| | | Gnome XML Library Reference Manual | |
|---|
tree —
struct xmlParserInputBuffer; typedef xmlParserInputBufferPtr; struct xmlOutputBuffer; typedef xmlOutputBufferPtr; struct xmlParserInput; typedef xmlParserInputPtr; struct xmlParserCtxt; typedef xmlParserCtxtPtr; struct xmlSAXLocator; typedef xmlSAXLocatorPtr; struct xmlSAXHandler; typedef xmlSAXHandlerPtr; struct xmlEntity; typedef xmlEntityPtr; #define BASE_BUFFER_SIZE #define XML_XML_NAMESPACE enum xmlElementType; typedef xmlChar; #define BAD_CAST struct xmlNotation; typedef xmlNotationPtr; enum xmlAttributeType; enum xmlAttributeDefault; struct xmlEnumeration; typedef xmlEnumerationPtr; struct xmlAttribute; typedef xmlAttributePtr; enum xmlElementContentType; enum xmlElementContentOccur; struct xmlElementContent; typedef xmlElementContentPtr; enum xmlElementTypeVal; struct xmlElement; typedef xmlElementPtr; #define XML_LOCAL_NAMESPACE typedef xmlNsType; struct xmlNs; typedef xmlNsPtr; struct xmlDtd; typedef xmlDtdPtr; struct xmlAttr; typedef xmlAttrPtr; struct xmlID; typedef xmlIDPtr; struct xmlRef; typedef xmlRefPtr; enum xmlBufferAllocationScheme; struct xmlBuffer; typedef xmlBufferPtr; struct xmlNode; typedef xmlNodePtr; #define XML_GET_CONTENT (n) #define XML_GET_LINE (n) struct xmlDoc; typedef xmlDocPtr; #define xmlChildrenNode #define xmlRootNode
struct xmlParserInputBuffer {
void* context;
xmlInputReadCallback readcallback;
xmlInputCloseCallback closecallback;
xmlCharEncodingHandlerPtr encoder; /* I18N conversions to UTF-8 */
xmlBufferPtr buffer; /* Local buffer encoded in UTF-8 */
xmlBufferPtr raw; /* if encoder != NULL buffer for raw input */
int compressed; /* -1=unknown, 0=not compressed, 1=compressed */
int error;
};
struct xmlOutputBuffer {
void* context;
xmlOutputWriteCallback writecallback;
xmlOutputCloseCallback closecallback;
xmlCharEncodingHandlerPtr encoder; /* I18N conversions to UTF-8 */
xmlBufferPtr buffer; /* Local buffer encoded in UTF-8 or ISOLatin */
xmlBufferPtr conv; /* if encoder != NULL buffer for output */
int written; /* total number of byte written */
int error;
};
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 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 {
const xmlChar *(*getPublicId)(void *ctx);
const xmlChar *(*getSystemId)(void *ctx);
int (*getLineNumber)(void *ctx);
int (*getColumnNumber)(void *ctx);
};
A SAX Locator.
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 xmlEntity {
void *_private; /* application data */
xmlElementType type; /* XML_ENTITY_DECL, must be second ! */
const xmlChar *name; /* Entity name */
struct _xmlNode *children; /* First child link */
struct _xmlNode *last; /* Last child link */
struct _xmlDtd *parent; /* -> DTD */
struct _xmlNode *next; /* next sibling link */
struct _xmlNode *prev; /* previous sibling link */
struct _xmlDoc *doc; /* the containing document */
xmlChar *orig; /* content without ref substitution */
xmlChar *content; /* content or ndata if unparsed */
int length; /* the content length */
xmlEntityType etype; /* The entity type */
const xmlChar *ExternalID; /* External identifier for PUBLIC */
const xmlChar *SystemID; /* URI for a SYSTEM or PUBLIC Entity */
struct _xmlEntity *nexte; /* unused */
const xmlChar *URI; /* the full URI as computed */
int owner; /* does the entity own the childrens */
};
#define XML_XML_NAMESPACE
This is the namespace for the special xml: prefix predefined in the XML Namespace specification.
typedef enum {
XML_ELEMENT_NODE= 1,
XML_ATTRIBUTE_NODE= 2,
XML_TEXT_NODE= 3,
XML_CDATA_SECTION_NODE= 4,
XML_ENTITY_REF_NODE= 5,
XML_ENTITY_NODE= 6,
XML_PI_NODE= 7,
XML_COMMENT_NODE= 8,
XML_DOCUMENT_NODE= 9,
XML_DOCUMENT_TYPE_NODE= 10,
XML_DOCUMENT_FRAG_NODE= 11,
XML_NOTATION_NODE= 12,
XML_HTML_DOCUMENT_NODE= 13,
XML_DTD_NODE= 14,
XML_ELEMENT_DECL= 15,
XML_ATTRIBUTE_DECL= 16,
XML_ENTITY_DECL= 17,
XML_NAMESPACE_DECL= 18,
XML_XINCLUDE_START= 19,
XML_XINCLUDE_END= 20
#ifdef LIBXML_DOCB_ENABLED
,XML_DOCB_DOCUMENT_NODE= 21
#endif
} xmlElementType;
typedef unsigned char xmlChar;
This is a basic byte in an UTF-8 encoded string. It's unsigned allowing to pinpoint case where char * are assigned to xmlChar * (possibly making serialization back impossible).
struct xmlNotation {
const xmlChar *name; /* Notation name */
const xmlChar *PublicID; /* Public identifier, if any */
const xmlChar *SystemID; /* System identifier, if any */
};
A DTD Notation definition.
typedef enum {
XML_ATTRIBUTE_CDATA = 1,
XML_ATTRIBUTE_ID,
XML_ATTRIBUTE_IDREF ,
XML_ATTRIBUTE_IDREFS,
XML_ATTRIBUTE_ENTITY,
XML_ATTRIBUTE_ENTITIES,
XML_ATTRIBUTE_NMTOKEN,
XML_ATTRIBUTE_NMTOKENS,
XML_ATTRIBUTE_ENUMERATION,
XML_ATTRIBUTE_NOTATION
} xmlAttributeType;
A DTD Attribute type definition.
typedef enum {
XML_ATTRIBUTE_NONE = 1,
XML_ATTRIBUTE_REQUIRED,
XML_ATTRIBUTE_IMPLIED,
XML_ATTRIBUTE_FIXED
} xmlAttributeDefault;
A DTD Attribute default definition.
struct xmlEnumeration {
struct _xmlEnumeration *next; /* next one */
const xmlChar *name; /* Enumeration name */
};
List structure used when there is an enumeration in DTDs.
struct xmlAttribute {
void *_private; /* application data */
xmlElementType type; /* XML_ATTRIBUTE_DECL, must be second ! */
const xmlChar *name; /* Attribute name */
struct _xmlNode *children; /* NULL */
struct _xmlNode *last; /* NULL */
struct _xmlDtd *parent; /* -> DTD */
struct _xmlNode *next; /* next sibling link */
struct _xmlNode *prev; /* previous sibling link */
struct _xmlDoc *doc; /* the containing document */
struct _xmlAttribute *nexth; /* next in hash table */
xmlAttributeType atype; /* The attribute type */
xmlAttributeDefault def; /* the default */
const xmlChar *defaultValue; /* or the default value */
xmlEnumerationPtr tree; /* or the enumeration tree if any */
const xmlChar *prefix; /* the namespace prefix if any */
const xmlChar *elem; /* Element holding the attribute */
};
An Attribute declaration in a DTD.
typedef enum {
XML_ELEMENT_CONTENT_PCDATA = 1,
XML_ELEMENT_CONTENT_ELEMENT,
XML_ELEMENT_CONTENT_SEQ,
XML_ELEMENT_CONTENT_OR
} xmlElementContentType;
Possible definitions of element content types.
typedef enum {
XML_ELEMENT_CONTENT_ONCE = 1,
XML_ELEMENT_CONTENT_OPT,
XML_ELEMENT_CONTENT_MULT,
XML_ELEMENT_CONTENT_PLUS
} xmlElementContentOccur;
Possible definitions of element content occurrences.
struct xmlElementContent {
xmlElementContentType type; /* PCDATA, ELEMENT, SEQ or OR */
xmlElementContentOccur ocur; /* ONCE, OPT, MULT or PLUS */
const xmlChar *name; /* Element name */
struct _xmlElementContent *c1; /* first child */
struct _xmlElementContent *c2; /* second child */
struct _xmlElementContent *parent; /* parent */
const xmlChar *prefix; /* Namespace prefix */
};
An XML Element content as stored after parsing an element definition in a DTD.
typedef enum {
XML_ELEMENT_TYPE_UNDEFINED = 0,
XML_ELEMENT_TYPE_EMPTY = 1,
XML_ELEMENT_TYPE_ANY,
XML_ELEMENT_TYPE_MIXED,
XML_ELEMENT_TYPE_ELEMENT
} xmlElementTypeVal;
The different possibilities for an element content type.
struct xmlElement {
void *_private; /* application data */
xmlElementType type; /* XML_ELEMENT_DECL, must be second ! */
const xmlChar *name; /* Element name */
struct _xmlNode *children; /* NULL */
struct _xmlNode *last; /* NULL */
struct _xmlDtd *parent; /* -> DTD */
struct _xmlNode *next; /* next sibling link */
struct _xmlNode *prev; /* previous sibling link */
struct _xmlDoc *doc; /* the containing document */
xmlElementTypeVal etype; /* The type */
xmlElementContentPtr content; /* the allowed element content */
xmlAttributePtr attributes; /* List of the declared attributes */
const xmlChar *prefix; /* the namespace prefix if any */
#ifdef LIBXML_REGEXP_ENABLED
xmlRegexpPtr contModel; /* the validating regexp */
#else
void *contModel;
#endif
};
An XML Element declaration from a DTD.
struct xmlNs {
struct _xmlNs *next; /* next Ns link for this node */
xmlNsType type; /* global or local */
const xmlChar *href; /* URL for the namespace */
const xmlChar *prefix; /* prefix for the namespace */
void *_private; /* application data */
};
An XML namespace. Note that prefix == NULL is valid, it defines the default namespace within the subtree (until overridden).
xmlNsType is unified with xmlElementType.
struct xmlDtd {
void *_private; /* application data */
xmlElementType type; /* XML_DTD_NODE, must be second ! */
const xmlChar *name; /* Name of the DTD */
struct _xmlNode *children; /* the value of the property link */
struct _xmlNode *last; /* last child link */
struct _xmlDoc *parent; /* child->parent link */
struct _xmlNode *next; /* next sibling link */
struct _xmlNode *prev; /* previous sibling link */
struct _xmlDoc *doc; /* the containing document */
/* End of common part */
void *notations; /* Hash table for notations if any */
void *elements; /* Hash table for elements if any */
void *attributes; /* Hash table for attributes if any */
void *entities; /* Hash table for entities if any */
const xmlChar *ExternalID; /* External identifier for PUBLIC DTD */
const xmlChar *SystemID; /* URI for a SYSTEM or PUBLIC DTD */
void *pentities; /* Hash table for param entities if any */
};
An XML DTD, as defined by <!DOCTYPE ... There is actually one for the internal subset and for the external subset.
struct xmlAttr {
void *_private; /* application data */
xmlElementType type; /* XML_ATTRIBUTE_NODE, must be second ! */
const xmlChar *name; /* the name of the property */
struct _xmlNode *children; /* the value of the property */
struct _xmlNode *last; /* NULL */
struct _xmlNode *parent; /* child->parent link */
struct _xmlAttr *next; /* next sibling link */
struct _xmlAttr *prev; /* previous sibling link */
struct _xmlDoc *doc; /* the containing document */
xmlNs *ns; /* pointer to the associated namespace */
xmlAttributeType atype; /* the attribute type if validating */
void *psvi; /* for type/PSVI informations */
};
An attribute on an XML node.
struct xmlID {
struct _xmlID *next; /* next ID */
const xmlChar *value; /* The ID name */
xmlAttrPtr attr; /* The attribute holding it */
const xmlChar *name; /* The attribute if attr is not available */
int lineno; /* The line number if attr is not available */
};
An XML ID instance.
struct xmlRef {
struct _xmlRef *next; /* next Ref */
const xmlChar *value; /* The Ref name */
xmlAttrPtr attr; /* The attribute holding it */
const xmlChar *name; /* The attribute if attr is not available */
int lineno; /* The line number if attr is not available */
};
An XML IDREF instance.
typedef enum {
XML_BUFFER_ALLOC_DOUBLEIT,
XML_BUFFER_ALLOC_EXACT,
XML_BUFFER_ALLOC_IMMUTABLE
} xmlBufferAllocationScheme;
A buffer allocation scheme can be defined to either match exactly the need or double it's allocated size each time it is found too small.
struct xmlBuffer {
xmlChar *content; /* The buffer content UTF8 */
unsigned int use; /* The buffer size used */
unsigned int size; /* The buffer size */
xmlBufferAllocationScheme alloc; /* The realloc method */
};
A buffer structure.
struct xmlNode {
void *_private; /* application data */
xmlElementType type; /* type number, must be second ! */
const xmlChar *name; /* the name of the node, or the entity */
struct _xmlNode *children; /* parent->childs link */
struct _xmlNode *last; /* last child link */
struct _xmlNode *parent; /* child->parent link */
struct _xmlNode *next; /* next sibling link */
struct _xmlNode *prev; /* previous sibling link */
struct _xmlDoc *doc; /* the containing document */
/* End of common part */
xmlNs *ns; /* pointer to the associated namespace */
xmlChar *content; /* the content */
struct _xmlAttr *properties;/* properties list */
xmlNs *nsDef; /* namespace definitions on this node */
void *psvi; /* for type/PSVI informations */
unsigned short line; /* line number */
unsigned short extra; /* extra data for XPath/XSLT */
};
A node in an XML tree.
#define XML_GET_LINE(n)
Macro to extract the line number of an element node. This will work only if line numbering is activated by calling xmlLineNumbersDefault(1) before parsing.
| n: |
struct xmlDoc {
void *_private; /* application data */
xmlElementType type; /* XML_DOCUMENT_NODE, must be second ! */
char *name; /* name/filename/URI of the document */
struct _xmlNode *children; /* the document tree */
struct _xmlNode *last; /* last child link */
struct _xmlNode *parent; /* child->parent link */
struct _xmlNode *next; /* next sibling link */
struct _xmlNode *prev; /* previous sibling link */
struct _xmlDoc *doc; /* autoreference to itself */
/* End of common part */
int compression;/* level of zlib compression */
int standalone; /* standalone document (no external refs) */
struct _xmlDtd *intSubset; /* the document internal subset */
struct _xmlDtd *extSubset; /* the document external subset */
struct _xmlNs *oldNs; /* Global namespace, the old way */
const xmlChar *version; /* the XML version string */
const xmlChar *encoding; /* external initial encoding, if any */
void *ids; /* Hash table for ID attributes if any */
void *refs; /* Hash table for IDREFs attributes if any */
const xmlChar *URL; /* The URI for that document */
int charset; /* encoding of the in-memory content
actually an xmlCharEncoding */
struct _xmlDict *dict; /* dict used to allocate names or NULL */
void *psvi; /* for type/PSVI informations */
};
An XML document.
| << catalog | globals >> |