/usr/lib/python3/dist-packages/markdown/extensions/headerid.py is in python3-markdown 2.4-1.
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 | """
HeaderID Extension for Python-Markdown
======================================
Auto-generate id attributes for HTML headers.
Basic usage:
>>> import markdown
>>> text = "# Some Header #"
>>> md = markdown.markdown(text, ['headerid'])
>>> print md
<h1 id="some-header">Some Header</h1>
All header IDs are unique:
>>> text = '''
... #Header
... #Header
... #Header'''
>>> md = markdown.markdown(text, ['headerid'])
>>> print md
<h1 id="header">Header</h1>
<h1 id="header_1">Header</h1>
<h1 id="header_2">Header</h1>
To fit within a html template's hierarchy, set the header base level:
>>> text = '''
... #Some Header
... ## Next Level'''
>>> md = markdown.markdown(text, ['headerid(level=3)'])
>>> print md
<h3 id="some-header">Some Header</h3>
<h4 id="next-level">Next Level</h4>
Works with inline markup.
>>> text = '#Some *Header* with [markup](http://example.com).'
>>> md = markdown.markdown(text, ['headerid'])
>>> print md
<h1 id="some-header-with-markup">Some <em>Header</em> with <a href="http://example.com">markup</a>.</h1>
Turn off auto generated IDs:
>>> text = '''
... # Some Header
... # Another Header'''
>>> md = markdown.markdown(text, ['headerid(forceid=False)'])
>>> print md
<h1>Some Header</h1>
<h1>Another Header</h1>
Use with MetaData extension:
>>> text = '''header_level: 2
... header_forceid: Off
...
... # A Header'''
>>> md = markdown.markdown(text, ['headerid', 'meta'])
>>> print md
<h2>A Header</h2>
Copyright 2007-2011 [Waylan Limberg](http://achinghead.com/).
Project website: <http://packages.python.org/Markdown/extensions/header_id.html>
Contact: markdown@freewisdom.org
License: BSD (see ../docs/LICENSE for details)
Dependencies:
* [Python 2.3+](http://python.org)
* [Markdown 2.0+](http://packages.python.org/Markdown/)
"""
from __future__ import absolute_import
from __future__ import unicode_literals
from . import Extension
from ..treeprocessors import Treeprocessor
from ..util import HTML_PLACEHOLDER_RE, parseBoolValue
import re
import logging
import unicodedata
logger = logging.getLogger('MARKDOWN')
IDCOUNT_RE = re.compile(r'^(.*)_([0-9]+)$')
def slugify(value, separator):
""" Slugify a string, to make it URL friendly. """
value = unicodedata.normalize('NFKD', value).encode('ascii', 'ignore')
value = re.sub('[^\w\s-]', '', value.decode('ascii')).strip().lower()
return re.sub('[%s\s]+' % separator, separator, value)
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
def itertext(elem):
""" Loop through all children and return text only.
Reimplements method of same name added to ElementTree in Python 2.7
"""
if elem.text:
yield elem.text
for e in elem:
for s in itertext(e):
yield s
if e.tail:
yield e.tail
def stashedHTML2text(text, md):
""" Extract raw HTML, reduce to plain text and swap with placeholder. """
def _html_sub(m):
""" Substitute raw html with plain text. """
try:
raw, safe = md.htmlStash.rawHtmlBlocks[int(m.group(1))]
except (IndexError, TypeError):
return m.group(0)
if md.safeMode and not safe:
return ''
# Strip out tags and entities - leaveing text
return re.sub(r'(<[^>]+>)|(&[\#a-zA-Z0-9]+;)', '', raw)
return HTML_PLACEHOLDER_RE.sub(_html_sub, text)
class HeaderIdTreeprocessor(Treeprocessor):
""" Assign IDs to headers. """
IDs = set()
def run(self, doc):
start_level, force_id = self._get_meta()
slugify = self.config['slugify']
sep = self.config['separator']
for elem in doc.getiterator():
if elem.tag in ['h1', 'h2', 'h3', 'h4', 'h5', 'h6']:
if force_id:
if "id" in elem.attrib:
id = elem.get('id')
else:
id = stashedHTML2text(''.join(itertext(elem)), self.md)
id = slugify(id, sep)
elem.set('id', unique(id, self.IDs))
if start_level:
level = int(elem.tag[-1]) + start_level
if level > 6:
level = 6
elem.tag = 'h%d' % level
def _get_meta(self):
""" Return meta data suported by this ext as a tuple """
level = int(self.config['level']) - 1
force = parseBoolValue(self.config['forceid'])
if hasattr(self.md, 'Meta'):
if 'header_level' in self.md.Meta:
level = int(self.md.Meta['header_level'][0]) - 1
if 'header_forceid' in self.md.Meta:
force = parseBoolValue(self.md.Meta['header_forceid'][0])
return level, force
class HeaderIdExtension(Extension):
def __init__(self, configs):
# set defaults
self.config = {
'level' : ['1', 'Base level for headers.'],
'forceid' : ['True', 'Force all headers to have an id.'],
'separator' : ['-', 'Word separator.'],
'slugify' : [slugify, 'Callable to generate anchors'],
}
for key, value in configs:
self.setConfig(key, value)
def extendMarkdown(self, md, md_globals):
md.registerExtension(self)
self.processor = HeaderIdTreeprocessor()
self.processor.md = md
self.processor.config = self.getConfigs()
if 'attr_list' in md.treeprocessors.keys():
# insert after attr_list treeprocessor
md.treeprocessors.add('headerid', self.processor, '>attr_list')
else:
# insert after 'prettify' treeprocessor.
md.treeprocessors.add('headerid', self.processor, '>prettify')
def reset(self):
self.processor.IDs = set()
def makeExtension(configs=None):
return HeaderIdExtension(configs=configs)
|