Remove truncation to 32 characters
Thanks @perkuhn !
Change-Id: I511b347b269c68cb9095f9fde61cf22ae6d439b4
diff --git a/script/korapxml2conllu b/script/korapxml2conllu
index d3a292c..9674b28 100755
--- a/script/korapxml2conllu
+++ b/script/korapxml2conllu
@@ -123,7 +123,7 @@
($current_from) = /from="([^\"]*)"/;
($current_to) = /to="([^\"]*)"/;
print STDERR "found span: $current_id $current_from $current_to\n" if($debug);
- $token = substr($plain_texts{$docid}, $current_from, min($current_to - $current_from, 32));
+ $token = substr($plain_texts{$docid}, $current_from, $current_to - $current_from);
if (!defined $token) {
print STDERR "WARNING: could not retrieve token for $docid at $current_from-$current_to/", length($plain_texts{$docid}), " - ending with: ", substr($plain_texts{$docid},length($plain_texts{$docid})-10), "\n";
$token = "_";