EXHAUSTED;
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++)
+ for (to = *toP, from = *fromP; (from < fromLim) && (to < toLim); from++, to++)
*to = *from;
*fromP = from;
*toP = to;
+
+ if ((to == toLim) && (from < fromLim))
+ return XML_CONVERT_OUTPUT_EXHAUSTED;
+ else
+ return res;
}
-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;
+ break;
+ }
*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;
+ break;
+ }
*to++ = (unsigned short)(((from[0] & 0xf) << 12)
| ((from[1] & 0x3f) << 6) | (from[2] & 0x3f));
from += 3;
@@ -379,8 +395,14 @@ 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;
@@ -398,6 +420,7 @@ utf8_toUtf16(const ENCODING *enc,
after:
*fromP = from;
*toP = to;
+ return res;
}
#ifdef XML_NS
@@ -446,7 +469,7 @@ static const struct normal_encoding internal_utf8_encoding = {
STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_)
};
-static void PTRCALL
+static enum XML_Convert_Result PTRCALL
latin1_toUtf8(const ENCODING *enc,
const char **fromP, const char *fromLim,
char **toP, const char *toLim)
@@ -456,32 +479,37 @@ latin1_toUtf8(const ENCODING *enc,
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
+static enum XML_Convert_Result PTRCALL
latin1_toUtf16(const ENCODING *enc,
const char **fromP, const char *fromLim,
unsigned short **toP, const unsigned short *toLim)
{
UNUSED(enc);
- 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
@@ -508,15 +536,20 @@ static const struct normal_encoding latin1_encoding = {
STANDARD_VTABLE(sb_) ZERO_VTABLE
};
-static void PTRCALL
+static enum XML_Convert_Result PTRCALL
ascii_toUtf8(const ENCODING *enc,
const char **fromP, const char *fromLim,
char **toP, const char *toLim)
{
UNUSED(enc);
- 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
@@ -563,14 +596,15 @@ unicode_byte_type(char hi, char lo)
}
#define DEFINE_UTF16_TO_UTF8(E) \
-static void PTRCALL \
+static enum XML_Convert_Result PTRCALL \
E ## toUtf8(const ENCODING *enc, \
const char **fromP, const char *fromLim, \
char **toP, const char *toLim) \
{ \
- const char *from; \
+ const char *from = *fromP; \
UNUSED(enc); \
- for (from = *fromP; from != fromLim; from += 2) { \
+ 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); \
@@ -580,7 +614,7 @@ E ## toUtf8(const ENCODING *enc, \
if (lo < 0x80) { \
if (*toP == toLim) { \
*fromP = from; \
- return; \
+ return XML_CONVERT_OUTPUT_EXHAUSTED; \
} \
*(*toP)++ = lo; \
break; \
@@ -590,7 +624,7 @@ 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); \
@@ -598,7 +632,7 @@ 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); \
@@ -608,7 +642,11 @@ 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); \
@@ -624,21 +662,33 @@ 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 \
+static enum XML_Convert_Result PTRCALL \
E ## toUtf16(const ENCODING *enc, \
const char **fromP, const char *fromLim, \
unsigned short **toP, const unsigned short *toLim) \
{ \
- UNUSED(enc); \
+ enum XML_Convert_Result res = XML_CONVERT_COMPLETED; \
+ UNUSED(enc); \
+ 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) \
@@ -1318,7 +1368,7 @@ 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)
@@ -1329,21 +1379,21 @@ 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 {
@@ -1352,13 +1402,13 @@ 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)
@@ -1370,6 +1420,11 @@ unknown_toUtf16(const ENCODING *enc,
(*fromP)++;
*(*toP)++ = c;
}
+
+ if ((*toP == toLim) && (*fromP < fromLim))
+ return XML_CONVERT_OUTPUT_EXHAUSTED;
+ else
+ return XML_CONVERT_COMPLETED;
}
ENCODING *
@@ -1533,7 +1588,7 @@ 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) {
diff --git a/libstudxml/details/expat/xmltok.h b/libstudxml/details/expat/xmltok.h
index ca867aa..752007e 100644
--- a/libstudxml/details/expat/xmltok.h
+++ b/libstudxml/details/expat/xmltok.h
@@ -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,
diff --git a/libstudxml/details/expat/xmltok_impl.c b/libstudxml/details/expat/xmltok_impl.c
index de4d21a..0a7fe34 100644
--- a/libstudxml/details/expat/xmltok_impl.c
+++ b/libstudxml/details/expat/xmltok_impl.c
@@ -34,7 +34,7 @@
case BT_LEAD ## n: \
if (end - ptr < n) \
return XML_TOK_PARTIAL_CHAR; \
- if (!IS_NAME_CHAR(enc, ptr, n)) { \
+ if (IS_INVALID_CHAR(enc, ptr, n) || !IS_NAME_CHAR(enc, ptr, n)) { \
*nextTokPtr = ptr; \
return XML_TOK_INVALID; \
} \
@@ -62,7 +62,7 @@
case BT_LEAD ## n: \
if (end - ptr < n) \
return XML_TOK_PARTIAL_CHAR; \
- if (!IS_NMSTRT_CHAR(enc, ptr, n)) { \
+ if (IS_INVALID_CHAR(enc, ptr, n) || !IS_NMSTRT_CHAR(enc, ptr, n)) { \
*nextTokPtr = ptr; \
return XML_TOK_INVALID; \
} \
@@ -93,13 +93,13 @@ static int PTRCALL
PREFIX(scanComment)(const ENCODING *enc, const char *ptr,
const char *end, const char **nextTokPtr)
{
- if (ptr != end) {
+ if (ptr < end) {
if (!CHAR_MATCHES(enc, ptr, ASCII_MINUS)) {
*nextTokPtr = ptr;
return XML_TOK_INVALID;
}
ptr += MINBPC(enc);
- while (ptr != end) {
+ while (ptr < end) {
switch (BYTE_TYPE(enc, ptr)) {
INVALID_CASES(ptr, nextTokPtr)
case BT_MINUS:
@@ -147,7 +147,7 @@ PREFIX(scanDecl)(const ENCODING *enc, const char *ptr,
*nextTokPtr = ptr;
return XML_TOK_INVALID;
}
- while (ptr != end) {
+ while (ptr < end) {
switch (BYTE_TYPE(enc, ptr)) {
case BT_PERCNT:
if (ptr + MINBPC(enc) == end)
@@ -236,7 +236,7 @@ PREFIX(scanPi)(const ENCODING *enc, const char *ptr,
*nextTokPtr = ptr;
return XML_TOK_INVALID;
}
- while (ptr != end) {
+ while (ptr < end) {
switch (BYTE_TYPE(enc, ptr)) {
CHECK_NAME_CASES(enc, ptr, end, nextTokPtr)
case BT_S: case BT_CR: case BT_LF:
@@ -245,7 +245,7 @@ PREFIX(scanPi)(const ENCODING *enc, const char *ptr,
return XML_TOK_INVALID;
}
ptr += MINBPC(enc);
- while (ptr != end) {
+ while (ptr < end) {
switch (BYTE_TYPE(enc, ptr)) {
INVALID_CASES(ptr, nextTokPtr)
case BT_QUEST:
@@ -311,7 +311,7 @@ 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;
@@ -354,7 +354,7 @@ PREFIX(cdataSectionTok)(const ENCODING *enc, const char *ptr,
ptr += MINBPC(enc);
break;
}
- while (ptr != end) {
+ while (ptr < end) {
switch (BYTE_TYPE(enc, ptr)) {
#define LEAD_CASE(n) \
case BT_LEAD ## n: \
@@ -397,11 +397,11 @@ PREFIX(scanEndTag)(const ENCODING *enc, const char *ptr,
*nextTokPtr = ptr;
return XML_TOK_INVALID;
}
- while (ptr != end) {
+ 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)) {
+ for (ptr += MINBPC(enc); ptr < end; ptr += MINBPC(enc)) {
switch (BYTE_TYPE(enc, ptr)) {
case BT_S: case BT_CR: case BT_LF:
break;
@@ -438,7 +438,7 @@ static int PTRCALL
PREFIX(scanHexCharRef)(const ENCODING *enc, const char *ptr,
const char *end, const char **nextTokPtr)
{
- if (ptr != end) {
+ if (ptr < end) {
switch (BYTE_TYPE(enc, ptr)) {
case BT_DIGIT:
case BT_HEX:
@@ -447,7 +447,7 @@ 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); ptr < end; ptr += MINBPC(enc)) {
switch (BYTE_TYPE(enc, ptr)) {
case BT_DIGIT:
case BT_HEX:
@@ -470,7 +470,7 @@ static int PTRCALL
PREFIX(scanCharRef)(const ENCODING *enc, const char *ptr,
const char *end, const char **nextTokPtr)
{
- if (ptr != end) {
+ if (ptr < end) {
if (CHAR_MATCHES(enc, ptr, ASCII_x))
return PREFIX(scanHexCharRef)(enc, ptr + MINBPC(enc), end, nextTokPtr);
switch (BYTE_TYPE(enc, ptr)) {
@@ -480,7 +480,7 @@ 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); ptr < end; ptr += MINBPC(enc)) {
switch (BYTE_TYPE(enc, ptr)) {
case BT_DIGIT:
break;
@@ -512,7 +512,7 @@ PREFIX(scanRef)(const ENCODING *enc, const char *ptr, const char *end,
*nextTokPtr = ptr;
return XML_TOK_INVALID;
}
- while (ptr != end) {
+ while (ptr < end) {
switch (BYTE_TYPE(enc, ptr)) {
CHECK_NAME_CASES(enc, ptr, end, nextTokPtr)
case BT_SEMI:
@@ -535,7 +535,7 @@ PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end,
#ifdef XML_NS
int hadColon = 0;
#endif
- while (ptr != end) {
+ while (ptr < end) {
switch (BYTE_TYPE(enc, ptr)) {
CHECK_NAME_CASES(enc, ptr, end, nextTokPtr)
#ifdef XML_NS
@@ -722,7 +722,7 @@ PREFIX(scanLt)(const ENCODING *enc, const char *ptr, const char *end,
hadColon = 0;
#endif
/* we have a start-tag */
- while (ptr != end) {
+ while (ptr < end) {
switch (BYTE_TYPE(enc, ptr)) {
CHECK_NAME_CASES(enc, ptr, end, nextTokPtr)
#ifdef XML_NS
@@ -746,7 +746,7 @@ 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 (ptr < end) {
switch (BYTE_TYPE(enc, ptr)) {
CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr)
case BT_GT:
@@ -791,7 +791,7 @@ 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;
@@ -838,7 +838,7 @@ PREFIX(contentTok)(const ENCODING *enc, const char *ptr, const char *end,
ptr += MINBPC(enc);
break;
}
- while (ptr != end) {
+ while (ptr < end) {
switch (BYTE_TYPE(enc, ptr)) {
#define LEAD_CASE(n) \
case BT_LEAD ## n: \
@@ -901,7 +901,7 @@ PREFIX(scanPercent)(const ENCODING *enc, const char *ptr, const char *end,
*nextTokPtr = ptr;
return XML_TOK_INVALID;
}
- while (ptr != end) {
+ while (ptr < end) {
switch (BYTE_TYPE(enc, ptr)) {
CHECK_NAME_CASES(enc, ptr, end, nextTokPtr)
case BT_SEMI:
@@ -927,7 +927,7 @@ PREFIX(scanPoundName)(const ENCODING *enc, const char *ptr, const char *end,
*nextTokPtr = ptr;
return XML_TOK_INVALID;
}
- while (ptr != end) {
+ while (ptr < end) {
switch (BYTE_TYPE(enc, ptr)) {
CHECK_NAME_CASES(enc, ptr, end, nextTokPtr)
case BT_CR: case BT_LF: case BT_S:
@@ -947,7 +947,7 @@ PREFIX(scanLit)(int open, const ENCODING *enc,
const char *ptr, const char *end,
const char **nextTokPtr)
{
- while (ptr != end) {
+ while (ptr < end) {
int t = BYTE_TYPE(enc, ptr);
switch (t) {
INVALID_CASES(ptr, nextTokPtr)
@@ -979,7 +979,7 @@ 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;
@@ -1103,6 +1103,10 @@ PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end,
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; \
+ } \
if (IS_NMSTRT_CHAR(enc, ptr, n)) { \
ptr += n; \
tok = XML_TOK_NAME; \
@@ -1147,7 +1151,7 @@ PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end,
*nextTokPtr = ptr;
return XML_TOK_INVALID;
}
- while (ptr != end) {
+ while (ptr < end) {
switch (BYTE_TYPE(enc, ptr)) {
CHECK_NAME_CASES(enc, ptr, end, nextTokPtr)
case BT_GT: case BT_RPAR: case BT_COMMA:
@@ -1210,10 +1214,10 @@ 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;
start = ptr;
- while (ptr != end) {
+ while (ptr < end) {
switch (BYTE_TYPE(enc, ptr)) {
#define LEAD_CASE(n) \
case BT_LEAD ## n: ptr += n; break;
@@ -1268,10 +1272,10 @@ 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;
start = ptr;
- while (ptr != end) {
+ while (ptr < end) {
switch (BYTE_TYPE(enc, ptr)) {
#define LEAD_CASE(n) \
case BT_LEAD ## n: ptr += n; break;
@@ -1332,7 +1336,7 @@ PREFIX(ignoreSectionTok)(const ENCODING *enc, const char *ptr,
end = ptr + n;
}
}
- while (ptr != end) {
+ while (ptr < end) {
switch (BYTE_TYPE(enc, ptr)) {
INVALID_CASES(ptr, nextTokPtr)
case BT_LT:
@@ -1379,7 +1383,7 @@ PREFIX(isPublicId)(const ENCODING *enc, const char *ptr, const char *end,
{
ptr += MINBPC(enc);
end -= MINBPC(enc);
- for (; ptr != end; ptr += MINBPC(enc)) {
+ for (; ptr < end; ptr += MINBPC(enc)) {
switch (BYTE_TYPE(enc, ptr)) {
case BT_DIGIT:
case BT_HEX:
@@ -1762,26 +1766,27 @@ PREFIX(updatePosition)(const ENCODING *enc,
#define LEAD_CASE(n) \
case BT_LEAD ## n: \
ptr += n; \
+ pos->columnNumber++; \
break;
LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4)
#undef LEAD_CASE
case BT_LF:
- pos->columnNumber = (XML_Size)-1;
+ pos->columnNumber = 0;
pos->lineNumber++;
ptr += MINBPC(enc);
break;
case BT_CR:
pos->lineNumber++;
ptr += MINBPC(enc);
- if (ptr != end && BYTE_TYPE(enc, ptr) == BT_LF)
+ if (ptr < end && BYTE_TYPE(enc, ptr) == BT_LF)
ptr += MINBPC(enc);
- pos->columnNumber = (XML_Size)-1;
+ pos->columnNumber = 0;
break;
default:
ptr += MINBPC(enc);
+ pos->columnNumber++;
break;
}
- pos->columnNumber++;
}
}
diff --git a/libstudxml/details/genx/LICENSE b/libstudxml/details/genx/LICENSE
index 218cb8d..895fef0 100644
--- a/libstudxml/details/genx/LICENSE
+++ b/libstudxml/details/genx/LICENSE
@@ -1,21 +1,22 @@
-Copyright (c) 2007-2020 Code Synthesis Tools CC.
+MIT License
+
+Copyright (c) 2007-2025 Code Synthesis Tools CC.
Copyright (c) Tim Bray and Sun Microsystems, 2004.
-Permission is hereby granted, free of charge, to any person obtaining
-a copy of this software and associated documentation files (the
-"Software"), to deal in the Software without restriction, including
-without limitation the rights to use, copy, modify, merge, publish,
-distribute, sublicense, and/or sell copies of the Software, and to
-permit persons to whom the Software is furnished to do so, subject to
-the following conditions:
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
-The above copyright notice and this permission notice shall be included
-in all copies or substantial portions of the Software.
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
-EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
-MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
-IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
-CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
-TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
-SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
diff --git a/libstudxml/details/genx/genx.c b/libstudxml/details/genx/genx.c
index 9c82059..4a6a61c 100644
--- a/libstudxml/details/genx/genx.c
+++ b/libstudxml/details/genx/genx.c
@@ -5,13 +5,23 @@
* For copying permission, see the accompanying LICENSE file.
*/
-#define GENX_VERSION "cs-1"
+/* Use snprintf() unless instructed otherwise. */
+#ifndef GENX_SNPRINTF
+# define GENX_SNPRINTF 1
+#endif
+
+#if defined(GENX_CUSTOM_ALLOC) != defined(GENX_CUSTOM_FREE)
+# error both GENX_CUSTOM_ALLOC and GENX_CUSTOM_FREE must be defined
+#endif
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <libstudxml/details/genx/genx.h>
+/*#include <libgenx/version.h>*/
+
+#define LIBGENX_VERSION_STR "0.2.0"
#define Boolean int
#define True 1
@@ -107,7 +117,7 @@ struct genxAttribute_rec
*/
struct genxWriter_rec
{
- genxSender * sender;
+ const genxSender * sender;
genxStatus status;
writerSequence sequence;
char xmlChars[GENX_CHAR_TABLE_SIZE];
@@ -165,7 +175,11 @@ static void * allocate(genxWriter w, size_t bytes)
if (w->alloc)
return (void *) (*w->alloc)(w->userData, bytes);
else
+#ifdef GENX_CUSTOM_ALLOC
+ return (void *) GENX_CUSTOM_ALLOC(bytes);
+#else
return (void *) malloc(bytes);
+#endif
}
static void deallocate(genxWriter w, void * data)
@@ -173,16 +187,24 @@ static void deallocate(genxWriter w, void * data)
if (w->dealloc)
(*w->dealloc)(w->userData, data);
else if (w->alloc == NULL)
+#ifdef GENX_CUSTOM_FREE
+ GENX_CUSTOM_FREE(data);
+#else
free(data);
+#endif
+
}
static utf8 copy(genxWriter w, constUtf8 from)
{
utf8 temp;
+ size_t sl = strlen((const char *) from);
- if ((temp = (utf8) allocate(w, strlen((const char *) from) + 1)) == NULL)
+ if ((temp = (utf8) allocate(w, sl + 1)) == NULL)
return NULL;
- strcpy((char *) temp, (const char *) from);
+
+ memcpy(temp, from, sl);
+ temp[sl] = 0;
return temp;
}
@@ -203,7 +225,7 @@ static genxStatus growCollector(genxWriter w, collector * c, size_t size)
if ((newSpace = (utf8) allocate(w, c->space)) == NULL)
return GENX_ALLOC_FAILED;
- strncpy((char *) newSpace, (const char *) c->buf, c->used);
+ memcpy(newSpace, c->buf, c->used);
newSpace[c->used] = 0;
deallocate(w, c->buf);
c->buf = newSpace;
@@ -227,10 +249,12 @@ static genxStatus collectString(genxWriter w, collector * c, constUtf8 string)
if ((w->status = growCollector(w, c, sl)) != GENX_SUCCESS)
return GENX_ALLOC_FAILED;
- strcpy((char *) c->buf, (const char *) string);
+ memcpy(c->buf, string, sl);
+ c->buf[sl] = 0;
return GENX_SUCCESS;
}
+/* Note: does not add the trailing '\0' (done by endCollect() call). */
#define collectPiece(w,c,d,size) {if (((c)->used+(size))>=(c)->space){if (((w)->status=growCollector(w,c,(c)->used+(size)))!=GENX_SUCCESS) return (w)->status;}memcpy((char *)(c)->buf+(c)->used,d,size);(c)->used+=size;}
/*******************************
@@ -357,7 +381,18 @@ static utf8 storePrefix(genxWriter w, constUtf8 prefix, Boolean force)
prefix = (utf8) "xmlns";
else
{
- sprintf((char *) buf, "xmlns:%s", prefix);
+ size_t pl = strlen((const char *) prefix);
+
+ if (pl > sizeof(buf) - (6 + 1))
+ {
+ w->status = GENX_BAD_NAMESPACE_NAME;
+ return NULL;
+ }
+
+ memcpy (buf, "xmlns:", 6);
+ memcpy (buf + 6, prefix, pl);
+ buf[pl + 6] = 0;
+
prefix = buf;
}
@@ -547,7 +582,11 @@ genxWriter genxNew(genxAlloc alloc, genxDealloc dealloc, void * userData)
if (alloc)
w = (genxWriter) (*alloc)(userData, sizeof(struct genxWriter_rec));
else
+#ifdef GENX_CUSTOM_ALLOC
+ w = (genxWriter) GENX_CUSTOM_ALLOC(sizeof(struct genxWriter_rec));
+#else
w = (genxWriter) malloc(sizeof(struct genxWriter_rec));
+#endif
if (w == NULL)
return NULL;
@@ -928,11 +967,11 @@ static genxStatus checkNCName(genxWriter w, constUtf8 name)
return GENX_SUCCESS;
}
-char * genxGetErrorMessage(genxWriter w, genxStatus status)
+const char * genxGetErrorMessage(genxWriter w, genxStatus status)
{
return w->etext[status];
}
-char * genxLastErrorMessage(genxWriter w)
+const char * genxLastErrorMessage(genxWriter w)
{
return w->etext[w->status];
}
@@ -983,11 +1022,14 @@ genxNamespace genxDeclareNamespace(genxWriter w, constUtf8 uri,
/* wasn't already declared */
else
{
-
/* make a default prefix if none provided */
if (defaultPref == NULL)
{
+#if GENX_SNPRINTF
+ snprintf((char *) newPrefix, sizeof(newPrefix), "g%d", w->nextPrefix++);
+#else
sprintf((char *) newPrefix, "g%d", w->nextPrefix++);
+#endif
defaultPref = newPrefix;
}
@@ -1051,7 +1093,7 @@ busted:
/*
* get namespace prefix
*/
-utf8 genxGetNamespacePrefix(genxNamespace ns)
+constUtf8 genxGetNamespacePrefix(genxNamespace ns)
{
if (ns->declaration == NULL)
return NULL;
@@ -1264,7 +1306,7 @@ static genxStatus sendxBounded(genxWriter w, constUtf8 start, constUtf8 end)
* for internal routines.
*/
-genxStatus genxStartDocSender(genxWriter w, genxSender * sender)
+genxStatus genxStartDocSender(genxWriter w, const genxSender * sender)
{
if (w->sequence != SEQUENCE_NO_DOC)
return w->status = GENX_SEQUENCE_ERROR;
@@ -2496,7 +2538,7 @@ genxStatus genxAddNamespaceLiteral(genxWriter w,
/*
* return version
*/
-char * genxGetVersion()
+const char * genxGetVersion()
{
- return GENX_VERSION;
+ return LIBGENX_VERSION_STR;
}
diff --git a/libstudxml/details/genx/genx.h b/libstudxml/details/genx/genx.h
index 041815f..a6711db 100644
--- a/libstudxml/details/genx/genx.h
+++ b/libstudxml/details/genx/genx.h
@@ -14,6 +14,10 @@
#include <stddef.h> /* size_t */
+/*#include <libgenx/export.h>*/
+
+#define LIBGENX_SYMEXPORT
+
#ifdef __cplusplus
extern "C" {
#endif
@@ -86,17 +90,20 @@ typedef void (*genxDealloc) (void * userData, void* data);
* one document at a time with a writer.
* Returns NULL if it fails, which can only be due to an allocation failure.
*/
+LIBGENX_SYMEXPORT
genxWriter genxNew(genxAlloc alloc, genxDealloc dealloc, void * userData);
/*
* Reset the writer object back into usable state after an error or
* interruption.
*/
+LIBGENX_SYMEXPORT
genxStatus genxReset (genxWriter w);
/*
* Dispose of a writer, freeing all associated memory
*/
+LIBGENX_SYMEXPORT
void genxDispose(genxWriter w);
/*
@@ -107,14 +114,20 @@ void genxDispose(genxWriter w);
* The userdata pointer will be passed to memory-allocation
* and I/O callbacks. If not set, genx will pass NULL
*/
+LIBGENX_SYMEXPORT
void genxSetUserData(genxWriter w, void * userData);
+
+LIBGENX_SYMEXPORT
void * genxGetUserData(genxWriter w);
/*
* Set/get pretty-printing. If indentation is set to 0, then no pretty-
* printing is performed.
*/
+LIBGENX_SYMEXPORT
genxStatus genxSetPrettyPrint(genxWriter w, int indentation);
+
+LIBGENX_SYMEXPORT
int genxGetPrettyPrint(genxWriter w);
/*
@@ -130,8 +143,13 @@ int genxGetPrettyPrint(genxWriter w);
* level at which pretty-printing was suspended, with root element
* being level 1.
*/
+LIBGENX_SYMEXPORT
genxStatus genxSuspendPrettyPrint(genxWriter w);
+
+LIBGENX_SYMEXPORT
genxStatus genxResumePrettyPrint(genxWriter w);
+
+LIBGENX_SYMEXPORT
int genxPrettyPrintSuspended(genxWriter w);
@@ -139,7 +157,10 @@ int genxPrettyPrintSuspended(genxWriter w);
* Set/get canonicalization. If true, then output explicit closing
* tags and sort attributes. Default is false.
*/
+LIBGENX_SYMEXPORT
genxStatus genxSetCanonical(genxWriter w, int flag);
+
+LIBGENX_SYMEXPORT
int genxGetCanonical(genxWriter w);
/*
@@ -151,15 +172,23 @@ int genxGetCanonical(genxWriter w);
* the memory; this would be appropriate in an Apache context.
* If "alloc" is not provided, genx routines use malloc() to allocate memory
*/
+LIBGENX_SYMEXPORT
void genxSetAlloc(genxWriter w, genxAlloc alloc);
+
+LIBGENX_SYMEXPORT
void genxSetDealloc(genxWriter w, genxDealloc dealloc);
+
+LIBGENX_SYMEXPORT
genxAlloc genxGetAlloc(genxWriter w);
+
+LIBGENX_SYMEXPORT
genxDealloc genxGetDealloc(genxWriter w);
/*
* Get the prefix associated with a namespace
*/
-utf8 genxGetNamespacePrefix(genxNamespace ns);
+LIBGENX_SYMEXPORT
+constUtf8 genxGetNamespacePrefix(genxNamespace ns);
/*
* Declaration functions
@@ -171,6 +200,7 @@ utf8 genxGetNamespacePrefix(genxNamespace ns);
* genx will generate one of the form g-%d.
* On error, returns NULL and signals via statusp
*/
+LIBGENX_SYMEXPORT
genxNamespace genxDeclareNamespace(genxWriter w,
constUtf8 uri, constUtf8 prefix,
genxStatus * statusP);
@@ -179,6 +209,7 @@ genxNamespace genxDeclareNamespace(genxWriter w,
* Declare an element
* If something failed, returns NULL and sets the status code via statusP
*/
+LIBGENX_SYMEXPORT
genxElement genxDeclareElement(genxWriter w,
genxNamespace ns, constUtf8 name,
genxStatus * statusP);
@@ -186,6 +217,7 @@ genxElement genxDeclareElement(genxWriter w,
/*
* Declare an attribute
*/
+LIBGENX_SYMEXPORT
genxAttribute genxDeclareAttribute(genxWriter w,
genxNamespace ns,
constUtf8 name, genxStatus * statusP);
@@ -207,17 +239,20 @@ typedef struct
genxStatus (* flush)(void * userData);
} genxSender;
-genxStatus genxStartDocSender(genxWriter w, genxSender * sender);
+LIBGENX_SYMEXPORT
+genxStatus genxStartDocSender(genxWriter w, const genxSender * sender);
/*
* End a document. Calls "flush".
*/
+LIBGENX_SYMEXPORT
genxStatus genxEndDocument(genxWriter w);
/*
* Write XML declaration. If encoding or standalone are NULL, then those
* attributes are omitted.
*/
+LIBGENX_SYMEXPORT
genxStatus genxXmlDeclaration(genxWriter w,
constUtf8 version,
constUtf8 encoding,
@@ -229,6 +264,7 @@ genxStatus genxXmlDeclaration(genxWriter w,
* that only contains the root element and, if not NULL, internal
* subset is written.
*/
+LIBGENX_SYMEXPORT
genxStatus genxDoctypeDeclaration(genxWriter w,
constUtf8 root_element,
constUtf8 public_id,
@@ -238,16 +274,19 @@ genxStatus genxDoctypeDeclaration(genxWriter w,
/*
* Write a comment
*/
+LIBGENX_SYMEXPORT
genxStatus genxComment(genxWriter w, constUtf8 text);
/*
* Write a PI
*/
+LIBGENX_SYMEXPORT
genxStatus genxPI(genxWriter w, constUtf8 target, constUtf8 text);
/*
* Start an element
*/
+LIBGENX_SYMEXPORT
genxStatus genxStartElementLiteral(genxWriter w,
constUtf8 xmlns, constUtf8 name);
@@ -255,6 +294,7 @@ genxStatus genxStartElementLiteral(genxWriter w,
* Start a predeclared element
* - element must have been declared
*/
+LIBGENX_SYMEXPORT
genxStatus genxStartElement(genxElement e);
/*
@@ -262,29 +302,34 @@ genxStatus genxStartElement(genxElement e);
* element ceases to be current (i.e., EndElement() is called).
* If the element is unqualified, then xmlns is set to NULL.
*/
+LIBGENX_SYMEXPORT
genxStatus genxGetCurrentElement (genxWriter w,
constUtf8* xmlns, constUtf8* name);
/*
* Write an attribute
*/
+LIBGENX_SYMEXPORT
genxStatus genxAddAttributeLiteral(genxWriter w, constUtf8 xmlns,
constUtf8 name, constUtf8 value);
/*
* Write a predeclared attribute
*/
+LIBGENX_SYMEXPORT
genxStatus genxAddAttribute(genxAttribute a, constUtf8 value);
/*
* Start an attribute
*/
+LIBGENX_SYMEXPORT
genxStatus genxStartAttributeLiteral(genxWriter w,
constUtf8 xmlns, constUtf8 name);
/*
* Start a predeclared attribute
*/
+LIBGENX_SYMEXPORT
genxStatus genxStartAttribute(genxAttribute a);
/*
@@ -292,33 +337,39 @@ genxStatus genxStartAttribute(genxAttribute a);
* attribute ceases to be current (i.e., EndAttribute() is called).
* If the attribute is unqualified, then xmlns is set to NULL.
*/
+LIBGENX_SYMEXPORT
genxStatus genxGetCurrentAttribute (genxWriter w,
constUtf8* xmlns, constUtf8* name);
/*
* End an attribute
*/
+LIBGENX_SYMEXPORT
genxStatus genxEndAttribute(genxWriter w);
/*
* add a namespace declaration
*/
+LIBGENX_SYMEXPORT
genxStatus genxAddNamespaceLiteral(genxWriter w,
constUtf8 uri, constUtf8 prefix);
/*
* add a predefined namespace declaration
*/
+LIBGENX_SYMEXPORT
genxStatus genxAddNamespace(genxNamespace ns, constUtf8 prefix);
/*
* Clear default namespace declaration
*/
+LIBGENX_SYMEXPORT
genxStatus genxUnsetDefaultNamespace(genxWriter w);
/*
* Write an end tag
*/
+LIBGENX_SYMEXPORT
genxStatus genxEndElement(genxWriter w);
/*
@@ -326,14 +377,20 @@ genxStatus genxEndElement(genxWriter w);
* You can't write any text outside the root element, except with
* genxComment and genxPI.
*/
+LIBGENX_SYMEXPORT
genxStatus genxAddText(genxWriter w, constUtf8 start);
+
+LIBGENX_SYMEXPORT
genxStatus genxAddCountedText(genxWriter w, constUtf8 start, size_t byteCount);
+
+LIBGENX_SYMEXPORT
genxStatus genxAddBoundedText(genxWriter w, constUtf8 start, constUtf8 end);
/*
* Write one character. The integer value is the Unicode character
* value, as usually expressed in U+XXXX notation.
*/
+LIBGENX_SYMEXPORT
genxStatus genxAddCharacter(genxWriter w, int c);
/*
@@ -347,18 +404,21 @@ genxStatus genxAddCharacter(genxWriter w, int c);
* argument to point at the first byte past the point past the malformed
* ones.
*/
+LIBGENX_SYMEXPORT
int genxNextUnicodeChar(constUtf8 * sp);
/*
* Scan a buffer allegedly full of UTF-8 encoded XML characters; return
* one of GENX_SUCCESS, GENX_BAD_UTF8, or GENX_NON_XML_CHARACTER
*/
+LIBGENX_SYMEXPORT
genxStatus genxCheckText(genxWriter w, constUtf8 s);
/*
* return character status, the OR of GENX_XML_CHAR,
* GENX_LETTER, and GENX_NAMECHAR
*/
+LIBGENX_SYMEXPORT
int genxCharClass(genxWriter w, int c);
/*
@@ -370,18 +430,23 @@ int genxCharClass(genxWriter w, int c);
* The output can never be longer than the input.
* Returns true if any changes were made.
*/
+LIBGENX_SYMEXPORT
int genxScrubText(genxWriter w, constUtf8 in, utf8 out);
/*
* return error messages
*/
-char * genxGetErrorMessage(genxWriter w, genxStatus status);
-char * genxLastErrorMessage(genxWriter w);
+LIBGENX_SYMEXPORT
+const char * genxGetErrorMessage(genxWriter w, genxStatus status);
+
+LIBGENX_SYMEXPORT
+const char * genxLastErrorMessage(genxWriter w);
/*
* return version
*/
-char * genxGetVersion();
+LIBGENX_SYMEXPORT
+const char * genxGetVersion();
#ifdef __cplusplus
}
diff --git a/libstudxml/parser.hxx b/libstudxml/parser.hxx
index c67919a..c04eded 100644
--- a/libstudxml/parser.hxx
+++ b/libstudxml/parser.hxx
@@ -12,8 +12,7 @@
#include <iosfwd>
#include <cstddef> // std::size_t
-#include <libstudxml/details/config.hxx> // STUDXML_NOTHROW_NOEXCEPT,
- // LIBSTUDXML_EXTERNAL_EXPAT
+#include <libstudxml/details/config.hxx>
#ifndef LIBSTUDXML_EXTERNAL_EXPAT
# include <libstudxml/details/expat/expat.h>
@@ -40,7 +39,7 @@ namespace xml
{
public:
virtual
- ~parsing () STUDXML_NOTHROW_NOEXCEPT {}
+ ~parsing () noexcept {}
parsing (const std::string& name,
unsigned long long line,
@@ -62,7 +61,7 @@ namespace xml
description () const {return description_;}
virtual const char*
- what () const STUDXML_NOTHROW_NOEXCEPT {return what_.c_str ();}
+ what () const noexcept {return what_.c_str ();}
private:
LIBSTUDXML_EXPORT void
diff --git a/libstudxml/serializer.hxx b/libstudxml/serializer.hxx
index 4913c25..ead52e9 100644
--- a/libstudxml/serializer.hxx
+++ b/libstudxml/serializer.hxx
@@ -16,7 +16,7 @@
#include <libstudxml/qname.hxx>
#include <libstudxml/exception.hxx>
-#include <libstudxml/details/config.hxx> // STUDXML_NOTHROW_NOEXCEPT
+#include <libstudxml/details/config.hxx>
#include <libstudxml/details/export.hxx>
namespace xml
@@ -25,7 +25,7 @@ namespace xml
{
public:
virtual
- ~serialization () STUDXML_NOTHROW_NOEXCEPT {}
+ ~serialization () noexcept {}
serialization (const std::string& name, const std::string& description);
serialization (const serializer& s, const std::string& description);
@@ -37,7 +37,7 @@ namespace xml
description () const {return description_;}
virtual const char*
- what () const STUDXML_NOTHROW_NOEXCEPT {return what_.c_str ();}
+ what () const noexcept {return what_.c_str ();}
private:
LIBSTUDXML_EXPORT void
generated by cgit v1.1 at 2025-07-02 01:10:51 +0000