tests/test-filelog

encoding: improve handling of buggy getpreferredencoding() on Mac OS X

Prior to version 2.7, calling locale.getpreferredencoding() would
always return 'mac-roman' on Mac OS X. Previously, this was handled by
a call to locale.setlocale(). Unfortunately, Python 2.6.5 and older
have a bug where isspace() would incorrectly report True for 0x85 and
0xa0 after such a call.

In order to fix this, we replace the previous _encodingfixup mapping
to an _encodingfixers mapping. Rather than mapping encodings to their
replacement, it maps them to a function returning the
replacement. This allows us to provide an simplified implementation of
getpreferredencoding() which extracts the expected encoding and
restores the locale.

This fix is based on a patch originally submitted by Martijn Pieters
as well as feedback from Brodie Rao.

#!/usr/bin/env python
"""
Tests the behaviour of filelog w.r.t. data starting with '\1\n'
"""
from mercurial import ui, hg
from mercurial.node import nullid, hex

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

fl = repo.file('foobar')

def addrev(text, renamed=False):
    if renamed:
        # data doesnt matter. Just make sure filelog.renamed() returns True
        meta = dict(copyrev=hex(nullid), copy='bar')
    else:
        meta = {}

    t = repo.transaction('commit')
    try:
        node = fl.add(text, meta, t, 0, nullid, nullid)
        return node
    finally:
        t.close()

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.'