##// END OF EJS Templates
discovery-helper: use reflink copy if available...
discovery-helper: use reflink copy if available A reflink copy will copy the files "as usual" but keep using the same data block underneath. This is only supported by "copy on write" file system like btrfs or zfs. This will achieve similar performance that the existing hardlink clone that Mercurial performs with the same initial space saving. However, it will behave better on revlogs start being touch by strip. Instead of duplicating all data in the touched revlogs, only the block actually affected by the strip will be duplicated. This save a lot of space when building many variants of large repositories. The --reflink=always flag make sure the `cp` call fails if reflink copies are not supported. Falling back to local clone.

File last commit:

r39139:da130c5c default
r42094:cae3f7e3 default
Show More
byteify-strings.py
230 lines | 8.0 KiB | text/x-python | PythonLexer
/ contrib / byteify-strings.py
Yuya Nishihara
byteify-strings: add basic command interface
r38404 #!/usr/bin/env python3
#
Yuya Nishihara
byteify-strings: fork py3 code transformer to make it a standalone command...
r38403 # byteify-strings.py - transform string literals to be Python 3 safe
#
# Copyright 2015 Gregory Szorc <gregory.szorc@gmail.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
from __future__ import absolute_import
Yuya Nishihara
byteify-strings: add basic command interface
r38404 import argparse
Yuya Nishihara
byteify-strings: add --inplace option to write back result
r38405 import contextlib
import errno
import os
Yuya Nishihara
byteify-strings: add basic command interface
r38404 import sys
Yuya Nishihara
byteify-strings: add --inplace option to write back result
r38405 import tempfile
Yuya Nishihara
byteify-strings: fork py3 code transformer to make it a standalone command...
r38403 import token
import tokenize
Yuya Nishihara
byteify-strings: try to preserve column alignment
r38409 def adjusttokenpos(t, ofs):
"""Adjust start/end column of the given token"""
return t._replace(start=(t.start[0], t.start[1] + ofs),
end=(t.end[0], t.end[1] + ofs))
Yuya Nishihara
byteify-strings: remove superfluous "if True" block
r38410 def replacetokens(tokens, opts):
"""Transform a stream of tokens from raw to Python 3.
Returns a generator of possibly rewritten tokens.
The input token list may be mutated as part of processing. However,
its changes do not necessarily match the output token stream.
"""
sysstrtokens = set()
Yuya Nishihara
byteify-strings: fork py3 code transformer to make it a standalone command...
r38403
Yuya Nishihara
byteify-strings: remove superfluous "if True" block
r38410 # The following utility functions access the tokens list and i index of
# the for i, t enumerate(tokens) loop below
def _isop(j, *o):
"""Assert that tokens[j] is an OP with one of the given values"""
try:
return tokens[j].type == token.OP and tokens[j].string in o
except IndexError:
return False
Yuya Nishihara
byteify-strings: fork py3 code transformer to make it a standalone command...
r38403
Yuya Nishihara
byteify-strings: remove superfluous "if True" block
r38410 def _findargnofcall(n):
"""Find arg n of a call expression (start at 0)
Returns index of the first token of that argument, or None if
there is not that many arguments.
Assumes that token[i + 1] is '('.
Yuya Nishihara
byteify-strings: do not rewrite system string literals to u''...
r38408
Yuya Nishihara
byteify-strings: remove superfluous "if True" block
r38410 """
nested = 0
for j in range(i + 2, len(tokens)):
if _isop(j, ')', ']', '}'):
# end of call, tuple, subscription or dict / set
nested -= 1
if nested < 0:
return None
elif n == 0:
# this is the starting position of arg
return j
elif _isop(j, '(', '[', '{'):
nested += 1
elif _isop(j, ',') and nested == 0:
n -= 1
Yuya Nishihara
byteify-strings: fork py3 code transformer to make it a standalone command...
r38403
Yuya Nishihara
byteify-strings: remove superfluous "if True" block
r38410 return None
def _ensuresysstr(j):
"""Make sure the token at j is a system string
Yuya Nishihara
byteify-strings: fork py3 code transformer to make it a standalone command...
r38403
Yuya Nishihara
byteify-strings: remove superfluous "if True" block
r38410 Remember the given token so the string transformer won't add
the byte prefix.
Yuya Nishihara
byteify-strings: fork py3 code transformer to make it a standalone command...
r38403
Yuya Nishihara
byteify-strings: remove superfluous "if True" block
r38410 Ignores tokens that are not strings. Assumes bounds checking has
already been done.
Yuya Nishihara
byteify-strings: fork py3 code transformer to make it a standalone command...
r38403
Yuya Nishihara
byteify-strings: remove superfluous "if True" block
r38410 """
st = tokens[j]
if st.type == token.STRING and st.string.startswith(("'", '"')):
sysstrtokens.add(st)
Yuya Nishihara
byteify-strings: fork py3 code transformer to make it a standalone command...
r38403
Yuya Nishihara
byteify-strings: remove superfluous "if True" block
r38410 coldelta = 0 # column increment for new opening parens
coloffset = -1 # column offset for the current line (-1: TBD)
parens = [(0, 0, 0)] # stack of (line, end-column, column-offset)
for i, t in enumerate(tokens):
# Compute the column offset for the current line, such that
# the current line will be aligned to the last opening paren
# as before.
if coloffset < 0:
if t.start[1] == parens[-1][1]:
coloffset = parens[-1][2]
elif t.start[1] + 1 == parens[-1][1]:
# fix misaligned indent of s/util.Abort/error.Abort/
coloffset = parens[-1][2] + (parens[-1][1] - t.start[1])
else:
coloffset = 0
Yuya Nishihara
byteify-strings: fork py3 code transformer to make it a standalone command...
r38403
Yuya Nishihara
byteify-strings: remove superfluous "if True" block
r38410 # Reset per-line attributes at EOL.
if t.type in (token.NEWLINE, tokenize.NL):
yield adjusttokenpos(t, coloffset)
coldelta = 0
coloffset = -1
continue
# Remember the last paren position.
if _isop(i, '(', '[', '{'):
parens.append(t.end + (coloffset + coldelta,))
elif _isop(i, ')', ']', '}'):
parens.pop()
Yuya Nishihara
byteify-strings: fork py3 code transformer to make it a standalone command...
r38403
Yuya Nishihara
byteify-strings: remove superfluous "if True" block
r38410 # Convert most string literals to byte literals. String literals
# in Python 2 are bytes. String literals in Python 3 are unicode.
# Most strings in Mercurial are bytes and unicode strings are rare.
# Rather than rewrite all string literals to use ``b''`` to indicate
# byte strings, we apply this token transformer to insert the ``b``
# prefix nearly everywhere.
if t.type == token.STRING and t not in sysstrtokens:
s = t.string
Yuya Nishihara
byteify-strings: try to preserve column alignment
r38409
Yuya Nishihara
byteify-strings: remove superfluous "if True" block
r38410 # Preserve docstrings as string literals. This is inconsistent
# with regular unprefixed strings. However, the
# "from __future__" parsing (which allows a module docstring to
# exist before it) doesn't properly handle the docstring if it
# is b''' prefixed, leading to a SyntaxError. We leave all
# docstrings as unprefixed to avoid this. This means Mercurial
# components touching docstrings need to handle unicode,
# unfortunately.
if s[0:3] in ("'''", '"""'):
Yuya Nishihara
byteify-strings: try to preserve column alignment
r38409 yield adjusttokenpos(t, coloffset)
continue
Yuya Nishihara
byteify-strings: remove superfluous "if True" block
r38410 # If the first character isn't a quote, it is likely a string
# prefixing character (such as 'b', 'u', or 'r'. Ignore.
if s[0] not in ("'", '"'):
yield adjusttokenpos(t, coloffset)
Yuya Nishihara
byteify-strings: fork py3 code transformer to make it a standalone command...
r38403 continue
Yuya Nishihara
byteify-strings: remove superfluous "if True" block
r38410 # String literal. Prefix to make a b'' string.
yield adjusttokenpos(t._replace(string='b%s' % t.string),
coloffset)
coldelta += 1
continue
Yuya Nishihara
byteify-strings: fork py3 code transformer to make it a standalone command...
r38403
Yuya Nishihara
byteify-strings: remove superfluous "if True" block
r38410 # This looks like a function call.
if t.type == token.NAME and _isop(i + 1, '('):
fn = t.string
# *attr() builtins don't accept byte strings to 2nd argument.
if (fn in ('getattr', 'setattr', 'hasattr', 'safehasattr') and
not _isop(i - 1, '.')):
arg1idx = _findargnofcall(1)
if arg1idx is not None:
_ensuresysstr(arg1idx)
Yuya Nishihara
byteify-strings: fork py3 code transformer to make it a standalone command...
r38403
Yuya Nishihara
byteify-strings: remove superfluous "if True" block
r38410 # .encode() and .decode() on str/bytes/unicode don't accept
# byte strings on Python 3.
elif fn in ('encode', 'decode') and _isop(i - 1, '.'):
for argn in range(2):
argidx = _findargnofcall(argn)
if argidx is not None:
_ensuresysstr(argidx)
Yuya Nishihara
byteify-strings: fork py3 code transformer to make it a standalone command...
r38403
Yuya Nishihara
byteify-strings: remove superfluous "if True" block
r38410 # It changes iteritems/values to items/values as they are not
# present in Python 3 world.
elif opts['dictiter'] and fn in ('iteritems', 'itervalues'):
yield adjusttokenpos(t._replace(string=fn[4:]), coloffset)
continue
Yuya Nishihara
byteify-strings: fork py3 code transformer to make it a standalone command...
r38403
Yuya Nishihara
byteify-strings: prevent "__name__ == '__main__'" from being transformed...
r39139 # Looks like "if __name__ == '__main__'".
if (t.type == token.NAME and t.string == '__name__'
and _isop(i + 1, '==')):
_ensuresysstr(i + 2)
Yuya Nishihara
byteify-strings: remove superfluous "if True" block
r38410 # Emit unmodified token.
yield adjusttokenpos(t, coloffset)
Yuya Nishihara
byteify-strings: add basic command interface
r38404
Yuya Nishihara
byteify-strings: do not rewrite iteritems() and itervalues() by default...
r38407 def process(fin, fout, opts):
Yuya Nishihara
byteify-strings: add basic command interface
r38404 tokens = tokenize.tokenize(fin.readline)
Yuya Nishihara
byteify-strings: do not rewrite iteritems() and itervalues() by default...
r38407 tokens = replacetokens(list(tokens), opts)
Yuya Nishihara
byteify-strings: add basic command interface
r38404 fout.write(tokenize.untokenize(tokens))
Yuya Nishihara
byteify-strings: add --inplace option to write back result
r38405 def tryunlink(fname):
try:
os.unlink(fname)
except OSError as err:
if err.errno != errno.ENOENT:
raise
@contextlib.contextmanager
def editinplace(fname):
n = os.path.basename(fname)
d = os.path.dirname(fname)
fp = tempfile.NamedTemporaryFile(prefix='.%s-' % n, suffix='~', dir=d,
delete=False)
try:
yield fp
fp.close()
if os.name == 'nt':
tryunlink(fname)
os.rename(fp.name, fname)
finally:
fp.close()
tryunlink(fp.name)
Yuya Nishihara
byteify-strings: add basic command interface
r38404 def main():
ap = argparse.ArgumentParser()
Yuya Nishihara
byteify-strings: add --inplace option to write back result
r38405 ap.add_argument('-i', '--inplace', action='store_true', default=False,
help='edit files in place')
Yuya Nishihara
byteify-strings: do not rewrite iteritems() and itervalues() by default...
r38407 ap.add_argument('--dictiter', action='store_true', default=False,
help='rewrite iteritems() and itervalues()'),
Yuya Nishihara
byteify-strings: add basic command interface
r38404 ap.add_argument('files', metavar='FILE', nargs='+', help='source file')
args = ap.parse_args()
Yuya Nishihara
byteify-strings: do not rewrite iteritems() and itervalues() by default...
r38407 opts = {
'dictiter': args.dictiter,
}
Yuya Nishihara
byteify-strings: add basic command interface
r38404 for fname in args.files:
Yuya Nishihara
byteify-strings: add --inplace option to write back result
r38405 if args.inplace:
with editinplace(fname) as fout:
with open(fname, 'rb') as fin:
Yuya Nishihara
byteify-strings: do not rewrite iteritems() and itervalues() by default...
r38407 process(fin, fout, opts)
Yuya Nishihara
byteify-strings: add --inplace option to write back result
r38405 else:
with open(fname, 'rb') as fin:
fout = sys.stdout.buffer
Yuya Nishihara
byteify-strings: do not rewrite iteritems() and itervalues() by default...
r38407 process(fin, fout, opts)
Yuya Nishihara
byteify-strings: add basic command interface
r38404
if __name__ == '__main__':
main()