view tests/test-duplicateoptions.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.

from __future__ import absolute_import, print_function
import os
from mercurial import (
    commands,
    extensions,
    ui as uimod,
)

ignore = {'highlight', 'win32text', 'factotum'}

if os.name != 'nt':
    ignore.add('win32mbcs')

disabled = [ext for ext in extensions.disabled().keys() if ext not in ignore]

hgrc = open(os.environ["HGRCPATH"], 'w')
hgrc.write('[extensions]\n')

for ext in disabled:
    hgrc.write(ext + '=\n')

hgrc.close()

u = uimod.ui.load()
extensions.loadall(u)

globalshort = set()
globallong = set()
for option in commands.globalopts:
    option[0] and globalshort.add(option[0])
    option[1] and globallong.add(option[1])

for cmd, entry in commands.table.iteritems():
    seenshort = globalshort.copy()
    seenlong = globallong.copy()
    for option in entry[1]:
        if (option[0] and option[0] in seenshort) or \
           (option[1] and option[1] in seenlong):
            print("command '" + cmd + "' has duplicate option " + str(option))
        seenshort.add(option[0])
        seenlong.add(option[1])