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
|
#! /usr/bin/env python
from __future__ import with_statement
from contextlib import closing
import re
import os.path as path
import sys
import textwrap
import encodings
def loadFile(path, encoding):
with closing( encodings.search_function(encoding).streamreader(open(path)) ) as fd:
return fd.read()
def writeFile(path, encoding, buffer):
with closing( encodings.search_function(encoding).streamwriter(open(path, "w")) ) as fd:
fd.write(buffer)
def splitSections(buffer):
while buffer:
assert len(buffer) >= 3
name = buffer.pop(0).lower()
assert buffer.pop(0) == ''
body = []
while buffer:
line = buffer.pop(0)
if line == '' or line[0].isspace():
body.append(line[2:])
else:
buffer.insert(0, line)
yield (name, body)
body = []
break
if body:
yield (name, body)
def collapseText(lines, width = 72):
wrapper = textwrap.TextWrapper( width = width
, expand_tabs = False
, break_on_hyphens = False
, break_long_words = False
)
body = []
prev = None
for line in lines:
if line == '':
prev = None
elif line[0].isspace():
if prev == "quote":
body[-1].append(line)
else:
body.append([line])
prev = "quote"
else:
if prev == "text":
newtext = ' '.join(body[-1]) + ' ' + line
body[-1] = wrapper.wrap(newtext)
else:
body.append(wrapper.wrap(line))
prev = "text"
return body
class Macro:
def __init__(self, filePath, encoding):
self.name = path.splitext(path.basename(filePath))[0]
# header and body are separated by an empty line.
(header,body) = loadFile(filePath, encoding).split("\n\n", 1)
self.body = body.split('\n')
# drop initial header (if present)
header = re.sub(r"^\n*# =+\n#[^\n]*\n# =+\n(#\n)+", '', header, 1)
# split buffer into lines and drop initial "# " prefix in the process
header = map(lambda l: l[2:], header.split('\n'))
# set defaults
self.authors = []
url = "http://www.nongnu.org/autoconf-archive/%s" % (self.name + ".html")
lineLen = max(75,len(url) + 2)
separator = '=' * lineLen
padding = ' ' * ((lineLen - len(url)) / 2)
self.m4header = "# %s\n"*3 % (separator, padding + url, separator)
# parse each section in the remaining list
for (key, body) in splitSections(header):
# drop empty lines at beginning and end of body
while body[0] == '': body.pop(0)
while body[-1] == '': body.pop(-1)
# each section has its own parser
if key == "synopsis":
if '' in body:
raise Exception("%s: malformed synopsis section" % filePath)
elif key == "description":
body = collapseText(body)
elif key == "license":
while True:
match = re.match(r"Copyright \(c\) ([0-9]+) (.*)", body[0])
if not match: break
(year,name) = (match.group(1), match.group(2))
match = re.match(r"(.*) <(.*)>", name)
if match:
(name,email) = (match.group(1), match.group(2))
self.authors.append(dict(year = year, name = name, email = email))
else:
self.authors.append(dict(year = year, name = name))
body.pop(0)
assert self.authors
if body.pop(0) != '':
raise Exception("%s: malformed license section" % filePath)
body = collapseText(body)
else:
raise Exception("%s: unknown section %r in macro" % (filePath, key))
self.__dict__[key] = body
def __repr__(self):
return repr(self.__dict__)
if __name__ == "__main__":
from stringtemplate3 import StringTemplateGroup, StringTemplate
from optparse import OptionParser
opts = OptionParser()
opts.add_option('', "--input-encoding", dest = "inEncode", default = "latin1")
opts.add_option('', "--output-encoding", dest = "outEncode", default = "latin1")
opts.add_option('', "--template-lexer", dest = "lexer", default = "angle-bracket")
opts.add_option('', "--output-dir", dest = "outDir", default = "stage")
opts.add_option('', "--output-suffix", dest = "suffix", default = ".m4")
(options, args) = opts.parse_args()
stFile = args.pop(0)
formatter = StringTemplateGroup(fileName = stFile, lexer = options.lexer)
for m4File in args:
(stem,suff) = path.splitext(path.basename(m4File))
assert suff == ".m4"
outFile = path.join(options.outDir, stem + options.suffix)
assert outFile != m4File
print m4File, "->", outFile
m = Macro(m4File, options.inEncode)
f = formatter.getInstanceOf("canon")
for (k,v) in m.__dict__.items():
f[k] = v
writeFile(outFile, options.outEncode, f.toString().strip() + '\n')
|
