Welcome to mirror list, hosted at ThFree Co, Russian Federation.

github.com/moses-smt/mosesdecoder.git - Unnamed repository; edit this file 'description' to name the repository.
summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat (limited to 'scripts/generic/lopar2pos.pl')
-rwxr-xr-xscripts/generic/lopar2pos.pl15
1 files changed, 15 insertions, 0 deletions
diff --git a/scripts/generic/lopar2pos.pl b/scripts/generic/lopar2pos.pl
new file mode 100755
index 000000000..84529eaf7
--- /dev/null
+++ b/scripts/generic/lopar2pos.pl
@@ -0,0 +1,15 @@
+#!/usr/bin/perl -w
+
+# $Id: lopar2pos.pl 1307 2007-03-14 22:22:36Z hieuhoang1972 $
+#lopar2pos: extract POSs from LOPAR output
+#usage: lopar2pos.pl CORPUS.lopar > CORPUS.pos
+
+my $infilename = shift @ARGV;
+open(INFILE, "<$infilename") or die "couldn't open '$infilename' for read: $!\n";
+while(my $line = <INFILE>)
+{
+ my @words = split(/\s+/, $line);
+ my @tags = map {$_ =~ /^[^_]*_([A-Z]+)/; $1} @words;
+ print join(' ', @tags) . "\n";
+}
+close(INFILE);