posix: add extended support for OS X path folding
OS X does the following transformation on paths for comparisons:
a) 8-bit strings are decoded as UTF-8 to UTF-16
b) undecodable bytes are percent-escaped
c) accented characters are converted to NFD decomposed form, approximately
d) characters are converted to _lowercase_ using internal tables
Both (c) and (d) are done using internal tables that vary from release
to release and match Unicode specs to greater or lesser extent. We
approximate these functions using Python's internal Unicode data.
With this change, Mercurial will (in almost all cases) match OS X
folding and not report unknown file aliases for files in UTF-8 or
other encodings.
from mercurial import demandimport
demandimport.enable()
import re
rsub = re.sub
def f(obj):
l = repr(obj)
l = rsub("0x[0-9a-fA-F]+", "0x?", l)
l = rsub("from '.*'", "from '?'", l)
l = rsub("'<[a-z]*>'", "'<whatever>'", l)
return l
import os
print "os =", f(os)
print "os.system =", f(os.system)
print "os =", f(os)
from mercurial import util
print "util =", f(util)
print "util.system =", f(util.system)
print "util =", f(util)
print "util.system =", f(util.system)
import re as fred
print "fred =", f(fred)
import sys as re
print "re =", f(re)
print "fred =", f(fred)
print "fred.sub =", f(fred.sub)
print "fred =", f(fred)
print "re =", f(re)
print "re.stderr =", f(re.stderr)
print "re =", f(re)