 |
improve parsing whitespace after end tag names - webdump - HTML to plain-text c… |
 |
git clone git://git.codemadness.org/webdump |
 |
Log |
|
Files |
|
Refs |
|
README |
|
LICENSE |
|
--- |
|
commit 72b23084b7c64c298c6b90ae6ad9f53f497cec57 |
|
parent a0118e672fd3fa0004ccf2850eaef4ec4bc6fb39 |
|
Author: Hiltjo Posthuma <[email protected]> |
|
Date: Sat, 29 Jun 2024 18:29:21 +0200 |
|
|
|
improve parsing whitespace after end tag names |
|
|
|
Real site example: |
|
|
|
https://www.gnupg.org/gph/en/manual.html |
|
|
|
Has HTML such as: |
|
|
|
<P |
|
CLASS="COPYRIGHT" |
|
>Copyright © 1999 by <SPAN |
|
CLASS="HOLDER" |
|
>The Free Software Foundation</SPAN |
|
></P |
|
> |
|
... |
|
|
|
This incorrectly showed ">" in the end tag as data. |
|
|
|
Reported by Jason Hood, thanks! |
|
|
|
Diffstat: |
|
M xml.c | 2 ++ |
|
|
|
1 file changed, 2 insertions(+), 0 deletions(-) |
|
--- |
|
diff --git a/xml.c b/xml.c |
|
@@ -386,6 +386,8 @@ xml_parse(XMLParser *x) |
|
else if (c == '>' || ISSPACE(c)) { |
|
x->tag[x->taglen] = '\0'; |
|
if (isend) { /* end tag, start… |
|
+ while (c != '>' && c !… |
|
+ c = GETNEXT(); |
|
if (x->xmltagend) |
|
x->xmltagend(x… |
|
x->tag[0] = '\0'; |
