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
|
#!/usr/bin/python3
# Script to download the Ada Reference Manual and its formatting tool.
# Copyright (c) 2010, 2012 Stephen Leake <stephen_leake@stephe-leake.org>
# Copyright (c) 2013 Nicolas Boulenguez <nicolas@debian.org>
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 3 of the License, or
# (at your option) any later version.
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
import os.path
import re
import urllib.request
import sys
USE_EXISTING_FILES = True
######################################################################
class CVSWeb ():
def __init__ (self, hostname, top_directory):
# Instantiation requires distant root.
self._host = 'http://' + hostname
self._cgi = '/cgi-bin/cvsweb.cgi/' + top_directory + '/'
def files_in_directory (self, path):
# List text files in the head revision of a directory.
# I did not find a way to list a tagged revision, except a
# direct tag list for each file.
cgi = self._cgi + str.lower (path) + '/'
with urllib.request.urlopen (self._host + cgi) as f:
contents = f.read ()
# Refuse directory names (with a trailing slash).
# Ignore case of the displayed file name.
pattern = '<a href="' + re.escape (cgi) + '([^"/]+)">(\\1)</a><br>'
matches = re.finditer (str.encode (pattern), contents, re.IGNORECASE)
return (bytes.decode (m.group (2)) for m in matches)
def download_file (self, path,
tag = None): # None means the head revision.
# Return the contents of the tagged revision of path, as bytes.
# If tag is provided, but no revision of this file carries it,
# None is returned.
cgi = self._cgi + str.lower (path)
if tag != None:
with urllib.request.urlopen (self._host + cgi) as f:
contents = f.read ()
pattern = '<a href="' + re.escape (cgi) \
+ '\?rev=([0-9.]+)">\\1</a></b></span><br>\r\n' \
+ 'Modified <i>[^<]*</i>\r\n' \
+ 'by <i>[^<]*</i>( with line changes <i>[^<]*</i>)?<br>\r\n' \
+ 'CVS Tags: <b>[^<]*' + re.escape (tag) + '[^<]*</b><br>'
match = re.search (str.encode (pattern), contents)
if not match:
return None
rev = bytes.decode (match.group (1))
cgi += '?rev=' + rev
print ('{:<30} : {}'.format (path, rev))
else:
cgi += '?rev=HEAD'
with urllib.request.urlopen (self._host + cgi) as f:
contents = f.read ()
return contents
######################################################################
def download_subdir (cvsweb, subdir,
tag = None, # None means the head revision.
rename_lowercase = False,
strip_carriage_returns = False):
def fmt (a, b):
print ('{:<30} : {}'.format (a, b))
fmt ('Subdirectory', subdir)
if tag:
fmt ('Revision', tag)
else:
fmt ('Revision', 'latest')
fmt ('Renaming files to lowercase', rename_lowercase)
fmt ('Stripping carriage returns', strip_carriage_returns)
try:
os.mkdir (subdir) # Fails if the directory exists.
except FileExistsError:
if not USE_EXISTING_FILES:
raise
failed_count = 0
no_such_tag_count = 0
for basename in cvsweb.files_in_directory (subdir):
src = subdir + '/' + basename
if rename_lowercase:
basename = str.lower (basename)
dst = os.path.join (subdir, basename) # Local path join.
if USE_EXISTING_FILES and os.path.exists (dst):
fmt (dst, 'using existing file')
continue
try:
contents = cvsweb.download_file (src, tag)
if not contents:
fmt (dst, 'no such tag')
no_such_tag_count = no_such_tag_count + 1
continue
if strip_carriage_returns:
contents = re.sub (b'\r\n', b'\n', contents)
with open (dst, 'bw') as o:
o.write (contents)
fmt (dst, 'downloaded')
except urllib.error.URLError:
fmt (dst, 'download failed')
failed_count = failed_count + 1
fmt ('no such tag :', no_such_tag_count)
fmt ('failed downloads:', failed_count)
######################################################################
cvsweb = CVSWeb (hostname = 'www.ada-auth.org',
top_directory = 'arm')
tags = { '1995':'Final_TC1',
'2005':'Amend_Final',
'2012':'Ada2012_TC1',
'2020':'Ada202x_D25' }
if len (sys.argv) == 2 and sys.argv [1] == 'progs':
download_subdir (cvsweb, 'progs',
rename_lowercase = True)
print ("""
No certification or signature used for downloaded code sources.
Hint: diff -rN --ignore-file-name-case --strip-trailing-cr old/ progs/
""")
elif len (sys.argv) == 2 and sys.argv [1] in tags:
download_subdir (cvsweb, 'source',
tag = tags [sys.argv [1]],
rename_lowercase = True,
strip_carriage_returns = True)
elif len (sys.argv) == 2 and sys.argv [1] == 'HEAD':
download_subdir (cvsweb, 'source',
tag = 'HEAD',
rename_lowercase = True,
strip_carriage_returns = True)
else:
print ('Usage: {} [progs | {}]'.format (
sys.argv [0],
str.join (' | ', sorted ([str (year) for year in tags.keys ()]))))
|
