summaryrefslogtreecommitdiffstats
path: root/Lib/tokenize.py
blob: e711a21f35cba493d87fa32f3a08e4932b54fa3f (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
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
"""Tokenization help for Python programs.

tokenize(readline) is a generator that breaks a stream of
bytes into Python tokens. It decodes the bytes according to
PEP-0263 for determining source file encoding.

It accepts a readline-like method which is called
repeatedly to get the next line of input (or b"" for EOF).  It generates
5-tuples with these members:

    the token type (see token.py)
    the token (a string)
    the starting (row, column) indices of the token (a 2-tuple of ints)
    the ending (row, column) indices of the token (a 2-tuple of ints)
    the original line (string)

It is designed to match the working of the Python tokenizer exactly, except
that it produces COMMENT tokens for comments and gives type OP for all
operators. Aditionally, all token lists start with an ENCODING token
which tells you which encoding was used to decode the bytes stream."""

__author__ = 'Ka-Ping Yee <ping@lfw.org>'
__credits__ = ('GvR, ESR, Tim Peters, Thomas Wouters, Fred Drake, '
               'Skip Montanaro, Raymond Hettinger, Trent Nelson, '
               'Michael Foord')
import re, string, sys
from token import *
from codecs import lookup, BOM_UTF8
cookie_re = re.compile("coding[:=]\s*([-\w.]+)")

import token
__all__ = [x for x in dir(token) if not x.startswith("_")]
__all__.extend(["COMMENT", "tokenize", "detect_encoding", "NL", "untokenize",
                "ENCODING", "TokenInfo"])
del token

COMMENT = N_TOKENS
tok_name[COMMENT] = 'COMMENT'
NL = N_TOKENS + 1
tok_name[NL] = 'NL'
ENCODING = N_TOKENS + 2
tok_name[ENCODING] = 'ENCODING'
N_TOKENS += 3

class TokenInfo(tuple):
    'TokenInfo(type, string, start, end, line)'

    __slots__ = ()

    _fields = ('type', 'string', 'start', 'end', 'line')

    def __new__(cls, type, string, start, end, line):
        return tuple.__new__(cls, (type, string, start, end, line))

    @classmethod
    def _make(cls, iterable, new=tuple.__new__, len=len):
        'Make a new TokenInfo object from a sequence or iterable'
        result = new(cls, iterable)
        if len(result) != 5:
            raise TypeError('Expected 5 arguments, got %d' % len(result))
        return result

    def __repr__(self):
        return 'TokenInfo(type=%r, string=%r, start=%r, end=%r, line=%r)' % self

    def _asdict(self):
        'Return a new dict which maps field names to their values'
        return dict(zip(self._fields, self))

    def _replace(self, **kwds):
        'Return a new TokenInfo object replacing specified fields with new values'
        result = self._make(map(kwds.pop, ('type', 'string', 'start', 'end', 'line'), self))
        if kwds:
            raise ValueError('Got unexpected field names: %r' % kwds.keys())
        return result

    def __getnewargs__(self):
        return tuple(self)

    type = property(lambda t: t[0])
    string = property(lambda t: t[1])
    start = property(lambda t: t[2])
    end = property(lambda t: t[3])
    line = property(lambda t: t[4])

def group(*choices): return '(' + '|'.join(choices) + ')'
def any(*choices): return group(*choices) + '*'
def maybe(*choices): return group(*choices) + '?'

# Note: we use unicode matching for names ("\w") but ascii matching for
# number literals.
Whitespace = r'[ \f\t]*'
Comment = r'#[^\r\n]*'
Ignore = Whitespace + any(r'\\\r?\n' + Whitespace) + maybe(Comment)
Name = r'\w+'

Hexnumber = r'0[xX][0-9a-fA-F]+'
Binnumber = r'0[bB][01]+'
Octnumber = r'0[oO][0-7]+'
Decnumber = r'(?:0+|[1-9][0-9]*)'
Intnumber = group(Hexnumber, Binnumber, Octnumber, Decnumber)
Exponent = r'[eE][-+]?[0-9]+'
Pointfloat = group(r'[0-9]+\.[0-9]*', r'\.[0-9]+') + maybe(Exponent)
Expfloat = r'[0-9]+' + Exponent
Floatnumber = group(Pointfloat, Expfloat)
Imagnumber = group(r'[0-9]+[jJ]', Floatnumber + r'[jJ]')
Number = group(Imagnumber, Floatnumber, Intnumber)

# Tail end of ' string.
Single = r"[^'\\]*(?:\\.[^'\\]*)*'"
# Tail end of " string.
Double = r'[^"\\]*(?:\\.[^"\\]*)*"'
# Tail end of ''' string.
Single3 = r"[^'\\]*(?:(?:\\.|'(?!''))[^'\\]*)*'''"
# Tail end of """ string.
Double3 = r'[^"\\]*(?:(?:\\.|"(?!""))[^"\\]*)*"""'
Triple = group("[bB]?[rR]?'''", '[bB]?[rR]?"""')
# Single-line ' or " string.
String = group(r"[bB]?[rR]?'[^\n'\\]*(?:\\.[^\n'\\]*)*'",
               r'[bB]?[rR]?"[^\n"\\]*(?:\\.[^\n"\\]*)*"')

# Because of leftmost-then-longest match semantics, be sure to put the
# longest operators first (e.g., if = came before ==, == would get
# recognized as two instances of =).
Operator = group(r"\*\*=?", r">>=?", r"<<=?", r"!=",
                 r"//=?", r"->",
                 r"[+\-*/%&|^=<>]=?",
                 r"~")

Bracket = '[][(){}]'
Special = group(r'\r?\n', r'\.\.\.', r'[:;.,@]')
Funny = group(Operator, Bracket, Special)

PlainToken = group(Number, Funny, String, Name)
Token = Ignore + PlainToken

# First (or only) line of ' or " string.
ContStr = group(r"[bB]?[rR]?'[^\n'\\]*(?:\\.[^\n'\\]*)*" +
                group("'", r'\\\r?\n'),
                r'[bB]?[rR]?"[^\n"\\]*(?:\\.[^\n"\\]*)*' +
                group('"', r'\\\r?\n'))
PseudoExtras = group(r'\\\r?\n', Comment, Triple)
PseudoToken = Whitespace + group(PseudoExtras, Number, Funny, ContStr, Name)

def _compile(expr):
    return re.compile(expr, re.UNICODE)

tokenprog, pseudoprog, single3prog, double3prog = map(
    _compile, (Token, PseudoToken, Single3, Double3))
endprogs = {"'": _compile(Single), '"': _compile(Double),
            "'''": single3prog, '"""': double3prog,
            "r'''": single3prog, 'r"""': double3prog,
            "b'''": single3prog, 'b"""': double3prog,
            "br'''": single3prog, 'br"""': double3prog,
            "R'''": single3prog, 'R"""': double3prog,
            "B'''": single3prog, 'B"""': double3prog,
            "bR'''": single3prog, 'bR"""': double3prog,
            "Br'''": single3prog, 'Br"""': double3prog,
            "BR'''": single3prog, 'BR"""': double3prog,
            'r': None, 'R': None, 'b': None, 'B': None}

triple_quoted = {}
for t in ("'''", '"""',
          "r'''", 'r"""', "R'''", 'R"""',
          "b'''", 'b"""', "B'''", 'B"""',
          "br'''", 'br"""', "Br'''", 'Br"""',
          "bR'''", 'bR"""', "BR'''", 'BR"""'):
    triple_quoted[t] = t
single_quoted = {}
for t in ("'", '"',
          "r'", 'r"', "R'", 'R"',
          "b'", 'b"', "B'", 'B"',
          "br'", 'br"', "Br'", 'Br"',
          "bR'", 'bR"', "BR'", 'BR"' ):
    single_quoted[t] = t

del _compile

tabsize = 8

class TokenError(Exception): pass

class StopTokenizing(Exception): pass


class Untokenizer:

    def __init__(self):
        self.tokens = []
        self.prev_row = 1
        self.prev_col = 0
        self.encoding = None

    def add_whitespace(self, start):
        row, col = start
        assert row <= self.prev_row
        col_offset = col - self.prev_col
        if col_offset:
            self.tokens.append(" " * col_offset)

    def untokenize(self, iterable):
        for t in iterable:
            if len(t) == 2:
                self.compat(t, iterable)
                break
            tok_type, token, start, end, line = t
            if tok_type == ENCODING:
                self.encoding = token
                continue
            self.add_whitespace(start)
            self.tokens.append(token)
            self.prev_row, self.prev_col = end
            if tok_type in (NEWLINE, NL):
                self.prev_row += 1
                self.prev_col = 0
        return "".join(self.tokens)

    def compat(self, token, iterable):
        startline = False
        indents = []
        toks_append = self.tokens.append
        toknum, tokval = token

        if toknum in (NAME, NUMBER):
            tokval += ' '
        if toknum in (NEWLINE, NL):
            startline = True
        prevstring = False
        for tok in iterable:
            toknum, tokval = tok[:2]
            if toknum == ENCODING:
                self.encoding = tokval
                continue

            if toknum in (NAME, NUMBER):
                tokval += ' '

            # Insert a space between two consecutive strings
            if toknum == STRING:
                if prevstring:
                    tokval = ' ' + tokval
                prevstring = True
            else:
                prevstring = False

            if toknum == INDENT:
                indents.append(tokval)
                continue
            elif toknum == DEDENT:
                indents.pop()
                continue
            elif toknum in (NEWLINE, NL):
                startline = True
            elif startline and indents:
                toks_append(indents[-1])
                startline = False
            toks_append(tokval)


def untokenize(iterable):
    """Transform tokens back into Python source code.
    It returns a bytes object, encoded using the ENCODING
    token, which is the first token sequence output by tokenize.

    Each element returned by the iterable must be a token sequence
    with at least two elements, a token number and token value.  If
    only two tokens are passed, the resulting output is poor.

    Round-trip invariant for full input:
        Untokenized source will match input source exactly

    Round-trip invariant for limited intput:
        # Output bytes will tokenize the back to the input
        t1 = [tok[:2] for tok in tokenize(f.readline)]
        newcode = untokenize(t1)
        readline = BytesIO(newcode).readline
        t2 = [tok[:2] for tok in tokenize(readline)]
        assert t1 == t2
    """
    ut = Untokenizer()
    out = ut.untokenize(iterable)
    if ut.encoding is not None:
        out = out.encode(ut.encoding)
    return out


def _get_normal_name(orig_enc):
    """Imitates get_normal_name in tokenizer.c."""
    # Only care about the first 12 characters.
    enc = orig_enc[:12].lower().replace("_", "-")
    if enc == "utf-8" or enc.startswith("utf-8-"):
        return "utf-8"
    if enc in ("latin-1", "iso-8859-1", "iso-latin-1") or \
       enc.startswith(("latin-1-", "iso-8859-1-", "iso-latin-1-")):
        return "iso-8859-1"
    return orig_enc

def detect_encoding(readline):
    """
    The detect_encoding() function is used to detect the encoding that should
    be used to decode a Python source file. It requires one argment, readline,
    in the same way as the tokenize() generator.

    It will call readline a maximum of twice, and return the encoding used
    (as a string) and a list of any lines (left as bytes) it has read
    in.

    It detects the encoding from the presence of a utf-8 bom or an encoding
    cookie as specified in pep-0263. If both a bom and a cookie are present,
    but disagree, a SyntaxError will be raised. If the encoding cookie is an
    invalid charset, raise a SyntaxError.

    If no encoding is specified, then the default of 'utf-8' will be returned.
    """
    bom_found = False
    encoding = None
    def read_or_stop():
        try:
            return readline()
        except StopIteration:
            return b''

    def find_cookie(line):
        try:
            line_string = line.decode('ascii')
        except UnicodeDecodeError:
            return None

        matches = cookie_re.findall(line_string)
        if not matches:
            return None
        encoding = _get_normal_name(matches[0])
        try:
            codec = lookup(encoding)
        except LookupError:
            # This behaviour mimics the Python interpreter
            raise SyntaxError("unknown encoding: " + encoding)

        if bom_found and codec.name != 'utf-8':
            # This behaviour mimics the Python interpreter
            raise SyntaxError('encoding problem: utf-8')
        return encoding

    first = read_or_stop()
    if first.startswith(BOM_UTF8):
        bom_found = True
        first = first[3:]
    if not first:
        return 'utf-8', []

    encoding = find_cookie(first)
    if encoding:
        return encoding, [first]

    second = read_or_stop()
    if not second:
        return 'utf-8', [first]

    encoding = find_cookie(second)
    if encoding:
        return encoding, [first, second]

    return 'utf-8', [first, second]


def tokenize(readline):
    """
    The tokenize() generator requires one argment, readline, which
    must be a callable object which provides the same interface as the
    readline() method of built-in file objects. Each call to the function
    should return one line of input as bytes.  Alternately, readline
    can be a callable function terminating with StopIteration:
        readline = open(myfile, 'rb').__next__  # Example of alternate readline

    The generator produces 5-tuples with these members: the token type; the
    token string; a 2-tuple (srow, scol) of ints specifying the row and
    column where the token begins in the source; a 2-tuple (erow, ecol) of
    ints specifying the row and column where the token ends in the source;
    and the line on which the token was found. The line passed is the
    logical line; continuation lines are included.

    The first token sequence will always be an ENCODING token
    which tells you which encoding was used to decode the bytes stream.
    """
    encoding, consumed = detect_encoding(readline)
    def readline_generator(consumed):
        for line in consumed:
            yield line
        while True:
            try:
                yield readline()
            except StopIteration:
                return
    chained = readline_generator(consumed)
    return _tokenize(chained.__next__, encoding)


def _tokenize(readline, encoding):
    lnum = parenlev = continued = 0
    numchars = '0123456789'
    contstr, needcont = '', 0
    contline = None
    indents = [0]

    if encoding is not None:
        yield TokenInfo(ENCODING, encoding, (0, 0), (0, 0), '')
    while True:             # loop over lines in stream
        try:
            line = readline()
        except StopIteration:
            line = b''

        if encoding is not None:
            line = line.decode(encoding)
        lnum += 1
        pos, max = 0, len(line)

        if contstr:                            # continued string
            if not line:
                raise TokenError("EOF in multi-line string", strstart)
            endmatch = endprog.match(line)
            if endmatch:
                pos = end = endmatch.end(0)
                yield TokenInfo(STRING, contstr + line[:end],
                       strstart, (lnum, end), contline + line)
                contstr, needcont = '', 0
                contline = None
            elif needcont and line[-2:] != '\\\n' and line[-3:] != '\\\r\n':
                yield TokenInfo(ERRORTOKEN, contstr + line,
                           strstart, (lnum, len(line)), contline)
                contstr = ''
                contline = None
                continue
            else:
                contstr = contstr + line
                contline = contline + line
                continue

        elif parenlev == 0 and not continued:  # new statement
            if not line: break
            column = 0
            while pos < max:                   # measure leading whitespace
                if line[pos] == ' ':
                    column += 1
                elif line[pos] == '\t':
                    column = (column//tabsize + 1)*tabsize
                elif line[pos] == '\f':
                    column = 0
                else:
                    break
                pos += 1
            if pos == max:
                break

            if line[pos] in '#\r\n':           # skip comments or blank lines
                if line[pos] == '#':
                    comment_token = line[pos:].rstrip('\r\n')
                    nl_pos = pos + len(comment_token)
                    yield TokenInfo(COMMENT, comment_token,
                           (lnum, pos), (lnum, pos + len(comment_token)), line)
                    yield TokenInfo(NL, line[nl_pos:],
                           (lnum, nl_pos), (lnum, len(line)), line)
                else:
                    yield TokenInfo((NL, COMMENT)[line[pos] == '#'], line[pos:],
                           (lnum, pos), (lnum, len(line)), line)
                continue

            if column > indents[-1]:           # count indents or dedents
                indents.append(column)
                yield TokenInfo(INDENT, line[:pos], (lnum, 0), (lnum, pos), line)
            while column < indents[-1]:
                if column not in indents:
                    raise IndentationError(
                        "unindent does not match any outer indentation level",
                        ("<tokenize>", lnum, pos, line))
                indents = indents[:-1]
                yield TokenInfo(DEDENT, '', (lnum, pos), (lnum, pos), line)

        else:                                  # continued statement
            if not line:
                raise TokenError("EOF in multi-line statement", (lnum, 0))
            continued = 0

        while pos < max:
            pseudomatch = pseudoprog.match(line, pos)
            if pseudomatch:                                # scan for tokens
                start, end = pseudomatch.span(1)
                spos, epos, pos = (lnum, start), (lnum, end), end
                token, initial = line[start:end], line[start]

                if (initial in numchars or                  # ordinary number
                    (initial == '.' and token != '.' and token != '...')):
                    yield TokenInfo(NUMBER, token, spos, epos, line)
                elif initial in '\r\n':
                    yield TokenInfo(NL if parenlev > 0 else NEWLINE,
                           token, spos, epos, line)
                elif initial == '#':
                    assert not token.endswith("\n")
                    yield TokenInfo(COMMENT, token, spos, epos, line)
                elif token in triple_quoted:
                    endprog = endprogs[token]
                    endmatch = endprog.match(line, pos)
                    if endmatch:                           # all on one line
                        pos = endmatch.end(0)
                        token = line[start:pos]
                        yield TokenInfo(STRING, token, spos, (lnum, pos), line)
                    else:
                        strstart = (lnum, start)           # multiple lines
                        contstr = line[start:]
                        contline = line
                        break
                elif initial in single_quoted or \
                    token[:2] in single_quoted or \
                    token[:3] in single_quoted:
                    if token[-1] == '\n':                  # continued string
                        strstart = (lnum, start)
                        endprog = (endprogs[initial] or endprogs[token[1]] or
                                   endprogs[token[2]])
                        contstr, needcont = line[start:], 1
                        contline = line
                        break
                    else:                                  # ordinary string
                        yield TokenInfo(STRING, token, spos, epos, line)
                elif initial.isidentifier():               # ordinary name
                    yield TokenInfo(NAME, token, spos, epos, line)
                elif initial == '\\':                      # continued stmt
                    continued = 1
                else:
                    if initial in '([{':
                        parenlev += 1
                    elif initial in ')]}':
                        parenlev -= 1
                    yield TokenInfo(OP, token, spos, epos, line)
            else:
                yield TokenInfo(ERRORTOKEN, line[pos],
                           (lnum, pos), (lnum, pos+1), line)
                pos += 1

    for indent in indents[1:]:                 # pop remaining indent levels
        yield TokenInfo(DEDENT, '', (lnum, 0), (lnum, 0), '')
    yield TokenInfo(ENDMARKER, '', (lnum, 0), (lnum, 0), '')


# An undocumented, backwards compatible, API for all the places in the standard
# library that expect to be able to use tokenize with strings
def generate_tokens(readline):
    return _tokenize(readline, None)