| ctxt: | an HTML parser context |
| Returns: | 0, -1 in case of error. the parser context is augmented as a result of the parsing. |
void htmlParseElement (htmlParserCtxtPtr ctxt)
-
parse an HTML element, this is highly recursive [39] element ::= EmptyElemTag | STag content ETag [41] Attribute ::= Name Eq AttValue
+parse an HTML element, this is highly recursive this is kept for compatibility with previous code versions [39] element ::= EmptyElemTag | STag content ETag [41] Attribute ::= Name Eq AttValue
| ctxt: | an HTML parser context |
const htmlEntityDesc * htmlParseEntityRef (htmlParserCtxtPtr ctxt,
const xmlChar ** str)
diff --git a/doc/devhelp/libxml2-tree.html b/doc/devhelp/libxml2-tree.html index c3702036..2c254a32 100644 --- a/doc/devhelp/libxml2-tree.html +++ b/doc/devhelp/libxml2-tree.html @@ -781,7 +781,11 @@ void xmlFreeNsList (xmlError lastError xmlParserMode parseMode : the parser mode unsigned long nbentities : number of entities references - unsigned long sizeentities : size of parsed entities + unsigned long sizeentities : size of parsed entities for use by HTML non-recursive parser + xmlParserNodeInfo * nodeInfo : Current NodeInfo + int nodeInfoNr : Depth of the parsing stack + int nodeInfoMax : Max depth of the parsing stack + xmlParserNodeInfo * nodeInfoTab : array of nodeInfos } xmlParserCtxt;
| buf: | the XML buffer output |
| doc: | the document |
| cur: | the current node |
| level: | the imbrication level for indenting |
| format: | is formatting allowed |
| encoding: | an optional encoding string |
xmlChar * xmlNodeGetBase (xmlDocPtr doc,
xmlNodePtr cur)
-
Searches for the BASE URL. The code should work on both XML and HTML document even if base mechanisms are completely different. It returns the base as defined in RFC 2396 sections 5.1.1. Base URI within Document Content and 5.1.2. Base URI from the Encapsulating Entity However it does not return the document base (5.1.3), use xmlDocumentGetBase() for this
+Searches for the BASE URL. The code should work on both XML and HTML document even if base mechanisms are completely different. It returns the base as defined in RFC 2396 sections 5.1.1. Base URI within Document Content and 5.1.2. Base URI from the Encapsulating Entity However it does not return the document base (5.1.3), use doc->URL in this case
| doc: | the document the node pertains to |
| cur: | the node being checked |
| Returns: | a pointer to the base URL, or NULL if not found It's up to the caller to free the memory with xmlFree(). |
xmlChar * xmlNodeGetContent (xmlNodePtr cur)
diff --git a/doc/devhelp/libxml2.devhelp b/doc/devhelp/libxml2.devhelp index 81529794..3e632b62 100644 --- a/doc/devhelp/libxml2.devhelp +++ b/doc/devhelp/libxml2.devhelp @@ -306,6 +306,7 @@+ diff --git a/doc/html/libxml-HTMLparser.html b/doc/html/libxml-HTMLparser.html index 0bc7dbd5..09c959b6 100644 --- a/doc/html/libxml-HTMLparser.html +++ b/doc/html/libxml-HTMLparser.html @@ -93,6 +93,7 @@ A:link, A:visited, A:active { text-decoration: underline } HTML_PARSE_PEDANTIC = 128 : pedantic error reporting HTML_PARSE_NOBLANKS = 256 : remove blank nodes HTML_PARSE_NONET = 2048 : Forbid network access + HTML_PARSE_NOIMPLIED = 8192 : Do not add implied html/body... elements HTML_PARSE_COMPACT = 65536 : compact small text nodes }
Enum htmlStatus {
@@ -157,7 +158,7 @@ A:link, A:visited, A:active { text-decoration: underline }
cur: a pointer to an array of xmlChar encoding: a free form C string describing the HTML document encoding, or NULL Returns: the resulting document tree
Function: htmlParseDocument
int htmlParseDocument (htmlParserCtxtPtr ctxt)
parse an HTML document (and build a tree if using the standard SAX interface).
ctxt: an HTML parser context Returns: 0, -1 in case of error. the parser context is augmented as a result of the parsing.
Function: htmlParseElement
void htmlParseElement (htmlParserCtxtPtr ctxt)
-
parse an HTML element, this is highly recursive [39] element ::= EmptyElemTag | STag content ETag [41] Attribute ::= Name Eq AttValue
+parse an HTML element, this is highly recursive this is kept for compatibility with previous code versions [39] element ::= EmptyElemTag | STag content ETag [41] Attribute ::= Name Eq AttValue
| ctxt: | an HTML parser context |
const htmlEntityDesc * htmlParseEntityRef (htmlParserCtxtPtr ctxt,
const xmlChar ** str)
parse an HTML ENTITY references [68] EntityRef ::= '&' Name ';'
| ctxt: | an HTML parser context |
| str: | location to store the entity name |
| Returns: | the associated htmlEntityDescPtr if found, or NULL otherwise, if non-NULL *str will have to be freed by the caller. |
htmlDocPtr htmlParseFile (const char * filename,
const char * encoding)
diff --git a/doc/html/libxml-tree.html b/doc/html/libxml-tree.html index 6f916056..50cc4471 100644 --- a/doc/html/libxml-tree.html +++ b/doc/html/libxml-tree.html @@ -563,7 +563,11 @@ A:link, A:visited, A:active { text-decoration: underline } xmlError lastError xmlParserMode parseMode : the parser mode unsigned long nbentities : number of entities references - unsigned long sizeentities : size of parsed entities + unsigned long sizeentities : size of parsed entities for use by HTML + xmlParserNodeInfo * nodeInfo : Current NodeInfo + int nodeInfoNr : Depth of the parsing stack + int nodeInfoMax : Max depth of the parsing stack + xmlParserNodeInfo * nodeInfoTab : array of nodeInfos }
Structure xmlParserInput
struct _xmlParserInput { xmlParserInputBufferPtr buf : UTF-8 encoded buffer const char * filename : The file analyzed, if any @@ -860,7 +864,7 @@ A:link, A:visited, A:active { text-decoration: underline }
buf: the XML buffer output doc: the document cur: the current node level: the imbrication level for indenting format: is formatting allowed Returns: the number of bytes written to the buffer or -1 in case of error Function: xmlNodeDumpOutput
void xmlNodeDumpOutput (xmlOutputBufferPtr buf,
xmlDocPtr doc,
xmlNodePtr cur,
int level,
int format,
const char * encoding)
Dump an XML node, recursive behaviour, children are printed too. Note that @format = 1 provide node indenting only if xmlIndentTreeOutput = 1 or xmlKeepBlanksDefault(0) was called
buf: the XML buffer output doc: the document cur: the current node level: the imbrication level for indenting format: is formatting allowed encoding: an optional encoding string Function: xmlNodeGetBase
xmlChar * xmlNodeGetBase (xmlDocPtr doc,
xmlNodePtr cur)
-Searches for the BASE URL. The code should work on both XML and HTML document even if base mechanisms are completely different. It returns the base as defined in RFC 2396 sections 5.1.1. Base URI within Document Content and 5.1.2. Base URI from the Encapsulating Entity However it does not return the document base (5.1.3), use xmlDocumentGetBase() for this
+
Searches for the BASE URL. The code should work on both XML and HTML document even if base mechanisms are completely different. It returns the base as defined in RFC 2396 sections 5.1.1. Base URI within Document Content and 5.1.2. Base URI from the Encapsulating Entity However it does not return the document base (5.1.3), use doc->URL in this case
| doc: | the document the node pertains to |
| cur: | the node being checked |
| Returns: | a pointer to the base URL, or NULL if not found It's up to the caller to free the memory with xmlFree(). |
xmlChar * xmlNodeGetContent (xmlNodePtr cur)
Read the value of a node, this can be either the text carried directly by this node if it's a TEXT node or the aggregate string of the values carried by this node child's (TEXT and ENTITY_REF). Entity references are substituted.
| cur: | the node being read |
| Returns: | a new #xmlChar * or NULL if no content is available. It's up to the caller to free the memory with xmlFree(). |
xmlChar * xmlNodeGetLang (xmlNodePtr cur)
diff --git a/doc/libxml2-api.xml b/doc/libxml2-api.xml index 5cf19cb9..046be3d5 100644 --- a/doc/libxml2-api.xml +++ b/doc/libxml2-api.xml @@ -42,6 +42,7 @@+ @@ -4593,6 +4594,7 @@ + @@ -6339,7 +6341,11 @@ actually an xmlCharEncoding'/> - + + + + + @@ -7647,7 +7653,7 @@ Could we use @subtypes for this?'/> @@ -11621,7 +11627,7 @@ Could we use @subtypes for this?'/> defined(LIBXML_HTML_ENABLED) -parse an HTML element, this is highly recursive [39] element ::= EmptyElemTag | STag content ETag [41] Attribute ::= Name Eq AttValue +parse an HTML element, this is highly recursive this is kept for compatibility with previous code versions [39] element ::= EmptyElemTag | STag content ETag [41] Attribute ::= Name Eq AttValue - Searches for the BASE URL. The code should work on both XML and HTML document even if base mechanisms are completely different. It returns the base as defined in RFC 2396 sections 5.1.1. Base URI within Document Content and 5.1.2. Base URI from the Encapsulating Entity However it does not return the document base (5.1.3), use xmlDocumentGetBase() for this +Searches for the BASE URL. The code should work on both XML and HTML document even if base mechanisms are completely different. It returns the base as defined in RFC 2396 sections 5.1.1. Base URI within Document Content and 5.1.2. Base URI from the Encapsulating Entity However it does not return the document base (5.1.3), use doc->URL in this case diff --git a/doc/libxml2-refs.xml b/doc/libxml2-refs.xml index 368c612b..3e26ec75 100644 --- a/doc/libxml2-refs.xml +++ b/doc/libxml2-refs.xml @@ -22,6 +22,7 @@ + @@ -3563,6 +3564,7 @@ + @@ -10622,6 +10624,7 @@ + @@ -16575,6 +16578,9 @@ + + + @@ -20305,6 +20311,7 @@ + @@ -21655,6 +21662,7 @@ + @@ -24225,6 +24233,7 @@ + @@ -25384,6 +25393,9 @@ ++ + @@ -25447,6 +25459,9 @@ + + + @@ -26525,6 +26540,7 @@ + @@ -29968,6 +29984,9 @@ + + + @@ -30613,9 +30632,6 @@ -- - diff --git a/python/setup.py b/python/setup.py index f80a66c4..6522a516 100755 --- a/python/setup.py +++ b/python/setup.py @@ -226,7 +226,7 @@ else: setup (name = "libxml2-python", # On *nix, the version number is created from setup.py.in # On windows, it is set by configure.js - version = "2.7.6", + version = "2.7.7", description = descr, author = "Daniel Veillard", author_email = "veillard@redhat.com",