From ce8574aff4e527b533557feedbb6256937359ede Mon Sep 17 00:00:00 2001
From: Deniz Turgut <dturgut@gmail.com>
Date: Wed, 11 Jun 2014 15:58:06 -0400
Subject: [PATCH 1/2] Fix HTMLParser related deprecation warnings in Py3.4

---
 pelican/readers.py              | 12 ++++++------
 pelican/tools/pelican_import.py |  9 ++++-----
 2 files changed, 10 insertions(+), 11 deletions(-)

diff --git a/pelican/readers.py b/pelican/readers.py
index 431e6937..954ea412 100644
--- a/pelican/readers.py
+++ b/pelican/readers.py
@@ -21,10 +21,7 @@ try:
     from html import escape
 except ImportError:
     from cgi import escape
-try:
-    from html.parser import HTMLParser
-except ImportError:
-    from HTMLParser import HTMLParser
+from six.moves.html_parser import HTMLParser
 
 from pelican import signals
 from pelican.contents import Page, Category, Tag, Author
@@ -43,7 +40,6 @@ METADATA_PROCESSORS = {
 
 logger = logging.getLogger(__name__)
 
-
 class BaseReader(object):
     """Base class to read files.
 
@@ -231,7 +227,11 @@ class HTMLReader(BaseReader):
 
     class _HTMLParser(HTMLParser):
         def __init__(self, settings, filename):
-            HTMLParser.__init__(self)
+            try:
+                # Python 3.4+
+                HTMLParser.__init__(self, convert_charrefs=False)
+            except TypeError:
+                HTMLParser.__init__(self)
             self.body = ''
             self.metadata = {}
             self.settings = settings
diff --git a/pelican/tools/pelican_import.py b/pelican/tools/pelican_import.py
index 7c8662c9..a50aa216 100755
--- a/pelican/tools/pelican_import.py
+++ b/pelican/tools/pelican_import.py
@@ -4,11 +4,10 @@
 from __future__ import unicode_literals, print_function
 import argparse
 try:
-    # py3k import
-    from html.parser import HTMLParser
+    from html import unescape  # py3.4+
 except ImportError:
-    # py2 import
-    from HTMLParser import HTMLParser  # NOQA
+    from six.moves.html_parser import HTMLParser
+    unescape = HTMLParser().unescape
 import os
 import re
 import subprocess
@@ -129,7 +128,7 @@ def wp2fields(xml, wp_custpost=False):
 
             try:
                 # Use HTMLParser due to issues with BeautifulSoup 3
-                title = HTMLParser().unescape(item.title.contents[0])
+                title = unescape(item.title.contents[0])
             except IndexError:
                 title = 'No title [%s]' % item.find('post_name').string
                 logger.warning('Post "%s" is lacking a proper title' % title)

From fc505091c280f2b8d5645c18352dd14c93e13f11 Mon Sep 17 00:00:00 2001
From: Deniz Turgut <dturgut@gmail.com>
Date: Wed, 11 Jun 2014 16:11:48 -0400
Subject: [PATCH 2/2] Patch docutils.io.FileInput to not use "U" mode in py3

"U" mode is redundant in py3 since "newline" argument replaces it and by default
universal newlines is enabled. As of py3.4, "U" mode triggers a deprecation warning.
---
 pelican/readers.py | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/pelican/readers.py b/pelican/readers.py
index 954ea412..101ed8b5 100644
--- a/pelican/readers.py
+++ b/pelican/readers.py
@@ -10,6 +10,7 @@ import docutils
 import docutils.core
 import docutils.io
 from docutils.writers.html4css1 import HTMLTranslator
+import six
 
 # import the directives to have pygments support
 from pelican import rstdirectives  # NOQA
@@ -118,6 +119,19 @@ class RstReader(BaseReader):
     enabled = bool(docutils)
     file_extensions = ['rst']
 
+    class FileInput(docutils.io.FileInput):
+        """Patch docutils.io.FileInput to remove "U" mode in py3.
+
+        Universal newlines is enabled by default and "U" mode is deprecated
+        in py3.
+
+        """
+
+        def __init__(self, *args, **kwargs):
+            if six.PY3:
+                kwargs['mode'] = kwargs.get('mode', 'r').replace('U', '')
+            docutils.io.FileInput.__init__(self, *args, **kwargs)
+
     def __init__(self, *args, **kwargs):
         super(RstReader, self).__init__(*args, **kwargs)
 
@@ -149,12 +163,14 @@ class RstReader(BaseReader):
         extra_params = {'initial_header_level': '2',
                         'syntax_highlight': 'short',
                         'input_encoding': 'utf-8',
-                        'exit_status_level': 2}
+                        'exit_status_level': 2,
+                        'embed_stylesheet': False}
         user_params = self.settings.get('DOCUTILS_SETTINGS')
         if user_params:
             extra_params.update(user_params)
 
         pub = docutils.core.Publisher(
+            source_class=self.FileInput,
             destination_class=docutils.io.StringOutput)
         pub.set_components('standalone', 'restructuredtext', 'html')
         pub.writer.translator_class = PelicanHTMLTranslator