Merge 1852b4ed86 into ebf5fca520

MANIFEST.in

@@ -1,3 +1,3 @@
 include *.rst
-recursive-include pelican *.html *.css *png *.in *.rst *.md *.mkd *.xml *.py
+recursive-include pelican *.html *.css *png *.in *.rst *.md *.mkd *.xml *.py *.markdown
 include LICENSE THANKS docs/changelog.rst

pelican/pandoc_templates/md_org_template.markdown

@@ -0,0 +1,11 @@
+$if(title)$Title: $title$$endif$
+$for(author)$Author: $author$$endfor$
+$if(date)$Date: $date$$endif$
+$if(category)$Category: $category$$endif$
+$if(summary)$Summary: $summary$$endif$
+$if(slug)$Slug: $slug$$endif$
+$for(tags)$Tags: $tags$$endfor$
+$if(modified)$Modified: $modified$$endif$
+$if(toc)$ $toc$$endif$
+$body$
+$for(include-after)$$include-after$$endfor$

pelican/readers.py

@@ -4,6 +4,7 @@ from __future__ import unicode_literals, print_function
 import logging
 import os
 import re
+import pkg_resources
 
 import docutils
 import docutils.core
@@ -21,6 +22,10 @@ try:
     from html import escape
 except ImportError:
     from cgi import escape
+try:
+    import pypandoc
+except ImportError:
+    pypandoc = False  # NOQA
 from six.moves.html_parser import HTMLParser
 
 from pelican import signals
@@ -86,7 +91,7 @@ class _FieldBodyTranslator(HTMLTranslator):
 
     def depart_field_body(self, node):
         pass
-
+    
 
 def render_node_to_html(document, node):
     visitor = _FieldBodyTranslator(document)
@@ -197,6 +202,10 @@ class MarkdownReader(BaseReader):
 
     enabled = bool(Markdown)
     file_extensions = ['md', 'markdown', 'mkd', 'mdown']
+    enable_pypandoc = bool(pypandoc)
+    if enable_pypandoc is True:
+        file_extensions.append('org')
+        logger.info('Using pandoc to convert org to markdown')
 
     def __init__(self, *args, **kwargs):
         super(MarkdownReader, self).__init__(*args, **kwargs)
@@ -239,6 +248,17 @@ class MarkdownReader(BaseReader):
         self._source_path = source_path
         self._md = Markdown(extensions=self.extensions)
         with pelican_open(source_path) as text:
+            if self._source_path[-4:] == '.org' and \
+               self.enable_pypandoc is True:
+                pandoc_data_dir = '='.join(['--data-dir',
+                                            pkg_resources.resource_filename(
+                                                'pelican', 'pandoc_templates')])
+                logger.info('Using %s as pandoc_data_dir',
+                            pandoc_data_dir)
+                text = pypandoc.convert(text, 'markdown', \
+                                        format='org',\
+                                        extra_args=['--template=md_org_template.markdown',
+                                                    pandoc_data_dir])
             content = self._md.convert(text)
 
         metadata = self._parse_metadata(self._md.Meta)

pelican/tests/content/article_with_org_extension.org

@@ -0,0 +1,143 @@
+#+Title: test org in md reader
+#+Date: 2014-01-26
+#+Author: Joth
+#+Category: pelican
+#+Tags: pelican readers, pypandoc
+#+Slug: test-org-md-reader
+#+Summary: Testing org reader
+#+OPTIONS: H:2
+#+OPTIONS: toc:2
+#+TOC: headlines 2
+
+* Org Metadata
+
+The following metadata are exporting properly
+
+#+begin_src 
+#+Title: test org in md reader
+#+Date: 2014-01-26
+#+Author: Joth
+#+Category: pelican
+#+end_src
+
+These metadata are not exporting properly. It may be in the
+pandoc template. It may be in the pandoc convert call.
+
+#+begin_src 
+#+Tags: pelican readers, pypandoc
+#+Slug: test-org-md-reader
+#+Summary: Testing org reader
+#+OPTIONS: toc:2
+#+TOC: headlines 2
+#+end_src
+
+
+* Markup
+
+Quotes
+#+BEGIN_QUOTE
+Everything should be made as simple as possible,
+but not any simpler -- Albert Einstein
+#+END_QUOTE
+
+are included with
+#+begin_src 
+#+BEGIN_QUOTE
+...
+#+END_QUOTE
+#+end_src
+
+Centred text and verse are not working in markdown export.
+
+#+begin_src 
+#+BEGIN_CENTER
+...
+#+END_CENTER
+#+end_src
+
+
+* Fonts
+
+*bold* =*bold*=
+
+/italic/ =/italic/=
+
+_underlined_ =_underlined_=
+
+=verbatim= ~=verbatim=~
+
+ ~code~ =~code~=
+
++strike-through+ =+strike-through+=
+
+
+* Code
+
+#+begin_src python :noeval
+class BaseReader(object):
+    """Base class to read files.
+
+    This class is used to process static files, and it can be inherited for
+    other types of file. A Reader class must have the following attributes:
+
+    - enabled: (boolean) tell if the Reader class is enabled. It
+      generally depends on the import of some dependency.
+    - file_extensions: a list of file extensions that the Reader will process.
+    - extensions: a list of extensions to use in the reader (typical use is
+      Markdown).
+
+    """
+    enabled = True
+    file_extensions = ['static']
+    extensions = None
+
+    def __init__(self, settings):
+        self.settings = settings
+
+    def process_metadata(self, name, value):
+        if name in METADATA_PROCESSORS:
+            return METADATA_PROCESSORS[name](value, self.settings)
+        return value
+
+    def read(self, source_path):
+        "No-op parser"
+        content = None
+        metadata = {}
+        return content, metadata
+#+end_src
+
+
+* Tables
+
+Not working nicely. They work with pandoc to rst.
+
+| header 1 | header 2 |
+|----------+----------|
+| and      | with     |
+| a        | two      |
+| table    | columns  |
+
+
+* Misc
+
+Five or more dashes make a line 
+
+------
+
+ # lines with whitespace infront of '# ' will be treated as comments
+
+#+begin_src sh
+ # lines with whitespace infront of '# ' will be treated as comments
+#+end_src
+
+
+* Alternatives and TODOs
+  - implement as plugin?
+    - org is amazin markup language, i like it native...
+  - do the org text to html with pandoc instead of markdown
+  - use Rst/html classes
+  - dedicated org class
+  - specify in SETTINGS which reader subclass to use for org files
+  - fix tables
+  - images example
+  - tests