cpython/Lib/tokenize.py

194 lines
8.4 KiB
Python
Raw Normal View History

"""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.
For compatibility with the older 'tokenize' module, this also compiles a
regular expression into 'tokenprog' that matches Python tokens in individual
lines of text, leaving the token in 'tokenprog.group(3)', but does not
handle indentation, continuations, or multi-line strings."""
__version__ = "Ka-Ping Yee, 29 March 1997"
1992-01-01 15:34:47 -04:00
1997-03-06 20:21:12 -04:00
import string, regex
from token import *
1992-01-01 15:34:47 -04:00
COMMENT = N_TOKENS
tok_name[COMMENT] = 'COMMENT'
# Changes from 1.3:
# Ignore now accepts \f as whitespace. Operator now includes '**'.
# Ignore and Special now accept \n or \r\n at the end of a line.
# Imagnumber is new. Expfloat is corrected to reject '0e4'.
# Note: to get a quoted backslash in a regex, it must be enclosed in brackets.
1997-03-06 20:21:12 -04:00
def group(*choices): return '\(' + string.join(choices, '\|') + '\)'
1992-01-01 15:34:47 -04:00
Whitespace = '[ \f\t]*'
Comment = '\(#[^\r\n]*\)'
Ignore = Whitespace + group('[\]\r?\n' + Whitespace)+'*' + Comment+'?'
1992-01-01 15:34:47 -04:00
Name = '[a-zA-Z_][a-zA-Z0-9_]*'
Hexnumber = '0[xX][0-9a-fA-F]*[lL]?'
Octnumber = '0[0-7]*[lL]?'
Decnumber = '[1-9][0-9]*[lL]?'
Intnumber = group(Hexnumber, Octnumber, Decnumber)
1992-01-01 15:34:47 -04:00
Exponent = '[eE][-+]?[0-9]+'
1997-03-06 20:21:12 -04:00
Pointfloat = group('[0-9]+\.[0-9]*', '\.[0-9]+') + group(Exponent) + '?'
Expfloat = '[1-9][0-9]*' + Exponent
Floatnumber = group(Pointfloat, Expfloat)
Imagnumber = group('0[jJ]', '[1-9][0-9]*[jJ]', Floatnumber + '[jJ]')
Number = group(Imagnumber, Floatnumber, Intnumber)
1992-01-01 15:34:47 -04:00
Single = group("[^'\]", "[\].") + "*'"
Double = group('[^"\]', '[\].') + '*"'
Single3 = group("[^'\]","[\].","'[^'\]","'[\].","''[^'\]","''[\].") + "*'''"
Double3 = group('[^"\]','[\].','"[^"\]','"[\].','""[^"\]','""[\].') + '*"""'
Triple = group("'''", '"""')
String = group("'" + group("[^\n'\]", "[\].") + "*'",
'"' + group('[^\n"\]', '[\].') + '*"')
1992-01-01 15:34:47 -04:00
1997-03-06 20:21:12 -04:00
Operator = group('\+', '\-', '\*\*', '\*', '\^', '~', '/', '%', '&', '|',
'<<', '>>', '==', '<=', '<>', '!=', '>=', '=', '<', '>')
1992-01-01 15:34:47 -04:00
Bracket = '[][(){}]'
Special = group('\r?\n', '[:;.,`]')
1997-03-06 20:21:12 -04:00
Funny = group(Operator, Bracket, Special)
1992-01-01 15:34:47 -04:00
PlainToken = group(Name, Number, String, Funny)
1997-03-06 20:21:12 -04:00
Token = Ignore + PlainToken
1992-01-01 15:34:47 -04:00
ContStr = group("'" + group('[\].', "[^\n'\]")+'*' + group("'", '[\]\r?\n'),
'"' + group('[\].', '[^\n"\]')+'*' + group('"', '[\]\r?\n'))
PseudoExtras = group('[\]\r?\n', Comment, Triple)
PseudoToken = Whitespace + group(PseudoExtras, Name, Number, ContStr, Funny)
1992-01-01 15:34:47 -04:00
try:
saved_syntax = regex.set_syntax(0) # use default syntax
1997-03-06 20:21:12 -04:00
tokenprog = regex.compile(Token)
pseudoprog = regex.compile(PseudoToken)
1997-03-06 20:21:12 -04:00
endprogs = { '\'': regex.compile(Single), '"': regex.compile(Double),
'\'\'\'': regex.compile(Single3), '"""': regex.compile(Double3) }
1992-01-01 15:34:47 -04:00
finally:
regex.set_syntax(saved_syntax) # restore original syntax
1997-03-06 20:21:12 -04:00
tabsize = 8
TokenError = 'TokenError'
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))
1997-03-06 20:21:12 -04:00
def tokenize(readline, tokeneater=printtoken):
lnum = parenlev = continued = 0
1997-03-06 20:21:12 -04:00
namechars, numchars = string.letters + '_', string.digits
contstr, needcont = '', 0
1997-03-06 20:21:12 -04:00
indents = [0]
1997-03-06 20:21:12 -04:00
while 1: # loop over lines in stream
line = readline()
lnum = lnum + 1
1997-03-06 20:21:12 -04:00
pos, max = 0, len(line)
if contstr: # continued string
if not line:
raise TokenError, ("EOF in multi-line string", strstart)
if endprog.match(line) >= 0:
1997-03-06 20:21:12 -04:00
pos = end = endprog.regs[0][1]
tokeneater(STRING, contstr + line[:end],
strstart, (lnum, end), line)
contstr, needcont = '', 0
elif needcont and line[-2:] != '\\\n' and line[-3:] != '\\\r\n':
tokeneater(ERRORTOKEN, contstr + line,
strstart, (lnum, len(line)), line)
1997-03-06 20:21:12 -04:00
contstr = ''
continue
1997-03-06 20:21:12 -04:00
else:
contstr = contstr + line
continue
elif parenlev == 0 and not continued: # new statement
1997-03-06 20:21:12 -04:00
if not line: break
column = 0
while pos < max: # measure leading whitespace
1997-03-06 20:21:12 -04:00
if line[pos] == ' ': column = column + 1
elif line[pos] == '\t': column = (column/tabsize + 1)*tabsize
1997-03-06 20:21:12 -04:00
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((NEWLINE, COMMENT)[line[pos] == '#'], line[pos:],
(lnum, pos), (lnum, len(line)), line)
continue
1997-03-06 20:21:12 -04:00
if column > indents[-1]: # count indents or dedents
indents.append(column)
tokeneater(INDENT, line[:pos], (lnum, 0), (lnum, pos), line)
1997-03-06 20:21:12 -04:00
while column < indents[-1]:
indents = indents[:-1]
tokeneater(DEDENT, '', (lnum, pos), (lnum, pos), line)
1997-03-06 20:21:12 -04:00
else: # continued statement
if not line:
raise TokenError, ("EOF in multi-line statement", (lnum, 0))
1997-03-06 20:21:12 -04:00
continued = 0
while pos < max:
if pseudoprog.match(line, pos) > 0: # scan for tokens
start, end = pseudoprog.regs[1]
spos, epos, pos = (lnum, start), (lnum, end), end
token, initial = line[start:end], line[start]
1997-03-06 20:21:12 -04:00
if initial in namechars: # ordinary name
tokeneater(NAME, token, spos, epos, line)
elif initial in numchars \
or (initial == '.' and token != '.'): # ordinary number
tokeneater(NUMBER, token, spos, epos, line)
elif initial in '\r\n':
tokeneater(NEWLINE, token, spos, epos, line)
elif initial == '#':
tokeneater(COMMENT, token, spos, epos, line)
elif initial == '\\': # continued stmt
continued = 1
1997-03-06 20:21:12 -04:00
elif token in ('\'\'\'', '"""'): # triple-quoted
endprog = endprogs[token]
if endprog.match(line, pos) >= 0: # all on one line
1997-03-06 20:21:12 -04:00
pos = endprog.regs[0][1]
token = line[start:pos]
tokeneater(STRING, token, spos, (lnum, pos), line)
1997-03-06 20:21:12 -04:00
else:
strstart = (lnum, start) # multiple lines
contstr = line[start:]
1997-03-06 20:21:12 -04:00
break
elif initial in '\'"':
1997-03-06 20:21:12 -04:00
if token[-1] == '\n': # continued string
strstart = (lnum, start)
endprog = endprogs[initial]
contstr, needcont = line[start:], 1
1997-03-06 20:21:12 -04:00
break
else: # ordinary string
tokeneater(STRING, token, spos, epos, line)
1997-03-06 20:21:12 -04:00
else:
if initial in '([{': parenlev = parenlev + 1
elif initial in ')]}': parenlev = parenlev - 1
tokeneater(OP, token, spos, epos, line)
1997-03-06 20:21:12 -04:00
else:
tokeneater(ERRORTOKEN, line[pos],
(lnum, pos), (lnum, pos+1), line)
1997-03-06 20:21:12 -04:00
pos = pos + 1
for indent in indents[1:]: # pop remaining indent levels
tokeneater(DEDENT, '', (lnum, 0), (lnum, 0), '')
tokeneater(ENDMARKER, '', (lnum, 0), (lnum, 0), '')
1997-03-06 20:21:12 -04:00
if __name__ == '__main__': # testing
import sys
if len(sys.argv) > 1: tokenize(open(sys.argv[1]).readline)
else: tokenize(sys.stdin.readline)