view tests/test-filelog.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.

#!/usr/bin/env python
"""
Tests the behavior of filelog w.r.t. data starting with '\1\n'
"""
from __future__ import absolute_import, print_function

from mercurial.node import (
    hex,
    nullid,
)
from mercurial import (
    hg,
    ui as uimod,
)

myui = uimod.ui.load()
repo = hg.repository(myui, path='.', create=True)

fl = repo.file('foobar')

def addrev(text, renamed=False):
    if renamed:
        # data doesn't matter. Just make sure filelog.renamed() returns True
        meta = {'copyrev': hex(nullid), 'copy': 'bar'}
    else:
        meta = {}

    lock = t = None
    try:
        lock = repo.lock()
        t = repo.transaction('commit')
        node = fl.add(text, meta, t, 0, nullid, nullid)
        return node
    finally:
        if t:
            t.close()
        if lock:
            lock.release()

def error(text):
    print('ERROR: ' + text)

textwith = '\1\nfoo'
without = 'foo'

node = addrev(textwith)
if not textwith == fl.read(node):
    error('filelog.read for data starting with \\1\\n')
if fl.cmp(node, textwith) or not fl.cmp(node, without):
    error('filelog.cmp for data starting with \\1\\n')
if fl.size(0) != len(textwith):
    error('FIXME: This is a known failure of filelog.size for data starting '
        'with \\1\\n')

node = addrev(textwith, renamed=True)
if not textwith == fl.read(node):
    error('filelog.read for a renaming + data starting with \\1\\n')
if fl.cmp(node, textwith) or not fl.cmp(node, without):
    error('filelog.cmp for a renaming + data starting with \\1\\n')
if fl.size(1) != len(textwith):
    error('filelog.size for a renaming + data starting with \\1\\n')

print('OK.')