reverted to pelicanconf and re-added toc plugin

pelicanconf.py

@@ -0,0 +1,60 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*- #
+from __future__ import unicode_literals
+from datetime import date
+
+
+AUTHOR = u'PonyGnomeBot'
+SITENAME = u'Apache Infrastructure'
+CURRENTYEAR = date.today().year
+
+PATH = 'content'
+
+TIMEZONE = 'UTC'
+DEFAULT_DATE = 'fs'
+DEFAULT_LANG = u'en'
+SITEURL = 'https://infra-test.apache.org'
+
+# Save pages using full directory preservation
+PATH_METADATA= '.*?(pages/)?(?P<path_no_ext>.*?)\.[a-z]*$'
+PAGE_SAVE_AS= './{slug}.html'
+PAGE_URL= './{slug}.html'
+
+# Make .htaccess static
+STATIC_PATHS = ['pages/.htaccess']
+
+# Standard behavior:
+#PAGE_SAVE_AS = './{slug}.html'
+
+#ARTICLE_SAVE_AS = 'news/{slug}.html'
+#ARTICLE_URL = 'news/{slug}.html'
+
+# Sort news by date, descending, latest article first
+ARTICLE_ORDER_BY = 'reversed-date'
+
+# Feed generation is usually not desired when developing
+FEED_ALL_ATOM = None
+CATEGORY_FEED_ATOM = None
+TRANSLATION_FEED_ATOM = None
+AUTHOR_FEED_ATOM = None
+AUTHOR_FEED_RSS = None
+
+# TOC Generator
+PLUGIN_PATHS = ['./theme/plugins']
+PLUGINS = ['toc', 'pelican-gfm', 'spu']
+TOC_HEADERS = r"h[1-6]"
+
+# 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', '#'),)
+
+# Social widget
+SOCIAL = (('You can add links in your config file', '#'),
+          ('Another social link', '#'),)
+
+DEFAULT_PAGINATION = False
+
+# Uncomment following line if you want document-relative URLs when developing
+#RELATIVE_URLS = True

theme/plugins/toc.py

@@ -0,0 +1,149 @@
+'''
+toc
+===================================
+Generates Table of Contents for markdown.
+Only generates a ToC for the headers FOLLOWING th [TOC] tag,
+so you can insert it after a specific section that need not be
+include in the ToC.
+'''
+
+import logging
+import re
+
+from bs4 import BeautifulSoup, Comment
+
+from pelican import contents, signals
+from pelican.utils import slugify
+
+
+logger = logging.getLogger(__name__)
+
+'''
+https://github.com/waylan/Python-Markdown/blob/master/markdown/extensions/headerid.py
+'''
+IDCOUNT_RE = re.compile(r'^(.*)_([0-9]+)$')
+
+
+def unique(id, ids):
+    """ Ensure id is unique in set of ids. Append '_1', '_2'... if not """
+    while id in ids or not id:
+        m = IDCOUNT_RE.match(id)
+        if m:
+            id = '%s_%d' % (m.group(1), int(m.group(2)) + 1)
+        else:
+            id = '%s_%d' % (id, 1)
+    ids.add(id)
+    return id
+'''
+end
+'''
+
+
+class HtmlTreeNode(object):
+    def __init__(self, parent, header, level, id):
+        self.children = []
+        self.parent = parent
+        self.header = header
+        self.level = level
+        self.id = id
+
+    def add(self, new_header, ids):
+        new_level = new_header.name
+        new_string = new_header.string
+        new_id = new_header.attrs.get('id')
+
+        if not new_string:
+            new_string = new_header.find_all(
+                    text=lambda t: not isinstance(t, Comment),
+                    recursive=True)
+            new_string = "".join(new_string)
+
+        if not new_id:
+            new_id = slugify(new_string, ())
+
+        new_id = unique(new_id, ids)  # make sure id is unique
+        new_header.attrs['id'] = new_id
+        if(self.level < new_level):
+            new_node = HtmlTreeNode(self, new_string, new_level, new_id)
+            self.children += [new_node]
+            return new_node, new_header
+        elif(self.level == new_level):
+            new_node = HtmlTreeNode(self.parent, new_string, new_level, new_id)
+            self.parent.children += [new_node]
+            return new_node, new_header
+        elif(self.level > new_level):
+            return self.parent.add(new_header, ids)
+
+    def __str__(self):
+        ret = ""
+        if self.parent:
+            ret = "<a class='toc-href' href='#{0}' title='{1}'>{1}</a>".format(
+                    self.id, self.header)
+
+        if self.children:
+            ret += "<ul>{}</ul>".format('{}'*len(self.children)).format(
+                    *self.children)
+
+        if self.parent:
+            ret = "<li>{}</li>".format(ret)
+
+        if not self.parent:
+            ret = "<div id='toc' style='border-radius: 3px; border: 1px solid #999; background-color: #EEE; padding: 4px;'><h4>Table of Contents:</h4><ul>{}</ul></div>".format(ret)
+
+        return ret
+
+
+def init_default_config(pelican):
+    from pelican.settings import DEFAULT_CONFIG
+
+    TOC_DEFAULT = {
+        'TOC_HEADERS': '^h[1-6]',
+        'TOC_RUN': 'true'
+    }
+
+    DEFAULT_CONFIG.setdefault('TOC', TOC_DEFAULT)
+    if(pelican):
+        pelican.settings.setdefault('TOC', TOC_DEFAULT)
+
+
+def generate_toc(content):
+    if isinstance(content, contents.Static):
+        return
+
+    all_ids = set()
+    title = content.metadata.get('title', 'Title')
+    tree = node = HtmlTreeNode(None, title, 'h0', '')
+    soup = BeautifulSoup(content._content, 'html.parser')
+    settoc = False
+
+    try:
+        header_re = re.compile(content.metadata.get(
+            'toc_headers', content.settings['TOC']['TOC_HEADERS']))
+    except re.error as e:
+        logger.error("TOC_HEADERS '%s' is not a valid re\n%s",
+                     content.settings['TOC']['TOC_HEADERS'])
+        raise e
+
+    # Find TOC tag
+    tocTag = soup.find('p', text = '[TOC]')
+    if tocTag:
+        for header in tocTag.findAllNext(header_re):
+            settoc = True
+            node, new_header = node.add(header, all_ids)
+            header.replaceWith(new_header)  # to get our ids back into soup
+
+        if settoc:
+            print("Generating ToC for %s" % content.slug)
+            tree_string = '{}'.format(tree)
+            tree_soup = BeautifulSoup(tree_string, 'html.parser')
+            content.toc = tree_soup.decode(formatter='html')
+            itoc = soup.find('p', text = '[TOC]')
+            if itoc:
+                itoc.replaceWith(tree_soup)
+
+        content._content = soup.decode(formatter='html')
+
+
+def register():
+    signals.initialized.connect(init_default_config)
+signals.content_object_init.connect(generate_toc)