Added latest reindent.py file

This commit is contained in:
Daniel Neuhäuser
2010-05-17 02:26:31 +02:00
parent 765871c86c
commit ad9055868e
2 changed files with 53 additions and 47 deletions

View File

@@ -1,16 +1,14 @@
#! /usr/bin/env python
# Released to the public domain, by Tim Peters, 03 October 2000.
# -B option added by Georg Brandl, 2006.
"""reindent [-d][-r][-v] [ path ... ]
-d (--dryrun) Dry run. Analyze, but don't make any changes to files.
-r (--recurse) Recurse. Search for all .py files in subdirectories too.
-B (--no-backup) Don't write .bak backup files.
-v (--verbose) Verbose. Print informative msgs; else only names of \
changed files.
-h (--help) Help. Print this usage information and exit.
-d (--dryrun) Dry run. Analyze, but don't make any changes to, files.
-r (--recurse) Recurse. Search for all .py files in subdirectories too.
-n (--nobackup) No backup. Does not make a ".bak" file before reindenting.
-v (--verbose) Verbose. Print informative msgs; else no output.
-h (--help) Help. Print this usage information and exit.
Change Python (.py) files to use 4-space indents and no hard tab characters.
Also trim excess spaces and tabs from ends of lines, and remove empty lines
@@ -34,29 +32,30 @@ resulting .py file won't change it again).
The hard part of reindenting is figuring out what to do with comment
lines. So long as the input files get a clean bill of health from
tabnanny.py, reindent should do a good job.
The backup file is a copy of the one that is being reindented. The ".bak"
file is generated with shutil.copy(), but some corner cases regarding
user/group and permissions could leave the backup file more readable that
you'd prefer. You can always use the --nobackup option to prevent this.
"""
__version__ = "1"
import tokenize
import os
import os, shutil
import sys
verbose = 0
recurse = 0
dryrun = 0
no_backup = 0
if sys.version_info >= (3, 0):
def tokens(readline, tokeneater):
for token in tokenize.tokenize(readline):
tokeneater(*token)
def b(s):
return s.encode('utf-8')
yield tokeneater(*token)
else:
tokens = tokenize.tokenize
b = str
verbose = 0
recurse = 0
dryrun = 0
makebackup = True
def usage(msg=None):
if msg is not None:
@@ -72,12 +71,10 @@ def errprint(*args):
def main():
import getopt
global verbose, recurse, dryrun, no_backup
global verbose, recurse, dryrun, makebackup
try:
opts, args = getopt.getopt(sys.argv[1:], "drvhB",
["dryrun", "recurse", "verbose", "help",
"no-backup"])
opts, args = getopt.getopt(sys.argv[1:], "drnvh",
["dryrun", "recurse", "nobackup", "verbose", "help"])
except getopt.error, msg:
usage(msg)
return
@@ -86,10 +83,10 @@ def main():
dryrun += 1
elif o in ('-r', '--recurse'):
recurse += 1
elif o in ('-n', '--nobackup'):
makebackup = False
elif o in ('-v', '--verbose'):
verbose += 1
elif o in ('-B', '--no-backup'):
no_backup += 1
elif o in ('-h', '--help'):
usage()
return
@@ -109,7 +106,8 @@ def check(file):
for name in names:
fullname = os.path.join(file, name)
if ((recurse and os.path.isdir(fullname) and
not os.path.islink(fullname))
not os.path.islink(fullname) and
not os.path.split(fullname)[1].startswith("."))
or name.lower().endswith(".py")):
check(fullname)
return
@@ -117,7 +115,7 @@ def check(file):
if verbose:
print "checking", file, "...",
try:
f = open(file, 'rb')
f = open(file)
except IOError, msg:
errprint("%s: I/O Error: %s" % (file, str(msg)))
return
@@ -129,26 +127,35 @@ def check(file):
print "changed."
if dryrun:
print "But this is a dry run, so leaving it alone."
else:
print "reindented", file, \
(dryrun and "(dry run => not really)" or "")
if not dryrun:
if not no_backup:
bak = file + ".bak"
if os.path.exists(bak):
os.remove(bak)
os.rename(file, bak)
bak = file + ".bak"
if makebackup:
shutil.copyfile(file, bak)
if verbose:
print "renamed", file, "to", bak
f = open(file, "wb")
print "backed up", file, "to", bak
f = open(file, "w")
r.write(f)
f.close()
if verbose:
print "wrote new", file
return True
else:
if verbose:
print "unchanged."
return False
def _rstrip(line, JUNK='\n \t'):
"""Return line stripped of trailing spaces, tabs, newlines.
Note that line.rstrip() instead also strips sundry control characters,
but at least one known Emacs user expects to keep junk like that, not
mentioning Barry by name or anything <wink>.
"""
i = len(line)
while i > 0 and line[i-1] in JUNK:
i -= 1
return line[:i]
class Reindenter:
@@ -162,7 +169,7 @@ class Reindenter:
# File lines, rstripped & tab-expanded. Dummy at start is so
# that we can use tokenize's 1-based line numbering easily.
# Note that a line is all-blank iff it's "\n".
self.lines = [line.rstrip(b('\n \t')).expandtabs() + b("\n")
self.lines = [_rstrip(line).expandtabs() + "\n"
for line in self.raw]
self.lines.insert(0, None)
self.index = 1 # index into self.lines of next line
@@ -177,7 +184,7 @@ class Reindenter:
tokens(self.getline, self.tokeneater)
# Remove trailing empty lines.
lines = self.lines
while lines and lines[-1] == b("\n"):
while lines and lines[-1] == "\n":
lines.pop()
# Sentinel.
stats = self.stats
@@ -233,10 +240,10 @@ class Reindenter:
else:
for line in lines[thisstmt:nextstmt]:
if diff > 0:
if line == b("\n"):
if line == "\n":
after.append(line)
else:
after.append(b(" ") * diff + line)
after.append(" " * diff + line)
else:
remove = min(getlspace(line), -diff)
after.append(line[remove:])
@@ -248,20 +255,19 @@ class Reindenter:
# Line-getter for tokenize.
def getline(self):
if self.index >= len(self.lines):
line = b("")
line = ""
else:
line = self.lines[self.index]
self.index += 1
return line
# Line-eater for tokenize.
def tokeneater(self, type, token, scell, end, line,
def tokeneater(self, type, token, (sline, scol), end, line,
INDENT=tokenize.INDENT,
DEDENT=tokenize.DEDENT,
NEWLINE=tokenize.NEWLINE,
COMMENT=tokenize.COMMENT,
NL=tokenize.NL):
sline, scol = scell
if type == NEWLINE:
# A program statement, or ENDMARKER, will eventually follow,
@@ -297,7 +303,7 @@ class Reindenter:
# Count number of leading blanks.
def getlspace(line):
i, n = 0, len(line)
while i < n and line[i] == b(" "):
while i < n and line[i] == " ":
i += 1
return i