view tests/autodiff.py @ 33388:0823f0983eaa

convert: transcode CVS log messages by specified encoding (issue5597)

Converting from CVS to Mercurial assumes that CVS log messages in "cvs
rlog" output are encoded in UTF-8 (or basic Latin-1). But cvs itself
is usually unaware of encoding of log messages, in practice.

Therefore, if there are commits, of which log message is encoded in
other than UTF-8, log message of corresponded revisions in the
converted repository will be broken.

To avoid such broken log messages, this patch transcodes CVS log
messages by encoding specified via "convert.cvsps.logencoding"
configuration.

This patch accepts multiple encoding for convenience, because
"multiple encoding mixed in a repository" easily occurs. For example,
UTF-8 (recent POSIX), cp932 (Windows), and EUC-JP (legacy POSIX) are
well known encoding for Japanese.

# Extension dedicated to test patch.diff() upgrade modes

from __future__ import absolute_import

from mercurial import (
    error,
    patch,
    registrar,
    scmutil,
)

cmdtable = {}
command = registrar.command(cmdtable)

@command('autodiff',
    [('', 'git', '', 'git upgrade mode (yes/no/auto/warn/abort)')],
    '[OPTION]... [FILE]...')
def autodiff(ui, repo, *pats, **opts):
    diffopts = patch.difffeatureopts(ui, opts)
    git = opts.get('git', 'no')
    brokenfiles = set()
    losedatafn = None
    if git in ('yes', 'no'):
        diffopts.git = git == 'yes'
        diffopts.upgrade = False
    elif git == 'auto':
        diffopts.git = False
        diffopts.upgrade = True
    elif git == 'warn':
        diffopts.git = False
        diffopts.upgrade = True
        def losedatafn(fn=None, **kwargs):
            brokenfiles.add(fn)
            return True
    elif git == 'abort':
        diffopts.git = False
        diffopts.upgrade = True
        def losedatafn(fn=None, **kwargs):
            raise error.Abort('losing data for %s' % fn)
    else:
        raise error.Abort('--git must be yes, no or auto')

    node1, node2 = scmutil.revpair(repo, [])
    m = scmutil.match(repo[node2], pats, opts)
    it = patch.diff(repo, node1, node2, match=m, opts=diffopts,
                    losedatafn=losedatafn)
    for chunk in it:
        ui.write(chunk)
    for fn in sorted(brokenfiles):
        ui.write(('data lost for: %s\n' % fn))