static Lisp_Object
parse_region (Lisp_Object start, Lisp_Object end, Lisp_Object base_url,
Lisp_Object discard_comments, bool htmlp)
{
xmlDoc *doc;
Lisp_Object result = Qnil;
const char *burl = "";
ptrdiff_t istart, iend, istart_byte, iend_byte;
unsigned char *buftext;
xmlCheckVersion (LIBXML_VERSION);
validate_region (&start, &end);
istart = XINT (start);
iend = XINT (end);
istart_byte = CHAR_TO_BYTE (istart);
iend_byte = CHAR_TO_BYTE (iend);
if (istart < GPT && GPT < iend)
move_gap_both (iend, iend_byte);
if (! NILP (base_url))
{
CHECK_STRING (base_url);
burl = SSDATA (base_url);
}
buftext = BYTE_POS_ADDR (istart_byte);
#ifdef REL_ALLOC
/* Prevent ralloc.c from relocating the current buffer while libxml2
functions below read its text. */
r_alloc_inhibit_buffer_relocation (1);
#endif
if (htmlp)
doc = htmlReadMemory ((char *)buftext,
iend_byte - istart_byte, burl, "utf-8",
HTML_PARSE_RECOVER|HTML_PARSE_NONET|
HTML_PARSE_NOWARNING|HTML_PARSE_NOERROR|
HTML_PARSE_NOBLANKS);
else
doc = xmlReadMemory ((char *)buftext,
iend_byte - istart_byte, burl, "utf-8",
XML_PARSE_NONET|XML_PARSE_NOWARNING|
XML_PARSE_NOBLANKS |XML_PARSE_NOERROR);
#ifdef REL_ALLOC
r_alloc_inhibit_buffer_relocation (0);
#endif
/* If the assertion below fails, malloc was called inside the above
libxml2 functions, and ralloc.c caused relocation of buffer text,
so we could have read from unrelated memory. */
eassert (buftext == BYTE_POS_ADDR (istart_byte));
if (doc != NULL)
{
Lisp_Object r = Qnil;
if (NILP(discard_comments))
{
/* If the document has toplevel comments, then this should
get us the nodes and the comments. */
xmlNode *n = doc->children;
while (n) {
if (!NILP (r))
result = Fcons (r, result);
r = make_dom (n);
n = n->next;
}
}
if (NILP (result)) {
/* The document doesn't have toplevel comments or we discarded
them. Get the tree the proper way. */
xmlNode *node = xmlDocGetRootElement (doc);
if (node != NULL)
result = make_dom (node);
} else
result = Fcons (Qtop, Fcons (Qnil, Fnreverse (Fcons (r, result))));
xmlFreeDoc (doc);
}
return result;
}
static Lisp_Object
parse_region (Lisp_Object start, Lisp_Object end, Lisp_Object base_url, int htmlp)
{
xmlDoc *doc;
Lisp_Object result = Qnil;
const char *burl = "";
ptrdiff_t istart, iend, istart_byte, iend_byte;
fn_xmlCheckVersion (LIBXML_VERSION);
validate_region (&start, &end);
istart = XINT (start);
iend = XINT (end);
istart_byte = CHAR_TO_BYTE (istart);
iend_byte = CHAR_TO_BYTE (iend);
if (istart < GPT && GPT < iend)
move_gap_both (iend, iend_byte);
if (! NILP (base_url))
{
CHECK_STRING (base_url);
burl = SSDATA (base_url);
}
if (htmlp)
doc = fn_htmlReadMemory ((char *) BYTE_POS_ADDR (istart_byte),
iend_byte - istart_byte, burl, "utf-8",
HTML_PARSE_RECOVER|HTML_PARSE_NONET|
HTML_PARSE_NOWARNING|HTML_PARSE_NOERROR|
HTML_PARSE_NOBLANKS);
else
doc = fn_xmlReadMemory ((char *) BYTE_POS_ADDR (istart_byte),
iend_byte - istart_byte, burl, "utf-8",
XML_PARSE_NONET|XML_PARSE_NOWARNING|
XML_PARSE_NOBLANKS |XML_PARSE_NOERROR);
if (doc != NULL)
{
/* 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 = fn_xmlDocGetRootElement (doc);
if (node != NULL)
result = make_dom (node);
} else
result = Fcons (intern ("top"),
Fcons (Qnil, Fnreverse (Fcons (r, result))));
fn_xmlFreeDoc (doc);
}
return result;
}
static Lisp_Object
parse_region (Lisp_Object start, Lisp_Object end, Lisp_Object base_url, int htmlp)
{
xmlDoc *doc;
Lisp_Object result = Qnil;
const char *burl = "";
EMACS_INT bytes;
EMACS_INT istart, iend;
LIBXML_TEST_VERSION;
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 = SSDATA (base_url);
}
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)
{
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))
result = r;
else
result = Fcons (intern ("top"),
Fcons (Qnil, Fnreverse (Fcons (r, result))));
xmlFreeDoc (doc);
xmlCleanupParser ();
}
return result;
}
