Awight has uploaded a new change for review.
https://gerrit.wikimedia.org/r/178972
Change subject: Parse XML charset declaration
......................................................................
Parse XML charset declaration
Now it's possible to consume text containing latin-1 characters.
Change-Id: I5bba92bc195602ada2f5cc0bb71a9e7c0ccd34ed
---
M sites/all/modules/wmf_audit/wmf_audit.module
1 file changed, 6 insertions(+), 1 deletion(-)
git pull ssh://gerrit.wikimedia.org:29418/wikimedia/fundraising/crm
refs/changes/72/178972/1
diff --git a/sites/all/modules/wmf_audit/wmf_audit.module
b/sites/all/modules/wmf_audit/wmf_audit.module
index 02a007b..ecc6cb1 100644
--- a/sites/all/modules/wmf_audit/wmf_audit.module
+++ b/sites/all/modules/wmf_audit/wmf_audit.module
@@ -1006,7 +1006,10 @@
//look for the raw xml
$full_xml = false;
$node = wmfa_execute('get_log_line_xml_outermost_node');
- $xmlstart = strpos($line, "<$node>");
+ $xmlstart = strpos($line, '<?xml');
+ if ($xmlstart === false) {
+ strpos($line, "<$node>");
+ }
$xmlend = strpos($line, "</$node>");
if ($xmlend) {
$full_xml = true;
@@ -1016,6 +1019,8 @@
//this is a broken line, and it won't load... but we can still parse
what's left of the thing, the slow way.
$xml = substr($line, $xmlstart);
}
+ // Syslog wart. Other control characters should be encoded normally.
+ $xml = str_replace( '#012', "\n", $xml );
$donor_data = array();
--
To view, visit https://gerrit.wikimedia.org/r/178972
To unsubscribe, visit https://gerrit.wikimedia.org/r/settings
Gerrit-MessageType: newchange
Gerrit-Change-Id: I5bba92bc195602ada2f5cc0bb71a9e7c0ccd34ed
Gerrit-PatchSet: 1
Gerrit-Project: wikimedia/fundraising/crm
Gerrit-Branch: master
Gerrit-Owner: Awight <[email protected]>
_______________________________________________
MediaWiki-commits mailing list
[email protected]
https://lists.wikimedia.org/mailman/listinfo/mediawiki-commits
