Update flake8 to the latest version and fix all errors

doc/conf.py

@@ -12,18 +12,11 @@
 # All configuration values have a default; values that are commented out
 # serve to show the default.
 
-import sys, os
-
-# If extensions (or modules to document with autodoc) are in another directory,
-# add these directories to sys.path here. If the directory is relative to the
-# documentation root, use os.path.abspath to make it absolute, like shown here.
-#sys.path.insert(0, os.path.abspath('.'))
+import sys
+import os
 
 # -- General configuration -----------------------------------------------------
 
-# If your documentation needs a minimal Sphinx version, state it here.
-#needs_sphinx = '1.0'
-
 # Add any Sphinx extension module names here, as strings. They can be extensions
 # coming with Sphinx (named 'sphinx.ext.*') or your custom ones.
 extensions = ['sphinx.ext.autodoc', 'sphinx.ext.doctest', 'sphinx.ext.viewcode']
@@ -34,9 +27,6 @@
 # The suffix of source filenames.
 source_suffix = '.rst'
 
-# The encoding of source files.
-#source_encoding = 'utf-8-sig'
-
 # The master toctree document.
 master_doc = 'index'
 
@@ -52,168 +42,35 @@
 version = '1.0'
 # The full version, including alpha/beta/rc tags.
 sys.path.append(os.path.abspath('..'))
-from html5lib import __version__
+from html5lib import __version__ # noqa
 release = __version__
 
-# The language for content autogenerated by Sphinx. Refer to documentation
-# for a list of supported languages.
-#language = 'en'
-
-# There are two options for replacing |today|: either, you set today to some
-# non-false value, then it is used:
-#today = ''
-# Else, today_fmt is used as the format for a strftime call.
-#today_fmt = '%B %d, %Y'
-
 # List of patterns, relative to source directory, that match files and
 # directories to ignore when looking for source files.
 exclude_patterns = ['_build', 'theme']
 
-# The reST default role (used for this markup: `text`) to use for all documents.
-#default_role = None
-
-# If true, '()' will be appended to :func: etc. cross-reference text.
-#add_function_parentheses = True
-
-# If true, the current module name will be prepended to all description
-# unit titles (such as .. function::).
-#add_module_names = True
-
-# If true, sectionauthor and moduleauthor directives will be shown in the
-# output. They are ignored by default.
-#show_authors = False
-
 # The name of the Pygments (syntax highlighting) style to use.
 pygments_style = 'sphinx'
 
-# A list of ignored prefixes for module index sorting.
-#modindex_common_prefix = []
-
-# If true, keep warnings as "system message" paragraphs in the built documents.
-#keep_warnings = False
-
-
 # -- Options for HTML output ---------------------------------------------------
 
 # The theme to use for HTML and HTML Help pages. See the documentation for
 # a list of builtin themes.
 html_theme = 'default'
 
-# Theme options are theme-specific and customize the look and feel of a theme
-# further. For a list of options available for each theme, see the
-# documentation.
-#html_theme_options = {}
-
-# Add any paths that contain custom themes here, relative to this directory.
-#html_theme_path = []
-
-# The name for this set of Sphinx documents. If None, it defaults to
-# "<project> v<release> documentation".
-#html_title = None
-
-# A shorter title for the navigation bar. Default is the same as html_title.
-#html_short_title = None
-
-# The name of an image file (relative to this directory) to place at the top
-# of the sidebar.
-#html_logo = None
-
-# The name of an image file (within the static path) to use as favicon of the
-# docs. This file should be a Windows icon file (.ico) being 16x16 or 32x32
-# pixels large.
-#html_favicon = None
-
-# Add any paths that contain custom static files (such as style sheets) here,
-# relative to this directory. They are copied after the builtin static files,
-# so a file named "default.css" will overwrite the builtin "default.css".
-#html_static_path = ['_static']
-
-# If not '', a 'Last updated on:' timestamp is inserted at every page bottom,
-# using the given strftime format.
-#html_last_updated_fmt = '%b %d, %Y'
-
-# If true, SmartyPants will be used to convert quotes and dashes to
-# typographically correct entities.
-#html_use_smartypants = True
-
-# Custom sidebar templates, maps document names to template names.
-#html_sidebars = {}
-
-# Additional templates that should be rendered to pages, maps page names to
-# template names.
-#html_additional_pages = {}
-
-# If false, no module index is generated.
-#html_domain_indices = True
-
-# If false, no index is generated.
-#html_use_index = True
-
-# If true, the index is split into individual pages for each letter.
-#html_split_index = False
-
-# If true, links to the reST sources are added to the pages.
-#html_show_sourcelink = True
-
-# If true, "Created using Sphinx" is shown in the HTML footer. Default is True.
-#html_show_sphinx = True
-
-# If true, "(C) Copyright ..." is shown in the HTML footer. Default is True.
-#html_show_copyright = True
-
-# If true, an OpenSearch description file will be output, and all pages will
-# contain a <link> tag referring to it. The value of this option must be the
-# base URL from which the finished HTML is served.
-#html_use_opensearch = ''
-
-# This is the file name suffix for HTML files (e.g. ".xhtml").
-#html_file_suffix = None
-
 # Output file base name for HTML help builder.
 htmlhelp_basename = 'html5libdoc'
 
 
 # -- Options for LaTeX output --------------------------------------------------
 
-latex_elements = {
-# The paper size ('letterpaper' or 'a4paper').
-#'papersize': 'letterpaper',
-
-# The font size ('10pt', '11pt' or '12pt').
-#'pointsize': '10pt',
-
-# Additional stuff for the LaTeX preamble.
-#'preamble': '',
-}
-
 # Grouping the document tree into LaTeX files. List of tuples
 # (source start file, target name, title, author, documentclass [howto/manual]).
 latex_documents = [
- ('index', 'html5lib.tex', 'html5lib Documentation',
- 'James Graham, Geoffrey Sneddon, and contributors', 'manual'),
+  ('index', 'html5lib.tex', 'html5lib Documentation',
+  'James Graham, Geoffrey Sneddon, and contributors', 'manual'),
 ]
 
-# The name of an image file (relative to this directory) to place at the top of
-# the title page.
-#latex_logo = None
-
-# For "manual" documents, if this is true, then toplevel headings are parts,
-# not chapters.
-#latex_use_parts = False
-
-# If true, show page references after internal links.
-#latex_show_pagerefs = False
-
-# If true, show URL addresses after external links.
-#latex_show_urls = False
-
-# Documents to append as an appendix to all manuals.
-#latex_appendices = []
-
-# If false, no module index is generated.
-#latex_domain_indices = True
-
-
 # -- Options for manual page output --------------------------------------------
 
 # One entry per manual page. List of tuples
@@ -223,32 +80,17 @@
  ['James Graham, Geoffrey Sneddon, and contributors'], 1)
 ]
 
-# If true, show URL addresses after external links.
-#man_show_urls = False
-
-
 # -- Options for Texinfo output ------------------------------------------------
 
 # Grouping the document tree into Texinfo files. List of tuples
 # (source start file, target name, title, author,
 # dir menu entry, description, category)
 texinfo_documents = [
- ('index', 'html5lib', 'html5lib Documentation',
- 'James Graham, Geoffrey Sneddon, and contributors', 'html5lib', 'One line description of project.',
- 'Miscellaneous'),
+  ('index', 'html5lib', 'html5lib Documentation',
+  'James Graham, Geoffrey Sneddon, and contributors', 'html5lib', 'One line description of project.',
+  'Miscellaneous'),
 ]
 
-# Documents to append as an appendix to all manuals.
-#texinfo_appendices = []
-
-# If false, no module index is generated.
-#texinfo_domain_indices = True
-
-# How to display URL addresses: 'footnote', 'no', or 'inline'.
-#texinfo_show_urls = 'footnote'
-
-# If true, do not generate a @detailmenu in the "Top" node's menu.
-#texinfo_no_detailmenu = False
 
 class CExtMock(object):
  """Required for autodoc on readthedocs.org where you cannot build C extensions."""
@@ -265,15 +107,16 @@ def __getattr__(cls, name):
  else:
  return CExtMock()
 
+
 try:
- import lxml # flake8: noqa
+ import lxml # noqa
 except ImportError:
  sys.modules['lxml'] = CExtMock()
  sys.modules['lxml.etree'] = CExtMock()
  print("warning: lxml modules mocked.")
 
 try:
- import genshi  # flake8: noqa
+ import genshi # noqa
 except ImportError:
  sys.modules['genshi'] = CExtMock()
  sys.modules['genshi.core'] = CExtMock()

html5lib/_ihatexml.py

@@ -136,6 +136,7 @@ def normaliseCharList(charList):
  i += j
  return rv
 
+
 # We don't really support characters above the BMP :(
 max_unicode = int("FFFF", 16)
 

html5lib/_inputstream.py

@@ -443,7 +443,7 @@ def openStream(self, source):
 
  try:
  stream.seek(stream.tell())
- except: # pylint:disable=bare-except
+ except Exception:
  stream = BufferedStream(stream)
 
  return stream

html5lib/_utils.py

@@ -27,7 +27,7 @@
  # We need this with u"" because of http:https://bugs.jython.org/issue2039
  _x = eval('u"\\uD800"') # pylint:disable=eval-used
  assert isinstance(_x, text_type)
-except: # pylint:disable=bare-except
+except Exception:
  supports_lone_surrogates = False
 else:
  supports_lone_surrogates = True

html5lib/tests/support.py

@@ -143,6 +143,7 @@ def convertData(data):
  return "\n".join(rv)
  return convertData
 
+
 convertExpected = convert(2)
 
 

html5lib/tests/tokenizer.py

@@ -176,6 +176,7 @@ def repl(m):
 def _doCapitalize(match):
  return match.group(1).upper()
 
+
 _capitalizeRe = re.compile(r"\W+(\w)").sub
 
 

html5lib/tests/tokenizertotree.py

@@ -64,5 +64,6 @@ def make_test(test_data):
  rv.append("")
  return "\n".join(rv)
 
+
 if __name__ == "__main__":
  main(sys.argv[1])

html5lib/tests/tree_construction.py

@@ -77,6 +77,7 @@ def _getTreeWalkerTests(self, treeName, treeAPIs):
 def convertTreeDump(data):
  return "\n".join(convert(3)(data).split("\n")[1:])
 
+
 namespaceExpected = re.compile(r"^(\s*)<(\S+)>", re.M).sub
 
 

html5lib/treewalkers/etree.py

@@ -127,4 +127,5 @@ def getParentNode(self, node):
 
  return locals()
 
+
 getETreeModule = moduleFactoryFactory(getETreeBuilder)

parse.py

@@ -33,7 +33,7 @@ def parse():
  if contentType:
  (mediaType, params) = cgi.parse_header(contentType)
  encoding = params.get('charset')
- except:
+ except Exception:
  pass
  elif f == '-':
  f = sys.stdin
@@ -94,7 +94,7 @@ def parse():
 def run(parseMethod, f, encoding, scripting):
  try:
  document = parseMethod(f, override_encoding=encoding, scripting=scripting)
- except:
+ except Exception:
  document = None
  traceback.print_exc()
  return document
@@ -127,7 +127,7 @@ def printOutput(parser, document, opts):
  for opt in serializer.HTMLSerializer.options:
  try:
  kwargs[opt] = getattr(opts, opt)
- except:
+ except Exception:
  pass
  if not kwargs['quote_char']:
  del kwargs['quote_char']
@@ -240,5 +240,6 @@ def getOptParser():
 
  return parser
 
+
 if __name__ == "__main__":
  parse()

requirements-test.txt

@@ -2,7 +2,7 @@
 
 tox
 
-flake8<3.0
+flake8==3.7.9
 
 pytest==3.2.5
 coverage

setup.cfg

@@ -7,7 +7,7 @@ max-line-length = 139
 exclude = .git,__pycache__,.tox,doc
 
 [flake8]
-ignore = N
+ignore = N, W504
 max-line-length = 139
 
 [metadata]

utils/entities.py

@@ -96,5 +96,6 @@ def main():
  code = make_entities_code(entities)
  open("entities_constants.py", "w").write(code)
 
+
 if __name__ == "__main__":
  main()