Introduce exclusivity for inline token handling
Change-Id: Ia34ec87b2c55aabd94c65ec1e0d63d0cadb27d75
diff --git a/script/tei2korapxml b/script/tei2korapxml
index 10a2787..0d196a5 100755
--- a/script/tei2korapxml
+++ b/script/tei2korapxml
@@ -42,6 +42,9 @@
warn 'KORAPXMLTEI_INLINE is deprecated in favor of --skip-inline-token-annotations';
};
+# Inline tokens won't be stored in the structure file
+my $inline_tokens_exclusive = 0;
+
# Parse options from the command line
GetOptions(
'root|r=s' => \(my $root_dir = '.'),
@@ -136,6 +139,11 @@
# i.e. tokens of the $_TOKENS_TAG, if $_TOKENS_PROC is set
my ($_tokens_dir, $_tokens_file) = split '#', $inline_tokens . '#morpho';
+if (index($_tokens_dir, '!') == 0) {
+ $_tokens_dir = substr($_tokens_dir, 1);
+ $inline_tokens_exclusive = 1;
+};
+
# Initialize zipper
my $zipper = KorAP::XML::TEI::Zipper->new($root_dir);
@@ -168,7 +176,8 @@
# Create inline parser object
my $inline = KorAP::XML::TEI::Inline->new(
$skip_inline_tokens,
- \%skip_inline_tags
+ \%skip_inline_tags,
+ $inline_tokens_exclusive
);
@@ -532,6 +541,17 @@
this will contain annotations as well.
Defaults to C<tokens> and C<morpho>.
+The inline token data will also be stored in the
+inline structures file (see I<--inline-structures>),
+unless the inline token foundry is prepended
+by an B<!> exclamation mark, indicating that inline
+tokens are stored exclusively in the inline tokens
+file.
+
+Example:
+
+ tei2korapxml --inline-tokens '!gingko#morpho' < data.i5.xml > korapxml.zip
+
=item B<--inline-structures> <foundry>#[<file>]
Define the foundry and file (without extension)