tests: stabilize doctest output

Avoid dependencies to dict iteration order.

mercurial/changelog.py

@@ -1,346 +1,348
 # changelog.py - changelog class for mercurial
 #
 # Copyright 2005-2007 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 node import bin, hex, nullid
 from i18n import _
 import util, error, revlog, encoding
 
 _defaultextra = {'branch': 'default'}
 
 def _string_escape(text):
     """
     >>> d = {'nl': chr(10), 'bs': chr(92), 'cr': chr(13), 'nul': chr(0)}
     >>> s = "ab%(nl)scd%(bs)s%(bs)sn%(nul)sab%(cr)scd%(bs)s%(nl)s" % d
     >>> s
     'ab\\ncd\\\\\\\\n\\x00ab\\rcd\\\\\\n'
     >>> res = _string_escape(s)
     >>> s == res.decode('string_escape')
     True
     """
     # subset of the string_escape codec
     text = text.replace('\\', '\\\\').replace('\n', '\\n').replace('\r', '\\r')
     return text.replace('\0', '\\0')
 
 def decodeextra(text):
     """
-    >>> decodeextra(encodeextra({'foo': 'bar', 'baz': chr(0) + '2'}))
-    {'foo': 'bar', 'baz': '\\x002', 'branch': 'default'}
-    >>> decodeextra(encodeextra({'foo': 'bar', 'baz': chr(92) + chr(0) + '2'}))
-    {'foo': 'bar', 'baz': '\\\\\\x002', 'branch': 'default'}
+    >>> from pprint import pprint as pp
+    >>> pp(decodeextra(encodeextra({'foo': 'bar', 'baz': chr(0) + '2'})))
+    {'baz': '\\x002', 'branch': 'default', 'foo': 'bar'}
+    >>> pp(decodeextra(encodeextra({'foo': 'bar',
+    ...                             'baz': chr(92) + chr(0) + '2'})))
+    {'baz': '\\\\\\x002', 'branch': 'default', 'foo': 'bar'}
     """
     extra = _defaultextra.copy()
     for l in text.split('\0'):
         if l:
             if '\\0' in l:
                 # fix up \0 without getting into trouble with \\0
                 l = l.replace('\\\\', '\\\\\n')
                 l = l.replace('\\0', '\0')
                 l = l.replace('\n', '')
             k, v = l.decode('string_escape').split(':', 1)
             extra[k] = v
     return extra
 
 def encodeextra(d):
     # keys must be sorted to produce a deterministic changelog entry
     items = [_string_escape('%s:%s' % (k, d[k])) for k in sorted(d)]
     return "\0".join(items)
 
 def stripdesc(desc):
     """strip trailing whitespace and leading and trailing empty lines"""
     return '\n'.join([l.rstrip() for l in desc.splitlines()]).strip('\n')
 
 class appender(object):
     '''the changelog index must be updated last on disk, so we use this class
     to delay writes to it'''
     def __init__(self, fp, buf):
         self.data = buf
         self.fp = fp
         self.offset = fp.tell()
         self.size = util.fstat(fp).st_size
 
     def end(self):
         return self.size + len("".join(self.data))
     def tell(self):
         return self.offset
     def flush(self):
         pass
     def close(self):
         self.fp.close()
 
     def seek(self, offset, whence=0):
         '''virtual file offset spans real file and data'''
         if whence == 0:
             self.offset = offset
         elif whence == 1:
             self.offset += offset
         elif whence == 2:
             self.offset = self.end() + offset
         if self.offset < self.size:
             self.fp.seek(self.offset)
 
     def read(self, count=-1):
         '''only trick here is reads that span real file and data'''
         ret = ""
         if self.offset < self.size:
             s = self.fp.read(count)
             ret = s
             self.offset += len(s)
             if count > 0:
                 count -= len(s)
         if count != 0:
             doff = self.offset - self.size
             self.data.insert(0, "".join(self.data))
             del self.data[1:]
             s = self.data[0][doff:doff + count]
             self.offset += len(s)
             ret += s
         return ret
 
     def write(self, s):
         self.data.append(str(s))
         self.offset += len(s)
 
 def delayopener(opener, target, divert, buf):
     def o(name, mode='r'):
         if name != target:
             return opener(name, mode)
         if divert:
             return opener(name + ".a", mode.replace('a', 'w'))
         # otherwise, divert to memory
         return appender(opener(name, mode), buf)
     return o
 
 class changelog(revlog.revlog):
     def __init__(self, opener):
         revlog.revlog.__init__(self, opener, "00changelog.i")
         if self._initempty:
             # changelogs don't benefit from generaldelta
             self.version &= ~revlog.REVLOGGENERALDELTA
             self._generaldelta = False
         self._realopener = opener
         self._delayed = False
         self._divert = False
         self.filteredrevs = frozenset()
 
     def tip(self):
         """filtered version of revlog.tip"""
         for i in xrange(len(self) -1, -2, -1):
             if i not in self.filteredrevs:
                 return self.node(i)
 
     def __iter__(self):
         """filtered version of revlog.__iter__"""
         if len(self.filteredrevs) == 0:
             return revlog.revlog.__iter__(self)
 
         def filterediter():
             for i in xrange(len(self)):
                 if i not in self.filteredrevs:
                     yield i
 
         return filterediter()
 
     def revs(self, start=0, stop=None):
         """filtered version of revlog.revs"""
         for i in super(changelog, self).revs(start, stop):
             if i not in self.filteredrevs:
                 yield i
 
     @util.propertycache
     def nodemap(self):
         # XXX need filtering too
         self.rev(self.node(0))
         return self._nodecache
 
     def hasnode(self, node):
         """filtered version of revlog.hasnode"""
         try:
             i = self.rev(node)
             return i not in self.filteredrevs
         except KeyError:
             return False
 
     def headrevs(self):
         if self.filteredrevs:
             # XXX we should fix and use the C version
             return self._headrevs()
         return super(changelog, self).headrevs()
 
     def strip(self, *args, **kwargs):
         # XXX make something better than assert
         # We can't expect proper strip behavior if we are filtered.
         assert not self.filteredrevs
         super(changelog, self).strip(*args, **kwargs)
 
     def rev(self, node):
         """filtered version of revlog.rev"""
         r = super(changelog, self).rev(node)
         if r in self.filteredrevs:
             raise error.LookupError(node, self.indexfile, _('no node'))
         return r
 
     def node(self, rev):
         """filtered version of revlog.node"""
         if rev in self.filteredrevs:
             raise IndexError(rev)
         return super(changelog, self).node(rev)
 
     def linkrev(self, rev):
         """filtered version of revlog.linkrev"""
         if rev in self.filteredrevs:
             raise IndexError(rev)
         return super(changelog, self).linkrev(rev)
 
     def parentrevs(self, rev):
         """filtered version of revlog.parentrevs"""
         if rev in self.filteredrevs:
             raise IndexError(rev)
         return super(changelog, self).parentrevs(rev)
 
     def flags(self, rev):
         """filtered version of revlog.flags"""
         if rev in self.filteredrevs:
             raise IndexError(rev)
         return super(changelog, self).flags(rev)
 
     def delayupdate(self):
         "delay visibility of index updates to other readers"
         self._delayed = True
         self._divert = (len(self) == 0)
         self._delaybuf = []
         self.opener = delayopener(self._realopener, self.indexfile,
                                   self._divert, self._delaybuf)
 
     def finalize(self, tr):
         "finalize index updates"
         self._delayed = False
         self.opener = self._realopener
         # move redirected index data back into place
         if self._divert:
             nfile = self.opener(self.indexfile + ".a")
             n = nfile.name
             nfile.close()
             util.rename(n, n[:-2])
         elif self._delaybuf:
             fp = self.opener(self.indexfile, 'a')
             fp.write("".join(self._delaybuf))
             fp.close()
             self._delaybuf = []
         # split when we're done
         self.checkinlinesize(tr)
 
     def readpending(self, file):
         r = revlog.revlog(self.opener, file)
         self.index = r.index
         self.nodemap = r.nodemap
         self._nodecache = r._nodecache
         self._chunkcache = r._chunkcache
 
     def writepending(self):
         "create a file containing the unfinalized state for pretxnchangegroup"
         if self._delaybuf:
             # make a temporary copy of the index
             fp1 = self._realopener(self.indexfile)
             fp2 = self._realopener(self.indexfile + ".a", "w")
             fp2.write(fp1.read())
             # add pending data
             fp2.write("".join(self._delaybuf))
             fp2.close()
             # switch modes so finalize can simply rename
             self._delaybuf = []
             self._divert = True
 
         if self._divert:
             return True
 
         return False
 
     def checkinlinesize(self, tr, fp=None):
         if not self._delayed:
             revlog.revlog.checkinlinesize(self, tr, fp)
 
     def read(self, node):
         """
         format used:
         nodeid\n        : manifest node in ascii
         user\n          : user, no \n or \r allowed
         time tz extra\n : date (time is int or float, timezone is int)
                         : extra is metadata, encoded and separated by '\0'
                         : older versions ignore it
         files\n\n       : files modified by the cset, no \n or \r allowed
         (.*)            : comment (free text, ideally utf-8)
 
         changelog v0 doesn't use extra
         """
         text = self.revision(node)
         if not text:
             return (nullid, "", (0, 0), [], "", _defaultextra)
         last = text.index("\n\n")
         desc = encoding.tolocal(text[last + 2:])
         l = text[:last].split('\n')
         manifest = bin(l[0])
         user = encoding.tolocal(l[1])
 
         tdata = l[2].split(' ', 2)
         if len(tdata) != 3:
             time = float(tdata[0])
             try:
                 # various tools did silly things with the time zone field.
                 timezone = int(tdata[1])
             except ValueError:
                 timezone = 0
             extra = _defaultextra
         else:
             time, timezone = float(tdata[0]), int(tdata[1])
             extra = decodeextra(tdata[2])
 
         files = l[3:]
         return (manifest, user, (time, timezone), files, desc, extra)
 
     def add(self, manifest, files, desc, transaction, p1, p2,
                   user, date=None, extra=None):
         # Convert to UTF-8 encoded bytestrings as the very first
         # thing: calling any method on a localstr object will turn it
         # into a str object and the cached UTF-8 string is thus lost.
         user, desc = encoding.fromlocal(user), encoding.fromlocal(desc)
 
         user = user.strip()
         # An empty username or a username with a "\n" will make the
         # revision text contain two "\n\n" sequences -> corrupt
         # repository since read cannot unpack the revision.
         if not user:
             raise error.RevlogError(_("empty username"))
         if "\n" in user:
             raise error.RevlogError(_("username %s contains a newline")
                                     % repr(user))
 
         desc = stripdesc(desc)
 
         if date:
             parseddate = "%d %d" % util.parsedate(date)
         else:
             parseddate = "%d %d" % util.makedate()
         if extra:
             branch = extra.get("branch")
             if branch in ("default", ""):
                 del extra["branch"]
             elif branch in (".", "null", "tip"):
                 raise error.RevlogError(_('the name \'%s\' is reserved')
                                         % branch)
         if extra:
             extra = encodeextra(extra)
             parseddate = "%s %s" % (parseddate, extra)
         l = [hex(manifest), user, parseddate] + sorted(files) + ["", desc]
         text = "\n".join(l)
         return self.addrevision(text, transaction, len(self), p1, p2)
 
     def branch(self, rev):
         """return the branch of a revision
 
         This function exists because creating a changectx object
         just to access this is costly."""
         return encoding.tolocal(self.read(rev)[5].get("branch"))

mercurial/encoding.py

@@ -1,287 +1,287
 # encoding.py - character transcoding support for Mercurial
 #
 #  Copyright 2005-2009 Matt Mackall <[e-mail]> and others
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 import error
 import unicodedata, locale, os
 
 def _getpreferredencoding():
     '''
     On darwin, getpreferredencoding ignores the locale environment and
     always returns mac-roman. http://bugs.python.org/issue6202 fixes this
     for Python 2.7 and up. This is the same corrected code for earlier
     Python versions.
 
     However, we can't use a version check for this method, as some distributions
     patch Python to fix this. Instead, we use it as a 'fixer' for the mac-roman
     encoding, as it is unlikely that this encoding is the actually expected.
     '''
     try:
         locale.CODESET
     except AttributeError:
         # Fall back to parsing environment variables :-(
         return locale.getdefaultlocale()[1]
 
     oldloc = locale.setlocale(locale.LC_CTYPE)
     locale.setlocale(locale.LC_CTYPE, "")
     result = locale.nl_langinfo(locale.CODESET)
     locale.setlocale(locale.LC_CTYPE, oldloc)
 
     return result
 
 _encodingfixers = {
     '646': lambda: 'ascii',
     'ANSI_X3.4-1968': lambda: 'ascii',
     'mac-roman': _getpreferredencoding
 }
 
 try:
     encoding = os.environ.get("HGENCODING")
     if not encoding:
         encoding = locale.getpreferredencoding() or 'ascii'
         encoding = _encodingfixers.get(encoding, lambda: encoding)()
 except locale.Error:
     encoding = 'ascii'
 encodingmode = os.environ.get("HGENCODINGMODE", "strict")
 fallbackencoding = 'ISO-8859-1'
 
 class localstr(str):
     '''This class allows strings that are unmodified to be
     round-tripped to the local encoding and back'''
     def __new__(cls, u, l):
         s = str.__new__(cls, l)
         s._utf8 = u
         return s
     def __hash__(self):
         return hash(self._utf8) # avoid collisions in local string space
 
 def tolocal(s):
     """
     Convert a string from internal UTF-8 to local encoding
 
     All internal strings should be UTF-8 but some repos before the
     implementation of locale support may contain latin1 or possibly
     other character sets. We attempt to decode everything strictly
     using UTF-8, then Latin-1, and failing that, we use UTF-8 and
     replace unknown characters.
 
     The localstr class is used to cache the known UTF-8 encoding of
     strings next to their local representation to allow lossless
     round-trip conversion back to UTF-8.
 
     >>> u = 'foo: \\xc3\\xa4' # utf-8
     >>> l = tolocal(u)
     >>> l
     'foo: ?'
     >>> fromlocal(l)
     'foo: \\xc3\\xa4'
     >>> u2 = 'foo: \\xc3\\xa1'
     >>> d = { l: 1, tolocal(u2): 2 }
-    >>> d # no collision
-    {'foo: ?': 1, 'foo: ?': 2}
+    >>> len(d) # no collision
+    2
     >>> 'foo: ?' in d
     False
     >>> l1 = 'foo: \\xe4' # historical latin1 fallback
     >>> l = tolocal(l1)
     >>> l
     'foo: ?'
     >>> fromlocal(l) # magically in utf-8
     'foo: \\xc3\\xa4'
     """
 
     try:
         try:
             # make sure string is actually stored in UTF-8
             u = s.decode('UTF-8')
             if encoding == 'UTF-8':
                 # fast path
                 return s
             r = u.encode(encoding, "replace")
             if u == r.decode(encoding):
                 # r is a safe, non-lossy encoding of s
                 return r
             return localstr(s, r)
         except UnicodeDecodeError:
             # we should only get here if we're looking at an ancient changeset
             try:
                 u = s.decode(fallbackencoding)
                 r = u.encode(encoding, "replace")
                 if u == r.decode(encoding):
                     # r is a safe, non-lossy encoding of s
                     return r
                 return localstr(u.encode('UTF-8'), r)
             except UnicodeDecodeError:
                 u = s.decode("utf-8", "replace") # last ditch
                 return u.encode(encoding, "replace") # can't round-trip
     except LookupError, k:
         raise error.Abort(k, hint="please check your locale settings")
 
 def fromlocal(s):
     """
     Convert a string from the local character encoding to UTF-8
 
     We attempt to decode strings using the encoding mode set by
     HGENCODINGMODE, which defaults to 'strict'. In this mode, unknown
     characters will cause an error message. Other modes include
     'replace', which replaces unknown characters with a special
     Unicode character, and 'ignore', which drops the character.
     """
 
     # can we do a lossless round-trip?
     if isinstance(s, localstr):
         return s._utf8
 
     try:
         return s.decode(encoding, encodingmode).encode("utf-8")
     except UnicodeDecodeError, inst:
         sub = s[max(0, inst.start - 10):inst.start + 10]
         raise error.Abort("decoding near '%s': %s!" % (sub, inst))
     except LookupError, k:
         raise error.Abort(k, hint="please check your locale settings")
 
 # How to treat ambiguous-width characters. Set to 'wide' to treat as wide.
 wide = (os.environ.get("HGENCODINGAMBIGUOUS", "narrow") == "wide"
         and "WFA" or "WF")
 
 def colwidth(s):
     "Find the column width of a string for display in the local encoding"
     return ucolwidth(s.decode(encoding, 'replace'))
 
 def ucolwidth(d):
     "Find the column width of a Unicode string for display"
     eaw = getattr(unicodedata, 'east_asian_width', None)
     if eaw is not None:
         return sum([eaw(c) in wide and 2 or 1 for c in d])
     return len(d)
 
 def getcols(s, start, c):
     '''Use colwidth to find a c-column substring of s starting at byte
     index start'''
     for x in xrange(start + c, len(s)):
         t = s[start:x]
         if colwidth(t) == c:
             return t
 
 def lower(s):
     "best-effort encoding-aware case-folding of local string s"
     try:
         s.decode('ascii') # throw exception for non-ASCII character
         return s.lower()
     except UnicodeDecodeError:
         pass
     try:
         if isinstance(s, localstr):
             u = s._utf8.decode("utf-8")
         else:
             u = s.decode(encoding, encodingmode)
 
         lu = u.lower()
         if u == lu:
             return s # preserve localstring
         return lu.encode(encoding)
     except UnicodeError:
         return s.lower() # we don't know how to fold this except in ASCII
     except LookupError, k:
         raise error.Abort(k, hint="please check your locale settings")
 
 def upper(s):
     "best-effort encoding-aware case-folding of local string s"
     try:
         s.decode('ascii') # throw exception for non-ASCII character
         return s.upper()
     except UnicodeDecodeError:
         pass
     try:
         if isinstance(s, localstr):
             u = s._utf8.decode("utf-8")
         else:
             u = s.decode(encoding, encodingmode)
 
         uu = u.upper()
         if u == uu:
             return s # preserve localstring
         return uu.encode(encoding)
     except UnicodeError:
         return s.upper() # we don't know how to fold this except in ASCII
     except LookupError, k:
         raise error.Abort(k, hint="please check your locale settings")
 
 def toutf8b(s):
     '''convert a local, possibly-binary string into UTF-8b
 
     This is intended as a generic method to preserve data when working
     with schemes like JSON and XML that have no provision for
     arbitrary byte strings. As Mercurial often doesn't know
     what encoding data is in, we use so-called UTF-8b.
 
     If a string is already valid UTF-8 (or ASCII), it passes unmodified.
     Otherwise, unsupported bytes are mapped to UTF-16 surrogate range,
     uDC00-uDCFF.
 
     Principles of operation:
 
     - ASCII and UTF-8 data successfully round-trips and is understood
       by Unicode-oriented clients
     - filenames and file contents in arbitrary other encodings can have
       be round-tripped or recovered by clueful clients
     - local strings that have a cached known UTF-8 encoding (aka
       localstr) get sent as UTF-8 so Unicode-oriented clients get the
       Unicode data they want
     - because we must preserve UTF-8 bytestring in places such as
       filenames, metadata can't be roundtripped without help
 
     (Note: "UTF-8b" often refers to decoding a mix of valid UTF-8 and
     arbitrary bytes into an internal Unicode format that can be
     re-encoded back into the original. Here we are exposing the
     internal surrogate encoding as a UTF-8 string.)
     '''
 
     if isinstance(s, localstr):
         return s._utf8
 
     try:
         if s.decode('utf-8'):
             return s
     except UnicodeDecodeError:
         # surrogate-encode any characters that don't round-trip
         s2 = s.decode('utf-8', 'ignore').encode('utf-8')
         r = ""
         pos = 0
         for c in s:
             if s2[pos:pos + 1] == c:
                 r += c
                 pos += 1
             else:
                 r += unichr(0xdc00 + ord(c)).encode('utf-8')
         return r
 
 def fromutf8b(s):
     '''Given a UTF-8b string, return a local, possibly-binary string.
 
     return the original binary string. This
     is a round-trip process for strings like filenames, but metadata
     that's was passed through tolocal will remain in UTF-8.
 
     >>> m = "\\xc3\\xa9\\x99abcd"
     >>> n = toutf8b(m)
     >>> n
     '\\xc3\\xa9\\xed\\xb2\\x99abcd'
     >>> fromutf8b(n) == m
     True
     '''
 
     # fast path - look for uDxxx prefixes in s
     if "\xed" not in s:
         return s
 
     u = s.decode("utf-8")
     r = ""
     for c in u:
         if ord(c) & 0xff00 == 0xdc00:
             r += chr(ord(c) & 0xff)
         else:
             r += c.encode("utf-8")
     return r