sapling/edenscm/hgext/win32text.py

224 lines
6.4 KiB
Python
Raw Normal View History

2008-04-03 15:41:31 +04:00
# win32text.py - LF <-> CRLF/CR translation utilities for Windows/Mac users
#
2009-04-26 03:49:12 +04:00
# Copyright 2005, 2007-2009 Matt Mackall <mpm@selenic.com> and others
#
# This software may be used and distributed according to the terms of the
2010-01-20 07:20:08 +03:00
# GNU General Public License version 2 or any later version.
"""perform automatic newline conversion (DEPRECATED)
Deprecation: The win32text extension requires each user to configure
the extension again and again for each clone since the configuration
is not copied when cloning.
We have therefore made the ``eol`` as an alternative. The ``eol``
uses a version controlled file for its configuration and each clone
will therefore use the right settings from the start.
To perform automatic newline conversion, use::
[extensions]
win32text =
[encode]
** = cleverencode:
# or ** = macencode:
[decode]
** = cleverdecode:
# or ** = macdecode:
If not doing conversion, to make sure you do not commit CRLF/CR by accident::
[hooks]
pretxncommit.crlf = python:hgext.win32text.forbidcrlf
# or pretxncommit.cr = python:hgext.win32text.forbidcr
To do the same check on a server to prevent CRLF/CR from being
pushed or pulled::
[hooks]
pretxnchangegroup.crlf = python:hgext.win32text.forbidcrlf
# or pretxnchangegroup.cr = python:hgext.win32text.forbidcr
"""
from __future__ import absolute_import
import re
from edenscm.mercurial import registrar, util
from edenscm.mercurial.i18n import _
from edenscm.mercurial.node import short
# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
# be specifying the version(s) of Mercurial they are tested with, or
# leave the attribute unspecified.
testedwith = "ships-with-hg-core"
configtable = {}
configitem = registrar.configitem(configtable)
configitem("win32text", "warn", default=True)
# regexp for single LF without CR preceding.
re_single_lf = re.compile("(^|[^\r])\n", re.MULTILINE)
newlinestr = {"\r\n": "CRLF", "\r": "CR"}
filterstr = {"\r\n": "clever", "\r": "mac"}
2008-04-03 15:41:31 +04:00
flake8: enable F821 check Summary: This check is useful and detects real errors (ex. fbconduit). Unfortunately `arc lint` will run it with both py2 and py3 so a lot of py2 builtins will still be warned. I didn't find a clean way to disable py3 check. So this diff tries to fix them. For `xrange`, the change was done by a script: ``` import sys import redbaron headertypes = {'comment', 'endl', 'from_import', 'import', 'string', 'assignment', 'atomtrailers'} xrangefix = '''try: xrange(0) except NameError: xrange = range ''' def isxrange(x): try: return x[0].value == 'xrange' except Exception: return False def main(argv): for i, path in enumerate(argv): print('(%d/%d) scanning %s' % (i + 1, len(argv), path)) content = open(path).read() try: red = redbaron.RedBaron(content) except Exception: print(' warning: failed to parse') continue hasxrange = red.find('atomtrailersnode', value=isxrange) hasxrangefix = 'xrange = range' in content if hasxrangefix or not hasxrange: print(' no need to change') continue # find a place to insert the compatibility statement changed = False for node in red: if node.type in headertypes: continue # node.insert_before is an easier API, but it has bugs changing # other "finally" and "except" positions. So do the insert # manually. # # node.insert_before(xrangefix) line = node.absolute_bounding_box.top_left.line - 1 lines = content.splitlines(1) content = ''.join(lines[:line]) + xrangefix + ''.join(lines[line:]) changed = True break if changed: # "content" is faster than "red.dumps()" open(path, 'w').write(content) print(' updated') if __name__ == "__main__": sys.exit(main(sys.argv[1:])) ``` For other py2 builtins that do not have a py3 equivalent, some `# noqa` were added as a workaround for now. Reviewed By: DurhamG Differential Revision: D6934535 fbshipit-source-id: 546b62830af144bc8b46788d2e0fd00496838939
2018-02-10 04:31:44 +03:00
try:
xrange(0)
except NameError:
xrange = range
2008-04-03 15:41:31 +04:00
def checknewline(s, newline, ui=None, repo=None, filename=None):
# warn if already has 'newline' in repository.
# it might cause unexpected eol conversion.
# see issue 302:
# https://bz.mercurial-scm.org/302
2008-04-03 15:41:31 +04:00
if newline in s and ui and filename and repo:
ui.warn(
_(
"WARNING: %s already has %s line endings\n"
"and does not need EOL conversion by the win32text plugin.\n"
"Before your next commit, please reconsider your "
"encode/decode settings in \nMercurial.ini or %s.\n"
)
% (filename, newlinestr[newline], repo.localvfs.join("hgrc"))
)
2008-04-03 15:41:31 +04:00
def dumbdecode(s, cmd, **kwargs):
checknewline(s, "\r\n", **kwargs)
# replace single LF to CRLF
return re_single_lf.sub("\\1\r\n", s)
def dumbencode(s, cmd):
return s.replace("\r\n", "\n")
2008-04-03 15:41:31 +04:00
def macdumbdecode(s, cmd, **kwargs):
checknewline(s, "\r", **kwargs)
return s.replace("\n", "\r")
2008-04-03 15:41:31 +04:00
def macdumbencode(s, cmd):
return s.replace("\r", "\n")
2008-04-03 15:41:31 +04:00
def cleverdecode(s, cmd, **kwargs):
if not util.binary(s):
return dumbdecode(s, cmd, **kwargs)
return s
def cleverencode(s, cmd):
if not util.binary(s):
return dumbencode(s, cmd)
return s
2008-04-03 15:41:31 +04:00
def macdecode(s, cmd, **kwargs):
if not util.binary(s):
2008-04-05 21:33:34 +04:00
return macdumbdecode(s, cmd, **kwargs)
return s
2008-04-03 15:41:31 +04:00
2008-04-03 15:41:31 +04:00
def macencode(s, cmd):
if not util.binary(s):
2008-04-05 21:33:34 +04:00
return macdumbencode(s, cmd)
return s
2008-04-03 15:41:31 +04:00
_filters = {
"dumbdecode:": dumbdecode,
"dumbencode:": dumbencode,
"cleverdecode:": cleverdecode,
"cleverencode:": cleverencode,
"macdumbdecode:": macdumbdecode,
"macdumbencode:": macdumbencode,
"macdecode:": macdecode,
"macencode:": macencode,
}
def forbidnewline(ui, repo, hooktype, node, newline, **kwargs):
halt = False
seen = set()
# we try to walk changesets in reverse order from newest to
# oldest, so that if we see a file multiple times, we take the
# newest version as canonical. this prevents us from blocking a
# changegroup that contains an unacceptable commit followed later
# by a commit that fixes the problem.
tip = repo["tip"]
for rev in xrange(len(repo) - 1, repo[node].rev() - 1, -1):
2008-06-26 23:35:46 +04:00
c = repo[rev]
for f in c.files():
if f in seen or f not in tip or f not in c:
continue
seen.add(f)
data = c[f].data()
if not util.binary(data) and newline in data:
if not halt:
ui.warn(
_(
"attempt to commit or push text file(s) "
"using %s line endings\n"
)
% newlinestr[newline]
)
ui.warn(_("in %s: %s\n") % (short(c.node()), f))
halt = True
if halt and hooktype == "pretxnchangegroup":
2008-04-03 15:41:31 +04:00
crlf = newlinestr[newline].lower()
filter = filterstr[newline]
ui.warn(
_(
"\nTo prevent this mistake in your local repository,\n"
"add to Mercurial.ini or .hg/hgrc:\n"
"\n"
"[hooks]\n"
"pretxncommit.%s = python:hgext.win32text.forbid%s\n"
"\n"
"and also consider adding:\n"
"\n"
"[extensions]\n"
"win32text =\n"
"[encode]\n"
"** = %sencode:\n"
"[decode]\n"
"** = %sdecode:\n"
)
% (crlf, crlf, filter, filter)
)
return halt
2008-04-03 15:41:31 +04:00
def forbidcrlf(ui, repo, hooktype, node, **kwargs):
return forbidnewline(ui, repo, hooktype, node, "\r\n", **kwargs)
2008-04-03 15:41:31 +04:00
def forbidcr(ui, repo, hooktype, node, **kwargs):
return forbidnewline(ui, repo, hooktype, node, "\r", **kwargs)
2008-04-03 15:41:31 +04:00
def reposetup(ui, repo):
if not repo.local():
return
for name, fn in _filters.iteritems():
repo.adddatafilter(name, fn)
def extsetup(ui):
# deprecated config: win32text.warn
if ui.configbool("win32text", "warn"):
ui.warn(
_(
"win32text is deprecated: "
"https://mercurial-scm.org/wiki/Win32TextExtension\n"
)
)