flake8

irs_reader/filing.py

@@ -1,22 +1,14 @@
 import io
 import json
 import os
-import sys
 from collections import OrderedDict
 from xml.parsers.expat import ExpatError
 
 import xmltodict
 
 from .file_utils import get_local_path, get_s3_URL, stream_download, validate_object_id
-from .settings import IRS_READER_ROOT, KNOWN_SCHEDULES
-from .type_utils import (
- dictType,
- listType,
- noneType,
- orderedDictType,
- strType,
- unicodeType,
-)
+from .settings import KNOWN_SCHEDULES
+from .type_utils import dictType, listType, orderedDictType
 
 
 class InvalidXMLException(Exception):

irs_reader/irsx_cli.py

@@ -1,8 +1,8 @@
 import argparse
 
 from .filing import Filing
-from .settings import IRS_READER_ROOT, KNOWN_SCHEDULES
-from .text_format_utils import *
+from .settings import KNOWN_SCHEDULES
+from .text_format_utils import to_csv, to_json, to_txt
 from .xmlrunner import XMLRunner
 
 

irs_reader/irsx_index_cli.py

@@ -1,5 +1,4 @@
 import argparse
-import sys
 from datetime import date
 
 from .file_utils import get_index_file_URL, get_local_index_path, stream_download

irs_reader/irsx_retrieve_cli.py

@@ -1,6 +1,5 @@
 import argparse
 import os
-import sys
 from zipfile import ZipFile
 
 from .file_utils import stream_download
@@ -79,7 +78,7 @@ def run_cli_retrieve_main(args_read):
  print(
  """
  Please visit https://www.irs.gov/charities-non-profits/form-990-series-downloads
- To see if any additional files are available. 
+ To see if any additional files are available.
  """
  )
  for year in args_read.year:

irs_reader/keyerror_utils.py

@@ -1,6 +1,6 @@
 ignorable_keyerrors = ["/ReturnHeader/BuildTS"]
 
-## Todo: put in 2013 / 2015 series canonicals.
+# Todo: put in 2013 / 2015 series canonicals.
 # 2013 vars that no longer exist
 discontinued_2013_vars = [
  "/IRS990ScheduleA/CertificationInd",

irs_reader/settings.py

@@ -1,5 +1,4 @@
 import os
-import sys
 
 from .dir_utils import mkdir_p
 
@@ -117,7 +116,7 @@
 ]
 
 # 2020 is experimental
-# see https://www.irs.gov/charities-non-profits/ty2020-xml-schemas-and-business-rules-for-exempt-organizations-modernized-e-file
+# see https://www.irs.gov/charities-non-profits/ty2020-xml-schemas-and-business-rules-for-exempt-organizations-modernized-e-file # noqa
 
 # We can capture the group structure for these so it doesn't break
 # but these versions ARE NOT supported and aren't mapped to IRSx variables
@@ -145,6 +144,6 @@
 mkdir_p([WORKING_DIRECTORY, INDEX_DIRECTORY])
 
 try:
- from .local_settings import *
+ from .local_settings import * # noqa
 except ImportError:
  pass

irs_reader/sked_dict_reader.py

@@ -1,6 +1,5 @@
 from .flatten_utils import flatten
 from .keyerror_utils import ignorable_keyerror
-from .settings import LOG_KEY
 from .type_utils import (
  dictType,
  listType,
@@ -228,7 +227,8 @@ def _parse_json(self, json_node, parent_path=""):
  pass
 
  elif this_node_type == strType:
- msg = "String '%s'" % json_node
+ pass
+ # msg = "String '%s'" % json_node
  # self.logging.debug(msg)
  else:
  raise Exception("Unhandled type: %s" % (type(json_node)))

irs_reader/standardizer.py

@@ -1,18 +1,7 @@
-import collections
+import csv
 import os
-import sys
 
-# import logging
-from datetime import datetime
-
-from .settings import KEYERROR_LOG, METADATA_DIRECTORY
-from .sked_dict_reader import SkedDictReader
-from .type_utils import listType
-
-if sys.version_info >= (3, 0):
- import csv
-else:
- import unicodecsv as csv
+from .settings import METADATA_DIRECTORY
 
 
 class Standardizer(object):

irs_reader/text_format_utils.py

@@ -6,7 +6,7 @@
 
 import unicodecsv
 
-from .standardizer import Documentizer, Standardizer, VersionDocumentizer
+from .standardizer import VersionDocumentizer
 
 BRACKET_RE = re.compile(r"\[.*?\]")
 
@@ -114,7 +114,7 @@ def to_txt(
  for result in results:
  for this_result in result["csv_line_array"]:
 
- #### Collect the variables we need
+ # Collect the variables we need
  vardata = None
  textoutput = "\n" # This is what we'll eventually write out
  this_result["form"] = this_result["xpath"].split("/")[1]
@@ -137,7 +137,7 @@ def to_txt(
  )
  this_result["description"] = debracket(raw_description)
 
- #### Write the output, now that we've got the vars
+ # Write the output, now that we've got the vars
 
  if this_sked_name != this_result["form"]:
  textoutput += (

irs_reader/xmlrunner.py

@@ -1,11 +1,7 @@
 from .filing import Filing
-from .settings import (
- ALLOWED_VERSIONSTRINGS,
- CSV_ALLOWED_VERSIONSTRINGS,
- WORKING_DIRECTORY,
-)
+from .settings import ALLOWED_VERSIONSTRINGS, CSV_ALLOWED_VERSIONSTRINGS
 from .sked_dict_reader import SkedDictReader
-from .standardizer import Documentizer, Standardizer, VersionDocumentizer
+from .standardizer import Documentizer, Standardizer
 
 # from .log_utils import configure_logging
 from .type_utils import listType
@@ -149,30 +145,6 @@ def run_filing(self, object_id, verbose=False):
  print("Filing version %s isn't supported for this operation" % this_version)
  return this_filing
 
- """
- def run_from_filing_obj(self, this_filing, verbose=False): 
- 
- #Run from a pre-created filing object.
- 
- self.whole_filing_data = []
- self.filing_keyerr_data = []
- this_filing.process(verbose=verbose)
- object_id = this_filing.get_object_id()
- this_version = this_filing.get_version()
- if this_version in ALLOWED_VERSIONSTRINGS:
- this_version = this_filing.get_version()
- schedules = this_filing.list_schedules()
- ein = this_filing.get_ein()
- for sked in schedules:
- sked_dict = this_filing.get_schedule(sked)
- self._run_schedule(sked, object_id, sked_dict, ein)
- this_filing.set_result(self.whole_filing_data)
- this_filing.set_keyerrors(self.filing_keyerr_data)
- return this_filing
- else:
- return this_filing
- """
-
  def run_sked(self, object_id, sked, verbose=False):
  """
  sked is the proper name of the schedule:

setup.py

@@ -23,12 +23,7 @@
  install_requires=["requests", "xmltodict", "unicodecsv"],
  extras_require={
  "tests": [
- "nose",
- "requests",
- "xmltodict",
- "unicodecsv",
- "tox",
- "tox-pyenv",
+ "pytest",
  ]
  },
  packages=["irsx"],

tests/tests.py → tests/test_all.py

@@ -2,16 +2,15 @@
 
 import pytest
 
-from irs_reader.file_utils import validate_object_id
-from irs_reader.filing import Filing
-from irs_reader.irsx_cli import get_parser as get_cli_parser
-from irs_reader.irsx_cli import run_main as run_cli_main
-from irs_reader.irsx_index_cli import get_cli_index_parser, run_cli_index_main
-from irs_reader.object_ids import (object_ids_2015, object_ids_2016,
- object_ids_2017)
-from irs_reader.settings import WORKING_DIRECTORY
-from irs_reader.standardizer import Standardizer
-from irs_reader.xmlrunner import XMLRunner
+from irsx.file_utils import validate_object_id
+from irsx.filing import Filing
+from irsx.irsx_cli import get_parser as get_cli_parser
+from irsx.irsx_cli import run_main as run_cli_main
+from irsx.irsx_index_cli import get_cli_index_parser, run_cli_index_main
+from irsx.object_ids import object_ids_2015, object_ids_2016, object_ids_2017
+from irsx.settings import WORKING_DIRECTORY
+from irsx.standardizer import Standardizer
+from irsx.xmlrunner import XMLRunner
 
 FILING_2015V21 = "201642229349300909"
 FILING_2015V21_skeds = [