pcbje / gransk Goto Github PK

import io

import gransk.api as api
import gransk.core.document as document

gransk = api.API(config_path=u'config.yml')

doc = document.get_document(u'C:\\Users\\mohit.motwani\\Desktop\\EY Projects\\testing.txt')
doc.tag = u'demo'

content= io.BytesIO(b'Data buffer')

gransk.add_file(doc, content)
gransk.stop()

[2019-01-08 13:01:33] [INFO] gransk.plugins.storage.es_index: {'error': {'root_cause': [{'type': 'mapper_parsing_exception', 'reason': 'No handler for type [string] declared on field [entity_value]'}], 'type': 'mapper_parsing_exception', 'reason': 'Failed to parse mapping [in_doc]: No handler for type [string] declared on field [entity_value]', 'caused_by': {'type': 'mapper_parsing_exception', 'reason': 'No handler for type [string] declared on field [entity_value]'}}, 'status': 400}
[2019-01-08 13:01:33] [ERROR] MAIN: could not process C:\Users\mohit.motwani\Desktop\EY Projects\testing.txt: [WinError 2] The system cannot find the file specified
Traceback (most recent call last):
  File "C:\Users\mohit.motwani\Desktop\EY Projects\gransk\gransk\api.py", line 72, in consume
    self.produce(helper.EXTRACT_META, doc, file_object)
  File "C:\Users\mohit.motwani\Desktop\EY Projects\gransk\gransk\core\abstract_subscriber.py", line 97, in produce
    self.pipeline.produce(topic, doc, payload)
  File "C:\Users\mohit.motwani\Desktop\EY Projects\gransk\gransk\core\pipeline.py", line 100, in produce
    callback(doc, payload)
  File "C:\Users\mohit.motwani\Desktop\EY Projects\gransk\gransk\core\abstract_subscriber.py", line 61, in time_consume
    self.consume(doc, payload)
  File "C:\Users\mohit.motwani\Desktop\EY Projects\gransk\gransk\plugins\extractors\file_meta.py", line 132, in consume
    mime_type = self.__get_mime_type(doc, payload)
  File "C:\Users\mohit.motwani\Desktop\EY Projects\gransk\gransk\plugins\extractors\file_meta.py", line 106, in __get_mime_type
    proc = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
  File "C:\Users\mohit.motwani\AppData\Local\Continuum\anaconda3\lib\subprocess.py", line 709, in __init__
    restore_signals, start_new_session)
  File "C:\Users\mohit.motwani\AppData\Local\Continuum\anaconda3\lib\subprocess.py", line 997, in _execute_child
    startupinfo)
FileNotFoundError: [WinError 2] The system cannot find the file specified

Traceback (most recent call last):
  File "C:/Users/mohit.motwani/AppData/Local/Continuum/anaconda3/Lib/site-packages/polyglot-16.7.4-py3.6.egg/polyglot/__main__.py", line 13, in <module>
    import logging
  File "C:\Users\mohit.motwani\AppData\Local\Continuum\anaconda3\lib\logging\__init__.py", line 26, in <module>
    import sys, os, time, io, traceback, warnings, weakref, collections
  File "C:\Users\mohit.motwani\AppData\Local\Continuum\anaconda3\lib\traceback.py", line 5, in <module>
    import linecache
  File "C:\Users\mohit.motwani\AppData\Local\Continuum\anaconda3\lib\linecache.py", line 11, in <module>
    import tokenize
  File "C:\Users\mohit.motwani\AppData\Local\Continuum\anaconda3\Lib\site-packages\polyglot-16.7.4-py3.6.egg\polyglot\tokenize\__init__.py", line 4, in <module>
    from .base import WordTokenizer, SentenceTokenizer
  File "C:\Users\mohit.motwani\AppData\Local\Continuum\anaconda3\Lib\site-packages\polyglot-16.7.4-py3.6.egg\polyglot\tokenize\base.py", line 7, in <module>
    from polyglot.base import Sequence
  File "C:\Users\mohit.motwani\AppData\Local\Continuum\anaconda3\lib\site-packages\polyglot-16.7.4-py3.6.egg\polyglot\__init__.py", line 12, in <module>
    from .base import Sequence, TokenSequence
  File "C:\Users\mohit.motwani\AppData\Local\Continuum\anaconda3\lib\site-packages\polyglot-16.7.4-py3.6.egg\polyglot\base.py", line 9, in <module>
    from concurrent.futures import ProcessPoolExecutor
  File "C:\Users\mohit.motwani\AppData\Local\Continuum\anaconda3\lib\concurrent\futures\__init__.py", line 8, in <module>
    from concurrent.futures._base import (FIRST_COMPLETED,
  File "C:\Users\mohit.motwani\AppData\Local\Continuum\anaconda3\lib\concurrent\futures\_base.py", line 8, in <module>
    import threading
  File "C:\Users\mohit.motwani\AppData\Local\Continuum\anaconda3\lib\threading.py", line 7, in <module>
    from traceback import format_exc as _format_exc
ImportError: cannot import name 'format_exc'