view tests/test-walkrepo.py @ 11297:d320e70442a5

replace Python standard textwrap by MBCS sensitive one for i18n text

Mercurial has problem around text wrapping/filling in MBCS encoding
environment, because standard 'textwrap' module of Python can not
treat it correctly. It splits byte sequence for one character into two
lines.

According to unicode specification, "east asian width" classifies
characters into:

   W(ide), N(arrow), F(ull-width), H(alf-width), A(mbiguous)


W/N/F/H can be always recognized as 2/1/2/1 bytes in byte sequence,
but 'A' can not. Size of 'A' depends on language in which it is used.

Unicode specification says:

   If the context(= language) cannot be established reliably they
   should be treated as narrow characters by default

but many of class 'A' characters are full-width, at least, in Japanese
environment.

So, this patch treats class 'A' characters as full-width always for
safety wrapping.

This patch focuses only on MBCS safe-ness, not on writing/printing
rule strict wrapping for each languages

MBCS sensitive textwrap class is originally implemented
by ITO Nobuaki <[e-mail]>.

import os
from mercurial import hg, ui
from mercurial.util import walkrepos
from os import mkdir, chdir
from os.path import join as pjoin

u = ui.ui()
sym = hasattr(os, 'symlink') and hasattr(os.path, 'samestat')

hg.repository(u, 'top1', create=1)
mkdir('subdir')
chdir('subdir')
hg.repository(u, 'sub1', create=1)
mkdir('subsubdir')
chdir('subsubdir')
hg.repository(u, 'subsub1', create=1)
chdir(os.path.pardir)
if sym:
    os.symlink(os.path.pardir, 'circle')
    os.symlink(pjoin('subsubdir', 'subsub1'), 'subsub1')

def runtest():
    reposet = frozenset(walkrepos('.', followsym=True))
    if sym and (len(reposet) != 3):
        print "reposet = %r" % (reposet,)
        print "Found %d repositories when I should have found 3" % (len(reposet),)
    if (not sym) and (len(reposet) != 2):
        print "reposet = %r" % (reposet,)
        print "Found %d repositories when I should have found 2" % (len(reposet),)
    sub1set = frozenset((pjoin('.', 'sub1'),
                         pjoin('.', 'circle', 'subdir', 'sub1')))
    if len(sub1set & reposet) != 1:
        print "sub1set = %r" % (sub1set,)
        print "reposet = %r" % (reposet,)
        print "sub1set and reposet should have exactly one path in common."
    sub2set = frozenset((pjoin('.', 'subsub1'),
                         pjoin('.', 'subsubdir', 'subsub1')))
    if len(sub2set & reposet) != 1:
        print "sub2set = %r" % (sub2set,)
        print "reposet = %r" % (reposet,)
        print "sub1set and reposet should have exactly one path in common."
    sub3 = pjoin('.', 'circle', 'top1')
    if sym and not (sub3 in reposet):
        print "reposet = %r" % (reposet,)
        print "Symbolic links are supported and %s is not in reposet" % (sub3,)

runtest()
if sym:
    # Simulate not having symlinks.
    del os.path.samestat
    sym = False
    runtest()