summaryrefslogtreecommitdiffstats
path: root/Tools/idle/tabnanny.py
blob: 9af8ecb847d454782c6e6aed76d1ea01eeab7dae (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
#! /usr/bin/env python

"""The Tab Nanny despises ambiguous indentation.  She knows no mercy."""

# Released to the public domain, by Tim Peters, 4 April 1998.

__version__ = "3"

import os
import sys
import getopt
import tokenize

verbose = 0

def main():
    global verbose
    try:
        opts, args = getopt.getopt(sys.argv[1:], "v")
    except getopt.error, msg:
        print msg
    for o, a in opts:
        if o == '-v':
            verbose = verbose + 1
    for arg in args:
        check(arg)

class NannyNag:
    def __init__(self, lineno, msg, line):
        self.lineno, self.msg, self.line = lineno, msg, line
    def get_lineno(self):
        return self.lineno
    def get_msg(self):
        return self.msg
    def get_line(self):
        return self.line

def check(file):
    if os.path.isdir(file) and not os.path.islink(file):
        if verbose:
            print "%s: listing directory" % `file`
        names = os.listdir(file)
        for name in names:
            fullname = os.path.join(file, name)
            if (os.path.isdir(fullname) and
                not os.path.islink(fullname) or
                os.path.normcase(name[-3:]) == ".py"):
                check(fullname)
        return

    try:
        f = open(file)
    except IOError, msg:
        print "%s: I/O Error: %s" % (`file`, str(msg))
        return

    if verbose > 1:
        print "checking", `file`, "..."

    reset_globals()
    try:
        tokenize.tokenize(f.readline, tokeneater)

    except tokenize.TokenError, msg:
        print "%s: Token Error: %s" % (`fname`, str(msg))
        return

    except NannyNag, nag:
        badline = nag.get_lineno()
        line = nag.get_line()
        if verbose:
            print "%s: *** Line %d: trouble in tab city! ***" % (
                `file`, badline)
            print "offending line:", `line`
            print nag.get_msg()
        else:
            print file, badline, `line`
        return

    if verbose:
        print "%s: Clean bill of health." % `file`

class Whitespace:
    # the characters used for space and tab
    S, T = ' \t'

    # members:
    #   raw
    #       the original string
    #   n
    #       the number of leading whitespace characters in raw
    #   nt
    #       the number of tabs in raw[:n]
    #   norm
    #       the normal form as a pair (count, trailing), where:
    #       count
    #           a tuple such that raw[:n] contains count[i]
    #           instances of S * i + T
    #       trailing
    #           the number of trailing spaces in raw[:n]
    #       It's A Theorem that m.indent_level(t) ==
    #       n.indent_level(t) for all t >= 1 iff m.norm == n.norm.
    #   is_simple
    #       true iff raw[:n] is of the form (T*)(S*)

    def __init__(self, ws):
        self.raw  = ws
        S, T = Whitespace.S, Whitespace.T
        count = []
        b = n = nt = 0
        for ch in self.raw:
            if ch == S:
                n = n + 1
                b = b + 1
            elif ch == T:
                n = n + 1
                nt = nt + 1
                if b >= len(count):
                    count = count + [0] * (b - len(count) + 1)
                count[b] = count[b] + 1
                b = 0
            else:
                break
        self.n    = n
        self.nt   = nt
        self.norm = tuple(count), b
        self.is_simple = len(count) <= 1

    # return length of longest contiguous run of spaces (whether or not
    # preceding a tab)
    def longest_run_of_spaces(self):
        count, trailing = self.norm
        return max(len(count)-1, trailing)

    def indent_level(self, tabsize):
        # count, il = self.norm
        # for i in range(len(count)):
        #    if count[i]:
        #        il = il + (i/tabsize + 1)*tabsize * count[i]
        # return il

        # quicker:
        # il = trailing + sum (i/ts + 1)*ts*count[i] =
        # trailing + ts * sum (i/ts + 1)*count[i] =
        # trailing + ts * sum i/ts*count[i] + count[i] =
        # trailing + ts * [(sum i/ts*count[i]) + (sum count[i])] =
        # trailing + ts * [(sum i/ts*count[i]) + num_tabs]
        # and note that i/ts*count[i] is 0 when i < ts

        count, trailing = self.norm
        il = 0
        for i in range(tabsize, len(count)):
            il = il + i/tabsize * count[i]
        return trailing + tabsize * (il + self.nt)

    # return true iff self.indent_level(t) == other.indent_level(t)
    # for all t >= 1
    def equal(self, other):
        return self.norm == other.norm

    # return a list of tuples (ts, i1, i2) such that
    # i1 == self.indent_level(ts) != other.indent_level(ts) == i2.
    # Intended to be used after not self.equal(other) is known, in which
    # case it will return at least one witnessing tab size.
    def not_equal_witness(self, other):
        n = max(self.longest_run_of_spaces(),
                other.longest_run_of_spaces()) + 1
        a = []
        for ts in range(1, n+1):
            if self.indent_level(ts) != other.indent_level(ts):
                a.append( (ts,
                           self.indent_level(ts),
                           other.indent_level(ts)) )
        return a

    # Return true iff self.indent_level(t) < other.indent_level(t)
    # for all t >= 1.
    # The algorithm is due to Vincent Broman.
    # Easy to prove it's correct.
    # XXXpost that.
    # Trivial to prove n is sharp (consider T vs ST).
    # Unknown whether there's a faster general way.  I suspected so at
    # first, but no longer.
    # For the special (but common!) case where M and N are both of the
    # form (T*)(S*), M.less(N) iff M.len() < N.len() and
    # M.num_tabs() <= N.num_tabs(). Proof is easy but kinda long-winded.
    # XXXwrite that up.
    # Note that M is of the form (T*)(S*) iff len(M.norm[0]) <= 1.
    def less(self, other):
        if self.n >= other.n:
            return 0
        if self.is_simple and other.is_simple:
            return self.nt <= other.nt
        n = max(self.longest_run_of_spaces(),
                other.longest_run_of_spaces()) + 1
        # the self.n >= other.n test already did it for ts=1
        for ts in range(2, n+1):
            if self.indent_level(ts) >= other.indent_level(ts):
                return 0
        return 1

    # return a list of tuples (ts, i1, i2) such that
    # i1 == self.indent_level(ts) >= other.indent_level(ts) == i2.
    # Intended to be used after not self.less(other) is known, in which
    # case it will return at least one witnessing tab size.
    def not_less_witness(self, other):
        n = max(self.longest_run_of_spaces(),
                other.longest_run_of_spaces()) + 1
        a = []
        for ts in range(1, n+1):
            if self.indent_level(ts) >= other.indent_level(ts):
                a.append( (ts,
                           self.indent_level(ts),
                           other.indent_level(ts)) )
        return a

def format_witnesses(w):
    import string
    firsts = map(lambda tup: str(tup[0]), w)
    prefix = "at tab size"
    if len(w) > 1:
        prefix = prefix + "s"
    return prefix + " " + string.join(firsts, ', ')

# The collection of globals, the reset_globals() function, and the
# tokeneater() function, depend on which version of tokenize is
# in use.

if hasattr(tokenize, 'NL'):
 # take advantage of Guido's patch!

 indents = []
 check_equal = 0

 def reset_globals():
     global indents, check_equal
     check_equal = 0
     indents = [Whitespace("")]

 def tokeneater(type, token, start, end, line,
                INDENT=tokenize.INDENT,
                DEDENT=tokenize.DEDENT,
                NEWLINE=tokenize.NEWLINE,
                COMMENT=tokenize.COMMENT,
                NL=tokenize.NL):
     global indents, check_equal

     # test in decreasing order of frequency, although the check_equal
     # test *must* be last; INDENT and DEDENT appear equally often

     if type in (COMMENT, NL):
         # the indentation of these guys is meaningless
         pass

     elif type == NEWLINE:
         # a program statement, or ENDMARKER, will eventually follow,
         # after some (possibly empty) run of tokens of the form
         #     (NL | COMMENT)* (INDENT | DEDENT+)?
         # If an INDENT appears, setting check_equal is wrong, and will
         # be undone when we see the INDENT.
         check_equal = 1

     elif type == INDENT:
         check_equal = 0
         thisguy = Whitespace(token)
         if not indents[-1].less(thisguy):
             witness = indents[-1].not_less_witness(thisguy)
             msg = "indent not greater e.g. " + format_witnesses(witness)
             raise NannyNag(start[0], msg, line)
         indents.append(thisguy)

     elif type == DEDENT:
         # there's nothing we need to check here!  what's important is
         # that when the run of DEDENTs ends, the indentation of the
         # program statement (or ENDMARKER) that triggered the run is
         # equal to what's left at the top of the indents stack
         assert check_equal  # else no earlier NEWLINE, or an earlier INDENT
         del indents[-1]

     elif check_equal:
         # this is the first "real token" following a NEWLINE, so it
         # must be the first token of the next program statement, or an
         # ENDMARKER; the "line" argument exposes the leading whitespace
         # for this statement; in the case of ENDMARKER, line is an empty
         # string, so will properly match the empty string with which the
         # "indents" stack was seeded
         check_equal = 0
         thisguy = Whitespace(line)
         if not indents[-1].equal(thisguy):
             witness = indents[-1].not_equal_witness(thisguy)
             msg = "indent not equal e.g. " + format_witnesses(witness)
             raise NannyNag(start[0], msg, line)

else:
 # unpatched version of tokenize

 nesting_level = 0
 indents = []
 check_equal = 0

 def reset_globals():
     global nesting_level, indents, check_equal
     nesting_level = check_equal = 0
     indents = [Whitespace("")]

 def tokeneater(type, token, start, end, line,
                INDENT=tokenize.INDENT,
                DEDENT=tokenize.DEDENT,
                NEWLINE=tokenize.NEWLINE,
                COMMENT=tokenize.COMMENT,
                OP=tokenize.OP):
     global nesting_level, indents, check_equal

     if type == INDENT:
         check_equal = 0
         thisguy = Whitespace(token)
         if not indents[-1].less(thisguy):
             witness = indents[-1].not_less_witness(thisguy)
             msg = "indent not greater e.g. " + format_witnesses(witness)
             raise NannyNag(start[0], msg, line)
         indents.append(thisguy)

     elif type == DEDENT:
         del indents[-1]

     elif type == NEWLINE:
         if nesting_level == 0:
             check_equal = 1

     elif type == COMMENT:
         pass

     elif check_equal:
         check_equal = 0
         thisguy = Whitespace(line)
         if not indents[-1].equal(thisguy):
             witness = indents[-1].not_equal_witness(thisguy)
             msg = "indent not equal e.g. " + format_witnesses(witness)
             raise NannyNag(start[0], msg, line)

     if type == OP and token in ('{', '[', '('):
         nesting_level = nesting_level + 1

     elif type == OP and token in ('}', ']', ')'):
         if nesting_level == 0:
             raise NannyNag(start[0],
                            "unbalanced bracket '" + token + "'",
                            line)
         nesting_level = nesting_level - 1

if __name__ == '__main__':
    main()