fixed bug in cli that didn't handle txt files (from google)

transcript_processing/converter.py

@@ -33,6 +33,11 @@ class TranscriptConverter:
                 tagged_words
                 )
 
+    @property        
+    @abc.abstractmethod
+    def transcript_type(self):
+        pass
+
     @abc.abstractmethod
     def get_word_objects(self, json_data):
         pass

transcript_processing/converters/amazon.py

@@ -9,6 +9,7 @@ from .. import helpers
 class AmazonConverter(TranscriptConverter):
 
     name = 'amazon'
+    transcript_type = dict
 
     def __init__(self, json_data):
         super().__init__(json_data)

transcript_processing/converters/gentle.py

@@ -6,6 +6,7 @@ from ..converter import TranscriptConverter
 class GentleConverter(TranscriptConverter):
 
     name = 'gentle'
+    transcript_type = dict
 
     def __init__(self, json_data):
         super().__init__(json_data)

transcript_processing/converters/google.py

@@ -8,6 +8,8 @@ from .. import helpers
 
 class GoogleConverter(TranscriptConverter):
 
+    transcript_type = str
+
     def __init__(self, transcript_data: str):
         super().__init__(transcript_data)
         self.json_data = self.pre_process(transcript_data)

transcript_processing/converters/speechmatics.py

@@ -9,6 +9,7 @@ from .. import helpers
 class SpeechmaticsConverter(TranscriptConverter):
 
     name = 'speechmatics'
+    transcript_type = dict
 
     def __init__(self, path):
         super().__init__(path)

transcript_processing/outputs.py

@@ -10,7 +10,7 @@ def vo(self):
         if word['always_capitalized']:
             word_word = word['word'].title()
         else:
-            word_word['word']
+            word_word = word['word']
 
         transcript.append({
             'start': word['start'],

transcript_processing/tpro.py

@@ -23,10 +23,15 @@ def cli(print_output,
         input_format,
         output_format):
 
-    json_data = json.load(transcript_data_path)
-    service = services[input_format]
+    transcript_data_file_handle = transcript_data_path
 
-    converter = service(json_data)
+    service = services[input_format]
+    if service.transcript_type == dict:
+        transcript_data = json.load(transcript_data_file_handle)
+    else:
+        transcript_data = transcript_data_file_handle.read()
+
+    converter = service(transcript_data)
     converter.convert()
     converter.save(output_path, output_format)