mirror of
https://github.com/python/cpython.git
synced 2025-07-24 11:44:31 +00:00
Incorporate Expat 1.95.6.
This commit is contained in:
parent
5a772d32f4
commit
fc03a94aac
11 changed files with 5443 additions and 3941 deletions
|
@ -1,5 +1,4 @@
|
|||
/*
|
||||
Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
|
||||
/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
|
||||
See the file COPYING for copying permission.
|
||||
*/
|
||||
|
||||
|
|
|
@ -1,16 +1,28 @@
|
|||
/*
|
||||
Copyright (c) 1998, 1999, 2000 Thai Open Source Software Center Ltd
|
||||
/* 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
|
||||
|
||||
#ifdef __VMS
|
||||
/* 0 1 2 3 0 1 2 3
|
||||
1234567890123456789012345678901 1234567890123456789012345678901 */
|
||||
#define XML_SetProcessingInstructionHandler XML_SetProcessingInstrHandler
|
||||
#define XML_SetUnparsedEntityDeclHandler XML_SetUnparsedEntDeclHandler
|
||||
#define XML_SetStartNamespaceDeclHandler XML_SetStartNamespcDeclHandler
|
||||
#define XML_SetExternalEntityRefHandlerArg XML_SetExternalEntRefHandlerArg
|
||||
#endif
|
||||
|
||||
#include <stdlib.h>
|
||||
|
||||
#ifndef XMLPARSEAPI
|
||||
# if defined(__declspec) && !defined(__BEOS__) && !defined(__CYGWIN__)
|
||||
#if defined(_MSC_EXTENSIONS) && !defined(__BEOS__) && !defined(__CYGWIN__)
|
||||
#ifdef XML_STATIC
|
||||
#define XMLPARSEAPI(type) type __cdecl
|
||||
#else
|
||||
#define XMLPARSEAPI(type) __declspec(dllimport) type __cdecl
|
||||
#endif
|
||||
#else
|
||||
#define XMLPARSEAPI(type) type
|
||||
#endif
|
||||
|
@ -20,11 +32,60 @@ See the file COPYING for copying permission.
|
|||
extern "C" {
|
||||
#endif
|
||||
|
||||
typedef void *XML_Parser;
|
||||
#ifdef XML_UNICODE_WCHAR_T
|
||||
#define XML_UNICODE
|
||||
#endif
|
||||
|
||||
/* Information is UTF-8 encoded. */
|
||||
struct XML_ParserStruct;
|
||||
typedef struct XML_ParserStruct *XML_Parser;
|
||||
|
||||
#ifdef XML_UNICODE /* Information is UTF-16 encoded. */
|
||||
#ifdef XML_UNICODE_WCHAR_T
|
||||
typedef wchar_t XML_Char;
|
||||
typedef wchar_t XML_LChar;
|
||||
#else
|
||||
typedef unsigned short XML_Char;
|
||||
typedef char XML_LChar;
|
||||
#endif /* XML_UNICODE_WCHAR_T */
|
||||
#else /* Information is UTF-8 encoded. */
|
||||
typedef char XML_Char;
|
||||
typedef char XML_LChar;
|
||||
#endif /* XML_UNICODE */
|
||||
|
||||
/* Should this be defined using stdbool.h when C99 is available? */
|
||||
typedef unsigned char XML_Bool;
|
||||
#define XML_TRUE ((XML_Bool) 1)
|
||||
#define XML_FALSE ((XML_Bool) 0)
|
||||
|
||||
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,
|
||||
XML_ERROR_ENTITY_DECLARED_IN_PE,
|
||||
XML_ERROR_FEATURE_REQUIRES_XML_DTD,
|
||||
XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING
|
||||
};
|
||||
|
||||
enum XML_Content_Type {
|
||||
XML_CTYPE_EMPTY = 1,
|
||||
|
@ -75,7 +136,6 @@ 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);
|
||||
|
@ -84,16 +144,14 @@ XMLPARSEAPI(void)
|
|||
XML_SetElementDeclHandler(XML_Parser parser,
|
||||
XML_ElementDeclHandler eldecl);
|
||||
|
||||
/*
|
||||
The Attlist declaration handler is called for *each* attribute. So
|
||||
/* 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.
|
||||
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,
|
||||
|
@ -105,15 +163,14 @@ 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.
|
||||
/* 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,
|
||||
|
@ -131,26 +188,27 @@ typedef struct {
|
|||
} XML_Memory_Handling_Suite;
|
||||
|
||||
/* Constructs a new parser; encoding is the encoding specified by the
|
||||
external protocol or null if there is none specified. */
|
||||
|
||||
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. */
|
||||
|
||||
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
|
||||
/* Constructs a new parser using the memory management suite 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
|
||||
|
@ -159,15 +217,26 @@ XML_ParserCreateNS(const XML_Char *encoding, XML_Char namespaceSeparator);
|
|||
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. */
|
||||
/* Prepare a parser object to be re-used. This is particularly
|
||||
valuable when memory allocation overhead is disproportionatly high,
|
||||
such as when a large number of small documnents need to be parsed.
|
||||
All handlers are cleared from the parser, except for the
|
||||
unknownEncodingHandler. The parser's external state is re-initialized
|
||||
except for the values of ns and ns_triplets.
|
||||
|
||||
Added in Expat 1.95.3.
|
||||
*/
|
||||
XMLPARSEAPI(XML_Bool)
|
||||
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);
|
||||
|
@ -192,26 +261,26 @@ 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. */
|
||||
|
||||
/* 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 or UTF-16.
|
||||
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. */
|
||||
|
||||
any DTD or internal subset is parsed.
|
||||
*/
|
||||
typedef void (*XML_StartDoctypeDeclHandler)(void *userData,
|
||||
const XML_Char *doctypeName,
|
||||
const XML_Char *sysid,
|
||||
|
@ -219,7 +288,9 @@ typedef void (*XML_StartDoctypeDeclHandler)(void *userData,
|
|||
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. */
|
||||
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
|
||||
|
@ -227,17 +298,19 @@ typedef void (*XML_EndDoctypeDeclHandler)(void *userData);
|
|||
otherwise.
|
||||
|
||||
For internal entities (<!ENTITY foo "bar">), 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
|
||||
be non-NULL and systemId, publicID, and notationName will be NULL.
|
||||
The value string is NOT nul-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.
|
||||
*/
|
||||
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.
|
||||
|
||||
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,
|
||||
|
@ -255,11 +328,12 @@ XML_SetEntityDeclHandler(XML_Parser parser,
|
|||
/* 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. */
|
||||
|
||||
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,
|
||||
|
@ -267,10 +341,10 @@ typedef void (*XML_UnparsedEntityDeclHandler)(void *userData,
|
|||
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. */
|
||||
|
||||
/* 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,
|
||||
|
@ -280,9 +354,9 @@ typedef void (*XML_NotationDeclHandler)(void *userData,
|
|||
/* 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. */
|
||||
|
||||
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);
|
||||
|
@ -290,65 +364,101 @@ typedef void (*XML_StartNamespaceDeclHandler)(void *userData,
|
|||
typedef void (*XML_EndNamespaceDeclHandler)(void *userData,
|
||||
const XML_Char *prefix);
|
||||
|
||||
/* This is called if the document is not standalone (it has an
|
||||
/* 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
|
||||
have standalone="yes"). If this handler returns 0, then processing
|
||||
will not continue, and the parser will return a
|
||||
XML_ERROR_NOT_STANDALONE error. */
|
||||
|
||||
have standalone="yes". If this handler returns XML_STATUS_ERROR,
|
||||
then processing will not continue, and the parser will return a
|
||||
XML_ERROR_NOT_STANDALONE error.
|
||||
If parameter entity parsing is enabled, then in addition to the
|
||||
conditions above this handler will only be called if the referenced
|
||||
entity was actually read.
|
||||
*/
|
||||
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
|
||||
/* 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. */
|
||||
|
||||
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.
|
||||
context is NULL only when the entity is a parameter entity.
|
||||
|
||||
The handler should return XML_STATUS_ERROR 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
|
||||
/* This is called in two situations:
|
||||
1) An entity reference is encountered for which no declaration
|
||||
has been read *and* this is not an error.
|
||||
2) An internal entity reference is read, but not expanded, because
|
||||
XML_SetDefaultHandler has been called.
|
||||
Note: skipped parameter entities in declarations and skipped general
|
||||
entities in attribute values cannot be reported, because
|
||||
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);
|
||||
|
||||
/* 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.
|
||||
|
||||
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.
|
||||
|
||||
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.
|
||||
|
@ -363,14 +473,14 @@ 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. */
|
||||
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;
|
||||
|
@ -379,16 +489,20 @@ typedef struct {
|
|||
} 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. */
|
||||
|
||||
If the callback can provide information about the encoding, it must
|
||||
fill in the XML_Encoding structure, and return XML_STATUS_OK.
|
||||
Otherwise it must return XML_STATUS_ERROR.
|
||||
|
||||
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);
|
||||
|
@ -429,17 +543,17 @@ 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. */
|
||||
|
||||
internal entities. These entity references will be passed to the
|
||||
default handler, or to the skipped entity handler, if one is set.
|
||||
*/
|
||||
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. */
|
||||
|
||||
default handler.
|
||||
*/
|
||||
XMLPARSEAPI(void)
|
||||
XML_SetDefaultHandlerExpand(XML_Parser parser,
|
||||
XML_DefaultHandler handler);
|
||||
|
@ -486,32 +600,41 @@ 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. */
|
||||
/* 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_SetSkippedEntityHandler(XML_Parser parser,
|
||||
XML_SkippedEntityHandler handler);
|
||||
|
||||
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. */
|
||||
/* 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.
|
||||
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
|
||||
default manner (URI + sep + local_name) whether or not the name
|
||||
has a prefix.
|
||||
|
||||
Note: Calling XML_SetReturnNSTriplet after XML_Parse or
|
||||
XML_ParseBuffer has no effect.
|
||||
*/
|
||||
|
||||
XMLPARSEAPI(void)
|
||||
|
@ -521,31 +644,53 @@ XML_SetReturnNSTriplet(XML_Parser parser, int do_nst);
|
|||
XMLPARSEAPI(void)
|
||||
XML_SetUserData(XML_Parser parser, void *userData);
|
||||
|
||||
/* Returns the last value set by XML_SetUserData or null. */
|
||||
/* 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)
|
||||
/* This is equivalent to supplying an encoding argument to
|
||||
XML_ParserCreate. On success XML_SetEncoding returns non-zero,
|
||||
zero otherwise.
|
||||
Note: Calling XML_SetEncoding after XML_Parse or XML_ParseBuffer
|
||||
has no effect and returns XML_STATUS_ERROR.
|
||||
*/
|
||||
XMLPARSEAPI(enum XML_Status)
|
||||
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. */
|
||||
|
||||
/* 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. */
|
||||
/* If useDTD == XML_TRUE is passed to this function, then the parser
|
||||
will assume that there is an external subset, even if none is
|
||||
specified in the document. In such a case the parser will call the
|
||||
externalEntityRefHandler with a value of NULL for the systemId
|
||||
argument (the publicId and context arguments will be NULL as well).
|
||||
Note: If this function is called, then this must be done before
|
||||
the first call to XML_Parse or XML_ParseBuffer, since it will
|
||||
have no effect after that. Returns
|
||||
XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING.
|
||||
Note: If the document does not have a DOCTYPE declaration at all,
|
||||
then startDoctypeDeclHandler and endDoctypeDeclHandler will not
|
||||
be called, despite an external subset being parsed.
|
||||
Note: If XML_DTD is not defined when Expat is compiled, returns
|
||||
XML_ERROR_FEATURE_REQUIRES_XML_DTD.
|
||||
*/
|
||||
XMLPARSEAPI(enum XML_Error)
|
||||
XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD);
|
||||
|
||||
XMLPARSEAPI(int)
|
||||
|
||||
/* 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 XML_STATUS_ERROR if out of memory,
|
||||
XML_STATUS_OK otherwise.
|
||||
*/
|
||||
XMLPARSEAPI(enum XML_Status)
|
||||
XML_SetBase(XML_Parser parser, const XML_Char *base);
|
||||
|
||||
XMLPARSEAPI(const XML_Char *)
|
||||
|
@ -555,46 +700,70 @@ XML_GetBase(XML_Parser parser);
|
|||
to the XML_StartElementHandler that were specified in the start-tag
|
||||
rather than defaulted. Each attribute/value pair counts as 2; thus
|
||||
this correspondds to an index into the atts array passed to the
|
||||
XML_StartElementHandler. */
|
||||
|
||||
XML_StartElementHandler.
|
||||
*/
|
||||
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. */
|
||||
|
||||
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)
|
||||
/* Parses some input. Returns XML_STATUS_ERROR 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).
|
||||
|
||||
The XML_Status enum gives the possible return values for the
|
||||
XML_Parse and XML_ParseBuffer functions. Though the return values
|
||||
for these functions has always been described as a Boolean value,
|
||||
the implementation, at least for the 1.95.x series, has always
|
||||
returned exactly one of these values. The preprocessor #defines
|
||||
are included so this stanza can be added to code that still needs
|
||||
to support older versions of Expat 1.95.x:
|
||||
|
||||
#ifndef XML_STATUS_OK
|
||||
#define XML_STATUS_OK 1
|
||||
#define XML_STATUS_ERROR 0
|
||||
#endif
|
||||
|
||||
Otherwise, the #define hackery is quite ugly and would have been dropped.
|
||||
*/
|
||||
enum XML_Status {
|
||||
XML_STATUS_ERROR = 0,
|
||||
#define XML_STATUS_ERROR XML_STATUS_ERROR
|
||||
XML_STATUS_OK = 1
|
||||
#define XML_STATUS_OK XML_STATUS_OK
|
||||
};
|
||||
|
||||
XMLPARSEAPI(enum XML_Status)
|
||||
XML_Parse(XML_Parser parser, const char *s, int len, int isFinal);
|
||||
|
||||
XMLPARSEAPI(void *)
|
||||
XML_GetBuffer(XML_Parser parser, int len);
|
||||
|
||||
XMLPARSEAPI(int)
|
||||
XMLPARSEAPI(enum XML_Status)
|
||||
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. */
|
||||
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 NULL if out of memory.
|
||||
Otherwise returns a new XML_Parser object.
|
||||
*/
|
||||
XMLPARSEAPI(XML_Parser)
|
||||
XML_ExternalEntityParserCreate(XML_Parser parser,
|
||||
const XML_Char *context,
|
||||
|
@ -607,76 +776,56 @@ enum XML_ParamEntityParsing {
|
|||
};
|
||||
|
||||
/* 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
|
||||
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. */
|
||||
|
||||
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.
|
||||
Note: If XML_SetParamEntityParsing is called after XML_Parse or
|
||||
XML_ParseBuffer, then it has no effect and will always return 0.
|
||||
*/
|
||||
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. */
|
||||
|
||||
/* If XML_Parse or XML_ParseBuffer have returned XML_STATUS_ERROR, 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. */
|
||||
/* 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.
|
||||
|
||||
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
|
||||
was detected; otherwise the location is the location of the last
|
||||
parse event, as described above.
|
||||
*/
|
||||
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. */
|
||||
|
||||
Returns 0 if the event is in an internal entity.
|
||||
*/
|
||||
XMLPARSEAPI(int)
|
||||
XML_GetCurrentByteCount(XML_Parser parser);
|
||||
|
||||
|
@ -684,12 +833,12 @@ XML_GetCurrentByteCount(XML_Parser parser);
|
|||
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
|
||||
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. */
|
||||
|
||||
the handler that makes the call.
|
||||
*/
|
||||
XMLPARSEAPI(const char *)
|
||||
XML_GetInputContext(XML_Parser parser,
|
||||
int *offset,
|
||||
|
@ -700,13 +849,27 @@ XML_GetInputContext(XML_Parser parser,
|
|||
#define XML_GetErrorColumnNumber XML_GetCurrentColumnNumber
|
||||
#define XML_GetErrorByteIndex XML_GetCurrentByteIndex
|
||||
|
||||
/* Frees the content model passed to the element declaration handler */
|
||||
XMLPARSEAPI(void)
|
||||
XML_FreeContentModel(XML_Parser parser, XML_Content *model);
|
||||
|
||||
/* Exposing the memory handling functions used in Expat */
|
||||
XMLPARSEAPI(void *)
|
||||
XML_MemMalloc(XML_Parser parser, size_t size);
|
||||
|
||||
XMLPARSEAPI(void *)
|
||||
XML_MemRealloc(XML_Parser parser, void *ptr, size_t size);
|
||||
|
||||
XMLPARSEAPI(void)
|
||||
XML_MemFree(XML_Parser parser, void *ptr);
|
||||
|
||||
/* 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);
|
||||
XML_ErrorString(enum XML_Error code);
|
||||
|
||||
/* Return a string containing the version number of this expat */
|
||||
XMLPARSEAPI(const XML_LChar *)
|
||||
|
@ -719,18 +882,42 @@ typedef struct {
|
|||
} XML_Expat_Version;
|
||||
|
||||
/* Return an XML_Expat_Version structure containing numeric version
|
||||
number information for this version of expat */
|
||||
|
||||
number information for this version of expat.
|
||||
*/
|
||||
XMLPARSEAPI(XML_Expat_Version)
|
||||
XML_ExpatVersionInfo(void);
|
||||
|
||||
/* VERSION is not defined in expat.h.in, but it really belongs here,
|
||||
and defining it on the command line gives difficulties with MSVC. */
|
||||
#define VERSION "1.95.2"
|
||||
/* Added in Expat 1.95.5. */
|
||||
enum XML_FeatureEnum {
|
||||
XML_FEATURE_END = 0,
|
||||
XML_FEATURE_UNICODE,
|
||||
XML_FEATURE_UNICODE_WCHAR_T,
|
||||
XML_FEATURE_DTD,
|
||||
XML_FEATURE_CONTEXT_BYTES,
|
||||
XML_FEATURE_MIN_SIZE,
|
||||
XML_FEATURE_SIZEOF_XML_CHAR,
|
||||
XML_FEATURE_SIZEOF_XML_LCHAR
|
||||
/* Additional features must be added to the end of this enum. */
|
||||
};
|
||||
|
||||
typedef struct {
|
||||
enum XML_FeatureEnum feature;
|
||||
const XML_LChar *name;
|
||||
long int value;
|
||||
} XML_Feature;
|
||||
|
||||
XMLPARSEAPI(const XML_Feature *)
|
||||
XML_GetFeatureList(void);
|
||||
|
||||
|
||||
/* Expat follows the GNU/Linux convention of odd number minor version for
|
||||
beta/development releases and even number minor version for stable
|
||||
releases. Micro is bumped with each release, and set to 0 with each
|
||||
change to major or minor version.
|
||||
*/
|
||||
#define XML_MAJOR_VERSION 1
|
||||
#define XML_MINOR_VERSION 95
|
||||
#define XML_MICRO_VERSION 2
|
||||
#define XML_MICRO_VERSION 6
|
||||
|
||||
#ifdef __cplusplus
|
||||
}
|
||||
|
|
73
Modules/expat/internal.h
Normal file
73
Modules/expat/internal.h
Normal file
|
@ -0,0 +1,73 @@
|
|||
/* internal.h
|
||||
|
||||
Internal definitions used by Expat. This is not needed to compile
|
||||
client code.
|
||||
|
||||
The following calling convention macros are defined for frequently
|
||||
called functions:
|
||||
|
||||
FASTCALL - Used for those internal functions that have a simple
|
||||
body and a low number of arguments and local variables.
|
||||
|
||||
PTRCALL - Used for functions called though function pointers.
|
||||
|
||||
PTRFASTCALL - Like PTRCALL, but for low number of arguments.
|
||||
|
||||
inline - Used for selected internal functions for which inlining
|
||||
may improve performance on some platforms.
|
||||
|
||||
Note: Use of these macros is based on judgement, not hard rules,
|
||||
and therefore subject to change.
|
||||
*/
|
||||
|
||||
#if defined(__GNUC__)
|
||||
/* Instability reported with egcs on a RedHat Linux 7.3.
|
||||
Let's comment it out:
|
||||
#define FASTCALL __attribute__((stdcall, regparm(3)))
|
||||
and let's try this:
|
||||
*/
|
||||
#define FASTCALL __attribute__((regparm(3)))
|
||||
#define PTRCALL
|
||||
#define PTRFASTCALL __attribute__((regparm(3)))
|
||||
|
||||
#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
|
||||
if it can be made more effective.
|
||||
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
|
||||
|
||||
#ifndef FASTCALL
|
||||
#define FASTCALL
|
||||
#endif
|
||||
|
||||
#ifndef PTRCALL
|
||||
#define PTRCALL
|
||||
#endif
|
||||
|
||||
#ifndef PTRFASTCALL
|
||||
#define PTRFASTCALL
|
||||
#endif
|
||||
|
||||
#ifndef XML_MIN_SIZE
|
||||
#if !defined(__cplusplus) && !defined(inline)
|
||||
#ifdef __GNUC__
|
||||
#define inline __inline
|
||||
#endif /* __GNUC__ */
|
||||
#endif
|
||||
#endif /* XML_MIN_SIZE */
|
||||
|
||||
#ifdef __cplusplus
|
||||
#define inline inline
|
||||
#else
|
||||
#ifndef inline
|
||||
#define inline
|
||||
#endif
|
||||
#endif
|
File diff suppressed because it is too large
Load diff
File diff suppressed because it is too large
Load diff
|
@ -1,11 +1,16 @@
|
|||
/*
|
||||
Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
|
||||
/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
|
||||
See the file COPYING for copying permission.
|
||||
*/
|
||||
|
||||
#ifndef XmlRole_INCLUDED
|
||||
#define XmlRole_INCLUDED 1
|
||||
|
||||
#ifdef __VMS
|
||||
/* 0 1 2 3 0 1 2 3
|
||||
1234567890123456789012345678901 1234567890123456789012345678901 */
|
||||
#define XmlPrologStateInitExternalEntity XmlPrologStateInitExternalEnt
|
||||
#endif
|
||||
|
||||
#include "xmltok.h"
|
||||
|
||||
#ifdef __cplusplus
|
||||
|
@ -17,6 +22,7 @@ enum {
|
|||
XML_ROLE_NONE = 0,
|
||||
XML_ROLE_XML_DECL,
|
||||
XML_ROLE_INSTANCE_START,
|
||||
XML_ROLE_DOCTYPE_NONE,
|
||||
XML_ROLE_DOCTYPE_NAME,
|
||||
XML_ROLE_DOCTYPE_SYSTEM_ID,
|
||||
XML_ROLE_DOCTYPE_PUBLIC_ID,
|
||||
|
@ -24,11 +30,13 @@ enum {
|
|||
XML_ROLE_DOCTYPE_CLOSE,
|
||||
XML_ROLE_GENERAL_ENTITY_NAME,
|
||||
XML_ROLE_PARAM_ENTITY_NAME,
|
||||
XML_ROLE_ENTITY_NONE,
|
||||
XML_ROLE_ENTITY_VALUE,
|
||||
XML_ROLE_ENTITY_SYSTEM_ID,
|
||||
XML_ROLE_ENTITY_PUBLIC_ID,
|
||||
XML_ROLE_ENTITY_COMPLETE,
|
||||
XML_ROLE_ENTITY_NOTATION_NAME,
|
||||
XML_ROLE_NOTATION_NONE,
|
||||
XML_ROLE_NOTATION_NAME,
|
||||
XML_ROLE_NOTATION_SYSTEM_ID,
|
||||
XML_ROLE_NOTATION_NO_SYSTEM_ID,
|
||||
|
@ -44,11 +52,13 @@ enum {
|
|||
XML_ROLE_ATTRIBUTE_TYPE_NMTOKENS,
|
||||
XML_ROLE_ATTRIBUTE_ENUM_VALUE,
|
||||
XML_ROLE_ATTRIBUTE_NOTATION_VALUE,
|
||||
XML_ROLE_ATTLIST_NONE,
|
||||
XML_ROLE_ATTLIST_ELEMENT_NAME,
|
||||
XML_ROLE_IMPLIED_ATTRIBUTE_VALUE,
|
||||
XML_ROLE_REQUIRED_ATTRIBUTE_VALUE,
|
||||
XML_ROLE_DEFAULT_ATTRIBUTE_VALUE,
|
||||
XML_ROLE_FIXED_ATTRIBUTE_VALUE,
|
||||
XML_ROLE_ELEMENT_NONE,
|
||||
XML_ROLE_ELEMENT_NAME,
|
||||
XML_ROLE_CONTENT_ANY,
|
||||
XML_ROLE_CONTENT_EMPTY,
|
||||
|
@ -64,6 +74,8 @@ enum {
|
|||
XML_ROLE_CONTENT_ELEMENT_REP,
|
||||
XML_ROLE_CONTENT_ELEMENT_OPT,
|
||||
XML_ROLE_CONTENT_ELEMENT_PLUS,
|
||||
XML_ROLE_PI,
|
||||
XML_ROLE_COMMENT,
|
||||
#ifdef XML_DTD
|
||||
XML_ROLE_TEXT_DECL,
|
||||
XML_ROLE_IGNORE_SECT,
|
||||
|
@ -73,15 +85,17 @@ enum {
|
|||
};
|
||||
|
||||
typedef struct prolog_state {
|
||||
int (*handler)(struct prolog_state *state,
|
||||
int (PTRCALL *handler) (struct prolog_state *state,
|
||||
int tok,
|
||||
const char *ptr,
|
||||
const char *end,
|
||||
const ENCODING *enc);
|
||||
unsigned level;
|
||||
int role_none;
|
||||
#ifdef XML_DTD
|
||||
unsigned includeLevel;
|
||||
int documentEntity;
|
||||
int inEntityValue;
|
||||
#endif /* XML_DTD */
|
||||
} PROLOG_STATE;
|
||||
|
||||
|
|
File diff suppressed because it is too large
Load diff
|
@ -1,5 +1,4 @@
|
|||
/*
|
||||
Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
|
||||
/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
|
||||
See the file COPYING for copying permission.
|
||||
*/
|
||||
|
||||
|
@ -11,9 +10,11 @@ extern "C" {
|
|||
#endif
|
||||
|
||||
/* The following token may be returned by XmlContentTok */
|
||||
#define XML_TOK_TRAILING_RSQB -5 /* ] or ]] at the end of the scan; might be start of
|
||||
illegal ]]> sequence */
|
||||
/* The following tokens may be returned by both XmlPrologTok and XmlContentTok */
|
||||
#define XML_TOK_TRAILING_RSQB -5 /* ] or ]] at the end of the scan; might be
|
||||
start of illegal ]]> sequence */
|
||||
/* The following tokens may be returned by both XmlPrologTok and
|
||||
XmlContentTok.
|
||||
*/
|
||||
#define XML_TOK_NONE -4 /* The string to be scanned is empty */
|
||||
#define XML_TOK_TRAILING_CR -3 /* A CR at the end of the scan;
|
||||
might be part of CRLF sequence */
|
||||
|
@ -22,8 +23,8 @@ extern "C" {
|
|||
#define XML_TOK_INVALID 0
|
||||
|
||||
/* The following tokens are returned by XmlContentTok; some are also
|
||||
returned by XmlAttributeValueTok, XmlEntityTok, XmlCdataSectionTok */
|
||||
|
||||
returned by XmlAttributeValueTok, XmlEntityTok, XmlCdataSectionTok.
|
||||
*/
|
||||
#define XML_TOK_START_TAG_WITH_ATTS 1
|
||||
#define XML_TOK_START_TAG_NO_ATTS 2
|
||||
#define XML_TOK_EMPTY_ELEMENT_WITH_ATTS 3 /* empty element tag <e/> */
|
||||
|
@ -35,7 +36,9 @@ extern "C" {
|
|||
#define XML_TOK_ENTITY_REF 9
|
||||
#define XML_TOK_CHAR_REF 10 /* numeric character reference */
|
||||
|
||||
/* The following tokens may be returned by both XmlPrologTok and XmlContentTok */
|
||||
/* The following tokens may be returned by both XmlPrologTok and
|
||||
XmlContentTok.
|
||||
*/
|
||||
#define XML_TOK_PI 11 /* processing instruction */
|
||||
#define XML_TOK_XML_DECL 12 /* XML decl or text decl */
|
||||
#define XML_TOK_COMMENT 13
|
||||
|
@ -75,8 +78,9 @@ extern "C" {
|
|||
/* The following token is returned only by XmlCdataSectionTok */
|
||||
#define XML_TOK_CDATA_SECT_CLOSE 40
|
||||
|
||||
/* With namespace processing this is returned by XmlPrologTok
|
||||
for a name with a colon. */
|
||||
/* With namespace processing this is returned by XmlPrologTok for a
|
||||
name with a colon.
|
||||
*/
|
||||
#define XML_TOK_PREFIXED_NAME 41
|
||||
|
||||
#ifdef XML_DTD
|
||||
|
@ -121,37 +125,45 @@ typedef struct {
|
|||
struct encoding;
|
||||
typedef struct encoding ENCODING;
|
||||
|
||||
typedef int (PTRCALL *SCANNER)(const ENCODING *,
|
||||
const char *,
|
||||
const char *,
|
||||
const char **);
|
||||
|
||||
struct encoding {
|
||||
int (*scanners[XML_N_STATES])(const ENCODING *,
|
||||
SCANNER scanners[XML_N_STATES];
|
||||
SCANNER literalScanners[XML_N_LITERAL_TYPES];
|
||||
int (PTRCALL *sameName)(const ENCODING *,
|
||||
const char *,
|
||||
const char *);
|
||||
int (PTRCALL *nameMatchesAscii)(const ENCODING *,
|
||||
const char *,
|
||||
const char *,
|
||||
const char **);
|
||||
int (*literalScanners[XML_N_LITERAL_TYPES])(const ENCODING *,
|
||||
const char *);
|
||||
int (PTRFASTCALL *nameLength)(const ENCODING *, const char *);
|
||||
const char *(PTRFASTCALL *skipS)(const ENCODING *, const char *);
|
||||
int (PTRCALL *getAtts)(const ENCODING *enc,
|
||||
const char *ptr,
|
||||
int attsMax,
|
||||
ATTRIBUTE *atts);
|
||||
int (PTRFASTCALL *charRefNumber)(const ENCODING *enc, const char *ptr);
|
||||
int (PTRCALL *predefinedEntityName)(const ENCODING *,
|
||||
const char *,
|
||||
const char *,
|
||||
const char **);
|
||||
int (*sameName)(const ENCODING *,
|
||||
const char *, const char *);
|
||||
int (*nameMatchesAscii)(const ENCODING *,
|
||||
const char *, const char *, const char *);
|
||||
int (*nameLength)(const ENCODING *, const char *);
|
||||
const char *(*skipS)(const ENCODING *, const char *);
|
||||
int (*getAtts)(const ENCODING *enc, const char *ptr,
|
||||
int attsMax, ATTRIBUTE *atts);
|
||||
int (*charRefNumber)(const ENCODING *enc, const char *ptr);
|
||||
int (*predefinedEntityName)(const ENCODING *, const char *, const char *);
|
||||
void (*updatePosition)(const ENCODING *,
|
||||
const char *);
|
||||
void (PTRCALL *updatePosition)(const ENCODING *,
|
||||
const char *ptr,
|
||||
const char *end,
|
||||
POSITION *);
|
||||
int (*isPublicId)(const ENCODING *enc, const char *ptr, const char *end,
|
||||
int (PTRCALL *isPublicId)(const ENCODING *enc,
|
||||
const char *ptr,
|
||||
const char *end,
|
||||
const char **badPtr);
|
||||
void (*utf8Convert)(const ENCODING *enc,
|
||||
void (PTRCALL *utf8Convert)(const ENCODING *enc,
|
||||
const char **fromP,
|
||||
const char *fromLim,
|
||||
char **toP,
|
||||
const char *toLim);
|
||||
void (*utf16Convert)(const ENCODING *enc,
|
||||
void (PTRCALL *utf16Convert)(const ENCODING *enc,
|
||||
const char **fromP,
|
||||
const char *fromLim,
|
||||
unsigned short **toP,
|
||||
|
@ -161,24 +173,25 @@ struct encoding {
|
|||
char isUtf16;
|
||||
};
|
||||
|
||||
/*
|
||||
Scan the string starting at ptr until the end of the next complete token,
|
||||
but do not scan past eptr. Return an integer giving the type of token.
|
||||
/* Scan the string starting at ptr until the end of the next complete
|
||||
token, but do not scan past eptr. Return an integer giving the
|
||||
type of token.
|
||||
|
||||
Return XML_TOK_NONE when ptr == eptr; nextTokPtr will not be set.
|
||||
|
||||
Return XML_TOK_PARTIAL when the string does not contain a complete token;
|
||||
nextTokPtr will not be set.
|
||||
Return XML_TOK_PARTIAL when the string does not contain a complete
|
||||
token; nextTokPtr will not be set.
|
||||
|
||||
Return XML_TOK_INVALID when the string does not start a valid token; nextTokPtr
|
||||
will be set to point to the character which made the token invalid.
|
||||
Return XML_TOK_INVALID when the string does not start a valid
|
||||
token; nextTokPtr will be set to point to the character which made
|
||||
the token invalid.
|
||||
|
||||
Otherwise the string starts with a valid token; nextTokPtr will be set to point
|
||||
to the character following the end of that token.
|
||||
Otherwise the string starts with a valid token; nextTokPtr will be
|
||||
set to point to the character following the end of that token.
|
||||
|
||||
Each data character counts as a single token, but adjacent data characters
|
||||
may be returned together. Similarly for characters in the prolog outside
|
||||
literals, comments and processing instructions.
|
||||
Each data character counts as a single token, but adjacent data
|
||||
characters may be returned together. Similarly for characters in
|
||||
the prolog outside literals, comments and processing instructions.
|
||||
*/
|
||||
|
||||
|
||||
|
@ -201,9 +214,9 @@ literals, comments and processing instructions.
|
|||
|
||||
#endif /* XML_DTD */
|
||||
|
||||
/* This is used for performing a 2nd-level tokenization on
|
||||
the content of a literal that has already been returned by XmlTok. */
|
||||
|
||||
/* This is used for performing a 2nd-level tokenization on the content
|
||||
of a literal that has already been returned by XmlTok.
|
||||
*/
|
||||
#define XmlLiteralTok(enc, literalType, ptr, end, nextTokPtr) \
|
||||
(((enc)->literalScanners[literalType])(enc, ptr, end, nextTokPtr))
|
||||
|
||||
|
@ -264,14 +277,16 @@ int XmlParseXmlDecl(int isGeneralTextEntity,
|
|||
int XmlInitEncoding(INIT_ENCODING *, const ENCODING **, const char *name);
|
||||
const ENCODING *XmlGetUtf8InternalEncoding(void);
|
||||
const ENCODING *XmlGetUtf16InternalEncoding(void);
|
||||
int XmlUtf8Encode(int charNumber, char *buf);
|
||||
int XmlUtf16Encode(int charNumber, unsigned short *buf);
|
||||
|
||||
int FASTCALL XmlUtf8Encode(int charNumber, char *buf);
|
||||
int FASTCALL XmlUtf16Encode(int charNumber, unsigned short *buf);
|
||||
int XmlSizeOfUnknownEncoding(void);
|
||||
|
||||
typedef int (*CONVERTER)(void *userData, const char *p);
|
||||
|
||||
ENCODING *
|
||||
XmlInitUnknownEncoding(void *mem,
|
||||
int *table,
|
||||
int (*conv)(void *userData, const char *p),
|
||||
CONVERTER convert,
|
||||
void *userData);
|
||||
|
||||
int XmlParseXmlDeclNS(int isGeneralTextEntity,
|
||||
|
@ -284,13 +299,14 @@ int XmlParseXmlDeclNS(int isGeneralTextEntity,
|
|||
const char **encodingNamePtr,
|
||||
const ENCODING **namedEncodingPtr,
|
||||
int *standalonePtr);
|
||||
|
||||
int XmlInitEncodingNS(INIT_ENCODING *, const ENCODING **, const char *name);
|
||||
const ENCODING *XmlGetUtf8InternalEncodingNS(void);
|
||||
const ENCODING *XmlGetUtf16InternalEncodingNS(void);
|
||||
ENCODING *
|
||||
XmlInitUnknownEncodingNS(void *mem,
|
||||
int *table,
|
||||
int (*conv)(void *userData, const char *p),
|
||||
CONVERTER convert,
|
||||
void *userData);
|
||||
#ifdef __cplusplus
|
||||
}
|
||||
|
|
|
@ -1,5 +1,4 @@
|
|||
/*
|
||||
Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
|
||||
/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
|
||||
See the file COPYING for copying permission.
|
||||
*/
|
||||
|
||||
|
@ -87,9 +86,9 @@ See the file COPYING for copying permission.
|
|||
|
||||
/* ptr points to character following "<!-" */
|
||||
|
||||
static
|
||||
int PREFIX(scanComment)(const ENCODING *enc, const char *ptr, const char *end,
|
||||
const char **nextTokPtr)
|
||||
static int PTRCALL
|
||||
PREFIX(scanComment)(const ENCODING *enc, const char *ptr,
|
||||
const char *end, const char **nextTokPtr)
|
||||
{
|
||||
if (ptr != end) {
|
||||
if (!CHAR_MATCHES(enc, ptr, ASCII_MINUS)) {
|
||||
|
@ -125,9 +124,9 @@ int PREFIX(scanComment)(const ENCODING *enc, const char *ptr, const char *end,
|
|||
|
||||
/* ptr points to character following "<!" */
|
||||
|
||||
static
|
||||
int PREFIX(scanDecl)(const ENCODING *enc, const char *ptr, const char *end,
|
||||
const char **nextTokPtr)
|
||||
static int PTRCALL
|
||||
PREFIX(scanDecl)(const ENCODING *enc, const char *ptr,
|
||||
const char *end, const char **nextTokPtr)
|
||||
{
|
||||
if (ptr == end)
|
||||
return XML_TOK_PARTIAL;
|
||||
|
@ -172,8 +171,9 @@ int PREFIX(scanDecl)(const ENCODING *enc, const char *ptr, const char *end,
|
|||
return XML_TOK_PARTIAL;
|
||||
}
|
||||
|
||||
static
|
||||
int PREFIX(checkPiTarget)(const ENCODING *enc, const char *ptr, const char *end, int *tokPtr)
|
||||
static int PTRCALL
|
||||
PREFIX(checkPiTarget)(const ENCODING *enc, const char *ptr,
|
||||
const char *end, int *tokPtr)
|
||||
{
|
||||
int upper = 0;
|
||||
*tokPtr = XML_TOK_PI;
|
||||
|
@ -216,9 +216,9 @@ int PREFIX(checkPiTarget)(const ENCODING *enc, const char *ptr, const char *end,
|
|||
|
||||
/* ptr points to character following "<?" */
|
||||
|
||||
static
|
||||
int PREFIX(scanPi)(const ENCODING *enc, const char *ptr, const char *end,
|
||||
const char **nextTokPtr)
|
||||
static int PTRCALL
|
||||
PREFIX(scanPi)(const ENCODING *enc, const char *ptr,
|
||||
const char *end, const char **nextTokPtr)
|
||||
{
|
||||
int tok;
|
||||
const char *target = ptr;
|
||||
|
@ -278,12 +278,12 @@ int PREFIX(scanPi)(const ENCODING *enc, const char *ptr, const char *end,
|
|||
return XML_TOK_PARTIAL;
|
||||
}
|
||||
|
||||
|
||||
static
|
||||
int PREFIX(scanCdataSection)(const ENCODING *enc, const char *ptr, const char *end,
|
||||
const char **nextTokPtr)
|
||||
static int PTRCALL
|
||||
PREFIX(scanCdataSection)(const ENCODING *enc, const char *ptr,
|
||||
const char *end, const char **nextTokPtr)
|
||||
{
|
||||
static const char CDATA_LSQB[] = { ASCII_C, ASCII_D, ASCII_A, ASCII_T, ASCII_A, ASCII_LSQB };
|
||||
static const char CDATA_LSQB[] = { ASCII_C, ASCII_D, ASCII_A,
|
||||
ASCII_T, ASCII_A, ASCII_LSQB };
|
||||
int i;
|
||||
/* CDATA[ */
|
||||
if (end - ptr < 6 * MINBPC(enc))
|
||||
|
@ -298,9 +298,9 @@ int PREFIX(scanCdataSection)(const ENCODING *enc, const char *ptr, const char *e
|
|||
return XML_TOK_CDATA_SECT_OPEN;
|
||||
}
|
||||
|
||||
static
|
||||
int PREFIX(cdataSectionTok)(const ENCODING *enc, const char *ptr, const char *end,
|
||||
const char **nextTokPtr)
|
||||
static int PTRCALL
|
||||
PREFIX(cdataSectionTok)(const ENCODING *enc, const char *ptr,
|
||||
const char *end, const char **nextTokPtr)
|
||||
{
|
||||
if (ptr == end)
|
||||
return XML_TOK_NONE;
|
||||
|
@ -376,9 +376,9 @@ int PREFIX(cdataSectionTok)(const ENCODING *enc, const char *ptr, const char *en
|
|||
|
||||
/* ptr points to character following "</" */
|
||||
|
||||
static
|
||||
int PREFIX(scanEndTag)(const ENCODING *enc, const char *ptr, const char *end,
|
||||
const char **nextTokPtr)
|
||||
static int PTRCALL
|
||||
PREFIX(scanEndTag)(const ENCODING *enc, const char *ptr,
|
||||
const char *end, const char **nextTokPtr)
|
||||
{
|
||||
if (ptr == end)
|
||||
return XML_TOK_PARTIAL;
|
||||
|
@ -407,7 +407,8 @@ int PREFIX(scanEndTag)(const ENCODING *enc, const char *ptr, const char *end,
|
|||
return XML_TOK_PARTIAL;
|
||||
#ifdef XML_NS
|
||||
case BT_COLON:
|
||||
/* no need to check qname syntax here, since end-tag must match exactly */
|
||||
/* no need to check qname syntax here,
|
||||
since end-tag must match exactly */
|
||||
ptr += MINBPC(enc);
|
||||
break;
|
||||
#endif
|
||||
|
@ -424,9 +425,9 @@ int PREFIX(scanEndTag)(const ENCODING *enc, const char *ptr, const char *end,
|
|||
|
||||
/* ptr points to character following "&#X" */
|
||||
|
||||
static
|
||||
int PREFIX(scanHexCharRef)(const ENCODING *enc, const char *ptr, const char *end,
|
||||
const char **nextTokPtr)
|
||||
static int PTRCALL
|
||||
PREFIX(scanHexCharRef)(const ENCODING *enc, const char *ptr,
|
||||
const char *end, const char **nextTokPtr)
|
||||
{
|
||||
if (ptr != end) {
|
||||
switch (BYTE_TYPE(enc, ptr)) {
|
||||
|
@ -456,9 +457,9 @@ int PREFIX(scanHexCharRef)(const ENCODING *enc, const char *ptr, const char *end
|
|||
|
||||
/* ptr points to character following "&#" */
|
||||
|
||||
static
|
||||
int PREFIX(scanCharRef)(const ENCODING *enc, const char *ptr, const char *end,
|
||||
const char **nextTokPtr)
|
||||
static int PTRCALL
|
||||
PREFIX(scanCharRef)(const ENCODING *enc, const char *ptr,
|
||||
const char *end, const char **nextTokPtr)
|
||||
{
|
||||
if (ptr != end) {
|
||||
if (CHAR_MATCHES(enc, ptr, ASCII_x))
|
||||
|
@ -488,8 +489,8 @@ int PREFIX(scanCharRef)(const ENCODING *enc, const char *ptr, const char *end,
|
|||
|
||||
/* ptr points to character following "&" */
|
||||
|
||||
static
|
||||
int PREFIX(scanRef)(const ENCODING *enc, const char *ptr, const char *end,
|
||||
static int PTRCALL
|
||||
PREFIX(scanRef)(const ENCODING *enc, const char *ptr, const char *end,
|
||||
const char **nextTokPtr)
|
||||
{
|
||||
if (ptr == end)
|
||||
|
@ -518,8 +519,8 @@ int PREFIX(scanRef)(const ENCODING *enc, const char *ptr, const char *end,
|
|||
|
||||
/* ptr points to character following first character of attribute name */
|
||||
|
||||
static
|
||||
int PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end,
|
||||
static int PTRCALL
|
||||
PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end,
|
||||
const char **nextTokPtr)
|
||||
{
|
||||
#ifdef XML_NS
|
||||
|
@ -574,7 +575,6 @@ int PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end,
|
|||
hadColon = 0;
|
||||
#endif
|
||||
for (;;) {
|
||||
|
||||
ptr += MINBPC(enc);
|
||||
if (ptr == end)
|
||||
return XML_TOK_PARTIAL;
|
||||
|
@ -678,8 +678,8 @@ int PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end,
|
|||
|
||||
/* ptr points to character following "<" */
|
||||
|
||||
static
|
||||
int PREFIX(scanLt)(const ENCODING *enc, const char *ptr, const char *end,
|
||||
static int PTRCALL
|
||||
PREFIX(scanLt)(const ENCODING *enc, const char *ptr, const char *end,
|
||||
const char **nextTokPtr)
|
||||
{
|
||||
#ifdef XML_NS
|
||||
|
@ -696,7 +696,8 @@ int PREFIX(scanLt)(const ENCODING *enc, const char *ptr, const char *end,
|
|||
case BT_MINUS:
|
||||
return PREFIX(scanComment)(enc, ptr + MINBPC(enc), end, nextTokPtr);
|
||||
case BT_LSQB:
|
||||
return PREFIX(scanCdataSection)(enc, ptr + MINBPC(enc), end, nextTokPtr);
|
||||
return PREFIX(scanCdataSection)(enc, ptr + MINBPC(enc),
|
||||
end, nextTokPtr);
|
||||
}
|
||||
*nextTokPtr = ptr;
|
||||
return XML_TOK_INVALID;
|
||||
|
@ -777,8 +778,8 @@ int PREFIX(scanLt)(const ENCODING *enc, const char *ptr, const char *end,
|
|||
return XML_TOK_PARTIAL;
|
||||
}
|
||||
|
||||
static
|
||||
int PREFIX(contentTok)(const ENCODING *enc, const char *ptr, const char *end,
|
||||
static int PTRCALL
|
||||
PREFIX(contentTok)(const ENCODING *enc, const char *ptr, const char *end,
|
||||
const char **nextTokPtr)
|
||||
{
|
||||
if (ptr == end)
|
||||
|
@ -876,8 +877,8 @@ int PREFIX(contentTok)(const ENCODING *enc, const char *ptr, const char *end,
|
|||
|
||||
/* ptr points to character following "%" */
|
||||
|
||||
static
|
||||
int PREFIX(scanPercent)(const ENCODING *enc, const char *ptr, const char *end,
|
||||
static int PTRCALL
|
||||
PREFIX(scanPercent)(const ENCODING *enc, const char *ptr, const char *end,
|
||||
const char **nextTokPtr)
|
||||
{
|
||||
if (ptr == end)
|
||||
|
@ -905,8 +906,8 @@ int PREFIX(scanPercent)(const ENCODING *enc, const char *ptr, const char *end,
|
|||
return XML_TOK_PARTIAL;
|
||||
}
|
||||
|
||||
static
|
||||
int PREFIX(scanPoundName)(const ENCODING *enc, const char *ptr, const char *end,
|
||||
static int PTRCALL
|
||||
PREFIX(scanPoundName)(const ENCODING *enc, const char *ptr, const char *end,
|
||||
const char **nextTokPtr)
|
||||
{
|
||||
if (ptr == end)
|
||||
|
@ -932,8 +933,8 @@ int PREFIX(scanPoundName)(const ENCODING *enc, const char *ptr, const char *end,
|
|||
return -XML_TOK_POUND_NAME;
|
||||
}
|
||||
|
||||
static
|
||||
int PREFIX(scanLit)(int open, const ENCODING *enc,
|
||||
static int PTRCALL
|
||||
PREFIX(scanLit)(int open, const ENCODING *enc,
|
||||
const char *ptr, const char *end,
|
||||
const char **nextTokPtr)
|
||||
{
|
||||
|
@ -964,8 +965,8 @@ int PREFIX(scanLit)(int open, const ENCODING *enc,
|
|||
return XML_TOK_PARTIAL;
|
||||
}
|
||||
|
||||
static
|
||||
int PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end,
|
||||
static int PTRCALL
|
||||
PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end,
|
||||
const char **nextTokPtr)
|
||||
{
|
||||
int tok;
|
||||
|
@ -1008,8 +1009,11 @@ int PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end,
|
|||
return XML_TOK_INVALID;
|
||||
}
|
||||
case BT_CR:
|
||||
if (ptr + MINBPC(enc) == end)
|
||||
if (ptr + MINBPC(enc) == end) {
|
||||
*nextTokPtr = end;
|
||||
/* indicate that this might be part of a CR/LF pair */
|
||||
return -XML_TOK_PROLOG_S;
|
||||
}
|
||||
/* fall through */
|
||||
case BT_S: case BT_LF:
|
||||
for (;;) {
|
||||
|
@ -1192,9 +1196,9 @@ int PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end,
|
|||
return -tok;
|
||||
}
|
||||
|
||||
static
|
||||
int PREFIX(attributeValueTok)(const ENCODING *enc, const char *ptr, const char *end,
|
||||
const char **nextTokPtr)
|
||||
static int PTRCALL
|
||||
PREFIX(attributeValueTok)(const ENCODING *enc, const char *ptr,
|
||||
const char *end, const char **nextTokPtr)
|
||||
{
|
||||
const char *start;
|
||||
if (ptr == end)
|
||||
|
@ -1250,9 +1254,9 @@ int PREFIX(attributeValueTok)(const ENCODING *enc, const char *ptr, const char *
|
|||
return XML_TOK_DATA_CHARS;
|
||||
}
|
||||
|
||||
static
|
||||
int PREFIX(entityValueTok)(const ENCODING *enc, const char *ptr, const char *end,
|
||||
const char **nextTokPtr)
|
||||
static int PTRCALL
|
||||
PREFIX(entityValueTok)(const ENCODING *enc, const char *ptr,
|
||||
const char *end, const char **nextTokPtr)
|
||||
{
|
||||
const char *start;
|
||||
if (ptr == end)
|
||||
|
@ -1307,9 +1311,9 @@ int PREFIX(entityValueTok)(const ENCODING *enc, const char *ptr, const char *end
|
|||
|
||||
#ifdef XML_DTD
|
||||
|
||||
static
|
||||
int PREFIX(ignoreSectionTok)(const ENCODING *enc, const char *ptr, const char *end,
|
||||
const char **nextTokPtr)
|
||||
static int PTRCALL
|
||||
PREFIX(ignoreSectionTok)(const ENCODING *enc, const char *ptr,
|
||||
const char *end, const char **nextTokPtr)
|
||||
{
|
||||
int level = 0;
|
||||
if (MINBPC(enc) > 1) {
|
||||
|
@ -1360,8 +1364,8 @@ int PREFIX(ignoreSectionTok)(const ENCODING *enc, const char *ptr, const char *e
|
|||
|
||||
#endif /* XML_DTD */
|
||||
|
||||
static
|
||||
int PREFIX(isPublicId)(const ENCODING *enc, const char *ptr, const char *end,
|
||||
static int PTRCALL
|
||||
PREFIX(isPublicId)(const ENCODING *enc, const char *ptr, const char *end,
|
||||
const char **badPtr)
|
||||
{
|
||||
ptr += MINBPC(enc);
|
||||
|
@ -1415,12 +1419,13 @@ int PREFIX(isPublicId)(const ENCODING *enc, const char *ptr, const char *end,
|
|||
return 1;
|
||||
}
|
||||
|
||||
/* This must only be called for a well-formed start-tag or empty element tag.
|
||||
Returns the number of attributes. Pointers to the first attsMax attributes
|
||||
are stored in atts. */
|
||||
/* This must only be called for a well-formed start-tag or empty
|
||||
element tag. Returns the number of attributes. Pointers to the
|
||||
first attsMax attributes are stored in atts.
|
||||
*/
|
||||
|
||||
static
|
||||
int PREFIX(getAtts)(const ENCODING *enc, const char *ptr,
|
||||
static int PTRCALL
|
||||
PREFIX(getAtts)(const ENCODING *enc, const char *ptr,
|
||||
int attsMax, ATTRIBUTE *atts)
|
||||
{
|
||||
enum { other, inName, inValue } state = inName;
|
||||
|
@ -1512,14 +1517,16 @@ int PREFIX(getAtts)(const ENCODING *enc, const char *ptr,
|
|||
/* not reached */
|
||||
}
|
||||
|
||||
static
|
||||
int PREFIX(charRefNumber)(const ENCODING *enc, const char *ptr)
|
||||
static int PTRFASTCALL
|
||||
PREFIX(charRefNumber)(const ENCODING *enc, const char *ptr)
|
||||
{
|
||||
int result = 0;
|
||||
/* skip &# */
|
||||
ptr += 2*MINBPC(enc);
|
||||
if (CHAR_MATCHES(enc, ptr, ASCII_x)) {
|
||||
for (ptr += MINBPC(enc); !CHAR_MATCHES(enc, ptr, ASCII_SEMI); ptr += MINBPC(enc)) {
|
||||
for (ptr += MINBPC(enc);
|
||||
!CHAR_MATCHES(enc, ptr, ASCII_SEMI);
|
||||
ptr += MINBPC(enc)) {
|
||||
int c = BYTE_TO_ASCII(enc, ptr);
|
||||
switch (c) {
|
||||
case ASCII_0: case ASCII_1: case ASCII_2: case ASCII_3: case ASCII_4:
|
||||
|
@ -1527,11 +1534,13 @@ int PREFIX(charRefNumber)(const ENCODING *enc, const char *ptr)
|
|||
result <<= 4;
|
||||
result |= (c - ASCII_0);
|
||||
break;
|
||||
case ASCII_A: case ASCII_B: case ASCII_C: case ASCII_D: case ASCII_E: case ASCII_F:
|
||||
case ASCII_A: case ASCII_B: case ASCII_C:
|
||||
case ASCII_D: case ASCII_E: case ASCII_F:
|
||||
result <<= 4;
|
||||
result += 10 + (c - ASCII_A);
|
||||
break;
|
||||
case ASCII_a: case ASCII_b: case ASCII_c: case ASCII_d: case ASCII_e: case ASCII_f:
|
||||
case ASCII_a: case ASCII_b: case ASCII_c:
|
||||
case ASCII_d: case ASCII_e: case ASCII_f:
|
||||
result <<= 4;
|
||||
result += 10 + (c - ASCII_a);
|
||||
break;
|
||||
|
@ -1552,8 +1561,9 @@ int PREFIX(charRefNumber)(const ENCODING *enc, const char *ptr)
|
|||
return checkCharRefNumber(result);
|
||||
}
|
||||
|
||||
static
|
||||
int PREFIX(predefinedEntityName)(const ENCODING *enc, const char *ptr, const char *end)
|
||||
static int PTRCALL
|
||||
PREFIX(predefinedEntityName)(const ENCODING *enc, const char *ptr,
|
||||
const char *end)
|
||||
{
|
||||
switch ((end - ptr)/MINBPC(enc)) {
|
||||
case 2:
|
||||
|
@ -1605,8 +1615,8 @@ int PREFIX(predefinedEntityName)(const ENCODING *enc, const char *ptr, const cha
|
|||
return 0;
|
||||
}
|
||||
|
||||
static
|
||||
int PREFIX(sameName)(const ENCODING *enc, const char *ptr1, const char *ptr2)
|
||||
static int PTRCALL
|
||||
PREFIX(sameName)(const ENCODING *enc, const char *ptr1, const char *ptr2)
|
||||
{
|
||||
for (;;) {
|
||||
switch (BYTE_TYPE(enc, ptr1)) {
|
||||
|
@ -1669,8 +1679,8 @@ int PREFIX(sameName)(const ENCODING *enc, const char *ptr1, const char *ptr2)
|
|||
/* not reached */
|
||||
}
|
||||
|
||||
static
|
||||
int PREFIX(nameMatchesAscii)(const ENCODING *enc, const char *ptr1,
|
||||
static int PTRCALL
|
||||
PREFIX(nameMatchesAscii)(const ENCODING *enc, const char *ptr1,
|
||||
const char *end1, const char *ptr2)
|
||||
{
|
||||
for (; *ptr2; ptr1 += MINBPC(enc), ptr2++) {
|
||||
|
@ -1682,8 +1692,8 @@ int PREFIX(nameMatchesAscii)(const ENCODING *enc, const char *ptr1,
|
|||
return ptr1 == end1;
|
||||
}
|
||||
|
||||
static
|
||||
int PREFIX(nameLength)(const ENCODING *enc, const char *ptr)
|
||||
static int PTRFASTCALL
|
||||
PREFIX(nameLength)(const ENCODING *enc, const char *ptr)
|
||||
{
|
||||
const char *start = ptr;
|
||||
for (;;) {
|
||||
|
@ -1709,8 +1719,8 @@ int PREFIX(nameLength)(const ENCODING *enc, const char *ptr)
|
|||
}
|
||||
}
|
||||
|
||||
static
|
||||
const char *PREFIX(skipS)(const ENCODING *enc, const char *ptr)
|
||||
static const char * PTRFASTCALL
|
||||
PREFIX(skipS)(const ENCODING *enc, const char *ptr)
|
||||
{
|
||||
for (;;) {
|
||||
switch (BYTE_TYPE(enc, ptr)) {
|
||||
|
@ -1725,8 +1735,8 @@ const char *PREFIX(skipS)(const ENCODING *enc, const char *ptr)
|
|||
}
|
||||
}
|
||||
|
||||
static
|
||||
void PREFIX(updatePosition)(const ENCODING *enc,
|
||||
static void PTRCALL
|
||||
PREFIX(updatePosition)(const ENCODING *enc,
|
||||
const char *ptr,
|
||||
const char *end,
|
||||
POSITION *pos)
|
||||
|
@ -1766,3 +1776,4 @@ void PREFIX(updatePosition)(const ENCODING *enc,
|
|||
#undef CHECK_NAME_CASES
|
||||
#undef CHECK_NMSTRT_CASE
|
||||
#undef CHECK_NMSTRT_CASES
|
||||
|
||||
|
|
|
@ -1,22 +1,25 @@
|
|||
const ENCODING *NS(XmlGetUtf8InternalEncoding)(void)
|
||||
const ENCODING *
|
||||
NS(XmlGetUtf8InternalEncoding)(void)
|
||||
{
|
||||
return &ns(internal_utf8_encoding).enc;
|
||||
}
|
||||
|
||||
const ENCODING *NS(XmlGetUtf16InternalEncoding)(void)
|
||||
const ENCODING *
|
||||
NS(XmlGetUtf16InternalEncoding)(void)
|
||||
{
|
||||
#if XML_BYTE_ORDER == 12
|
||||
#if BYTEORDER == 1234
|
||||
return &ns(internal_little2_encoding).enc;
|
||||
#elif XML_BYTE_ORDER == 21
|
||||
#elif BYTEORDER == 4321
|
||||
return &ns(internal_big2_encoding).enc;
|
||||
#else
|
||||
const short n = 1;
|
||||
return *(const char *)&n ? &ns(internal_little2_encoding).enc : &ns(internal_big2_encoding).enc;
|
||||
return (*(const char *)&n
|
||||
? &ns(internal_little2_encoding).enc
|
||||
: &ns(internal_big2_encoding).enc);
|
||||
#endif
|
||||
}
|
||||
|
||||
static
|
||||
const ENCODING *NS(encodings)[] = {
|
||||
static const ENCODING *NS(encodings)[] = {
|
||||
&ns(latin1_encoding).enc,
|
||||
&ns(ascii_encoding).enc,
|
||||
&ns(utf8_encoding).enc,
|
||||
|
@ -26,21 +29,25 @@ const ENCODING *NS(encodings)[] = {
|
|||
&ns(utf8_encoding).enc /* NO_ENC */
|
||||
};
|
||||
|
||||
static
|
||||
int NS(initScanProlog)(const ENCODING *enc, const char *ptr, const char *end,
|
||||
static int PTRCALL
|
||||
NS(initScanProlog)(const ENCODING *enc, const char *ptr, const char *end,
|
||||
const char **nextTokPtr)
|
||||
{
|
||||
return initScan(NS(encodings), (const INIT_ENCODING *)enc, XML_PROLOG_STATE, ptr, end, nextTokPtr);
|
||||
return initScan(NS(encodings), (const INIT_ENCODING *)enc,
|
||||
XML_PROLOG_STATE, ptr, end, nextTokPtr);
|
||||
}
|
||||
|
||||
static
|
||||
int NS(initScanContent)(const ENCODING *enc, const char *ptr, const char *end,
|
||||
static int PTRCALL
|
||||
NS(initScanContent)(const ENCODING *enc, const char *ptr, const char *end,
|
||||
const char **nextTokPtr)
|
||||
{
|
||||
return initScan(NS(encodings), (const INIT_ENCODING *)enc, XML_CONTENT_STATE, ptr, end, nextTokPtr);
|
||||
return initScan(NS(encodings), (const INIT_ENCODING *)enc,
|
||||
XML_CONTENT_STATE, ptr, end, nextTokPtr);
|
||||
}
|
||||
|
||||
int NS(XmlInitEncoding)(INIT_ENCODING *p, const ENCODING **encPtr, const char *name)
|
||||
int
|
||||
NS(XmlInitEncoding)(INIT_ENCODING *p, const ENCODING **encPtr,
|
||||
const char *name)
|
||||
{
|
||||
int i = getEncodingIndex(name);
|
||||
if (i == UNKNOWN_ENC)
|
||||
|
@ -54,8 +61,8 @@ int NS(XmlInitEncoding)(INIT_ENCODING *p, const ENCODING **encPtr, const char *n
|
|||
return 1;
|
||||
}
|
||||
|
||||
static
|
||||
const ENCODING *NS(findEncoding)(const ENCODING *enc, const char *ptr, const char *end)
|
||||
static const ENCODING *
|
||||
NS(findEncoding)(const ENCODING *enc, const char *ptr, const char *end)
|
||||
{
|
||||
#define ENCODING_MAX 128
|
||||
char buf[ENCODING_MAX];
|
||||
|
@ -73,7 +80,8 @@ const ENCODING *NS(findEncoding)(const ENCODING *enc, const char *ptr, const cha
|
|||
return NS(encodings)[i];
|
||||
}
|
||||
|
||||
int NS(XmlParseXmlDecl)(int isGeneralTextEntity,
|
||||
int
|
||||
NS(XmlParseXmlDecl)(int isGeneralTextEntity,
|
||||
const ENCODING *enc,
|
||||
const char *ptr,
|
||||
const char *end,
|
||||
|
|
7
setup.py
7
setup.py
|
@ -690,9 +690,9 @@ class PyBuildExt(build_ext):
|
|||
# More information on Expat can be found at www.libexpat.org.
|
||||
#
|
||||
if sys.byteorder == "little":
|
||||
xmlbo = "12"
|
||||
xmlbo = "1234"
|
||||
else:
|
||||
xmlbo = "21"
|
||||
xmlbo = "4321"
|
||||
expatinc = os.path.join(os.getcwd(), srcdir, 'Modules', 'expat')
|
||||
exts.append(Extension('pyexpat',
|
||||
sources = [
|
||||
|
@ -702,10 +702,9 @@ class PyBuildExt(build_ext):
|
|||
'expat/xmltok.c',
|
||||
],
|
||||
define_macros = [
|
||||
('HAVE_EXPAT_H',None),
|
||||
('XML_NS', '1'),
|
||||
('XML_DTD', '1'),
|
||||
('XML_BYTE_ORDER', xmlbo),
|
||||
('BYTEORDER', xmlbo),
|
||||
('XML_CONTEXT_BYTES','1024'),
|
||||
],
|
||||
include_dirs = [expatinc]
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue