Merge pull request #544 from hellohaptik/BB-11092

(adhoc)(platform-support) Add logs for debugging the entity detection issue for NSDC

docker/Dockerfile

@@ -18,7 +18,7 @@ COPY docker/nginx.conf /etc/nginx/nginx.conf
 COPY docker/default.site.conf /etc/nginx/sites-available/default
 
 # TODO: Separate this out to a dev/test docker image
-RUN curl -sL https://deb.nodesource.com/setup_12.x | bash && \
+RUN curl -sL https://deb.nodesource.com/setup_16.x | bash && \
     apt-get install nodejs && \
     npm install -g newman && \
     npm install -g newman-reporter-htmlextra && \

ner_v2/api.py

@@ -799,6 +799,7 @@ def text(request):
 
         try:
             validate_text_request(request)
+            ner_logger.debug("Valid text request")
             # if verify success get detection data
             data = get_text_entity_detection_data(request)
         except InvalidTextRequest as err:

ner_v2/detectors/textual/text_detection.py

@@ -442,7 +442,7 @@ def _get_bulk_text_detection_with_variants(self, messages):
                                                   entity_list=entity_list,
                                                   text=text, processed_text=processed_text)
             final_list.append(result_list)
-
+        ner_logger.debug(f'[bulk_text_detection_with_variants] final_list: {final_list}')
         return final_list
 
     def _get_entity_substring_from_text(self, text, variant, entity_name):
@@ -668,7 +668,6 @@ def detect(self, message=None, **kwargs):
 
                 entities[entity] = out
             data_list.append(entities)
-
         return data_list
 
     def detect_bulk(self, messages=None, **kwargs):
@@ -768,7 +767,6 @@ def detect_bulk(self, messages=None, **kwargs):
 
                 entities[entity] = out
             data_list.append(entities)
-
         return data_list
 
     @staticmethod

ner_v2/detectors/textual/utils.py

@@ -72,13 +72,16 @@ def get_detection(message, entity_dict, bot_message=None, language=ENGLISH_LANG,
 
         detected entity output
     """
+    ner_logger.debug(f'[get_detection] message: {message}')
     text_detector = TextDetector(entity_dict=entity_dict, source_language_script=language,
                                  target_language_script=target_language_script)
     if isinstance(message, six.string_types):
         entity_output = text_detector.detect(message=message,
                                              bot_message=bot_message)
+        ner_logger.debug(f'[Single Message Detection] Entity Output {entity_output}')
     elif isinstance(message, (list, tuple)):
         entity_output = text_detector.detect_bulk(messages=message)
+        ner_logger.debug(f'[Multiple Message Detection] Entity Output {entity_output}')
     else:
         raise TypeError('`message` argument must be either of type `str`, `unicode`, `list` or `tuple`.')
 
@@ -158,10 +161,12 @@ def get_text_entity_detection_data(request):
     """
     request_data = json.loads(request.body)
     messages = request_data.get("messages", [])
+    ner_logger.debug(f"Request message data {messages}")
     bot_message = request_data.get("bot_message")
     entities = request_data.get("entities", {})
     target_language_script = request_data.get('language_script') or ENGLISH_LANG
     source_language = request_data.get('source_language') or ENGLISH_LANG
+    ner_logger.debug(f"Request entity data {entities}")
 
     data = []
 
@@ -188,10 +193,12 @@ def get_text_entity_detection_data(request):
         # get detection for text entities which has ignore_message flag
         if fallback_value_entities:
             output = get_output_for_fallback_entities(fallback_value_entities, source_language)
+            ner_logger.debug(f'[output_for_fallback_entities] output: {output}')
             data[0]["entities"].update(output)
 
         # get detection for text entities
         if text_value_entities:
+            ner_logger.debug(f'[output_for_fallback_entities] text_value_entities {text_value_entities}')
             output = get_detection(message=message_str, entity_dict=text_value_entities,
                                    structured_value=None, bot_message=bot_message,
                                    language_script=source_language,
@@ -202,14 +209,13 @@ def get_text_entity_detection_data(request):
     elif len(messages) > 1:
         text_detection_result = get_detection(message=messages, entity_dict=entities,
                                               structured_value=None, bot_message=bot_message)
-
         data = [{"entities": x, "language": source_language} for x in text_detection_result]
 
     else:
         ner_logger.debug("No valid message provided")
         raise InvalidTextRequest(f"Key `messages` is required to be a non-empty List[str], "
                                  f"but got a list with length {message_len}")
-
+    ner_logger.debug(f"Final data {data}")
     return data