Remove extract_text and extract_doc in favor of extract_sigle
Change-Id: I6577a8f453baab96e684da3b2238a31b4f0175e3
diff --git a/script/korapxml2krill b/script/korapxml2krill
index d53004b..5e5b315 100644
--- a/script/korapxml2krill
+++ b/script/korapxml2krill
@@ -769,9 +769,10 @@
# TODO: Make this OS independent
print '... ' . (
- $archive->extract_text(
- ($prefix ? './' : '') . $_, $output
- ) ? '' : 'not '
+ # TODO:
+ # - prefix???
+ $archive->extract_sigle([$_], $output, $jobs)
+ ? '' : 'not '
);
print "extracted.\n";
};
@@ -1004,7 +1005,7 @@
# because extraction can be horrible slow!
# Extract from archive
- if ($archive->extract_text($dirs[$i], $temp)) {
+ if ($archive->extract_sigle([join('/', $corpus, $doc, $text)], $temp, $sequential_extraction ? 1 : $jobs)) {
# Create corpus directory
my $input = catdir("$temp", $corpus);
@@ -1108,13 +1109,9 @@
print "\n";
- # TODO: Make this OS independent
- my $path = ($prefix ? './' : '') . $_;
-
print '... ' . (
- $archive->extract_doc(
- $path, $output, $sequential_extraction ? 1 : $jobs
- ) ? '' : 'not '
+ $archive->extract_sigle([$_], $output, $sequential_extraction ? 1 : $jobs)
+ ? '' : 'not '
);
print "extracted.\n";
}