code format cleanup

.github/workflows/lint-and-test.yml

@@ -32,12 +32,16 @@ jobs:
 
     - run: python -V
     - run: pip -V
+
     - run: pip install -e .
+    - run: pip install -r requirements_dev.txt
 
     - name: Lint
-      continue-on-error: true
-      # run: flake8 pdfx tests setup.py --exclude="pdfx/libs,pdfx/extractor.py"
-      run: flake8 pdfx tests setup.py
+      run: make lint
 
-    - name: Run the test suite
-      run: py.test --strict --capture=no tests
+    - name: Test
+      run: make test
+
+    - name: Checks
+      continue-on-error: true
+      run: make ceck

pdfx/__init__.py

@@ -31,23 +31,26 @@
 License: GPLv3
 """
 from __future__ import absolute_import, division, print_function, unicode_literals
-from pdfminer.pdfparser import PDFSyntaxError
-from .exceptions import FileNotFoundError, DownloadError, PDFInvalidError
-from .downloader import download_urls
-from .backends import PDFMinerBackend, TextBackend
-from .extractor import extract_urls
+
+__title__ = "pdfx"
+__version__ = "1.3.1"
+__author__ = "Chris Hager"
+__license__ = "Apache 2.0"
+__copyright__ = "Copyright 2015 Chris Hager"
 
 import os
 import sys
 import json
 import shutil
 import logging
 
-__title__ = "pdfx"
-__version__ = "1.3.1"
-__author__ = "Chris Hager"
-__license__ = "Apache 2.0"
-__copyright__ = "Copyright 2015 Chris Hager"
+
+from .extractor import extract_urls
+from .backends import PDFMinerBackend, TextBackend
+from .downloader import download_urls
+from .exceptions import FileNotFoundError, DownloadError, PDFInvalidError
+from pdfminer.pdfparser import PDFSyntaxError
+
 
 IS_PY2 = sys.version_info < (3, 0)
 
@@ -62,7 +65,6 @@
 
     unicode = str
 
-
 logger = logging.getLogger(__name__)
 
 
@@ -92,7 +94,7 @@ class PDFx(object):
     reader = None  # ReaderBackend
     summary = {}
 
-    def __init__(self, uri):  # noqa: C901
+    def __init__(self, uri):
         """
         Open PDF handle and parse PDF metadata
         - `uri` can bei either a filename or an url

pdfx/backends.py

@@ -4,14 +4,6 @@
 """
 
 from __future__ import absolute_import, division, print_function, unicode_literals
-from pdfminer.layout import LAParams
-from pdfminer.converter import TextConverter
-from pdfminer.pdftypes import resolve1, PDFObjRef
-from pdfminer.pdfpage import PDFPage
-from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
-from pdfminer.pdfparser import PDFParser
-from pdfminer.pdfdocument import PDFDocument
-from pdfminer import psparser
 
 import sys
 import logging
@@ -30,6 +22,14 @@
 from pdfminer import settings as pdfminer_settings
 
 pdfminer_settings.STRICT = False
+from pdfminer import psparser  # noqa: E402
+from pdfminer.pdfdocument import PDFDocument  # noqa: E402
+from pdfminer.pdfparser import PDFParser  # noqa: E402
+from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter  # noqa: E402
+from pdfminer.pdfpage import PDFPage  # noqa: E402
+from pdfminer.pdftypes import resolve1, PDFObjRef  # noqa: E402
+from pdfminer.converter import TextConverter  # noqa: E402
+from pdfminer.layout import LAParams  # noqa: E402
 
 
 logger = logging.getLogger(__name__)
@@ -41,7 +41,7 @@
     unicode = str
 
 
-def make_compat_str(in_str):  # noqa: C901
+def make_compat_str(in_str):
     """
     Tries to guess encoding of [str/bytes] and
     return a standard unicode string
@@ -134,7 +134,7 @@ def __init__(self):
     def get_metadata(self):
         return self.metadata
 
-    def metadata_key_cleanup(self, d, k):  # noqa: C901
+    def metadata_key_cleanup(self, d, k):
         """ Recursively clean metadata dictionaries """
         if isinstance(d[k], (str, unicode)):
             d[k] = d[k].strip()
@@ -264,7 +264,7 @@ def __init__(self, pdf_stream, password="", pagenos=[], maxpages=0):  # noqa: C9
         for ref in extractor.extract_doi(self.text):
             self.references.add(Reference(ref, self.curpage))
 
-    def resolve_PDFObjRef(self, obj_ref):  # noqa: C901
+    def resolve_PDFObjRef(self, obj_ref):
         """
         Resolves PDFObjRef objects. Returns either None, a Reference object or
         a list of Reference objects.

pdfx/cli.py

@@ -97,7 +97,7 @@ def create_parser():
     return parser
 
 
-def get_text_output(pdf, args):  # noqa: C901
+def get_text_output(pdf, args):
     """ Normal output of infos of PDFx instance """
     # Metadata
     ret = ""
@@ -145,7 +145,7 @@ def print_to_console(text):
     sys.stdout.write("\n")
 
 
-def main():  # noqa: C901
+def main():
     parser = create_parser()
     args = parser.parse_args()
 

pdfx/downloader.py

@@ -58,7 +58,7 @@ def get_status_code(url):
         return None
 
 
-def check_refs(refs, verbose=True, max_threads=MAX_THREADS_DEFAULT):  # noqa: C901
+def check_refs(refs, verbose=True, max_threads=MAX_THREADS_DEFAULT):
     """ Check if urls exist """
     codes = defaultdict(list)
 
@@ -97,7 +97,7 @@ def check_url(ref):
                 print(o)
 
 
-def download_urls(  # noqa: C901
+def download_urls(
     urls, output_directory, verbose=True, max_threads=MAX_THREADS_DEFAULT
 ):
     """ Download urls to a target directory """

setup.cfg

@@ -6,4 +6,4 @@ universal = 1
 
 [flake8]
 max-line-length = 100
-max-complexity = 5
+max-complexity = 15