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
|
#!/usr/bin/env python3
"""
Output a combined news.adoc document
Also write an Atom feed document
"""
import os
import sys
import hashlib
import datetime
import time
OUTPUT_HEADER = """= News
"""
OUTPUT_FOOTER = """
link:https://savannah.nongnu.org/news/?group_id=10890[Old News Archive]
"""
ATOM_TEMPLATE = """<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
<title>crmsh</title>
<subtitle>Cluster manager shell news</subtitle>
<link href="/atom.xml" rel="self" />
<link href="/" />
<id>%(id)s</id>
<updated>%(updated)s</updated>
%(entries)s
</feed>
"""
ATOM_NAME = "gen/atom.xml"
root_id = "tag:crmsh.github.io,2014:/atom"
def escape(s):
s = s.replace('&', '&')
s = s.replace('<', '<')
s = s.replace('>', '>')
s = s.replace('"', """)
return s
class Entry(object):
def __init__(self, fname):
self.filename = fname
self.name = os.path.splitext(os.path.basename(fname))[0]
with open(fname) as f:
self.title = f.readline().strip()
f.readline()
l = f.readline()
while l.startswith(':'):
k, v = l[1:].split(':', 1)
k = k.lower()
v = v.strip()
setattr(self, k, v)
l = f.readline()
self.content = l + f.read()
if not hasattr(self, 'author'):
raise ValueError("Missing author")
if not hasattr(self, 'email'):
raise ValueError("Missing email")
if not hasattr(self, 'date'):
raise ValueError("Missing date")
def atom_id(self):
return root_id + '::' + hashlib.sha1(self.filename.encode('utf-8')).hexdigest()
def atom_date(self):
return self.date.replace(' ', 'T') + ':00' + time.tzname[0]
def date_obj(self):
from dateutil import parser
return (parser.parse(self.date))
def atom_content(self):
return escape('<pre>\n' + self.content + '\n</pre>\n')
def atom(self):
data = {'title': self.title,
'id': self.atom_id(),
'updated': self.atom_date(),
'name': self.name,
'content': self.atom_content(),
'author': self.author,
'email': self.email}
return """<entry>
<title>%(title)s</title>
<id>%(id)s</id>
<updated>%(updated)s</updated>
<link>http://crmsh.github.io/news/%(name)s</link>
<content type="html">
%(content)s
</content>
<author>
<name>%(author)s</name>
<email>%(email)s</email>
</author>
</entry>
""" % data
def sort_entries(entries):
return list(reversed(sorted(entries, key=lambda e: e.date_obj())))
def make_atom():
inputs = sort_entries([Entry(f) for f in sys.argv[2:]])
with open(ATOM_NAME, 'w') as output:
output.write(ATOM_TEMPLATE % {
'id': root_id,
'updated': inputs[0].atom_date(),
'entries': '\n'.join(f.atom() for f in inputs)
})
def main():
# TODO: sort by date
inputs = sort_entries([Entry(f) for f in sys.argv[2:]])
with open(sys.argv[1], 'w') as output:
output.write(OUTPUT_HEADER)
e = inputs[0]
output.write("link:/news/%s[%s]\n\n" % (e.name, e.date))
output.write(":leveloffset: 1\n\n")
output.write("include::%s[]\n\n" % (e.filename))
output.write(":leveloffset: 0\n\n")
output.write("''''\n")
for e in inputs[1:]:
output.write("* link:/news/%s[%s %s]\n" % (e.name, e.date, e.title))
output.write(OUTPUT_FOOTER)
if __name__ == "__main__":
if sys.argv[1] == ATOM_NAME:
make_atom()
else:
main()
|
