From 224be546596aae5fe3bcd9c46d3eac3f84b386fd Mon Sep 17 00:00:00 2001 From: Patrick Simianer
Date: Sun, 16 Mar 2014 19:17:24 +0100 Subject: no non printables in preproc --- preprocess | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'preprocess') diff --git a/preprocess b/preprocess index 4bf782a..f3c3d10 100755 --- a/preprocess +++ b/preprocess @@ -1,5 +1,5 @@ #!/bin/bash LANG=$1 -/toolbox/scripts/htmlentities 2>htmlentities.$LANG.err | /toolbox/scripts/normalize_punctuation 2>normalize-punctuation.$LANG.err | /toolbox/moses/scripts/tokenizer/tokenizer.no-escape.perl -a -b -threads 1 -l $LANG 2>tokenizer.$LANG.err | /toolbox/moses/scripts/tokenizer/lowercase.perl 2>lowercase.$LANG.err +/toolbox/scripts/no_non_printables | /toolbox/scripts/htmlentities 2>htmlentities.$LANG.err | /toolbox/scripts/normalize_punctuation 2>normalize-punctuation.$LANG.err | /toolbox/moses/scripts/tokenizer/tokenizer.no-escape.perl -a -b -threads 1 -l $LANG 2>tokenizer.$LANG.err | /toolbox/moses/scripts/tokenizer/lowercase.perl 2>lowercase.$LANG.err -- cgit v1.2.3