OLD | NEW |
(Empty) | |
| 1 """ |
| 2 Attribute List Extension for Python-Markdown |
| 3 ============================================ |
| 4 |
| 5 Adds attribute list syntax. Inspired by |
| 6 [maruku](http://maruku.rubyforge.org/proposal.html#attribute_lists)'s |
| 7 feature of the same name. |
| 8 |
| 9 Copyright 2011 [Waylan Limberg](http://achinghead.com/). |
| 10 |
| 11 Contact: markdown@freewisdom.org |
| 12 |
| 13 License: BSD (see ../LICENSE.md for details) |
| 14 |
| 15 Dependencies: |
| 16 * [Python 2.4+](http://python.org) |
| 17 * [Markdown 2.1+](http://packages.python.org/Markdown/) |
| 18 |
| 19 """ |
| 20 |
| 21 from __future__ import absolute_import |
| 22 from __future__ import unicode_literals |
| 23 from . import Extension |
| 24 from ..treeprocessors import Treeprocessor |
| 25 from ..util import isBlockLevel |
| 26 import re |
| 27 |
| 28 try: |
| 29 Scanner = re.Scanner |
| 30 except AttributeError: |
| 31 # must be on Python 2.4 |
| 32 from sre import Scanner |
| 33 |
| 34 def _handle_double_quote(s, t): |
| 35 k, v = t.split('=') |
| 36 return k, v.strip('"') |
| 37 |
| 38 def _handle_single_quote(s, t): |
| 39 k, v = t.split('=') |
| 40 return k, v.strip("'") |
| 41 |
| 42 def _handle_key_value(s, t): |
| 43 return t.split('=') |
| 44 |
| 45 def _handle_word(s, t): |
| 46 if t.startswith('.'): |
| 47 return '.', t[1:] |
| 48 if t.startswith('#'): |
| 49 return 'id', t[1:] |
| 50 return t, t |
| 51 |
| 52 _scanner = Scanner([ |
| 53 (r'[^ ]+=".*?"', _handle_double_quote), |
| 54 (r"[^ ]+='.*?'", _handle_single_quote), |
| 55 (r'[^ ]+=[^ ]*', _handle_key_value), |
| 56 (r'[^ ]+', _handle_word), |
| 57 (r' ', None) |
| 58 ]) |
| 59 |
| 60 def get_attrs(str): |
| 61 """ Parse attribute list and return a list of attribute tuples. """ |
| 62 return _scanner.scan(str)[0] |
| 63 |
| 64 def isheader(elem): |
| 65 return elem.tag in ['h1', 'h2', 'h3', 'h4', 'h5', 'h6'] |
| 66 |
| 67 class AttrListTreeprocessor(Treeprocessor): |
| 68 |
| 69 BASE_RE = r'\{\:?([^\}]*)\}' |
| 70 HEADER_RE = re.compile(r'[ ]*%s[ ]*$' % BASE_RE) |
| 71 BLOCK_RE = re.compile(r'\n[ ]*%s[ ]*$' % BASE_RE) |
| 72 INLINE_RE = re.compile(r'^%s' % BASE_RE) |
| 73 NAME_RE = re.compile(r'[^A-Z_a-z\u00c0-\u00d6\u00d8-\u00f6\u00f8-\u02ff\u037
0-\u037d' |
| 74 r'\u037f-\u1fff\u200c-\u200d\u2070-\u218f\u2c00-\u2fef' |
| 75 r'\u3001-\ud7ff\uf900-\ufdcf\ufdf0-\ufffd' |
| 76 r'\:\-\.0-9\u00b7\u0300-\u036f\u203f-\u2040]+') |
| 77 |
| 78 def run(self, doc): |
| 79 for elem in doc.getiterator(): |
| 80 if isBlockLevel(elem.tag): |
| 81 # Block level: check for attrs on last line of text |
| 82 RE = self.BLOCK_RE |
| 83 if isheader(elem): |
| 84 # header: check for attrs at end of line |
| 85 RE = self.HEADER_RE |
| 86 if len(elem) and elem[-1].tail: |
| 87 # has children. Get from tail of last child |
| 88 m = RE.search(elem[-1].tail) |
| 89 if m: |
| 90 self.assign_attrs(elem, m.group(1)) |
| 91 elem[-1].tail = elem[-1].tail[:m.start()] |
| 92 if isheader(elem): |
| 93 # clean up trailing #s |
| 94 elem[-1].tail = elem[-1].tail.rstrip('#').rstrip() |
| 95 elif elem.text: |
| 96 # no children. Get from text. |
| 97 m = RE.search(elem.text) |
| 98 if m: |
| 99 self.assign_attrs(elem, m.group(1)) |
| 100 elem.text = elem.text[:m.start()] |
| 101 if isheader(elem): |
| 102 # clean up trailing #s |
| 103 elem.text = elem.text.rstrip('#').rstrip() |
| 104 else: |
| 105 # inline: check for attrs at start of tail |
| 106 if elem.tail: |
| 107 m = self.INLINE_RE.match(elem.tail) |
| 108 if m: |
| 109 self.assign_attrs(elem, m.group(1)) |
| 110 elem.tail = elem.tail[m.end():] |
| 111 |
| 112 def assign_attrs(self, elem, attrs): |
| 113 """ Assign attrs to element. """ |
| 114 for k, v in get_attrs(attrs): |
| 115 if k == '.': |
| 116 # add to class |
| 117 cls = elem.get('class') |
| 118 if cls: |
| 119 elem.set('class', '%s %s' % (cls, v)) |
| 120 else: |
| 121 elem.set('class', v) |
| 122 else: |
| 123 # assign attr k with v |
| 124 elem.set(self.sanitize_name(k), v) |
| 125 |
| 126 def sanitize_name(self, name): |
| 127 """ |
| 128 Sanitize name as 'an XML Name, minus the ":"'. |
| 129 See http://www.w3.org/TR/REC-xml-names/#NT-NCName |
| 130 """ |
| 131 return self.NAME_RE.sub('_', name) |
| 132 |
| 133 |
| 134 class AttrListExtension(Extension): |
| 135 def extendMarkdown(self, md, md_globals): |
| 136 md.treeprocessors.add('attr_list', AttrListTreeprocessor(md), '>prettify
') |
| 137 |
| 138 |
| 139 def makeExtension(configs={}): |
| 140 return AttrListExtension(configs=configs) |
OLD | NEW |