merge upstream

pelican/__init__.py

@@ -8,11 +8,13 @@ import argparse
 
 from pelican import signals
 
-from pelican.generators import (Generator, ArticlesGenerator, PagesGenerator,
-        StaticGenerator, PdfGenerator, LessCSSGenerator)
+from pelican.generators import (ArticlesGenerator, PagesGenerator,
+                                StaticGenerator, PdfGenerator,
+                                LessCSSGenerator, SourceFileGenerator)
 from pelican.log import init
 from pelican.settings import read_settings, _DEFAULT_CONFIG
-from pelican.utils import clean_output_dir, files_changed, file_changed, NoFilesError
+from pelican.utils import (clean_output_dir, files_changed, file_changed,
+                           NoFilesError)
 from pelican.writers import Writer
 
 __major__ = 3
@@ -78,7 +80,7 @@ class Pelican(object):
                 logger.debug("Loading plugin `{0}' ...".format(plugin))
                 plugin = __import__(plugin, globals(), locals(), 'module')
 
-            logger.debug("Registering plugin `{0}' ...".format(plugin.__name__))
+            logger.debug("Registering plugin `{0}'".format(plugin.__name__))
             plugin.register()
 
     def _handle_deprecation(self):
@@ -139,8 +141,8 @@ class Pelican(object):
             'Modify CATEGORY_FEED to CATEGORY_FEED_ATOM in your settings and '
             'theme for the same behavior. Temporarily setting '
             'CATEGORY_FEED_ATOM for backwards compatibility.')
-            self.settings['CATEGORY_FEED_ATOM'] = self.settings['CATEGORY_FEED']
-
+            self.settings['CATEGORY_FEED_ATOM'] =\
+                    self.settings['CATEGORY_FEED']
 
     def run(self):
         """Run the generators and return"""
@@ -187,6 +189,8 @@ class Pelican(object):
             generators.append(PdfGenerator)
         if self.settings['LESS_GENERATOR']:  # can be True or PATH to lessc
             generators.append(LessCSSGenerator)
+        if self.settings['OUTPUT_SOURCES']:
+            generators.append(SourceFileGenerator)
 
         for pair in signals.get_generators.send(self):
             (funct, value) = pair
@@ -290,7 +294,7 @@ def main():
                     # have.
                     if files_changed(pelican.path, pelican.markup) or \
                             files_changed(pelican.theme, ['']):
-                        if files_found_error == False:
+                        if not files_found_error:
                             files_found_error = True
                         pelican.run()
 
@@ -306,8 +310,9 @@ def main():
                     logger.warning("Keyboard interrupt, quitting.")
                     break
                 except NoFilesError:
-                    if files_found_error == True:
-                        logger.warning("No valid files found in content. Nothing to generate.")
+                    if files_found_error:
+                        logger.warning("No valid files found in content. "
+                                       "Nothing to generate.")
                         files_found_error = False
                     time.sleep(1)  # sleep to avoid cpu load
                 except Exception, e:

pelican/generators.py

@@ -518,6 +518,19 @@ class PdfGenerator(Generator):
         for page in self.context['pages']:
             self._create_pdf(page, pdf_path)
 
+class SourceFileGenerator(Generator):
+    def generate_context(self):
+        self.output_extension = self.settings['OUTPUT_SOURCES_EXTENSION']
+
+    def _create_source(self, obj, output_path):
+        filename = os.path.splitext(obj.save_as)[0]
+        dest = os.path.join(output_path, filename + self.output_extension)
+        copy('', obj.filename, dest)
+
+    def generate_output(self, writer=None):
+        logger.info(u' Generating source files...')
+        for object in chain(self.context['articles'], self.context['pages']):
+            self._create_source(object, self.output_path)
 
 class LessCSSGenerator(Generator):
     """Compile less css files."""

pelican/plugins/sitemap.py

@@ -1,7 +1,8 @@
+import collections
 import os.path
 
 from datetime import datetime
-from logging import debug, warning, error, info
+from logging import warning, info
 from codecs import open
 
 from pelican import signals, contents
@@ -14,45 +15,17 @@ TXT_HEADER = u"""{0}/index.html
 
 XML_HEADER = u"""<?xml version="1.0" encoding="utf-8"?>
 <urlset xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
-         xsi:schemaLocation="http://www.sitemaps.org/schemas/sitemap/0.9 http://www.sitemaps.org/schemas/sitemap/0.9/sitemap.xsd"
-         xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
-
-  <url>
-    <loc>{0}/index.html</loc>
-    <lastmod>{1}</lastmod>
-    <changefreq>{2}</changefreq>
-    <priority>{3}</priority>
-  </url>
-
-  <url>
-    <loc>{0}/archives.html</loc>
-    <lastmod>{1}</lastmod>
-    <changefreq>{2}</changefreq>
-    <priority>{3}</priority>
-  </url>
-
-  <url>
-    <loc>{0}/tags.html</loc>
-    <lastmod>{1}</lastmod>
-    <changefreq>{2}</changefreq>
-    <priority>{3}</priority>
-  </url>
-
-  <url>
-    <loc>{0}/categories.html</loc>
-    <lastmod>{1}</lastmod>
-    <changefreq>{2}</changefreq>
-    <priority>{3}</priority>
-  </url>
+xsi:schemaLocation="http://www.sitemaps.org/schemas/sitemap/0.9 http://www.sitemaps.org/schemas/sitemap/0.9/sitemap.xsd"
+xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
 """
 
 XML_URL = u"""
-  <url>
-    <loc>{0}/{1}</loc>
-    <lastmod>{2}</lastmod>
-    <changefreq>{3}</changefreq>
-    <priority>{4}</priority>
-  </url>
+<url>
+<loc>{0}/{1}</loc>
+<lastmod>{2}</lastmod>
+<changefreq>{3}</changefreq>
+<priority>{4}</priority>
+</url>
 """
 
 XML_FOOTER = u"""
@@ -69,7 +42,6 @@ def format_date(date):
     return date.strftime("%Y-%m-%dT%H:%M:%S") + tz
 
 
-
 class SitemapGenerator(object):
 
     def __init__(self, context, settings, path, theme, output_path, *null):
@@ -146,6 +118,10 @@ class SitemapGenerator(object):
         if getattr(page, 'status', 'published') != 'published':
             return
 
+        page_path = os.path.join(self.output_path, page.url)
+        if not os.path.exists(page_path):
+            return
+
         lastmod = format_date(getattr(page, 'date', self.now))
 
         if isinstance(page, contents.Article):
@@ -176,22 +152,29 @@ class SitemapGenerator(object):
         for article in self.context['articles']:
             pages += article.translations
 
-
         info('writing {0}'.format(path))
 
         with open(path, 'w', encoding='utf-8') as fd:
 
             if self.format == 'xml':
-                fd.write(XML_HEADER.format(
-                        self.siteurl,
-                        format_date(self.now),
-                        self.changefreqs['indexes'],
-                        self.priorities['indexes']
-                    )
-                )
+                fd.write(XML_HEADER)
             else:
                 fd.write(TXT_HEADER.format(self.siteurl))
 
+            FakePage = collections.namedtuple('FakePage',
+                                              ['status',
+                                               'date',
+                                               'url'])
+
+            for standard_page_url in ['index.html',
+                                      'archives.html',
+                                      'tags.html',
+                                      'categories.html']:
+                fake = FakePage(status='published',
+                                date=self.now,
+                                url=standard_page_url)
+                self.write_url(fake, fd)
+
             for page in pages:
                 self.write_url(page, fd)
 
@@ -199,7 +182,6 @@ class SitemapGenerator(object):
                 fd.write(XML_FOOTER)
 
 
-
 def get_generators(generators):
     return SitemapGenerator
 

pelican/readers.py

@@ -102,7 +102,7 @@ class RstReader(Reader):
     def _get_publisher(self, filename):
         extra_params = {'initial_header_level': '2'}
         pub = docutils.core.Publisher(
-                destination_class=docutils.io.StringOutput)
+            destination_class=docutils.io.StringOutput)
         pub.set_components('standalone', 'restructuredtext', 'html')
         pub.writer.translator_class = PelicanHTMLTranslator
         pub.process_programmatic_settings(None, extra_params, None)
@@ -129,8 +129,13 @@ class MarkdownReader(Reader):
 
     def read(self, filename):
         """Parse content and metadata of markdown files"""
+        markdown_extensions = self.settings.get('MARKDOWN_EXTENSIONS', [])
+        if isinstance(markdown_extensions, (str, unicode)):
+            markdown_extensions = [m.strip() for m in
+                                   markdown_extensions.split(',')]
         text = pelican_open(filename)
-        md = Markdown(extensions=set(self.extensions + ['meta']))
+        md = Markdown(extensions=set(
+            self.extensions + markdown_extensions + ['meta']))
         content = md.convert(text)
 
         metadata = {}

pelican/settings.py

@@ -32,6 +32,8 @@ _DEFAULT_CONFIG = {'PATH': '.',
                    'SITENAME': 'A Pelican Blog',
                    'DISPLAY_PAGES_ON_MENU': True,
                    'PDF_GENERATOR': False,
+                   'OUTPUT_SOURCES': False,
+                   'OUTPUT_SOURCES_EXTENSION': '.text',
                    'DEFAULT_CATEGORY': 'misc',
                    'DEFAULT_DATE': 'fs',
                    'WITH_FUTURE_DATES': True,
@@ -76,6 +78,7 @@ _DEFAULT_CONFIG = {'PATH': '.',
                    'SUMMARY_MAX_LENGTH': 50,
                    'WEBASSETS': False,
                    'PLUGINS': [],
+                   'MARKDOWN_EXTENSIONS': ['toc', ],
                    }
 
 
@@ -175,4 +178,11 @@ def configure_settings(settings, default_settings=None, filename=None):
             logger.warn("You must install the webassets module to use WEBASSETS.")
             settings['WEBASSETS'] = False
 
+    if 'OUTPUT_SOURCES_EXTENSION' in settings:
+        if not isinstance(settings['OUTPUT_SOURCES_EXTENSION'], str):
+            settings['OUTPUT_SOURCES_EXTENSION'] = _DEFAULT_CONFIG['OUTPUT_SOURCES_EXTENSION']
+            logger.warn("Detected misconfiguration with OUTPUT_SOURCES_EXTENSION."
+                       " falling back to the default extension " +
+                       _DEFAULT_CONFIG['OUTPUT_SOURCES_EXTENSION'])
+
     return settings

pelican/tools/pelican_import.py

@@ -184,6 +184,8 @@ def build_header(title, date, author, categories, tags):
     header = '%s\n%s\n' % (title, '#' * len(title))
     if date:
         header += ':date: %s\n' % date
+    if author:
+        header += ':author: %s\n' % author
     if categories:
         header += ':category: %s\n' % ', '.join(categories)
     if tags:
@@ -196,6 +198,8 @@ def build_markdown_header(title, date, author, categories, tags):
     header = 'Title: %s\n' % title
     if date:
         header += 'Date: %s\n' % date
+    if author:
+        header += 'Author: %s\n' % author
     if categories:
         header += 'Category: %s\n' % ', '.join(categories)
     if tags:

pelican/utils.py

@@ -97,6 +97,17 @@ def copy(path, source, destination, destination_path=None, overwrite=False):
 def clean_output_dir(path):
     """Remove all the files from the output directory"""
 
+    if not os.path.exists(path):
+        logger.debug("Directory already removed: %s" % path)
+        return
+
+    if not os.path.isdir(path):
+        try:
+            os.remove(path)
+        except Exception, e:
+            logger.error("Unable to delete file %s; %e" % path, e)
+        return
+
     # remove all the existing content from the output folder
     for filename in os.listdir(path):
         file = os.path.join(path, filename)

pelican/writers.py

@@ -148,9 +148,9 @@ class Writer(object):
                     paginators[key] = Paginator(object_list, len(object_list))
 
             # generated pages, and write
+            name_root, ext = os.path.splitext(name)
             for page_num in range(paginators.values()[0].num_pages):
                 paginated_localcontext = localcontext.copy()
-                paginated_name = name
                 for key in paginators.iterkeys():
                     paginator = paginators[key]
                     page = paginator.page(page_num + 1)
@@ -158,9 +158,10 @@ class Writer(object):
                             {'%s_paginator' % key: paginator,
                              '%s_page' % key: page})
                 if page_num > 0:
-                    ext = '.' + paginated_name.rsplit('.')[-1]
-                    paginated_name = paginated_name.replace(ext,
-                        '%s%s' % (page_num + 1, ext))
+                    paginated_name = '%s%s%s' % (
+                        name_root, page_num + 1, ext)
+                else:
+                    paginated_name = name
 
                 _write_file(template, paginated_localcontext, self.output_path,
                     paginated_name)