view hgext/parentrevspec.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/

# Mercurial extension to make it easy to refer to the parent of a revision
#
# Copyright (C) 2007 Alexis S. L. Carvalho <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2, incorporated herein by reference.

'''interpret suffixes to refer to ancestor revisions

This extension allows you to use git-style suffixes to refer to the
ancestors of a specific revision.

For example, if you can refer to a revision as "foo", then:

- foo^N = Nth parent of foo
  foo^0 = foo
  foo^1 = first parent of foo
  foo^2 = second parent of foo
  foo^  = foo^1

- foo~N = Nth first grandparent of foo
  foo~0 = foo
  foo~1 = foo^1 = foo^ = first parent of foo
  foo~2 = foo^1^1 = foo^^ = first parent of first parent of foo
'''
from mercurial import error

def reposetup(ui, repo):
    if not repo.local():
        return

    class parentrevspecrepo(repo.__class__):
        def lookup(self, key):
            try:
                _super = super(parentrevspecrepo, self)
                return _super.lookup(key)
            except error.RepoError:
                pass

            circ = key.find('^')
            tilde = key.find('~')
            if circ < 0 and tilde < 0:
                raise
            elif circ >= 0 and tilde >= 0:
                end = min(circ, tilde)
            else:
                end = max(circ, tilde)

            cl = self.changelog
            base = key[:end]
            try:
                node = _super.lookup(base)
            except error.RepoError:
                # eek - reraise the first error
                return _super.lookup(key)

            rev = cl.rev(node)
            suffix = key[end:]
            i = 0
            while i < len(suffix):
                # foo^N => Nth parent of foo
                # foo^0 == foo
                # foo^1 == foo^ == 1st parent of foo
                # foo^2 == 2nd parent of foo
                if suffix[i] == '^':
                    j = i + 1
                    p = cl.parentrevs(rev)
                    if j < len(suffix) and suffix[j].isdigit():
                        j += 1
                        n = int(suffix[i+1:j])
                        if n > 2 or n == 2 and p[1] == -1:
                            raise
                    else:
                        n = 1
                    if n:
                        rev = p[n - 1]
                    i = j
                # foo~N => Nth first grandparent of foo
                # foo~0 = foo
                # foo~1 = foo^1 == foo^ == 1st parent of foo
                # foo~2 = foo^1^1 == foo^^ == 1st parent of 1st parent of foo
                elif suffix[i] == '~':
                    j = i + 1
                    while j < len(suffix) and suffix[j].isdigit():
                        j += 1
                    if j == i + 1:
                        raise
                    n = int(suffix[i+1:j])
                    for k in xrange(n):
                        rev = cl.parentrevs(rev)[0]
                    i = j
                else:
                    raise
            return cl.node(rev)

    repo.__class__ = parentrevspecrepo