OLD | NEW |
(Empty) | |
| 1 """ |
| 2 HeaderID Extension for Python-Markdown |
| 3 ====================================== |
| 4 |
| 5 Auto-generate id attributes for HTML headers. |
| 6 |
| 7 Basic usage: |
| 8 |
| 9 >>> import markdown |
| 10 >>> text = "# Some Header #" |
| 11 >>> md = markdown.markdown(text, ['headerid']) |
| 12 >>> print md |
| 13 <h1 id="some-header">Some Header</h1> |
| 14 |
| 15 All header IDs are unique: |
| 16 |
| 17 >>> text = ''' |
| 18 ... #Header |
| 19 ... #Header |
| 20 ... #Header''' |
| 21 >>> md = markdown.markdown(text, ['headerid']) |
| 22 >>> print md |
| 23 <h1 id="header">Header</h1> |
| 24 <h1 id="header_1">Header</h1> |
| 25 <h1 id="header_2">Header</h1> |
| 26 |
| 27 To fit within a html template's hierarchy, set the header base level: |
| 28 |
| 29 >>> text = ''' |
| 30 ... #Some Header |
| 31 ... ## Next Level''' |
| 32 >>> md = markdown.markdown(text, ['headerid(level=3)']) |
| 33 >>> print md |
| 34 <h3 id="some-header">Some Header</h3> |
| 35 <h4 id="next-level">Next Level</h4> |
| 36 |
| 37 Works with inline markup. |
| 38 |
| 39 >>> text = '#Some *Header* with [markup](http://example.com).' |
| 40 >>> md = markdown.markdown(text, ['headerid']) |
| 41 >>> print md |
| 42 <h1 id="some-header-with-markup">Some <em>Header</em> with <a href="http://e
xample.com">markup</a>.</h1> |
| 43 |
| 44 Turn off auto generated IDs: |
| 45 |
| 46 >>> text = ''' |
| 47 ... # Some Header |
| 48 ... # Another Header''' |
| 49 >>> md = markdown.markdown(text, ['headerid(forceid=False)']) |
| 50 >>> print md |
| 51 <h1>Some Header</h1> |
| 52 <h1>Another Header</h1> |
| 53 |
| 54 Use with MetaData extension: |
| 55 |
| 56 >>> text = '''header_level: 2 |
| 57 ... header_forceid: Off |
| 58 ... |
| 59 ... # A Header''' |
| 60 >>> md = markdown.markdown(text, ['headerid', 'meta']) |
| 61 >>> print md |
| 62 <h2>A Header</h2> |
| 63 |
| 64 Copyright 2007-2011 [Waylan Limberg](http://achinghead.com/). |
| 65 |
| 66 Project website: <http://packages.python.org/Markdown/extensions/header_id.html> |
| 67 Contact: markdown@freewisdom.org |
| 68 |
| 69 License: BSD (see ../docs/LICENSE for details) |
| 70 |
| 71 Dependencies: |
| 72 * [Python 2.3+](http://python.org) |
| 73 * [Markdown 2.0+](http://packages.python.org/Markdown/) |
| 74 |
| 75 """ |
| 76 |
| 77 from __future__ import absolute_import |
| 78 from __future__ import unicode_literals |
| 79 from . import Extension |
| 80 from ..treeprocessors import Treeprocessor |
| 81 import re |
| 82 import logging |
| 83 import unicodedata |
| 84 |
| 85 logger = logging.getLogger('MARKDOWN') |
| 86 |
| 87 IDCOUNT_RE = re.compile(r'^(.*)_([0-9]+)$') |
| 88 |
| 89 |
| 90 def slugify(value, separator): |
| 91 """ Slugify a string, to make it URL friendly. """ |
| 92 value = unicodedata.normalize('NFKD', value).encode('ascii', 'ignore') |
| 93 value = re.sub('[^\w\s-]', '', value.decode('ascii')).strip().lower() |
| 94 return re.sub('[%s\s]+' % separator, separator, value) |
| 95 |
| 96 |
| 97 def unique(id, ids): |
| 98 """ Ensure id is unique in set of ids. Append '_1', '_2'... if not """ |
| 99 while id in ids or not id: |
| 100 m = IDCOUNT_RE.match(id) |
| 101 if m: |
| 102 id = '%s_%d'% (m.group(1), int(m.group(2))+1) |
| 103 else: |
| 104 id = '%s_%d'% (id, 1) |
| 105 ids.add(id) |
| 106 return id |
| 107 |
| 108 |
| 109 def itertext(elem): |
| 110 """ Loop through all children and return text only. |
| 111 |
| 112 Reimplements method of same name added to ElementTree in Python 2.7 |
| 113 |
| 114 """ |
| 115 if elem.text: |
| 116 yield elem.text |
| 117 for e in elem: |
| 118 for s in itertext(e): |
| 119 yield s |
| 120 if e.tail: |
| 121 yield e.tail |
| 122 |
| 123 |
| 124 class HeaderIdTreeprocessor(Treeprocessor): |
| 125 """ Assign IDs to headers. """ |
| 126 |
| 127 IDs = set() |
| 128 |
| 129 def run(self, doc): |
| 130 start_level, force_id = self._get_meta() |
| 131 slugify = self.config['slugify'] |
| 132 sep = self.config['separator'] |
| 133 for elem in doc.getiterator(): |
| 134 if elem.tag in ['h1', 'h2', 'h3', 'h4', 'h5', 'h6']: |
| 135 if force_id: |
| 136 if "id" in elem.attrib: |
| 137 id = elem.get('id') |
| 138 else: |
| 139 id = slugify(''.join(itertext(elem)), sep) |
| 140 elem.set('id', unique(id, self.IDs)) |
| 141 if start_level: |
| 142 level = int(elem.tag[-1]) + start_level |
| 143 if level > 6: |
| 144 level = 6 |
| 145 elem.tag = 'h%d' % level |
| 146 |
| 147 |
| 148 def _get_meta(self): |
| 149 """ Return meta data suported by this ext as a tuple """ |
| 150 level = int(self.config['level']) - 1 |
| 151 force = self._str2bool(self.config['forceid']) |
| 152 if hasattr(self.md, 'Meta'): |
| 153 if 'header_level' in self.md.Meta: |
| 154 level = int(self.md.Meta['header_level'][0]) - 1 |
| 155 if 'header_forceid' in self.md.Meta: |
| 156 force = self._str2bool(self.md.Meta['header_forceid'][0]) |
| 157 return level, force |
| 158 |
| 159 def _str2bool(self, s, default=False): |
| 160 """ Convert a string to a booleen value. """ |
| 161 s = str(s) |
| 162 if s.lower() in ['0', 'f', 'false', 'off', 'no', 'n']: |
| 163 return False |
| 164 elif s.lower() in ['1', 't', 'true', 'on', 'yes', 'y']: |
| 165 return True |
| 166 return default |
| 167 |
| 168 |
| 169 class HeaderIdExtension(Extension): |
| 170 def __init__(self, configs): |
| 171 # set defaults |
| 172 self.config = { |
| 173 'level' : ['1', 'Base level for headers.'], |
| 174 'forceid' : ['True', 'Force all headers to have an id.'], |
| 175 'separator' : ['-', 'Word separator.'], |
| 176 'slugify' : [slugify, 'Callable to generate anchors'], |
| 177 } |
| 178 |
| 179 for key, value in configs: |
| 180 self.setConfig(key, value) |
| 181 |
| 182 def extendMarkdown(self, md, md_globals): |
| 183 md.registerExtension(self) |
| 184 self.processor = HeaderIdTreeprocessor() |
| 185 self.processor.md = md |
| 186 self.processor.config = self.getConfigs() |
| 187 if 'attr_list' in md.treeprocessors.keys(): |
| 188 # insert after attr_list treeprocessor |
| 189 md.treeprocessors.add('headerid', self.processor, '>attr_list') |
| 190 else: |
| 191 # insert after 'prettify' treeprocessor. |
| 192 md.treeprocessors.add('headerid', self.processor, '>prettify') |
| 193 |
| 194 def reset(self): |
| 195 self.processor.IDs = set() |
| 196 |
| 197 |
| 198 def makeExtension(configs=None): |
| 199 return HeaderIdExtension(configs=configs) |
OLD | NEW |