i18n: cache the result of every gettext call

In looking at profiler output for 'hg log' on mozilla-central, I
noticed we spent a _huge_ amount of time in gettext relative to what
it's doing. Caching provides a roughly 15% performance improvement
even on repositories as small as hg.

== hg repo on linux ==

Before:
  %   cumulative      self
 time    seconds   seconds  name
  5.05      0.19      0.19  i18n.py:62:gettext
  4.84      0.18      0.18  revlog.py:88:decompress
  2.95      0.17      0.11  changelog.py:201:node
  2.32      0.09      0.09  ui.py:577:write
  2.11      0.08      0.08  i18n.py:72:gettext
  2.11      0.08      0.08  obsolete.py:196:_fm0readmarkers
  1.89      0.07      0.07  obsolete.py:569:_load
  1.68      0.63      0.06  localrepo.py:29:__get__

real	0m4.026s
user	0m3.993s
sys	0m0.034s

After:
  %   cumulative      self
 time    seconds   seconds  name
  8.05      0.26      0.26  revlog.py:88:decompress
  2.68      0.22      0.09  color.py:395:write
  2.20      0.07      0.07  obsolete.py:196:_fm0readmarkers
  1.95      0.06      0.06  obsolete.py:174:_fm0readmarkers
  1.95      0.06      0.06  ui.py:577:write
  1.95      0.06      0.06  util.py:1228:datestr
  1.71      0.06      0.06  utf_8.py:16:decode
  1.71      0.06      0.06  revlog.py:273:__len__

real	0m3.519s
user	0m3.447s
sys	0m0.073s


== mozilla-central repo on linux ==
Before:
  %   cumulative      self
 time    seconds   seconds  name
  7.72      2.35      2.35  revlog.py:88:decompress
  4.46      1.36      1.36  i18n.py:62:gettext
  2.22      0.67      0.67  i18n.py:72:gettext
  2.19      1.14      0.67  changelog.py:201:node
  2.16      0.66      0.66  ui.py:577:write
  1.96      0.60      0.60  utf_8.py:16:decode
  1.93      1.97      0.59  color.py:395:write
  1.85      0.81      0.56  changelog.py:136:tip

real	0m30.822s
user	0m30.660s
sys	0m0.149s

After:
  %   cumulative      self
 time    seconds   seconds  name
  9.82      2.49      2.49  revlog.py:88:decompress
  2.67      1.31      0.68  localrepo.py:29:__get__
  2.57      0.65      0.65  utf_8.py:16:decode
  2.48      1.01      0.63  changelog.py:201:node
  2.10      0.82      0.53  changelog.py:136:tip
  2.01      0.51      0.51  ui.py:577:write
  1.91      0.49      0.49  util.py:1232:datestr
  1.85      1.65      0.47  color.py:395:write

real	0m25.619s
user	0m25.446s
sys	0m0.166s

== cpython repo on os x =
Before:
  %   cumulative      self
 time    seconds   seconds  name
  5.05      1.35      1.35  cmdutil.py:982:_show
  4.59      1.22      1.22  revlog.py:274:__len__
  3.98      1.06      1.06  i18n.py:62:gettext
  3.91      1.04      1.04  revlog.py:1016:revision
  3.68      0.98      0.98  revlog.py:337:parents
  3.45      0.92      0.92  revlog.py:88:decompress
  2.91      0.78      0.78  revlog.py:309:rev
  2.62      0.70      0.70  revlog.py:1033:revision

real	0m30.414s
user	0m28.145s
sys	0m0.541s



After:
  %   cumulative      self
 time    seconds   seconds  name
  7.98      1.66      1.66  cmdutil.py:982:_show
  6.83      1.42      1.42  changelog.py:46:decodeextra
  5.18      1.08      1.08  revlog.py:274:__len__
  3.94      0.82      0.82  revlog.py:1016:revision
  3.41      0.71      0.71  revlog.py:309:rev
  3.32      0.69      0.69  revlog.py:88:decompress
  2.99      0.63      0.62  revlog.py:1033:revision
  2.69      0.56      0.56  revlog.py:341:start

real	0m22.811s
user	0m21.883s
sys	0m0.397s

mercurial/i18n.py

@@ -1,86 +1,90 b''
 # i18n.py - internationalization support for mercurial
 #
 # Copyright 2005, 2006 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.
 
 import encoding
 import gettext as gettextmod, sys, os, locale
 
 # modelled after templater.templatepath:
 if getattr(sys, 'frozen', None) is not None:
     module = sys.executable
 else:
     module = __file__
 
 
 _languages = None
 if (os.name == 'nt'
     and 'LANGUAGE' not in os.environ
     and 'LC_ALL' not in os.environ
     and 'LC_MESSAGES' not in os.environ
     and 'LANG' not in os.environ):
     # Try to detect UI language by "User Interface Language Management" API
     # if no locale variables are set. Note that locale.getdefaultlocale()
     # uses GetLocaleInfo(), which may be different from UI language.
     # (See http://msdn.microsoft.com/en-us/library/dd374098(v=VS.85).aspx )
     try:
         import ctypes
         langid = ctypes.windll.kernel32.GetUserDefaultUILanguage()
         _languages = [locale.windows_locale[langid]]
     except (ImportError, AttributeError, KeyError):
         # ctypes not found or unknown langid
         pass
 
 _ugettext = None
 
 def setdatapath(datapath):
     localedir = os.path.join(datapath, 'locale')
     t = gettextmod.translation('hg', localedir, _languages, fallback=True)
     global _ugettext
     _ugettext = t.ugettext
 
+_msgcache = {}
+
 def gettext(message):
     """Translate message.
 
     The message is looked up in the catalog to get a Unicode string,
     which is encoded in the local encoding before being returned.
 
     Important: message is restricted to characters in the encoding
     given by sys.getdefaultencoding() which is most likely 'ascii'.
     """
     # If message is None, t.ugettext will return u'None' as the
     # translation whereas our callers expect us to return None.
     if message is None or not _ugettext:
         return message
 
-    if type(message) is unicode:
-        # goofy unicode docstrings in test
-        paragraphs = message.split(u'\n\n')
-    else:
-        paragraphs = [p.decode("ascii") for p in message.split('\n\n')]
-    # Be careful not to translate the empty string -- it holds the
-    # meta data of the .po file.
-    u = u'\n\n'.join([p and _ugettext(p) or '' for p in paragraphs])
-    try:
-        # encoding.tolocal cannot be used since it will first try to
-        # decode the Unicode string. Calling u.decode(enc) really
-        # means u.encode(sys.getdefaultencoding()).decode(enc). Since
-        # the Python encoding defaults to 'ascii', this fails if the
-        # translated string use non-ASCII characters.
-        return u.encode(encoding.encoding, "replace")
-    except LookupError:
-        # An unknown encoding results in a LookupError.
-        return message
+    if message not in _msgcache:
+        if type(message) is unicode:
+            # goofy unicode docstrings in test
+            paragraphs = message.split(u'\n\n')
+        else:
+            paragraphs = [p.decode("ascii") for p in message.split('\n\n')]
+        # Be careful not to translate the empty string -- it holds the
+        # meta data of the .po file.
+        u = u'\n\n'.join([p and _ugettext(p) or '' for p in paragraphs])
+        try:
+            # encoding.tolocal cannot be used since it will first try to
+            # decode the Unicode string. Calling u.decode(enc) really
+            # means u.encode(sys.getdefaultencoding()).decode(enc). Since
+            # the Python encoding defaults to 'ascii', this fails if the
+            # translated string use non-ASCII characters.
+            _msgcache[message] = u.encode(encoding.encoding, "replace")
+        except LookupError:
+            # An unknown encoding results in a LookupError.
+            _msgcache[message] = message
+    return _msgcache[message]
 
 def _plain():
     if 'HGPLAIN' not in os.environ and 'HGPLAINEXCEPT' not in os.environ:
         return False
     exceptions = os.environ.get('HGPLAINEXCEPT', '').strip().split(',')
     return 'i18n' not in exceptions
 
 if _plain():
     _ = lambda message: message
 else:
     _ = gettext