From 1915f029aa02f3528dafcd7b80a62a9c890b462b Mon Sep 17 00:00:00 2001
From: Chris Dyer <cdyer@allegro.clab.cs.cmu.edu>
Date: Mon, 20 Jan 2014 00:11:27 -0500
Subject: hindi edits

---
 corpus/support/fix-eos.pl | 10 ++++++++++
 1 file changed, 10 insertions(+)
 create mode 100755 corpus/support/fix-eos.pl

(limited to 'corpus/support/fix-eos.pl')

diff --git a/corpus/support/fix-eos.pl b/corpus/support/fix-eos.pl
new file mode 100755
index 00000000..584f8b46
--- /dev/null
+++ b/corpus/support/fix-eos.pl
@@ -0,0 +1,10 @@
+#!/usr/bin/perl -w
+use strict;
+use utf8;
+
+binmode(STDIN, ":utf8");
+binmode(STDOUT, ":utf8");
+while(<STDIN>) {
+  s/(\p{Devanagari}{2}[A-Za-z0-9! ,.\@\p{Devanagari}]+?)\s+(\.)(\s*$|\s+\|\|\|)/$1 \x{0964}$3/s;
+  print;
+}
-- 
cgit v1.2.3