[MRG + 1] Make pep8 (#125)

* Make setup.py pep8

Add new line at end of file, fix bare except, remove unused import.

* Make tests/*.py pep8

Add some newlines at and of files and a visual indent.

* Make docs/*.py pep8

Fix block comments and add new lines at end of files.

* Make camelot/*.py pep8

Fixed unused import, a few weirdly ordered imports, a docstring typo and  many new lines at the end of lines.

* Fix imports

Fix import order and remove a couple more unused imports.

* Fix indents

Fix indentation (no opening delimiter alignment).

* Add newlines

camelot/__init__.py

@@ -2,6 +2,9 @@
 
 import logging
 
+from .__version__ import __version__
+from .io import read_pdf
+
 
 # set up logging
 logger = logging.getLogger('camelot')
@@ -12,8 +15,3 @@ handler = logging.StreamHandler()
 handler.setFormatter(formatter)
 
 logger.addHandler(handler)
-
-
-from .__version__ import __version__
-
-from .io import read_pdf

camelot/cli.py

@@ -2,15 +2,16 @@
 
 import logging
 
-logger = logging.getLogger('camelot')
-logger.setLevel(logging.INFO)
-
 import click
 
 from . import __version__
 from .io import read_pdf
 
 
+logger = logging.getLogger('camelot')
+logger.setLevel(logging.INFO)
+
+
 class Config(object):
     def __init__(self):
         self.config = {}

camelot/core.py

@@ -1,7 +1,6 @@
 # -*- coding: utf-8 -*-
 
 import os
-import json
 import zipfile
 import tempfile
 

camelot/image_processing.py

@@ -1,8 +1,6 @@
 # -*- coding: utf-8 -*-
 
 from __future__ import division
-from itertools import groupby
-from operator import itemgetter
 
 import cv2
 import numpy as np
@@ -40,10 +38,12 @@ def adaptive_threshold(imagename, process_background=False, blocksize=15, c=-2):
     gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
 
     if process_background:
-        threshold = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
+        threshold = cv2.adaptiveThreshold(
+            gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
             cv2.THRESH_BINARY, blocksize, c)
     else:
-        threshold = cv2.adaptiveThreshold(np.invert(gray), 255,
+        threshold = cv2.adaptiveThreshold(
+            np.invert(gray), 255,
             cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, blocksize, c)
     return img, threshold
 

camelot/parsers/lattice.py

@@ -201,8 +201,9 @@ class Lattice(BaseParser):
             if 'ghostscript' in subprocess.check_output(['gs', '-version']).decode('utf-8').lower():
                 gs_call.insert(0, 'gs')
             else:
-                gs_call.insert(0, 'gsc')
+                gs_call.insert(0, "gsc")
-        subprocess.call(gs_call, stdout=open(os.devnull, 'w'),
+        subprocess.call(
+            gs_call, stdout=open(os.devnull, 'w'),
             stderr=subprocess.STDOUT)
 
     def _generate_table_bbox(self):
@@ -339,8 +340,8 @@ class Lattice(BaseParser):
 
         _tables = []
         # sort tables based on y-coord
-        for table_idx, tk in enumerate(sorted(self.table_bbox.keys(),
+        for table_idx, tk in enumerate(sorted(
-                key=lambda x: x[1], reverse=True)):
+                self.table_bbox.keys(), key=lambda x: x[1], reverse=True)):
             cols, rows, v_s, h_s = self._generate_columns_and_rows(table_idx, tk)
             table = self._generate_table(table_idx, cols, rows, v_s=v_s, h_s=h_s)
             _tables.append(table)

camelot/parsers/stream.py

@@ -357,8 +357,8 @@ class Stream(BaseParser):
 
         _tables = []
         # sort tables based on y-coord
-        for table_idx, tk in enumerate(sorted(self.table_bbox.keys(),
+        for table_idx, tk in enumerate(sorted(
-                key=lambda x: x[1], reverse=True)):
+                self.table_bbox.keys(), key=lambda x: x[1], reverse=True)):
             cols, rows = self._generate_columns_and_rows(table_idx, tk)
             table = self._generate_table(table_idx, cols, rows)
             _tables.append(table)

camelot/utils.py

@@ -1,5 +1,4 @@
 from __future__ import division
-import os
 import shutil
 import tempfile
 import warnings
@@ -14,7 +13,6 @@ from pdfminer.pdfpage import PDFPage
 from pdfminer.pdfpage import PDFTextExtractionNotAllowed
 from pdfminer.pdfinterp import PDFResourceManager
 from pdfminer.pdfinterp import PDFPageInterpreter
-from pdfminer.pdfdevice import PDFDevice
 from pdfminer.converter import PDFPageAggregator
 from pdfminer.layout import (LAParams, LTAnno, LTChar, LTTextLineHorizontal,
                              LTTextLineVertical)

setup.py

@@ -2,7 +2,6 @@
 
 import os
 from setuptools import find_packages
-from pkg_resources import parse_version
 
 
 here = os.path.abspath(os.path.dirname(__file__))
@@ -56,7 +55,7 @@ def setup_package():
 
     try:
         from setuptools import setup
-    except:
+    except ImportError:
         from distutils.core import setup
 
     setup(**metadata)

tests/test_common.py

@@ -82,8 +82,8 @@ def test_stream_flag_size():
 def test_lattice():
     df = pd.DataFrame(data_lattice)
 
-    filename = os.path.join(testdir,
+    filename = os.path.join(
-        "tabula/icdar2013-dataset/competition-dataset-us/us-030.pdf")
+        testdir, "tabula/icdar2013-dataset/competition-dataset-us/us-030.pdf")
     tables = camelot.read_pdf(filename, pages="2")
     assert df.equals(tables[0].df)