parser

Gnome XML Library Reference Manual
<<< Previous Page	Home	Up	Next Page >>>

Details

XML_DEFAULT_VERSION

#define XML_DEFAULT_VERSION	"1.0"

The default version of XML used: 1.0

xmlParserInputDeallocate ()

void        (*xmlParserInputDeallocate)     (xmlChar *str);

Callback for freeing some parser input allocations.

str : the string to deallocate

struct xmlParserInput

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 the file */
    const xmlChar *base;              /* Base of the array to parse */
    const xmlChar *cur;               /* Current char being parsed */
    const xmlChar *end;               /* end of the array to parse */
    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 */
    const xmlChar *encoding;          /* the encoding string for entity */
    const xmlChar *version;           /* the version string for entity */
    int standalone;                   /* Was that entity marked standalone */
};

An xmlParserInput is an input flow for the XML processor. Each entity parsed is associated an xmlParserInput (except the few predefined ones). This is the case both for internal entities - in which case the flow is already completely in memory - or external entities - in which case we use the buf structure for progressive reading and I18N conversions to the internal UTF-8 format.

struct xmlParserNodeInfo

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;
};

The parser can be asked to collect Node informations, i.e. at what place in the file they were detected. NOTE: This is off by default and not very well tested.

xmlParserNodeInfoPtr

typedef xmlParserNodeInfo *xmlParserNodeInfoPtr;

struct xmlParserNodeInfoSeq

struct xmlParserNodeInfoSeq {
  unsigned long maximum;
  unsigned long length;
  xmlParserNodeInfo* buffer;
};

xmlParserNodeInfoSeqPtr

typedef xmlParserNodeInfoSeq *xmlParserNodeInfoSeqPtr;

enum xmlParserInputState

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,		/* Within 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_SYSTEM_LITERAL,	/* within a SYSTEM value */
    XML_PARSER_EPILOG, 		/* the Misc* after the last end tag */
    XML_PARSER_IGNORE,		/* within an IGNORED section */
    XML_PARSER_PUBLIC_LITERAL 	/* within a PUBLIC value */
} xmlParserInputState;

The parser is now working also as a state based parser. The recursive one use the state info for entities processing.

XML_DETECT_IDS

#define XML_DETECT_IDS		2

Bit in the loadsubset context field to tell to do ID/REFs lookups. Use it to initialize xmlLoadExtDtdDefaultValue.

XML_COMPLETE_ATTRS

#define XML_COMPLETE_ATTRS	4

Bit in the loadsubset context field to tell to do complete the elements attributes lists with the ones defaulted from the DTDs. Use it to initialize xmlLoadExtDtdDefaultValue.

struct xmlParserCtxt

struct xmlParserCtxt {
    struct _xmlSAXHandler *sax;       /* The SAX handler */
    void            *userData;        /* For SAX interface only, used by DOM build */
    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;        /* the declared encoding, if any */
    int            standalone;        /* standalone document */
    int                  html;        /* an HTML(1)/Docbook(2) 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 */
    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 ... */
    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 */
    void              *_private;      /* For user data, libxml won't touch it */

    int                loadsubset;    /* should the external subset be loaded */
    int                linenumbers;   /* set line number in element content */
    void              *catalogs;       /* document's own catalog */
};

The parser context. NOTE This doesn't completely define the parser state, the (current ?) design of the parser uses recursive function calls since this allow and easy mapping from the production rules of the specification to the actual code. The drawback is that the actual function call also reflect the parser state. However most of the parsing routines takes as the only argument the parser context pointer, so migrating to a state based parser for progressive parsing shouldn't be too hard.

struct xmlSAXLocator

struct xmlSAXLocator {
    const xmlChar *(*getPublicId)(void *ctx);
    const xmlChar *(*getSystemId)(void *ctx);
    int (*getLineNumber)(void *ctx);
    int (*getColumnNumber)(void *ctx);
};

A SAX Locator.

resolveEntitySAXFunc ()

xmlParserInputPtr (*resolveEntitySAXFunc)   (void *ctx,
                                             const xmlChar *publicId,
                                             const xmlChar *systemId);

Callback: The entity loader, to control the loading of external entities, the application can either: - override this resolveEntity() callback in the SAX block - or better use the xmlSetExternalEntityLoader() function to set up it's own entity resolution routine

`ctx` :	the user data (XML parser context)
`publicId` :	The public ID of the entity
`systemId` :	The system ID of the entity
Returns :	the xmlParserInputPtr if inlined or NULL for DOM behaviour.

internalSubsetSAXFunc ()

void        (*internalSubsetSAXFunc)        (void *ctx,
                                             const xmlChar *name,
                                             const xmlChar *ExternalID,
                                             const xmlChar *SystemID);

Callback on internal subset declaration.

`ctx` :	the user data (XML parser context)
`name` :	the root element name
`ExternalID` :	the external ID
`SystemID` :	the SYSTEM ID (e.g. filename or URL)

externalSubsetSAXFunc ()

void        (*externalSubsetSAXFunc)        (void *ctx,
                                             const xmlChar *name,
                                             const xmlChar *ExternalID,
                                             const xmlChar *SystemID);

Callback on external subset declaration.

`ctx` :	the user data (XML parser context)
`name` :	the root element name
`ExternalID` :	the external ID
`SystemID` :	the SYSTEM ID (e.g. filename or URL)

getEntitySAXFunc ()

xmlEntityPtr (*getEntitySAXFunc)            (void *ctx,
                                             const xmlChar *name);

Get an entity by name.

`ctx` :	the user data (XML parser context)
`name` :	The entity name
Returns :	the xmlEntityPtr if found.

getParameterEntitySAXFunc ()

xmlEntityPtr (*getParameterEntitySAXFunc)   (void *ctx,
                                             const xmlChar *name);

Get a parameter entity by name.

`ctx` :	the user data (XML parser context)
`name` :	The entity name
Returns :	the xmlEntityPtr if found.

entityDeclSAXFunc ()

void        (*entityDeclSAXFunc)            (void *ctx,
                                             const xmlChar *name,
                                             int type,
                                             const xmlChar *publicId,
                                             const xmlChar *systemId,
                                             xmlChar *content);

An entity definition has been parsed.

`ctx` :	the user data (XML parser context)
`name` :	the entity name
`type` :	the entity type
`publicId` :	The public ID of the entity
`systemId` :	The system ID of the entity
`content` :	the entity value (without processing).

notationDeclSAXFunc ()

void        (*notationDeclSAXFunc)          (void *ctx,
                                             const xmlChar *name,
                                             const xmlChar *publicId,
                                             const xmlChar *systemId);

What to do when a notation declaration has been parsed.

`ctx` :	the user data (XML parser context)
`name` :	The name of the notation
`publicId` :	The public ID of the entity
`systemId` :	The system ID of the entity

attributeDeclSAXFunc ()

void        (*attributeDeclSAXFunc)         (void *ctx,
                                             const xmlChar *elem,
                                             const xmlChar *fullname,
                                             int type,
                                             int def,
                                             const xmlChar *defaultValue,
                                             xmlEnumerationPtr tree);

An attribute definition has been parsed.

`ctx` :	the user data (XML parser context)
`elem` :	the name of the element
`fullname` :	the attribute name
`type` :	the attribute type
`def` :	the type of default value
`defaultValue` :	the attribute default value
`tree` :	the tree of enumerated value set

elementDeclSAXFunc ()

void        (*elementDeclSAXFunc)           (void *ctx,
                                             const xmlChar *name,
                                             int type,
                                             xmlElementContentPtr content);

An element definition has been parsed.

`ctx` :	the user data (XML parser context)
`name` :	the element name
`type` :	the element type
`content` :	the element value tree

unparsedEntityDeclSAXFunc ()

void        (*unparsedEntityDeclSAXFunc)    (void *ctx,
                                             const xmlChar *name,
                                             const xmlChar *publicId,
                                             const xmlChar *systemId,
                                             const xmlChar *notationName);

What to do when an unparsed entity declaration is parsed.

`ctx` :	the user data (XML parser context)
`name` :	The name of the entity
`publicId` :	The public ID of the entity
`systemId` :	The system ID of the entity
`notationName` :	the name of the notation

setDocumentLocatorSAXFunc ()

void        (*setDocumentLocatorSAXFunc)    (void *ctx,
                                             xmlSAXLocatorPtr loc);

Receive the document locator at startup, actually xmlDefaultSAXLocator. Everything is available on the context, so this is useless in our case.

`ctx` :	the user data (XML parser context)
`loc` :	A SAX Locator

startDocumentSAXFunc ()

void        (*startDocumentSAXFunc)         (void *ctx);

Called when the document start being processed.

ctx : the user data (XML parser context)

endDocumentSAXFunc ()

void        (*endDocumentSAXFunc)           (void *ctx);

Called when the document end has been detected.

ctx : the user data (XML parser context)

startElementSAXFunc ()

void        (*startElementSAXFunc)          (void *ctx,
                                             const xmlChar *name,
                                             const xmlChar **atts);

Called when an opening tag has been processed.

`ctx` :	the user data (XML parser context)
`name` :	The element name, including namespace prefix
`atts` :	An array of name/value attributes pairs, NULL terminated

endElementSAXFunc ()

void        (*endElementSAXFunc)            (void *ctx,
                                             const xmlChar *name);

Called when the end of an element has been detected.

`ctx` :	the user data (XML parser context)
`name` :	The element name

attributeSAXFunc ()

void        (*attributeSAXFunc)             (void *ctx,
                                             const xmlChar *name,
                                             const xmlChar *value);

Handle an attribute that has been read by the parser. The default handling is to convert the attribute into an DOM subtree and past it in a new xmlAttr element added to the element.

`ctx` :	the user data (XML parser context)
`name` :	The attribute name, including namespace prefix
`value` :	The attribute value

referenceSAXFunc ()

void        (*referenceSAXFunc)             (void *ctx,
                                             const xmlChar *name);

Called when an entity reference is detected.

`ctx` :	the user data (XML parser context)
`name` :	The entity name

charactersSAXFunc ()

void        (*charactersSAXFunc)            (void *ctx,
                                             const xmlChar *ch,
                                             int len);

Receiving some chars from the parser.

`ctx` :	the user data (XML parser context)
`ch` :	a xmlChar string
`len` :	the number of xmlChar

ignorableWhitespaceSAXFunc ()

void        (*ignorableWhitespaceSAXFunc)   (void *ctx,
                                             const xmlChar *ch,
                                             int len);

Receiving some ignorable whitespaces from the parser. UNUSED: by default the DOM building will use characters.

`ctx` :	the user data (XML parser context)
`ch` :	a xmlChar string
`len` :	the number of xmlChar

processingInstructionSAXFunc ()

void        (*processingInstructionSAXFunc) (void *ctx,
                                             const xmlChar *target,
                                             const xmlChar *data);

A processing instruction has been parsed.

`ctx` :	the user data (XML parser context)
`target` :	the target name
`data` :	the PI data's

commentSAXFunc ()

void        (*commentSAXFunc)               (void *ctx,
                                             const xmlChar *value);

A comment has been parsed.

`ctx` :	the user data (XML parser context)
`value` :	the comment content

cdataBlockSAXFunc ()

void        (*cdataBlockSAXFunc)            (void *ctx,
                                             const xmlChar *value,
                                             int len);

Called when a pcdata block has been parsed.

`ctx` :	the user data (XML parser context)
`value` :	The pcdata content
`len` :	the block length

warningSAXFunc ()

void        (*warningSAXFunc)               (void *ctx,
                                             const char *msg,
                                             ...);

Display and format a warning messages, callback.

`ctx` :	an XML parser context
`msg` :	the message to display/transmit
`...` :	extra parameters for the message display

errorSAXFunc ()

void        (*errorSAXFunc)                 (void *ctx,
                                             const char *msg,
                                             ...);

Display and format an error messages, callback.

`ctx` :	an XML parser context
`msg` :	the message to display/transmit
`...` :	extra parameters for the message display

fatalErrorSAXFunc ()

void        (*fatalErrorSAXFunc)            (void *ctx,
                                             const char *msg,
                                             ...);

Display and format fatal error messages, callback.

`ctx` :	an XML parser context
`msg` :	the message to display/transmit
`...` :	extra parameters for the message display

isStandaloneSAXFunc ()

int         (*isStandaloneSAXFunc)          (void *ctx);

Is this document tagged standalone?

`ctx` :	the user data (XML parser context)
Returns :	1 if true

hasInternalSubsetSAXFunc ()

int         (*hasInternalSubsetSAXFunc)     (void *ctx);

Does this document has an internal subset.

`ctx` :	the user data (XML parser context)
Returns :	1 if true

hasExternalSubsetSAXFunc ()

int         (*hasExternalSubsetSAXFunc)     (void *ctx);

Does this document has an external subset?

`ctx` :	the user data (XML parser context)
Returns :	1 if true

struct xmlSAXHandler

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;
    externalSubsetSAXFunc externalSubset;
    int initialized;
};

A SAX handler is bunch of callbacks called by the parser when processing of the input generate data or structure informations.

xmlExternalEntityLoader ()

xmlParserInputPtr (*xmlExternalEntityLoader)
                                            (const char *URL,
                                             const char *ID,
                                             xmlParserCtxtPtr context);

External entity loaders types.

`URL` :	The System ID of the resource requested
`ID` :	The Public ID of the resource requested
`context` :	the XML parser context
Returns :	the entity input parser.

xmlSubstituteEntitiesDefaultValue

#define     xmlSubstituteEntitiesDefaultValue

Global variable controlling the entity substitution default behavior.

xmlInitParser ()

void        xmlInitParser                   (void);

Initialization function for the XML parser. This is not reentrant. Call once before processing in case of use in multithreaded programs.

xmlCleanupParser ()

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.

xmlParserInputRead ()

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

`in` :	an XML parser input
`len` :	an indicative size for the lookahead
Returns :	the number of xmlChars read, or -1 in case of error, 0 indicate the end of this entity

xmlParserInputGrow ()

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

`in` :	an XML parser input
`len` :	an indicative size for the lookahead
Returns :	the number of xmlChars read, or -1 in case of error, 0 indicate the end of this entity

xmlStrdup ()

xmlChar*    xmlStrdup                       (const xmlChar *cur);

a strdup for array of xmlChar's. Since they are supposed to be encoded in UTF-8 or an encoding with 8bit based chars, we assume a termination mark of '0'.

`cur` :	the input xmlChar *
Returns :	a new xmlChar * or NULL

xmlStrndup ()

xmlChar*    xmlStrndup                      (const xmlChar *cur,
                                             int len);

a strndup for array of xmlChar's

`cur` :	the input xmlChar *
`len` :	the len of `cur`
Returns :	a new xmlChar * or NULL

xmlCharStrndup ()

xmlChar*    xmlCharStrndup                  (const char *cur,
                                             int len);

a strndup for char's to xmlChar's

`cur` :	the input char *
`len` :	the len of `cur`
Returns :	a new xmlChar * or NULL

xmlCharStrdup ()

xmlChar*    xmlCharStrdup                   (const char *cur);

a strdup for char's to xmlChar's

`cur` :	the input char *
Returns :	a new xmlChar * or NULL

xmlStrsub ()

xmlChar*    xmlStrsub                       (const xmlChar *str,
                                             int start,
                                             int len);

Extract a substring of a given string

`str` :	the xmlChar * array (haystack)
`start` :	the index of the first char (zero based)
`len` :	the length of the substring
Returns :	the xmlChar * for the first occurrence or NULL.

xmlStrchr ()

const xmlChar* xmlStrchr                    (const xmlChar *str,
                                             xmlChar val);

a strchr for xmlChar's

`str` :	the xmlChar * array
`val` :	the xmlChar to search
Returns :	the xmlChar * for the first occurrence or NULL.

xmlStrstr ()

const xmlChar* xmlStrstr                    (const xmlChar *str,
                                             const xmlChar *val);

a strstr for xmlChar's

`str` :	the xmlChar * array (haystack)
`val` :	the xmlChar to search (needle)
Returns :	the xmlChar * for the first occurrence or NULL.

xmlStrcasestr ()

const xmlChar* xmlStrcasestr                (const xmlChar *str,
                                             xmlChar *val);

a case-ignoring strstr for xmlChar's

`str` :	the xmlChar * array (haystack)
`val` :	the xmlChar to search (needle)
Returns :	the xmlChar * for the first occurrence or NULL.

xmlStrcmp ()

int         xmlStrcmp                       (const xmlChar *str1,
                                             const xmlChar *str2);

a strcmp for xmlChar's

`str1` :	the first xmlChar *
`str2` :	the second xmlChar *
Returns :	the integer result of the comparison

xmlStrncmp ()

int         xmlStrncmp                      (const xmlChar *str1,
                                             const xmlChar *str2,
                                             int len);

a strncmp for xmlChar's

`str1` :	the first xmlChar *
`str2` :	the second xmlChar *
`len` :	the max comparison length
Returns :	the integer result of the comparison

xmlStrcasecmp ()

int         xmlStrcasecmp                   (const xmlChar *str1,
                                             const xmlChar *str2);

a strcasecmp for xmlChar's

`str1` :	the first xmlChar *
`str2` :	the second xmlChar *
Returns :	the integer result of the comparison

xmlStrncasecmp ()

int         xmlStrncasecmp                  (const xmlChar *str1,
                                             const xmlChar *str2,
                                             int len);

a strncasecmp for xmlChar's

`str1` :	the first xmlChar *
`str2` :	the second xmlChar *
`len` :	the max comparison length
Returns :	the integer result of the comparison

xmlStrEqual ()

int         xmlStrEqual                     (const xmlChar *str1,
                                             const xmlChar *str2);

Check if both string are equal of have same content Should be a bit more readable and faster than xmlStrEqual()

`str1` :	the first xmlChar *
`str2` :	the second xmlChar *
Returns :	1 if they are equal, 0 if they are different

xmlStrlen ()

int         xmlStrlen                       (const xmlChar *str);

length of a xmlChar's string

`str` :	the xmlChar * array
Returns :	the number of xmlChar contained in the ARRAY.

xmlStrcat ()

xmlChar*    xmlStrcat                       (xmlChar *cur,
                                             const xmlChar *add);

a strcat for array of xmlChar's. Since they are supposed to be encoded in UTF-8 or an encoding with 8bit based chars, we assume a termination mark of '0'.

`cur` :	the original xmlChar * array
`add` :	the xmlChar * array added
Returns :	a new xmlChar * containing the concatenated string.

xmlStrncat ()

xmlChar*    xmlStrncat                      (xmlChar *cur,
                                             const xmlChar *add,
                                             int len);

a strncat for array of xmlChar's, it will extend cur with the len first bytes of add.

`cur` :	the original xmlChar * array
`add` :	the xmlChar * array added
`len` :	the length of `add`
Returns :	a new xmlChar *, the original `cur` is reallocated if needed and should not be freed

xmlParseDoc ()

xmlDocPtr   xmlParseDoc                     (xmlChar *cur);

parse an XML in-memory document and build a tree.

`cur` :	a pointer to an array of xmlChar
Returns :	the resulting document tree

xmlParseMemory ()

xmlDocPtr   xmlParseMemory                  (const char *buffer,
                                             int size);

parse an XML in-memory block and build a tree.

`buffer` :	an pointer to a char array
`size` :	the size of the array
Returns :	the resulting document tree

xmlParseFile ()

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.

`filename` :	the filename
Returns :	the resulting document tree if the file was wellformed, NULL otherwise.

xmlSubstituteEntitiesDefault ()

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 behavior SAX::substituteEntities() has to be used for changing that on a file by file basis.

`val` :	int 0 or 1
Returns :	the last value for 0 for no substitution, 1 for substitution.

xmlKeepBlanksDefault ()

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 behavior 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.

`val` :	int 0 or 1
Returns :	the last value for 0 for no substitution, 1 for substitution.

xmlStopParser ()

void        xmlStopParser                   (xmlParserCtxtPtr ctxt);

Blocks further parser processing

ctxt : an XML parser context

xmlPedanticParserDefault ()

int         xmlPedanticParserDefault        (int val);

Set and return the previous value for enabling pedantic warnings.

`val` :	int 0 or 1
Returns :	the last value for 0 for no substitution, 1 for substitution.

xmlLineNumbersDefault ()

int         xmlLineNumbersDefault           (int val);

Set and return the previous value for enabling line numbers in elements contents. This may break on old application and is turned off by default.

`val` :	int 0 or 1
Returns :	the last value for 0 for no substitution, 1 for substitution.

xmlRecoverDoc ()

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

`cur` :	a pointer to an array of xmlChar
Returns :	the resulting document tree

xmlRecoverMemory ()

xmlDocPtr   xmlRecoverMemory                (const 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

`buffer` :	an pointer to a char array
`size` :	the size of the array
Returns :	the resulting document tree

xmlRecoverFile ()

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

`filename` :	the filename
Returns :	the resulting document tree

xmlParseDocument ()

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*)?

`ctxt` :	an XML parser context
Returns :	0, -1 in case of error. the parser context is augmented as a result of the parsing.

xmlParseExtParsedEnt ()

int         xmlParseExtParsedEnt            (xmlParserCtxtPtr ctxt);

parse a general parsed entity An external general parsed entity is well-formed if it matches the production labeled extParsedEnt.

[78] extParsedEnt ::= TextDecl? content

`ctxt` :	an XML parser context
Returns :	0, -1 in case of error. the parser context is augmented as a result of the parsing.

xmlSAXParseDoc ()

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.

`sax` :	the SAX handler block
`cur` :	a pointer to an array of xmlChar
`recovery` :	work in recovery mode, i.e. tries to read no Well Formed documents
Returns :	the resulting document tree

xmlSAXUserParseFile ()

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

`sax` :	a SAX handler
`user_data` :	The user data returned on SAX callbacks
`filename` :	a file name
Returns :	0 in case of success or a error number otherwise

xmlSAXUserParseMemory ()

int         xmlSAXUserParseMemory           (xmlSAXHandlerPtr sax,
                                             void *user_data,
                                             const char *buffer,
                                             int size);

A better SAX parsing routine. parse an XML in-memory buffer and call the given SAX handler routines.

`sax` :	a SAX handler
`user_data` :	The user data returned on SAX callbacks
`buffer` :	an in-memory XML document input
`size` :	the length of the XML document in bytes
Returns :	0 in case of success or a error number otherwise

xmlSAXParseMemory ()

xmlDocPtr   xmlSAXParseMemory               (xmlSAXHandlerPtr sax,
                                             const 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.

`sax` :	the SAX handler block
`buffer` :	an pointer to a char array
`size` :	the size of the array
`recovery` :	work in recovery mode, i.e. tries to read not Well Formed documents
Returns :	the resulting document tree

xmlSAXParseFile ()

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.

`sax` :	the SAX handler block
`filename` :	the filename
`recovery` :	work in recovery mode, i.e. tries to read no Well Formed documents
Returns :	the resulting document tree

xmlSAXParseFileWithData ()

xmlDocPtr   xmlSAXParseFileWithData         (xmlSAXHandlerPtr sax,
                                             const char *filename,
                                             int recovery,
                                             void *data);

User data (void *) is stored within the parser context in the context's _private member, so it is available nearly everywhere in libxml

`sax` :	the SAX handler block
`filename` :	the filename
`recovery` :	work in recovery mode, i.e. tries to read no Well Formed documents
`data` :	the userdata
Returns :	the resulting document tree

xmlSAXParseEntity ()

xmlDocPtr   xmlSAXParseEntity               (xmlSAXHandlerPtr sax,
                                             const char *filename);

parse an XML external entity out of context 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.

[78] extParsedEnt ::= TextDecl? content

This correspond to a "Well Balanced" chunk

`sax` :	the SAX handler block
`filename` :	the filename
Returns :	the resulting document tree

xmlParseEntity ()

xmlDocPtr   xmlParseEntity                  (const char *filename);

parse an XML external entity out of context and build a tree.

[78] extParsedEnt ::= TextDecl? content

This correspond to a "Well Balanced" chunk

`filename` :	the filename
Returns :	the resulting document tree

xmlParseDTD ()

xmlDtdPtr   xmlParseDTD                     (const xmlChar *ExternalID,
                                             const xmlChar *SystemID);

Load and parse an external subset.

`ExternalID` :	a NAME* containing the External ID of the DTD
`SystemID` :	a NAME* containing the URL to the DTD
Returns :	the resulting xmlDtdPtr or NULL in case of error.

xmlSAXParseDTD ()

xmlDtdPtr   xmlSAXParseDTD                  (xmlSAXHandlerPtr sax,
                                             const xmlChar *ExternalID,
                                             const xmlChar *SystemID);

Load and parse an external subset.

`sax` :	the SAX handler block
`ExternalID` :	a NAME* containing the External ID of the DTD
`SystemID` :	a NAME* containing the URL to the DTD
Returns :	the resulting xmlDtdPtr or NULL in case of error.

xmlIOParseDTD ()

xmlDtdPtr   xmlIOParseDTD                   (xmlSAXHandlerPtr sax,
                                             xmlParserInputBufferPtr input,
                                             xmlCharEncoding enc);

Load and parse a DTD

`sax` :	the SAX handler block or NULL
`input` :	an Input Buffer
`enc` :	the charset encoding if known
Returns :	the resulting xmlDtdPtr or NULL in case of error. `input` will be freed at parsing end.

xmlParseBalancedChunkMemory ()

int         xmlParseBalancedChunkMemory     (xmlDocPtr doc,
                                             xmlSAXHandlerPtr sax,
                                             void *user_data,
                                             int depth,
                                             const xmlChar *string,
                                             xmlNodePtr *lst);

Parse a well-balanced chunk of an XML document called by the parser The allowed sequence for the Well Balanced Chunk is the one defined by the content production in the XML grammar:

`doc` :	the document the chunk pertains to
`sax` :	the SAX handler bloc (possibly NULL)
`user_data` :	The user data returned on SAX callbacks (possibly NULL)
`depth` :	Used for loop detection, use 0
`string` :	the input string in UTF8 or ISO-Latin (zero terminated)
`lst` :	the return value for the set of parsed nodes
Returns :	0 if the chunk is well balanced, -1 in case of args problem and the parser error code otherwise

xmlParseExternalEntity ()

int         xmlParseExternalEntity          (xmlDocPtr doc,
                                             xmlSAXHandlerPtr sax,
                                             void *user_data,
                                             int depth,
                                             const xmlChar *URL,
                                             const xmlChar *ID,
                                             xmlNodePtr *lst);

Parse an external general entity An external general parsed entity is well-formed if it matches the production labeled extParsedEnt.

[78] extParsedEnt ::= TextDecl? content

`doc` :	the document the chunk pertains to
`sax` :	the SAX handler bloc (possibly NULL)
`user_data` :	The user data returned on SAX callbacks (possibly NULL)
`depth` :	Used for loop detection, use 0
`URL` :	the URL for the entity to load
`ID` :	the System ID for the entity to load
`lst` :	the return value for the set of parsed nodes
Returns :	0 if the entity is well formed, -1 in case of args problem and the parser error code otherwise

xmlParseCtxtExternalEntity ()

int         xmlParseCtxtExternalEntity      (xmlParserCtxtPtr ctx,
                                             const xmlChar *URL,
                                             const xmlChar *ID,
                                             xmlNodePtr *lst);

Parse an external general entity within an existing parsing context An external general parsed entity is well-formed if it matches the production labeled extParsedEnt.

[78] extParsedEnt ::= TextDecl? content

`ctx` :	the existing parsing context
`URL` :	the URL for the entity to load
`ID` :	the System ID for the entity to load
`lst` :	the return value for the set of parsed nodes
Returns :	0 if the entity is well formed, -1 in case of args problem and the parser error code otherwise

xmlInitParserCtxt ()

void        xmlInitParserCtxt               (xmlParserCtxtPtr ctxt);

Initialize a parser context

ctxt : an XML parser context

xmlClearParserCtxt ()

void        xmlClearParserCtxt              (xmlParserCtxtPtr ctxt);

Clear (release owned resources) and reinitialize a parser context

ctxt : an XML parser context

xmlFreeParserCtxt ()

void        xmlFreeParserCtxt               (xmlParserCtxtPtr ctxt);

Free all the memory used by a parser context. However the parsed document in ctxt->myDoc is not freed.

ctxt : an XML parser context

xmlSetupParserForBuffer ()

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

`ctxt` :	an XML parser context
`buffer` :	a xmlChar * buffer
`filename` :	a file name

xmlCreateDocParserCtxt ()

xmlParserCtxtPtr xmlCreateDocParserCtxt     (xmlChar *cur);

Creates a parser context for an XML in-memory document.

`cur` :	a pointer to an array of xmlChar
Returns :	the new parser context or NULL

xmlGetFeaturesList ()

int         xmlGetFeaturesList              (int *len,
                                             const char **result);

Copy at most *len feature names into the result array

`len` :	the length of the features name array (input/output)
`result` :	an array of string to be filled with the features name.
Returns :	-1 in case or error, or the total number of features, len is updated with the number of strings copied, strings must not be deallocated

xmlGetFeature ()

int         xmlGetFeature                   (xmlParserCtxtPtr ctxt,
                                             const char *name,
                                             void *result);

Read the current value of one feature of this parser instance

`ctxt` :	an XML/HTML parser context
`name` :	the feature name
`result` :	location to store the result
Returns :	-1 in case or error, 0 otherwise

xmlSetFeature ()

int         xmlSetFeature                   (xmlParserCtxtPtr ctxt,
                                             const char *name,
                                             void *value);

Change the current value of one feature of this parser instance

`ctxt` :	an XML/HTML parser context
`name` :	the feature name
`value` :	pointer to the location of the new value
Returns :	-1 in case or error, 0 otherwise

xmlCreatePushParserCtxt ()

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.

`sax` :	a SAX handler
`user_data` :	The user data returned on SAX callbacks
`chunk` :	a pointer to an array of chars
`size` :	number of chars in the array
`filename` :	an optional file name or URI
Returns :	the new parser context or NULL

xmlParseChunk ()

int         xmlParseChunk                   (xmlParserCtxtPtr ctxt,
                                             const char *chunk,
                                             int size,
                                             int terminate);

Parse a Chunk of memory

`ctxt` :	an XML parser context
`chunk` :	an char array
`size` :	the size in byte of the chunk
`terminate` :	last chunk indicator
Returns :	zero if no error, the xmlParserErrors otherwise.

xmlCreateIOParserCtxt ()

xmlParserCtxtPtr xmlCreateIOParserCtxt      (xmlSAXHandlerPtr sax,
                                             void *user_data,
                                             xmlInputReadCallback ioread,
                                             xmlInputCloseCallback ioclose,
                                             void *ioctx,
                                             xmlCharEncoding enc);

Create a parser context for using the XML parser with an existing I/O stream

`sax` :	a SAX handler
`user_data` :	The user data returned on SAX callbacks
`ioread` :	an I/O read function
`ioclose` :	an I/O close function
`ioctx` :	an I/O handler
`enc` :	the charset encoding if known
Returns :	the new parser context or NULL

xmlNewIOInputStream ()

xmlParserInputPtr xmlNewIOInputStream       (xmlParserCtxtPtr ctxt,
                                             xmlParserInputBufferPtr input,
                                             xmlCharEncoding enc);

Create a new input stream structure encapsulating the input into a stream suitable for the parser.

`ctxt` :	an XML parser context
`input` :	an I/O Input
`enc` :	the charset encoding if known
Returns :	the new input stream or NULL

xmlParserFindNodeInfo ()

const xmlParserNodeInfo* xmlParserFindNodeInfo
                                            (const xmlParserCtxtPtr ctxt,
                                             const xmlNodePtr node);

Find the parser node info struct for a given node

`ctxt` :	an XML parser context
`node` :	an XML node within the tree
Returns :	an xmlParserNodeInfo block pointer or NULL

xmlInitNodeInfoSeq ()

void        xmlInitNodeInfoSeq              (xmlParserNodeInfoSeqPtr seq);

-- Initialize (set to initial state) node info sequence

seq : a node info sequence pointer

xmlClearNodeInfoSeq ()

void        xmlClearNodeInfoSeq             (xmlParserNodeInfoSeqPtr seq);

-- Clear (release memory and reinitialize) node info sequence

seq : a node info sequence pointer

xmlParserFindNodeInfoIndex ()

unsigned long xmlParserFindNodeInfoIndex    (const xmlParserNodeInfoSeqPtr seq,
                                             const xmlNodePtr node);

xmlParserFindNodeInfoIndex : Find the index that the info record for the given node is or should be at in a sorted sequence

`seq` :	a node info sequence pointer
`node` :	an XML node pointer
Returns :	a long indicating the position of the record

xmlParserAddNodeInfo ()

void        xmlParserAddNodeInfo            (xmlParserCtxtPtr ctxt,
                                             const xmlParserNodeInfoPtr info);

Insert node info record into the sorted sequence

`ctxt` :	an XML parser context
`info` :	a node info sequence pointer

xmlSetExternalEntityLoader ()

void        xmlSetExternalEntityLoader      (xmlExternalEntityLoader f);

Changes the defaultexternal entity resolver function for the application

f : the new entity resolver function

xmlGetExternalEntityLoader ()

xmlExternalEntityLoader xmlGetExternalEntityLoader
                                            (void);

Get the default external entity resolver function for the application

Returns :

the xmlExternalEntityLoader function pointer

xmlLoadExternalEntity ()

xmlParserInputPtr xmlLoadExternalEntity     (const char *URL,
                                             const char *ID,
                                             xmlParserCtxtPtr ctxt);

Load an external entity, note that the use of this function for unparsed entities may generate problems TODO: a more generic External entity API must be designed

`URL` :	the URL for the entity to load
`ID` :	the Public ID for the entity to load
`ctxt` :	the context in which the entity is called or NULL
Returns :	the xmlParserInputPtr or NULL

parser

Name

Synopsis

Description

Details

XML_DEFAULT_VERSION

xmlParserInputDeallocate ()

struct xmlParserInput

struct xmlParserNodeInfo

xmlParserNodeInfoPtr

struct xmlParserNodeInfoSeq

xmlParserNodeInfoSeqPtr

enum xmlParserInputState

XML_DETECT_IDS

XML_COMPLETE_ATTRS

struct xmlParserCtxt

struct xmlSAXLocator

resolveEntitySAXFunc ()

internalSubsetSAXFunc ()

externalSubsetSAXFunc ()

getEntitySAXFunc ()

getParameterEntitySAXFunc ()

entityDeclSAXFunc ()

notationDeclSAXFunc ()

attributeDeclSAXFunc ()

elementDeclSAXFunc ()

unparsedEntityDeclSAXFunc ()

setDocumentLocatorSAXFunc ()

startDocumentSAXFunc ()

endDocumentSAXFunc ()

startElementSAXFunc ()

endElementSAXFunc ()

attributeSAXFunc ()

referenceSAXFunc ()

charactersSAXFunc ()

ignorableWhitespaceSAXFunc ()

processingInstructionSAXFunc ()

commentSAXFunc ()

cdataBlockSAXFunc ()

warningSAXFunc ()

errorSAXFunc ()

fatalErrorSAXFunc ()

isStandaloneSAXFunc ()

hasInternalSubsetSAXFunc ()

hasExternalSubsetSAXFunc ()

struct xmlSAXHandler

xmlExternalEntityLoader ()

xmlSubstituteEntitiesDefaultValue

xmlInitParser ()

xmlCleanupParser ()

xmlParserInputRead ()

xmlParserInputGrow ()

xmlStrdup ()

xmlStrndup ()

xmlCharStrndup ()

xmlCharStrdup ()

xmlStrsub ()

xmlStrchr ()

xmlStrstr ()

xmlStrcasestr ()

xmlStrcmp ()

xmlStrncmp ()

xmlStrcasecmp ()

xmlStrncasecmp ()

xmlStrEqual ()

xmlStrlen ()

xmlStrcat ()

xmlStrncat ()

xmlParseDoc ()

xmlParseMemory ()

xmlParseFile ()

xmlSubstituteEntitiesDefault ()

xmlKeepBlanksDefault ()

xmlStopParser ()

xmlPedanticParserDefault ()

xmlLineNumbersDefault ()

xmlRecoverDoc ()

xmlRecoverMemory ()

xmlRecoverFile ()

xmlParseDocument ()