commit 19c6c358875209350c1b9eda87e027236d161676
author Akron <nils@diewald-online.de> Sat Aug 01 13:29:00 2020 +0200
committer Peter Harders <harders@ids-mannheim.de> Tue Sep 22 12:01:00 2020 +0200
tree 9a842bae894a8ac83b53dd7af041916e91201faf
parent fe1aa5416ecd7fa41a0d3ac11d3cd50bfa0a4701

Fix bug in comment removal procedure

Change-Id: Ia9fa8bd9f52f7b1404412602b1c04fca46a3d88d

script/tei2korapxml

diff --git a/script/tei2korapxml b/script/tei2korapxml
index da2cec6..df4150a 100755
--- a/script/tei2korapxml
+++ b/script/tei2korapxml
@@ -259,7 +259,7 @@
 
     # TODO: yet not tested fo big amounts of data
     # must-have, otherwise comments in input could be fatal (e.g.: ...<!--\n<idsHeader...\n-->...)
-    remove_xml_comments( $input_fh, $_ ); # remove HTML comments (<!--...-->)
+    $_ = remove_xml_comments( $input_fh, $_ ); # remove HTML comments (<!--...-->)
 
     if ( $data_fl && ($pos = index($_, '</' . $_TEXT_BODY)) >= 0) {
 

t/tei.t

diff --git a/t/tei.t b/t/tei.t
index 928d28f..94f7577 100644
--- a/t/tei.t
+++ b/t/tei.t
@@ -7,7 +7,7 @@
   unshift @INC, "$FindBin::Bin/../lib";
 };
 
-use Test::KorAP::XML::TEI qw!korap_tempfile!;
+use Test::KorAP::XML::TEI qw!korap_tempfile test_tei2korapxml!;
 
 use_ok('KorAP::XML::TEI', 'remove_xml_comments', 'escape_xml');
 
@@ -45,6 +45,21 @@
   close($fh);
 };
 
+
+subtest 'remove_xml_comments in script' => sub {
+  test_tei2korapxml(
+    template => {
+      text => "<!--\nDies ist ein\nmehrzeiligerKommentar -->Text1",
+      textSigle => 'A/B.1',
+      pattern => 'xx'
+    }
+  )
+    ->file_exists('A/B/1/data.xml')
+    ->unzip_xml('A/B/1/data.xml')
+    ->text_is('text', 'Text1');
+};
+
+
 subtest 'escape_xml' => sub {
   is(
     escape_xml('"""'),