summaryrefslogtreecommitdiffstats
path: root/Lib/tokenize.py
blob: 2af595daea44425dc0a46b9717d836d8ebfd9197 (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
"""Tokenization help for Python programs.

This module exports a function called 'tokenize()' that breaks a stream of
text into Python tokens.  It accepts a readline-like method which is called
repeatedly to get the next line of input (or "" for EOF) and a "token-eater"
function which is called once for each token found.  The latter function is
passed the token type, a string containing the token, the starting and
ending (row, column) coordinates of the token, and the original line.  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."""

__author__ = 'Ka-Ping Yee <ping@lfw.org>'
__credits__ = \
    'GvR, ESR, Tim Peters, Thomas Wouters, Fred Drake, Skip Montanaro'

import string, re
from token import *

import token
__all__ = [x for x in dir(token) if x[0] != '_'] + ["COMMENT", "tokenize", "NL"]
del token

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

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

Whitespace = r'[ \f\t]*'
Comment = r'#[^\r\n]*'
Ignore = Whitespace + any(r'\\\r?\n' + Whitespace) + maybe(Comment)
Name = r'[a-zA-Z_]\w*'

Hexnumber = r'0[xX][\da-fA-F]*[lL]?'
Octnumber = r'0[0-7]*[lL]?'
Decnumber = r'[1-9]\d*[lL]?'
Intnumber = group(Hexnumber, Octnumber, Decnumber)
Exponent = r'[eE][-+]?\d+'
Pointfloat = group(r'\d+\.\d*', r'\.\d+') + maybe(Exponent)
Expfloat = r'[1-9]\d*' + Exponent
Floatnumber = group(Pointfloat, Expfloat)
Imagnumber = group(r'0[jJ]', r'[1-9]\d*[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("[uU]?[rR]?'''", '[uU]?[rR]?"""')
# Single-line ' or " string.
String = group(r"[uU]?[rR]?'[^\n'\\]*(?:\\.[^\n'\\]*)*'",
               r'[uU]?[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"~")

Bracket = '[][(){}]'
Special = group(r'\r?\n', 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"[uU]?[rR]?'[^\n'\\]*(?:\\.[^\n'\\]*)*" +
                group("'", r'\\\r?\n'),
                r'[uU]?[rR]?"[^\n"\\]*(?:\\.[^\n"\\]*)*' +
                group('"', r'\\\r?\n'))
PseudoExtras = group(r'\\\r?\n', Comment, Triple)
PseudoToken = Whitespace + group(PseudoExtras, Number, Funny, ContStr, Name)

tokenprog, pseudoprog, single3prog, double3prog = map(
    re.compile, (Token, PseudoToken, Single3, Double3))
endprogs = {"'": re.compile(Single), '"': re.compile(Double),
            "'''": single3prog, '"""': double3prog,
            "r'''": single3prog, 'r"""': double3prog,
            "u'''": single3prog, 'u"""': double3prog,
            "ur'''": single3prog, 'ur"""': double3prog,
            "R'''": single3prog, 'R"""': double3prog,
            "U'''": single3prog, 'U"""': double3prog,
            "uR'''": single3prog, 'uR"""': double3prog,
            "Ur'''": single3prog, 'Ur"""': double3prog,
            "UR'''": single3prog, 'UR"""': double3prog,
            'r': None, 'R': None, 'u': None, 'U': None}

tabsize = 8

class TokenError(Exception): pass

class StopTokenizing(Exception): pass

def printtoken(type, token, (srow, scol), (erow, ecol), line): # for testing
    print "%d,%d-%d,%d:\t%s\t%s" % \
        (srow, scol, erow, ecol, tok_name[type], repr(token))

def tokenize(readline, tokeneater=printtoken):
    try:
        tokenize_loop(readline, tokeneater)
    except StopTokenizing:
        pass

def tokenize_loop(readline, tokeneater):
    lnum = parenlev = continued = 0
    namechars, numchars = string.letters + '_', string.digits
    contstr, needcont = '', 0
    contline = None
    indents = [0]

    while 1:                                   # loop over lines in stream
        line = readline()
        lnum = 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)
                tokeneater(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':
                tokeneater(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 = column + 1
                elif line[pos] == '\t': column = (column/tabsize + 1)*tabsize
                elif line[pos] == '\f': column = 0
                else: break
                pos = pos + 1
            if pos == max: break

            if line[pos] in '#\r\n':           # skip comments or blank lines
                tokeneater((NL, COMMENT)[line[pos] == '#'], line[pos:],
                           (lnum, pos), (lnum, len(line)), line)
                continue

            if column > indents[-1]:           # count indents or dedents
                indents.append(column)
                tokeneater(INDENT, line[:pos], (lnum, 0), (lnum, pos), line)
            while column < indents[-1]:
                indents = indents[:-1]
                tokeneater(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 \
                   (initial == '.' and token != '.'):      # ordinary number
                    tokeneater(NUMBER, token, spos, epos, line)
                elif initial in '\r\n':
                    tokeneater(parenlev > 0 and NL or NEWLINE,
                               token, spos, epos, line)
                elif initial == '#':
                    tokeneater(COMMENT, token, spos, epos, line)
                elif token in ("'''", '"""',               # triple-quoted
                               "r'''", 'r"""', "R'''", 'R"""',
                               "u'''", 'u"""', "U'''", 'U"""',
                               "ur'''", 'ur"""', "Ur'''", 'Ur"""',
                               "uR'''", 'uR"""', "UR'''", 'UR"""'):
                    endprog = endprogs[token]
                    endmatch = endprog.match(line, pos)
                    if endmatch:                           # all on one line
                        pos = endmatch.end(0)
                        token = line[start:pos]
                        tokeneater(STRING, token, spos, (lnum, pos), line)
                    else:
                        strstart = (lnum, start)           # multiple lines
                        contstr = line[start:]
                        contline = line
                        break
                elif initial in ("'", '"') or \
                    token[:2] in ("r'", 'r"', "R'", 'R"',
                                  "u'", 'u"', "U'", 'U"') or \
                    token[:3] in ("ur'", 'ur"', "Ur'", 'Ur"',
                                  "uR'", 'uR"', "UR'", 'UR"' ):
                    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
                        tokeneater(STRING, token, spos, epos, line)
                elif initial in namechars:                 # ordinary name
                    tokeneater(NAME, token, spos, epos, line)
                elif initial == '\\':                      # continued stmt
                    continued = 1
                else:
                    if initial in '([{': parenlev = parenlev + 1
                    elif initial in ')]}': parenlev = parenlev - 1
                    tokeneater(OP, token, spos, epos, line)
            else:
                tokeneater(ERRORTOKEN, line[pos],
                           (lnum, pos), (lnum, pos+1), line)
                pos = pos + 1

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

if __name__ == '__main__':                     # testing
    import sys
    if len(sys.argv) > 1: tokenize(open(sys.argv[1]).readline)
    else: tokenize(sys.stdin.readline)