Gnome XML Library Reference Manual | |||
---|---|---|---|
<<< Previous Page | Home | Up | Next Page >>> |
struct xmlParserInput { /* Input buffer */ xmlParserInputBufferPtr buf; /* UTF-8 encoded buffer */ const char *filename; /* The file analyzed, if any */ const char *directory; /* the directory/base of teh file */ const xmlChar *base; /* Base of the array to parse */ const xmlChar *cur; /* Current char being parsed */ int length; /* length if known */ int line; /* Current line */ int col; /* Current column */ int consumed; /* How many xmlChars already consumed */ xmlParserInputDeallocate free; /* function to deallocate the base */ /* added after 2.3.5 integration */ const xmlChar *end; /* end of the arry to parse */ const xmlChar *encoding; /* the encoding string for entity */ const xmlChar *version; /* the version string for entity */ int standalone; /* Was that entity marked standalone */ }; |
struct xmlParserNodeInfo { const struct _xmlNode* node; /* Position & line # that text that created the node begins & ends on */ unsigned long begin_pos; unsigned long begin_line; unsigned long end_pos; unsigned long end_line; }; |
struct xmlParserNodeInfoSeq { unsigned long maximum; unsigned long length; xmlParserNodeInfo* buffer; }; |
typedef enum { XML_PARSER_EOF = -1, /* nothing is to be parsed */ XML_PARSER_START = 0, /* nothing has been parsed */ XML_PARSER_MISC, /* Misc* before int subset */ XML_PARSER_PI, /* Whithin a processing instruction */ XML_PARSER_DTD, /* within some DTD content */ XML_PARSER_PROLOG, /* Misc* after internal subset */ XML_PARSER_COMMENT, /* within a comment */ XML_PARSER_START_TAG, /* within a start tag */ XML_PARSER_CONTENT, /* within the content */ XML_PARSER_CDATA_SECTION, /* within a CDATA section */ XML_PARSER_END_TAG, /* within a closing tag */ XML_PARSER_ENTITY_DECL, /* within an entity declaration */ XML_PARSER_ENTITY_VALUE, /* within an entity value in a decl */ XML_PARSER_ATTRIBUTE_VALUE, /* within an attribute value */ XML_PARSER_EPILOG, /* the Misc* after the last end tag */ /* added after 2.3.5 integration */ XML_PARSER_SYSTEM_LITERAL, /* within a SYSTEM value */ XML_PARSER_IGNORE /* within an IGNORED section */ } xmlParserInputState; |
struct xmlParserCtxt { struct _xmlSAXHandler *sax; /* The SAX handler */ void *userData; /* the document being built */ xmlDocPtr myDoc; /* the document being built */ int wellFormed; /* is the document well formed */ int replaceEntities; /* shall we replace entities ? */ const xmlChar *version; /* the XML version string */ const xmlChar *encoding; /* encoding, if any */ int standalone; /* standalone document */ int html; /* are we parsing an HTML document */ /* Input stream stack */ xmlParserInputPtr input; /* Current input stream */ int inputNr; /* Number of current input streams */ int inputMax; /* Max number of input streams */ xmlParserInputPtr *inputTab; /* stack of inputs */ /* Node analysis stack only used for DOM building */ xmlNodePtr node; /* Current parsed Node */ int nodeNr; /* Depth of the parsing stack */ int nodeMax; /* Max depth of the parsing stack */ xmlNodePtr *nodeTab; /* array of nodes */ int record_info; /* Whether node info should be kept */ xmlParserNodeInfoSeq node_seq; /* info about each node parsed */ int errNo; /* error code */ int hasExternalSubset; /* reference and external subset */ int hasPErefs; /* the internal subset has PE refs */ int external; /* are we parsing an external entity */ int valid; /* is the document valid */ int validate; /* shall we try to validate ? */ xmlValidCtxt vctxt; /* The validity context */ xmlParserInputState instate; /* current type of input */ int token; /* next char look-ahead */ char *directory; /* the data directory */ /* Node name stack only used for HTML parsing */ xmlChar *name; /* Current parsed Node */ int nameNr; /* Depth of the parsing stack */ int nameMax; /* Max depth of the parsing stack */ xmlChar * *nameTab; /* array of nodes */ long nbChars; /* number of xmlChar processed */ long checkIndex; /* used by progressive parsing lookup */ int keepBlanks; /* ugly but ... */ /* Added after integration of 2.3.5 parser */ int disableSAX; /* SAX callbacks are disabled */ int inSubset; /* Parsing is in int 1/ext 2 subset */ xmlChar * intSubName; /* name of subset */ xmlChar * extSubURI; /* URI of external subset */ xmlChar * extSubSystem; /* SYSTEM ID of external subset */ /* xml:space values */ int * space; /* Should the parser preserve spaces */ int spaceNr; /* Depth of the parsing stack */ int spaceMax; /* Max depth of the parsing stack */ int * spaceTab; /* array of space infos */ int depth; /* to prevent entity substitution loops */ xmlParserInputPtr entity; /* used to check entities boundaries */ int charset; /* encoding of the in-memory content actually an xmlCharEncoding */ int nodelen; /* Those two fields are there to */ int nodemem; /* Speed up large node parsing */ int pedantic; /* signal pedantic warnings or loose behaviour */ void *_private; /* For user data, libxml won't touch it */ int loadsubset; /* should the external subset be loaded */ }; |
struct xmlSAXLocator { const xmlChar *(*getPublicId)(void *ctx); const xmlChar *(*getSystemId)(void *ctx); int (*getLineNumber)(void *ctx); int (*getColumnNumber)(void *ctx); }; |
xmlParserInputPtr (*resolveEntitySAXFunc) (void *ctx, const xmlChar *publicId, const xmlChar *systemId); |
void (*internalSubsetSAXFunc) (void *ctx, const xmlChar *name, const xmlChar *ExternalID, const xmlChar *SystemID); |
xmlEntityPtr (*getParameterEntitySAXFunc) (void *ctx, const xmlChar *name); |
void (*entityDeclSAXFunc) (void *ctx, const xmlChar *name, int type, const xmlChar *publicId, const xmlChar *systemId, xmlChar *content); |
void (*notationDeclSAXFunc) (void *ctx, const xmlChar *name, const xmlChar *publicId, const xmlChar *systemId); |
void (*attributeDeclSAXFunc) (void *ctx, const xmlChar *elem, const xmlChar *name, int type, int def, const xmlChar *defaultValue, xmlEnumerationPtr tree); |
void (*elementDeclSAXFunc) (void *ctx, const xmlChar *name, int type, xmlElementContentPtr content); |
void (*unparsedEntityDeclSAXFunc) (void *ctx, const xmlChar *name, const xmlChar *publicId, const xmlChar *systemId, const xmlChar *notationName); |
void (*startElementSAXFunc) (void *ctx, const xmlChar *name, const xmlChar **atts); |
void (*ignorableWhitespaceSAXFunc) (void *ctx, const xmlChar *ch, int len); |
void (*processingInstructionSAXFunc) (void *ctx, const xmlChar *target, const xmlChar *data); |
struct xmlSAXHandler { internalSubsetSAXFunc internalSubset; isStandaloneSAXFunc isStandalone; hasInternalSubsetSAXFunc hasInternalSubset; hasExternalSubsetSAXFunc hasExternalSubset; resolveEntitySAXFunc resolveEntity; getEntitySAXFunc getEntity; entityDeclSAXFunc entityDecl; notationDeclSAXFunc notationDecl; attributeDeclSAXFunc attributeDecl; elementDeclSAXFunc elementDecl; unparsedEntityDeclSAXFunc unparsedEntityDecl; setDocumentLocatorSAXFunc setDocumentLocator; startDocumentSAXFunc startDocument; endDocumentSAXFunc endDocument; startElementSAXFunc startElement; endElementSAXFunc endElement; referenceSAXFunc reference; charactersSAXFunc characters; ignorableWhitespaceSAXFunc ignorableWhitespace; processingInstructionSAXFunc processingInstruction; commentSAXFunc comment; warningSAXFunc warning; errorSAXFunc error; fatalErrorSAXFunc fatalError; getParameterEntitySAXFunc getParameterEntity; cdataBlockSAXFunc cdataBlock; }; |
xmlParserInputPtr (*xmlExternalEntityLoader) (const char *URL, const char *ID, xmlParserCtxtPtr context); |
void xmlCleanupParser (void); |
Cleanup function for the XML parser. It tries to reclaim all parsing related global memory allocated for the parser processing. It doesn't deallocate any document related memory. Calling this function should not prevent reusing the parser.
int xmlParserInputRead (xmlParserInputPtr in, int len); |
This function refresh the input for the parser. It doesn't try to preserve pointers to the input buffer, and discard already read data
int xmlParserInputGrow (xmlParserInputPtr in, int len); |
This function increase the input for the parser. It tries to preserve pointers to the input buffer, and keep already read data
xmlChar* xmlStrsub (const xmlChar *str, int start, int len); |
Extract a substring of a given string
int xmlStrncmp (const xmlChar *str1, const xmlChar *str2, int len); |
a strncmp for xmlChar's
xmlChar* xmlStrncat (xmlChar *cur, const xmlChar *add, int len); |
a strncat for array of xmlChar's
xmlDocPtr xmlParseDoc (xmlChar *cur); |
parse an XML in-memory document and build a tree.
xmlDocPtr xmlParseMemory (char *buffer, int size); |
parse an XML in-memory block and build a tree.
xmlDocPtr xmlParseFile (const char *filename); |
parse an XML file and build a tree. Automatic support for ZLIB/Compress compressed document is provided by default if found at compile-time.
int xmlSubstituteEntitiesDefault (int val); |
Set and return the previous value for default entity support. Initially the parser always keep entity references instead of substituting entity values in the output. This function has to be used to change the default parser behaviour SAX::subtituteEntities() has to be used for changing that on a file by file basis.
int xmlKeepBlanksDefault (int val); |
Set and return the previous value for default blanks text nodes support. The 1.x version of the parser used an heuristic to try to detect ignorable white spaces. As a result the SAX callback was generating ignorableWhitespace() callbacks instead of characters() one, and when using the DOM output text nodes containing those blanks were not generated. The 2.x and later version will switch to the XML standard way and ignorableWhitespace() are only generated when running the parser in validating mode and when the current element doesn't allow CDATA or mixed content. This function is provided as a way to force the standard behaviour on 1.X libs and to switch back to the old mode for compatibility when running 1.X client code on 2.X . Upgrade of 1.X code should be done by using xmlIsBlankNode() commodity function to detect the "empty" nodes generated. This value also affect autogeneration of indentation when saving code if blanks sections are kept, indentation is not generated.
xmlDocPtr xmlRecoverDoc (xmlChar *cur); |
parse an XML in-memory document and build a tree. In the case the document is not Well Formed, a tree is built anyway
xmlDocPtr xmlRecoverMemory (char *buffer, int size); |
parse an XML in-memory block and build a tree. In the case the document is not Well Formed, a tree is built anyway
xmlDocPtr xmlRecoverFile (const char *filename); |
parse an XML file and build a tree. Automatic support for ZLIB/Compress compressed document is provided by default if found at compile-time. In the case the document is not Well Formed, a tree is built anyway
int xmlParseDocument (xmlParserCtxtPtr ctxt); |
parse an XML document (and build a tree if using the standard SAX interface).
[1] document ::= prolog element Misc*
[22] prolog ::= XMLDecl? Misc* (doctypedecl Misc*)?
xmlDocPtr xmlSAXParseDoc (xmlSAXHandlerPtr sax, xmlChar *cur, int recovery); |
parse an XML in-memory document and build a tree. It use the given SAX function block to handle the parsing callback. If sax is NULL, fallback to the default DOM tree building routines.
int xmlSAXUserParseFile (xmlSAXHandlerPtr sax, void *user_data, const char *filename); |
parse an XML file and call the given SAX handler routines. Automatic support for ZLIB/Compress compressed document is provided
int xmlSAXUserParseMemory (xmlSAXHandlerPtr sax, void *user_data, char *buffer, int size); |
A better SAX parsing routine. parse an XML in-memory buffer and call the given SAX handler routines.
xmlDocPtr xmlSAXParseMemory (xmlSAXHandlerPtr sax, char *buffer, int size, int recovery); |
parse an XML in-memory block and use the given SAX function block to handle the parsing callback. If sax is NULL, fallback to the default DOM tree building routines.
xmlDocPtr xmlSAXParseFile (xmlSAXHandlerPtr sax, const char *filename, int recovery); |
parse an XML file and build a tree. Automatic support for ZLIB/Compress compressed document is provided by default if found at compile-time. It use the given SAX function block to handle the parsing callback. If sax is NULL, fallback to the default DOM tree building routines.
xmlDtdPtr xmlParseDTD (const xmlChar *ExternalID, const xmlChar *SystemID); |
Load and parse an external subset.
xmlDtdPtr xmlSAXParseDTD (xmlSAXHandlerPtr sax, const xmlChar *ExternalID, const xmlChar *SystemID); |
Load and parse an external subset.
void htmlDefaultSAXHandlerInit (void); |
Initialize the default SAX handler
void xmlClearParserCtxt (xmlParserCtxtPtr ctxt); |
Clear (release owned resources) and reinitialize a parser context
void xmlFreeParserCtxt (xmlParserCtxtPtr ctxt); |
Free all the memory used by a parser context. However the parsed document in ctxt->myDoc is not freed.
void xmlSetupParserForBuffer (xmlParserCtxtPtr ctxt, const xmlChar *buffer, const char *filename); |
Setup the parser context to parse a new buffer; Clears any prior contents from the parser context. The buffer parameter must not be NULL, but the filename parameter can be
xmlParserCtxtPtr xmlCreateDocParserCtxt (xmlChar *cur); |
Create a parser context for an XML in-memory document.
xmlParserCtxtPtr xmlCreatePushParserCtxt (xmlSAXHandlerPtr sax, void *user_data, const char *chunk, int size, const char *filename); |
Create a parser context for using the XML parser in push mode To allow content encoding detection, size should be >= 4 The value of filename is used for fetching external entities and error/warning reports.
int xmlParseChunk (xmlParserCtxtPtr ctxt, const char *chunk, int size, int terminate); |
Parse a Chunk of memory
const xmlParserNodeInfo* xmlParserFindNodeInfo (const xmlParserCtxt *ctxt, const xmlNode *node); |
Find the parser node info struct for a given node
void xmlInitNodeInfoSeq (xmlParserNodeInfoSeqPtr seq); |
-- Initialize (set to initial state) node info sequence
void xmlClearNodeInfoSeq (xmlParserNodeInfoSeqPtr seq); |
-- Clear (release memory and reinitialize) node info sequence
unsigned long xmlParserFindNodeInfoIndex (const xmlParserNodeInfoSeq *seq, const xmlNode *node); |
xmlParserFindNodeInfoIndex : Find the index that the info record for the given node is or should be at in a sorted sequence
void xmlParserAddNodeInfo (xmlParserCtxtPtr ctxt, const xmlParserNodeInfo *info); |
Insert node info record into the sorted sequence
xmlParserInputPtr xmlLoadExternalEntity (const char *URL, const char *ID, xmlParserCtxtPtr context); |
int xmlUseNewParser (int val); |
Set and return the previous value for the default XML parser to use The 1.x version of the parser up to 1.8.11 is horribly broken The 2.x and later version aim at completete compliance to the standard This function is provided as a way to force using the new parser on 1.X libs when the applications are ready to handle correct XML and the UTF8 character flow provided by the new parser.