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
184
185
186
187
188
189
190
191
192
193
194
195
|
#!/usr/bin/python
# Untested code from https://www.snip2code.com/Snippet/1704331/Convert-trac-markup-to-Markdown/
# This code mostly taken from patches to pagure_importer by mreynolds
import sys
import re
import time
import requests
import shutil
import os
from base64 import b64decode
from datetime import datetime
wikilink_pattern = re.compile('\[http(.*)\]')
wikilink_extract = re.compile('\[(.*)\]')
wikiheading1_pattern = re.compile('^= (.*) =$')
wikiheading2_pattern = re.compile('^== (.*) ==$')
wikiheading3_pattern = re.compile('^=== (.*) ===$')
strikethrough_pattern = re.compile('~~(.*)~~')
def to_timestamp(tm):
''' Convert to timestamp which can be jsonified '''
tm = tm.replace('+00:00', '')
date = datetime.strptime(tm, '%Y-%m-%dT%H:%M:%S')
ts = str(time.mktime(date.timetuple()))[:-2] # Strip the .0
return ts
def strip_wikilink(content):
''' Need to remove wiki link format from custom fields. They come in a
variety of forms that can be comma or whitespace separated. They can also
include link names which must also be removed.
[https://bugzilla.redhat.com/show_bug.cgi?id=772777]
[https://bugzilla.com/123456789], [http://bugzilla.com/7777777 7777777]
[https://bugzilla.com/6666666 6666666]
'''
links = []
if wikilink_pattern.search(content):
# Looks like we have a link in here
links = []
mylist = re.findall(r'\[([^]]*)\]', content)
for i in mylist:
links.append(i.split(' ', 1)[0])
return ', '.join(links)
else:
return content
def convert_headers(line):
''' Convert wikiformat headers
'''
level_count = 1
for header in [wikiheading1_pattern,
wikiheading2_pattern,
wikiheading3_pattern]:
try:
level = header.search(line).group(1)
if level:
line = "%s %s" % ('#' * level_count, level)
break # No need to check other heading levels
except:
# Try the next heading level
pass
level_count += 1
return line
def convert_wikilinks(line):
''' Convert wikiformat links
'''
if wikilink_pattern.search(line):
try:
result = wikilink_extract.search(line).group(1)
if result:
parts = result.split(' ', 1)
if len(parts) == 1:
mdlink = '[%s](%s)' % (parts[0], parts[0])
elif len(parts) == 2:
mdlink = '[%s](%s)' % (parts[1], parts[0])
line = line.replace('[' + result + ']', mdlink)
except:
# Not a link, not a problem
pass
return line
def convert_strike(line):
''' Convert wikiformat striked text
'''
striked_result = strikethrough_pattern.search(line)
if striked_result:
try:
striked_text = striked_result.group(1)
if striked_text:
orig_text = '~~%s~~' % striked_text
new_text = '<s>%s</s>' % striked_text
line = line.replace(orig_text, new_text)
except:
# Not striked
pass
return line
def WikiToMD(content):
''' Convert wiki/RST format to Markdown. Code blocks, bold/italics,
wiki links, lists, striked text, and headers. '''
code_block = False
in_list = False
nested_level = 0
prev_indent = 0
old_content = content.splitlines()
new_content = []
while old_content:
line = old_content.pop(0).replace("\r", "")
while "{{{" in line or "}}}" in line:
if "{{{" in line:
code_block = True
line = line.replace("{{{", "```")
if "}}}" in line:
code_block = False
line = line.replace("}}}", "```")
if not code_block:
#
# Convert bullet lists. The start and end of a list needs
# an empty line. wikiformat uses both '*' and '-' for its
# lists. However, markdown only supports '-'.
#
if line.startswith('* '):
if not in_list:
new_content.append("\n")
in_list = True
line = line[1:]
line = '-%s' % (line)
elif line.startswith('- '):
# No need to modify the line, just add the new line
if not in_list:
new_content.append("\n")
in_list = True
elif line.startswith(' '):
# Check for nested lists
nested_line = line.lstrip(' ')
if nested_line.startswith('* ') or \
nested_line.startswith('- '):
# Adjust the nested list level as needed
indent = len(line) - len(nested_line)
if indent > prev_indent:
nested_level += 1
elif indent < prev_indent:
nested_level -= 1
prev_indent = indent
# Set the proper indentation for markdown
line = ('%s-%s' % (' ' * nested_level,
nested_line[1:]))
else:
if in_list:
# Add the closing empty line
new_content.append("\n")
in_list = False
nested_level = 0
prev_indent = 0
# Convert headers
line = convert_headers(line)
# Convert wiki links
line = convert_wikilinks(line)
# Convert striked through text
line = convert_strike(line)
# Convert bold and italic text (do this last)
line = line.replace("'''", "**") # Convert bold text
line = line.replace("''", "*") # Convert italic text
new_content.append(line)
new_content.append("\n")
return "".join(new_content)
for f in sys.argv[1:]:
d = WikiToMD(open(f, "r").read())
newf = f.replace(".trac", ".md")
with open(newf, "w") as fp:
fp.write(d)
pass
pass
|
