/usr/lib/python2.7/dist-packages/markdown/extensions/toc.py is in python-markdown 2.5.1-2.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 | """
Table of Contents Extension for Python-Markdown
===============================================
See <https://pythonhosted.org/Markdown/extensions/toc.html>
for documentation.
Oringinal code Copyright 2008 [Jack Miller](http://codezen.org)
All changes Copyright 2008-2014 The Python Markdown Project
License: [BSD](http://www.opensource.org/licenses/bsd-license.php)
"""
from __future__ import absolute_import
from __future__ import unicode_literals
from . import Extension
from ..treeprocessors import Treeprocessor
from ..util import etree, parseBoolValue, AMP_SUBSTITUTE
from .headerid import slugify, unique, itertext, stashedHTML2text
import re
def order_toc_list(toc_list):
"""Given an unsorted list with errors and skips, return a nested one.
[{'level': 1}, {'level': 2}]
=>
[{'level': 1, 'children': [{'level': 2, 'children': []}]}]
A wrong list is also converted:
[{'level': 2}, {'level': 1}]
=>
[{'level': 2, 'children': []}, {'level': 1, 'children': []}]
"""
def build_correct(remaining_list, prev_elements=[{'level': 1000}]):
if not remaining_list:
return [], []
current = remaining_list.pop(0)
if not 'children' in current.keys():
current['children'] = []
if not prev_elements:
# This happens for instance with [8, 1, 1], ie. when some
# header level is outside a scope. We treat it as a
# top-level
next_elements, children = build_correct(remaining_list, [current])
current['children'].append(children)
return [current] + next_elements, []
prev_element = prev_elements.pop()
children = []
next_elements = []
# Is current part of the child list or next list?
if current['level'] > prev_element['level']:
#print "%d is a child of %d" % (current['level'], prev_element['level'])
prev_elements.append(prev_element)
prev_elements.append(current)
prev_element['children'].append(current)
next_elements2, children2 = build_correct(remaining_list, prev_elements)
children += children2
next_elements += next_elements2
else:
#print "%d is ancestor of %d" % (current['level'], prev_element['level'])
if not prev_elements:
#print "No previous elements, so appending to the next set"
next_elements.append(current)
prev_elements = [current]
next_elements2, children2 = build_correct(remaining_list, prev_elements)
current['children'].extend(children2)
else:
#print "Previous elements, comparing to those first"
remaining_list.insert(0, current)
next_elements2, children2 = build_correct(remaining_list, prev_elements)
children.extend(children2)
next_elements += next_elements2
return next_elements, children
ordered_list, __ = build_correct(toc_list)
return ordered_list
class TocTreeprocessor(Treeprocessor):
# Iterator wrapper to get parent and child all at once
def iterparent(self, root):
for parent in root.getiterator():
for child in parent:
yield parent, child
def add_anchor(self, c, elem_id): #@ReservedAssignment
anchor = etree.Element("a")
anchor.text = c.text
anchor.attrib["href"] = "#" + elem_id
anchor.attrib["class"] = "toclink"
c.text = ""
for elem in c.getchildren():
anchor.append(elem)
c.remove(elem)
c.append(anchor)
def add_permalink(self, c, elem_id):
permalink = etree.Element("a")
permalink.text = ("%spara;" % AMP_SUBSTITUTE
if self.use_permalinks is True else self.use_permalinks)
permalink.attrib["href"] = "#" + elem_id
permalink.attrib["class"] = "headerlink"
permalink.attrib["title"] = "Permanent link"
c.append(permalink)
def build_toc_etree(self, div, toc_list):
# Add title to the div
if self.config["title"]:
header = etree.SubElement(div, "span")
header.attrib["class"] = "toctitle"
header.text = self.config["title"]
def build_etree_ul(toc_list, parent):
ul = etree.SubElement(parent, "ul")
for item in toc_list:
# List item link, to be inserted into the toc div
li = etree.SubElement(ul, "li")
link = etree.SubElement(li, "a")
link.text = item.get('name', '')
link.attrib["href"] = '#' + item.get('id', '')
if item['children']:
build_etree_ul(item['children'], li)
return ul
return build_etree_ul(toc_list, div)
def run(self, doc):
div = etree.Element("div")
div.attrib["class"] = "toc"
header_rgx = re.compile("[Hh][123456]")
self.use_anchors = parseBoolValue(self.config["anchorlink"])
self.use_permalinks = parseBoolValue(self.config["permalink"], False)
if self.use_permalinks is None:
self.use_permalinks = self.config["permalink"]
# Get a list of id attributes
used_ids = set()
for c in doc.getiterator():
if "id" in c.attrib:
used_ids.add(c.attrib["id"])
toc_list = []
marker_found = False
for (p, c) in self.iterparent(doc):
text = ''.join(itertext(c)).strip()
if not text:
continue
# To keep the output from screwing up the
# validation by putting a <div> inside of a <p>
# we actually replace the <p> in its entirety.
# We do not allow the marker inside a header as that
# would causes an enless loop of placing a new TOC
# inside previously generated TOC.
if c.text and c.text.strip() == self.config["marker"] and \
not header_rgx.match(c.tag) and c.tag not in ['pre', 'code']:
for i in range(len(p)):
if p[i] == c:
p[i] = div
break
marker_found = True
if header_rgx.match(c.tag):
# Do not override pre-existing ids
if not "id" in c.attrib:
elem_id = stashedHTML2text(text, self.markdown)
elem_id = unique(self.config["slugify"](elem_id, '-'), used_ids)
c.attrib["id"] = elem_id
else:
elem_id = c.attrib["id"]
tag_level = int(c.tag[-1])
toc_list.append({'level': tag_level,
'id': elem_id,
'name': text})
if self.use_anchors:
self.add_anchor(c, elem_id)
if self.use_permalinks:
self.add_permalink(c, elem_id)
toc_list_nested = order_toc_list(toc_list)
self.build_toc_etree(div, toc_list_nested)
prettify = self.markdown.treeprocessors.get('prettify')
if prettify: prettify.run(div)
if not marker_found:
# serialize and attach to markdown instance.
toc = self.markdown.serializer(div)
for pp in self.markdown.postprocessors.values():
toc = pp.run(toc)
self.markdown.toc = toc
class TocExtension(Extension):
TreeProcessorClass = TocTreeprocessor
def __init__(self, *args, **kwargs):
self.config = {
"marker" : ["[TOC]",
"Text to find and replace with Table of Contents - "
"Defaults to \"[TOC]\""],
"slugify" : [slugify,
"Function to generate anchors based on header text - "
"Defaults to the headerid ext's slugify function."],
"title" : ["",
"Title to insert into TOC <div> - "
"Defaults to an empty string"],
"anchorlink" : [0,
"1 if header should be a self link - "
"Defaults to 0"],
"permalink" : [0,
"1 or link text if a Sphinx-style permalink should be added - "
"Defaults to 0"]
}
super(TocExtension, self).__init__(*args, **kwargs)
def extendMarkdown(self, md, md_globals):
tocext = self.TreeProcessorClass(md)
tocext.config = self.getConfigs()
# Headerid ext is set to '>prettify'. With this set to '_end',
# it should always come after headerid ext (and honor ids assinged
# by the header id extension) if both are used. Same goes for
# attr_list extension. This must come last because we don't want
# to redefine ids after toc is created. But we do want toc prettified.
md.treeprocessors.add("toc", tocext, "_end")
def makeExtension(*args, **kwargs):
return TocExtension(*args, **kwargs)
|