cpython/Lib/lib2to3/pgen2/tokenize.py

565 lines
21 KiB
Python
Raw Normal View History

# Copyright (c) 2001, 2002, 2003, 2004, 2005, 2006 Python Software Foundation.
# All rights reserved.
"""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 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
Older entry points
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>'
__credits__ = \
'GvR, ESR, Tim Peters, Thomas Wouters, Fred Drake, Skip Montanaro'
import string, re
from codecs import BOM_UTF8, lookup
from lib2to3.pgen2.token import *
from . import token
__all__ = [x for x in dir(token) if x[0] != '_'] + ["tokenize",
"generate_tokens", "untokenize"]
del token
Merged revisions 80934 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ................ r80934 | benjamin.peterson | 2010-05-07 13:58:23 -0500 (Fri, 07 May 2010) | 69 lines Merged revisions 79911,79916-79917,80018,80418,80572-80573,80635-80639,80668,80922 via svnmerge from svn+ssh://pythondev@svn.python.org/sandbox/trunk/2to3/lib2to3 ........ r79911 | benjamin.peterson | 2010-04-09 15:38:53 -0500 (Fri, 09 Apr 2010) | 1 line use absolute import ........ r79916 | benjamin.peterson | 2010-04-09 16:05:21 -0500 (Fri, 09 Apr 2010) | 1 line generalize detection of __future__ imports and attach them to the tree ........ r79917 | benjamin.peterson | 2010-04-09 16:11:44 -0500 (Fri, 09 Apr 2010) | 1 line don't try to 'fix' relative imports when absolute_import is enabled #8858 ........ r80018 | benjamin.peterson | 2010-04-12 16:12:12 -0500 (Mon, 12 Apr 2010) | 4 lines prevent diffs from being mangled is multiprocess mode #6409 Patch by George Boutsioukis. ........ r80418 | benjamin.peterson | 2010-04-23 16:00:03 -0500 (Fri, 23 Apr 2010) | 1 line remove unhelpful description ........ r80572 | benjamin.peterson | 2010-04-27 20:33:54 -0500 (Tue, 27 Apr 2010) | 1 line use unicode literals ........ r80573 | jeffrey.yasskin | 2010-04-27 23:08:27 -0500 (Tue, 27 Apr 2010) | 6 lines Don't transform imports that are already relative. 2to3 turned from . import refactor into from .. import refactor which broke the transformation of 2to3 itself. ........ r80635 | benjamin.peterson | 2010-04-29 16:02:23 -0500 (Thu, 29 Apr 2010) | 1 line remove imports ........ r80636 | benjamin.peterson | 2010-04-29 16:02:41 -0500 (Thu, 29 Apr 2010) | 1 line unicode literal ........ r80637 | benjamin.peterson | 2010-04-29 16:03:42 -0500 (Thu, 29 Apr 2010) | 1 line must pass a string to Number ........ r80638 | benjamin.peterson | 2010-04-29 16:05:34 -0500 (Thu, 29 Apr 2010) | 1 line unicode literals ........ r80639 | benjamin.peterson | 2010-04-29 16:06:09 -0500 (Thu, 29 Apr 2010) | 1 line pass string to Number ........ r80668 | jeffrey.yasskin | 2010-04-30 18:02:47 -0500 (Fri, 30 Apr 2010) | 4 lines Make 2to3 run under Python 2.5 so that the benchmark suite at http://hg.python.org/benchmarks/ can use it and still run on implementations that haven't gotten to 2.6 yet. Fixes issue 8566. ........ r80922 | benjamin.peterson | 2010-05-07 11:06:25 -0500 (Fri, 07 May 2010) | 1 line prevent xrange transformation from wrapping range calls it produces in list ........ ................
2010-05-07 16:10:11 -03:00
try:
bytes
except NameError:
# Support bytes type in Python <= 2.5, so 2to3 turns itself into
# valid Python 3 code.
bytes = str
def group(*choices): return '(' + '|'.join(choices) + ')'
def any(*choices): return group(*choices) + '*'
def maybe(*choices): return group(*choices) + '?'
def _combinations(*l):
return set(
x + y for x in l for y in l + ("",) if x.casefold() != y.casefold()
)
Whitespace = r'[ \f\t]*'
Comment = r'#[^\r\n]*'
Ignore = Whitespace + any(r'\\\r?\n' + Whitespace) + maybe(Comment)
Name = r'\w+'
Binnumber = r'0[bB]_?[01]+(?:_[01]+)*'
Hexnumber = r'0[xX]_?[\da-fA-F]+(?:_[\da-fA-F]+)*[lL]?'
Octnumber = r'0[oO]?_?[0-7]+(?:_[0-7]+)*[lL]?'
Decnumber = group(r'[1-9]\d*(?:_\d+)*[lL]?', '0[lL]?')
Intnumber = group(Binnumber, Hexnumber, Octnumber, Decnumber)
Exponent = r'[eE][-+]?\d+(?:_\d+)*'
Pointfloat = group(r'\d+(?:_\d+)*\.(?:\d+(?:_\d+)*)?', r'\.\d+(?:_\d+)*') + maybe(Exponent)
Expfloat = r'\d+(?:_\d+)*' + Exponent
Floatnumber = group(Pointfloat, Expfloat)
Imagnumber = group(r'\d+(?:_\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'[^"\\]*(?:(?:\\.|"(?!""))[^"\\]*)*"""'
_litprefix = r"(?:[uUrRbBfF]|[rR][fFbB]|[fFbBuU][rR])?"
Triple = group(_litprefix + "'''", _litprefix + '"""')
# Single-line ' or " string.
String = group(_litprefix + r"'[^\n'\\]*(?:\\.[^\n'\\]*)*'",
_litprefix + r'"[^\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"[+\-*/%&@|^=<>]=?",
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(_litprefix + r"'[^\n'\\]*(?:\\.[^\n'\\]*)*" +
group("'", r'\\\r?\n'),
_litprefix + r'"[^\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))
_strprefixes = (
_combinations('r', 'R', 'f', 'F') |
_combinations('r', 'R', 'b', 'B') |
{'u', 'U', 'ur', 'uR', 'Ur', 'UR'}
)
endprogs = {"'": re.compile(Single), '"': re.compile(Double),
"'''": single3prog, '"""': double3prog,
**{f"{prefix}'''": single3prog for prefix in _strprefixes},
**{f'{prefix}"""': double3prog for prefix in _strprefixes},
**{prefix: None for prefix in _strprefixes}}
triple_quoted = (
{"'''", '"""'} |
{f"{prefix}'''" for prefix in _strprefixes} |
{f'{prefix}"""' for prefix in _strprefixes}
)
single_quoted = (
{"'", '"'} |
{f"{prefix}'" for prefix in _strprefixes} |
{f'{prefix}"' for prefix in _strprefixes}
)
tabsize = 8
class TokenError(Exception): pass
class StopTokenizing(Exception): pass
2008-03-19 02:33:36 -03:00
def printtoken(type, token, xxx_todo_changeme, xxx_todo_changeme1, line): # for testing
(srow, scol) = xxx_todo_changeme
(erow, ecol) = xxx_todo_changeme1
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().
"""
try:
tokenize_loop(readline, tokeneater)
except StopTokenizing:
pass
# backwards compatible interface
def tokenize_loop(readline, tokeneater):
for token_info in generate_tokens(readline):
tokeneater(*token_info)
class Untokenizer:
def __init__(self):
self.tokens = []
self.prev_row = 1
self.prev_col = 0
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
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
for tok in iterable:
toknum, tokval = tok[:2]
if toknum in (NAME, NUMBER, ASYNC, AWAIT):
tokval += ' '
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)
cookie_re = re.compile(r'^[ \t\f]*#.*?coding[:=][ \t]*([-\w.]+)', re.ASCII)
blank_re = re.compile(br'^[ \t\f]*(?:[#\r\n]|$)', re.ASCII)
Merged revisions 76062 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ................ r76062 | benjamin.peterson | 2009-11-02 12:12:12 -0600 (Mon, 02 Nov 2009) | 70 lines Merged revisions 74359,75081,75088,75213,75278,75303,75427-75428,75734-75736,75865,76059-76061 via svnmerge from svn+ssh://pythondev@svn.python.org/sandbox/trunk/2to3/lib2to3 ........ r74359 | benjamin.peterson | 2009-08-12 17:23:13 -0500 (Wed, 12 Aug 2009) | 1 line don't pass the deprecated print_function option ........ r75081 | benjamin.peterson | 2009-09-26 22:02:57 -0500 (Sat, 26 Sep 2009) | 1 line let 2to3 work with extended iterable unpacking ........ r75088 | benjamin.peterson | 2009-09-27 11:25:21 -0500 (Sun, 27 Sep 2009) | 1 line look on the type only for __call__ ........ r75213 | benjamin.peterson | 2009-10-03 10:09:46 -0500 (Sat, 03 Oct 2009) | 5 lines revert 75212; it's not correct People can use isinstance(x, collections.Callable) if they expect objects with __call__ in their instance dictionaries. ........ r75278 | benjamin.peterson | 2009-10-07 16:25:56 -0500 (Wed, 07 Oct 2009) | 4 lines fix whitespace problems with fix_idioms #3563 Patch by Joe Amenta. ........ r75303 | benjamin.peterson | 2009-10-09 16:59:11 -0500 (Fri, 09 Oct 2009) | 1 line port latin-1 and utf-8 cookie improvements ........ r75427 | benjamin.peterson | 2009-10-14 20:35:57 -0500 (Wed, 14 Oct 2009) | 1 line force floor division ........ r75428 | benjamin.peterson | 2009-10-14 20:39:21 -0500 (Wed, 14 Oct 2009) | 1 line silence -3 warnings about __hash__ ........ r75734 | benjamin.peterson | 2009-10-26 16:25:53 -0500 (Mon, 26 Oct 2009) | 2 lines warn on map(None, ...) with more than 2 arguments #7203 ........ r75735 | benjamin.peterson | 2009-10-26 16:28:25 -0500 (Mon, 26 Oct 2009) | 1 line remove unused result ........ r75736 | benjamin.peterson | 2009-10-26 16:29:02 -0500 (Mon, 26 Oct 2009) | 1 line using get() here is a bit pointless ........ r75865 | benjamin.peterson | 2009-10-27 15:49:00 -0500 (Tue, 27 Oct 2009) | 1 line explain reason for warning ........ r76059 | benjamin.peterson | 2009-11-02 11:43:47 -0600 (Mon, 02 Nov 2009) | 1 line tuples are no longer used for children ........ r76060 | benjamin.peterson | 2009-11-02 11:55:40 -0600 (Mon, 02 Nov 2009) | 1 line revert r76059; apparently some fixers rely on Leaf no () for children ........ r76061 | benjamin.peterson | 2009-11-02 12:06:17 -0600 (Mon, 02 Nov 2009) | 1 line make fix_tuple_params keep the tree valid #7253 ........ ................
2009-11-02 14:16:28 -04:00
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 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
in.
It detects the encoding from the presence of a utf-8 bom or an encoding
Merged revisions 79306,79311,79325 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ................ r79306 | benjamin.peterson | 2010-03-22 17:40:06 -0500 (Mon, 22 Mar 2010) | 21 lines Merged revisions 79077,79137,79304-79305 via svnmerge from svn+ssh://pythondev@svn.python.org/sandbox/trunk/2to3/lib2to3 ........ r79077 | benjamin.peterson | 2010-03-18 18:05:29 -0500 (Thu, 18 Mar 2010) | 1 line port detect_encoding improvements from py3k ........ r79137 | benjamin.peterson | 2010-03-20 11:12:53 -0500 (Sat, 20 Mar 2010) | 1 line add a fixer for setting sys.exitfunc #2356 ........ r79304 | benjamin.peterson | 2010-03-22 17:20:22 -0500 (Mon, 22 Mar 2010) | 1 line fix test_parser when it's run in a path with spaces #7666 ........ r79305 | benjamin.peterson | 2010-03-22 17:27:07 -0500 (Mon, 22 Mar 2010) | 1 line normalize whitespace ........ ................ r79311 | benjamin.peterson | 2010-03-22 17:54:42 -0500 (Mon, 22 Mar 2010) | 9 lines Merged revisions 79309 via svnmerge from svn+ssh://pythondev@svn.python.org/sandbox/trunk/2to3/lib2to3 ........ r79309 | benjamin.peterson | 2010-03-22 17:50:47 -0500 (Mon, 22 Mar 2010) | 1 line pass correct symbol in ........ ................ r79325 | benjamin.peterson | 2010-03-22 22:03:55 -0500 (Mon, 22 Mar 2010) | 13 lines Merged revisions 79313,79324 via svnmerge from svn+ssh://pythondev@svn.python.org/sandbox/trunk/2to3/lib2to3 ........ r79313 | benjamin.peterson | 2010-03-22 17:59:57 -0500 (Mon, 22 Mar 2010) | 1 line another case where a symbol is needed ........ r79324 | benjamin.peterson | 2010-03-22 21:59:47 -0500 (Mon, 22 Mar 2010) | 1 line use unicode literals ........ ................
2010-03-23 00:22:05 -03:00
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,
'utf-8-sig' is returned.
If no encoding is specified, then the default of 'utf-8' will be returned.
"""
bom_found = False
encoding = None
Merged revisions 79306,79311,79325 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ................ r79306 | benjamin.peterson | 2010-03-22 17:40:06 -0500 (Mon, 22 Mar 2010) | 21 lines Merged revisions 79077,79137,79304-79305 via svnmerge from svn+ssh://pythondev@svn.python.org/sandbox/trunk/2to3/lib2to3 ........ r79077 | benjamin.peterson | 2010-03-18 18:05:29 -0500 (Thu, 18 Mar 2010) | 1 line port detect_encoding improvements from py3k ........ r79137 | benjamin.peterson | 2010-03-20 11:12:53 -0500 (Sat, 20 Mar 2010) | 1 line add a fixer for setting sys.exitfunc #2356 ........ r79304 | benjamin.peterson | 2010-03-22 17:20:22 -0500 (Mon, 22 Mar 2010) | 1 line fix test_parser when it's run in a path with spaces #7666 ........ r79305 | benjamin.peterson | 2010-03-22 17:27:07 -0500 (Mon, 22 Mar 2010) | 1 line normalize whitespace ........ ................ r79311 | benjamin.peterson | 2010-03-22 17:54:42 -0500 (Mon, 22 Mar 2010) | 9 lines Merged revisions 79309 via svnmerge from svn+ssh://pythondev@svn.python.org/sandbox/trunk/2to3/lib2to3 ........ r79309 | benjamin.peterson | 2010-03-22 17:50:47 -0500 (Mon, 22 Mar 2010) | 1 line pass correct symbol in ........ ................ r79325 | benjamin.peterson | 2010-03-22 22:03:55 -0500 (Mon, 22 Mar 2010) | 13 lines Merged revisions 79313,79324 via svnmerge from svn+ssh://pythondev@svn.python.org/sandbox/trunk/2to3/lib2to3 ........ r79313 | benjamin.peterson | 2010-03-22 17:59:57 -0500 (Mon, 22 Mar 2010) | 1 line another case where a symbol is needed ........ r79324 | benjamin.peterson | 2010-03-22 21:59:47 -0500 (Mon, 22 Mar 2010) | 1 line use unicode literals ........ ................
2010-03-23 00:22:05 -03:00
default = 'utf-8'
def read_or_stop():
try:
return readline()
except StopIteration:
Merged revisions 80934 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ................ r80934 | benjamin.peterson | 2010-05-07 13:58:23 -0500 (Fri, 07 May 2010) | 69 lines Merged revisions 79911,79916-79917,80018,80418,80572-80573,80635-80639,80668,80922 via svnmerge from svn+ssh://pythondev@svn.python.org/sandbox/trunk/2to3/lib2to3 ........ r79911 | benjamin.peterson | 2010-04-09 15:38:53 -0500 (Fri, 09 Apr 2010) | 1 line use absolute import ........ r79916 | benjamin.peterson | 2010-04-09 16:05:21 -0500 (Fri, 09 Apr 2010) | 1 line generalize detection of __future__ imports and attach them to the tree ........ r79917 | benjamin.peterson | 2010-04-09 16:11:44 -0500 (Fri, 09 Apr 2010) | 1 line don't try to 'fix' relative imports when absolute_import is enabled #8858 ........ r80018 | benjamin.peterson | 2010-04-12 16:12:12 -0500 (Mon, 12 Apr 2010) | 4 lines prevent diffs from being mangled is multiprocess mode #6409 Patch by George Boutsioukis. ........ r80418 | benjamin.peterson | 2010-04-23 16:00:03 -0500 (Fri, 23 Apr 2010) | 1 line remove unhelpful description ........ r80572 | benjamin.peterson | 2010-04-27 20:33:54 -0500 (Tue, 27 Apr 2010) | 1 line use unicode literals ........ r80573 | jeffrey.yasskin | 2010-04-27 23:08:27 -0500 (Tue, 27 Apr 2010) | 6 lines Don't transform imports that are already relative. 2to3 turned from . import refactor into from .. import refactor which broke the transformation of 2to3 itself. ........ r80635 | benjamin.peterson | 2010-04-29 16:02:23 -0500 (Thu, 29 Apr 2010) | 1 line remove imports ........ r80636 | benjamin.peterson | 2010-04-29 16:02:41 -0500 (Thu, 29 Apr 2010) | 1 line unicode literal ........ r80637 | benjamin.peterson | 2010-04-29 16:03:42 -0500 (Thu, 29 Apr 2010) | 1 line must pass a string to Number ........ r80638 | benjamin.peterson | 2010-04-29 16:05:34 -0500 (Thu, 29 Apr 2010) | 1 line unicode literals ........ r80639 | benjamin.peterson | 2010-04-29 16:06:09 -0500 (Thu, 29 Apr 2010) | 1 line pass string to Number ........ r80668 | jeffrey.yasskin | 2010-04-30 18:02:47 -0500 (Fri, 30 Apr 2010) | 4 lines Make 2to3 run under Python 2.5 so that the benchmark suite at http://hg.python.org/benchmarks/ can use it and still run on implementations that haven't gotten to 2.6 yet. Fixes issue 8566. ........ r80922 | benjamin.peterson | 2010-05-07 11:06:25 -0500 (Fri, 07 May 2010) | 1 line prevent xrange transformation from wrapping range calls it produces in list ........ ................
2010-05-07 16:10:11 -03:00
return bytes()
def find_cookie(line):
try:
line_string = line.decode('ascii')
except UnicodeDecodeError:
return None
match = cookie_re.match(line_string)
if not match:
return None
encoding = _get_normal_name(match.group(1))
try:
codec = lookup(encoding)
except LookupError:
# This behaviour mimics the Python interpreter
raise SyntaxError("unknown encoding: " + encoding)
Merged revisions 76259,76326,76376-76377,76430,76471,76517 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ................ r76259 | georg.brandl | 2009-11-14 05:50:51 -0600 (Sat, 14 Nov 2009) | 1 line Fix terminology. ................ r76326 | georg.brandl | 2009-11-16 10:44:05 -0600 (Mon, 16 Nov 2009) | 1 line #7302: fix link. ................ r76376 | georg.brandl | 2009-11-18 13:39:14 -0600 (Wed, 18 Nov 2009) | 1 line upcase Python ................ r76377 | georg.brandl | 2009-11-18 14:05:15 -0600 (Wed, 18 Nov 2009) | 1 line Fix markup. ................ r76430 | r.david.murray | 2009-11-20 07:29:43 -0600 (Fri, 20 Nov 2009) | 2 lines Issue 7363: fix indentation in socketserver udpserver example. ................ r76471 | georg.brandl | 2009-11-23 13:53:19 -0600 (Mon, 23 Nov 2009) | 1 line #7345: fix arguments of formatyear(). ................ r76517 | benjamin.peterson | 2009-11-25 12:16:46 -0600 (Wed, 25 Nov 2009) | 29 lines Merged revisions 76160-76161,76250,76252,76447,76506 via svnmerge from svn+ssh://pythondev@svn.python.org/sandbox/trunk/2to3/lib2to3 ........ r76160 | benjamin.peterson | 2009-11-08 18:53:48 -0600 (Sun, 08 Nov 2009) | 1 line undeprecate the -p option; it's useful for converting python3 sources ........ r76161 | benjamin.peterson | 2009-11-08 19:05:37 -0600 (Sun, 08 Nov 2009) | 1 line simplify condition ........ r76250 | benjamin.peterson | 2009-11-13 16:56:48 -0600 (Fri, 13 Nov 2009) | 1 line fix handling of a utf-8 bom #7313 ........ r76252 | benjamin.peterson | 2009-11-13 16:58:36 -0600 (Fri, 13 Nov 2009) | 1 line remove pdb turd ........ r76447 | benjamin.peterson | 2009-11-22 18:17:40 -0600 (Sun, 22 Nov 2009) | 1 line #7375 fix nested transformations in fix_urllib ........ r76506 | benjamin.peterson | 2009-11-24 18:34:31 -0600 (Tue, 24 Nov 2009) | 1 line use generator expressions in any() ........ ................
2009-11-25 14:34:42 -04:00
if bom_found:
if codec.name != 'utf-8':
# This behaviour mimics the Python interpreter
raise SyntaxError('encoding problem: utf-8')
Merged revisions 79306,79311,79325 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ................ r79306 | benjamin.peterson | 2010-03-22 17:40:06 -0500 (Mon, 22 Mar 2010) | 21 lines Merged revisions 79077,79137,79304-79305 via svnmerge from svn+ssh://pythondev@svn.python.org/sandbox/trunk/2to3/lib2to3 ........ r79077 | benjamin.peterson | 2010-03-18 18:05:29 -0500 (Thu, 18 Mar 2010) | 1 line port detect_encoding improvements from py3k ........ r79137 | benjamin.peterson | 2010-03-20 11:12:53 -0500 (Sat, 20 Mar 2010) | 1 line add a fixer for setting sys.exitfunc #2356 ........ r79304 | benjamin.peterson | 2010-03-22 17:20:22 -0500 (Mon, 22 Mar 2010) | 1 line fix test_parser when it's run in a path with spaces #7666 ........ r79305 | benjamin.peterson | 2010-03-22 17:27:07 -0500 (Mon, 22 Mar 2010) | 1 line normalize whitespace ........ ................ r79311 | benjamin.peterson | 2010-03-22 17:54:42 -0500 (Mon, 22 Mar 2010) | 9 lines Merged revisions 79309 via svnmerge from svn+ssh://pythondev@svn.python.org/sandbox/trunk/2to3/lib2to3 ........ r79309 | benjamin.peterson | 2010-03-22 17:50:47 -0500 (Mon, 22 Mar 2010) | 1 line pass correct symbol in ........ ................ r79325 | benjamin.peterson | 2010-03-22 22:03:55 -0500 (Mon, 22 Mar 2010) | 13 lines Merged revisions 79313,79324 via svnmerge from svn+ssh://pythondev@svn.python.org/sandbox/trunk/2to3/lib2to3 ........ r79313 | benjamin.peterson | 2010-03-22 17:59:57 -0500 (Mon, 22 Mar 2010) | 1 line another case where a symbol is needed ........ r79324 | benjamin.peterson | 2010-03-22 21:59:47 -0500 (Mon, 22 Mar 2010) | 1 line use unicode literals ........ ................
2010-03-23 00:22:05 -03:00
encoding += '-sig'
return encoding
first = read_or_stop()
if first.startswith(BOM_UTF8):
bom_found = True
first = first[3:]
Merged revisions 79306,79311,79325 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ................ r79306 | benjamin.peterson | 2010-03-22 17:40:06 -0500 (Mon, 22 Mar 2010) | 21 lines Merged revisions 79077,79137,79304-79305 via svnmerge from svn+ssh://pythondev@svn.python.org/sandbox/trunk/2to3/lib2to3 ........ r79077 | benjamin.peterson | 2010-03-18 18:05:29 -0500 (Thu, 18 Mar 2010) | 1 line port detect_encoding improvements from py3k ........ r79137 | benjamin.peterson | 2010-03-20 11:12:53 -0500 (Sat, 20 Mar 2010) | 1 line add a fixer for setting sys.exitfunc #2356 ........ r79304 | benjamin.peterson | 2010-03-22 17:20:22 -0500 (Mon, 22 Mar 2010) | 1 line fix test_parser when it's run in a path with spaces #7666 ........ r79305 | benjamin.peterson | 2010-03-22 17:27:07 -0500 (Mon, 22 Mar 2010) | 1 line normalize whitespace ........ ................ r79311 | benjamin.peterson | 2010-03-22 17:54:42 -0500 (Mon, 22 Mar 2010) | 9 lines Merged revisions 79309 via svnmerge from svn+ssh://pythondev@svn.python.org/sandbox/trunk/2to3/lib2to3 ........ r79309 | benjamin.peterson | 2010-03-22 17:50:47 -0500 (Mon, 22 Mar 2010) | 1 line pass correct symbol in ........ ................ r79325 | benjamin.peterson | 2010-03-22 22:03:55 -0500 (Mon, 22 Mar 2010) | 13 lines Merged revisions 79313,79324 via svnmerge from svn+ssh://pythondev@svn.python.org/sandbox/trunk/2to3/lib2to3 ........ r79313 | benjamin.peterson | 2010-03-22 17:59:57 -0500 (Mon, 22 Mar 2010) | 1 line another case where a symbol is needed ........ r79324 | benjamin.peterson | 2010-03-22 21:59:47 -0500 (Mon, 22 Mar 2010) | 1 line use unicode literals ........ ................
2010-03-23 00:22:05 -03:00
default = 'utf-8-sig'
if not first:
Merged revisions 79306,79311,79325 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ................ r79306 | benjamin.peterson | 2010-03-22 17:40:06 -0500 (Mon, 22 Mar 2010) | 21 lines Merged revisions 79077,79137,79304-79305 via svnmerge from svn+ssh://pythondev@svn.python.org/sandbox/trunk/2to3/lib2to3 ........ r79077 | benjamin.peterson | 2010-03-18 18:05:29 -0500 (Thu, 18 Mar 2010) | 1 line port detect_encoding improvements from py3k ........ r79137 | benjamin.peterson | 2010-03-20 11:12:53 -0500 (Sat, 20 Mar 2010) | 1 line add a fixer for setting sys.exitfunc #2356 ........ r79304 | benjamin.peterson | 2010-03-22 17:20:22 -0500 (Mon, 22 Mar 2010) | 1 line fix test_parser when it's run in a path with spaces #7666 ........ r79305 | benjamin.peterson | 2010-03-22 17:27:07 -0500 (Mon, 22 Mar 2010) | 1 line normalize whitespace ........ ................ r79311 | benjamin.peterson | 2010-03-22 17:54:42 -0500 (Mon, 22 Mar 2010) | 9 lines Merged revisions 79309 via svnmerge from svn+ssh://pythondev@svn.python.org/sandbox/trunk/2to3/lib2to3 ........ r79309 | benjamin.peterson | 2010-03-22 17:50:47 -0500 (Mon, 22 Mar 2010) | 1 line pass correct symbol in ........ ................ r79325 | benjamin.peterson | 2010-03-22 22:03:55 -0500 (Mon, 22 Mar 2010) | 13 lines Merged revisions 79313,79324 via svnmerge from svn+ssh://pythondev@svn.python.org/sandbox/trunk/2to3/lib2to3 ........ r79313 | benjamin.peterson | 2010-03-22 17:59:57 -0500 (Mon, 22 Mar 2010) | 1 line another case where a symbol is needed ........ r79324 | benjamin.peterson | 2010-03-22 21:59:47 -0500 (Mon, 22 Mar 2010) | 1 line use unicode literals ........ ................
2010-03-23 00:22:05 -03:00
return default, []
encoding = find_cookie(first)
if encoding:
return encoding, [first]
if not blank_re.match(first):
return default, [first]
second = read_or_stop()
if not second:
Merged revisions 79306,79311,79325 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ................ r79306 | benjamin.peterson | 2010-03-22 17:40:06 -0500 (Mon, 22 Mar 2010) | 21 lines Merged revisions 79077,79137,79304-79305 via svnmerge from svn+ssh://pythondev@svn.python.org/sandbox/trunk/2to3/lib2to3 ........ r79077 | benjamin.peterson | 2010-03-18 18:05:29 -0500 (Thu, 18 Mar 2010) | 1 line port detect_encoding improvements from py3k ........ r79137 | benjamin.peterson | 2010-03-20 11:12:53 -0500 (Sat, 20 Mar 2010) | 1 line add a fixer for setting sys.exitfunc #2356 ........ r79304 | benjamin.peterson | 2010-03-22 17:20:22 -0500 (Mon, 22 Mar 2010) | 1 line fix test_parser when it's run in a path with spaces #7666 ........ r79305 | benjamin.peterson | 2010-03-22 17:27:07 -0500 (Mon, 22 Mar 2010) | 1 line normalize whitespace ........ ................ r79311 | benjamin.peterson | 2010-03-22 17:54:42 -0500 (Mon, 22 Mar 2010) | 9 lines Merged revisions 79309 via svnmerge from svn+ssh://pythondev@svn.python.org/sandbox/trunk/2to3/lib2to3 ........ r79309 | benjamin.peterson | 2010-03-22 17:50:47 -0500 (Mon, 22 Mar 2010) | 1 line pass correct symbol in ........ ................ r79325 | benjamin.peterson | 2010-03-22 22:03:55 -0500 (Mon, 22 Mar 2010) | 13 lines Merged revisions 79313,79324 via svnmerge from svn+ssh://pythondev@svn.python.org/sandbox/trunk/2to3/lib2to3 ........ r79313 | benjamin.peterson | 2010-03-22 17:59:57 -0500 (Mon, 22 Mar 2010) | 1 line another case where a symbol is needed ........ r79324 | benjamin.peterson | 2010-03-22 21:59:47 -0500 (Mon, 22 Mar 2010) | 1 line use unicode literals ........ ................
2010-03-23 00:22:05 -03:00
return default, [first]
encoding = find_cookie(second)
if encoding:
return encoding, [first, second]
Merged revisions 79306,79311,79325 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ................ r79306 | benjamin.peterson | 2010-03-22 17:40:06 -0500 (Mon, 22 Mar 2010) | 21 lines Merged revisions 79077,79137,79304-79305 via svnmerge from svn+ssh://pythondev@svn.python.org/sandbox/trunk/2to3/lib2to3 ........ r79077 | benjamin.peterson | 2010-03-18 18:05:29 -0500 (Thu, 18 Mar 2010) | 1 line port detect_encoding improvements from py3k ........ r79137 | benjamin.peterson | 2010-03-20 11:12:53 -0500 (Sat, 20 Mar 2010) | 1 line add a fixer for setting sys.exitfunc #2356 ........ r79304 | benjamin.peterson | 2010-03-22 17:20:22 -0500 (Mon, 22 Mar 2010) | 1 line fix test_parser when it's run in a path with spaces #7666 ........ r79305 | benjamin.peterson | 2010-03-22 17:27:07 -0500 (Mon, 22 Mar 2010) | 1 line normalize whitespace ........ ................ r79311 | benjamin.peterson | 2010-03-22 17:54:42 -0500 (Mon, 22 Mar 2010) | 9 lines Merged revisions 79309 via svnmerge from svn+ssh://pythondev@svn.python.org/sandbox/trunk/2to3/lib2to3 ........ r79309 | benjamin.peterson | 2010-03-22 17:50:47 -0500 (Mon, 22 Mar 2010) | 1 line pass correct symbol in ........ ................ r79325 | benjamin.peterson | 2010-03-22 22:03:55 -0500 (Mon, 22 Mar 2010) | 13 lines Merged revisions 79313,79324 via svnmerge from svn+ssh://pythondev@svn.python.org/sandbox/trunk/2to3/lib2to3 ........ r79313 | benjamin.peterson | 2010-03-22 17:59:57 -0500 (Mon, 22 Mar 2010) | 1 line another case where a symbol is needed ........ r79324 | benjamin.peterson | 2010-03-22 21:59:47 -0500 (Mon, 22 Mar 2010) | 1 line use unicode literals ........ ................
2010-03-23 00:22:05 -03:00
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 input:
# Output text will tokenize the back to the input
t1 = [tok[:2] for tok in generate_tokens(f.readline)]
newcode = untokenize(t1)
readline = iter(newcode.splitlines(1)).next
t2 = [tok[:2] for tokin generate_tokens(readline)]
assert t1 == t2
"""
ut = Untokenizer()
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
physical line.
"""
lnum = parenlev = continued = 0
contstr, needcont = '', 0
contline = None
indents = [0]
# 'stashed' and 'async_*' are used for async/await parsing
stashed = None
async_def = False
async_def_indent = 0
async_def_nl = False
while 1: # loop over lines in stream
try:
line = readline()
except StopIteration:
line = ''
lnum = lnum + 1
pos, max = 0, len(line)
if contstr: # continued string
if not line:
2008-03-19 02:33:36 -03:00
raise TokenError("EOF in multi-line string", strstart)
endmatch = endprog.match(line)
if endmatch:
pos = end = endmatch.end(0)
yield (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 (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
Merged revisions 76062 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ................ r76062 | benjamin.peterson | 2009-11-02 12:12:12 -0600 (Mon, 02 Nov 2009) | 70 lines Merged revisions 74359,75081,75088,75213,75278,75303,75427-75428,75734-75736,75865,76059-76061 via svnmerge from svn+ssh://pythondev@svn.python.org/sandbox/trunk/2to3/lib2to3 ........ r74359 | benjamin.peterson | 2009-08-12 17:23:13 -0500 (Wed, 12 Aug 2009) | 1 line don't pass the deprecated print_function option ........ r75081 | benjamin.peterson | 2009-09-26 22:02:57 -0500 (Sat, 26 Sep 2009) | 1 line let 2to3 work with extended iterable unpacking ........ r75088 | benjamin.peterson | 2009-09-27 11:25:21 -0500 (Sun, 27 Sep 2009) | 1 line look on the type only for __call__ ........ r75213 | benjamin.peterson | 2009-10-03 10:09:46 -0500 (Sat, 03 Oct 2009) | 5 lines revert 75212; it's not correct People can use isinstance(x, collections.Callable) if they expect objects with __call__ in their instance dictionaries. ........ r75278 | benjamin.peterson | 2009-10-07 16:25:56 -0500 (Wed, 07 Oct 2009) | 4 lines fix whitespace problems with fix_idioms #3563 Patch by Joe Amenta. ........ r75303 | benjamin.peterson | 2009-10-09 16:59:11 -0500 (Fri, 09 Oct 2009) | 1 line port latin-1 and utf-8 cookie improvements ........ r75427 | benjamin.peterson | 2009-10-14 20:35:57 -0500 (Wed, 14 Oct 2009) | 1 line force floor division ........ r75428 | benjamin.peterson | 2009-10-14 20:39:21 -0500 (Wed, 14 Oct 2009) | 1 line silence -3 warnings about __hash__ ........ r75734 | benjamin.peterson | 2009-10-26 16:25:53 -0500 (Mon, 26 Oct 2009) | 2 lines warn on map(None, ...) with more than 2 arguments #7203 ........ r75735 | benjamin.peterson | 2009-10-26 16:28:25 -0500 (Mon, 26 Oct 2009) | 1 line remove unused result ........ r75736 | benjamin.peterson | 2009-10-26 16:29:02 -0500 (Mon, 26 Oct 2009) | 1 line using get() here is a bit pointless ........ r75865 | benjamin.peterson | 2009-10-27 15:49:00 -0500 (Tue, 27 Oct 2009) | 1 line explain reason for warning ........ r76059 | benjamin.peterson | 2009-11-02 11:43:47 -0600 (Mon, 02 Nov 2009) | 1 line tuples are no longer used for children ........ r76060 | benjamin.peterson | 2009-11-02 11:55:40 -0600 (Mon, 02 Nov 2009) | 1 line revert r76059; apparently some fixers rely on Leaf no () for children ........ r76061 | benjamin.peterson | 2009-11-02 12:06:17 -0600 (Mon, 02 Nov 2009) | 1 line make fix_tuple_params keep the tree valid #7253 ........ ................
2009-11-02 14:16:28 -04:00
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 stashed:
yield stashed
stashed = None
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 (COMMENT, comment_token,
(lnum, pos), (lnum, pos + len(comment_token)), line)
yield (NL, line[nl_pos:],
(lnum, nl_pos), (lnum, len(line)), line)
else:
yield ((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 (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]
if async_def and async_def_indent >= indents[-1]:
async_def = False
async_def_nl = False
async_def_indent = 0
yield (DEDENT, '', (lnum, pos), (lnum, pos), line)
if async_def and async_def_nl and async_def_indent >= indents[-1]:
async_def = False
async_def_nl = False
async_def_indent = 0
else: # continued statement
if not line:
2008-03-19 02:33:36 -03:00
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 string.digits or \
(initial == '.' and token != '.'): # ordinary number
yield (NUMBER, token, spos, epos, line)
elif initial in '\r\n':
newline = NEWLINE
if parenlev > 0:
newline = NL
elif async_def:
async_def_nl = True
if stashed:
yield stashed
stashed = None
yield (newline, token, spos, epos, line)
elif initial == '#':
assert not token.endswith("\n")
if stashed:
yield stashed
stashed = None
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
pos = endmatch.end(0)
token = line[start:pos]
if stashed:
yield stashed
stashed = None
yield (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
if stashed:
yield stashed
stashed = None
yield (STRING, token, spos, epos, line)
elif initial.isidentifier(): # ordinary name
if token in ('async', 'await'):
if async_def:
yield (ASYNC if token == 'async' else AWAIT,
token, spos, epos, line)
continue
tok = (NAME, token, spos, epos, line)
if token == 'async' and not stashed:
stashed = tok
continue
if token in ('def', 'for'):
if (stashed
and stashed[0] == NAME
and stashed[1] == 'async'):
if token == 'def':
async_def = True
async_def_indent = indents[-1]
yield (ASYNC, stashed[1],
stashed[2], stashed[3],
stashed[4])
stashed = None
if stashed:
yield stashed
stashed = None
yield tok
elif initial == '\\': # continued stmt
# This yield is new; needed for better idempotency:
if stashed:
yield stashed
stashed = None
yield (NL, token, spos, (lnum, pos), line)
continued = 1
else:
if initial in '([{': parenlev = parenlev + 1
elif initial in ')]}': parenlev = parenlev - 1
if stashed:
yield stashed
stashed = None
yield (OP, token, spos, epos, line)
else:
yield (ERRORTOKEN, line[pos],
(lnum, pos), (lnum, pos+1), line)
pos = pos + 1
if stashed:
yield stashed
stashed = None
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
import sys
if len(sys.argv) > 1: tokenize(open(sys.argv[1]).readline)
else: tokenize(sys.stdin.readline)