xml.h File Reference

#include "mupdf/fitz/system.h"
#include "mupdf/fitz/context.h"
#include "mupdf/fitz/buffer.h"
#include "mupdf/fitz/pool.h"
#include "mupdf/fitz/archive.h"

Include dependency graph for xml.h:

This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Typedefs
typedef struct fz_xml	fz_xml
typedef fz_xml	fz_xml_doc

Functions
fz_xml *	fz_parse_xml (fz_context *ctx, fz_buffer *buf, int preserve_white)
fz_xml *	fz_parse_xml_stream (fz_context *ctx, fz_stream *stream, int preserve_white)
fz_xml *	fz_parse_xml_archive_entry (fz_context *ctx, fz_archive *dir, const char *filename, int preserve_white)
fz_xml *	fz_try_parse_xml_archive_entry (fz_context *ctx, fz_archive *dir, const char *filename, int preserve_white)
fz_xml *	fz_parse_xml_from_html5 (fz_context *ctx, fz_buffer *buf)
fz_xml *	fz_keep_xml (fz_context *ctx, fz_xml *xml)
void	fz_drop_xml (fz_context *ctx, fz_xml *xml)
void	fz_detach_xml (fz_context *ctx, fz_xml *node)
fz_xml *	fz_xml_root (fz_xml_doc *xml)
fz_xml *	fz_xml_prev (fz_xml *item)
fz_xml *	fz_xml_next (fz_xml *item)
fz_xml *	fz_xml_up (fz_xml *item)
fz_xml *	fz_xml_down (fz_xml *item)
int	fz_xml_is_tag (fz_xml *item, const char *name)
char *	fz_xml_tag (fz_xml *item)
char *	fz_xml_att (fz_xml *item, const char *att)
char *	fz_xml_att_alt (fz_xml *item, const char *one, const char *two)
int	fz_xml_att_eq (fz_xml *item, const char *name, const char *match)
void	fz_xml_add_att (fz_context *ctx, fz_pool *pool, fz_xml *node, const char *key, const char *val)
char *	fz_xml_text (fz_xml *item)
void	fz_output_xml (fz_context *ctx, fz_output *out, fz_xml *item, int level)
void	fz_debug_xml (fz_xml *item, int level)
fz_xml *	fz_xml_find (fz_xml *item, const char *tag)
fz_xml *	fz_xml_find_next (fz_xml *item, const char *tag)
fz_xml *	fz_xml_find_down (fz_xml *item, const char *tag)
fz_xml *	fz_xml_find_match (fz_xml *item, const char *tag, const char *att, const char *match)
fz_xml *	fz_xml_find_next_match (fz_xml *item, const char *tag, const char *att, const char *match)
fz_xml *	fz_xml_find_down_match (fz_xml *item, const char *tag, const char *att, const char *match)
fz_xml *	fz_xml_find_dfs (fz_xml *item, const char *tag, const char *att, const char *match)
fz_xml *	fz_xml_find_dfs_top (fz_xml *item, const char *tag, const char *att, const char *match, fz_xml *top)
fz_xml *	fz_xml_find_next_dfs (fz_xml *item, const char *tag, const char *att, const char *match)
fz_xml *	fz_xml_find_next_dfs_top (fz_xml *item, const char *tag, const char *att, const char *match, fz_xml *top)
char *	fz_new_text_from_xml (fz_context *ctx, fz_xml *root)
fz_xml *	fz_dom_body (fz_context *ctx, fz_xml *dom)
fz_xml *	fz_dom_document_element (fz_context *ctx, fz_xml *dom)
fz_xml *	fz_dom_create_element (fz_context *ctx, fz_xml *dom, const char *tag)
fz_xml *	fz_dom_create_text_node (fz_context *ctx, fz_xml *dom, const char *text)
fz_xml *	fz_dom_find (fz_context *ctx, fz_xml *elt, const char *tag, const char *att, const char *match)
fz_xml *	fz_dom_find_next (fz_context *ctx, fz_xml *elt, const char *tag, const char *att, const char *match)
void	fz_dom_append_child (fz_context *ctx, fz_xml *parent, fz_xml *child)
void	fz_dom_insert_before (fz_context *ctx, fz_xml *node, fz_xml *new_elt)
void	fz_dom_insert_after (fz_context *ctx, fz_xml *node, fz_xml *new_elt)
void	fz_dom_remove (fz_context *ctx, fz_xml *elt)
fz_xml *	fz_dom_clone (fz_context *ctx, fz_xml *elt)
fz_xml *	fz_dom_first_child (fz_context *ctx, fz_xml *elt)
fz_xml *	fz_dom_parent (fz_context *ctx, fz_xml *elt)
fz_xml *	fz_dom_next (fz_context *ctx, fz_xml *elt)
fz_xml *	fz_dom_previous (fz_context *ctx, fz_xml *elt)
void	fz_dom_add_attribute (fz_context *ctx, fz_xml *elt, const char *att, const char *value)
void	fz_dom_remove_attribute (fz_context *ctx, fz_xml *elt, const char *att)
const char *	fz_dom_attribute (fz_context *ctx, fz_xml *elt, const char *att)
const char *	fz_dom_get_attribute (fz_context *ctx, fz_xml *elt, int i, const char **att)
fz_xml *	fz_new_dom (fz_context *ctx, const char *tag)
fz_xml *	fz_new_dom_node (fz_context *ctx, fz_xml *dom, const char *tag)
fz_xml *	fz_new_dom_text_node (fz_context *ctx, fz_xml *dom, const char *text)
void	fz_write_xml (fz_context *ctx, fz_xml *root, fz_output *out, int indented)
void	fz_save_xml (fz_context *ctx, fz_xml *root, const char *path, int indented)

Typedef Documentation

fz_xml

typedef struct fz_xml fz_xml

XML document model

fz_xml_doc

typedef fz_xml fz_xml_doc

Function Documentation

fz_debug_xml()

void fz_debug_xml	(	fz_xml *	item,
		int	level )

Pretty-print an XML tree to stdout. (Deprecated, use fz_output_xml in preference).

fz_detach_xml()

void fz_detach_xml	(	fz_context *	ctx,
		fz_xml *	node )

Detach a node from the tree, unlinking it from its parent, and setting the document root to the node.

fz_dom_add_attribute()

void fz_dom_add_attribute	(	fz_context *	ctx,
		fz_xml *	elt,
		const char *	att,
		const char *	value )

Add an attribute to an element.

Ownership of att and value remain with the caller.

fz_dom_append_child()

void fz_dom_append_child	(	fz_context *	ctx,
		fz_xml *	parent,
		fz_xml *	child )

Insert an element as the last child of a parent, unlinking the child from its current position if required.

fz_dom_attribute()

const char * fz_dom_attribute	(	fz_context *	ctx,
		fz_xml *	elt,
		const char *	att )

Retrieve the value of a given attribute from a given element.

Returns a borrowed pointer to the value or NULL if not found.

fz_dom_body()

fz_xml * fz_dom_body	(	fz_context *	ctx,
		fz_xml *	dom )

DOM-like functions for html in xml. Return a borrowed reference for the 'body' element of the given DOM.

fz_dom_clone()

fz_xml * fz_dom_clone	(	fz_context *	ctx,
		fz_xml *	elt )

Clone an element (and its children).

A borrowed reference to the clone is returned. The clone is not yet linked into the DOM.

fz_dom_create_element()

fz_xml * fz_dom_create_element	(	fz_context *	ctx,
		fz_xml *	dom,
		const char *	tag )

Create an element of a given tag type for the given DOM.

The element is not linked into the DOM yet.

fz_dom_create_text_node()

fz_xml * fz_dom_create_text_node	(	fz_context *	ctx,
		fz_xml *	dom,
		const char *	text )

Create a text node for the given DOM.

The element is not linked into the DOM yet.

fz_dom_document_element()

fz_xml * fz_dom_document_element	(	fz_context *	ctx,
		fz_xml *	dom )

Return a borrowed reference for the document (the top level element) of the DOM.

fz_dom_find()

fz_xml * fz_dom_find	(	fz_context *	ctx,
		fz_xml *	elt,
		const char *	tag,
		const char *	att,
		const char *	match )

Find the first element matching the requirements in a depth first traversal from elt.

The tagname must match tag, unless tag is NULL, when all tag names are considered to match.

If att is NULL, then all tags match. Otherwise: If match is NULL, then only nodes that have an att attribute match. If match is non-NULL, then only nodes that have an att attribute that matches match match.

Returns NULL (if no match found), or a borrowed reference to the first matching element.

fz_dom_find_next()

fz_xml * fz_dom_find_next	(	fz_context *	ctx,
		fz_xml *	elt,
		const char *	tag,
		const char *	att,
		const char *	match )

Find the next element matching the requirements.

fz_dom_first_child()

fz_xml * fz_dom_first_child	(	fz_context *	ctx,
		fz_xml *	elt )

Return a borrowed reference to the first child of a node, or NULL if there isn't one.

fz_dom_get_attribute()

const char * fz_dom_get_attribute	(	fz_context *	ctx,
		fz_xml *	elt,
		int	i,
		const char **	att )

Enumerate through the attributes of an element.

Call with i=0,1,2,3... to enumerate attributes.

On return *att and the return value will be NULL if there are not that many attributes to read. Otherwise, *att will be filled in with a borrowed pointer to the attribute name, and the return value will be a borrowed pointer to the value.

fz_dom_insert_after()

void fz_dom_insert_after	(	fz_context *	ctx,
		fz_xml *	node,
		fz_xml *	new_elt )

Insert an element (new_elt), after another element (node), unlinking the new_elt from its current position if required.

fz_dom_insert_before()

void fz_dom_insert_before	(	fz_context *	ctx,
		fz_xml *	node,
		fz_xml *	new_elt )

Insert an element (new_elt), before another element (node), unlinking the new_elt from its current position if required.

fz_dom_next()

fz_xml * fz_dom_next	(	fz_context *	ctx,
		fz_xml *	elt )

Return a borrowed reference to the next sibling of a node, or NULL if there isn't one.

fz_dom_parent()

fz_xml * fz_dom_parent	(	fz_context *	ctx,
		fz_xml *	elt )

Return a borrowed reference to the parent of a node, or NULL if there isn't one.

fz_dom_previous()

fz_xml * fz_dom_previous	(	fz_context *	ctx,
		fz_xml *	elt )

Return a borrowed reference to the previous sibling of a node, or NULL if there isn't one.

fz_dom_remove()

void fz_dom_remove	(	fz_context *	ctx,
		fz_xml *	elt )

Remove an element from the DOM. The element can be added back elsewhere if required.

No reference counting changes for the element.

fz_dom_remove_attribute()

void fz_dom_remove_attribute	(	fz_context *	ctx,
		fz_xml *	elt,
		const char *	att )

Remove an attribute from an element.

fz_drop_xml()

void fz_drop_xml	(	fz_context *	ctx,
		fz_xml *	xml )

Drop a reference to the XML. When the last reference is dropped, the node and all its children and siblings will be freed.

fz_keep_xml()

fz_xml * fz_keep_xml	(	fz_context *	ctx,
		fz_xml *	xml )

Add a reference to the XML.

fz_new_dom()

fz_xml * fz_new_dom	(	fz_context *	ctx,
		const char *	tag )

Make new xml dom root element.

fz_new_dom_node()

fz_xml * fz_new_dom_node	(	fz_context *	ctx,
		fz_xml *	dom,
		const char *	tag )

Create a new dom node.

This will NOT be linked in yet.

fz_new_dom_text_node()

fz_xml * fz_new_dom_text_node	(	fz_context *	ctx,
		fz_xml *	dom,
		const char *	text )

Create a new dom text node.

This will NOT be linked in yet.

fz_new_text_from_xml()

char * fz_new_text_from_xml	(	fz_context *	ctx,
		fz_xml *	root )

Extract and concatenate all plain text data from XML tree into a new string.

fz_output_xml()

void fz_output_xml	(	fz_context *	ctx,
		fz_output *	out,
		fz_xml *	item,
		int	level )

Pretty-print an XML tree to given output.

fz_parse_xml()

fz_xml * fz_parse_xml	(	fz_context *	ctx,
		fz_buffer *	buf,
		int	preserve_white )

Parse the contents of buffer into a tree of xml nodes.

preserve_white: whether to keep or delete all-whitespace nodes.

fz_parse_xml_archive_entry()

fz_xml * fz_parse_xml_archive_entry	(	fz_context *	ctx,
		fz_archive *	dir,
		const char *	filename,
		int	preserve_white )

Parse the contents of an archive entry into a tree of xml nodes.

preserve_white: whether to keep or delete all-whitespace nodes.

fz_parse_xml_from_html5()

fz_xml * fz_parse_xml_from_html5	(	fz_context *	ctx,
		fz_buffer *	buf )

Parse the contents of a buffer into a tree of XML nodes, using the HTML5 parsing algorithm.

fz_parse_xml_stream()

fz_xml * fz_parse_xml_stream	(	fz_context *	ctx,
		fz_stream *	stream,
		int	preserve_white )

Parse the contents of buffer into a tree of xml nodes.

preserve_white: whether to keep or delete all-whitespace nodes.

fz_save_xml()

void fz_save_xml	(	fz_context *	ctx,
		fz_xml *	root,
		const char *	path,
		int	indented )

As for fz_write_xml, but direct to a file.

fz_try_parse_xml_archive_entry()

fz_xml * fz_try_parse_xml_archive_entry	(	fz_context *	ctx,
		fz_archive *	dir,
		const char *	filename,
		int	preserve_white )

Try and parse the contents of an archive entry into a tree of xml nodes.

preserve_white: whether to keep or delete all-whitespace nodes.

Will return NULL if the archive entry can't be found. Otherwise behaves the same as fz_parse_xml_archive_entry. May throw exceptions.

fz_write_xml()

void fz_write_xml	(	fz_context *	ctx,
		fz_xml *	root,
		fz_output *	out,
		int	indented )

Write our xml structure out to an xml stream.

Properly formatted XML is only allowed to have a single top-level node under which everything must sit. Our structures allow for multiple top level nodes. If required, we will output an extra 'ROOT' node at the top so that the xml is well-formed.

If 'indented' is non-zero then additional whitespace will be added to make the XML easier to read in a text editor. It will NOT be properly compliant.

fz_xml_add_att()

void fz_xml_add_att	(	fz_context *	ctx,
		fz_pool *	pool,
		fz_xml *	node,
		const char *	key,
		const char *	val )

Add an attribute to an XML node.

fz_xml_att()

char * fz_xml_att	(	fz_xml *	item,
		const char *	att )

Return the value of an attribute of an XML node. NULL if the attribute doesn't exist.

fz_xml_att_alt()

char * fz_xml_att_alt	(	fz_xml *	item,
		const char *	one,
		const char *	two )

Return the value of an attribute of an XML node. If the first attribute doesn't exist, try the second. NULL if neither attribute exists.

fz_xml_att_eq()

int fz_xml_att_eq	(	fz_xml *	item,
		const char *	name,
		const char *	match )

Check for a matching attribute on an XML node.

If the node has the requested attribute (name), and the value matches (match) then return 1. Otherwise, 0.

fz_xml_down()

fz_xml * fz_xml_down

(

fz_xml *

item

)

Return first child of XML node.

fz_xml_find()

fz_xml * fz_xml_find	(	fz_xml *	item,
		const char *	tag )

Search the siblings of XML nodes starting with item looking for the first with the given tag.

Return NULL if none found.

fz_xml_find_dfs()

fz_xml * fz_xml_find_dfs	(	fz_xml *	item,
		const char *	tag,
		const char *	att,
		const char *	match )

Perform a depth first search from item, returning the first child that matches the given tag (or any tag if tag is NULL), with the given attribute (if att is non NULL), that matches match (if match is non NULL).

fz_xml_find_dfs_top()

fz_xml * fz_xml_find_dfs_top	(	fz_xml *	item,
		const char *	tag,
		const char *	att,
		const char *	match,
		fz_xml *	top )

Perform a depth first search from item, returning the first child that matches the given tag (or any tag if tag is NULL), with the given attribute (if att is non NULL), that matches match (if match is non NULL). The search stops if it ever reaches the top of the tree, or the declared 'top' item.

fz_xml_find_down()

fz_xml * fz_xml_find_down	(	fz_xml *	item,
		const char *	tag )

Search the siblings of XML nodes starting with the first child of item looking for the first with the given tag.

Return NULL if none found.

fz_xml_find_down_match()

fz_xml * fz_xml_find_down_match	(	fz_xml *	item,
		const char *	tag,
		const char *	att,
		const char *	match )

Search the siblings of XML nodes starting with the first child of item looking for the first with the given tag (or any tag if tag is NULL), and with a matching attribute.

Return NULL if none found.

fz_xml_find_match()

fz_xml * fz_xml_find_match	(	fz_xml *	item,
		const char *	tag,
		const char *	att,
		const char *	match )

Search the siblings of XML nodes starting with item looking for the first with the given tag (or any tag if tag is NULL), and with a matching attribute.

Return NULL if none found.

fz_xml_find_next()

fz_xml * fz_xml_find_next	(	fz_xml *	item,
		const char *	tag )

Search the siblings of XML nodes starting with the first sibling of item looking for the first with the given tag.

Return NULL if none found.

fz_xml_find_next_dfs()

fz_xml * fz_xml_find_next_dfs	(	fz_xml *	item,
		const char *	tag,
		const char *	att,
		const char *	match )

Perform a depth first search onwards from item, returning the first child that matches the given tag (or any tag if tag is NULL), with the given attribute (if att is non NULL), that matches match (if match is non NULL).

fz_xml_find_next_dfs_top()

fz_xml * fz_xml_find_next_dfs_top	(	fz_xml *	item,
		const char *	tag,
		const char *	att,
		const char *	match,
		fz_xml *	top )

Perform a depth first search onwards from item, returning the first child that matches the given tag (or any tag if tag is NULL), with the given attribute (if att is non NULL), that matches match (if match is non NULL). The search stops if it ever reaches the top of the tree, or the declared 'top' item.

fz_xml_find_next_match()

fz_xml * fz_xml_find_next_match	(	fz_xml *	item,
		const char *	tag,
		const char *	att,
		const char *	match )

Search the siblings of XML nodes starting with the first sibling of item looking for the first with the given tag (or any tag if tag is NULL), and with a matching attribute.

Return NULL if none found.

fz_xml_is_tag()

int fz_xml_is_tag	(	fz_xml *	item,
		const char *	name )

Return true if the tag name matches.

fz_xml_next()

fz_xml * fz_xml_next

(

fz_xml *

item

)

Return next sibling of XML node.

fz_xml_prev()

fz_xml * fz_xml_prev

(

fz_xml *

item

)

Return previous sibling of XML node.

fz_xml_root()

fz_xml * fz_xml_root

(

fz_xml_doc *

xml

)

Return the topmost XML node of a document.

fz_xml_tag()

char * fz_xml_tag

(

fz_xml *

item

)

Return tag of XML node. Return NULL for text nodes.

fz_xml_text()

char * fz_xml_text

(

fz_xml *

item

)

Return the text content of an XML node. Return NULL if the node is a tag.

fz_xml_up()

fz_xml * fz_xml_up

(

fz_xml *

item

)

Return parent of XML node.