summaryrefslogtreecommitdiffstats
path: root/Tools/scripts/reindent.py
blob: 4a916ea149c5a8a930004ccd27bad6dfa220bc90 (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
#! /usr/bin/env python3

# Released to the public domain, by Tim Peters, 03 October 2000.

"""reindent [-d][-r][-v] [ path ... ]

-d (--dryrun)   Dry run.   Analyze, but don't make any changes to, files.
-r (--recurse)  Recurse.   Search for all .py files in subdirectories too.
-n (--nobackup) No backup. Does not make a ".bak" file before reindenting.
-v (--verbose)  Verbose.   Print informative msgs; else no output.
   (--newline)  Newline.   Specify the newline character to use (CRLF, LF).
                           Default is the same as the original file.
-h (--help)     Help.      Print this usage information and exit.

Change Python (.py) files to use 4-space indents and no hard tab characters.
Also trim excess spaces and tabs from ends of lines, and remove empty lines
at the end of files.  Also ensure the last line ends with a newline.

If no paths are given on the command line, reindent operates as a filter,
reading a single source file from standard input and writing the transformed
source to standard output.  In this case, the -d, -r and -v flags are
ignored.

You can pass one or more file and/or directory paths.  When a directory
path, all .py files within the directory will be examined, and, if the -r
option is given, likewise recursively for subdirectories.

If output is not to standard output, reindent overwrites files in place,
renaming the originals with a .bak extension.  If it finds nothing to
change, the file is left alone.  If reindent does change a file, the changed
file is a fixed-point for future runs (i.e., running reindent on the
resulting .py file won't change it again).

The hard part of reindenting is figuring out what to do with comment
lines.  So long as the input files get a clean bill of health from
tabnanny.py, reindent should do a good job.

The backup file is a copy of the one that is being reindented. The ".bak"
file is generated with shutil.copy(), but some corner cases regarding
user/group and permissions could leave the backup file more readable than
you'd prefer. You can always use the --nobackup option to prevent this.
"""

__version__ = "1"

import tokenize
import os
import shutil
import sys

verbose = False
recurse = False
dryrun = False
makebackup = True
spec_newline = None
"""A specified newline to be used in the output (set by --newline option)"""


def usage(msg=None):
    if msg is None:
        msg = __doc__
    print(msg, file=sys.stderr)


def errprint(*args):
    sys.stderr.write(" ".join(str(arg) for arg in args))
    sys.stderr.write("\n")

def main():
    import getopt
    global verbose, recurse, dryrun, makebackup, spec_newline
    try:
        opts, args = getopt.getopt(sys.argv[1:], "drnvh",
            ["dryrun", "recurse", "nobackup", "verbose", "newline=", "help"])
    except getopt.error as msg:
        usage(msg)
        return
    for o, a in opts:
        if o in ('-d', '--dryrun'):
            dryrun = True
        elif o in ('-r', '--recurse'):
            recurse = True
        elif o in ('-n', '--nobackup'):
            makebackup = False
        elif o in ('-v', '--verbose'):
            verbose = True
        elif o in ('--newline',):
            if not a.upper() in ('CRLF', 'LF'):
                usage()
                return
            spec_newline = dict(CRLF='\r\n', LF='\n')[a.upper()]
        elif o in ('-h', '--help'):
            usage()
            return
    if not args:
        r = Reindenter(sys.stdin)
        r.run()
        r.write(sys.stdout)
        return
    for arg in args:
        check(arg)


def check(file):
    if os.path.isdir(file) and not os.path.islink(file):
        if verbose:
            print("listing directory", file)
        names = os.listdir(file)
        for name in names:
            fullname = os.path.join(file, name)
            if ((recurse and os.path.isdir(fullname) and
                 not os.path.islink(fullname) and
                 not os.path.split(fullname)[1].startswith("."))
                or name.lower().endswith(".py")):
                check(fullname)
        return

    if verbose:
        print("checking", file, "...", end=' ')
    with open(file, 'rb') as f:
        encoding, _ = tokenize.detect_encoding(f.readline)
    try:
        with open(file, encoding=encoding) as f:
            r = Reindenter(f)
    except IOError as msg:
        errprint("%s: I/O Error: %s" % (file, str(msg)))
        return

    newline = spec_newline if spec_newline else r.newlines
    if isinstance(newline, tuple):
        errprint("%s: mixed newlines detected; cannot continue without --newline" % file)
        return

    if r.run():
        if verbose:
            print("changed.")
            if dryrun:
                print("But this is a dry run, so leaving it alone.")
        if not dryrun:
            bak = file + ".bak"
            if makebackup:
                shutil.copyfile(file, bak)
                if verbose:
                    print("backed up", file, "to", bak)
            with open(file, "w", encoding=encoding, newline=newline) as f:
                r.write(f)
            if verbose:
                print("wrote new", file)
        return True
    else:
        if verbose:
            print("unchanged.")
        return False


def _rstrip(line, JUNK='\n \t'):
    """Return line stripped of trailing spaces, tabs, newlines.

    Note that line.rstrip() instead also strips sundry control characters,
    but at least one known Emacs user expects to keep junk like that, not
    mentioning Barry by name or anything <wink>.
    """

    i = len(line)
    while i > 0 and line[i - 1] in JUNK:
        i -= 1
    return line[:i]


class Reindenter:

    def __init__(self, f):
        self.find_stmt = 1  # next token begins a fresh stmt?
        self.level = 0      # current indent level

        # Raw file lines.
        self.raw = f.readlines()

        # File lines, rstripped & tab-expanded.  Dummy at start is so
        # that we can use tokenize's 1-based line numbering easily.
        # Note that a line is all-blank iff it's "\n".
        self.lines = [_rstrip(line).expandtabs() + "\n"
                      for line in self.raw]
        self.lines.insert(0, None)
        self.index = 1  # index into self.lines of next line

        # List of (lineno, indentlevel) pairs, one for each stmt and
        # comment line.  indentlevel is -1 for comment lines, as a
        # signal that tokenize doesn't know what to do about them;
        # indeed, they're our headache!
        self.stats = []

        # Save the newlines found in the file so they can be used to
        #  create output without mutating the newlines.
        self.newlines = f.newlines

    def run(self):
        tokens = tokenize.generate_tokens(self.getline)
        for _token in tokens:
            self.tokeneater(*_token)
        # Remove trailing empty lines.
        lines = self.lines
        while lines and lines[-1] == "\n":
            lines.pop()
        # Sentinel.
        stats = self.stats
        stats.append((len(lines), 0))
        # Map count of leading spaces to # we want.
        have2want = {}
        # Program after transformation.
        after = self.after = []
        # Copy over initial empty lines -- there's nothing to do until
        # we see a line with *something* on it.
        i = stats[0][0]
        after.extend(lines[1:i])
        for i in range(len(stats) - 1):
            thisstmt, thislevel = stats[i]
            nextstmt = stats[i + 1][0]
            have = getlspace(lines[thisstmt])
            want = thislevel * 4
            if want < 0:
                # A comment line.
                if have:
                    # An indented comment line.  If we saw the same
                    # indentation before, reuse what it most recently
                    # mapped to.
                    want = have2want.get(have, -1)
                    if want < 0:
                        # Then it probably belongs to the next real stmt.
                        for j in range(i + 1, len(stats) - 1):
                            jline, jlevel = stats[j]
                            if jlevel >= 0:
                                if have == getlspace(lines[jline]):
                                    want = jlevel * 4
                                break
                    if want < 0:           # Maybe it's a hanging
                                           # comment like this one,
                        # in which case we should shift it like its base
                        # line got shifted.
                        for j in range(i - 1, -1, -1):
                            jline, jlevel = stats[j]
                            if jlevel >= 0:
                                want = have + (getlspace(after[jline - 1]) -
                                               getlspace(lines[jline]))
                                break
                    if want < 0:
                        # Still no luck -- leave it alone.
                        want = have
                else:
                    want = 0
            assert want >= 0
            have2want[have] = want
            diff = want - have
            if diff == 0 or have == 0:
                after.extend(lines[thisstmt:nextstmt])
            else:
                for line in lines[thisstmt:nextstmt]:
                    if diff > 0:
                        if line == "\n":
                            after.append(line)
                        else:
                            after.append(" " * diff + line)
                    else:
                        remove = min(getlspace(line), -diff)
                        after.append(line[remove:])
        return self.raw != self.after

    def write(self, f):
        f.writelines(self.after)

    # Line-getter for tokenize.
    def getline(self):
        if self.index >= len(self.lines):
            line = ""
        else:
            line = self.lines[self.index]
            self.index += 1
        return line

    # Line-eater for tokenize.
    def tokeneater(self, type, token, slinecol, end, line,
                   INDENT=tokenize.INDENT,
                   DEDENT=tokenize.DEDENT,
                   NEWLINE=tokenize.NEWLINE,
                   COMMENT=tokenize.COMMENT,
                   NL=tokenize.NL):

        if type == NEWLINE:
            # A program statement, or ENDMARKER, will eventually follow,
            # after some (possibly empty) run of tokens of the form
            #     (NL | COMMENT)* (INDENT | DEDENT+)?
            self.find_stmt = 1

        elif type == INDENT:
            self.find_stmt = 1
            self.level += 1

        elif type == DEDENT:
            self.find_stmt = 1
            self.level -= 1

        elif type == COMMENT:
            if self.find_stmt:
                self.stats.append((slinecol[0], -1))
                # but we're still looking for a new stmt, so leave
                # find_stmt alone

        elif type == NL:
            pass

        elif self.find_stmt:
            # This is the first "real token" following a NEWLINE, so it
            # must be the first token of the next program statement, or an
            # ENDMARKER.
            self.find_stmt = 0
            if line:   # not endmarker
                self.stats.append((slinecol[0], self.level))


# Count number of leading blanks.
def getlspace(line):
    i, n = 0, len(line)
    while i < n and line[i] == " ":
        i += 1
    return i


if __name__ == '__main__':
    main()