From c2295530401f53653386ff07a43c668a6a574d65 Mon Sep 17 00:00:00 2001 From: Pasi Kallinen Date: Thu, 24 Apr 2014 11:01:52 +0300 Subject: [PATCH] Bug 11631: Make i18n toolchain ignore useless strings This patch removes several types of strings from the PO files that cannot be usefully translated, including ones that consist entirely of punctuation and/or HTML entities. Test: 1) Update PO files of some lang, xx-YY-*po cd misc/translator perl translate update xx-YY 2) Do it again, just in case 3) rm po/xx-YY*po~ 4) Extract all msgid's, sorted cat po/xx-YY*po | egrep "^msgid" | sort | uniq > xx-YY-pre 5) Apply the patch 6) Repeat 1-3 7) Repeat 4 again, other file cat po/xx-YY*po | egrep "^msgid" | sort | uniq > xx-YY-post 8) Do a diff, inspect results, only strings with %s and \s diff xx-YY-pre xx-YY-post | less Signed-off-by: Bernardo Gonzalez Kriegel Works as described, 380 strings less to 'translate' No koha-qa errors. Signed-off-by: Katrin Fischer Tested according to test plan, works as described. Signed-off-by: Galen Charlton --- misc/translator/xgettext.pl | 1 + 1 file changed, 1 insertion(+) diff --git a/misc/translator/xgettext.pl b/misc/translator/xgettext.pl index 032117d5bd..ea75794f94 100755 --- a/misc/translator/xgettext.pl +++ b/misc/translator/xgettext.pl @@ -37,6 +37,7 @@ sub string_negligible_p ($) { || $t =~ /^\d+$/ # purely digits || $t =~ /^[-\+\.,:;!\?'"%\(\)\[\]\|]+$/ # punctuation w/o context || $t =~ /^[A-Za-z]$/ # single letters + || $t =~ /^(&[a-z]+;|&#\d+;|&#x[0-9a-fA-F]+;|%%|%s|\s|[[:punct:]])*$/ # html entities,placeholder,punct, ... ) } -- 2.39.5