summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorAmir Sarabadani <ladsgroup@gmail.com>2023-06-08 14:20:51 +0200
committerLadsgroup <Ladsgroup@gmail.com>2023-06-13 11:06:28 +0000
commitb8e25022d842dbceb44377b139a5fb66867a7d5a (patch)
tree126e705925d199afbf32c4e009dede42ef87d460
parentd5a48eeb47a236f1a0eef56f9993608c0eddc834 (diff)
moveToExternal: Also check for utf8 encoding before trying to convertwmf/1.41.0-wmf.12
While most rows in production use 'utf-8' to flag content being UTF-8, we have lots of rows flagged with 'utf8': mysql:research@s3-analytics-replica.eqiad.wmnet [dawiki]> select old_flags, count(*) from text group by old_flags limit 50; +---------------------+----------+ | old_flags | count(*) | +---------------------+----------+ | error | 2 | | external,gzip | 49 | | external,object | 36 | | external,utf-8 | 1614469 | | external,utf8 | 336780 | | gzip,utf-8,external | 1094 | | utf-8,gzip,external | 9458083 | +---------------------+----------+ 7 rows in set (26.038 sec) This would confuse the script to try to reencode it again which possibly could lead to all sorts of errors Change-Id: I9b4a38538199c9954cfed51cdd2bba8b0f6cb953 (cherry picked from commit 4dd3850bebdd972001a007f1bcc5a127d3d4dc4f)
-rw-r--r--maintenance/storage/moveToExternal.php1
1 files changed, 1 insertions, 0 deletions
diff --git a/maintenance/storage/moveToExternal.php b/maintenance/storage/moveToExternal.php
index 520d55ab18ae..470af0cd203a 100644
--- a/maintenance/storage/moveToExternal.php
+++ b/maintenance/storage/moveToExternal.php
@@ -232,6 +232,7 @@ class MoveToExternal extends Maintenance {
private function resolveLegacyEncoding( $text, $flags ) {
if ( $this->legacyEncoding !== null
&& !in_array( 'utf-8', $flags )
+ && !in_array( 'utf8', $flags )
) {
AtEase::suppressWarnings();
$text = iconv( $this->legacyEncoding, 'UTF-8//IGNORE', $text );