OLD | NEW |
(Empty) | |
| 1 # -*- coding: utf-8 -*- |
| 2 from __future__ import unicode_literals |
| 3 import re |
| 4 import sys |
| 5 |
| 6 |
| 7 """ |
| 8 Python 3 Stuff |
| 9 ============================================================================= |
| 10 """ |
| 11 PY3 = sys.version_info[0] == 3 |
| 12 |
| 13 if PY3: |
| 14 string_type = str |
| 15 text_type = str |
| 16 int2str = chr |
| 17 else: |
| 18 string_type = basestring |
| 19 text_type = unicode |
| 20 int2str = unichr |
| 21 |
| 22 |
| 23 """ |
| 24 Constants you might want to modify |
| 25 ----------------------------------------------------------------------------- |
| 26 """ |
| 27 |
| 28 BLOCK_LEVEL_ELEMENTS = re.compile("^(p|div|h[1-6]|blockquote|pre|table|dl|ol|ul" |
| 29 "|script|noscript|form|fieldset|iframe|math" |
| 30 "|hr|hr/|style|li|dt|dd|thead|tbody" |
| 31 "|tr|th|td|section|footer|header|group|figure" |
| 32 "|figcaption|aside|article|canvas|output" |
| 33 "|progress|video)$", re.IGNORECASE) |
| 34 # Placeholders |
| 35 STX = '\u0002' # Use STX ("Start of text") for start-of-placeholder |
| 36 ETX = '\u0003' # Use ETX ("End of text") for end-of-placeholder |
| 37 INLINE_PLACEHOLDER_PREFIX = STX+"klzzwxh:" |
| 38 INLINE_PLACEHOLDER = INLINE_PLACEHOLDER_PREFIX + "%s" + ETX |
| 39 INLINE_PLACEHOLDER_RE = re.compile(INLINE_PLACEHOLDER % r'([0-9]{4})') |
| 40 AMP_SUBSTITUTE = STX+"amp"+ETX |
| 41 |
| 42 """ |
| 43 Constants you probably do not need to change |
| 44 ----------------------------------------------------------------------------- |
| 45 """ |
| 46 |
| 47 RTL_BIDI_RANGES = ( ('\u0590', '\u07FF'), |
| 48 # Hebrew (0590-05FF), Arabic (0600-06FF), |
| 49 # Syriac (0700-074F), Arabic supplement (0750-077F), |
| 50 # Thaana (0780-07BF), Nko (07C0-07FF). |
| 51 ('\u2D30', '\u2D7F'), # Tifinagh |
| 52 ) |
| 53 |
| 54 # Extensions should use "markdown.util.etree" instead of "etree" (or do `from |
| 55 # markdown.util import etree`). Do not import it by yourself. |
| 56 |
| 57 try: # Is the C implemenation of ElementTree available? |
| 58 import xml.etree.cElementTree as etree |
| 59 from xml.etree.ElementTree import Comment |
| 60 # Serializers (including ours) test with non-c Comment |
| 61 etree.test_comment = Comment |
| 62 if etree.VERSION < "1.0.5": |
| 63 raise RuntimeError("cElementTree version 1.0.5 or higher is required.") |
| 64 except (ImportError, RuntimeError): |
| 65 # Use the Python implementation of ElementTree? |
| 66 import xml.etree.ElementTree as etree |
| 67 if etree.VERSION < "1.1": |
| 68 raise RuntimeError("ElementTree version 1.1 or higher is required") |
| 69 |
| 70 |
| 71 """ |
| 72 AUXILIARY GLOBAL FUNCTIONS |
| 73 ============================================================================= |
| 74 """ |
| 75 |
| 76 |
| 77 def isBlockLevel(tag): |
| 78 """Check if the tag is a block level HTML tag.""" |
| 79 if isinstance(tag, string_type): |
| 80 return BLOCK_LEVEL_ELEMENTS.match(tag) |
| 81 # Some ElementTree tags are not strings, so return False. |
| 82 return False |
| 83 |
| 84 """ |
| 85 MISC AUXILIARY CLASSES |
| 86 ============================================================================= |
| 87 """ |
| 88 |
| 89 class AtomicString(text_type): |
| 90 """A string which should not be further processed.""" |
| 91 pass |
| 92 |
| 93 |
| 94 class Processor(object): |
| 95 def __init__(self, markdown_instance=None): |
| 96 if markdown_instance: |
| 97 self.markdown = markdown_instance |
| 98 |
| 99 |
| 100 class HtmlStash(object): |
| 101 """ |
| 102 This class is used for stashing HTML objects that we extract |
| 103 in the beginning and replace with place-holders. |
| 104 """ |
| 105 |
| 106 def __init__ (self): |
| 107 """ Create a HtmlStash. """ |
| 108 self.html_counter = 0 # for counting inline html segments |
| 109 self.rawHtmlBlocks=[] |
| 110 |
| 111 def store(self, html, safe=False): |
| 112 """ |
| 113 Saves an HTML segment for later reinsertion. Returns a |
| 114 placeholder string that needs to be inserted into the |
| 115 document. |
| 116 |
| 117 Keyword arguments: |
| 118 |
| 119 * html: an html segment |
| 120 * safe: label an html segment as safe for safemode |
| 121 |
| 122 Returns : a placeholder string |
| 123 |
| 124 """ |
| 125 self.rawHtmlBlocks.append((html, safe)) |
| 126 placeholder = self.get_placeholder(self.html_counter) |
| 127 self.html_counter += 1 |
| 128 return placeholder |
| 129 |
| 130 def reset(self): |
| 131 self.html_counter = 0 |
| 132 self.rawHtmlBlocks = [] |
| 133 |
| 134 def get_placeholder(self, key): |
| 135 return "%swzxhzdk:%d%s" % (STX, key, ETX) |
| 136 |
OLD | NEW |