Add the PATH_METADATA setting

Sometimes the base filename doesn't have everything you need.

Remember that os.sep is platform dependent, so using it in a regular
expression for this setting may not be portable (boo MS Windows!).

docs/settings.rst

@@ -59,6 +59,8 @@ Setting name (default value)                                            What doe
                                                                         For example, if you would like to extract both the
                                                                         date and the slug, you could set something like:
                                                                         ``'(?P<date>\d{4}-\d{2}-\d{2})_(?P<slug>.*)'``.
+`PATH_METADATA` (``''``)                                                Like ``FILENAME_METADATA``, but parsed from a page's
+                                                                        full path relative to the content source directory.
 `DELETE_OUTPUT_DIRECTORY` (``False``)                                   Delete the content of the output directory before
                                                                         generating new files.
 `FILES_TO_COPY` (``()``)                                                A list of files (or directories) to copy from the source (inside the

pelican/readers.py

@@ -353,19 +353,24 @@ def parse_path_metadata(path, settings=None, process=None):
     >>> import pprint
     >>> settings = {
     ...     'FILENAME_METADATA': '(?P<slug>[^.]*).*',
+    ...     'PATH_METADATA':
+    ...         '(?P<category>[^/]*)/(?P<date>\d{4}-\d{2}-\d{2})/.*',
     ...     }
     >>> reader = Reader(settings=settings)
     >>> metadata = parse_path_metadata(
     ...     path='my-cat/2013-01-01/my-slug.html',
     ...     settings=settings,
     ...     process=reader.process_metadata)
-    >>> pprint.pprint(metadata)
-    {'slug': 'my-slug'}
+    >>> pprint.pprint(metadata)  # doctest: +ELLIPSIS
+    {'category': <pelican.urlwrappers.Category object at ...>,
+     'date': datetime.datetime(2013, 1, 1, 0, 0),
+     'slug': 'my-slug'}
     """
     metadata = {}
     base, ext = os.path.splitext(os.path.basename(path))
     if settings:
         for key,data in [('FILENAME_METADATA', base),
+                         ('PATH_METADATA', path),
                          ]:
             regexp = settings.get(key)
             if regexp:

pelican/settings.py

@@ -77,6 +77,7 @@ _DEFAULT_CONFIG = {'PATH': '.',
                    'DEFAULT_ORPHANS': 0,
                    'DEFAULT_METADATA': (),
                    'FILENAME_METADATA': '(?P<date>\d{4}-\d{2}-\d{2}).*',
+                   'PATH_METADATA': '',
                    'FILES_TO_COPY': (),
                    'DEFAULT_STATUS': 'published',
                    'ARTICLE_PERMALINK_STRUCTURE': '',