summaryrefslogtreecommitdiffstats
path: root/Lib/tokenize.py
diff options
context:
space:
mode:
authorBenjamin Peterson <benjamin@python.org>2009-11-13 02:29:35 (GMT)
committerBenjamin Peterson <benjamin@python.org>2009-11-13 02:29:35 (GMT)
commit8f6713f46d774942beb7984792a7a4c8666aab9a (patch)
tree4e47b228f3b5ad0a2d155b76c3da18e0f195b538 /Lib/tokenize.py
parentba8cfdad9427ba330bfa3ffbb97a2ec52360e95f (diff)
downloadcpython-8f6713f46d774942beb7984792a7a4c8666aab9a.zip
cpython-8f6713f46d774942beb7984792a7a4c8666aab9a.tar.gz
cpython-8f6713f46d774942beb7984792a7a4c8666aab9a.tar.bz2
Merged revisions 76235 via svnmerge from
svn+ssh://pythondev@svn.python.org/python/branches/py3k ................ r76235 | benjamin.peterson | 2009-11-12 20:25:08 -0600 (Thu, 12 Nov 2009) | 170 lines Merged revisions 75149,75260-75263,75265-75267,75292,75300,75376,75405,75429-75433,75437,75445,75501,75551,75572,75589-75591,75657,75742,75868,75952-75957,76057,76105,76139,76143,76162,76223 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r75149 | gregory.p.smith | 2009-09-29 16:56:31 -0500 (Tue, 29 Sep 2009) | 3 lines Mention issue6972 in extractall docs about overwriting things outside of the supplied path. ........ r75260 | andrew.kuchling | 2009-10-05 16:24:20 -0500 (Mon, 05 Oct 2009) | 1 line Wording fix ........ r75261 | andrew.kuchling | 2009-10-05 16:24:35 -0500 (Mon, 05 Oct 2009) | 1 line Fix narkup ........ r75262 | andrew.kuchling | 2009-10-05 16:25:03 -0500 (Mon, 05 Oct 2009) | 1 line Document 'skip' parameter to constructor ........ r75263 | andrew.kuchling | 2009-10-05 16:25:35 -0500 (Mon, 05 Oct 2009) | 1 line Note side benefit of socket.create_connection() ........ r75265 | andrew.kuchling | 2009-10-05 17:31:11 -0500 (Mon, 05 Oct 2009) | 1 line Reword sentence ........ r75266 | andrew.kuchling | 2009-10-05 17:32:48 -0500 (Mon, 05 Oct 2009) | 1 line Use standard comma punctuation; reword some sentences in the docs ........ r75267 | andrew.kuchling | 2009-10-05 17:42:56 -0500 (Mon, 05 Oct 2009) | 1 line Backport r73983: Document the thousands separator. ........ r75292 | benjamin.peterson | 2009-10-08 22:11:36 -0500 (Thu, 08 Oct 2009) | 1 line death to old CVS keyword ........ r75300 | benjamin.peterson | 2009-10-09 16:48:14 -0500 (Fri, 09 Oct 2009) | 1 line fix some coding style ........ r75376 | benjamin.peterson | 2009-10-11 20:26:07 -0500 (Sun, 11 Oct 2009) | 1 line platform we don't care about ........ r75405 | neil.schemenauer | 2009-10-14 12:17:14 -0500 (Wed, 14 Oct 2009) | 4 lines Issue #1754094: Improve the stack depth calculation in the compiler. There should be no other effect than a small decrease in memory use. Patch by Christopher Tur Lesniewski-Laas. ........ r75429 | benjamin.peterson | 2009-10-14 20:47:28 -0500 (Wed, 14 Oct 2009) | 1 line pep8ify if blocks ........ r75430 | benjamin.peterson | 2009-10-14 20:49:37 -0500 (Wed, 14 Oct 2009) | 1 line use floor division and add a test that exercises the tabsize codepath ........ r75431 | benjamin.peterson | 2009-10-14 20:56:25 -0500 (Wed, 14 Oct 2009) | 1 line change test to what I intended ........ r75432 | benjamin.peterson | 2009-10-14 22:05:39 -0500 (Wed, 14 Oct 2009) | 1 line some cleanups ........ r75433 | benjamin.peterson | 2009-10-14 22:06:55 -0500 (Wed, 14 Oct 2009) | 1 line make inspect.isabstract() always return a boolean; add a test for it, too #7069 ........ r75437 | benjamin.peterson | 2009-10-15 10:44:46 -0500 (Thu, 15 Oct 2009) | 1 line only clear a module's __dict__ if the module is the only one with a reference to it #7140 ........ r75445 | vinay.sajip | 2009-10-16 09:06:44 -0500 (Fri, 16 Oct 2009) | 1 line Issue #7120: logging: Removed import of multiprocessing which is causing crash in GAE. ........ r75501 | antoine.pitrou | 2009-10-18 13:37:11 -0500 (Sun, 18 Oct 2009) | 3 lines Add a comment about unreachable code, and fix a typo ........ r75551 | benjamin.peterson | 2009-10-19 22:14:10 -0500 (Mon, 19 Oct 2009) | 1 line use property api ........ r75572 | benjamin.peterson | 2009-10-20 16:55:17 -0500 (Tue, 20 Oct 2009) | 1 line clarify buffer arg #7178 ........ r75589 | benjamin.peterson | 2009-10-21 21:26:47 -0500 (Wed, 21 Oct 2009) | 1 line whitespace ........ r75590 | benjamin.peterson | 2009-10-21 21:36:47 -0500 (Wed, 21 Oct 2009) | 1 line rewrite to be nice to other implementations ........ r75591 | benjamin.peterson | 2009-10-21 21:50:38 -0500 (Wed, 21 Oct 2009) | 4 lines rewrite for style, clarify, and comments Also, use the hasattr() like scheme of allowing BaseException exceptions through. ........ r75657 | antoine.pitrou | 2009-10-24 07:41:27 -0500 (Sat, 24 Oct 2009) | 3 lines Fix compilation error in debug mode. ........ r75742 | benjamin.peterson | 2009-10-26 17:51:16 -0500 (Mon, 26 Oct 2009) | 1 line use 'is' instead of id() ........ r75868 | benjamin.peterson | 2009-10-27 15:59:18 -0500 (Tue, 27 Oct 2009) | 1 line test expect base classes ........ r75952 | georg.brandl | 2009-10-29 15:38:32 -0500 (Thu, 29 Oct 2009) | 1 line Use the correct function name in docstring. ........ r75953 | georg.brandl | 2009-10-29 15:39:50 -0500 (Thu, 29 Oct 2009) | 1 line Remove mention of the old -X command line switch. ........ r75954 | georg.brandl | 2009-10-29 15:53:00 -0500 (Thu, 29 Oct 2009) | 1 line Use constants instead of magic integers for test result. Do not re-run with --verbose3 for environment changing tests. ........ r75955 | georg.brandl | 2009-10-29 15:54:03 -0500 (Thu, 29 Oct 2009) | 1 line Use a single style for all the docstrings in the math module. ........ r75956 | georg.brandl | 2009-10-29 16:16:34 -0500 (Thu, 29 Oct 2009) | 1 line I do not think the "railroad" program mentioned is still available. ........ r75957 | georg.brandl | 2009-10-29 16:44:56 -0500 (Thu, 29 Oct 2009) | 1 line Fix constant name. ........ r76057 | benjamin.peterson | 2009-11-02 09:06:45 -0600 (Mon, 02 Nov 2009) | 1 line prevent a rather unlikely segfault ........ r76105 | georg.brandl | 2009-11-04 01:38:12 -0600 (Wed, 04 Nov 2009) | 1 line #7259: show correct equivalent for operator.i* operations in docstring; fix minor issues in operator docs. ........ r76139 | benjamin.peterson | 2009-11-06 19:04:38 -0600 (Fri, 06 Nov 2009) | 1 line spelling ........ r76143 | georg.brandl | 2009-11-07 02:26:07 -0600 (Sat, 07 Nov 2009) | 1 line #7271: fix typo. ........ r76162 | benjamin.peterson | 2009-11-08 22:10:53 -0600 (Sun, 08 Nov 2009) | 1 line discuss how to use -p ........ r76223 | georg.brandl | 2009-11-12 02:29:46 -0600 (Thu, 12 Nov 2009) | 1 line Give the profile module a module directive. ........ ................
Diffstat (limited to 'Lib/tokenize.py')
-rw-r--r--Lib/tokenize.py33
1 files changed, 20 insertions, 13 deletions
diff --git a/Lib/tokenize.py b/Lib/tokenize.py
index fb58c6b..9d2a6bb 100644
--- a/Lib/tokenize.py
+++ b/Lib/tokenize.py
@@ -23,15 +23,15 @@ __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 x[0] != '_'] + ["COMMENT", "tokenize",
- "detect_encoding", "NL", "untokenize", "ENCODING", "TokenInfo"]
+__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
@@ -407,7 +407,7 @@ def _tokenize(readline, encoding):
if encoding is not None:
line = line.decode(encoding)
- lnum = lnum + 1
+ lnum += 1
pos, max = 0, len(line)
if contstr: # continued string
@@ -435,12 +435,17 @@ def _tokenize(readline, encoding):
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] == ' ':
+ 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] == '#':
@@ -516,13 +521,15 @@ def _tokenize(readline, encoding):
elif initial == '\\': # continued stmt
continued = 1
else:
- if initial in '([{': parenlev = parenlev + 1
- elif initial in ')]}': parenlev = parenlev - 1
+ 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 = pos + 1
+ pos += 1
for indent in indents[1:]: # pop remaining indent levels
yield TokenInfo(DEDENT, '', (lnum, 0), (lnum, 0), '')