Closed
Description
Input:
#include <tidy.h>
int main(void)
{
TidyDoc tdoc = tidyCreate();
tidyParseString(tdoc, "<!DOCTYPE HTML PUBLIC \"\"-//W3C//DTD HTML 4.0 Transitional//EN\"\"><html><head><meta content=\"\"text/html; charset=utf-8\"\" http-equiv=Content-Type>");
tidyCleanAndRepair(tdoc);
return 0;
}
Output:
GNU gdb (GDB; openSUSE Tumbleweed) 8.1
Copyright (C) 2018 Free Software Foundation, Inc.
License GPLv3+: GNU GPL version 3 or later <http://gnu.org/licenses/gpl.html>
This is free software: you are free to change and redistribute it.
There is NO WARRANTY, to the extent permitted by law. Type "show copying"
and "show warranty" for details.
This GDB was configured as "x86_64-suse-linux".
Type "show configuration" for configuration details.
For bug reporting instructions, please see:
<http://bugs.opensuse.org/>.
Find the GDB manual and other documentation resources online at:
<http://www.gnu.org/software/gdb/documentation/>.
For help, type "help".
Type "apropos word" to search for commands related to "word"...
Reading symbols from a.out...done.
(gdb) r
Starting program: /home/jengelh/work/kc/librosie/a.out
line 1 column 77 - Warning: <meta> attribute "text/html;" lacks value
line 1 column 77 - Info: value for attribute "charset" missing quote marks
line 1 column 77 - Info: value for attribute "http-equiv" missing quote marks
line 1 column 71 - Warning: inserting missing 'title' element
line 1 column 77 - Warning: discarding unexpected <meta>
Program received signal SIGSEGV, Segmentation fault.
0x00007ffff7b31418 in prvTidyTidyMetaCharset (doc=0x602260) at /usr/src/debug/tidy-5.6.0-0.x86_64/src/clean.c:2215
2215 for (currentNode = head->content; currentNode; currentNode = currentNode->next)
(gdb) b prvTidyTidyMetaCharset
Breakpoint 1 at 0x7ffff7b30d2a: file /usr/src/debug/tidy-5.6.0-0.x86_64/src/clean.c, line 2178.
(gdb) r
The program being debugged has been started already.
Start it from the beginning? (y or n) y
Starting program: /home/jengelh/work/kc/librosie/a.out
line 1 column 77 - Warning: <meta> attribute "text/html;" lacks value
line 1 column 77 - Info: value for attribute "charset" missing quote marks
line 1 column 77 - Info: value for attribute "http-equiv" missing quote marks
line 1 column 71 - Warning: inserting missing 'title' element
Breakpoint 1, prvTidyTidyMetaCharset (doc=0x602260) at /usr/src/debug/tidy-5.6.0-0.x86_64/src/clean.c:2178
2178 {
(gdb) n
2182 Bool charsetFound = no;
(gdb)
2183 uint outenc = cfg(doc, TidyOutCharEncoding);
(gdb)
2184 ctmbstr enc = TY_(GetEncodingNameFromTidyId)(outenc);
(gdb)
2186 Node *head = TY_(FindHEAD)(doc);
(gdb)
2194 Bool add_meta = cfgBool(doc, TidyMetaCharset);
(gdb)
2197 if (!head || !enc || !TY_(tmbstrlen)(enc))
(gdb)
2199 if (outenc == RAW)
(gdb)
2202 if (outenc == ISO2022)
(gdb)
2205 if (cfgAutoBool(doc, TidyBodyOnly) == TidyYesState)
(gdb)
2208 tidyBufInit(&charsetString);
(gdb)
2210 tidyBufClear(&charsetString);
(gdb)
2211 tidyBufAppend(&charsetString, "charset=", 8);
(gdb)
2212 tidyBufAppend(&charsetString, (char*)enc, TY_(tmbstrlen)(enc));
(gdb)
2213 tidyBufAppend(&charsetString, "\0", 1); /* zero terminate the buffer */
(gdb)
2215 for (currentNode = head->content; currentNode; currentNode = currentNode->next)
(gdb)
2217 if (!nodeIsMETA(currentNode))
(gdb) p currentNode
$1 = (Node *) 0x60b5f0
(gdb) p currentNode->prev
$2 = (Node *) 0x0
(gdb) n
2219 charsetAttr = attrGetCHARSET(currentNode);
(gdb)
2220 httpEquivAttr = attrGetHTTP_EQUIV(currentNode);
(gdb)
2221 if (!charsetAttr && !httpEquivAttr)
(gdb)
2227 if (charsetAttr && !httpEquivAttr)
(gdb)
2262 if (httpEquivAttr && !charsetAttr)
(gdb)
2329 if (httpEquivAttr && charsetAttr)
(gdb)
2332 prevNode = currentNode->prev;
(gdb)
2333 TY_(Report)(doc, head, currentNode, DISCARDING_UNEXPECTED);
(gdb)
line 1 column 77 - Warning: discarding unexpected <meta>
2334 TY_(DiscardElement)(doc, currentNode);
(gdb)
2335 currentNode = prevNode;
(gdb)
2215 for (currentNode = head->content; currentNode; currentNode = currentNode->next)
(gdb)
Program received signal SIGSEGV, Segmentation fault.
0x00007ffff7b31418 in prvTidyTidyMetaCharset (doc=0x602260) at /usr/src/debug/tidy-5.6.0-0.x86_64/src/clean.c:2215
2215 for (currentNode = head->content; currentNode; currentNode = currentNode->next)
More info:
libtidy 5.6.0.
Regression from 5.4.0 where it appeared to work fine (no crash).