forked from Python-Markdown/markdown
-
Notifications
You must be signed in to change notification settings - Fork 0
/
util.py
178 lines (143 loc) · 5.5 KB
/
util.py
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
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import re
import sys
"""
Python 3 Stuff
=============================================================================
"""
PY3 = sys.version_info[0] == 3
if PY3: # pragma: no cover
string_type = str
text_type = str
int2str = chr
iterrange = range
else: # pragma: no cover
string_type = basestring # noqa
text_type = unicode # noqa
int2str = unichr # noqa
iterrange = xrange # noqa
"""
Constants you might want to modify
-----------------------------------------------------------------------------
"""
BLOCK_LEVEL_ELEMENTS = re.compile(
r"^(p|div|h[1-6]|blockquote|pre|table|dl|ol|ul"
r"|script|noscript|form|fieldset|iframe|math"
r"|hr|hr/|style|li|dt|dd|thead|tbody"
r"|tr|th|td|section|footer|header|group|figure"
r"|figcaption|aside|article|canvas|output"
r"|progress|video|nav|main)$",
re.IGNORECASE
)
# Placeholders
STX = '\u0002' # Use STX ("Start of text") for start-of-placeholder
ETX = '\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]+)')
AMP_SUBSTITUTE = STX+"amp"+ETX
HTML_PLACEHOLDER = STX + "wzxhzdk:%s" + ETX
HTML_PLACEHOLDER_RE = re.compile(HTML_PLACEHOLDER % r'([0-9]+)')
TAG_PLACEHOLDER = STX + "hzzhzkh:%s" + ETX
"""
Constants you probably do not need to change
-----------------------------------------------------------------------------
"""
RTL_BIDI_RANGES = (
('\u0590', '\u07FF'),
# Hebrew (0590-05FF), Arabic (0600-06FF),
# Syriac (0700-074F), Arabic supplement (0750-077F),
# Thaana (0780-07BF), Nko (07C0-07FF).
('\u2D30', '\u2D7F') # Tifinagh
)
# Extensions should use "markdown.util.etree" instead of "etree" (or do `from
# markdown.util import etree`). Do not import it by yourself.
try: # pragma: no cover
# Is the C implementation of ElementTree available?
import xml.etree.cElementTree as etree
from xml.etree.ElementTree import Comment
# Serializers (including ours) test with non-c Comment
etree.test_comment = Comment
if etree.VERSION < "1.0.5":
raise RuntimeError("cElementTree version 1.0.5 or higher is required.")
except (ImportError, RuntimeError): # pragma: no cover
# Use the Python implementation of ElementTree?
import xml.etree.ElementTree as etree
if etree.VERSION < "1.1":
raise RuntimeError("ElementTree version 1.1 or higher is required")
"""
AUXILIARY GLOBAL FUNCTIONS
=============================================================================
"""
def isBlockLevel(tag):
"""Check if the tag is a block level HTML tag."""
if isinstance(tag, string_type):
return BLOCK_LEVEL_ELEMENTS.match(tag)
# Some ElementTree tags are not strings, so return False.
return False
def parseBoolValue(value, fail_on_errors=True, preserve_none=False):
"""Parses a string representing bool value. If parsing was successful,
returns True or False. If preserve_none=True, returns True, False,
or None. If parsing was not successful, raises ValueError, or, if
fail_on_errors=False, returns None."""
if not isinstance(value, string_type):
if preserve_none and value is None:
return value
return bool(value)
elif preserve_none and value.lower() == 'none':
return None
elif value.lower() in ('true', 'yes', 'y', 'on', '1'):
return True
elif value.lower() in ('false', 'no', 'n', 'off', '0', 'none'):
return False
elif fail_on_errors:
raise ValueError('Cannot parse bool value: %r' % value)
"""
MISC AUXILIARY CLASSES
=============================================================================
"""
class AtomicString(text_type):
"""A string which should not be further processed."""
pass
class Processor(object):
def __init__(self, markdown_instance=None):
if markdown_instance:
self.markdown = markdown_instance
class HtmlStash(object):
"""
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 = []
self.tag_counter = 0
self.tag_data = [] # list of dictionaries in the order tags appear
def store(self, html):
"""
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
Returns : a placeholder string
"""
self.rawHtmlBlocks.append(html)
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 HTML_PLACEHOLDER % key
def store_tag(self, tag, attrs, left_index, right_index):
"""Store tag data and return a placeholder."""
self.tag_data.append({'tag': tag, 'attrs': attrs,
'left_index': left_index,
'right_index': right_index})
placeholder = TAG_PLACEHOLDER % str(self.tag_counter)
self.tag_counter += 1 # equal to the tag's index in self.tag_data
return placeholder