From 899f78c7c4c3a8cff97494665ed52ddb3460d44a Mon Sep 17 00:00:00 2001
From: Victor Chahuneau <vchahune@cs.cmu.edu>
Date: Thu, 21 Jun 2012 17:27:48 -0400
Subject: Allow SA rule extraction to write to a python buffer

+ very small sa-extract cleanup
---
 python/cdec/scfg/extractor.py | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'python')

diff --git a/python/cdec/scfg/extractor.py b/python/cdec/scfg/extractor.py
index 9f1e1137..0a45ddb8 100644
--- a/python/cdec/scfg/extractor.py
+++ b/python/cdec/scfg/extractor.py
@@ -1,5 +1,5 @@
-#!/usr/bin/env python
 import StringIO
+from itertools import chain
 
 import clex
 import rulefactory
@@ -9,12 +9,12 @@ import cdat
 import sym
 import log
 
-log.level = -1
-
 from features import EgivenFCoherent, SampleCountF, CountEF,\
         MaxLexEgivenF, MaxLexFgivenE, IsSingletonF, IsSingletonFE
 from features import contextless
 
+log.level = -1
+
 class Output(StringIO.StringIO):
     def close(self):
         pass
@@ -22,8 +22,6 @@ class Output(StringIO.StringIO):
     def __str__(self):
         return self.getvalue()
 
-from itertools import chain
-
 def get_cn(sentence):
     sentence = chain(('<s>',), sentence.split(), ('</s>',))
     sentence = (sym.fromstring(word, terminal=True) for word in sentence)
@@ -93,9 +91,11 @@ class GrammarExtractor:
         self.models = tuple(contextless(feature) for feature in self.models)
 
     def grammar(self, sentence):
+        if isinstance(sentence, unicode):
+            sentence = sentence.encode('utf8')
         out = Output()
         cn = get_cn(sentence)
-        self.factory.input_file(cn, out)
+        self.factory.input(cn, output=out)
         return str(out)
 
 def main(config):
-- 
cgit v1.2.3