/* Interface to libxml2.
- Copyright (C) 2010 Free Software Foundation, Inc.
+ Copyright (C) 2010-2011 Free Software Foundation, Inc.
This file is part of GNU Emacs.
#include "lisp.h"
#include "buffer.h"
-Lisp_Object make_dom (xmlNode *node)
+static Lisp_Object
+make_dom (xmlNode *node)
{
if (node->type == XML_ELEMENT_NODE)
{
- Lisp_Object result = Fcons (intern (node->name), Qnil);
+ Lisp_Object result = Fcons (intern ((char *) node->name), Qnil);
xmlNode *child;
xmlAttr *property;
Lisp_Object plist = Qnil;
if (property->children &&
property->children->content)
{
- plist = Fcons (Fcons (intern (property->name),
- build_string (property->children->content)),
+ char *content = (char *) property->children->content;
+ plist = Fcons (Fcons (intern ((char *) property->name),
+ build_string (content)),
plist);
}
property = property->next;
return Fnreverse (result);
}
- else if (node->type == XML_TEXT_NODE)
+ else if (node->type == XML_TEXT_NODE || node->type == XML_CDATA_SECTION_NODE)
+ {
+ if (node->content)
+ return build_string ((char *) node->content);
+ else
+ return Qnil;
+ }
+ else if (node->type == XML_COMMENT_NODE)
{
if (node->content)
- return build_string (node->content);
+ return list3 (intern ("comment"), Qnil,
+ build_string ((char *) node->content));
else
return Qnil;
}
}
static Lisp_Object
-parse_string (Lisp_Object string, Lisp_Object base_url, int htmlp)
+parse_region (Lisp_Object start, Lisp_Object end, Lisp_Object base_url, int htmlp)
{
xmlDoc *doc;
- xmlNode *node;
Lisp_Object result = Qnil;
- int ibeg, iend;
- char *burl = "";
+ const char *burl = "";
+ EMACS_INT bytes;
+ EMACS_INT istart, iend;
LIBXML_TEST_VERSION;
- CHECK_STRING (string);
+ validate_region (&start, &end);
+
+ istart = XINT (start);
+ iend = XINT (end);
+
+ if (istart < GPT && GPT < iend)
+ move_gap (iend);
if (! NILP (base_url))
{
CHECK_STRING (base_url);
- burl = SDATA (base_url);
+ burl = SSDATA (base_url);
}
- doc = htmlp
- ? htmlReadMemory (SDATA (string), SBYTES (string), burl, "utf-8",
- HTML_PARSE_RECOVER|HTML_PARSE_NONET|
- HTML_PARSE_NOWARNING|HTML_PARSE_NOERROR)
- : xmlReadMemory (SDATA (string), SBYTES (string), burl, "utf-8",
- XML_PARSE_NONET|XML_PARSE_NOWARNING|
- XML_PARSE_NOERROR);
+ bytes = CHAR_TO_BYTE (iend) - CHAR_TO_BYTE (istart);
+
+ if (htmlp)
+ doc = htmlReadMemory ((char *) BYTE_POS_ADDR (CHAR_TO_BYTE (istart)),
+ bytes, burl, "utf-8",
+ HTML_PARSE_RECOVER|HTML_PARSE_NONET|
+ HTML_PARSE_NOWARNING|HTML_PARSE_NOERROR|
+ HTML_PARSE_NOBLANKS);
+ else
+ doc = xmlReadMemory ((char *) BYTE_POS_ADDR (CHAR_TO_BYTE (istart)),
+ bytes, burl, "utf-8",
+ XML_PARSE_NONET|XML_PARSE_NOWARNING|
+ XML_PARSE_NOBLANKS |XML_PARSE_NOERROR);
if (doc != NULL)
{
- node = xmlDocGetRootElement (doc);
- if (node != NULL)
- result = make_dom (node);
+ /* If the document is just comments, then this should get us the
+ nodes anyway. */
+ xmlNode *n = doc->children->next;
+ Lisp_Object r = Qnil;
+
+ while (n) {
+ if (!NILP (r))
+ result = Fcons (r, result);
+ r = make_dom (n);
+ n = n->next;
+ }
+
+ if (NILP (result)) {
+ /* The document isn't just comments, so get the tree the
+ proper way. */
+ xmlNode *node = xmlDocGetRootElement (doc);
+ if (node != NULL)
+ result = make_dom (node);
+ } else
+ result = Fcons (intern ("top"),
+ Fcons (Qnil, Fnreverse (Fcons (r, result))));
+
xmlFreeDoc (doc);
- xmlCleanupParser ();
}
return result;
}
-DEFUN ("xml-parse-html-string-internal", Fxml_parse_html_string_internal,
- Sxml_parse_html_string_internal,
- 1, 2, 0,
- doc: /* Parse STRING as an HTML document and return the parse tree.
+DEFUN ("libxml-parse-html-region", Flibxml_parse_html_region,
+ Slibxml_parse_html_region,
+ 2, 3, 0,
+ doc: /* Parse the region as an HTML document and return the parse tree.
If BASE-URL is non-nil, it is used to expand relative URLs. */)
- (Lisp_Object string, Lisp_Object base_url)
+ (Lisp_Object start, Lisp_Object end, Lisp_Object base_url)
{
- return parse_string (string, base_url, 1);
+ return parse_region (start, end, base_url, 1);
}
-DEFUN ("xml-parse-string-internal", Fxml_parse_string_internal,
- Sxml_parse_string_internal,
- 1, 2, 0,
- doc: /* Parse STRING as an XML document and return the parse tree.
+DEFUN ("libxml-parse-xml-region", Flibxml_parse_xml_region,
+ Slibxml_parse_xml_region,
+ 2, 3, 0,
+ doc: /* Parse the region as an XML document and return the parse tree.
If BASE-URL is non-nil, it is used to expand relative URLs. */)
- (Lisp_Object string, Lisp_Object base_url)
+ (Lisp_Object start, Lisp_Object end, Lisp_Object base_url)
{
- return parse_string (string, base_url, 0);
+ return parse_region (start, end, base_url, 0);
}
\f
void
syms_of_xml (void)
{
- defsubr (&Sxml_parse_html_string_internal);
- defsubr (&Sxml_parse_string_internal);
+ defsubr (&Slibxml_parse_html_region);
+ defsubr (&Slibxml_parse_xml_region);
}
#endif /* HAVE_LIBXML2 */
HCoop / bpt / emacs.git / blobdiff