commit d50de7cf22cc21bed266c4bd355f9218ab1f8f41
author Marc Kupietz <kupietz@ids-mannheim.de> Sun Mar 10 15:24:55 2024 +0100
committer Marc Kupietz <kupietz@ids-mannheim.de> Sun Mar 10 15:24:55 2024 +0100
tree b85739cff20611fa527e5c1716ee38fd6b818a15
parent 29cfcf3114c454620296b0038a243217e6741868

conllu2korapxml2: escape &, <, >

Change-Id: Ieb1d5fc36b27783bc652b3345bb24e52fead3220

script/conllu2korapxml

diff --git a/script/conllu2korapxml b/script/conllu2korapxml
index 3e97fa7..53cdeca 100755
--- a/script/conllu2korapxml
+++ b/script/conllu2korapxml
@@ -137,7 +137,13 @@
           next MAIN if m!^\s*$!s;
         }
       };
-      my @parsed=split('\t');
+      my @parsed = map {
+        my $s = $_;
+        $s =~ s/&/&/g;
+        $s =~ s/</&lt;/g;
+        $s =~ s/>/&gt;/g;
+        $s;
+      } split('\t');
       chomp  $parsed[9];
       if (@parsed != 10) {
         $log->warn("WARNING: skipping strange parser output line in $docid");