From 08317aefef89ca18ce12e53c0cdb3c8e132a6201 Mon Sep 17 00:00:00 2001 From: Fred Drake Date: Tue, 21 Oct 2003 15:38:55 +0000 Subject: Update to Expat 1.95.7; there are no changes to the Expat sources. --- Modules/expat/asciitab.h | 5 +- Modules/expat/expat.h | 242 ++++++++++----- Modules/expat/expat.h.in | 735 -------------------------------------------- Modules/expat/iasciitab.h | 5 +- Modules/expat/internal.h | 18 +- Modules/expat/latin1tab.h | 5 +- Modules/expat/macconfig.h | 104 +++++++ Modules/expat/utf8tab.h | 5 +- Modules/expat/winconfig.h | 9 +- Modules/expat/xmlparse.c | 511 ++++++++++++++++++------------ Modules/expat/xmlrole.c | 4 +- Modules/expat/xmltok.c | 4 +- Modules/expat/xmltok_impl.c | 2 +- 13 files changed, 604 insertions(+), 1045 deletions(-) delete mode 100644 Modules/expat/expat.h.in create mode 100644 Modules/expat/macconfig.h diff --git a/Modules/expat/asciitab.h b/Modules/expat/asciitab.h index eb445cc..79a15c2 100644 --- a/Modules/expat/asciitab.h +++ b/Modules/expat/asciitab.h @@ -1,6 +1,5 @@ -/* -Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd -See the file COPYING for copying permission. +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. */ /* 0x00 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, diff --git a/Modules/expat/expat.h b/Modules/expat/expat.h index 5322bea..455e5b8 100644 --- a/Modules/expat/expat.h +++ b/Modules/expat/expat.h @@ -16,17 +16,71 @@ #include -#ifndef XMLPARSEAPI #if defined(_MSC_EXTENSIONS) && !defined(__BEOS__) && !defined(__CYGWIN__) -#ifdef XML_STATIC -#define XMLPARSEAPI(type) type __cdecl -#else -#define XMLPARSEAPI(type) __declspec(dllimport) type __cdecl +#define XML_USE_MSC_EXTENSIONS 1 #endif + +/* Expat tries very hard to make the API boundary very specifically + defined. There are two macros defined to control this boundary; + each of these can be defined before including this header to + achieve some different behavior, but doing so it not recommended or + tested frequently. + + XMLCALL - The calling convention to use for all calls across the + "library boundary." This will default to cdecl, and + try really hard to tell the compiler that's what we + want. + + XMLIMPORT - Whatever magic is needed to note that a function is + to be imported from a dynamically loaded library + (.dll, .so, or .sl, depending on your platform). + + The XMLCALL macro was added in Expat 1.95.7. The only one which is + expected to be directly useful in client code is XMLCALL. + + Note that on at least some Unix versions, the Expat library must be + compiled with the cdecl calling convention as the default since + system headers may assume the cdecl convention. +*/ +#ifndef XMLCALL +#if defined(XML_USE_MSC_EXTENSIONS) +#define XMLCALL __cdecl +#elif defined(__GNUC__) +#define XMLCALL __attribute__((cdecl)) #else -#define XMLPARSEAPI(type) type +/* For any platform which uses this definition and supports more than + one calling convention, we need to extend this definition to + declare the convention used on that platform, if it's possible to + do so. + + If this is the case for your platform, please file a bug report + with information on how to identify your platform via the C + pre-processor and how to specify the same calling convention as the + platform's malloc() implementation. +*/ +#define XMLCALL +#endif +#endif /* not defined XMLCALL */ + + +#if !defined(XML_STATIC) && !defined(XMLIMPORT) +#ifndef XML_BUILDING_EXPAT +/* using Expat from an application */ + +#ifdef XML_USE_MSC_EXTENSIONS +#define XMLIMPORT __declspec(dllimport) +#endif + #endif -#endif /* not defined XMLPARSEAPI */ +#endif /* not defined XML_STATIC */ + +/* If we didn't define it above, define it away: */ +#ifndef XMLIMPORT +#define XMLIMPORT +#endif + + +#define XMLPARSEAPI(type) XMLIMPORT type XMLCALL #ifdef __cplusplus extern "C" { @@ -104,7 +158,8 @@ enum XML_Error { XML_ERROR_UNEXPECTED_STATE, XML_ERROR_ENTITY_DECLARED_IN_PE, XML_ERROR_FEATURE_REQUIRES_XML_DTD, - XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING + XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING, + XML_ERROR_UNBOUND_PREFIX }; enum XML_Content_Type { @@ -156,9 +211,9 @@ struct XML_cp { description of the model argument. It's the caller's responsibility to free model when finished with it. */ -typedef void (*XML_ElementDeclHandler) (void *userData, - const XML_Char *name, - XML_Content *model); +typedef void (XMLCALL *XML_ElementDeclHandler) (void *userData, + const XML_Char *name, + XML_Content *model); XMLPARSEAPI(void) XML_SetElementDeclHandler(XML_Parser parser, @@ -172,12 +227,13 @@ XML_SetElementDeclHandler(XML_Parser parser, value will be NULL in the case of "#REQUIRED". If "isrequired" is true and default is non-NULL, then this is a "#FIXED" default. */ -typedef void (*XML_AttlistDeclHandler) (void *userData, - const XML_Char *elname, - const XML_Char *attname, - const XML_Char *att_type, - const XML_Char *dflt, - int isrequired); +typedef void (XMLCALL *XML_AttlistDeclHandler) ( + void *userData, + const XML_Char *elname, + const XML_Char *attname, + const XML_Char *att_type, + const XML_Char *dflt, + int isrequired); XMLPARSEAPI(void) XML_SetAttlistDeclHandler(XML_Parser parser, @@ -191,10 +247,10 @@ XML_SetAttlistDeclHandler(XML_Parser parser, was no standalone parameter in the declaration, that it was given as no, or that it was given as yes. */ -typedef void (*XML_XmlDeclHandler) (void *userData, - const XML_Char *version, - const XML_Char *encoding, - int standalone); +typedef void (XMLCALL *XML_XmlDeclHandler) (void *userData, + const XML_Char *version, + const XML_Char *encoding, + int standalone); XMLPARSEAPI(void) XML_SetXmlDeclHandler(XML_Parser parser, @@ -202,9 +258,9 @@ XML_SetXmlDeclHandler(XML_Parser parser, typedef struct { - void *(*malloc_fcn)(size_t size); - void *(*realloc_fcn)(void *ptr, size_t size); - void (*free_fcn)(void *ptr); + void *(XMLCALL *malloc_fcn)(size_t size); + void *(XMLCALL *realloc_fcn)(void *ptr, size_t size); + void (XMLCALL *free_fcn)(void *ptr); } XML_Memory_Handling_Suite; /* Constructs a new parser; encoding is the encoding specified by the @@ -257,29 +313,31 @@ XML_ParserReset(XML_Parser parser, const XML_Char *encoding); /* atts is array of name/value pairs, terminated by 0; names and values are 0 terminated. */ -typedef void (*XML_StartElementHandler)(void *userData, - const XML_Char *name, - const XML_Char **atts); +typedef void (XMLCALL *XML_StartElementHandler) (void *userData, + const XML_Char *name, + const XML_Char **atts); -typedef void (*XML_EndElementHandler)(void *userData, - const XML_Char *name); +typedef void (XMLCALL *XML_EndElementHandler) (void *userData, + const XML_Char *name); /* s is not 0 terminated. */ -typedef void (*XML_CharacterDataHandler)(void *userData, - const XML_Char *s, - int len); +typedef void (XMLCALL *XML_CharacterDataHandler) (void *userData, + const XML_Char *s, + int len); /* target and data are 0 terminated */ -typedef void (*XML_ProcessingInstructionHandler)(void *userData, - const XML_Char *target, - const XML_Char *data); +typedef void (XMLCALL *XML_ProcessingInstructionHandler) ( + void *userData, + const XML_Char *target, + const XML_Char *data); /* data is 0 terminated */ -typedef void (*XML_CommentHandler)(void *userData, const XML_Char *data); +typedef void (XMLCALL *XML_CommentHandler) (void *userData, + const XML_Char *data); -typedef void (*XML_StartCdataSectionHandler)(void *userData); -typedef void (*XML_EndCdataSectionHandler)(void *userData); +typedef void (XMLCALL *XML_StartCdataSectionHandler) (void *userData); +typedef void (XMLCALL *XML_EndCdataSectionHandler) (void *userData); /* This is called for any characters in the XML document for which there is no applicable handler. This includes both characters that @@ -294,14 +352,15 @@ typedef void (*XML_EndCdataSectionHandler)(void *userData); default handler: for example, a comment might be split between multiple calls. */ -typedef void (*XML_DefaultHandler)(void *userData, - const XML_Char *s, - int len); +typedef void (XMLCALL *XML_DefaultHandler) (void *userData, + const XML_Char *s, + int len); /* This is called for the start of the DOCTYPE declaration, before any DTD or internal subset is parsed. */ -typedef void (*XML_StartDoctypeDeclHandler)(void *userData, +typedef void (XMLCALL *XML_StartDoctypeDeclHandler) ( + void *userData, const XML_Char *doctypeName, const XML_Char *sysid, const XML_Char *pubid, @@ -311,7 +370,7 @@ typedef void (*XML_StartDoctypeDeclHandler)(void *userData, closing > is encountered, but after processing any external subset. */ -typedef void (*XML_EndDoctypeDeclHandler)(void *userData); +typedef void (XMLCALL *XML_EndDoctypeDeclHandler)(void *userData); /* This is called for entity declarations. The is_parameter_entity argument will be non-zero if the entity is a parameter entity, zero @@ -331,15 +390,16 @@ typedef void (*XML_EndDoctypeDeclHandler)(void *userData); Note that is_parameter_entity can't be changed to XML_Bool, since that would break binary compatibility. */ -typedef void (*XML_EntityDeclHandler) (void *userData, - const XML_Char *entityName, - int is_parameter_entity, - const XML_Char *value, - int value_length, - const XML_Char *base, - const XML_Char *systemId, - const XML_Char *publicId, - const XML_Char *notationName); +typedef void (XMLCALL *XML_EntityDeclHandler) ( + void *userData, + const XML_Char *entityName, + int is_parameter_entity, + const XML_Char *value, + int value_length, + const XML_Char *base, + const XML_Char *systemId, + const XML_Char *publicId, + const XML_Char *notationName); XMLPARSEAPI(void) XML_SetEntityDeclHandler(XML_Parser parser, @@ -354,22 +414,24 @@ XML_SetEntityDeclHandler(XML_Parser parser, entityName, systemId and notationName arguments will never be NULL. The other arguments may be. */ -typedef void (*XML_UnparsedEntityDeclHandler)(void *userData, - const XML_Char *entityName, - const XML_Char *base, - const XML_Char *systemId, - const XML_Char *publicId, - const XML_Char *notationName); +typedef void (XMLCALL *XML_UnparsedEntityDeclHandler) ( + void *userData, + const XML_Char *entityName, + const XML_Char *base, + const XML_Char *systemId, + const XML_Char *publicId, + const XML_Char *notationName); /* This is called for a declaration of notation. The base argument is whatever was set by XML_SetBase. The notationName will never be NULL. The other arguments can be. */ -typedef void (*XML_NotationDeclHandler)(void *userData, - const XML_Char *notationName, - const XML_Char *base, - const XML_Char *systemId, - const XML_Char *publicId); +typedef void (XMLCALL *XML_NotationDeclHandler) ( + void *userData, + const XML_Char *notationName, + const XML_Char *base, + const XML_Char *systemId, + const XML_Char *publicId); /* When namespace processing is enabled, these are called once for each namespace declaration. The call to the start and end element @@ -377,12 +439,14 @@ typedef void (*XML_NotationDeclHandler)(void *userData, declaration handlers. For an xmlns attribute, prefix will be NULL. For an xmlns="" attribute, uri will be NULL. */ -typedef void (*XML_StartNamespaceDeclHandler)(void *userData, - const XML_Char *prefix, - const XML_Char *uri); +typedef void (XMLCALL *XML_StartNamespaceDeclHandler) ( + void *userData, + const XML_Char *prefix, + const XML_Char *uri); -typedef void (*XML_EndNamespaceDeclHandler)(void *userData, - const XML_Char *prefix); +typedef void (XMLCALL *XML_EndNamespaceDeclHandler) ( + void *userData, + const XML_Char *prefix); /* This is called if the document is not standalone, that is, it has an external subset or a reference to a parameter entity, but does not @@ -393,7 +457,7 @@ typedef void (*XML_EndNamespaceDeclHandler)(void *userData, conditions above this handler will only be called if the referenced entity was actually read. */ -typedef int (*XML_NotStandaloneHandler)(void *userData); +typedef int (XMLCALL *XML_NotStandaloneHandler) (void *userData); /* This is called for a reference to an external parsed general entity. The referenced entity is not automatically parsed. The @@ -429,11 +493,12 @@ typedef int (*XML_NotStandaloneHandler)(void *userData); Note that unlike other handlers the first argument is the parser, not userData. */ -typedef int (*XML_ExternalEntityRefHandler)(XML_Parser parser, - const XML_Char *context, - const XML_Char *base, - const XML_Char *systemId, - const XML_Char *publicId); +typedef int (XMLCALL *XML_ExternalEntityRefHandler) ( + XML_Parser parser, + const XML_Char *context, + const XML_Char *base, + const XML_Char *systemId, + const XML_Char *publicId); /* This is called in two situations: 1) An entity reference is encountered for which no declaration @@ -445,9 +510,10 @@ typedef int (*XML_ExternalEntityRefHandler)(XML_Parser parser, the event would be out of sync with the reporting of the declarations or attribute values */ -typedef void (*XML_SkippedEntityHandler)(void *userData, - const XML_Char *entityName, - int is_parameter_entity); +typedef void (XMLCALL *XML_SkippedEntityHandler) ( + void *userData, + const XML_Char *entityName, + int is_parameter_entity); /* This structure is filled in by the XML_UnknownEncodingHandler to provide information to the parser about encodings that are unknown @@ -504,8 +570,8 @@ typedef void (*XML_SkippedEntityHandler)(void *userData, typedef struct { int map[256]; void *data; - int (*convert)(void *data, const char *s); - void (*release)(void *data); + int (XMLCALL *convert)(void *data, const char *s); + void (XMLCALL *release)(void *data); } XML_Encoding; /* This is called for an encoding that is unknown to the parser. @@ -523,9 +589,10 @@ typedef struct { If info does not describe a suitable encoding, then the parser will return an XML_UNKNOWN_ENCODING error. */ -typedef int (*XML_UnknownEncodingHandler)(void *encodingHandlerData, - const XML_Char *name, - XML_Encoding *info); +typedef int (XMLCALL *XML_UnknownEncodingHandler) ( + void *encodingHandlerData, + const XML_Char *name, + XML_Encoding *info); XMLPARSEAPI(void) XML_SetElementHandler(XML_Parser parser, @@ -813,8 +880,13 @@ XML_GetErrorCode(XML_Parser parser); /* These functions return information about the current parse location. They may be called from any callback called to report - some parse event; in this case the location is the location of - the first of the sequence of characters that generated the event. + some parse event; in this case the location is the location of the + first of the sequence of characters that generated the event. When + called from callbacks generated by declarations in the document + prologue, the location identified isn't as neatly defined, but will + 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 @@ -920,7 +992,7 @@ XML_GetFeatureList(void); */ #define XML_MAJOR_VERSION 1 #define XML_MINOR_VERSION 95 -#define XML_MICRO_VERSION 6 +#define XML_MICRO_VERSION 7 #ifdef __cplusplus } diff --git a/Modules/expat/expat.h.in b/Modules/expat/expat.h.in deleted file mode 100644 index 7c928b1..0000000 --- a/Modules/expat/expat.h.in +++ /dev/null @@ -1,735 +0,0 @@ -/* -Copyright (c) 1998, 1999, 2000 Thai Open Source Software Center Ltd -See the file COPYING for copying permission. -*/ - -#ifndef XmlParse_INCLUDED -#define XmlParse_INCLUDED 1 - -#include - -#ifndef XMLPARSEAPI -# if defined(__declspec) && !defined(__BEOS__) -# define XMLPARSEAPI(type) __declspec(dllimport) type __cdecl -# else -# define XMLPARSEAPI(type) type -# endif -#endif /* not defined XMLPARSEAPI */ - -#ifdef __cplusplus -extern "C" { -#endif - -typedef void *XML_Parser; - -/* Information is UTF-8 encoded. */ -typedef char XML_Char; -typedef char XML_LChar; - -enum XML_Content_Type { - XML_CTYPE_EMPTY = 1, - XML_CTYPE_ANY, - XML_CTYPE_MIXED, - XML_CTYPE_NAME, - XML_CTYPE_CHOICE, - XML_CTYPE_SEQ -}; - -enum XML_Content_Quant { - XML_CQUANT_NONE, - XML_CQUANT_OPT, - XML_CQUANT_REP, - XML_CQUANT_PLUS -}; - -/* If type == XML_CTYPE_EMPTY or XML_CTYPE_ANY, then quant will be - XML_CQUANT_NONE, and the other fields will be zero or NULL. - If type == XML_CTYPE_MIXED, then quant will be NONE or REP and - numchildren will contain number of elements that may be mixed in - and children point to an array of XML_Content cells that will be - all of XML_CTYPE_NAME type with no quantification. - - If type == XML_CTYPE_NAME, then the name points to the name, and - the numchildren field will be zero and children will be NULL. The - quant fields indicates any quantifiers placed on the name. - - CHOICE and SEQ will have name NULL, the number of children in - numchildren and children will point, recursively, to an array - of XML_Content cells. - - The EMPTY, ANY, and MIXED types will only occur at top level. -*/ - -typedef struct XML_cp XML_Content; - -struct XML_cp { - enum XML_Content_Type type; - enum XML_Content_Quant quant; - XML_Char * name; - unsigned int numchildren; - XML_Content * children; -}; - - -/* This is called for an element declaration. See above for - description of the model argument. It's the caller's responsibility - to free model when finished with it. -*/ - -typedef void (*XML_ElementDeclHandler) (void *userData, - const XML_Char *name, - XML_Content *model); - -XMLPARSEAPI(void) -XML_SetElementDeclHandler(XML_Parser parser, - XML_ElementDeclHandler eldecl); - -/* - The Attlist declaration handler is called for *each* attribute. So - a single Attlist declaration with multiple attributes declared will - generate multiple calls to this handler. The "default" parameter - may be NULL in the case of the "#IMPLIED" or "#REQUIRED" keyword. - The "isrequired" parameter will be true and the default value will - be NULL in the case of "#REQUIRED". If "isrequired" is true and - default is non-NULL, then this is a "#FIXED" default. - */ - -typedef void (*XML_AttlistDeclHandler) (void *userData, - const XML_Char *elname, - const XML_Char *attname, - const XML_Char *att_type, - const XML_Char *dflt, - int isrequired); - -XMLPARSEAPI(void) -XML_SetAttlistDeclHandler(XML_Parser parser, - XML_AttlistDeclHandler attdecl); - - - /* The XML declaration handler is called for *both* XML declarations and - text declarations. The way to distinguish is that the version parameter - will be null for text declarations. The encoding parameter may be null - for XML declarations. The standalone parameter will be -1, 0, or 1 - indicating respectively that there was no standalone parameter in - the declaration, that it was given as no, or that it was given as yes. - */ - -typedef void (*XML_XmlDeclHandler) (void *userData, - const XML_Char *version, - const XML_Char *encoding, - int standalone); - -XMLPARSEAPI(void) -XML_SetXmlDeclHandler(XML_Parser parser, - XML_XmlDeclHandler xmldecl); - - -typedef struct { - void *(*malloc_fcn)(size_t size); - void *(*realloc_fcn)(void *ptr, size_t size); - void (*free_fcn)(void *ptr); -} XML_Memory_Handling_Suite; - -/* Constructs a new parser; encoding is the encoding specified by the -external protocol or null if there is none specified. */ - -XMLPARSEAPI(XML_Parser) -XML_ParserCreate(const XML_Char *encoding); - -/* Constructs a new parser and namespace processor. Element type -names and attribute names that belong to a namespace will be expanded; -unprefixed attribute names are never expanded; unprefixed element type -names are expanded only if there is a default namespace. The expanded -name is the concatenation of the namespace URI, the namespace -separator character, and the local part of the name. If the namespace -separator is '\0' then the namespace URI and the local part will be -concatenated without any separator. When a namespace is not declared, -the name and prefix will be passed through without expansion. */ - -XMLPARSEAPI(XML_Parser) -XML_ParserCreateNS(const XML_Char *encoding, XML_Char namespaceSeparator); - - -/* Constructs a new parser using the memory management suit referred to - by memsuite. If memsuite is NULL, then use the standard library memory - suite. If namespaceSeparator is non-NULL it creates a parser with - namespace processing as described above. The character pointed at - will serve as the namespace separator. - - All further memory operations used for the created parser will come from - the given suite. -*/ - -XMLPARSEAPI(XML_Parser) -XML_ParserCreate_MM(const XML_Char *encoding, - const XML_Memory_Handling_Suite *memsuite, - const XML_Char *namespaceSeparator); - -/* atts is array of name/value pairs, terminated by 0; - names and values are 0 terminated. */ - -typedef void (*XML_StartElementHandler)(void *userData, - const XML_Char *name, - const XML_Char **atts); - -typedef void (*XML_EndElementHandler)(void *userData, - const XML_Char *name); - - -/* s is not 0 terminated. */ -typedef void (*XML_CharacterDataHandler)(void *userData, - const XML_Char *s, - int len); - -/* target and data are 0 terminated */ -typedef void (*XML_ProcessingInstructionHandler)(void *userData, - const XML_Char *target, - const XML_Char *data); - -/* data is 0 terminated */ -typedef void (*XML_CommentHandler)(void *userData, const XML_Char *data); - -typedef void (*XML_StartCdataSectionHandler)(void *userData); -typedef void (*XML_EndCdataSectionHandler)(void *userData); - -/* This is called for any characters in the XML document for -which there is no applicable handler. This includes both -characters that are part of markup which is of a kind that is -not reported (comments, markup declarations), or characters -that are part of a construct which could be reported but -for which no handler has been supplied. The characters are passed -exactly as they were in the XML document except that -they will be encoded in UTF-8. Line boundaries are not normalized. -Note that a byte order mark character is not passed to the default handler. -There are no guarantees about how characters are divided between calls -to the default handler: for example, a comment might be split between -multiple calls. */ - -typedef void (*XML_DefaultHandler)(void *userData, - const XML_Char *s, - int len); - -/* This is called for the start of the DOCTYPE declaration, before - any DTD or internal subset is parsed. */ - -typedef void (*XML_StartDoctypeDeclHandler)(void *userData, - const XML_Char *doctypeName, - const XML_Char *sysid, - const XML_Char *pubid, - int has_internal_subset); - -/* This is called for the start of the DOCTYPE declaration when the -closing > is encountered, but after processing any external subset. */ -typedef void (*XML_EndDoctypeDeclHandler)(void *userData); - -/* This is called for entity declarations. The is_parameter_entity - argument will be non-zero if the entity is a parameter entity, zero - otherwise. - - For internal entities (), value will - be non-null and systemId, publicID, and notationName will be null. - The value string is NOT null terminated; the length is provided in - the value_length argument. Since it is legal to have zero-length - values, do not use this argument to test for internal entities. - - For external entities, value will be null and systemId will be non-null. - The publicId argument will be null unless a public identifier was - provided. The notationName argument will have a non-null value only - for unparsed entity declarations. -*/ - -typedef void (*XML_EntityDeclHandler) (void *userData, - const XML_Char *entityName, - int is_parameter_entity, - const XML_Char *value, - int value_length, - const XML_Char *base, - const XML_Char *systemId, - const XML_Char *publicId, - const XML_Char *notationName); - -XMLPARSEAPI(void) -XML_SetEntityDeclHandler(XML_Parser parser, - XML_EntityDeclHandler handler); - -/* OBSOLETE -- OBSOLETE -- OBSOLETE - This handler has been superceded by the EntityDeclHandler above. - It is provided here for backward compatibility. -This is called for a declaration of an unparsed (NDATA) -entity. The base argument is whatever was set by XML_SetBase. -The entityName, systemId and notationName arguments will never be null. -The other arguments may be. */ - -typedef void (*XML_UnparsedEntityDeclHandler)(void *userData, - const XML_Char *entityName, - const XML_Char *base, - const XML_Char *systemId, - const XML_Char *publicId, - const XML_Char *notationName); - -/* This is called for a declaration of notation. -The base argument is whatever was set by XML_SetBase. -The notationName will never be null. The other arguments can be. */ - -typedef void (*XML_NotationDeclHandler)(void *userData, - const XML_Char *notationName, - const XML_Char *base, - const XML_Char *systemId, - const XML_Char *publicId); - -/* When namespace processing is enabled, these are called once for -each namespace declaration. The call to the start and end element -handlers occur between the calls to the start and end namespace -declaration handlers. For an xmlns attribute, prefix will be null. -For an xmlns="" attribute, uri will be null. */ - -typedef void (*XML_StartNamespaceDeclHandler)(void *userData, - const XML_Char *prefix, - const XML_Char *uri); - -typedef void (*XML_EndNamespaceDeclHandler)(void *userData, - const XML_Char *prefix); - -/* This is called if the document is not standalone (it has an -external subset or a reference to a parameter entity, but does not -have standalone="yes"). If this handler returns 0, then processing -will not continue, and the parser will return a -XML_ERROR_NOT_STANDALONE error. */ - -typedef int (*XML_NotStandaloneHandler)(void *userData); - -/* This is called for a reference to an external parsed general entity. -The referenced entity is not automatically parsed. -The application can parse it immediately or later using -XML_ExternalEntityParserCreate. -The parser argument is the parser parsing the entity containing the reference; -it can be passed as the parser argument to XML_ExternalEntityParserCreate. -The systemId argument is the system identifier as specified in the entity -declaration; it will not be null. -The base argument is the system identifier that should be used as the base for -resolving systemId if systemId was relative; this is set by XML_SetBase; -it may be null. -The publicId argument is the public identifier as specified in the entity -declaration, or null if none was specified; the whitespace in the public -identifier will have been normalized as required by the XML spec. -The context argument specifies the parsing context in the format -expected by the context argument to -XML_ExternalEntityParserCreate; context is valid only until the handler -returns, so if the referenced entity is to be parsed later, it must be copied. -The handler should return 0 if processing should not continue because of -a fatal error in the handling of the external entity. -In this case the calling parser will return an -XML_ERROR_EXTERNAL_ENTITY_HANDLING error. -Note that unlike other handlers the first argument is the parser, not -userData. */ - -typedef int (*XML_ExternalEntityRefHandler)(XML_Parser parser, - const XML_Char *context, - const XML_Char *base, - const XML_Char *systemId, - const XML_Char *publicId); - -/* This structure is filled in by the XML_UnknownEncodingHandler -to provide information to the parser about encodings that are unknown -to the parser. -The map[b] member gives information about byte sequences -whose first byte is b. -If map[b] is c where c is >= 0, then b by itself encodes the Unicode scalar -value c. -If map[b] is -1, then the byte sequence is malformed. -If map[b] is -n, where n >= 2, then b is the first byte of an n-byte -sequence that encodes a single Unicode scalar value. -The data member will be passed as the first argument to the convert function. -The convert function is used to convert multibyte sequences; -s will point to a n-byte sequence where map[(unsigned char)*s] == -n. -The convert function must return the Unicode scalar value -represented by this byte sequence or -1 if the byte sequence is malformed. -The convert function may be null if the encoding is a single-byte encoding, -that is if map[b] >= -1 for all bytes b. -When the parser is finished with the encoding, then if release is not null, -it will call release passing it the data member; -once release has been called, the convert function will not be called again. - -Expat places certain restrictions on the encodings that are supported -using this mechanism. - -1. Every ASCII character that can appear in a well-formed XML document, -other than the characters - - $@\^`{}~ - -must be represented by a single byte, and that byte must be the -same byte that represents that character in ASCII. - -2. No character may require more than 4 bytes to encode. - -3. All characters encoded must have Unicode scalar values <= 0xFFFF, (i.e., -characters that would be encoded by surrogates in UTF-16 are not -allowed). Note that this restriction doesn't apply to the built-in -support for UTF-8 and UTF-16. - -4. No Unicode character may be encoded by more than one distinct sequence -of bytes. */ - -typedef struct { - int map[256]; - void *data; - int (*convert)(void *data, const char *s); - void (*release)(void *data); -} XML_Encoding; - -/* This is called for an encoding that is unknown to the parser. -The encodingHandlerData argument is that which was passed as the -second argument to XML_SetUnknownEncodingHandler. -The name argument gives the name of the encoding as specified in -the encoding declaration. -If the callback can provide information about the encoding, -it must fill in the XML_Encoding structure, and return 1. -Otherwise it must return 0. -If info does not describe a suitable encoding, -then the parser will return an XML_UNKNOWN_ENCODING error. */ - -typedef int (*XML_UnknownEncodingHandler)(void *encodingHandlerData, - const XML_Char *name, - XML_Encoding *info); - -XMLPARSEAPI(void) -XML_SetElementHandler(XML_Parser parser, - XML_StartElementHandler start, - XML_EndElementHandler end); - -XMLPARSEAPI(void) -XML_SetStartElementHandler(XML_Parser, XML_StartElementHandler); - -XMLPARSEAPI(void) -XML_SetEndElementHandler(XML_Parser, XML_EndElementHandler); - -XMLPARSEAPI(void) -XML_SetCharacterDataHandler(XML_Parser parser, - XML_CharacterDataHandler handler); - -XMLPARSEAPI(void) -XML_SetProcessingInstructionHandler(XML_Parser parser, - XML_ProcessingInstructionHandler handler); -XMLPARSEAPI(void) -XML_SetCommentHandler(XML_Parser parser, - XML_CommentHandler handler); - -XMLPARSEAPI(void) -XML_SetCdataSectionHandler(XML_Parser parser, - XML_StartCdataSectionHandler start, - XML_EndCdataSectionHandler end); - -XMLPARSEAPI(void) -XML_SetStartCdataSectionHandler(XML_Parser parser, - XML_StartCdataSectionHandler start); - -XMLPARSEAPI(void) -XML_SetEndCdataSectionHandler(XML_Parser parser, - XML_EndCdataSectionHandler end); - -/* This sets the default handler and also inhibits expansion of -internal entities. The entity reference will be passed to the default -handler. */ - -XMLPARSEAPI(void) -XML_SetDefaultHandler(XML_Parser parser, - XML_DefaultHandler handler); - -/* This sets the default handler but does not inhibit expansion of -internal entities. The entity reference will not be passed to the -default handler. */ - -XMLPARSEAPI(void) -XML_SetDefaultHandlerExpand(XML_Parser parser, - XML_DefaultHandler handler); - -XMLPARSEAPI(void) -XML_SetDoctypeDeclHandler(XML_Parser parser, - XML_StartDoctypeDeclHandler start, - XML_EndDoctypeDeclHandler end); - -XMLPARSEAPI(void) -XML_SetStartDoctypeDeclHandler(XML_Parser parser, - XML_StartDoctypeDeclHandler start); - -XMLPARSEAPI(void) -XML_SetEndDoctypeDeclHandler(XML_Parser parser, - XML_EndDoctypeDeclHandler end); - -XMLPARSEAPI(void) -XML_SetUnparsedEntityDeclHandler(XML_Parser parser, - XML_UnparsedEntityDeclHandler handler); - -XMLPARSEAPI(void) -XML_SetNotationDeclHandler(XML_Parser parser, - XML_NotationDeclHandler handler); - -XMLPARSEAPI(void) -XML_SetNamespaceDeclHandler(XML_Parser parser, - XML_StartNamespaceDeclHandler start, - XML_EndNamespaceDeclHandler end); - -XMLPARSEAPI(void) -XML_SetStartNamespaceDeclHandler(XML_Parser parser, - XML_StartNamespaceDeclHandler start); - -XMLPARSEAPI(void) -XML_SetEndNamespaceDeclHandler(XML_Parser parser, - XML_EndNamespaceDeclHandler end); - -XMLPARSEAPI(void) -XML_SetNotStandaloneHandler(XML_Parser parser, - XML_NotStandaloneHandler handler); - -XMLPARSEAPI(void) -XML_SetExternalEntityRefHandler(XML_Parser parser, - XML_ExternalEntityRefHandler handler); - -/* If a non-null value for arg is specified here, then it will be passed -as the first argument to the external entity ref handler instead -of the parser object. */ -XMLPARSEAPI(void) -XML_SetExternalEntityRefHandlerArg(XML_Parser, void *arg); - -XMLPARSEAPI(void) -XML_SetUnknownEncodingHandler(XML_Parser parser, - XML_UnknownEncodingHandler handler, - void *encodingHandlerData); - -/* This can be called within a handler for a start element, end element, -processing instruction or character data. It causes the corresponding -markup to be passed to the default handler. */ -XMLPARSEAPI(void) -XML_DefaultCurrent(XML_Parser parser); - -/* If do_nst is non-zero, and namespace processing is in effect, and - a name has a prefix (i.e. an explicit namespace qualifier) then - that name is returned as a triplet in a single - string separated by the separator character specified when the parser - was created: URI + sep + local_name + sep + prefix. - - If do_nst is zero, then namespace information is returned in the - default manner (URI + sep + local_name) whether or not the names - has a prefix. -*/ - -XMLPARSEAPI(void) -XML_SetReturnNSTriplet(XML_Parser parser, int do_nst); - -/* This value is passed as the userData argument to callbacks. */ -XMLPARSEAPI(void) -XML_SetUserData(XML_Parser parser, void *userData); - -/* Returns the last value set by XML_SetUserData or null. */ -#define XML_GetUserData(parser) (*(void **)(parser)) - -/* This is equivalent to supplying an encoding argument -to XML_ParserCreate. It must not be called after XML_Parse -or XML_ParseBuffer. */ - -XMLPARSEAPI(int) -XML_SetEncoding(XML_Parser parser, const XML_Char *encoding); - -/* If this function is called, then the parser will be passed -as the first argument to callbacks instead of userData. -The userData will still be accessible using XML_GetUserData. */ - -XMLPARSEAPI(void) -XML_UseParserAsHandlerArg(XML_Parser parser); - -/* Sets the base to be used for resolving relative URIs in system -identifiers in declarations. Resolving relative identifiers is left -to the application: this value will be passed through as the base -argument to the XML_ExternalEntityRefHandler, XML_NotationDeclHandler -and XML_UnparsedEntityDeclHandler. The base argument will be copied. -Returns zero if out of memory, non-zero otherwise. */ - -XMLPARSEAPI(int) -XML_SetBase(XML_Parser parser, const XML_Char *base); - -XMLPARSEAPI(const XML_Char *) -XML_GetBase(XML_Parser parser); - -/* Returns the number of the attribute/value pairs passed in last call -to the XML_StartElementHandler that were specified in the start-tag -rather than defaulted. Each attribute/value pair counts as 2; thus -this correspondds to an index into the atts array passed to the -XML_StartElementHandler. */ - -XMLPARSEAPI(int) -XML_GetSpecifiedAttributeCount(XML_Parser parser); - -/* Returns the index of the ID attribute passed in the last call to -XML_StartElementHandler, or -1 if there is no ID attribute. Each -attribute/value pair counts as 2; thus this correspondds to an index -into the atts array passed to the XML_StartElementHandler. */ - -XMLPARSEAPI(int) -XML_GetIdAttributeIndex(XML_Parser parser); - -/* Parses some input. Returns 0 if a fatal error is detected. -The last call to XML_Parse must have isFinal true; -len may be zero for this call (or any other). */ -XMLPARSEAPI(int) -XML_Parse(XML_Parser parser, const char *s, int len, int isFinal); - -XMLPARSEAPI(void *) -XML_GetBuffer(XML_Parser parser, int len); - -XMLPARSEAPI(int) -XML_ParseBuffer(XML_Parser parser, int len, int isFinal); - -/* Creates an XML_Parser object that can parse an external general -entity; context is a '\0'-terminated string specifying the parse -context; encoding is a '\0'-terminated string giving the name of the -externally specified encoding, or null if there is no externally -specified encoding. The context string consists of a sequence of -tokens separated by formfeeds (\f); a token consisting of a name -specifies that the general entity of the name is open; a token of the -form prefix=uri specifies the namespace for a particular prefix; a -token of the form =uri specifies the default namespace. This can be -called at any point after the first call to an -ExternalEntityRefHandler so longer as the parser has not yet been -freed. The new parser is completely independent and may safely be -used in a separate thread. The handlers and userData are initialized -from the parser argument. Returns 0 if out of memory. Otherwise -returns a new XML_Parser object. */ -XMLPARSEAPI(XML_Parser) -XML_ExternalEntityParserCreate(XML_Parser parser, - const XML_Char *context, - const XML_Char *encoding); - -enum XML_ParamEntityParsing { - XML_PARAM_ENTITY_PARSING_NEVER, - XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE, - XML_PARAM_ENTITY_PARSING_ALWAYS -}; - -/* Controls parsing of parameter entities (including the external DTD -subset). If parsing of parameter entities is enabled, then references -to external parameter entities (including the external DTD subset) -will be passed to the handler set with -XML_SetExternalEntityRefHandler. The context passed will be 0. -Unlike external general entities, external parameter entities can only -be parsed synchronously. If the external parameter entity is to be -parsed, it must be parsed during the call to the external entity ref -handler: the complete sequence of XML_ExternalEntityParserCreate, -XML_Parse/XML_ParseBuffer and XML_ParserFree calls must be made during -this call. After XML_ExternalEntityParserCreate has been called to -create the parser for the external parameter entity (context must be 0 -for this call), it is illegal to make any calls on the old parser -until XML_ParserFree has been called on the newly created parser. If -the library has been compiled without support for parameter entity -parsing (ie without XML_DTD being defined), then -XML_SetParamEntityParsing will return 0 if parsing of parameter -entities is requested; otherwise it will return non-zero. */ - -XMLPARSEAPI(int) -XML_SetParamEntityParsing(XML_Parser parser, - enum XML_ParamEntityParsing parsing); - -enum XML_Error { - XML_ERROR_NONE, - XML_ERROR_NO_MEMORY, - XML_ERROR_SYNTAX, - XML_ERROR_NO_ELEMENTS, - XML_ERROR_INVALID_TOKEN, - XML_ERROR_UNCLOSED_TOKEN, - XML_ERROR_PARTIAL_CHAR, - XML_ERROR_TAG_MISMATCH, - XML_ERROR_DUPLICATE_ATTRIBUTE, - XML_ERROR_JUNK_AFTER_DOC_ELEMENT, - XML_ERROR_PARAM_ENTITY_REF, - XML_ERROR_UNDEFINED_ENTITY, - XML_ERROR_RECURSIVE_ENTITY_REF, - XML_ERROR_ASYNC_ENTITY, - XML_ERROR_BAD_CHAR_REF, - XML_ERROR_BINARY_ENTITY_REF, - XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF, - XML_ERROR_MISPLACED_XML_PI, - XML_ERROR_UNKNOWN_ENCODING, - XML_ERROR_INCORRECT_ENCODING, - XML_ERROR_UNCLOSED_CDATA_SECTION, - XML_ERROR_EXTERNAL_ENTITY_HANDLING, - XML_ERROR_NOT_STANDALONE, - XML_ERROR_UNEXPECTED_STATE -}; - -/* If XML_Parse or XML_ParseBuffer have returned 0, then XML_GetErrorCode -returns information about the error. */ - -XMLPARSEAPI(enum XML_Error) -XML_GetErrorCode(XML_Parser parser); - -/* These functions return information about the current parse location. -They may be called when XML_Parse or XML_ParseBuffer return 0; -in this case the location is the location of the character at which -the error was detected. -They may also be called from any other callback called to report -some parse event; in this the location is the location of the first -of the sequence of characters that generated the event. */ - -XMLPARSEAPI(int) XML_GetCurrentLineNumber(XML_Parser parser); -XMLPARSEAPI(int) XML_GetCurrentColumnNumber(XML_Parser parser); -XMLPARSEAPI(long) XML_GetCurrentByteIndex(XML_Parser parser); - -/* Return the number of bytes in the current event. -Returns 0 if the event is in an internal entity. */ - -XMLPARSEAPI(int) -XML_GetCurrentByteCount(XML_Parser parser); - -/* If XML_CONTEXT_BYTES is defined, returns the input buffer, sets - the integer pointed to by offset to the offset within this buffer - of the current parse position, and sets the integer pointed to by size - to the size of this buffer (the number of input bytes). Otherwise - returns a null pointer. Also returns a null pointer if a parse isn't - active. - - NOTE: The character pointer returned should not be used outside - the handler that makes the call. */ - -XMLPARSEAPI(const char *) -XML_GetInputContext(XML_Parser parser, - int *offset, - int *size); - -/* For backwards compatibility with previous versions. */ -#define XML_GetErrorLineNumber XML_GetCurrentLineNumber -#define XML_GetErrorColumnNumber XML_GetCurrentColumnNumber -#define XML_GetErrorByteIndex XML_GetCurrentByteIndex - -/* Frees memory used by the parser. */ -XMLPARSEAPI(void) -XML_ParserFree(XML_Parser parser); - -/* Returns a string describing the error. */ -XMLPARSEAPI(const XML_LChar *) -XML_ErrorString(int code); - -/* Return a string containing the version number of this expat */ -XMLPARSEAPI(const XML_LChar *) -XML_ExpatVersion(void); - -typedef struct { - int major; - int minor; - int micro; -} XML_Expat_Version; - -/* Return an XML_Expat_Version structure containing numeric version - number information for this version of expat */ - -XMLPARSEAPI(XML_Expat_Version) -XML_ExpatVersionInfo(void); - -#define XML_MAJOR_VERSION @EXPAT_MAJOR_VERSION@ -#define XML_MINOR_VERSION @EXPAT_MINOR_VERSION@ -#define XML_MICRO_VERSION @EXPAT_EDIT@ - -#ifdef __cplusplus -} -#endif - -#endif /* not XmlParse_INCLUDED */ diff --git a/Modules/expat/iasciitab.h b/Modules/expat/iasciitab.h index 55dbc39..24a1d5c 100644 --- a/Modules/expat/iasciitab.h +++ b/Modules/expat/iasciitab.h @@ -1,6 +1,5 @@ -/* -Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd -See the file COPYING for copying permission. +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. */ /* Like asciitab.h, except that 0xD has code BT_S rather than BT_CR */ diff --git a/Modules/expat/internal.h b/Modules/expat/internal.h index 1bf6baa..ff056c6 100644 --- a/Modules/expat/internal.h +++ b/Modules/expat/internal.h @@ -20,17 +20,20 @@ and therefore subject to change. */ -#if defined(__GNUC__) -/* Instability reported with egcs on a RedHat Linux 7.3. - Let's comment it out: +#if defined(__GNUC__) && defined(__i386__) +/* We'll use this version by default only where we know it helps. + + regparm() generates warnings on Solaris boxes. See SF bug #692878. + + Instability reported with egcs on a RedHat Linux 7.3. + Let's comment out: #define FASTCALL __attribute__((stdcall, regparm(3))) and let's try this: */ #define FASTCALL __attribute__((regparm(3))) -#define PTRCALL #define PTRFASTCALL __attribute__((regparm(3))) +#endif -#elif defined(WIN32) /* Using __fastcall seems to have an unexpected negative effect under MS VC++, especially for function pointers, so we won't use it for now on that platform. It may be reconsidered for a future release @@ -38,11 +41,8 @@ Likely reason: __fastcall on Windows is like stdcall, therefore the compiler cannot perform stack optimizations for call clusters. */ -#define FASTCALL -#define PTRCALL -#define PTRFASTCALL -#endif +/* Make sure all of these are defined if they aren't already. */ #ifndef FASTCALL #define FASTCALL diff --git a/Modules/expat/latin1tab.h b/Modules/expat/latin1tab.h index 178b1d1..53c25d7 100644 --- a/Modules/expat/latin1tab.h +++ b/Modules/expat/latin1tab.h @@ -1,6 +1,5 @@ -/* -Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd -See the file COPYING for copying permission. +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. */ /* 0x80 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, diff --git a/Modules/expat/macconfig.h b/Modules/expat/macconfig.h new file mode 100644 index 0000000..3c5eb54 --- /dev/null +++ b/Modules/expat/macconfig.h @@ -0,0 +1,104 @@ +/*================================================================ +** Copyright 2000, Clark Cooper +** All rights reserved. +** +** This is free software. You are permitted to copy, distribute, or modify +** it under the terms of the MIT/X license (contained in the COPYING file +** with this distribution.) +** +*/ + +#ifndef MACCONFIG_H +#define MACCONFIG_H + + +/* 1234 = LIL_ENDIAN, 4321 = BIGENDIAN */ +#define BYTEORDER 4321 + +/* Define to 1 if you have the `bcopy' function. */ +#undef HAVE_BCOPY + +/* Define to 1 if you have the header file. */ +#undef HAVE_DLFCN_H + +/* Define to 1 if you have the header file. */ +#undef HAVE_FCNTL_H + +/* Define to 1 if you have the `getpagesize' function. */ +#undef HAVE_GETPAGESIZE + +/* Define to 1 if you have the header file. */ +#undef HAVE_INTTYPES_H + +/* Define to 1 if you have the `memmove' function. */ +#define HAVE_MEMMOVE + +/* Define to 1 if you have the header file. */ +#undef HAVE_MEMORY_H + +/* Define to 1 if you have a working `mmap' system call. */ +#undef HAVE_MMAP + +/* Define to 1 if you have the header file. */ +#undef HAVE_STDINT_H + +/* Define to 1 if you have the header file. */ +#define HAVE_STDLIB_H + +/* Define to 1 if you have the header file. */ +#undef HAVE_STRINGS_H + +/* Define to 1 if you have the header file. */ +#define HAVE_STRING_H + +/* Define to 1 if you have the header file. */ +#undef HAVE_SYS_STAT_H + +/* Define to 1 if you have the header file. */ +#undef HAVE_SYS_TYPES_H + +/* Define to 1 if you have the header file. */ +#undef HAVE_UNISTD_H + +/* Define to the address where bug reports for this package should be sent. */ +#undef PACKAGE_BUGREPORT + +/* Define to the full name of this package. */ +#undef PACKAGE_NAME + +/* Define to the full name and version of this package. */ +#undef PACKAGE_STRING + +/* Define to the one symbol short name of this package. */ +#undef PACKAGE_TARNAME + +/* Define to the version of this package. */ +#undef PACKAGE_VERSION + +/* Define to 1 if you have the ANSI C header files. */ +#define STDC_HEADERS + +/* whether byteorder is bigendian */ +#define WORDS_BIGENDIAN + +/* Define to specify how much context to retain around the current parse + point. */ +#undef XML_CONTEXT_BYTES + +/* Define to make parameter entity parsing functionality available. */ +#define XML_DTD + +/* Define to make XML Namespaces functionality available. */ +#define XML_NS + +/* Define to empty if `const' does not conform to ANSI C. */ +#undef const + +/* Define to `long' if does not define. */ +#define off_t long + +/* Define to `unsigned' if does not define. */ +#undef size_t + + +#endif /* ifndef MACCONFIG_H */ diff --git a/Modules/expat/utf8tab.h b/Modules/expat/utf8tab.h index 9e3b6b8..7bb3e77 100644 --- a/Modules/expat/utf8tab.h +++ b/Modules/expat/utf8tab.h @@ -1,6 +1,5 @@ -/* -Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd -See the file COPYING for copying permission. +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. */ diff --git a/Modules/expat/winconfig.h b/Modules/expat/winconfig.h index 77b1ece..c1b791d 100644 --- a/Modules/expat/winconfig.h +++ b/Modules/expat/winconfig.h @@ -5,8 +5,6 @@ ** This is free software. You are permitted to copy, distribute, or modify ** it under the terms of the MIT/X license (contained in the COPYING file ** with this distribution.) -** -** */ #ifndef WINCONFIG_H @@ -21,7 +19,12 @@ #define XML_NS 1 #define XML_DTD 1 -#define XML_BYTE_ORDER 12 #define XML_CONTEXT_BYTES 1024 +/* we will assume all Windows platforms are little endian */ +#define BYTEORDER 1234 + +/* Windows has memmove() available. */ +#define HAVE_MEMMOVE + #endif /* ndef WINCONFIG_H */ diff --git a/Modules/expat/xmlparse.c b/Modules/expat/xmlparse.c index eae9374..fc4adbb 100644 --- a/Modules/expat/xmlparse.c +++ b/Modules/expat/xmlparse.c @@ -5,35 +5,20 @@ #include #include /* memset(), memcpy() */ -#ifdef COMPILED_FROM_DSP +#define XML_BUILDING_EXPAT 1 +#ifdef COMPILED_FROM_DSP #include "winconfig.h" -#define XMLPARSEAPI(type) type __cdecl -#include "expat.h" -#undef XMLPARSEAPI - #elif defined(MACOS_CLASSIC) - #include "macconfig.h" -#include "expat.h" - #else - -/* Unused - MvL +#ifdef HAVE_EXPAT_CONFIG_H #include -*/ - -#ifdef __declspec -#define XMLPARSEAPI(type) type __cdecl #endif +#endif /* ndef COMPILED_FROM_DSP */ #include "expat.h" -#ifdef __declspec -#undef XMLPARSEAPI -#endif -#endif /* ndef COMPILED_FROM_DSP */ - #ifdef XML_UNICODE #define XML_ENCODE_MAX XML_UTF16_ENCODE_MAX #define XmlConvert XmlUtf16Convert @@ -83,6 +68,15 @@ typedef char ICHAR; /* Round up n to be a multiple of sz, where sz is a power of 2. */ #define ROUND_UP(n, sz) (((n) + ((sz) - 1)) & ~((sz) - 1)) +/* Handle the case where memmove() doesn't exist. */ +#ifndef HAVE_MEMMOVE +#ifdef HAVE_BCOPY +#define memmove(d,s,l) bcopy((s),(d),(l)) +#else +#error memmove does not exist on this platform, nor is a substitute available +#endif /* HAVE_BCOPY */ +#endif /* HAVE_MEMMOVE */ + #include "internal.h" #include "xmltok.h" #include "xmlrole.h" @@ -95,12 +89,37 @@ typedef struct { typedef struct { NAMED **v; + unsigned char power; size_t size; size_t used; - size_t usedLim; const XML_Memory_Handling_Suite *mem; } HASH_TABLE; +/* Basic character hash algorithm, taken from Python's string hash: + h = h * 1000003 ^ character, the constant being a prime number. + +*/ +#ifdef XML_UNICODE +#define CHAR_HASH(h, c) \ + (((h) * 0xF4243) ^ (unsigned short)(c)) +#else +#define CHAR_HASH(h, c) \ + (((h) * 0xF4243) ^ (unsigned char)(c)) +#endif + +/* For probing (after a collision) we need a step size relative prime + to the hash table size, which is a power of 2. We use double-hashing, + since we can calculate a second hash value cheaply by taking those bits + of the first hash value that were discarded (masked out) when the table + index was calculated: index = hash & mask, where mask = table->size - 1. + We limit the maximum step size to table->size / 4 (mask >> 2) and make + it odd, since odd numbers are always relative prime to a power of 2. +*/ +#define SECOND_HASH(hash, mask, power) \ + ((((hash) & ~(mask)) >> ((power) - 1)) & ((mask) >> 2)) +#define PROBE_STEP(hash, mask, power) \ + ((unsigned char)((SECOND_HASH(hash, mask, power)) | 1)) + typedef struct { NAMED **p; NAMED **end; @@ -109,6 +128,7 @@ typedef struct { #define INIT_TAG_BUF_SIZE 32 /* must be a multiple of sizeof(XML_Char) */ #define INIT_DATA_BUF_SIZE 1024 #define INIT_ATTS_SIZE 16 +#define INIT_ATTS_VERSION 0xFFFFFFFF #define INIT_BLOCK_SIZE 1024 #define INIT_BUFFER_SIZE 1024 @@ -217,6 +237,12 @@ typedef struct { } DEFAULT_ATTRIBUTE; typedef struct { + unsigned long version; + unsigned long hash; + const XML_Char *uriName; +} NS_ATT; + +typedef struct { const XML_Char *name; PREFIX *prefix; const ATTRIBUTE_ID *idAtt; @@ -492,11 +518,14 @@ struct XML_ParserStruct { int m_nSpecifiedAtts; int m_idAttIndex; ATTRIBUTE *m_atts; + NS_ATT *m_nsAtts; + unsigned long m_nsAttsVersion; + unsigned char m_nsAttsPower; POSITION m_position; STRING_POOL m_tempPool; STRING_POOL m_temp2Pool; char *m_groupConnector; - unsigned m_groupSize; + unsigned int m_groupSize; XML_Char m_namespaceSeparator; XML_Parser m_parentParser; #ifdef XML_DTD @@ -594,6 +623,9 @@ struct XML_ParserStruct { #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 tempPool (parser->m_tempPool) #define temp2Pool (parser->m_temp2Pool) #define groupConnector (parser->m_groupConnector) @@ -606,6 +638,7 @@ struct XML_ParserStruct { #define paramEntityParsing (parser->m_paramEntityParsing) #endif /* XML_DTD */ +#ifdef XML_DTD #define parsing \ (parentParser \ ? \ @@ -616,14 +649,22 @@ struct XML_ParserStruct { (processor != externalEntityInitProcessor)) \ : \ (processor != prologInitProcessor)) +#else +#define parsing \ + (parentParser \ + ? \ + (processor != externalEntityInitProcessor) \ + : \ + (processor != prologInitProcessor)) +#endif /* XML_DTD */ -XML_Parser +XML_Parser XMLCALL XML_ParserCreate(const XML_Char *encodingName) { return XML_ParserCreate_MM(encodingName, NULL, NULL); } -XML_Parser +XML_Parser XMLCALL XML_ParserCreateNS(const XML_Char *encodingName, XML_Char nsSep) { XML_Char tmp[2]; @@ -638,7 +679,7 @@ static const XML_Char implicitContext[] = { 'n', 'a', 'm', 'e', 's', 'p', 'a', 'c', 'e', '\0' }; -XML_Parser +XML_Parser XMLCALL XML_ParserCreate_MM(const XML_Char *encodingName, const XML_Memory_Handling_Suite *memsuite, const XML_Char *nameSep) @@ -731,6 +772,10 @@ parserCreate(const XML_Char *encodingName, ns = XML_FALSE; ns_triplets = XML_FALSE; + nsAtts = NULL; + nsAttsVersion = 0; + nsAttsPower = 0; + poolInit(&tempPool, &(parser->m_mem)); poolInit(&temp2Pool, &(parser->m_mem)); parserInit(parser, encodingName); @@ -835,7 +880,7 @@ moveToFreeBindingList(XML_Parser parser, BINDING *bindings) } } -XML_Bool +XML_Bool XMLCALL XML_ParserReset(XML_Parser parser, const XML_Char *encodingName) { TAG *tStk; @@ -852,8 +897,7 @@ XML_ParserReset(XML_Parser parser, const XML_Char *encodingName) freeTagList = tag; } moveToFreeBindingList(parser, inheritedBindings); - if (unknownEncodingMem) - FREE(unknownEncodingMem); + FREE(unknownEncodingMem); if (unknownEncodingRelease) unknownEncodingRelease(unknownEncodingData); poolClear(&tempPool); @@ -863,7 +907,7 @@ XML_ParserReset(XML_Parser parser, const XML_Char *encodingName) return setContext(parser, implicitContext); } -enum XML_Status +enum XML_Status XMLCALL XML_SetEncoding(XML_Parser parser, const XML_Char *encodingName) { /* Block after XML_Parse()/XML_ParseBuffer() has been called. @@ -882,7 +926,7 @@ XML_SetEncoding(XML_Parser parser, const XML_Char *encodingName) return XML_STATUS_OK; } -XML_Parser +XML_Parser XMLCALL XML_ExternalEntityParserCreate(XML_Parser oldParser, const XML_Char *context, const XML_Char *encodingName) @@ -1025,7 +1069,7 @@ destroyBindings(BINDING *bindings, XML_Parser parser) } } -void +void XMLCALL XML_ParserFree(XML_Parser parser) { for (;;) { @@ -1056,25 +1100,23 @@ XML_ParserFree(XML_Parser parser) #endif /* XML_DTD */ dtdDestroy(_dtd, (XML_Bool)!parentParser, &parser->m_mem); FREE((void *)atts); - if (groupConnector) - FREE(groupConnector); - if (buffer) - FREE(buffer); + FREE(groupConnector); + FREE(buffer); FREE(dataBuf); - if (unknownEncodingMem) - FREE(unknownEncodingMem); + FREE(nsAtts); + FREE(unknownEncodingMem); if (unknownEncodingRelease) unknownEncodingRelease(unknownEncodingData); FREE(parser); } -void +void XMLCALL XML_UseParserAsHandlerArg(XML_Parser parser) { handlerArg = parser; } -enum XML_Error +enum XML_Error XMLCALL XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD) { #ifdef XML_DTD @@ -1088,7 +1130,7 @@ XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD) #endif } -void +void XMLCALL XML_SetReturnNSTriplet(XML_Parser parser, int do_nst) { /* block after XML_Parse()/XML_ParseBuffer() has been called */ @@ -1097,7 +1139,7 @@ XML_SetReturnNSTriplet(XML_Parser parser, int do_nst) ns_triplets = do_nst ? XML_TRUE : XML_FALSE; } -void +void XMLCALL XML_SetUserData(XML_Parser parser, void *p) { if (handlerArg == userData) @@ -1106,7 +1148,7 @@ XML_SetUserData(XML_Parser parser, void *p) userData = p; } -enum XML_Status +enum XML_Status XMLCALL XML_SetBase(XML_Parser parser, const XML_Char *p) { if (p) { @@ -1120,25 +1162,25 @@ XML_SetBase(XML_Parser parser, const XML_Char *p) return XML_STATUS_OK; } -const XML_Char * +const XML_Char * XMLCALL XML_GetBase(XML_Parser parser) { return curBase; } -int +int XMLCALL XML_GetSpecifiedAttributeCount(XML_Parser parser) { return nSpecifiedAtts; } -int +int XMLCALL XML_GetIdAttributeIndex(XML_Parser parser) { return idAttIndex; } -void +void XMLCALL XML_SetElementHandler(XML_Parser parser, XML_StartElementHandler start, XML_EndElementHandler end) @@ -1147,40 +1189,40 @@ XML_SetElementHandler(XML_Parser parser, endElementHandler = end; } -void +void XMLCALL XML_SetStartElementHandler(XML_Parser parser, XML_StartElementHandler start) { startElementHandler = start; } -void +void XMLCALL XML_SetEndElementHandler(XML_Parser parser, XML_EndElementHandler end) { endElementHandler = end; } -void +void XMLCALL XML_SetCharacterDataHandler(XML_Parser parser, XML_CharacterDataHandler handler) { characterDataHandler = handler; } -void +void XMLCALL XML_SetProcessingInstructionHandler(XML_Parser parser, XML_ProcessingInstructionHandler handler) { processingInstructionHandler = handler; } -void +void XMLCALL XML_SetCommentHandler(XML_Parser parser, XML_CommentHandler handler) { commentHandler = handler; } -void +void XMLCALL XML_SetCdataSectionHandler(XML_Parser parser, XML_StartCdataSectionHandler start, XML_EndCdataSectionHandler end) @@ -1189,19 +1231,19 @@ XML_SetCdataSectionHandler(XML_Parser parser, endCdataSectionHandler = end; } -void +void XMLCALL XML_SetStartCdataSectionHandler(XML_Parser parser, XML_StartCdataSectionHandler start) { startCdataSectionHandler = start; } -void +void XMLCALL XML_SetEndCdataSectionHandler(XML_Parser parser, XML_EndCdataSectionHandler end) { endCdataSectionHandler = end; } -void +void XMLCALL XML_SetDefaultHandler(XML_Parser parser, XML_DefaultHandler handler) { @@ -1209,7 +1251,7 @@ XML_SetDefaultHandler(XML_Parser parser, defaultExpandInternalEntities = XML_FALSE; } -void +void XMLCALL XML_SetDefaultHandlerExpand(XML_Parser parser, XML_DefaultHandler handler) { @@ -1217,7 +1259,7 @@ XML_SetDefaultHandlerExpand(XML_Parser parser, defaultExpandInternalEntities = XML_TRUE; } -void +void XMLCALL XML_SetDoctypeDeclHandler(XML_Parser parser, XML_StartDoctypeDeclHandler start, XML_EndDoctypeDeclHandler end) @@ -1226,33 +1268,33 @@ XML_SetDoctypeDeclHandler(XML_Parser parser, endDoctypeDeclHandler = end; } -void +void XMLCALL XML_SetStartDoctypeDeclHandler(XML_Parser parser, XML_StartDoctypeDeclHandler start) { startDoctypeDeclHandler = start; } -void +void XMLCALL XML_SetEndDoctypeDeclHandler(XML_Parser parser, XML_EndDoctypeDeclHandler end) { endDoctypeDeclHandler = end; } -void +void XMLCALL XML_SetUnparsedEntityDeclHandler(XML_Parser parser, XML_UnparsedEntityDeclHandler handler) { unparsedEntityDeclHandler = handler; } -void +void XMLCALL XML_SetNotationDeclHandler(XML_Parser parser, XML_NotationDeclHandler handler) { notationDeclHandler = handler; } -void +void XMLCALL XML_SetNamespaceDeclHandler(XML_Parser parser, XML_StartNamespaceDeclHandler start, XML_EndNamespaceDeclHandler end) @@ -1261,33 +1303,33 @@ XML_SetNamespaceDeclHandler(XML_Parser parser, endNamespaceDeclHandler = end; } -void +void XMLCALL XML_SetStartNamespaceDeclHandler(XML_Parser parser, XML_StartNamespaceDeclHandler start) { startNamespaceDeclHandler = start; } -void +void XMLCALL XML_SetEndNamespaceDeclHandler(XML_Parser parser, XML_EndNamespaceDeclHandler end) { endNamespaceDeclHandler = end; } -void +void XMLCALL XML_SetNotStandaloneHandler(XML_Parser parser, XML_NotStandaloneHandler handler) { notStandaloneHandler = handler; } -void +void XMLCALL XML_SetExternalEntityRefHandler(XML_Parser parser, XML_ExternalEntityRefHandler handler) { externalEntityRefHandler = handler; } -void +void XMLCALL XML_SetExternalEntityRefHandlerArg(XML_Parser parser, void *arg) { if (arg) @@ -1296,14 +1338,14 @@ XML_SetExternalEntityRefHandlerArg(XML_Parser parser, void *arg) externalEntityRefHandlerArg = parser; } -void +void XMLCALL XML_SetSkippedEntityHandler(XML_Parser parser, XML_SkippedEntityHandler handler) { skippedEntityHandler = handler; } -void +void XMLCALL XML_SetUnknownEncodingHandler(XML_Parser parser, XML_UnknownEncodingHandler handler, void *data) @@ -1312,34 +1354,34 @@ XML_SetUnknownEncodingHandler(XML_Parser parser, unknownEncodingHandlerData = data; } -void +void XMLCALL XML_SetElementDeclHandler(XML_Parser parser, XML_ElementDeclHandler eldecl) { elementDeclHandler = eldecl; } -void +void XMLCALL XML_SetAttlistDeclHandler(XML_Parser parser, XML_AttlistDeclHandler attdecl) { attlistDeclHandler = attdecl; } -void +void XMLCALL XML_SetEntityDeclHandler(XML_Parser parser, XML_EntityDeclHandler handler) { entityDeclHandler = handler; } -void +void XMLCALL XML_SetXmlDeclHandler(XML_Parser parser, XML_XmlDeclHandler handler) { xmlDeclHandler = handler; } -int +int XMLCALL XML_SetParamEntityParsing(XML_Parser parser, enum XML_ParamEntityParsing peParsing) { @@ -1354,7 +1396,7 @@ XML_SetParamEntityParsing(XML_Parser parser, #endif } -enum XML_Status +enum XML_Status XMLCALL XML_Parse(XML_Parser parser, const char *s, int len, int isFinal) { if (len == 0) { @@ -1429,7 +1471,7 @@ XML_Parse(XML_Parser parser, const char *s, int len, int isFinal) } } -enum XML_Status +enum XML_Status XMLCALL XML_ParseBuffer(XML_Parser parser, int len, int isFinal) { const char *start = bufferPtr; @@ -1452,7 +1494,7 @@ XML_ParseBuffer(XML_Parser parser, int len, int isFinal) } } -void * +void * XMLCALL XML_GetBuffer(XML_Parser parser, int len) { if (len > bufferLim - bufferEnd) { @@ -1521,13 +1563,13 @@ XML_GetBuffer(XML_Parser parser, int len) return bufferEnd; } -enum XML_Error +enum XML_Error XMLCALL XML_GetErrorCode(XML_Parser parser) { return errorCode; } -long +long XMLCALL XML_GetCurrentByteIndex(XML_Parser parser) { if (eventPtr) @@ -1535,7 +1577,7 @@ XML_GetCurrentByteIndex(XML_Parser parser) return -1; } -int +int XMLCALL XML_GetCurrentByteCount(XML_Parser parser) { if (eventEndPtr && eventPtr) @@ -1543,7 +1585,7 @@ XML_GetCurrentByteCount(XML_Parser parser) return 0; } -const char * +const char * XMLCALL XML_GetInputContext(XML_Parser parser, int *offset, int *size) { #ifdef XML_CONTEXT_BYTES @@ -1556,7 +1598,7 @@ XML_GetInputContext(XML_Parser parser, int *offset, int *size) return (char *) 0; } -int +int XMLCALL XML_GetCurrentLineNumber(XML_Parser parser) { if (eventPtr) { @@ -1566,7 +1608,7 @@ XML_GetCurrentLineNumber(XML_Parser parser) return position.lineNumber + 1; } -int +int XMLCALL XML_GetCurrentColumnNumber(XML_Parser parser) { if (eventPtr) { @@ -1576,31 +1618,31 @@ XML_GetCurrentColumnNumber(XML_Parser parser) return position.columnNumber; } -void +void XMLCALL XML_FreeContentModel(XML_Parser parser, XML_Content *model) { FREE(model); } -void * +void * XMLCALL XML_MemMalloc(XML_Parser parser, size_t size) { return MALLOC(size); } -void * +void * XMLCALL XML_MemRealloc(XML_Parser parser, void *ptr, size_t size) { return REALLOC(ptr, size); } -void +void XMLCALL XML_MemFree(XML_Parser parser, void *ptr) { FREE(ptr); } -void +void XMLCALL XML_DefaultCurrent(XML_Parser parser) { if (defaultHandler) { @@ -1614,7 +1656,7 @@ XML_DefaultCurrent(XML_Parser parser) } } -const XML_LChar * +const XML_LChar * XMLCALL XML_ErrorString(enum XML_Error code) { static const XML_LChar *message[] = { @@ -1644,14 +1686,15 @@ XML_ErrorString(enum XML_Error code) XML_L("unexpected parser state - please send a bug report"), XML_L("entity declared in parameter entity"), XML_L("requested feature requires XML_DTD support in Expat"), - XML_L("cannot change setting once parsing has begun") + XML_L("cannot change setting once parsing has begun"), + XML_L("unbound prefix") }; if (code > 0 && code < sizeof(message)/sizeof(message[0])) return message[code]; return NULL; } -const XML_LChar * +const XML_LChar * XMLCALL XML_ExpatVersion(void) { /* V1 is used to string-ize the version number. However, it would @@ -1671,7 +1714,7 @@ XML_ExpatVersion(void) { #undef V2 } -XML_Expat_Version +XML_Expat_Version XMLCALL XML_ExpatVersionInfo(void) { XML_Expat_Version version; @@ -1683,29 +1726,29 @@ XML_ExpatVersionInfo(void) return version; } -const XML_Feature * +const XML_Feature * XMLCALL XML_GetFeatureList(void) { static XML_Feature features[] = { - {XML_FEATURE_SIZEOF_XML_CHAR, XML_L("sizeof(XML_Char)")}, - {XML_FEATURE_SIZEOF_XML_LCHAR, XML_L("sizeof(XML_LChar)")}, + {XML_FEATURE_SIZEOF_XML_CHAR, XML_L("sizeof(XML_Char)"), 0}, + {XML_FEATURE_SIZEOF_XML_LCHAR, XML_L("sizeof(XML_LChar)"), 0}, #ifdef XML_UNICODE - {XML_FEATURE_UNICODE, XML_L("XML_UNICODE")}, + {XML_FEATURE_UNICODE, XML_L("XML_UNICODE"), 0}, #endif #ifdef XML_UNICODE_WCHAR_T - {XML_FEATURE_UNICODE_WCHAR_T, XML_L("XML_UNICODE_WCHAR_T")}, + {XML_FEATURE_UNICODE_WCHAR_T, XML_L("XML_UNICODE_WCHAR_T"), 0}, #endif #ifdef XML_DTD - {XML_FEATURE_DTD, XML_L("XML_DTD")}, + {XML_FEATURE_DTD, XML_L("XML_DTD"), 0}, #endif #ifdef XML_CONTEXT_BYTES {XML_FEATURE_CONTEXT_BYTES, XML_L("XML_CONTEXT_BYTES"), XML_CONTEXT_BYTES}, #endif #ifdef XML_MIN_SIZE - {XML_FEATURE_MIN_SIZE, XML_L("XML_MIN_SIZE")}, + {XML_FEATURE_MIN_SIZE, XML_L("XML_MIN_SIZE"), 0}, #endif - {XML_FEATURE_END, NULL} + {XML_FEATURE_END, NULL, 0} }; features[0].value = sizeof(XML_Char); @@ -2344,8 +2387,8 @@ storeAtts(XML_Parser parser, const ENCODING *enc, BINDING **bindingsPtr) { DTD * const dtd = _dtd; /* save one level of indirection */ - ELEMENT_TYPE *elementType = NULL; - int nDefaultAtts = 0; + ELEMENT_TYPE *elementType; + int nDefaultAtts; const XML_Char **appAtts; /* the attribute list for the application */ int attIndex = 0; int prefixLen; @@ -2393,7 +2436,10 @@ storeAtts(XML_Parser parser, const ENCODING *enc, + XmlNameLength(enc, atts[i].name)); if (!attId) return XML_ERROR_NO_MEMORY; - /* detect duplicate attributes */ + /* 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; @@ -2493,58 +2539,126 @@ storeAtts(XML_Parser parser, const ENCODING *enc, } appAtts[attIndex] = 0; + /* expand prefixed attribute names, check for duplicates, + and clear flags that say whether attributes were specified */ i = 0; if (nPrefixes) { - /* expand prefixed attribute names */ + int j; /* hash table index */ + unsigned long version = nsAttsVersion; + int nsAttsSize = (int)1 << nsAttsPower; + /* size of hash table must be at least 2 * (# of prefixed attributes) */ + if ((nPrefixes << 1) >> nsAttsPower) { /* true for 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)); + if (!temp) + return XML_ERROR_NO_MEMORY; + nsAtts = temp; + version = 0; /* force re-initialization of nsAtts hash table */ + } + /* using a version flag saves us from initializing 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; + } + nsAttsVersion = --version; + + /* expand prefixed names and check for duplicates */ for (; i < attIndex; i += 2) { - if (appAtts[i][-1] == 2) { + const XML_Char *s = appAtts[i]; + if (s[-1] == 2) { /* prefixed */ ATTRIBUTE_ID *id; - ((XML_Char *)(appAtts[i]))[-1] = 0; - id = (ATTRIBUTE_ID *)lookup(&dtd->attributeIds, appAtts[i], 0); - if (id->prefix->binding) { - int j; - const BINDING *b = id->prefix->binding; - const XML_Char *s = appAtts[i]; - for (j = 0; j < b->uriLen; j++) { - if (!poolAppendChar(&tempPool, b->uri[j])) - return XML_ERROR_NO_MEMORY; + const BINDING *b; + unsigned long uriHash = 0; + ((XML_Char *)s)[-1] = 0; /* clear flag */ + id = (ATTRIBUTE_ID *)lookup(&dtd->attributeIds, s, 0); + 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++) { + const XML_Char c = b->uri[j]; + if (!poolAppendChar(&tempPool, c)) + return XML_ERROR_NO_MEMORY; + uriHash = CHAR_HASH(uriHash, c); + } + while (*s++ != XML_T(':')) + ; + do { /* copies null terminator */ + const XML_Char c = *s; + if (!poolAppendChar(&tempPool, *s)) + return XML_ERROR_NO_MEMORY; + uriHash = CHAR_HASH(uriHash, c); + } while (*s++); + + { /* Check hash table for duplicate of expanded name (uriName). + Derived from code in lookup(HASH_TABLE *table, ...). + */ + unsigned char step = 0; + unsigned long mask = nsAttsSize - 1; + j = uriHash & mask; /* index into hash table */ + while (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; + /* 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); + j < step ? ( j += nsAttsSize - step) : (j -= step); } - while (*s++ != XML_T(':')) - ; + } + + if (ns_triplets) { /* append namespace separator and prefix */ + tempPool.ptr[-1] = namespaceSeparator; + s = b->prefix->name; do { if (!poolAppendChar(&tempPool, *s)) return XML_ERROR_NO_MEMORY; } while (*s++); - if (ns_triplets) { - tempPool.ptr[-1] = namespaceSeparator; - s = b->prefix->name; - do { - if (!poolAppendChar(&tempPool, *s)) - return XML_ERROR_NO_MEMORY; - } while (*s++); - } - - appAtts[i] = poolStart(&tempPool); - poolFinish(&tempPool); } + + /* store expanded name in attribute list */ + s = poolStart(&tempPool); + poolFinish(&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; + if (!--nPrefixes) break; } - else - ((XML_Char *)(appAtts[i]))[-1] = 0; + else /* not prefixed */ + ((XML_Char *)s)[-1] = 0; /* clear flag */ } } - /* clear the flags that say whether attributes were specified */ + /* clear flags for the remaining attributes */ for (; i < attIndex; i += 2) ((XML_Char *)(appAtts[i]))[-1] = 0; for (binding = *bindingsPtr; binding; binding = binding->nextTagBinding) binding->attId->name[-1] = 0; + if (!ns) + return XML_ERROR_NONE; + /* expand the element type name */ if (elementType->prefix) { binding = elementType->prefix->binding; if (!binding) - return XML_ERROR_NONE; + return XML_ERROR_UNBOUND_PREFIX; localPart = tagNamePtr->str; while (*localPart++ != XML_T(':')) ; @@ -2556,7 +2670,7 @@ storeAtts(XML_Parser parser, const ENCODING *enc, else return XML_ERROR_NONE; prefixLen = 0; - if (ns && ns_triplets && binding->prefix->name) { + if (ns_triplets && binding->prefix->name) { for (; binding->prefix->name[prefixLen++];) ; } @@ -2583,8 +2697,9 @@ storeAtts(XML_Parser parser, const ENCODING *enc, uri = binding->uri + binding->uriLen; memcpy(uri, localPart, i * sizeof(XML_Char)); if (prefixLen) { - uri = uri + (i - 1); - if (namespaceSeparator) { *(uri) = namespaceSeparator; } + uri = uri + (i - 1); + if (namespaceSeparator) + *uri = namespaceSeparator; memcpy(uri + 1, binding->prefix->name, prefixLen * sizeof(XML_Char)); } tagNamePtr->str = binding->uri; @@ -2639,6 +2754,7 @@ addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId, b->prefix = prefix; b->attId = attId; b->prevPrefixBinding = prefix->binding; + /* NULL binding when default namespace undeclared */ if (*uri == XML_T('\0') && prefix == &_dtd->defaultPrefix) prefix->binding = NULL; else @@ -3486,8 +3602,8 @@ doProlog(XML_Parser parser, case XML_ROLE_REQUIRED_ATTRIBUTE_VALUE: if (dtd->keepProcessing) { if (!defineAttribute(declElementType, declAttributeId, - declAttributeIsCdata, declAttributeIsId, 0, - parser)) + declAttributeIsCdata, declAttributeIsId, + 0, parser)) return XML_ERROR_NO_MEMORY; if (attlistDeclHandler && declAttributeType) { if (*declAttributeType == XML_T('(') @@ -3513,11 +3629,11 @@ doProlog(XML_Parser parser, case XML_ROLE_FIXED_ATTRIBUTE_VALUE: if (dtd->keepProcessing) { const XML_Char *attVal; - enum XML_Error result - = storeAttributeValue(parser, enc, declAttributeIsCdata, - s + enc->minBytesPerChar, - next - enc->minBytesPerChar, - &dtd->pool); + enum XML_Error result = + storeAttributeValue(parser, enc, declAttributeIsCdata, + s + enc->minBytesPerChar, + next - enc->minBytesPerChar, + &dtd->pool); if (result) return result; attVal = poolStart(&dtd->pool); @@ -4665,7 +4781,7 @@ 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(type->allocDefaultAtts * sizeof(DEFAULT_ATTRIBUTE)); if (!type->defaultAtts) return 0; @@ -4733,6 +4849,7 @@ getAttributeId(XML_Parser parser, const ENCODING *enc, name = poolStoreString(&dtd->pool, enc, start, end); if (!name) return NULL; + /* skip quotation mark - its storage will be re-used (like in name[-1]) */ ++name; id = (ATTRIBUTE_ID *)lookup(&dtd->attributeIds, name, sizeof(ATTRIBUTE_ID)); if (!id) @@ -4758,6 +4875,7 @@ getAttributeId(XML_Parser parser, const ENCODING *enc, else { int i; for (i = 0; name[i]; i++) { + /* attributes without prefix are *not* in the default namespace */ if (name[i] == XML_T(':')) { int j; for (j = 0; j < i; j++) { @@ -4997,14 +5115,12 @@ dtdReset(DTD *p, const XML_Memory_Handling_Suite *ms) p->defaultPrefix.binding = NULL; p->in_eldecl = XML_FALSE; - if (p->scaffIndex) { - ms->free_fcn(p->scaffIndex); - p->scaffIndex = NULL; - } - if (p->scaffold) { - ms->free_fcn(p->scaffold); - p->scaffold = NULL; - } + + ms->free_fcn(p->scaffIndex); + p->scaffIndex = NULL; + ms->free_fcn(p->scaffold); + p->scaffold = NULL; + p->scaffLevel = 0; p->scaffSize = 0; p->scaffCount = 0; @@ -5039,10 +5155,8 @@ dtdDestroy(DTD *p, XML_Bool isDocEntity, const XML_Memory_Handling_Suite *ms) poolDestroy(&(p->entityValuePool)); #endif /* XML_DTD */ if (isDocEntity) { - if (p->scaffIndex) - ms->free_fcn(p->scaffIndex); - if (p->scaffold) - ms->free_fcn(p->scaffold); + ms->free_fcn(p->scaffIndex); + ms->free_fcn(p->scaffold); } ms->free_fcn(p); } @@ -5246,15 +5360,15 @@ copyEntityTable(HASH_TABLE *newTable, return 1; } -#define INIT_SIZE 64 +#define INIT_POWER 6 -static int FASTCALL +static XML_Bool FASTCALL keyeq(KEY s1, KEY s2) { for (; *s1 == *s2; s1++, s2++) if (*s1 == 0) - return 1; - return 0; + return XML_TRUE; + return XML_FALSE; } static unsigned long FASTCALL @@ -5262,7 +5376,7 @@ hash(KEY s) { unsigned long h = 0; while (*s) - h = (h << 5) + h + (unsigned char)*s++; + h = CHAR_HASH(h, *s++); return h; } @@ -5272,31 +5386,38 @@ lookup(HASH_TABLE *table, KEY name, size_t createSize) size_t i; if (table->size == 0) { size_t tsize; - if (!createSize) return NULL; - tsize = INIT_SIZE * sizeof(NAMED *); + table->power = INIT_POWER; + /* table->size is a power of 2 */ + table->size = (size_t)1 << INIT_POWER; + tsize = table->size * sizeof(NAMED *); table->v = (NAMED **)table->mem->malloc_fcn(tsize); if (!table->v) return NULL; memset(table->v, 0, tsize); - table->size = INIT_SIZE; - table->usedLim = INIT_SIZE / 2; - i = hash(name) & (table->size - 1); + i = hash(name) & ((unsigned long)table->size - 1); } else { unsigned long h = hash(name); - for (i = h & (table->size - 1); - table->v[i]; - i == 0 ? i = table->size - 1 : --i) { + unsigned long mask = (unsigned long)table->size - 1; + unsigned char step = 0; + i = h & mask; + while (table->v[i]) { if (keyeq(name, table->v[i]->name)) return table->v[i]; + if (!step) + step = PROBE_STEP(h, mask, table->power); + i < step ? (i += table->size - step) : (i -= step); } if (!createSize) return NULL; - if (table->used == table->usedLim) { - /* check for overflow */ - size_t newSize = table->size * 2; + + /* check for overflow (table is half full) */ + if (table->used >> (table->power - 1)) { + unsigned char newPower = table->power + 1; + size_t newSize = (size_t)1 << newPower; + unsigned long newMask = (unsigned long)newSize - 1; size_t tsize = newSize * sizeof(NAMED *); NAMED **newV = (NAMED **)table->mem->malloc_fcn(tsize); if (!newV) @@ -5304,21 +5425,27 @@ lookup(HASH_TABLE *table, KEY name, size_t createSize) memset(newV, 0, tsize); for (i = 0; i < table->size; i++) if (table->v[i]) { - size_t j; - for (j = hash(table->v[i]->name) & (newSize - 1); - newV[j]; - j == 0 ? j = newSize - 1 : --j) - ; + unsigned long newHash = hash(table->v[i]->name); + size_t j = newHash & newMask; + step = 0; + while (newV[j]) { + if (!step) + step = PROBE_STEP(newHash, newMask, newPower); + j < step ? (j += newSize - step) : (j -= step); + } newV[j] = table->v[i]; } table->mem->free_fcn(table->v); table->v = newV; + table->power = newPower; table->size = newSize; - table->usedLim = newSize/2; - for (i = h & (table->size - 1); - table->v[i]; - i == 0 ? i = table->size - 1 : --i) - ; + i = h & newMask; + step = 0; + while (table->v[i]) { + if (!step) + step = PROBE_STEP(h, newMask, newPower); + i < step ? (i += newSize - step) : (i -= step); + } } } table->v[i] = (NAMED *)table->mem->malloc_fcn(createSize); @@ -5335,13 +5462,9 @@ hashTableClear(HASH_TABLE *table) { size_t i; for (i = 0; i < table->size; i++) { - NAMED *p = table->v[i]; - if (p) { - table->mem->free_fcn(p); - table->v[i] = NULL; - } + table->mem->free_fcn(table->v[i]); + table->v[i] = NULL; } - table->usedLim = table->size / 2; table->used = 0; } @@ -5349,20 +5472,16 @@ static void FASTCALL hashTableDestroy(HASH_TABLE *table) { size_t i; - for (i = 0; i < table->size; i++) { - NAMED *p = table->v[i]; - if (p) - table->mem->free_fcn(p); - } - if (table->v) - table->mem->free_fcn(table->v); + for (i = 0; i < table->size; i++) + table->mem->free_fcn(table->v[i]); + table->mem->free_fcn(table->v); } static void FASTCALL hashTableInit(HASH_TABLE *p, const XML_Memory_Handling_Suite *ms) { + p->power = 0; p->size = 0; - p->usedLim = 0; p->used = 0; p->v = NULL; p->mem = ms; @@ -5529,8 +5648,8 @@ poolGrow(STRING_POOL *pool) int blockSize = (pool->end - pool->start)*2; pool->blocks = (BLOCK *) pool->mem->realloc_fcn(pool->blocks, - (offsetof(BLOCK, s) - + blockSize * sizeof(XML_Char))); + (offsetof(BLOCK, s) + + blockSize * sizeof(XML_Char))); if (pool->blocks == NULL) return XML_FALSE; pool->blocks->size = blockSize; @@ -5546,7 +5665,7 @@ poolGrow(STRING_POOL *pool) else blockSize *= 2; tem = (BLOCK *)pool->mem->malloc_fcn(offsetof(BLOCK, s) - + blockSize * sizeof(XML_Char)); + + blockSize * sizeof(XML_Char)); if (!tem) return XML_FALSE; tem->size = blockSize; diff --git a/Modules/expat/xmlrole.c b/Modules/expat/xmlrole.c index ea14a19..83c0d71 100644 --- a/Modules/expat/xmlrole.c +++ b/Modules/expat/xmlrole.c @@ -7,9 +7,9 @@ #elif defined(MACOS_CLASSIC) #include "macconfig.h" #else -/* Unused - MvL +#ifdef HAVE_EXPAT_CONFIG_H #include -*/ +#endif #endif /* ndef COMPILED_FROM_DSP */ #include "internal.h" diff --git a/Modules/expat/xmltok.c b/Modules/expat/xmltok.c index 1248583..962df0e 100644 --- a/Modules/expat/xmltok.c +++ b/Modules/expat/xmltok.c @@ -7,9 +7,9 @@ #elif defined(MACOS_CLASSIC) #include "macconfig.h" #else -/* Unused - MvL +#ifdef HAVE_EXPAT_CONFIG_H #include -*/ +#endif #endif /* ndef COMPILED_FROM_DSP */ #include "internal.h" diff --git a/Modules/expat/xmltok_impl.c b/Modules/expat/xmltok_impl.c index 84a3267..46569fe 100644 --- a/Modules/expat/xmltok_impl.c +++ b/Modules/expat/xmltok_impl.c @@ -882,7 +882,7 @@ PREFIX(scanPercent)(const ENCODING *enc, const char *ptr, const char *end, const char **nextTokPtr) { if (ptr == end) - return XML_TOK_PARTIAL; + return -XML_TOK_PERCENT; switch (BYTE_TYPE(enc, ptr)) { CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) case BT_S: case BT_LF: case BT_CR: case BT_PERCNT: -- cgit v0.12