Port pelican to python 3.

Stays compatible with 2.x series, thanks to an unified codebase.

.gitignore

@@ -11,3 +11,5 @@ tags
 .tox
 .coverage
 htmlcov
+six-*.egg/
+*.orig

.travis.yml

@@ -2,11 +2,13 @@ language: python
 python:
     - "2.6"
     - "2.7"
+#    - "3.2"
 before_install:
  - sudo apt-get update -qq
  - sudo apt-get install -qq ruby-sass
 install:
-    - pip install nose unittest2 mock --use-mirrors
+    - pip install nose mock --use-mirrors
+    - if [[ $TRAVIS_PYTHON_VERSION == '3.2' ]]; then pip install --use-mirrors unittest2py3k; else pip install --use-mirrors unittest2; fi
     - pip install . --use-mirrors
     - pip install Markdown
     - pip install webassets

dev_requirements.txt

@@ -1,8 +1,9 @@
 # Tests
-unittest2
 mock
+
 # Optional Packages
 Markdown
-BeautifulSoup
+BeautifulSoup4
+lxml
 typogrify
-webassets
+webassets

docs/changelog.rst

@@ -4,7 +4,7 @@ Release history
 3.2 (XXXX-XX-XX)
 ================
 
-* [...]
+* Support for Python 3!
 
 3.1 (2012-12-04)
 ================

docs/conf.py

@@ -1,4 +1,5 @@
 # -*- coding: utf-8 -*-
+from __future__ import unicode_literals
 import sys, os
 
 sys.path.append(os.path.abspath('..'))
@@ -10,8 +11,8 @@
 extensions = ['sphinx.ext.autodoc',]
 source_suffix = '.rst'
 master_doc = 'index'
-project = u'Pelican'
-copyright = u'2010, Alexis Metaireau and contributors'
+project = 'Pelican'
+copyright = '2010, Alexis Metaireau and contributors'
 exclude_patterns = ['_build']
 version = __version__
 release = __major__
@@ -34,16 +35,16 @@
 
 # -- Options for LaTeX output --------------------------------------------------
 latex_documents = [
-  ('index', 'Pelican.tex', u'Pelican Documentation',
-   u'Alexis Métaireau', 'manual'),
+  ('index', 'Pelican.tex', 'Pelican Documentation',
+   'Alexis Métaireau', 'manual'),
 ]
 
 # -- Options for manual page output --------------------------------------------
 man_pages = [
-    ('index', 'pelican', u'pelican documentation',
-     [u'Alexis Métaireau'], 1),
-    ('pelican-themes', 'pelican-themes', u'A theme manager for Pelican',
-     [u'Mickaël Raybaud'], 1),
-    ('themes', 'pelican-theming', u'How to create themes for Pelican',
-     [u'The Pelican contributors'], 1)
+    ('index', 'pelican', 'pelican documentation',
+     ['Alexis Métaireau'], 1),
+    ('pelican-themes', 'pelican-themes', 'A theme manager for Pelican',
+     ['Mickaël Raybaud'], 1),
+    ('themes', 'pelican-theming', 'How to create themes for Pelican',
+     ['The Pelican contributors'], 1)
 ]

pelican/__init__.py

@@ -1,3 +1,7 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals, print_function
+import six
+
 import os
 import re
 import sys
@@ -55,7 +59,7 @@ def init_plugins(self):
         self.plugins = self.settings['PLUGINS']
         for plugin in self.plugins:
             # if it's a string, then import it
-            if isinstance(plugin, basestring):
+            if isinstance(plugin, six.string_types):
                 logger.debug("Loading plugin `{0}' ...".format(plugin))
                 plugin = __import__(plugin, globals(), locals(), 'module')
 
@@ -265,7 +269,7 @@ def get_instance(args):
     settings = read_settings(args.settings, override=get_config(args))
 
     cls = settings.get('PELICAN_CLASS')
-    if isinstance(cls, basestring):
+    if isinstance(cls, six.string_types):
         module, cls_name = cls.rsplit('.', 1)
         module = __import__(module)
         cls = getattr(module, cls_name)
@@ -311,15 +315,15 @@ def main():
                                        "Nothing to generate.")
                         files_found_error = False
                     time.sleep(1)  # sleep to avoid cpu load
-                except Exception, e:
+                except Exception as e:
                     logger.warning(
                         "Caught exception \"{}\". Reloading.".format(e)
                     )
                     continue
         else:
             pelican.run()
-    except Exception, e:
-        logger.critical(unicode(e))
+    except Exception as e:
+        logger.critical(e)
 
         if (args.verbosity == logging.DEBUG):
             raise

pelican/contents.py

@@ -1,4 +1,7 @@
 # -*- coding: utf-8 -*-
+from __future__ import unicode_literals, print_function
+import six
+
 import copy
 import locale
 import logging
@@ -11,8 +14,10 @@
 
 
 from pelican.settings import _DEFAULT_CONFIG
-from pelican.utils import slugify, truncate_html_words, memoized
+from pelican.utils import (slugify, truncate_html_words, memoized,
+    python_2_unicode_compatible)
 from pelican import signals
+import pelican.utils
 
 logger = logging.getLogger(__name__)
 
@@ -85,13 +90,8 @@ def __init__(self, content, metadata=None, settings=None,
             self.date_format = self.date_format[1]
 
         if hasattr(self, 'date'):
-            encoded_date = self.date.strftime(
-                    self.date_format.encode('ascii', 'xmlcharrefreplace'))
-
-            if platform == 'win32':
-                self.locale_date = encoded_date.decode(stdin.encoding)
-            else:
-                self.locale_date = encoded_date.decode('utf')
+            self.locale_date = pelican.utils.strftime(self.date,
+                self.date_format)
 
         # manage status
         if not hasattr(self, 'status'):
@@ -167,7 +167,7 @@ def replacer(m):
                     origin = '/'.join((siteurl,
                              self._context['filenames'][value].url))
                 else:
-                    logger.warning(u"Unable to find {fn}, skipping url"
+                    logger.warning("Unable to find {fn}, skipping url"
                                     " replacement".format(fn=value))
 
             return m.group('markup') + m.group('quote') + origin \
@@ -243,10 +243,10 @@ class Article(Page):
 class Quote(Page):
     base_properties = ('author', 'date')
 
-
+@python_2_unicode_compatible
 class URLWrapper(object):
     def __init__(self, name, settings):
-        self.name = unicode(name)
+        self.name = name
         self.slug = slugify(self.name)
         self.settings = settings
 
@@ -257,12 +257,9 @@ def __hash__(self):
         return hash(self.name)
 
     def __eq__(self, other):
-        return self.name == unicode(other)
+        return self.name == other
 
     def __str__(self):
-        return str(self.name.encode('utf-8', 'replace'))
-
-    def __unicode__(self):
         return self.name
 
     def _from_settings(self, key, get_page_name=False):
@@ -272,14 +269,14 @@ def _from_settings(self, key, get_page_name=False):
         Useful for pagination."""
         setting = "%s_%s" % (self.__class__.__name__.upper(), key)
         value = self.settings[setting]
-        if not isinstance(value, basestring):
-            logger.warning(u'%s is set to %s' % (setting, value))
+        if not isinstance(value, six.string_types):
+            logger.warning('%s is set to %s' % (setting, value))
             return value
         else:
             if get_page_name:
-                return unicode(os.path.splitext(value)[0]).format(**self.as_dict())
+                return os.path.splitext(value)[0].format(**self.as_dict())
             else:
-                return unicode(value).format(**self.as_dict())
+                return value.format(**self.as_dict())
 
     page_name = property(functools.partial(_from_settings, key='URL', get_page_name=True))
     url = property(functools.partial(_from_settings, key='URL'))
@@ -292,13 +289,14 @@ class Category(URLWrapper):
 
 class Tag(URLWrapper):
     def __init__(self, name, *args, **kwargs):
-        super(Tag, self).__init__(unicode.strip(name), *args, **kwargs)
+        super(Tag, self).__init__(name.strip(), *args, **kwargs)
 
 
 class Author(URLWrapper):
     pass
 
 
+@python_2_unicode_compatible
 class StaticContent(object):
     def __init__(self, src, dst=None, settings=None):
         if not settings:
@@ -309,17 +307,14 @@ def __init__(self, src, dst=None, settings=None):
         self.save_as = os.path.join(settings['OUTPUT_PATH'], self.url)
 
     def __str__(self):
-        return str(self.filepath.encode('utf-8', 'replace'))
-
-    def __unicode__(self):
         return self.filepath
 
 
 def is_valid_content(content, f):
     try:
         content.check_properties()
         return True
-    except NameError, e:
-        logger.error(u"Skipping %s: impossible to find informations about"
+    except NameError as e:
+        logger.error("Skipping %s: impossible to find informations about"
                       "'%s'" % (f, e))
         return False

pelican/generators.py

@@ -1,10 +1,11 @@
 # -*- coding: utf-8 -*-
+from __future__ import unicode_literals, print_function
+
 import os
 import math
 import random
 import logging
 import datetime
-import subprocess
 import shutil
 
 from codecs import open
@@ -119,7 +120,7 @@ def _update_context(self, items):
         for item in items:
             value = getattr(self, item)
             if hasattr(value, 'items'):
-                value = value.items()
+                value = list(value.items())
             self.context[item] = value
 
 
@@ -133,8 +134,8 @@ def get_source(self, environment, template):
         if template != self.path or not os.path.exists(self.fullpath):
             raise TemplateNotFound(template)
         mtime = os.path.getmtime(self.fullpath)
-        with file(self.fullpath) as f:
-            source = f.read().decode('utf-8')
+        with open(self.fullpath, 'r', encoding='utf-8') as f:
+            source = f.read()
         return source, self.fullpath, \
                 lambda: mtime == os.path.getmtime(self.fullpath)
 
@@ -323,8 +324,8 @@ def generate_context(self):
             try:
                 signals.article_generate_preread.send(self)
                 content, metadata = read_file(f, settings=self.settings)
-            except Exception, e:
-                logger.warning(u'Could not process %s\n%s' % (f, str(e)))
+            except Exception as e:
+                logger.warning('Could not process %s\n%s' % (f, str(e)))
                 continue
 
             # if no category is set, use the name of the path as a category
@@ -333,8 +334,7 @@ def generate_context(self):
                 if (self.settings['USE_FOLDER_AS_CATEGORY']
                     and os.path.dirname(f) != article_path):
                     # if the article is in a subdirectory
-                    category = os.path.basename(os.path.dirname(f))\
-                        .decode('utf-8')
+                    category = os.path.basename(os.path.dirname(f))
                 else:
                     # if the article is not in a subdirectory
                     category = self.settings['DEFAULT_CATEGORY']
@@ -366,8 +366,8 @@ def generate_context(self):
             elif article.status == "draft":
                 self.drafts.append(article)
             else:
-                logger.warning(u"Unknown status %s for file %s, skipping it." %
-                               (repr(unicode.encode(article.status, 'utf-8')),
+                logger.warning("Unknown status %s for file %s, skipping it." %
+                               (repr(article.status),
                                 repr(f)))
 
         self.articles, self.translations = process_translations(all_articles)
@@ -394,7 +394,7 @@ def generate_context(self):
         tag_cloud = sorted(tag_cloud.items(), key=itemgetter(1), reverse=True)
         tag_cloud = tag_cloud[:self.settings.get('TAG_CLOUD_MAX_ITEMS')]
 
-        tags = map(itemgetter(1), tag_cloud)
+        tags = list(map(itemgetter(1), tag_cloud))
         if tags:
             max_count = max(tags)
         steps = self.settings.get('TAG_CLOUD_STEPS')
@@ -450,8 +450,8 @@ def generate_context(self):
                 exclude=self.settings['PAGE_EXCLUDES']):
             try:
                 content, metadata = read_file(f, settings=self.settings)
-            except Exception, e:
-                logger.warning(u'Could not process %s\n%s' % (f, str(e)))
+            except Exception as e:
+                logger.warning('Could not process %s\n%s' % (f, str(e)))
                 continue
             signals.pages_generate_context.send(self, metadata=metadata)
             page = Page(content, metadata, settings=self.settings,
@@ -466,8 +466,8 @@ def generate_context(self):
             elif page.status == "hidden":
                 hidden_pages.append(page)
             else:
-                logger.warning(u"Unknown status %s for file %s, skipping it." %
-                               (repr(unicode.encode(page.status, 'utf-8')),
+                logger.warning("Unknown status %s for file %s, skipping it." %
+                               (repr(page.status),
                                 repr(f)))
 
         self.pages, self.translations = process_translations(all_pages)
@@ -550,15 +550,15 @@ def _create_pdf(self, obj, output_path):
             # print "Generating pdf for", obj.filename, " in ", output_pdf
             with open(obj.filename) as f:
                 self.pdfcreator.createPdf(text=f.read(), output=output_pdf)
-            logger.info(u' [ok] writing %s' % output_pdf)
+            logger.info(' [ok] writing %s' % output_pdf)
 
     def generate_context(self):
         pass
 
     def generate_output(self, writer=None):
         # we don't use the writer passed as argument here
         # since we write our own files
-        logger.info(u' Generating PDF files...')
+        logger.info(' Generating PDF files...')
         pdf_path = os.path.join(self.output_path, 'pdf')
         if not os.path.exists(pdf_path):
             try:
@@ -583,6 +583,6 @@ def _create_source(self, obj, output_path):
         copy('', obj.filename, dest)
 
     def generate_output(self, writer=None):
-        logger.info(u' Generating source files...')
+        logger.info(' Generating source files...')
         for object in chain(self.context['articles'], self.context['pages']):
             self._create_source(object, self.output_path)