view hgext/win32text.py @ 9424:799373ff2554

highlight: fixes garbled text in non-UTF-8 environment

This patch treats all files inside repository as encoded by
locale's encoding when pygmentize.

We can assume that most files are written in locale's encoding,
but current implementation treats them as UTF-8.
So there's no way to specify the encoding of files.

Current implementation, db7557359636 (issue1341):
1. Convert original `text`, which is treated as UTF-8, to locale's encoding.
   `encoding.tolocal()` is the method to convert from internal UTF-8 to local.
   If original `text` is not UTF-8, e.g. Japanese EUC-JP, some characters
   become garbled here.
2. pygmentize, with no UnicodeDecodeError.

This patch:
1. Convert original `text`, which is treated as locale's encoding, to unicode.
   Pygments prefers unicode object than raw str. [1]_
   If original `text` is not encoded by locale's encoding, some characters
   become garbled here.
2. pygmentize, also with no UnicodeDecodeError :)
3. Convert unicode back to raw str, which is encoded by locale's.

.. [1] http://pygments.org/docs/unicode/

# win32text.py - LF <-> CRLF/CR translation utilities for Windows/Mac users
#
#  Copyright 2005, 2007-2009 Matt Mackall <[e-mail]> and others
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2, incorporated herein by reference.

'''perform automatic newline conversion

To perform automatic newline conversion, use:

[extensions]
hgext.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 mercurial.i18n import _
from mercurial.node import short
from mercurial import util
import re

# 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'}

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:
    #   http://mercurial.selenic.com/bts/issue302
    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.join('hgrc')))

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')

def macdumbdecode(s, cmd, **kwargs):
    checknewline(s, '\r', **kwargs)
    return s.replace('\n', '\r')

def macdumbencode(s, cmd):
    return s.replace('\r', '\n')

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

def macdecode(s, cmd, **kwargs):
    if not util.binary(s):
        return macdumbdecode(s, cmd, **kwargs)
    return s

def macencode(s, cmd):
    if not util.binary(s):
        return macdumbencode(s, cmd)
    return s

_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):
        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':
        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'
                  'hgext.win32text =\n'
                  '[encode]\n'
                  '** = %sencode:\n'
                  '[decode]\n'
                  '** = %sdecode:\n') % (crlf, crlf, filter, filter))
    return halt

def forbidcrlf(ui, repo, hooktype, node, **kwargs):
    return forbidnewline(ui, repo, hooktype, node, '\r\n', **kwargs)

def forbidcr(ui, repo, hooktype, node, **kwargs):
    return forbidnewline(ui, repo, hooktype, node, '\r', **kwargs)

def reposetup(ui, repo):
    if not repo.local():
        return
    for name, fn in _filters.iteritems():
        repo.adddatafilter(name, fn)