mirror of
https://github.com/moparisthebest/wget
synced 2024-07-03 16:38:41 -04:00
[svn] Support XML-style empty tags.
This commit is contained in:
parent
b1dd1c1bad
commit
0ce7b6bffc
@ -1,3 +1,7 @@
|
|||||||
|
2001-11-16 Hrvoje Niksic <hniksic@arsdigita.com>
|
||||||
|
|
||||||
|
* html-parse.c (map_html_tags): Support XML-style empty tags.
|
||||||
|
|
||||||
2001-06-26 Hrvoje Niksic <hniksic@arsdigita.com>
|
2001-06-26 Hrvoje Niksic <hniksic@arsdigita.com>
|
||||||
|
|
||||||
* wget.h (DO_REALLOC_FROM_ALLOCA): Check for do_realloc_newsize in
|
* wget.h (DO_REALLOC_FROM_ALLOCA): Check for do_realloc_newsize in
|
||||||
|
@ -638,6 +638,19 @@ map_html_tags (const char *text, int size,
|
|||||||
|
|
||||||
SKIP_WS (p);
|
SKIP_WS (p);
|
||||||
|
|
||||||
|
if (*p == '/')
|
||||||
|
{
|
||||||
|
/* A slash at this point means the tag is about to be
|
||||||
|
closed. This is legal in XML and has been popularized
|
||||||
|
in HTML via XHTML. */
|
||||||
|
/* <foo a=b c=d /> */
|
||||||
|
/* ^ */
|
||||||
|
ADVANCE (p);
|
||||||
|
SKIP_WS (p);
|
||||||
|
if (*p != '>')
|
||||||
|
goto backout_tag;
|
||||||
|
}
|
||||||
|
|
||||||
/* Check for end of tag definition. */
|
/* Check for end of tag definition. */
|
||||||
if (*p == '>')
|
if (*p == '>')
|
||||||
break;
|
break;
|
||||||
@ -654,7 +667,7 @@ map_html_tags (const char *text, int size,
|
|||||||
|
|
||||||
/* Establish bounds of attribute value. */
|
/* Establish bounds of attribute value. */
|
||||||
SKIP_WS (p);
|
SKIP_WS (p);
|
||||||
if (NAME_CHAR_P (*p) || *p == '>')
|
if (NAME_CHAR_P (*p) || *p == '/' || *p == '>')
|
||||||
{
|
{
|
||||||
/* Minimized attribute syntax allows `=' to be omitted.
|
/* Minimized attribute syntax allows `=' to be omitted.
|
||||||
For example, <UL COMPACT> is a valid shorthand for <UL
|
For example, <UL COMPACT> is a valid shorthand for <UL
|
||||||
@ -735,7 +748,7 @@ map_html_tags (const char *text, int size,
|
|||||||
/* We skipped the whitespace and found something that is
|
/* We skipped the whitespace and found something that is
|
||||||
neither `=' nor the beginning of the next attribute's
|
neither `=' nor the beginning of the next attribute's
|
||||||
name. Back out. */
|
name. Back out. */
|
||||||
goto backout_tag; /* <foo bar /... */
|
goto backout_tag; /* <foo bar [... */
|
||||||
/* ^ */
|
/* ^ */
|
||||||
}
|
}
|
||||||
|
|
||||||
|
Loading…
Reference in New Issue
Block a user