diff --git a/docs/settings.rst b/docs/settings.rst
index 2d40d4ec..69e2adc8 100644
--- a/docs/settings.rst
+++ b/docs/settings.rst
@@ -24,12 +24,7 @@ Basic settings
================================================ =====================================================
Setting name (default value) What does it do?
================================================ =====================================================
-`ARTICLE_PERMALINK_STRUCTURE` (``''``) Empty by default. Enables some customization of URL
- structure (see below for more detail).
`AUTHOR` Default author (put your name)
-`CLEAN_URLS` (``False``) If set to `True`, the URLs will not be suffixed by
- `.html`, so you will have to setup URL rewriting on
- your web server.
`DATE_FORMATS` (``{}``) If you do manage multiple languages, you can
set the date formatting here. See "Date format and locales"
section below for details.
@@ -79,16 +74,14 @@ Setting name (default value) What does it do?
.. [#] Default is the system locale.
-Article permalink structure
----------------------------
+URL Settings
+------------
-This setting allows you to output your articles sorted by date, provided that
-you specify a format as specified below. This format follows the Python
-``datetime`` directives:
-
-* %Y: Year with century as a decimal number.
-* %m: Month as a decimal number [01,12].
-* %d: Day of the month as a decimal number [01,31].
+You can customize the URL's and locations where files will be saved. The URL's and
+SAVE_AS variables use python's format strings. These variables allow you to place
+your articles in a location such as '{slug}/index.html' and link to then as
+'{slug}' for clean urls. These settings give you the flexibility to place your
+articles and pages anywhere you want.
Note: If you specify a datetime directive, it will be substituted using the
input files' date metadata attribute. If the date is not specified for a
@@ -99,15 +92,42 @@ information.
Also, you can use other file metadata attributes as well:
-* category: '%(category)s'
-* author: '%(author)s'
-* tags: '%(tags)s'
-* date: '%(date)s'
+* slug
+* date
+* lang
+* author
+* category
Example usage:
-* '/%Y/%m/' will render something like '/2011/07/sample-post.html'.
-* '/%Y/%(category)s/' will render something like '/2011/life/sample-post.html'.
+* ARTICLE_URL = 'posts/{date:%Y}/{date:%b}/{date:%d}/{slug}/'
+* ARTICLE_SAVE_AS = 'posts/{date:%Y}/{date:%b}/{date:%d}/{slug}/index.html'
+
+This would save your articles in something like '/posts/2011/Aug/07/sample-post/index.html',
+and the URL to this would be '/posts/2011/Aug/07/sample-post/'.
+
+================================================ =====================================================
+Setting name (default value) what does it do?
+================================================ =====================================================
+`ARTICLE_URL` ('{slug}.html') The URL to refer to an ARTICLE.
+`ARTICLE_SAVE_AS` ('{slug}.html') The place where we will save an article.
+`ARTICLE_LANG_URL` ('{slug}-{lang}.html') The URL to refer to an ARTICLE which doesn't use the
+ default language.
+`ARTICLE_LANG_SAVE_AS` ('{slug}-{lang}.html' The place where we will save an article which
+ doesn't use the default language.
+`PAGE_URL` ('pages/{slug}.html') The URL we will use to link to a page.
+`PAGE_SAVE_AS` ('pages/{slug}.html') The location we will save the page.
+`PAGE_LANG_URL` ('pages/{slug}-{lang}.html') The URL we will use to link to a page which doesn't
+ use the default language.
+`PAGE_LANG_SAVE_AS` ('pages/{slug}-{lang}.html') The location we will save the page which doesn't
+ use the default language.
+`AUTHOR_URL` ('author/{name}.html') The URL to use for an author.
+`AUTHOR_SAVE_AS` ('author/{name}.html') The location to save an author.
+`CATEGORY_URL` ('category/{name}.html') The URL to use for a category.
+`CATEGORY_SAVE_AS` ('category/{name}.html') The location to save a category.
+`TAG_URL` ('tag/{name}.html') The URL to use for a tag.
+`TAG_SAVE_AS` ('tag/{name}.html') The location to save the tag page.
+================================================ =====================================================
Timezone
--------
diff --git a/pelican/__init__.py b/pelican/__init__.py
index a0b5704c..bbd0b679 100644
--- a/pelican/__init__.py
+++ b/pelican/__init__.py
@@ -1,5 +1,6 @@
import argparse
import os, sys
+import re
import time
from pelican.generators import (ArticlesGenerator, PagesGenerator,
@@ -26,6 +27,42 @@ class Pelican(object):
if self.path.endswith('/'):
self.path = self.path[:-1]
+ if settings.get('CLEAN_URLS', False):
+ log.warning('Found deprecated `CLEAN_URLS` in settings. Modifing'
+ ' the following settings for the same behaviour.')
+
+ settings['ARTICLE_URL'] = '{slug}/'
+ settings['ARTICLE_LANG_URL'] = '{slug}-{lang}/'
+ settings['PAGE_URL'] = 'pages/{slug}/'
+ settings['PAGE_LANG_URL'] = 'pages/{slug}-{lang}/'
+
+ for setting in ('ARTICLE_URL', 'ARTICLE_LANG_URL', 'PAGE_URL',
+ 'PAGE_LANG_URL'):
+ log.warning("%s = '%s'" % (setting, settings[setting]))
+
+ if settings.get('ARTICLE_PERMALINK_STRUCTURE', False):
+ log.warning('Found deprecated `ARTICLE_PERMALINK_STRUCTURE` in'
+ ' settings. Modifing the following settings for'
+ ' the same behaviour.')
+
+ structure = settings['ARTICLE_PERMALINK_STRUCTURE']
+
+ # Convert %(variable) into {variable}.
+ structure = re.sub('%\((\w+)\)s', '{\g<1>}', structure)
+
+ # Convert %x into {date:%x} for strftime
+ structure = re.sub('(%[A-z])', '{date:\g<1>}', structure)
+
+ # Strip a / prefix
+ structure = re.sub('^/', '', structure)
+
+ for setting in ('ARTICLE_URL', 'ARTICLE_LANG_URL', 'PAGE_URL',
+ 'PAGE_LANG_URL', 'ARTICLE_SAVE_AS',
+ 'ARTICLE_LANG_SAVE_AS', 'PAGE_SAVE_AS',
+ 'PAGE_LANG_SAVE_AS'):
+ settings[setting] = os.path.join(structure, settings[setting])
+ log.warning("%s = '%s'" % (setting, settings[setting]))
+
# define the default settings
self.settings = settings
self.theme = theme or settings['THEME']
diff --git a/pelican/contents.py b/pelican/contents.py
index 49f30316..90bc189d 100644
--- a/pelican/contents.py
+++ b/pelican/contents.py
@@ -24,6 +24,7 @@ class Page(object):
if not settings:
settings = _DEFAULT_CONFIG
+ self.settings = settings
self._content = content
self.translations = []
@@ -37,9 +38,9 @@ class Page(object):
# default author to the one in settings if not defined
if not hasattr(self, 'author'):
if 'AUTHOR' in settings:
- self.author = settings['AUTHOR']
+ self.author = Author(settings['AUTHOR'], settings)
else:
- self.author = getenv('USER', 'John Doe')
+ self.author = Author(getenv('USER', 'John Doe'), settings)
warning(u"Author of `{0}' unknow, assuming that his name is `{1}'".format(filename or self.title, self.author))
# manage languages
@@ -55,29 +56,6 @@ class Page(object):
if not hasattr(self, 'slug') and hasattr(self, 'title'):
self.slug = slugify(self.title)
- # create save_as from the slug (+lang)
- if not hasattr(self, 'save_as') and hasattr(self, 'slug'):
- if self.in_default_lang:
- if settings.get('CLEAN_URLS', False):
- self.save_as = '%s/index.html' % self.slug
- else:
- self.save_as = '%s.html' % self.slug
-
- clean_url = '%s/' % self.slug
- else:
- if settings.get('CLEAN_URLS', False):
- self.save_as = '%s-%s/index.html' % (self.slug, self.lang)
- else:
- self.save_as = '%s-%s.html' % (self.slug, self.lang)
-
- clean_url = '%s-%s/' % (self.slug, self.lang)
-
- # change the save_as regarding the settings
- if settings.get('CLEAN_URLS', False):
- self.url = clean_url
- elif hasattr(self, 'save_as'):
- self.url = self.save_as
-
if filename:
self.filename = filename
@@ -115,6 +93,30 @@ class Page(object):
if not hasattr(self, prop):
raise NameError(prop)
+ @property
+ def url_format(self):
+ return {
+ 'slug': getattr(self, 'slug', ''),
+ 'lang': getattr(self, 'lang', 'en'),
+ 'date': getattr(self, 'date', datetime.datetime.now()),
+ 'author': self.author,
+ 'category': getattr(self, 'category', 'misc'),
+ }
+
+ @property
+ def url(self):
+ if self.in_default_lang:
+ return self.settings.get('PAGE_URL', u'pages/{slug}.html').format(**self.url_format)
+
+ return self.settings.get('PAGE_LANG_URL', u'pages/{slug}-{lang}.html').format(**self.url_format)
+
+ @property
+ def save_as(self):
+ if self.in_default_lang:
+ return self.settings.get('PAGE_SAVE_AS', u'pages/{slug}.html').format(**self.url_format)
+
+ return self.settings.get('PAGE_LANG_SAVE_AS', u'pages/{slug}-{lang}.html').format(**self.url_format)
+
@property
def content(self):
if hasattr(self, "_get_content"):
@@ -138,10 +140,74 @@ class Page(object):
class Article(Page):
mandatory_properties = ('title', 'date', 'category')
+ @property
+ def url(self):
+ if self.in_default_lang:
+ return self.settings.get('ARTICLE_URL', u'{slug}.html').format(**self.url_format)
+
+ return self.settings.get('ARTICLE_LANG_URL', u'{slug}-{lang}.html').format(**self.url_format)
+
+ @property
+ def save_as(self):
+ if self.in_default_lang:
+ return self.settings.get('ARTICLE_SAVE_AS', u'{slug}.html').format(**self.url_format)
+
+ return self.settings.get('ARTICLE_LANG_SAVE_AS', u'{slug}-{lang}.html').format(**self.url_format)
+
class Quote(Page):
base_properties = ('author', 'date')
+class URLWrapper(object):
+ def __init__(self, name, settings):
+ self.name = unicode(name)
+ self.settings = settings
+
+ def __hash__(self):
+ return hash(self.name)
+
+ def __eq__(self, other):
+ return self.name == unicode(other)
+
+ def __str__(self):
+ return str(self.name)
+
+ def __unicode__(self):
+ return self.name
+
+ @property
+ def url(self):
+ return '%s.html' % self.name
+
+class Category(URLWrapper):
+ @property
+ def url(self):
+ return self.settings.get('CATEGORY_URL', u'category/{name}.html').format(name=self.name)
+
+ @property
+ def save_as(self):
+ return self.settings.get('CATEGORY_SAVE_AS', u'category/{name}.html').format(name=self.name)
+
+class Tag(URLWrapper):
+ def __init__(self, name, *args, **kwargs):
+ super(Tag, self).__init__(unicode.strip(name), *args, **kwargs)
+
+ @property
+ def url(self):
+ return self.settings.get('TAG_URL', u'tag/{name}.html').format(name=self.name)
+
+ @property
+ def save_as(self):
+ return self.settings.get('TAG_SAVE_AS', u'tag/{name}.html').format(name=self.name)
+
+class Author(URLWrapper):
+ @property
+ def url(self):
+ return self.settings.get('AUTHOR_URL', u'author/{name}.html').format(name=self.name)
+
+ @property
+ def save_as(self):
+ return self.settings.get('AUTHOR_SAVE_AS', u'author/{name}.html').format(name=self.name)
def is_valid_content(content, f):
try:
diff --git a/pelican/generators.py b/pelican/generators.py
index 6715126a..47ebb941 100644
--- a/pelican/generators.py
+++ b/pelican/generators.py
@@ -13,7 +13,7 @@ from operator import attrgetter, itemgetter
from jinja2 import Environment, FileSystemLoader, PrefixLoader, ChoiceLoader
from jinja2.exceptions import TemplateNotFound
-from pelican.contents import Article, Page, is_valid_content
+from pelican.contents import Article, Page, Category, is_valid_content
from pelican.log import *
from pelican.readers import read_file
from pelican.utils import copy, process_translations, open
@@ -179,26 +179,26 @@ class ArticlesGenerator(Generator):
for tag, articles in self.tags.items():
articles.sort(key=attrgetter('date'), reverse=True)
dates = [article for article in self.dates if article in articles]
- write('tag/%s.html' % tag, tag_template, self.context, tag=tag,
+ write(tag.save_as, tag_template, self.context, tag=tag,
articles=articles, dates=dates,
paginated={'articles': articles, 'dates': dates},
- page_name='tag/%s' % tag)
+ page_name=u'tag/%s' % tag)
category_template = self.get_template('category')
for cat, articles in self.categories:
dates = [article for article in self.dates if article in articles]
- write('category/%s.html' % cat, category_template, self.context,
+ write(cat.save_as, category_template, self.context,
category=cat, articles=articles, dates=dates,
paginated={'articles': articles, 'dates': dates},
- page_name='category/%s' % cat)
+ page_name=u'category/%s' % cat)
author_template = self.get_template('author')
for aut, articles in self.authors:
dates = [article for article in self.dates if article in articles]
- write('author/%s.html' % aut, author_template, self.context,
+ write(aut.save_as, author_template, self.context,
author=aut, articles=articles, dates=dates,
paginated={'articles': articles, 'dates': dates},
- page_name='author/%s' % aut)
+ page_name=u'author/%s' % aut)
for article in self.drafts:
write('drafts/%s.html' % article.slug, article_template, self.context,
@@ -212,7 +212,6 @@ class ArticlesGenerator(Generator):
files = self.get_files(self.path, exclude=['pages',])
all_articles = []
for f in files:
-
try:
content, metadata = read_file(f, settings=self.settings)
except Exception, e:
@@ -228,7 +227,7 @@ class ArticlesGenerator(Generator):
category = os.path.basename(os.path.dirname(f)).decode('utf-8')
if category != '':
- metadata['category'] = unicode(category)
+ metadata['category'] = Category(category, self.settings)
if 'date' not in metadata.keys()\
and self.settings['FALLBACK_ON_FS_DATE']:
@@ -239,21 +238,6 @@ class ArticlesGenerator(Generator):
if not is_valid_content(article, f):
continue
- add_to_url = u''
- if 'ARTICLE_PERMALINK_STRUCTURE' in self.settings:
- article_permalink_structure = self.settings['ARTICLE_PERMALINK_STRUCTURE']
- article_permalink_structure = article_permalink_structure.lstrip('/').replace('%(', "%%(")
-
- # try to substitute any python datetime directive
- add_to_url = article.date.strftime(article_permalink_structure)
- # try to substitute any article metadata in rest file
- add_to_url = add_to_url % article.__dict__
- add_to_url = [slugify(i) for i in add_to_url.split('/')]
- add_to_url = os.path.join(*add_to_url)
-
- article.url = urlparse.urljoin(add_to_url, article.url)
- article.save_as = urlparse.urljoin(add_to_url, article.save_as)
-
if article.status == "published":
if hasattr(article, 'tags'):
for tag in article.tags:
@@ -348,7 +332,7 @@ class PagesGenerator(Generator):
def generate_output(self, writer):
for page in chain(self.translations, self.pages):
- writer.write_file('pages/%s' % page.save_as, self.get_template('page'),
+ writer.write_file(page.save_as, self.get_template('page'),
self.context, page=page,
relative_urls = self.settings.get('RELATIVE_URLS'))
diff --git a/pelican/readers.py b/pelican/readers.py
index ee3ecd2c..814f81d2 100644
--- a/pelican/readers.py
+++ b/pelican/readers.py
@@ -15,25 +15,30 @@ except ImportError:
Markdown = False
import re
+from pelican.contents import Category, Tag, Author, URLWrapper
from pelican.utils import get_date, open
_METADATA_PROCESSORS = {
- 'tags': lambda x: map(unicode.strip, unicode(x).split(',')),
- 'date': lambda x: get_date(x),
- 'status': unicode.strip,
+ 'tags': lambda x, y: [Tag(tag, y) for tag in unicode(x).split(',')],
+ 'date': lambda x, y: get_date(x),
+ 'status': lambda x,y: unicode.strip(x),
+ 'category': Category,
+ 'author': Author,
}
-def _process_metadata(name, value):
- if name.lower() in _METADATA_PROCESSORS:
- return _METADATA_PROCESSORS[name.lower()](value)
- return value
-
-
class Reader(object):
enabled = True
extensions = None
+ def __init__(self, settings):
+ self.settings = settings
+
+ def process_metadata(self, name, value):
+ if name.lower() in _METADATA_PROCESSORS:
+ return _METADATA_PROCESSORS[name.lower()](value, self.settings)
+ return value
+
class _FieldBodyTranslator(HTMLTranslator):
def astext(self):
@@ -51,29 +56,25 @@ def render_node_to_html(document, node):
node.walkabout(visitor)
return visitor.astext()
-def get_metadata(document):
- """Return the dict containing document metadata"""
- output = {}
- for docinfo in document.traverse(docutils.nodes.docinfo):
- for element in docinfo.children:
- if element.tagname == 'field': # custom fields (e.g. summary)
- name_elem, body_elem = element.children
- name = name_elem.astext()
- value = render_node_to_html(document, body_elem)
- else: # standard fields (e.g. address)
- name = element.tagname
- value = element.astext()
-
- output[name] = _process_metadata(name, value)
- return output
-
-
class RstReader(Reader):
enabled = bool(docutils)
extension = "rst"
def _parse_metadata(self, document):
- return get_metadata(document)
+ """Return the dict containing document metadata"""
+ output = {}
+ for docinfo in document.traverse(docutils.nodes.docinfo):
+ for element in docinfo.children:
+ if element.tagname == 'field': # custom fields (e.g. summary)
+ name_elem, body_elem = element.children
+ name = name_elem.astext()
+ value = render_node_to_html(document, body_elem)
+ else: # standard fields (e.g. address)
+ name = element.tagname
+ value = element.astext()
+
+ output[name] = self.process_metadata(name, value)
+ return output
def _get_publisher(self, filename):
extra_params = {'initial_header_level': '2'}
@@ -110,7 +111,7 @@ class MarkdownReader(Reader):
metadata = {}
for name, value in md.Meta.items():
name = name.lower()
- metadata[name] = _process_metadata(name, value[0])
+ metadata[name] = self.process_metadata(name, value[0])
return content, metadata
@@ -126,7 +127,7 @@ class HtmlReader(Reader):
key = i.split(':')[0][5:].strip()
value = i.split(':')[-1][:-3].strip()
name = key.lower()
- metadata[name] = _process_metadata(name, value)
+ metadata[name] = self.process_metadata(name, value)
return content, metadata
@@ -140,7 +141,7 @@ def read_file(filename, fmt=None, settings=None):
fmt = filename.split('.')[-1]
if fmt not in _EXTENSIONS.keys():
raise TypeError('Pelican does not know how to parse %s' % filename)
- reader = _EXTENSIONS[fmt]()
+ reader = _EXTENSIONS[fmt](settings)
settings_key = '%s_EXTENSIONS' % fmt.upper()
if settings and settings_key in settings:
reader.extensions = settings[settings_key]
diff --git a/pelican/settings.py b/pelican/settings.py
index cf6b23e5..ec6ec483 100644
--- a/pelican/settings.py
+++ b/pelican/settings.py
@@ -26,7 +26,14 @@ _DEFAULT_CONFIG = {'PATH': None,
'REVERSE_ARCHIVE_ORDER': False,
'REVERSE_CATEGORY_ORDER': False,
'DELETE_OUTPUT_DIRECTORY': False,
- 'CLEAN_URLS': False, # use /blah/ instead /blah.html in urls
+ 'ARTICLE_URL': '{slug}.html',
+ 'ARTICLE_SAVE_AS': '{slug}.html',
+ 'ARTICLE_LANG_URL': '{slug}-{lang}.html',
+ 'ARTICLE_LANG_SAVE_AS': '{slug}-{lang}.html',
+ 'PAGE_URL': 'pages/{slug}.html',
+ 'PAGE_SAVE_AS': 'pages/{slug}.html',
+ 'PAGE_LANG_URL': 'pages/{slug}-{lang}.html',
+ 'PAGE_LANG_SAVE_AS': 'pages/{slug}-{lang}.html',
'RELATIVE_URLS': True,
'DEFAULT_LANG': 'en',
'TAG_CLOUD_STEPS': 4,
diff --git a/pelican/themes/notmyidea/templates/article_infos.html b/pelican/themes/notmyidea/templates/article_infos.html
index e1803be8..a1993a09 100644
--- a/pelican/themes/notmyidea/templates/article_infos.html
+++ b/pelican/themes/notmyidea/templates/article_infos.html
@@ -5,10 +5,10 @@
{% if article.author %}
- By {{ article.author }}
+ By {{ article.author }}
{% endif %}
-
diff --git a/tests/test_contents.py b/tests/test_contents.py
index e4c98741..b44d151f 100644
--- a/tests/test_contents.py
+++ b/tests/test_contents.py
@@ -60,12 +60,12 @@ class TestPage(TestCase):
"""
# if a title is defined, save_as should be set
page = Page(**self.page_kwargs)
- page.save_as = 'foo-bar.html'
+ self.assertEqual(page.save_as, "pages/foo-bar.html")
# if a language is defined, save_as should include it accordingly
self.page_kwargs['metadata'].update({'lang': 'fr', })
page = Page(**self.page_kwargs)
- self.assertEqual(page.save_as, "foo-bar-fr.html")
+ self.assertEqual(page.save_as, "pages/foo-bar-fr.html")
def test_datetime(self):
"""If DATETIME is set to a tuple, it should be used to override LOCALE
diff --git a/tests/test_readers.py b/tests/test_readers.py
index 1e920e09..120b3125 100644
--- a/tests/test_readers.py
+++ b/tests/test_readers.py
@@ -19,7 +19,7 @@ def _filename(*args):
class RstReaderTest(unittest2.TestCase):
def test_article_with_metadata(self):
- reader = readers.RstReader()
+ reader = readers.RstReader({})
content, metadata = reader.read(_filename('article_with_metadata.rst'))
expected = {
'category': 'yeah',