projects
/
eprints3-migration.git
/ commitdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
| commitdiff |
tree
raw
|
patch
| inline |
side by side
(parent:
25207a5
)
eprints-dev: /home/dpavlin/mtoolkit/utf8-fix.pl [commit]
author
Dobrica Pavlinusic
<dpavlin@rot13.org>
Tue, 19 Oct 2010 16:19:52 +0000
(18:19 +0200)
committer
Dobrica Pavlinusic
<dpavlin@rot13.org>
Tue, 19 Oct 2010 16:19:52 +0000
(18:19 +0200)
mtoolkit/utf8-fix.pl
patch
|
blob
|
history
diff --git
a/mtoolkit/utf8-fix.pl
b/mtoolkit/utf8-fix.pl
index
3946bcd
..
3592209
100755
(executable)
--- a/
mtoolkit/utf8-fix.pl
+++ b/
mtoolkit/utf8-fix.pl
@@
-67,8
+67,9
@@
s/$junk\xC2\x9D/-/gs && $stat->{'-- ?'}++;
s/$junk\xC3\x82\xC2\xA2/- /gs && $stat->{'dot'}++;
+
my $e = $_;
- if ( $e =~ m/([\xC0-\xC4][\x80-\xff]{
4,8
})/s ) {
+ if ( $e =~ m/([\xC0-\xC4][\x80-\xff]{
3,99
})/s ) {
warn "XXX ", dump($e), "\n$e\n";
}
print $e;