github/pelican
1
0
Fork 1
mirror of https://github.com/getpelican/pelican.git synced 2025-10-15 20:28:56 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

add FILENAME_METADATA setting to extract metadata from filename

Browse source 
FILENAME_METADATA default to '(?P<date>\d{4}-\d{2}-\d{2}).*' which will allow
to extract date metadata from the filename.
This commit is contained in:
Bruno Binet 2012-11-28 00:29:30 +01:00
commit debd6fb3b4
2 changed files with 24 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

14
pelican/readers.py
View file

@ -1,4 +1,6 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
import os
import re
try: try:
import docutils import docutils
import docutils.core import docutils.core
@ -207,8 +209,9 @@ for cls in Reader.__subclasses__():
def read_file(filename, fmt=None, settings=None): def read_file(filename, fmt=None, settings=None):
"""Return a reader object using the given format.""" """Return a reader object using the given format."""
base, ext = os.path.splitext(os.path.basename(filename))
if not fmt: if not fmt:
fmt = filename.split('.')[-1] fmt = ext[1:]
if fmt not in _EXTENSIONS: if fmt not in _EXTENSIONS:
raise TypeError('Pelican does not know how to parse %s' % filename) raise TypeError('Pelican does not know how to parse %s' % filename)
@ -230,4 +233,13 @@ def read_file(filename, fmt=None, settings=None):
content = typogrify(content) content = typogrify(content)
metadata['title'] = typogrify(metadata['title']) metadata['title'] = typogrify(metadata['title'])
filename_metadata = settings and settings.get('FILENAME_METADATA')
if filename_metadata:
match = re.match(filename_metadata, base)
if match:
for k, v in match.groupdict().iteritems():
if k not in metadata:
k = k.lower() # metadata must be lowercase
metadata[k] = reader.process_metadata(k, v)
return content, metadata return content, metadata

12
pelican/settings.py
View file

@ -5,6 +5,7 @@ import inspect
import os import os
import locale import locale
import logging import logging
import re
from os.path import isabs from os.path import isabs
@ -60,7 +61,7 @@ _DEFAULT_CONFIG = {'PATH': '.',
'TAG_CLOUD_STEPS': 4, 'TAG_CLOUD_STEPS': 4,
'TAG_CLOUD_MAX_ITEMS': 100, 'TAG_CLOUD_MAX_ITEMS': 100,
'DIRECT_TEMPLATES': ('index', 'tags', 'categories', 'archives'), 'DIRECT_TEMPLATES': ('index', 'tags', 'categories', 'archives'),
'EXTRA_TEMPLATES_PATHS' : [], 'EXTRA_TEMPLATES_PATHS': [],
'PAGINATED_DIRECT_TEMPLATES': ('index', ), 'PAGINATED_DIRECT_TEMPLATES': ('index', ),
'PELICAN_CLASS': 'pelican.Pelican', 'PELICAN_CLASS': 'pelican.Pelican',
'DEFAULT_DATE_FORMAT': '%a %d %B %Y', 'DEFAULT_DATE_FORMAT': '%a %d %B %Y',
@ -70,6 +71,7 @@ _DEFAULT_CONFIG = {'PATH': '.',
'DEFAULT_PAGINATION': False, 'DEFAULT_PAGINATION': False,
'DEFAULT_ORPHANS': 0, 'DEFAULT_ORPHANS': 0,
'DEFAULT_METADATA': (), 'DEFAULT_METADATA': (),
'FILENAME_METADATA': '(?P<date>\d{4}-\d{2}-\d{2}).*',
'FILES_TO_COPY': (), 'FILES_TO_COPY': (),
'DEFAULT_STATUS': 'published', 'DEFAULT_STATUS': 'published',
'ARTICLE_PERMALINK_STRUCTURE': '', 'ARTICLE_PERMALINK_STRUCTURE': '',
@ -205,4 +207,12 @@ def configure_settings(settings):
" falling back to the default extension " + " falling back to the default extension " +
_DEFAULT_CONFIG['OUTPUT_SOURCES_EXTENSION']) _DEFAULT_CONFIG['OUTPUT_SOURCES_EXTENSION'])
filename_metadata = settings.get('FILENAME_METADATA')
if filename_metadata and not isinstance(filename_metadata, basestring):
logger.error("Detected misconfiguration with FILENAME_METADATA"
" setting (must be string or compiled pattern), falling"
"back to the default")
settings['FILENAME_METADATA'] = \
_DEFAULT_CONFIG['FILENAME_METADATA']
return settings return settings