Merge "Remove the call for select_tokenization as it needlessly doubles the tokenizer check"
diff --git a/script/tei2korapxml b/script/tei2korapxml
index 80178fc..785e976 100755
--- a/script/tei2korapxml
+++ b/script/tei2korapxml
@@ -362,13 +362,30 @@
if ( $_GEN_TOK_EXT || $_GEN_TOK_INT ){
- select_tokenization();
+ if ( $_GEN_TOK_EXT ) {
- if ( $_GEN_TOK_INT ){
+ $ext_tok->to_zip(
+ $zipper->new_stream("$_root_dir$dir/$_tok_dir/$_tok_file_ext"),
+ $text_id_esc
+ );
+
+ } elsif ( $_GEN_TOK_INT ){
+
+ # Output token streams to zip streams
+ $cons_tok->to_zip(
+ $zipper->new_stream("$_root_dir$dir/$_tok_dir/$_tok_file_con"),
+ $text_id_esc
+ );
+ $aggr_tok->to_zip(
+ $zipper->new_stream("$_root_dir$dir/$_tok_dir/$_tok_file_agg"),
+ $text_id_esc
+ );
$offset = 0;
$aggr_tok->reset;
$cons_tok->reset;
}
+
+ #print STDERR "$0: write_tokenization(): DONE\n";
}
$data_fl = 0; $buf_in = $data = $dir = ""; # reinit.
@@ -1032,35 +1049,6 @@
} # end: sub retr_info
-sub select_tokenization { # called from process()
-
- #print STDERR "$0: select_tokenization() ...\n";
-
- if( $_GEN_TOK_EXT ) {
-
- $ext_tok->to_zip(
- $zipper->new_stream("$_root_dir$dir/$_tok_dir/$_tok_file_ext"),
- $text_id_esc
- );
-
- }elsif( $_GEN_TOK_INT ){
-
- # Output token streams to zip streams
- $cons_tok->to_zip(
- $zipper->new_stream("$_root_dir$dir/$_tok_dir/$_tok_file_con"),
- $text_id_esc
- );
- $aggr_tok->to_zip(
- $zipper->new_stream("$_root_dir$dir/$_tok_dir/$_tok_file_agg"),
- $text_id_esc
- );
- }
-
- #print STDERR "$0: write_tokenization(): DONE\n";
-
-} # end: select_tokenization
-
-
sub write_structures { # called from process()
# ~ write @structures ~