Support configurable URL's & SAVE_AS path for Author, Category and Tag

docs/settings.rst

@@ -121,6 +121,12 @@ Setting name (default value)                        what does it do?
                                                     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

pelican/contents.py

@@ -38,9 +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 = Author(settings['AUTHOR'])
+                self.author = Author(settings['AUTHOR'], settings)
             else:
-                self.author = 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
@@ -159,8 +159,9 @@ class Quote(Page):
     base_properties = ('author', 'date')
 
 class URLWrapper(object):
-    def __init__(self, name):
+    def __init__(self, name, settings):
         self.name = unicode(name)
+        self.settings = settings
 
     def __hash__(self):
         return hash(self.name)
@@ -181,20 +182,32 @@ class URLWrapper(object):
 class Category(URLWrapper):
     @property
     def url(self):
-        return 'category/%s.html' % self
+        return self.settings.get('CATEGORY_URL', 'category/{name}.html').format(name=self.name)
+
+    @property
+    def save_as(self):
+        return self.settings.get('CATEGORY_SAVE_AS', 'category/{name}.html').format(name=self.name)
 
 class Tag(URLWrapper):
-    def __init__(self, name):
+    def __init__(self, name, *args, **kwargs):
-        self.name = unicode.strip(name)
+        super(Tag, self).__init__(unicode.strip(name), *args, **kwargs)
 
     @property
     def url(self):
-        return 'tag/%s.html' % self
+        return self.settings.get('TAG_URL', 'tag/{name}.html').format(name=self.name)
+
+    @property
+    def save_as(self):
+        return self.settings.get('TAG_SAVE_AS', 'tag/{name}.html').format(name=self.name)
 
 class Author(URLWrapper):
     @property
     def url(self):
-        return 'author/%s.html' % self 
+        return self.settings.get('AUTHOR_URL', 'author/{name}.html').format(name=self.name)
+
+    @property
+    def save_as(self):
+        return self.settings.get('AUTHOR_SAVE_AS', 'author/{name}.html').format(name=self.name)
 
 def is_valid_content(content, f):
     try:

pelican/generators.py

@@ -179,7 +179,7 @@ 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.url, 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)
@@ -187,7 +187,7 @@ class ArticlesGenerator(Generator):
         category_template = self.get_template('category')
         for cat, articles in self.categories:
             dates = [article for article in self.dates if article in articles]
-            write(cat.url, 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)
@@ -195,7 +195,7 @@ class ArticlesGenerator(Generator):
         author_template = self.get_template('author')
         for aut, articles in self.authors:
             dates = [article for article in self.dates if article in articles]
-            write(aut.url, 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)
@@ -228,7 +228,7 @@ class ArticlesGenerator(Generator):
                     category = os.path.basename(os.path.dirname(f)).decode('utf-8')
 
                 if category != '':
-                    metadata['category'] = Category(category)
+                    metadata['category'] = Category(category, self.settings)
 
             if 'date' not in metadata.keys()\
                 and self.settings['FALLBACK_ON_FS_DATE']:

pelican/readers.py

@@ -15,28 +15,30 @@ except ImportError:
     Markdown = False
 import re
 
-from pelican.contents import Category, Tag, Author
+from pelican.contents import Category, Tag, Author, URLWrapper
 from pelican.utils import get_date, open
 
 
 _METADATA_PROCESSORS = {
-    'tags': lambda x: map(Tag, unicode(x).split(',')),
+    'tags': lambda x, y: [Tag(tag, y) for tag in unicode(x).split(',')],
-    'date': lambda x: get_date(x),
+    'date': lambda x, y: get_date(x),
-    'status': unicode.strip,
+    '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):
@@ -54,29 +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'}
@@ -113,7 +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
 
 
@@ -129,7 +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
 
@@ -143,7 +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]