summaryrefslogtreecommitdiff
path: root/util/style.py
blob: 3d733638838b266a441bf76a5f4496b31fe8b52b (plain)
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
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
#! /usr/bin/env python
# Copyright (c) 2007 The Regents of The University of Michigan
# All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are
# met: redistributions of source code must retain the above copyright
# notice, this list of conditions and the following disclaimer;
# redistributions in binary form must reproduce the above copyright
# notice, this list of conditions and the following disclaimer in the
# documentation and/or other materials provided with the distribution;
# neither the name of the copyright holders nor the names of its
# contributors may be used to endorse or promote products derived from
# this software without specific prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
#
# Authors: Nathan Binkert

import re
import os
import sys

lead = re.compile(r'^([ \t]+)')
trail = re.compile(r'([ \t]+)$')
any_control = re.compile(r'\b(if|while|for)[ \t]*[(]')
good_control = re.compile(r'\b(if|while|for) [(]')

lang_types = { 'c'   : "C",
               'h'   : "C",
               'cc'  : "C++",
               'hh'  : "C++",
               'cxx' : "C++",
               'hxx' : "C++",
               'cpp' : "C++",
               'hpp' : "C++",
               'C'   : "C++",
               'H'   : "C++",
               'i'   : "swig",
               'py'  : "python",
               's'   : "asm",
               'S'   : "asm",
               'isa' : "isa" }
def file_type(filename):
    extension = filename.split('.')
    extension = len(extension) > 1 and extension[-1]
    return lang_types.get(extension, None)

whitespace_types = ('C', 'C++', 'swig', 'python', 'asm', 'isa')
def whitespace_file(filename):
    if file_type(filename) in whitespace_types:
        return True

    if filename.startswith("SCons"):
        return True

    return False

format_types = ( 'C', 'C++' )
def format_file(filename):
    if file_type(filename) in format_types:
        return True

    return False

def checkwhite_line(line):
    match = lead.search(line)
    if match and match.group(1).find('\t') != -1:
        return False

    match = trail.search(line)
    if match:
        return False

    return True

def checkwhite(filename):
    if not whitespace_file(filename):
        return

    try:
        f = file(filename, 'r+')
    except OSError, msg:
        print 'could not open file %s: %s' % (filename, msg)
        return

    for num,line in enumerate(f):
        if not checkwhite_line(line):
            yield line,num + 1

def fixwhite_line(line, tabsize):
    if lead.search(line):
        newline = ''
        for i,c in enumerate(line):
            if c == ' ':
                newline += ' '
            elif c == '\t':
                newline += ' ' * (tabsize - len(newline) % tabsize)
            else:
                newline += line[i:]
                break

        line = newline

    return line.rstrip() + '\n'

def fixwhite(filename, tabsize, fixonly=None):
    if not whitespace_file(filename):
        return

    try:
        f = file(filename, 'r+')
    except OSError, msg:
        print 'could not open file %s: %s' % (filename, msg)
        return

    lines = list(f)

    f.seek(0)
    f.truncate()

    for i,line in enumerate(lines):
        if fixonly is None or i in fixonly:
            line = fixwhite_line(line, tabsize)

        print >>f, line,

def linelen(line):
    tabs = line.count('\t')
    if not tabs:
        return len(line)

    count = 0
    for c in line:
        if c == '\t':
            count += tabsize - count % tabsize
        else:
            count += 1

    return count

class ValidationStats(object):
    def __init__(self):
        self.toolong = 0
        self.toolong80 = 0
        self.leadtabs = 0
        self.trailwhite = 0
        self.badcontrol = 0
        self.cret = 0

    def dump(self):
        print '''\
%d violations of lines over 79 chars. %d of which are 80 chars exactly.
%d cases of whitespace at the end of a line.
%d cases of tabs to indent.
%d bad parens after if/while/for.
%d carriage returns found.
''' % (self.toolong, self.toolong80, self.trailwhite, self.leadtabs,
       self.badcontrol, self.cret)

    def __nonzero__(self):
        return self.toolong or self.toolong80 or self.leadtabs or \
               self.trailwhite or self.badcontrol or self.cret

def validate(filename, stats, verbose, exit_code):
    if not format_file(filename):
        return

    def msg(lineno, line, message):
        print '%s:%d>' % (filename, lineno + 1), message
        if verbose > 2:
            print line

    def bad():
        if exit_code is not None:
            sys.exit(exit_code)

    cpp = filename.endswith('.cc') or filename.endswith('.hh')
    py = filename.endswith('.py')

    if py + cpp != 1:
        raise AttributeError, \
              "I don't know how to deal with the file %s" % filename

    try:
        f = file(filename, 'r')
    except OSError:
        if verbose > 0:
            print 'could not open file %s' % filename
        bad()
        return

    for i,line in enumerate(f):
        line = line.rstrip('\n')

        # no carriage returns
        if line.find('\r') != -1:
            self.cret += 1
            if verbose > 1:
                msg(i, line, 'carriage return found')
            bad()

        # lines max out at 79 chars
        llen = linelen(line)
        if llen > 79:
            stats.toolong += 1
            if llen == 80:
                stats.toolong80 += 1
            if verbose > 1:
                msg(i, line, 'line too long (%d chars)' % llen)
            bad()

        # no tabs used to indent
        match = lead.search(line)
        if match and match.group(1).find('\t') != -1:
            stats.leadtabs += 1
            if verbose > 1:
                msg(i, line, 'using tabs to indent')
            bad()

        # no trailing whitespace
        if trail.search(line):
            stats.trailwhite +=1
            if verbose > 1:
                msg(i, line, 'trailing whitespace')
            bad()

        # for c++, exactly one space betwen if/while/for and (
        if cpp:
            match = any_control.search(line)
            if match and not good_control.search(line):
                stats.badcontrol += 1
                if verbose > 1:
                    msg(i, line, 'improper spacing after %s' % match.group(1))
                bad()

def modified_lines(old_data, new_data, max_lines):
    from itertools import count
    from mercurial import bdiff, mdiff

    modified = set()
    counter = count()
    for pbeg, pend, fbeg, fend in bdiff.blocks(old_data, new_data):
        for i in counter:
            if i < fbeg:
                modified.add(i)
            elif i + 1 >= fend:
                break
            elif i > max_lines:
                break
    return modified

def check_whitespace(ui, repo, hooktype, node, parent1, parent2):
    from mercurial import mdiff

    if hooktype != 'pretxncommit':
        raise AttributeError, \
              "This hook is only meant for pretxncommit, not %s" % hooktype

    tabsize = 8
    verbose = ui.configbool('style', 'verbose', False)
    def prompt(name, fixonly=None):
        result = ui.prompt("(a)bort, (i)gnore, or (f)ix?", "^[aif]$", "a")
        if result == 'a':
            return True
        elif result == 'i':
            pass
        elif result == 'f':
            fixwhite(repo.wjoin(name), tabsize, fixonly)
        else:
            raise RepoError, "Invalid response: '%s'" % result

        return False

    modified, added, removed, deleted, unknown, ignore, clean = repo.status()

    for fname in added:
        ok = True
        for line,num in checkwhite(fname):
            ui.write("invalid whitespace in %s:%d\n" % (fname, num))
            if verbose:
                ui.write(">>%s<<\n" % line[-1])
            ok = False

        if not ok:
            if prompt(fname):
                return True

    wctx = repo.workingctx()
    for fname in modified:
        fctx = wctx.filectx(fname)
        pctx = fctx.parents()
        assert len(pctx) in (1, 2)

        file_data = fctx.data()
        lines = mdiff.splitnewlines(file_data)
        mod_lines = modified_lines(pctx[0].data(), file_data, len(lines))
        if len(pctx) == 2:
            m2 = modified_lines(pctx[1].data(), file_data, len(lines))
            mod_lines = mod_lines & m2 # only the lines that are new in both

        fixonly = set()
        for i,line in enumerate(lines):
            if i not in mod_lines:
                continue

            if checkwhite_line(line):
                continue

            ui.write("invalid whitespace: %s:%d\n" % (fname, i+1))
            if verbose:
                ui.write(">>%s<<\n" % line[:-1])
            fixonly.add(i)

        if fixonly:
            if prompt(fname, fixonly):
                return True

def check_format(ui, repo, hooktype, node, parent1, parent2):
    if hooktype != 'pretxncommit':
        raise AttributeError, \
              "This hook is only meant for pretxncommit, not %s" % hooktype

    modified, added, removed, deleted, unknown, ignore, clean = repo.status()

    verbose = 0
    stats = ValidationStats()
    for f in modified + added:
        validate(f, stats, verbose, None)

    if stats:
        stats.dump()
        result = ui.prompt("invalid formatting\n(i)gnore or (a)bort?",
                           "^[ia]$", "a")
        if result.startswith('i'):
            pass
        elif result.startswith('a'):
            return True
        else:
            raise RepoError, "Invalid response: '%s'" % result

    return False

if __name__ == '__main__':
    import getopt

    progname = sys.argv[0]
    if len(sys.argv) < 2:
        sys.exit('usage: %s <command> [<command args>]' % progname)

    fixwhite_usage = '%s fixwhite [-t <tabsize> ] <path> [...] \n' % progname
    chkformat_usage = '%s chkformat <path> [...] \n' % progname
    chkwhite_usage = '%s chkwhite <path> [...] \n' % progname

    command = sys.argv[1]
    if command == 'fixwhite':
        flags = 't:'
        usage = fixwhite_usage
    elif command == 'chkwhite':
        flags = 'nv'
        usage = chkwhite_usage
    elif command == 'chkformat':
        flags = 'nv'
        usage = chkformat_usage
    else:
        sys.exit(fixwhite_usage + chkwhite_usage + chkformat_usage)

    opts, args = getopt.getopt(sys.argv[2:], flags)

    code = 1
    verbose = 1
    tabsize = 8
    for opt,arg in opts:
        if opt == '-n':
            code = None
        if opt == '-t':
            tabsize = int(arg)
        if opt == '-v':
            verbose += 1

    if command == 'fixwhite':
        for filename in args:
            fixwhite(filename, tabsize)
    elif command == 'chkwhite':
        for filename in args:
            for line,num in checkwhite(filename):
                print 'invalid whitespace: %s:%d' % (filename, num)
                if verbose:
                    print '>>%s<<' % line[:-1]
    elif command == 'chkformat':
        stats = ValidationStats()
        for filename in files:
            validate(filename, stats=stats, verbose=verbose, exit_code=code)

        if verbose > 0:
            stats.dump()
    else:
        sys.exit("command '%s' not found" % command)