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
179
180
181
182
183
|
"""
PRE-PROCESSORS
=============================================================================
Preprocessors work on source text before we start doing anything too
complicated.
"""
import re
import util
import odict
def build_preprocessors(md_instance, **kwargs):
""" Build the default set of preprocessors used by Markdown. """
preprocessors = odict.OrderedDict()
preprocessors["html_block"] = HtmlBlockPreprocessor(md_instance)
preprocessors["reference"] = ReferencePreprocessor(md_instance)
return preprocessors
class Preprocessor(util.Processor):
"""
Preprocessors are run after the text is broken into lines.
Each preprocessor implements a "run" method that takes a pointer to a
list of lines of the document, modifies it as necessary and returns
either the same pointer or a pointer to a new list.
Preprocessors must extend markdown.Preprocessor.
"""
def run(self, lines):
"""
Each subclass of Preprocessor should override the `run` method, which
takes the document as a list of strings split by newlines and returns
the (possibly modified) list of lines.
"""
pass
class HtmlBlockPreprocessor(Preprocessor):
"""Remove html blocks from the text and store them for later retrieval."""
right_tag_patterns = ["</%s>", "%s>"]
def _get_left_tag(self, block):
return block[1:].replace(">", " ", 1).split()[0].lower()
def _get_right_tag(self, left_tag, block):
for p in self.right_tag_patterns:
tag = p % left_tag
i = block.rfind(tag)
if i > 2:
return tag.lstrip("<").rstrip(">"), i + len(p)-2 + len(left_tag)
return block.rstrip()[-len(left_tag)-2:-1].lower(), len(block)
def _equal_tags(self, left_tag, right_tag):
if left_tag == 'div' or left_tag[0] in ['?', '@', '%']: # handle PHP, etc.
return True
if ("/" + left_tag) == right_tag:
return True
if (right_tag == "--" and left_tag == "--"):
return True
elif left_tag == right_tag[1:] \
and right_tag[0] != "<":
return True
else:
return False
def _is_oneliner(self, tag):
return (tag in ['hr', 'hr/'])
def run(self, lines):
text = "\n".join(lines)
new_blocks = []
text = text.split("\n\n")
items = []
left_tag = ''
right_tag = ''
in_tag = False # flag
while text:
block = text[0]
if block.startswith("\n"):
block = block[1:]
text = text[1:]
if block.startswith("\n"):
block = block[1:]
if not in_tag:
if block.startswith("<"):
left_tag = self._get_left_tag(block)
right_tag, data_index = self._get_right_tag(left_tag, block)
if block[1] == "!":
# is a comment block
left_tag = "--"
right_tag, data_index = self._get_right_tag(left_tag, block)
# keep checking conditions below and maybe just append
if data_index < len(block) \
and util.isBlockLevel(left_tag):
text.insert(0, block[data_index:])
block = block[:data_index]
if not (util.isBlockLevel(left_tag) \
or block[1] in ["!", "?", "@", "%"]):
new_blocks.append(block)
continue
if self._is_oneliner(left_tag):
new_blocks.append(block.strip())
continue
if block.rstrip().endswith(">") \
and self._equal_tags(left_tag, right_tag):
new_blocks.append(
self.markdown.htmlStash.store(block.strip()))
continue
else: #if not block[1] == "!":
# if is block level tag and is not complete
if util.isBlockLevel(left_tag) or left_tag == "--" \
and not block.rstrip().endswith(">"):
items.append(block.strip())
in_tag = True
else:
new_blocks.append(
self.markdown.htmlStash.store(block.strip()))
continue
new_blocks.append(block)
else:
items.append(block)
right_tag, data_index = self._get_right_tag(left_tag, block)
if self._equal_tags(left_tag, right_tag):
# if find closing tag
in_tag = False
new_blocks.append(
self.markdown.htmlStash.store('\n\n'.join(items)))
items = []
if items:
new_blocks.append(self.markdown.htmlStash.store('\n\n'.join(items)))
new_blocks.append('\n')
new_text = "\n\n".join(new_blocks)
return new_text.split("\n")
class ReferencePreprocessor(Preprocessor):
""" Remove reference definitions from text and store for later use. """
RE = re.compile(r'^(\ ?\ ?\ ?)\[([^\]]*)\]:\s*([^ ]*)(.*)$', re.DOTALL)
def run (self, lines):
new_text = [];
for line in lines:
m = self.RE.match(line)
if m:
id = m.group(2).strip().lower()
link = m.group(3).lstrip('<').rstrip('>')
t = m.group(4).strip() # potential title
if not t:
self.markdown.references[id] = (link, t)
elif (len(t) >= 2
and (t[0] == t[-1] == "\""
or t[0] == t[-1] == "\'"
or (t[0] == "(" and t[-1] == ")") ) ):
self.markdown.references[id] = (link, t[1:-1])
else:
new_text.append(line)
else:
new_text.append(line)
return new_text #+ "\n"
|
