parser

parser —

Synopsis




#define     XML_DEFAULT_VERSION
void        (*xmlParserInputDeallocate)     (xmlChar *str);
struct      xmlParserInput;
struct      xmlParserNodeInfo;
typedef     xmlParserNodeInfoPtr;
struct      xmlParserNodeInfoSeq;
typedef     xmlParserNodeInfoSeqPtr;
enum        xmlParserInputState;
#define     XML_DETECT_IDS
#define     XML_COMPLETE_ATTRS
#define     XML_SKIP_IDS
struct      xmlParserCtxt;
struct      xmlSAXLocator;
xmlParserInputPtr (*resolveEntitySAXFunc)   (void *ctx,
                                             const xmlChar *publicId,
                                             const xmlChar *systemId);
void        (*internalSubsetSAXFunc)        (void *ctx,
                                             const xmlChar *name,
                                             const xmlChar *ExternalID,
                                             const xmlChar *SystemID);
void        (*externalSubsetSAXFunc)        (void *ctx,
                                             const xmlChar *name,
                                             const xmlChar *ExternalID,
                                             const xmlChar *SystemID);
xmlEntityPtr (*getEntitySAXFunc)            (void *ctx,
                                             const xmlChar *name);
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 *fullname,
                                             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        (*setDocumentLocatorSAXFunc)    (void *ctx,
                                             xmlSAXLocatorPtr loc);
void        (*startDocumentSAXFunc)         (void *ctx);
void        (*endDocumentSAXFunc)           (void *ctx);
void        (*startElementSAXFunc)          (void *ctx,
                                             const xmlChar *name,
                                             const xmlChar **atts);
void        (*endElementSAXFunc)            (void *ctx,
                                             const xmlChar *name);
void        (*attributeSAXFunc)             (void *ctx,
                                             const xmlChar *name,
                                             const xmlChar *value);
void        (*referenceSAXFunc)             (void *ctx,
                                             const xmlChar *name);
void        (*charactersSAXFunc)            (void *ctx,
                                             const xmlChar *ch,
                                             int len);
void        (*ignorableWhitespaceSAXFunc)   (void *ctx,
                                             const xmlChar *ch,
                                             int len);
void        (*processingInstructionSAXFunc) (void *ctx,
                                             const xmlChar *target,
                                             const xmlChar *data);
void        (*commentSAXFunc)               (void *ctx,
                                             const xmlChar *value);
void        (*cdataBlockSAXFunc)            (void *ctx,
                                             const xmlChar *value,
                                             int len);
void        (*warningSAXFunc)               (void *ctx,
                                             const char *msg,
                                             ...);
void        (*errorSAXFunc)                 (void *ctx,
                                             const char *msg,
                                             ...);
void        (*fatalErrorSAXFunc)            (void *ctx,
                                             const char *msg,
                                             ...);
int         (*isStandaloneSAXFunc)          (void *ctx);
int         (*hasInternalSubsetSAXFunc)     (void *ctx);
int         (*hasExternalSubsetSAXFunc)     (void *ctx);
#define     XML_SAX2_MAGIC
void        (*startElementNsSAX2Func)       (void *ctx,
                                             const xmlChar *localname,
                                             const xmlChar *prefix,
                                             const xmlChar *URI,
                                             int nb_namespaces,
                                             const xmlChar **namespaces,
                                             int nb_attributes,
                                             int nb_defaulted,
                                             const xmlChar **attributes);
void        (*endElementNsSAX2Func)         (void *ctx,
                                             const xmlChar *localname,
                                             const xmlChar *prefix,
                                             const xmlChar *URI);
struct      xmlSAXHandler;
struct      xmlSAXHandlerV1;
typedef     xmlSAXHandlerV1Ptr;
xmlParserInputPtr (*xmlExternalEntityLoader)
                                            (const char *URL,
                                             const char *ID,
                                             xmlParserCtxtPtr context);
enum        xmlParserOption;

Description

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 */
    /*
     * NOTE: consumed is only tested for equality in the parser code,
     *       so even if there is an overflow this should not give troubles
     *       for parsing very large instances.
     */
    unsigned long 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 */
    int id;                           /* an unique identifier for the entity */
};

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.


XML_SKIP_IDS

#define XML_SKIP_IDS		8

Bit in the loadsubset context field to tell to not do ID/REFs registration. Used to initialize xmlLoadExtDtdDefaultValue in some special cases.


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 */
    const xmlChar     *name;          /* Current parsed Node */
    int                nameNr;        /* Depth of the parsing stack */
    int                nameMax;       /* Max depth of the parsing stack */
    const 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 */
    const 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 */
    int                recovery;      /* run in recovery mode */
    int                progressive;   /* is this a progressive parsing */
    xmlDictPtr         dict;          /* dictionnary for the parser */
    const xmlChar *   *atts;          /* array for the attributes callbacks */
    int                maxatts;       /* the size of the array */
    int                docdict;       /* use strings from dict to build tree */

    /*
     * pre-interned strings
     */
    const xmlChar *str_xml;
    const xmlChar *str_xmlns;
    const xmlChar *str_xml_ns;

    /*
     * Everything below is used only by the new SAX mode
     */
    int                sax2;          /* operating in the new SAX mode */
    int                nsNr;          /* the number of inherited namespaces */
    int                nsMax;         /* the size of the arrays */
    const xmlChar *   *nsTab;         /* the array of prefix/namespace name */
    int               *attallocs;     /* which attribute were allocated */
    void *            *pushTab;       /* array of data for push */
    xmlHashTablePtr    attsDefault;   /* defaulted attributes if any */
    xmlHashTablePtr    attsSpecial;   /* non-CDATA attributes if any */
    int                nsWellFormed;  /* is the document XML Nanespace okay */
    int                options;       /* Extra options */

    /*
     * Those fields are needed only for treaming parsing so far
     */
    int               dictNames;    /* Use dictionary names for the tree */
    int               freeElemsNr;  /* number of freed element nodes */
    xmlNodePtr        freeElems;    /* List of freed element nodes */
    int               freeAttrsNr;  /* number of freed attributes nodes */
    xmlAttrPtr        freeAttrs;    /* List of freed attributes nodes */

    /*
     * the complete error informations for the last error.
     */
    xmlError          lastError;
};

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. Note: so far fatalError() SAX callbacks are not used, error() get all the callbacks for errors.

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

XML_SAX2_MAGIC

#define XML_SAX2_MAGIC 0xDEEDBEAF

Special constant found in SAX2 blocks initialized fields


startElementNsSAX2Func ()

void        (*startElementNsSAX2Func)       (void *ctx,
                                             const xmlChar *localname,
                                             const xmlChar *prefix,
                                             const xmlChar *URI,
                                             int nb_namespaces,
                                             const xmlChar **namespaces,
                                             int nb_attributes,
                                             int nb_defaulted,
                                             const xmlChar **attributes);

SAX2 callback when an element start has been detected by the parser. It provides the namespace informations for the element, as well as the new namespace declarations on the element.

ctx: the user data (XML parser context)
localname: the local name of the element
prefix: the element namespace prefix if available
URI: the element namespace name if available
nb_namespaces: number of namespace definitions on that node
namespaces: pointer to the array of prefix/URI pairs namespace definitions
nb_attributes: the number of attributes on that node
nb_defaulted: the number of defaulted attributes. The defaulted ones are at the end of the array
attributes: pointer to the array of (localname/prefix/URI/value/end) attribute values.

endElementNsSAX2Func ()

void        (*endElementNsSAX2Func)         (void *ctx,
                                             const xmlChar *localname,
                                             const xmlChar *prefix,
                                             const xmlChar *URI);

SAX2 callback when an element end has been detected by the parser. It provides the namespace informations for the element.

ctx: the user data (XML parser context)
localname: the local name of the element
prefix: the element namespace prefix if available
URI: the element namespace name if available

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; /* unused error() get all the errors */
    getParameterEntitySAXFunc getParameterEntity;
    cdataBlockSAXFunc cdataBlock;
    externalSubsetSAXFunc externalSubset;
    unsigned int initialized;
    /* The following fields are extensions available only on version 2 */
    void *_private;
    startElementNsSAX2Func startElementNs;
    endElementNsSAX2Func endElementNs;
    xmlStructuredErrorFunc serror;
};

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


struct xmlSAXHandlerV1

struct xmlSAXHandlerV1 {

    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; /* unused error() get all the errors */
    getParameterEntitySAXFunc getParameterEntity;
    cdataBlockSAXFunc cdataBlock;
    externalSubsetSAXFunc externalSubset;
    unsigned int initialized;
};


xmlSAXHandlerV1Ptr

typedef xmlSAXHandlerV1 *xmlSAXHandlerV1Ptr;


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.

enum xmlParserOption

typedef enum {
    XML_PARSE_RECOVER	= 1<<0,	/* recover on errors */
    XML_PARSE_NOENT	= 1<<1,	/* substitute entities */
    XML_PARSE_DTDLOAD	= 1<<2,	/* load the external subset */
    XML_PARSE_DTDATTR	= 1<<3,	/* default DTD attributes */
    XML_PARSE_DTDVALID	= 1<<4,	/* validate with the DTD */
    XML_PARSE_NOERROR	= 1<<5,	/* suppress error reports */
    XML_PARSE_NOWARNING	= 1<<6,	/* suppress warning reports */
    XML_PARSE_PEDANTIC	= 1<<7,	/* pedantic error reporting */
    XML_PARSE_NOBLANKS	= 1<<8,	/* remove blank nodes */
    XML_PARSE_SAX1	= 1<<9,	/* use the SAX1 interface internally */
    XML_PARSE_XINCLUDE	= 1<<10,/* Implement XInclude substitition  */
    XML_PARSE_NONET	= 1<<11,/* Forbid network access */
    XML_PARSE_NODICT	= 1<<12,/* Do not reuse the context dictionnary */
    XML_PARSE_NSCLEAN	= 1<<13,/* remove redundant namespaces declarations */
    XML_PARSE_NOCDATA	= 1<<14 /* merge CDATA as text nodes */
} xmlParserOption;

This is the set of XML parser options that can be passed down to the xmlReadDoc() and similar calls.