aboutsummaryrefslogtreecommitdiffstats
path: root/update_copyright.py
blob: 5ca54552042c23dd425331b92051312068522e86 (plain) (blame)
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
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
#!/usr/bin/python
#
# Copyright (C) 2009 W. Trevor King <wking@drexel.edu>
#
# 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 2 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.,
# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.

import os.path
import re
import sys
import time

import os
import sys
import select
from threading import Thread

from libbe.subproc import Pipe

COPYRIGHT_TEXT="""#
# 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 2 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.,
# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA."""

COPYRIGHT_TAG='-xyz-COPYRIGHT-zyx-' # unlikely to occur in the wild :p

ALIASES = [
    ['Ben Finney <benf@cybersource.com.au>',
     'Ben Finney <ben+python@benfinney.id.au>',
     'John Doe <jdoe@example.com>'],
    ['Chris Ball <cjb@laptop.org>',
     'Chris Ball <cjb@thunk.printf.net>'],
    ['Gianluca Montecchi <gian@grys.it>',
     'gian <gian@li82-39>',
     'gianluca <gian@galactica>'],
    ['W. Trevor King <wking@drexel.edu>',
     'wking <wking@mjolnir>'],
    [None,
     'j^ <j@oil21.org>'],
    ]
COPYRIGHT_ALIASES = [
    ['Aaron Bentley and Panometrics, Inc.',
     'Aaron Bentley <abentley@panoramicfeedback.com>'],
    ]
EXCLUDES = [
    ['Aaron Bentley and Panometrics, Inc.',
     'Aaron Bentley <aaron.bentley@utoronto.ca>',]
    ]


IGNORED_PATHS = ['./.be/', './.bzr/', './build/']
IGNORED_FILES = ['COPYING', 'update_copyright.py', 'catmutt']

def _strip_email(*args):
    """
    >>> _strip_email('J Doe <jdoe@a.com>')
    ['J Doe']
    >>> _strip_email('J Doe <jdoe@a.com>', 'JJJ Smith <jjjs@a.com>')
    ['J Doe', 'JJJ Smith']
    """
    args = list(args)
    for i,arg in enumerate(args):
        if arg == None:
            continue
        index = arg.find('<')
        if index > 0:
            args[i] = arg[:index].rstrip()
    return args

def _replace_aliases(authors, with_email=True, aliases=None,
                     excludes=None):
    """
    >>> aliases = [['J Doe and C, Inc.', 'J Doe <jdoe@c.com>'],
    ...            ['J Doe <jdoe@a.com>', 'Johnny <jdoe@b.edu>'],
    ...            ['JJJ Smith <jjjs@a.com>', 'Jingly <jjjs@b.edu>'],
    ...            [None, 'Anonymous <a@a.com>']]
    >>> excludes = [['J Doe and C, Inc.', 'J Doe <jdoe@a.com>']]
    >>> _replace_aliases(['JJJ Smith <jjjs@a.com>', 'Johnny <jdoe@b.edu>',
    ...                   'Jingly <jjjs@b.edu>', 'Anonymous <a@a.com>'],
    ...                  with_email=True, aliases=aliases, excludes=excludes)
    ['J Doe <jdoe@a.com>', 'JJJ Smith <jjjs@a.com>']
    >>> _replace_aliases(['JJJ Smith', 'Johnny', 'Jingly', 'Anonymous'],
    ...                  with_email=False, aliases=aliases, excludes=excludes)
    ['J Doe', 'JJJ Smith']
    >>> _replace_aliases(['JJJ Smith <jjjs@a.com>', 'Johnny <jdoe@b.edu>',
    ...                   'Jingly <jjjs@b.edu>', 'J Doe <jdoe@c.com>'],
    ...                  with_email=True, aliases=aliases, excludes=excludes)
    ['J Doe and C, Inc.', 'JJJ Smith <jjjs@a.com>']
    """
    if aliases == None:
        aliases = ALIASES
    if excludes == None:
        excludes = EXCLUDES
    if with_email == False:
        aliases = [_strip_email(*alias) for alias in aliases]
        exclude = [_strip_email(*exclude) for exclude in excludes]
    for i,author in enumerate(authors):
        for alias in aliases:
            if author in alias[1:]:
                authors[i] = alias[0]
                break
    for i,author in enumerate(authors):
        for exclude in excludes:
            if author in exclude[1:] and exclude[0] in authors:
                authors[i] = None
    authors = sorted(set(authors))
    if None in authors:
        authors.remove(None)
    return authors

def authors_list():
    p = Pipe([['bzr', 'log', '-n0'],
              ['grep', '^ *committer\|^ *author'],
              ['cut', '-d:', '-f2'],
              ['sed', 's/ <.*//;s/^ *//'],
              ['sort'],
              ['uniq']])
    assert p.status == 0, p.statuses
    authors = p.stdout.rstrip().split('\n')
    return _replace_aliases(authors, with_email=False)

def update_authors(verbose=True):
    print "updating AUTHORS"
    f = file('AUTHORS', 'w')
    authors_text = 'Bugs Everywhere was written by:\n%s\n' % '\n'.join(authors_list())
    f.write(authors_text)
    f.close()

def ignored_file(filename, ignored_paths=None, ignored_files=None):
    """
    >>> ignored_paths = ['./a/', './b/']
    >>> ignored_files = ['x', 'y']
    >>> ignored_file('./a/z', ignored_paths, ignored_files)
    True
    >>> ignored_file('./ab/z', ignored_paths, ignored_files)
    False
    >>> ignored_file('./ab/x', ignored_paths, ignored_files)
    True
    >>> ignored_file('./ab/xy', ignored_paths, ignored_files)
    False
    >>> ignored_file('./z', ignored_paths, ignored_files)
    False
    """
    if ignored_paths == None:
        ignored_paths = IGNORED_PATHS
    if ignored_files == None:
        ignored_files = IGNORED_FILES
    for path in ignored_paths:
        if filename.startswith(path):
            return True
    if os.path.basename(filename) in ignored_files:
        return True
    if os.path.abspath(filename) != os.path.realpath(filename):
        return True # symink somewhere in path...
    return False

def _copyright_string(orig_year, final_year, authors):
    """
    >>> print _copyright_string(orig_year=2005,
    ...                         final_year=2005,
    ...                         authors=['A <a@a.com>', 'B <b@b.edu>']
    ...                        ) # doctest: +ELLIPSIS
    # Copyright (C) 2005 A <a@a.com>
    #                    B <b@b.edu>
    #
    # This program...
    >>> print _copyright_string(orig_year=2005,
    ...                         final_year=2009,
    ...                         authors=['A <a@a.com>', 'B <b@b.edu>']
    ...                        ) # doctest: +ELLIPSIS
    # Copyright (C) 2005-2009 A <a@a.com>
    #                         B <b@b.edu>
    #
    # This program...
    """
    if orig_year == final_year:
        date_range = '%s' % orig_year
    else:
        date_range = '%s-%s' % (orig_year, final_year)
    lines = ['# Copyright (C) %s %s' % (date_range, authors[0])]
    for author in authors[1:]:
        lines.append('#' +
                     ' '*(len(' Copyright (C) ')+len(date_range)+1) +
                     author)
    return '%s\n%s' % ('\n'.join(lines), COPYRIGHT_TEXT)

def _tag_copyright(contents):
    """
    >>> contents = '''Some file
    ... bla bla
    ... # Copyright (copyright begins)
    ... # (copyright continues)
    ... # bla bla bla
    ... (copyright ends)
    ... bla bla bla
    ... '''
    >>> print _tag_copyright(contents),
    Some file
    bla bla
    -xyz-COPYRIGHT-zyx-
    (copyright ends)
    bla bla bla
    """
    lines = []
    incopy = False
    for line in contents.splitlines():
        if incopy == False and line.startswith('# Copyright'):
            incopy = True
            lines.append(COPYRIGHT_TAG)
        elif incopy == True and not line.startswith('#'):
            incopy = False
        if incopy == False:
            lines.append(line.rstrip('\n'))
    return '\n'.join(lines)+'\n'

def _update_copyright(contents, orig_year, authors):
    current_year = time.gmtime()[0]
    copyright_string = _copyright_string(orig_year, current_year, authors)
    contents = _tag_copyright(contents)
    return contents.replace(COPYRIGHT_TAG, copyright_string)

def update_file(filename, verbose=True):
    if verbose == True:
        print "updating", filename
    contents = file(filename, 'r').read()

    p = Pipe([['bzr', 'log', '-n0', filename],
              ['grep', '^ *timestamp: '],
              ['tail', '-n1'],
              ['sed', 's/^ *//;'],
              ['cut', '-b', '16-19']])
    if p.status != 0:
        assert p.statuses[0] == 3, p.statuses
        return # bzr doesn't version that file
    assert p.status == 0, p.statuses
    orig_year = int(p.stdout.strip())

    p = Pipe([['bzr', 'log', '-n0', filename],
              ['grep', '^ *author: \|^ *committer: '],
              ['cut', '-d:', '-f2'],
              ['sed', 's/^ *//;s/ *$//'],
              ['sort'],
              ['uniq']])
    assert p.status == 0, p.statuses
    authors = p.stdout.rstrip().split('\n')
    authors = _replace_aliases(authors, with_email=True,
                               aliases=ALIASES+COPYRIGHT_ALIASES)

    contents = _update_copyright(contents, orig_year, authors)
    f = file(filename, 'w')
    f.write(contents)
    f.close()

def update_files(files=None):
    if files == None or len(files) == 0:
        p = Pipe([['grep', '-rc', '# Copyright', '.'],
                  ['grep', '-v', ':0$'],
                  ['cut', '-d:', '-f1']])
        assert p.status == 0
        files = p.stdout.rstrip().split('\n')

    for filename in files:
        if ignored_file(filename) == True:
            continue
        update_file(filename)

def test():
    import doctest
    doctest.testmod() 

if __name__ == '__main__':
    import optparse
    usage = """%prog [options] [file ...]

Update copyright information in source code with information from
the bzr repository.  Run from the BE repository root.

Replaces every line starting with '^# Copyright' and continuing with
'^#' with an auto-generated copyright blurb.  If you want to add
#-commented material after a copyright blurb, please insert a blank
line between the blurb and your comment (as in this file), so the
next run of update_copyright.py doesn't clobber your comment.

If no files are given, a list of files to update is generated
automatically.
"""
    p = optparse.OptionParser(usage)
    p.add_option('--test', dest='test', default=False,
                 action='store_true', help='Run internal tests and exit')
    options,args = p.parse_args()

    if options.test == True:
        test()
        sys.exit(0)

    update_authors()
    update_files(files=args)