fixed problem with escaped unicode chars, from Spanish smple data

transcript_processing/converter.py

@@ -87,14 +87,14 @@ class TranscriptConverter:
         else:
             if word.upper() == 'I':
                 return True
-            word_category = tagged_words[index][1] 
+            word_category = tagged_words[index][1]
             return word_category in helpers.PROPER_NOUN_TAGS
 
     def get_word_object(
-            self, 
-            word_object, 
-            index, 
-            tagged_words, 
+            self,
+            word_object,
+            index,
+            tagged_words,
             word_objects,
             speaker_segments=None,
             ):
@@ -107,7 +107,7 @@ class TranscriptConverter:
             self.check_if_always_capitalized(word, index, tagged_words),
             self.get_next_word(word_objects, index),
             self.get_speaker_id(word_object, speaker_segments),
-                ) 
+                )
 
     def get_next_word(self, word_objects, index):
         if index < len(word_objects) - 1:

transcript_processing/converters/google.py

@@ -1,3 +1,4 @@
+import codecs
 import json
 import re
 
@@ -38,6 +39,7 @@ class GoogleConverter(TranscriptConverter):
             punc_after = helpers.get_punc_after(word_obj.word) or False
 
             the_word = word_obj.word
+
             if punc_before:
                 the_word = the_word[len(punc_before):]
             if punc_after:
@@ -128,6 +130,7 @@ def make_json_friendly(json_string):
 
         new_string += line
 
-    new_string = new_string.replace('\\', '')
+    if '\\' in new_string:
+        new_string = codecs.escape_decode(new_string)[0].decode('utf-8')
 
     return new_string[:-2] + ']'

transcript_processing/helpers.py

@@ -24,19 +24,19 @@ def is_a_proper_noun(phrase):
 def get_punc_before(word):
     punc = []
     for char in word:
-        if char.isalpha():
-            return punc
         if char in PUNCTUATION:
             punc.append(char)
+        else:
+            return punc
 
 
 def get_punc_after(word):
     punc = []
     for char in reversed(word):
-        if char.isalpha():
-            return punc
         if char in PUNCTUATION:
             punc.insert(0, char)
+        else:
+            return punc
 
 
 def is_path(string):

transcript_processing/tpro.py

@@ -11,7 +11,7 @@ output_choices =  [k for k, v in
                    if callable(v)]
 
 @click.command()
-@click.option('-p', '--print-output', is_flag=True, default=True,
+@click.option('-p', '--print-output', is_flag=True, default=False,
         help='pretty print the transcript, breaks pipeability')
 @click.option('--language-code', default='en-US',
         help='specify language, defaults to en-US.')