store: eliminate one level of lambda functions on _hybridencode

mercurial/store.py

@@ -1,449 +1,451 b''
 # store.py - repository store handling for Mercurial
 #
 # Copyright 2008 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from i18n import _
 import osutil, scmutil, util
 import os, stat, errno
 
 _sha = util.sha1
 
 # This avoids a collision between a file named foo and a dir named
 # foo.i or foo.d
 def encodedir(path):
     '''
     >>> encodedir('data/foo.i')
     'data/foo.i'
     >>> encodedir('data/foo.i/bla.i')
     'data/foo.i.hg/bla.i'
     >>> encodedir('data/foo.i.hg/bla.i')
     'data/foo.i.hg.hg/bla.i'
     '''
     return (path
             .replace(".hg/", ".hg.hg/")
             .replace(".i/", ".i.hg/")
             .replace(".d/", ".d.hg/"))
 
 def decodedir(path):
     '''
     >>> decodedir('data/foo.i')
     'data/foo.i'
     >>> decodedir('data/foo.i.hg/bla.i')
     'data/foo.i/bla.i'
     >>> decodedir('data/foo.i.hg.hg/bla.i')
     'data/foo.i.hg/bla.i'
     '''
     if ".hg/" not in path:
         return path
     return (path
             .replace(".d.hg/", ".d/")
             .replace(".i.hg/", ".i/")
             .replace(".hg.hg/", ".hg/"))
 
 def _buildencodefun():
     '''
     >>> enc, dec = _buildencodefun()
 
     >>> enc('nothing/special.txt')
     'nothing/special.txt'
     >>> dec('nothing/special.txt')
     'nothing/special.txt'
 
     >>> enc('HELLO')
     '_h_e_l_l_o'
     >>> dec('_h_e_l_l_o')
     'HELLO'
 
     >>> enc('hello:world?')
     'hello~3aworld~3f'
     >>> dec('hello~3aworld~3f')
     'hello:world?'
 
     >>> enc('the\x07quick\xADshot')
     'the~07quick~adshot'
     >>> dec('the~07quick~adshot')
     'the\\x07quick\\xadshot'
     '''
     e = '_'
     winreserved = [ord(x) for x in '\\:*?"<>|']
     cmap = dict([(chr(x), chr(x)) for x in xrange(127)])
     for x in (range(32) + range(126, 256) + winreserved):
         cmap[chr(x)] = "~%02x" % x
     for x in range(ord("A"), ord("Z")+1) + [ord(e)]:
         cmap[chr(x)] = e + chr(x).lower()
     dmap = {}
     for k, v in cmap.iteritems():
         dmap[v] = k
     def decode(s):
         i = 0
         while i < len(s):
             for l in xrange(1, 4):
                 try:
                     yield dmap[s[i:i + l]]
                     i += l
                     break
                 except KeyError:
                     pass
             else:
                 raise KeyError
     return (lambda s: "".join([cmap[c] for c in encodedir(s)]),
             lambda s: decodedir("".join(list(decode(s)))))
 
 encodefilename, decodefilename = _buildencodefun()
 
 def _buildlowerencodefun():
     '''
     >>> f = _buildlowerencodefun()
     >>> f('nothing/special.txt')
     'nothing/special.txt'
     >>> f('HELLO')
     'hello'
     >>> f('hello:world?')
     'hello~3aworld~3f'
     >>> f('the\x07quick\xADshot')
     'the~07quick~adshot'
     '''
     winreserved = [ord(x) for x in '\\:*?"<>|']
     cmap = dict([(chr(x), chr(x)) for x in xrange(127)])
     for x in (range(32) + range(126, 256) + winreserved):
         cmap[chr(x)] = "~%02x" % x
     for x in range(ord("A"), ord("Z")+1):
         cmap[chr(x)] = chr(x).lower()
     return lambda s: "".join([cmap[c] for c in s])
 
 lowerencode = _buildlowerencodefun()
 
 # Windows reserved names: con, prn, aux, nul, com1..com9, lpt1..lpt9
 _winres3 = ('aux', 'con', 'prn', 'nul') # length 3
 _winres4 = ('com', 'lpt')               # length 4 (with trailing 1..9)
 def _auxencode(path, dotencode):
     '''
     Encodes filenames containing names reserved by Windows or which end in
     period or space. Does not touch other single reserved characters c.
     Specifically, c in '\\:*?"<>|' or ord(c) <= 31 are *not* encoded here.
     Additionally encodes space or period at the beginning, if dotencode is
     True. Parameter path is assumed to be all lowercase.
     A segment only needs encoding if a reserved name appears as a
     basename (e.g. "aux", "aux.foo"). A directory or file named "foo.aux"
     doesn't need encoding.
 
     >>> s = '.foo/aux.txt/txt.aux/con/prn/nul/foo.'
     >>> _auxencode(s.split('/'), True)
     ['~2efoo', 'au~78.txt', 'txt.aux', 'co~6e', 'pr~6e', 'nu~6c', 'foo~2e']
     >>> s = '.com1com2/lpt9.lpt4.lpt1/conprn/com0/lpt0/foo.'
     >>> _auxencode(s.split('/'), False)
     ['.com1com2', 'lp~749.lpt4.lpt1', 'conprn', 'com0', 'lpt0', 'foo~2e']
     >>> _auxencode(['foo. '], True)
     ['foo.~20']
     >>> _auxencode([' .foo'], True)
     ['~20.foo']
     '''
     for i, n in enumerate(path):
         if not n:
             continue
         if dotencode and n[0] in '. ':
             n = "~%02x" % ord(n[0]) + n[1:]
             path[i] = n
         else:
             l = n.find('.')
             if l == -1:
                 l = len(n)
             if ((l == 3 and n[:3] in _winres3) or
                 (l == 4 and n[3] <= '9' and n[3] >= '1'
                         and n[:3] in _winres4)):
                 # encode third letter ('aux' -> 'au~78')
                 ec = "~%02x" % ord(n[2])
                 n = n[0:2] + ec + n[3:]
                 path[i] = n
         if n[-1] in '. ':
             # encode last period or space ('foo...' -> 'foo..~2e')
             path[i] = n[:-1] + "~%02x" % ord(n[-1])
     return path
 
 _maxstorepathlen = 120
 _dirprefixlen = 8
 _maxshortdirslen = 8 * (_dirprefixlen + 1) - 4
-def _hybridencode(path, auxencode):
+def _hybridencode(path, dotencode):
     '''encodes path with a length limit
 
     Encodes all paths that begin with 'data/', according to the following.
 
     Default encoding (reversible):
 
     Encodes all uppercase letters 'X' as '_x'. All reserved or illegal
     characters are encoded as '~xx', where xx is the two digit hex code
     of the character (see encodefilename).
     Relevant path components consisting of Windows reserved filenames are
     masked by encoding the third character ('aux' -> 'au~78', see auxencode).
 
     Hashed encoding (not reversible):
 
     If the default-encoded path is longer than _maxstorepathlen, a
     non-reversible hybrid hashing of the path is done instead.
     This encoding uses up to _dirprefixlen characters of all directory
     levels of the lowerencoded path, but not more levels than can fit into
     _maxshortdirslen.
     Then follows the filler followed by the sha digest of the full path.
     The filler is the beginning of the basename of the lowerencoded path
     (the basename is everything after the last path separator). The filler
     is as long as possible, filling in characters from the basename until
     the encoded path has _maxstorepathlen characters (or all chars of the
     basename have been taken).
     The extension (e.g. '.i' or '.d') is preserved.
 
     The string 'data/' at the beginning is replaced with 'dh/', if the hashed
     encoding was used.
     '''
-    res = '/'.join(auxencode(encodefilename(path).split('/')))
+    ef = encodefilename(path).split('/')
+    res = '/'.join(_auxencode(ef, dotencode))
     if len(res) > _maxstorepathlen:
         path = encodedir(path)
         digest = _sha(path).hexdigest()
-        parts = auxencode(lowerencode(path).split('/')[1:])
+        le = lowerencode(path).split('/')[1:]
+        parts = _auxencode(le, dotencode)
         basename = parts[-1]
         _root, ext = os.path.splitext(basename)
         sdirs = []
         sdirslen = 0
         for p in parts[:-1]:
             d = p[:_dirprefixlen]
             if d[-1] in '. ':
                 # Windows can't access dirs ending in period or space
                 d = d[:-1] + '_'
             if sdirslen == 0:
                 t = len(d)
             else:
                 t = sdirslen + 1 + len(d)
                 if t > _maxshortdirslen:
                     break
             sdirs.append(d)
             sdirslen = t
         dirs = '/'.join(sdirs)
         if len(dirs) > 0:
             dirs += '/'
         res = 'dh/' + dirs + digest + ext
         spaceleft = _maxstorepathlen - len(res)
         if spaceleft > 0:
             filler = basename[:spaceleft]
             res = 'dh/' + dirs + filler + digest + ext
     return res
 
 def _calcmode(path):
     try:
         # files in .hg/ will be created using this mode
         mode = os.stat(path).st_mode
             # avoid some useless chmods
         if (0777 & ~util.umask) == (0777 & mode):
             mode = None
     except OSError:
         mode = None
     return mode
 
 _data = ('data 00manifest.d 00manifest.i 00changelog.d 00changelog.i'
          ' phaseroots obsstore')
 
 class basicstore(object):
     '''base class for local repository stores'''
     def __init__(self, path, openertype):
         self.path = path
         self.createmode = _calcmode(path)
         op = openertype(self.path)
         op.createmode = self.createmode
         self.opener = scmutil.filteropener(op, encodedir)
 
     def join(self, f):
         return self.path + '/' + encodedir(f)
 
     def _walk(self, relpath, recurse):
         '''yields (unencoded, encoded, size)'''
         path = self.path
         if relpath:
             path += '/' + relpath
         striplen = len(self.path) + 1
         l = []
         if os.path.isdir(path):
             visit = [path]
             while visit:
                 p = visit.pop()
                 for f, kind, st in osutil.listdir(p, stat=True):
                     fp = p + '/' + f
                     if kind == stat.S_IFREG and f[-2:] in ('.d', '.i'):
                         n = util.pconvert(fp[striplen:])
                         l.append((decodedir(n), n, st.st_size))
                     elif kind == stat.S_IFDIR and recurse:
                         visit.append(fp)
         l.sort()
         return l
 
     def datafiles(self):
         return self._walk('data', True)
 
     def walk(self):
         '''yields (unencoded, encoded, size)'''
         # yield data files first
         for x in self.datafiles():
             yield x
         # yield manifest before changelog
         for x in reversed(self._walk('', False)):
             yield x
 
     def copylist(self):
         return ['requires'] + _data.split()
 
     def write(self):
         pass
 
 class encodedstore(basicstore):
     def __init__(self, path, openertype):
         self.path = path + '/store'
         self.createmode = _calcmode(self.path)
         op = openertype(self.path)
         op.createmode = self.createmode
         self.opener = scmutil.filteropener(op, encodefilename)
 
     def datafiles(self):
         for a, b, size in self._walk('data', True):
             try:
                 a = decodefilename(a)
             except KeyError:
                 a = None
             yield a, b, size
 
     def join(self, f):
         return self.path + '/' + encodefilename(f)
 
     def copylist(self):
         return (['requires', '00changelog.i'] +
                 ['store/' + f for f in _data.split()])
 
 class fncache(object):
     # the filename used to be partially encoded
     # hence the encodedir/decodedir dance
     def __init__(self, opener):
         self.opener = opener
         self.entries = None
         self._dirty = False
 
     def _load(self):
         '''fill the entries from the fncache file'''
         self._dirty = False
         try:
             fp = self.opener('fncache', mode='rb')
         except IOError:
             # skip nonexistent file
             self.entries = set()
             return
         self.entries = set(map(decodedir, fp.read().splitlines()))
         if '' in self.entries:
             fp.seek(0)
             for n, line in enumerate(fp):
                 if not line.rstrip('\n'):
                     t = _('invalid entry in fncache, line %s') % (n + 1)
                     raise util.Abort(t)
         fp.close()
 
     def _write(self, files, atomictemp):
         fp = self.opener('fncache', mode='wb', atomictemp=atomictemp)
         if files:
             fp.write('\n'.join(map(encodedir, files)) + '\n')
         fp.close()
         self._dirty = False
 
     def rewrite(self, files):
         self._write(files, False)
         self.entries = set(files)
 
     def write(self):
         if self._dirty:
             self._write(self.entries, True)
 
     def add(self, fn):
         if self.entries is None:
             self._load()
         if fn not in self.entries:
             self._dirty = True
             self.entries.add(fn)
 
     def __contains__(self, fn):
         if self.entries is None:
             self._load()
         return fn in self.entries
 
     def __iter__(self):
         if self.entries is None:
             self._load()
         return iter(self.entries)
 
 class _fncacheopener(scmutil.abstractopener):
     def __init__(self, op, fnc, encode):
         self.opener = op
         self.fncache = fnc
         self.encode = encode
 
     def _getmustaudit(self):
         return self.opener.mustaudit
 
     def _setmustaudit(self, onoff):
         self.opener.mustaudit = onoff
 
     mustaudit = property(_getmustaudit, _setmustaudit)
 
     def __call__(self, path, mode='r', *args, **kw):
         if mode not in ('r', 'rb') and path.startswith('data/'):
             self.fncache.add(path)
         return self.opener(self.encode(path), mode, *args, **kw)
 
 class fncachestore(basicstore):
     def __init__(self, path, openertype, encode):
         self.encode = encode
         self.path = path + '/store'
         self.pathsep = self.path + '/'
         self.createmode = _calcmode(self.path)
         op = openertype(self.path)
         op.createmode = self.createmode
         fnc = fncache(op)
         self.fncache = fnc
         self.opener = _fncacheopener(op, fnc, encode)
 
     def join(self, f):
         return self.pathsep + self.encode(f)
 
     def getsize(self, path):
         return os.stat(self.pathsep + path).st_size
 
     def datafiles(self):
         rewrite = False
         existing = []
         for f in sorted(self.fncache):
             ef = self.encode(f)
             try:
                 yield f, ef, self.getsize(ef)
                 existing.append(f)
             except OSError, err:
                 if err.errno != errno.ENOENT:
                     raise
                 # nonexistent entry
                 rewrite = True
         if rewrite:
             # rewrite fncache to remove nonexistent entries
             # (may be caused by rollback / strip)
             self.fncache.rewrite(existing)
 
     def copylist(self):
         d = ('data dh fncache phaseroots obsstore'
              ' 00manifest.d 00manifest.i 00changelog.d 00changelog.i')
         return (['requires', '00changelog.i'] +
                 ['store/' + f for f in d.split()])
 
     def write(self):
         self.fncache.write()
 
 def store(requirements, path, openertype):
     if 'store' in requirements:
         if 'fncache' in requirements:
-            auxencode = lambda f: _auxencode(f, 'dotencode' in requirements)
-            encode = lambda f: _hybridencode(f, auxencode)
+            de = 'dotencode' in requirements
+            encode = lambda f: _hybridencode(f, de)
             return fncachestore(path, openertype, encode)
         return encodedstore(path, openertype)
     return basicstore(path, openertype)

tests/test-hybridencode.py

@@ -1,454 +1,453 b''
 from mercurial import store
 
-auxencode = lambda f: store._auxencode(f, True)
-hybridencode = lambda f: store._hybridencode(f, auxencode)
+hybridencode = lambda f: store._hybridencode(f, True)
 
 enc = hybridencode # used for 'dotencode' repo format
 
 def show(s):
     print "A = '%s'" % s.encode("string_escape")
     print "B = '%s'" % enc(s).encode("string_escape")
     print
 
 show("data/abcdefghijklmnopqrstuvwxyz0123456789 !#%&'()+,-.;=[]^`{}")
 
 print "uppercase char X is encoded as _x"
 show("data/ABCDEFGHIJKLMNOPQRSTUVWXYZ")
 
 print "underbar is doubled"
 show("data/_")
 
 print "tilde is character-encoded"
 show("data/~")
 
 print "characters in ASCII code range 1..31"
 show('data/\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f'
           '\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f')
 
 print "characters in ASCII code range 126..255"
 show('data/\x7e\x7f'
           '\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f'
           '\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f')
 show('data/\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf'
           '\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf')
 show('data/\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf'
           '\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf')
 show('data/\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef'
           '\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff')
 
 print "Windows reserved characters"
 show('data/less <, greater >, colon :, double-quote ", backslash \\'
            ', pipe |, question-mark ?, asterisk *')
 
 print "encoding directories ending in .hg, .i or .d with '.hg' suffix"
 show('data/x.hg/x.i/x.d/foo')
 show('data/a.hg/a.i/a.d/foo')
 show('data/au.hg/au.i/au.d/foo')
 show('data/aux.hg/aux.i/aux.d/foo')
 show('data/auxy.hg/auxy.i/auxy.d/foo')
 
 print "but these are not encoded on *filenames*"
 show('data/foo/x.hg')
 show('data/foo/x.i')
 show('data/foo/x.d')
 show('data/foo/a.hg')
 show('data/foo/a.i')
 show('data/foo/a.d')
 show('data/foo/au.hg')
 show('data/foo/au.i')
 show('data/foo/au.d')
 show('data/foo/aux.hg')
 show('data/foo/aux.i')
 show('data/foo/aux.d')
 show('data/foo/auxy.hg')
 show('data/foo/auxy.i')
 show('data/foo/auxy.d')
 
 print "plain .hg, .i and .d directories have the leading dot encoded"
 show('data/.hg/.i/.d/foo')
 
 show('data/aux.bla/bla.aux/prn/PRN/lpt/com3/nul/coma/foo.NUL/normal.c.i')
 
 show('data/AUX/SECOND/X.PRN/FOURTH/FI:FTH/SIXTH/SEVENTH/EIGHTH/NINETH/'
      'TENTH/ELEVENTH/LOREMIPSUM.TXT.i')
 show('data/enterprise/openesbaddons/contrib-imola/corba-bc/netbeansplugin/'
      'wsdlExtension/src/main/java/META-INF/services/org.netbeans.modules'
      '.xml.wsdl.bindingsupport.spi.ExtensibilityElementTemplateProvider.i')
 show('data/AUX.THE-QUICK-BROWN-FOX-JU:MPS-OVER-THE-LAZY-DOG-THE-QUICK-'
      'BROWN-FOX-JUMPS-OVER-THE-LAZY-DOG.TXT.i')
 show('data/Project Planning/Resources/AnotherLongDirectoryName/'
      'Followedbyanother/AndAnother/AndThenAnExtremelyLongFileName.txt')
 show('data/Project.Planning/Resources/AnotherLongDirectoryName/'
      'Followedbyanother/AndAnother/AndThenAnExtremelyLongFileName.txt')
 show('data/foo.../foo   / /a./_. /__/.x../    bla/.FOO/something.i')
 
 show('data/c/co/com/com0/com1/com2/com3/com4/com5/com6/com7/com8/com9')
 show('data/C/CO/COM/COM0/COM1/COM2/COM3/COM4/COM5/COM6/COM7/COM8/COM9')
 show('data/c.x/co.x/com.x/com0.x/com1.x/com2.x/com3.x/com4.x/com5.x'
                                         '/com6.x/com7.x/com8.x/com9.x')
 show('data/x.c/x.co/x.com0/x.com1/x.com2/x.com3/x.com4/x.com5'
                                         '/x.com6/x.com7/x.com8/x.com9')
 show('data/cx/cox/comx/com0x/com1x/com2x/com3x/com4x/com5x'
                                             '/com6x/com7x/com8x/com9x')
 show('data/xc/xco/xcom0/xcom1/xcom2/xcom3/xcom4/xcom5'
                                             '/xcom6/xcom7/xcom8/xcom9')
 
 show('data/l/lp/lpt/lpt0/lpt1/lpt2/lpt3/lpt4/lpt5/lpt6/lpt7/lpt8/lpt9')
 show('data/L/LP/LPT/LPT0/LPT1/LPT2/LPT3/LPT4/LPT5/LPT6/LPT7/LPT8/LPT9')
 show('data/l.x/lp.x/lpt.x/lpt0.x/lpt1.x/lpt2.x/lpt3.x/lpt4.x/lpt5.x'
                                         '/lpt6.x/lpt7.x/lpt8.x/lpt9.x')
 show('data/x.l/x.lp/x.lpt/x.lpt0/x.lpt1/x.lpt2/x.lpt3/x.lpt4/x.lpt5'
                                         '/x.lpt6/x.lpt7/x.lpt8/x.lpt9')
 show('data/lx/lpx/lptx/lpt0x/lpt1x/lpt2x/lpt3x/lpt4x/lpt5x'
                                             '/lpt6x/lpt7x/lpt8x/lpt9x')
 show('data/xl/xlp/xlpt/xlpt0/xlpt1/xlpt2/xlpt3/xlpt4/xlpt5'
                                             '/xlpt6/xlpt7/xlpt8/xlpt9')
 
 show('data/con/p/pr/prn/a/au/aux/n/nu/nul')
 show('data/CON/P/PR/PRN/A/AU/AUX/N/NU/NUL')
 show('data/con.x/p.x/pr.x/prn.x/a.x/au.x/aux.x/n.x/nu.x/nul.x')
 show('data/x.con/x.p/x.pr/x.prn/x.a/x.au/x.aux/x.n/x.nu/x.nul')
 show('data/conx/px/prx/prnx/ax/aux/auxx/nx/nux/nulx')
 show('data/xcon/xp/xpr/xprn/xa/xau/xaux/xn/xnu/xnul')
 
 show('data/a./au./aux./auxy./aux.')
 show('data/c./co./con./cony./con.')
 show('data/p./pr./prn./prny./prn.')
 show('data/n./nu./nul./nuly./nul.')
 show('data/l./lp./lpt./lpt1./lpt1y./lpt1.')
 show('data/lpt9./lpt9y./lpt9.')
 show('data/com./com1./com1y./com1.')
 show('data/com9./com9y./com9.')
 
 show('data/a /au /aux /auxy /aux ')
 
 print "largest unhashed path"
 show('data/123456789-123456789-123456789-123456789-123456789-'
           'unhashed--xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12345')
 
 print "shortest hashed path"
 show('data/123456789-123456789-123456789-123456789-123456789-'
           'hashed----xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-123456')
 
 print "changing one char in part that's hashed away produces a different hash"
 show('data/123456789-123456789-123456789-123456789-123456789-'
           'hashed----xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxy-'
           '123456789-123456')
 
 print "uppercase hitting length limit due to encoding"
 show('data/A23456789-123456789-123456789-123456789-123456789-'
           'xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12345')
 show('data/Z23456789-123456789-123456789-123456789-123456789-'
           'xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12345')
 
 print "compare with lowercase not hitting limit"
 show('data/a23456789-123456789-123456789-123456789-123456789-'
           'xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12345')
 show('data/z23456789-123456789-123456789-123456789-123456789-'
           'xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12345')
 
 print "not hitting limit with any of these"
 show("data/abcdefghijklmnopqrstuvwxyz0123456789 !#%&'()+,-.;="
           "[]^`{}xxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-"
           "123456789-12345")
 
 print "underbar hitting length limit due to encoding"
 show('data/_23456789-123456789-123456789-123456789-123456789-'
           'xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12345')
 
 print "tilde hitting length limit due to encoding"
 show('data/~23456789-123456789-123456789-123456789-123456789-'
           'xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12345')
 
 print "Windows reserved characters hitting length limit"
 show('data/<23456789-123456789-123456789-123456789-123456789-'
           'xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12345')
 show('data/>23456789-123456789-123456789-123456789-123456789-'
           'xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12345')
 show('data/:23456789-123456789-123456789-123456789-123456789-'
           'xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12345')
 show('data/"23456789-123456789-123456789-123456789-123456789-'
           'xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12345')
 show('data/\\23456789-123456789-123456789-123456789-123456789-'
           'xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12345')
 show('data/|23456789-123456789-123456789-123456789-123456789-'
           'xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12345')
 show('data/?23456789-123456789-123456789-123456789-123456789-'
           'xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12345')
 show('data/*23456789-123456789-123456789-123456789-123456789-'
           'xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12345')
 
 print "initial space hitting length limit"
 show('data/ 23456789-123456789-123456789-123456789-123456789-'
           'xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12345')
 
 print "initial dot hitting length limit"
 show('data/.23456789-123456789-123456789-123456789-123456789-'
           'xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12345')
 
 print "trailing space in filename hitting length limit"
 show('data/123456789-123456789-123456789-123456789-123456789-'
           'xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-1234 ')
 
 print "trailing dot in filename hitting length limit"
 show('data/123456789-123456789-123456789-123456789-123456789-'
           'xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-1234.')
 
 print "initial space in directory hitting length limit"
 show('data/ x/456789-123456789-123456789-123456789-123456789-'
           'xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12345')
 
 print "initial dot in directory hitting length limit"
 show('data/.x/456789-123456789-123456789-123456789-123456789-'
           'xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12345')
 
 print "trailing space in directory hitting length limit"
 show('data/x /456789-123456789-123456789-123456789-123456789-'
           'xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12345')
 
 print "trailing dot in directory hitting length limit"
 show('data/x./456789-123456789-123456789-123456789-123456789-'
           'xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12345')
 
 print "with directories that need direncoding, hitting length limit"
 show('data/x.i/56789-123456789-123456789-123456789-123456789-'
           'xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12345')
 show('data/x.d/56789-123456789-123456789-123456789-123456789-'
           'xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12345')
 show('data/x.hg/5789-123456789-123456789-123456789-123456789-'
           'xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12345')
 
 print "Windows reserved filenames, hitting length limit"
 show('data/con/56789-123456789-123456789-123456789-123456789-'
           'xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12345')
 show('data/prn/56789-123456789-123456789-123456789-123456789-'
           'xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12345')
 show('data/aux/56789-123456789-123456789-123456789-123456789-'
           'xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12345')
 show('data/nul/56789-123456789-123456789-123456789-123456789-'
           'xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12345')
 show('data/com1/6789-123456789-123456789-123456789-123456789-'
           'xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12345')
 show('data/com9/6789-123456789-123456789-123456789-123456789-'
           'xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12345')
 show('data/lpt1/6789-123456789-123456789-123456789-123456789-'
           'xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12345')
 show('data/lpt9/6789-123456789-123456789-123456789-123456789-'
           'xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12345')
 
 print "non-reserved names, just not hitting limit"
 show('data/123456789-123456789-123456789-123456789-123456789-'
           '/com/com0/lpt/lpt0/-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12345')
 
 print "hashed path with largest untruncated 1st dir"
 show('data/12345678/-123456789-123456789-123456789-123456789-'
           'hashed----xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-123456')
 
 print "hashed path with smallest truncated 1st dir"
 show('data/123456789/123456789-123456789-123456789-123456789-'
           'hashed----xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-123456')
 
 print "hashed path with largest untruncated two dirs"
 show('data/12345678/12345678/9-123456789-123456789-123456789-'
           'hashed----xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-123456')
 
 print "hashed path with smallest truncated two dirs"
 show('data/123456789/123456789/123456789-123456789-123456789-'
           'hashed----xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-123456')
 
 print "hashed path with largest untruncated three dirs"
 show('data/12345678/12345678/12345678/89-123456789-123456789-'
           'hashed----xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-123456')
 
 print "hashed path with smallest truncated three dirs"
 show('data/123456789/123456789/123456789/123456789-123456789-'
           'hashed----xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-123456')
 
 print "hashed path with largest untruncated four dirs"
 show('data/12345678/12345678/12345678/12345678/789-123456789-'
           'hashed----xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-123456')
 
 print "hashed path with smallest truncated four dirs"
 show('data/123456789/123456789/123456789/123456789/123456789-'
           'hashed----xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-123456')
 
 print "hashed path with largest untruncated five dirs"
 show('data/12345678/12345678/12345678/12345678/12345678/6789-'
           'hashed----xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-123456')
 
 print "hashed path with smallest truncated five dirs"
 show('data/123456789/123456789/123456789/123456789/123456789/'
           'hashed----xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-123456')
 
 print "hashed path with largest untruncated six dirs"
 show('data/12345678/12345678/12345678/12345678/12345678/12345'
           '678/ed----xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-123456')
 
 print "hashed path with smallest truncated six dirs"
 show('data/123456789/123456789/123456789/123456789/123456789/'
           '123456789/xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-123456')
 
 print "hashed path with largest untruncated seven dirs"
 show('data/12345678/12345678/12345678/12345678/12345678/12345'
           '678/12345678/xxxxxx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-123456')
 
 print "hashed path with smallest truncated seven dirs"
 show('data/123456789/123456789/123456789/123456789/123456789/'
           '123456789/123456789/xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-123456')
 
 print "hashed path with largest untruncated eight dirs"
 print "(directory 8 is dropped because it hits _maxshortdirslen)"
 show('data/12345678/12345678/12345678/12345678/12345678/12345'
           '678/12345678/12345678/xxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-123456')
 
 print "hashed path with smallest truncated eight dirs"
 print "(directory 8 is dropped because it hits _maxshortdirslen)"
 show('data/123456789/123456789/123456789/123456789/123456789/'
           '123456789/123456789/123456789/xxxxxxxxx-xxxxxxxxx-'
           '123456789-123456')
 
 print "hashed path with largest non-dropped directory 8"
 print "(just not hitting the _maxshortdirslen boundary)"
 show('data/12345678/12345678/12345678/12345678/12345678/12345'
           '678/12345678/12345/-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-123456')
 
 print "...adding one truncated char to dir 1..7 won't drop dir 8"
 show('data/12345678x/12345678/12345678/12345678/12345678/12345'
           '678/12345678/12345/xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-123456')
 show('data/12345678/12345678x/12345678/12345678/12345678/12345'
           '678/12345678/12345/xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-123456')
 show('data/12345678/12345678/12345678x/12345678/12345678/12345'
           '678/12345678/12345/xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-123456')
 show('data/12345678/12345678/12345678/12345678x/12345678/12345'
           '678/12345678/12345/xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-123456')
 show('data/12345678/12345678/12345678/12345678/12345678x/12345'
           '678/12345678/12345/xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-123456')
 show('data/12345678/12345678/12345678/12345678/12345678/12345'
           '678x/12345678/12345/xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-123456')
 show('data/12345678/12345678/12345678/12345678/12345678/12345'
           '678/12345678x/12345/xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-123456')
 
 print "hashed path with shortest dropped directory 8"
 print "(just hitting the _maxshortdirslen boundary)"
 show('data/12345678/12345678/12345678/12345678/12345678/12345'
           '678/12345678/123456/xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-123456')
 
 print "hashed path that drops dir 8 due to dot or space at end is"
 print "encoded, and thus causing to hit _maxshortdirslen"
 show('data/12345678/12345678/12345678/12345678/12345678/12345'
           '678/12345678/1234./-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-123456')
 show('data/12345678/12345678/12345678/12345678/12345678/12345'
           '678/12345678/1234 /-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-123456')
 
 print "... with dir 8 short enough for encoding"
 show('data/12345678/12345678/12345678/12345678/12345678/12345'
           '678/12345678/12./xx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-123456')
 show('data/12345678/12345678/12345678/12345678/12345678/12345'
           '678/12345678/12 /xx-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-123456')
 
 print "extensions are replicated on hashed paths (unbounded!)"
 show('data/12345678/12345678/12345678/12345678/12345678/12345'
           '678/12345678/12345/-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12.345')
 show('data/12345678/12345678/12345678/12345678/12345678/12345'
           '678/12345678/12345/-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12.3456')
 show('data/12345678/12345678/12345678/12345678/12345678/12345'
           '678/12345678/12345/-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12.34567')
 show('data/12345678/12345678/12345678/12345678/12345678/12345'
           '678/12345678/12345/-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12.345678')
 show('data/12345678/12345678/12345678/12345678/12345678/12345'
           '678/12345678/12345/-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12.3456789')
 show('data/12345678/12345678/12345678/12345678/12345678/12345'
           '678/12345678/12345/-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12.3456789-')
 show('data/12345678/12345678/12345678/12345678/12345678/12345'
           '678/12345678/12345/-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12.3456789-1')
 show('data/12345678/12345678/12345678/12345678/12345678/12345'
           '678/12345678/12345/-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12.3456789-12')
 show('data/12345678/12345678/12345678/12345678/12345678/12345'
           '678/12345678/12345/-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12.3456789-123')
 show('data/12345678/12345678/12345678/12345678/12345678/12345'
           '678/12345678/12345/-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12.3456789-1234')
 show('data/12345678/12345678/12345678/12345678/12345678/12345'
           '678/12345678/12345/-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12.3456789-12345')
 show('data/12345678/12345678/12345678/12345678/12345678/12345'
           '678/12345678/12345/-xxxxxxxxx-xxxxxxxxx-xxxxxxxxx-'
           '123456789-12.3456789-12345-ABCDEFGHIJKLMNOPRSTUVWX'
           'YZ-abcdefghjiklmnopqrstuvwxyz-ABCDEFGHIJKLMNOPRSTU'
           'VWXYZ-1234567890-xxxxxxxxx-xxxxxxxxx-xxxxxxxx-xxxx'
           'xxxxx-wwwwwwwww-wwwwwwwww-wwwwwwwww-wwwwwwwww-wwww'
           'wwwww-wwwwwwwww-wwwwwwwww-wwwwwwwww-wwwwwwwww')