initial checkin

git-svn-id: https://ws10smt.googlecode.com/svn/trunk@2 ec762483-ff6d-05da-a07a-a48fb63a330f

1 files changed, 32 insertions, 0 deletions

diff --git a/word-aligner/ortho-norm/ar.pl b/word-aligner/ortho-norm/ar.pl
new file mode 100755
index 00000000..e8bd521a
--- /dev/null
+++ b/word-aligner/ortho-norm/ar.pl
@@ -0,0 +1,32 @@
+#!/usr/bin/perl -w
+use strict;
+use utf8;
+
+binmode(STDIN, ":utf8");
+binmode(STDOUT, ":utf8");
+
+while(<STDIN>) {
+  chomp;
+  my $len = length($_);
+  if ($len > 1 && !($_ =~ /\d/)) {
+    s/\$/sh/g;
+  }
+  s/([a-z])\~/$1$1/g;
+  s/E/'/g;
+  s/^Aw/o/g;
+  s/\|/a/g;
+  s/@/h/g;
+  s/c/ch/g;
+  s/x/kh/g;
+  s/\*/dh/g;
+  s/w/o/g;
+  s/v/th/g;
+  if ($len > 1) { s/}/'/g; }
+  s/Z/dh/g;
+  s/y/i/g;
+  s/Y/a/g;
+  if ($len > 1) { s/p$//; }
+  $_ = lc $_;
+  print "$_\n";
+}
+