Add support for toc and create a blog entry as a page

content/pages/01_index.md

@@ -2,4 +2,6 @@ Title: Acceuil
 url:
 save_as: index.html
 
-Bienvenue
+[TOC]
+
+# Bienvenue #

content/pages/05_blog.md

@@ -0,0 +1,5 @@
+Title: Blog
+Url: blog.html
+save_as:
+
+Fake entry

pelicanconf.py

@@ -19,12 +19,6 @@ TRANSLATION_FEED_ATOM = None
 AUTHOR_FEED_ATOM = None
 AUTHOR_FEED_RSS = None
 
-# Blogroll
-LINKS = (('Pelican', 'http://getpelican.com/'),
-         ('Python.org', 'http://python.org/'),
-         ('Jinja2', 'http://jinja.pocoo.org/'),
-         ('You can modify those links in your config file ', '#'),)
-
 THEME = "theme"
 
 # Social widget
@@ -35,10 +29,16 @@ DEFAULT_PAGINATION = 10
 
 ARTICLE_PATHS = ['blog']
 ARTICLE_URL = 'blog/{slug}.html'
+ARTICLE_SAVE_AS = 'blog/{slug}.html'
 
 PAGE_URL = '{slug}.html'
 PAGE_SAVE_AS = '{slug}.html'
 
+INDEX_SAVE_AS = 'blog.html'
+
+PLUGIN_PATHS = ["plugins"]
+PLUGINS = ['extract_toc']
 
+MD_EXTENSIONS = (['toc'])
 # Uncomment following line if you want document-relative URLs when developing
 #RELATIVE_URLS = True

plugins/extract_toc/README.md

@@ -0,0 +1,137 @@
+Extract Table of Content
+========================
+
+A Pelican plugin to extract table of contents (ToC) from `article.content` and
+place it in its own `article.toc` variable for use in templates.
+
+Copyright (c) Talha Mansoor
+
+Author          | Talha Mansoor
+----------------|-----
+Author Email    | talha131@gmail.com
+Author Homepage | http://onCrashReboot.com
+Github Account  | https://github.com/talha131
+
+
+Acknowledgement
+---------------
+
+Thanks to [Avaris](https://github.com/avaris) for going out of the way to help
+me fix Unicode issues and doing a thorough code review.
+
+Thanks to [gw0](http://gw.tnode.com/) for adding Pandoc reader support.
+
+
+Why do you need it?
+===================
+
+Pelican can generate ToC of reST and Markdown files, using markup's respective
+directive and extension. Such ToC is generated and placed at the beginning of
+`article.content` like a string. Consequently it can not be placed anywhere
+else on the page (eg. `<nav>` HTML5 tag, in header, or at the end of your
+article's contents).
+
+To solve this problem, this plugin extracts ToC from `article.content` and
+places it in its own `article.toc` variable for use in templates.
+
+
+Requirements
+============
+
+`extract_toc` requires BeautifulSoup.
+
+```bash
+pip install beautifulsoup4
+```
+
+
+How to Use
+==========
+
+This plugin works by extracting the first occurrence of enclosed in:
+
+- `<div class="toc">` for the default Markdown reader
+- `<div class="contents topic">` for the default reStructuredText reader
+- `<nav class="TOC">` for the Pandoc reader
+
+If ToC appears in your article at more than one places, `extract_toc` will
+remove only the first occurrence. You shouldn't probably need to have multiple
+ToC in your article. In case you need to display it multiple times, you can
+print it via your template.
+
+
+Template example
+----------------
+
+Add something like this to your Pelican templates if missing:
+
+```python
+{% if article.toc %}
+    <nav class="toc">
+    {{ article.toc }}
+    </nav>
+{% endif %}
+```
+
+
+reStructuredText reader
+-----------------------
+
+To add a table of contents to your reStructuredText document (`.rst`) you need to add a `.. contents::` directive to its beginning. See the [docutils documentation](http://docutils.sourceforge.net/docs/ref/rst/directives.html#table-of-contents) for more details.
+
+```rst
+My super title
+##############
+
+:date: 2010-10-03
+:tags: thats, awesome
+
+.. contents::
+..
+   1  Head 1
+     1.1  Head 2
+   2  Head 3
+   3  head 4
+
+Heading 1
+---------
+
+Lorem ipsum dolor sit amet, consectetuer adipiscing elit. Aenean commodo ligula eget dolor. Aenean massa.
+```
+
+
+Markdown reader
+---------------
+
+To enable table of contents generation for the Markdown reader you need to set `MD_EXTENSIONS = (['toc'])` in your Pelican configuration file.
+
+To add a table of contents to your Markdown document (`.md`) you need to place the `[TOC]` marker to its beginning. See the [Python Markdown documentation](http://pythonhosted.org/Markdown/extensions/toc.html) for more details.
+
+```markdown
+title: My super title
+date: 4-4-2013
+tags: thats, awesome
+
+[TOC]
+
+# Heading 1 #
+
+Lorem ipsum dolor sit amet, consectetuer adipiscing elit. Aenean commodo ligula eget dolor. Aenean massa.
+```
+
+
+Pandoc reader
+-------------
+
+To enable table of contents generation for the Pandoc reader you need to set `PANDOC_ARGS = (['--toc', '--template=pandoc-template-toc'])` in your Pelican configuration file.
+
+Contents of the Pandoc template file `pandoc-template-toc.html5`:
+
+```html
+$if(toc)$
+<nav id="TOC">
+$toc$
+</nav>
+$endif$
+$body$
+```

plugins/extract_toc/__init__.py

@@ -0,0 +1 @@
+from .extract_toc import *

plugins/extract_toc/extract_toc.py

@@ -0,0 +1,50 @@
+# -*- coding: utf-8 -*-
+"""
+Extract Table of Content
+========================
+
+A Pelican plugin to extract table of contents (ToC) from `article.content` and
+place it in its own `article.toc` variable for use in templates.
+"""
+
+from os import path
+from bs4 import BeautifulSoup
+from pelican import signals, readers, contents
+
+
+def extract_toc(content):
+
+    if isinstance(content, contents.Static):
+        return
+
+    soup = BeautifulSoup(content._content,'html.parser')
+    filename = content.source_path
+    extension = path.splitext(filename)[1][1:]
+    toc = None
+    # if it is a Markdown file
+    if extension in readers.MarkdownReader.file_extensions:
+        toc = soup.find('div', class_='toc')
+        if toc: toc.extract()
+    # else if it is a reST file
+    elif extension in readers.RstReader.file_extensions:
+        toc = soup.find('div', class_='contents topic')
+        if toc: toc.extract()
+        if toc:
+            tag=BeautifulSoup(str(toc))
+            tag.div['class']='toc'
+            tag.div['id']=''
+            p=tag.find('p', class_='topic-title first')
+            if p:p.extract()
+            toc=tag
+    elif not toc:  # Pandoc reader
+        toc = soup.find('nav', id='TOC')
+    if toc:
+        toc.extract()
+        content._content = soup.decode()
+        content.toc = toc.decode()
+        if content.toc.startswith('<html>'):
+            content.toc = content.toc[12:-14]
+
+
+def register():
+    signals.content_object_init.connect(extract_toc)