# Copyright (c) 2001, 2002, 2003, 2004, 2005, 2006 Python Software Foundation.
"""Tokenization help for Python programs.
generate_tokens(readline) is a generator 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). It generates
5-tuples with these members:
the token type (see token.py)
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
tokenize_loop(readline, tokeneater)
tokenize(readline, tokeneater=printtoken)
are the same, except instead of generating tokens, tokeneater is a callback
function to which the 5 fields described above are passed as 5 arguments,
each time a new token is found."""
__author__ = 'Ka-Ping Yee <ping@lfw.org>'
'GvR, ESR, Tim Peters, Thomas Wouters, Fred Drake, Skip Montanaro'
from codecs import BOM_UTF8, lookup
from lib2to3.pgen2.token import *
__all__ = [x for x in dir(token) if x[0] != '_'] + ["tokenize",
"generate_tokens", "untokenize"]
# Support bytes type in Python <= 2.5, so 2to3 turns itself into
def group(*choices): return '(' + '|'.join(choices) + ')'
def any(*choices): return group(*choices) + '*'
def maybe(*choices): return group(*choices) + '?'
Ignore = Whitespace + any(r'\\\r?\n' + Whitespace) + maybe(Comment)
Binnumber = r'0[bB][01]*'
Hexnumber = r'0[xX][\da-fA-F]*[lL]?'
Octnumber = r'0[oO]?[0-7]*[lL]?'
Decnumber = r'[1-9]\d*[lL]?'
Intnumber = group(Binnumber, Hexnumber, Octnumber, Decnumber)
Exponent = r'[eE][-+]?\d+'
Pointfloat = group(r'\d+\.\d*', r'\.\d+') + maybe(Exponent)
Expfloat = r'\d+' + Exponent
Floatnumber = group(Pointfloat, Expfloat)
Imagnumber = group(r'\d+[jJ]', Floatnumber + r'[jJ]')
Number = group(Imagnumber, Floatnumber, Intnumber)
Single = r"[^'\\]*(?:\\.[^'\\]*)*'"
Double = r'[^"\\]*(?:\\.[^"\\]*)*"'
# Tail end of ''' string.
Single3 = r"[^'\\]*(?:(?:\\.|'(?!''))[^'\\]*)*'''"
# Tail end of """ string.
Double3 = r'[^"\\]*(?:(?:\\.|"(?!""))[^"\\]*)*"""'
Triple = group("[ubUB]?[rR]?'''", '[ubUB]?[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"!=",
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"[uUbB]?[rR]?'[^\n'\\]*(?:\\.[^\n'\\]*)*" +
r'[uUbB]?[rR]?"[^\n"\\]*(?:\\.[^\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,
"b'''": single3prog, 'b"""': double3prog,
"ur'''": single3prog, 'ur"""': double3prog,
"br'''": single3prog, 'br"""': double3prog,
"R'''": single3prog, 'R"""': double3prog,
"U'''": single3prog, 'U"""': double3prog,
"B'''": single3prog, 'B"""': double3prog,
"uR'''": single3prog, 'uR"""': double3prog,
"Ur'''": single3prog, 'Ur"""': double3prog,
"UR'''": single3prog, 'UR"""': double3prog,
"bR'''": single3prog, 'bR"""': double3prog,
"Br'''": single3prog, 'Br"""': double3prog,
"BR'''": single3prog, 'BR"""': double3prog,
"r'''", 'r"""', "R'''", 'R"""',
"u'''", 'u"""', "U'''", 'U"""',
"b'''", 'b"""', "B'''", 'B"""',
"ur'''", 'ur"""', "Ur'''", 'Ur"""',
"uR'''", 'uR"""', "UR'''", 'UR"""',
"br'''", 'br"""', "Br'''", 'Br"""',
"bR'''", 'bR"""', "BR'''", 'BR"""',):
"ur'", 'ur"', "Ur'", 'Ur"',
"uR'", 'uR"', "UR'", 'UR"',
"br'", 'br"', "Br'", 'Br"',
"bR'", 'bR"', "BR'", 'BR"', ):
class TokenError(Exception): pass
class StopTokenizing(Exception): pass
def printtoken(type, token, start, end, 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):
The tokenize() function accepts two parameters: one representing the
input stream, and one providing an output mechanism for tokenize().
The first parameter, readline, 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 a string.
The second parameter, tokeneater, must also be a callable object. It is
called once for each token, with five arguments, corresponding to the
tuples generated by generate_tokens().
tokenize_loop(readline, tokeneater)
# backwards compatible interface
def tokenize_loop(readline, tokeneater):
for token_info in generate_tokens(readline):
def add_whitespace(self, start):
assert row <= self.prev_row
col_offset = col - self.prev_col
self.tokens.append(" " * col_offset)
def untokenize(self, iterable):
tok_type, token, start, end, line = t
self.add_whitespace(start)
self.tokens.append(token)
self.prev_row, self.prev_col = end
if tok_type in (NEWLINE, NL):
return "".join(self.tokens)
def compat(self, token, iterable):
toks_append = self.tokens.append
if toknum in (NAME, NUMBER):
if toknum in (NEWLINE, NL):
if toknum in (NAME, NUMBER):
elif toknum in (NEWLINE, NL):
elif startline and indents:
cookie_re = re.compile(r'^[ \t\f]*#.*?coding[:=][ \t]*([-\w.]+)')
blank_re = re.compile(r'^[ \t\f]*(?:[#\r\n]|$)')
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-"):
if enc in ("latin-1", "iso-8859-1", "iso-latin-1") or \
enc.startswith(("latin-1-", "iso-8859-1-", "iso-latin-1-")):
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 argument, 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
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. Note that if a utf-8 bom is found,
If no encoding is specified, then the default of 'utf-8' will be returned.
line_string = line.decode('ascii')
except UnicodeDecodeError:
match = cookie_re.match(line_string)
encoding = _get_normal_name(match.group(1))
# This behaviour mimics the Python interpreter
raise SyntaxError("unknown encoding: " + encoding)
if codec.name != 'utf-8':
# This behaviour mimics the Python interpreter
raise SyntaxError('encoding problem: utf-8')
if first.startswith(BOM_UTF8):
encoding = find_cookie(first)
if not blank_re.match(first):
encoding = find_cookie(second)
return encoding, [first, second]
return default, [first, second]
def untokenize(iterable):
"""Transform tokens back into Python source code.
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 text will tokenize the back to the input
t1 = [tok[:2] for tok in generate_tokens(f.readline)]
readline = iter(newcode.splitlines(1)).next
t2 = [tok[:2] for tokin generate_tokens(readline)]
return ut.untokenize(iterable)
def generate_tokens(readline):
The generate_tokens() generator requires one argument, 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 a string. Alternately, readline
can be a callable function terminating with StopIteration:
readline = open(myfile).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.
lnum = parenlev = continued = 0
namechars, numchars = string.ascii_letters + '_', '0123456789'
contstr, needcont = '', 0
while 1: # loop over lines in stream
if contstr: # continued string
raise TokenError, ("EOF in multi-line string", strstart)
endmatch = endprog.match(line)
pos = end = endmatch.end(0)
yield (STRING, contstr + line[:end],
strstart, (lnum, end), contline + line)
contstr, needcont = '', 0
elif needcont and line[-2:] != '\\\n' and line[-3:] != '\\\r\n':
yield (ERRORTOKEN, contstr + line,
strstart, (lnum, len(line)), contline)
contline = contline + line
elif parenlev == 0 and not continued: # new statement
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
if line[pos] in '#\r\n': # skip comments or blank lines
comment_token = line[pos:].rstrip('\r\n')
nl_pos = pos + len(comment_token)
yield (COMMENT, comment_token,
(lnum, pos), (lnum, pos + len(comment_token)), line)
yield (NL, line[nl_pos:],
(lnum, nl_pos), (lnum, len(line)), line)
yield ((NL, COMMENT)[line[pos] == '#'], line[pos:],
(lnum, pos), (lnum, len(line)), line)
if column > indents[-1]: # count indents or dedents
yield (INDENT, line[:pos], (lnum, 0), (lnum, pos), line)
while column < indents[-1]:
if column not in indents:
"unindent does not match any outer indentation level",
("<tokenize>", lnum, pos, line))
yield (DEDENT, '', (lnum, pos), (lnum, pos), line)
else: # continued statement
raise TokenError, ("EOF in multi-line statement", (lnum, 0))
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
yield (NUMBER, token, spos, epos, line)
yield (newline, token, spos, epos, line)
assert not token.endswith("\n")
yield (COMMENT, token, spos, epos, line)
elif token in triple_quoted:
endprog = endprogs[token]
endmatch = endprog.match(line, pos)
if endmatch: # all on one line
yield (STRING, token, spos, (lnum, pos), line)
strstart = (lnum, start) # multiple lines
elif initial in single_quoted or \
token[:2] in single_quoted or \
token[:3] in single_quoted:
if token[-1] == '\n': # continued string
endprog = (endprogs[initial] or endprogs[token[1]] or
contstr, needcont = line[start:], 1
yield (STRING, token, spos, epos, line)
elif initial in namechars: # ordinary name
yield (NAME, token, spos, epos, line)
elif initial == '\\': # continued stmt
# This yield is new; needed for better idempotency:
yield (NL, token, spos, (lnum, pos), line)
if initial in '([{': parenlev = parenlev + 1
elif initial in ')]}': parenlev = parenlev - 1
yield (OP, token, spos, epos, line)
yield (ERRORTOKEN, line[pos],
(lnum, pos), (lnum, pos+1), line)
for indent in indents[1:]: # pop remaining indent levels
yield (DEDENT, '', (lnum, 0), (lnum, 0), '')
yield (ENDMARKER, '', (lnum, 0), (lnum, 0), '')
if __name__ == '__main__': # testing
It is recommended that you Edit text format, this type of Fix handles quite a lot in one request
