Add --auto-textsigle <start-sigle> option
Also allows for processing plain TEI P5 files without any IDs.
Change-Id: Ic16b089c916d2e50458aa1aa6cb80ce4d37d97ba
diff --git a/script/tei2korapxml b/script/tei2korapxml
index 418408e..86f7527 100755
--- a/script/tei2korapxml
+++ b/script/tei2korapxml
@@ -6,6 +6,7 @@
use Log::Any::Adapter;
use Pod::Usage;
use Getopt::Long qw(GetOptions :config no_auto_abbrev);
+use KorAP::XML::TEI qw(increase_auto_textsigle);
use File::Basename qw(dirname);
@@ -45,6 +46,7 @@
# Parse options from the command line
GetOptions(
+ 'auto-textsigle|A=s' => \(my $auto_textsigle = ''),
'root|r=s' => \(my $root_dir = '.'),
'input|i=s' => \(my $input_fname = ''),
'output|o=s' => \(my $output_fname = ''),
@@ -460,8 +462,11 @@
};
# Parse header
- my $header = KorAP::XML::TEI::Header->new($content, $input_enc, $text_id_esc)->parse($input_fh);
-
+ my $header = KorAP::XML::TEI::Header->new($content, $input_enc, $text_id_esc // $auto_textsigle)->parse($input_fh);
+ if ($auto_textsigle) {
+ $auto_textsigle = increase_auto_textsigle($auto_textsigle);
+ $log->debug("Auto-incremented text sigle to $auto_textsigle");
+ };
# Header was parseable
if ($header) {
@@ -666,6 +671,17 @@
Expects a comma-separated list of tags to be ignored when the structure
is parsed. Content of these tags however will be processed.
+=item B<--auto-textsigle> <textsigle>
+
+Expects a text sigle thats serves as fallback if no text sigles
+are given in the input data.
+The auto text sigle will be incremented for each text processed.
+
+Example:
+
+ tei2korapxml --auto-textsigle 'ICC/GER.00001' -s -tk - \
+ < data.i5.xml > korapxml.zip
+
=item B<--xmlid-to-textsigle> <from-regex>@<to-c/to-d/to-t>
Expects a regular replacement expression (separated by B<@> between the