From 347f3ea0b59d57a99829ad7bca60238747bceacd Mon Sep 17 00:00:00 2001
From: Richard Harding <rharding@mitechie.com>
Date: Thu, 2 Jan 2014 21:24:37 -0500
Subject: [PATCH] Lint

---
 Makefile                 |  7 +++++++
 breadability/_compat.py  |  4 ++++
 breadability/document.py | 11 +++++++++--
 3 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/Makefile b/Makefile
index eaf10c1..45a8ee3 100644
--- a/Makefile
+++ b/Makefile
@@ -49,6 +49,13 @@ clean_all: clean_venv
     fi
 
 
+bin/flake8: venv
+	bin/pip install flake8
+
+lint: bin/flake8
+	flake8 breadability
+
+
 # ###########
 # Deploy
 # ###########
diff --git a/breadability/_compat.py b/breadability/_compat.py
index 76f5c98..dcc7d47 100644
--- a/breadability/_compat.py
+++ b/breadability/_compat.py
@@ -19,9 +19,13 @@ string_types = (bytes, unicode,)
 
 
 try:
+    # Assert to hush pyflakes about the unused import. This is a _compat
+    # module and we expect this to aid in other code importing urllib.
     import urllib2 as urllib
+    assert urllib
 except ImportError:
     import urllib.request as urllib
+    assert urllib
 
 
 def unicode_compatible(cls):
diff --git a/breadability/document.py b/breadability/document.py
index 1d9920d..8c08523 100644
--- a/breadability/document.py
+++ b/breadability/document.py
@@ -30,6 +30,9 @@ logger = logging.getLogger("breadability")
 
 
 TAG_MARK_PATTERN = re.compile(to_bytes(r"</?[^>]*>\s*"))
+UTF8_PARSER = HTMLParser(encoding="utf8")
+
+
 def determine_encoding(page):
     encoding = "utf8"
     text = TAG_MARK_PATTERN.sub(to_bytes(" "), page)
@@ -54,7 +57,12 @@ def determine_encoding(page):
     return encoding
 
 
-BREAK_TAGS_PATTERN = re.compile(to_unicode(r"(?:<\s*[bh]r[^>]*>\s*)+"), re.IGNORECASE)
+BREAK_TAGS_PATTERN = re.compile(
+    to_unicode(r"(?:<\s*[bh]r[^>]*>\s*)+"),
+    re.IGNORECASE
+)
+
+
 def convert_breaks_to_paragraphs(html):
     """
     Converts <hr> tag and multiple <br> tags into paragraph.
@@ -75,7 +83,6 @@ def _replace_break_tags(match):
         return tags
 
 
-UTF8_PARSER = HTMLParser(encoding="utf8")
 def build_document(html_content, base_href=None):
     """Requires that the `html_content` not be None"""
     assert html_content is not None