basic unit test for vocabcompiler

2 files changed, 39 insertions, 2 deletions

diff --git a/boot/test.py b/boot/test.py
new file mode 100644
index 0000000..1c03a33
--- /dev/null
+++ b/boot/test.py
@@ -0,0 +1,36 @@
+import os
+import sys
+import unittest
+from mock import patch
+import vocabcompiler
+
+lib_path = os.path.abspath('../client')
+mod_path = os.path.abspath('../client/modules/')
+
+sys.path.append(lib_path)
+sys.path.append(mod_path)
+
+import g2p
+
+class TestVocabCompiler(unittest.TestCase):
+
+    def testWordExtraction(self):
+        sentences = "temp_sentences.txt"
+        dictionary = "temp_dictionary.dic"
+        languagemodel = "temp_languagemodel.lm"
+
+        words = ['HACKER', 'LIFE', 'FACEBOOK', 'THIRD', 'NO', 'JOKE', 'NOTIFICATION', 'MEANING', 'TIME', 'TODAY', 'SECOND', 'BIRTHDAY', 'KNOCK KNOCK', 'INBOX', 'OF', 'NEWS', 'YES', 'TOMORROW', 'EMAIL', 'WEATHER', 'FIRST', 'MUSIC', 'SPOTIFY']
+
+        with patch.object(g2p, 'translateWords') as translateWords:
+            with patch.object(vocabcompiler, 'text2lm') as text2lm:
+                vocabcompiler.compile(sentences, dictionary, languagemodel)
+
+                # 'words' is appended with ['MUSIC', 'SPOTIFY']
+                # so must be > 2 to have received WORDS from modules
+                translateWords.assert_called_once_with(words)
+                self.assertTrue(text2lm.called)
+        os.remove(sentences)
+        os.remove(dictionary)
+
+if __name__ == '__main__':
+    unittest.main()
diff --git a/boot/vocabcompiler.py b/boot/vocabcompiler.py
index a3aaf66..33fb0a8 100644
--- a/boot/vocabcompiler.py
+++ b/boot/vocabcompiler.py
@@ -48,6 +48,7 @@ def compile(sentences, dictionary, languagemodel):
             pass  # module probably doesn't have the property
 
     words = list(set(words))
+    print words
 
     # for spotify module
     words.extend(["MUSIC", "SPOTIFY"])
@@ -57,11 +58,11 @@ def compile(sentences, dictionary, languagemodel):
     zipped = zip(words, pronounced)
     lines = ["%s %s" % (x, y) for x, y in zipped]
 
-    with open(dictionary, "w") as f:
+    with open(dictionary, "w+") as f:
         f.write("\n".join(lines) + "\n")
 
     # create the language model
-    with open(sentences, "w") as f:
+    with open(sentences, "w+") as f:
         f.write("\n".join(words) + "\n")
         f.write("<s> \n </s> \n")
         f.close()