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
|
# -*- coding: utf-8 -*-
import re
from logging import CRITICAL
import etree_loader
"""
CONSTANTS
=============================================================================
"""
"""
Constants you might want to modify
-----------------------------------------------------------------------------
"""
BLOCK_LEVEL_ELEMENTS = re.compile("p|div|h[1-6]|blockquote|pre|table|dl|ol|ul"
"|script|noscript|form|fieldset|iframe|math"
"|ins|del|hr|hr/|style|li|dt|dd|thead|tbody"
"|tr|th|td|section|footer|header|group|figure"
"|figcaption|aside|article|canvas|output"
"|progress|video")
# Placeholders
STX = u'\u0002' # Use STX ("Start of text") for start-of-placeholder
ETX = u'\u0003' # Use ETX ("End of text") for end-of-placeholder
INLINE_PLACEHOLDER_PREFIX = STX+"klzzwxh:"
INLINE_PLACEHOLDER = INLINE_PLACEHOLDER_PREFIX + "%s" + ETX
INLINE_PLACEHOLDER_RE = re.compile(INLINE_PLACEHOLDER % r'([0-9]{4})')
AMP_SUBSTITUTE = STX+"amp"+ETX
"""
Constants you probably do not need to change
-----------------------------------------------------------------------------
"""
RTL_BIDI_RANGES = ( (u'\u0590', u'\u07FF'),
# Hebrew (0590-05FF), Arabic (0600-06FF),
# Syriac (0700-074F), Arabic supplement (0750-077F),
# Thaana (0780-07BF), Nko (07C0-07FF).
(u'\u2D30', u'\u2D7F'), # Tifinagh
)
# Extensions should use "markdown.util.etree" instead of "etree" (or do `from
# markdown.util import etree`). Do not import it by yourself.
etree = etree_loader.importETree()
"""
AUXILIARY GLOBAL FUNCTIONS
=============================================================================
"""
def isBlockLevel(tag):
"""Check if the tag is a block level HTML tag."""
if isinstance(tag, basestring):
return BLOCK_LEVEL_ELEMENTS.match(tag)
# Some ElementTree tags are not strings, so return False.
return False
"""
MISC AUXILIARY CLASSES
=============================================================================
"""
class AtomicString(unicode):
"""A string which should not be further processed."""
pass
class Processor:
def __init__(self, markdown_instance=None):
if markdown_instance:
self.markdown = markdown_instance
class HtmlStash:
"""
This class is used for stashing HTML objects that we extract
in the beginning and replace with place-holders.
"""
def __init__ (self):
""" Create a HtmlStash. """
self.html_counter = 0 # for counting inline html segments
self.rawHtmlBlocks=[]
def store(self, html, safe=False):
"""
Saves an HTML segment for later reinsertion. Returns a
placeholder string that needs to be inserted into the
document.
Keyword arguments:
* html: an html segment
* safe: label an html segment as safe for safemode
Returns : a placeholder string
"""
self.rawHtmlBlocks.append((html, safe))
placeholder = self.get_placeholder(self.html_counter)
self.html_counter += 1
return placeholder
def reset(self):
self.html_counter = 0
self.rawHtmlBlocks = []
def get_placeholder(self, key):
return "%swzxhzdk:%d%s" % (STX, key, ETX)
|
