[Python-checkins] python/dist/src/Lib _strptime.py,1.10,1.11

[tim_one@users.sourceforge.net]

Update of /cvsroot/python/python/dist/src/Lib
In directory sc8-pr-cvs1:/tmp/cvs-serv15164/python/Lib

Modified Files:
	_strptime.py 
Log Message:
SF patch 670194: Performance enhancement for _strptime.py.
>From Brett Cannon.  Mostly speedups via caching format string ->
compiled regexp.


Index: _strptime.py
===================================================================
RCS file: /cvsroot/python/python/dist/src/Lib/_strptime.py,v
retrieving revision 1.10
retrieving revision 1.11
diff -C2 -d -r1.10 -r1.11
*** _strptime.py	18 Jan 2003 03:53:49 -0000	1.10
--- _strptime.py	19 Jan 2003 04:40:44 -0000	1.11
***************
*** 25,29 ****
  from re import compile as re_compile
  from re import IGNORECASE
- from string import whitespace as whitespace_string
  
  __author__ = "Brett Cannon"
--- 25,28 ----
***************
*** 34,37 ****
--- 33,47 ----
  RegexpType = type(re_compile(''))
  
+ def _getlang():
+     # Figure out what the current language is set to.
+     current_lang = locale.getlocale(locale.LC_TIME)[0]
+     if current_lang:
+         return current_lang
+     else:
+         current_lang = locale.getdefaultlocale()[0]
+         if current_lang:
+             return current_lang
+         else:
+             return ''
  
  class LocaleTime(object):
***************
*** 286,302 ****
  
      def __calc_lang(self):
!         # Set self.__lang by using locale.getlocale() or
!         # locale.getdefaultlocale().  If both turn up empty, set the attribute
!         # to ''.  This is to stop calls to this method and to make sure
!         # strptime() can produce an re object correctly.
!         current_lang = locale.getlocale(locale.LC_TIME)[0]
!         if current_lang:
!             self.__lang = current_lang
!         else:
!             current_lang = locale.getdefaultlocale()[0]
!             if current_lang:
!                 self.__lang = current_lang
!             else:
!                 self.__lang = ''
  
  
--- 296,302 ----
  
      def __calc_lang(self):
!         # Set self.__lang by using __getlang().
!         self.__lang = _getlang()
! 
  
  
***************
*** 383,388 ****
          """Return re pattern for the format string."""
          processed_format = ''
!         for whitespace in whitespace_string:
!             format = format.replace(whitespace, r'\s*')
          while format.find('%') != -1:
              directive_index = format.index('%')+1
--- 383,388 ----
          """Return re pattern for the format string."""
          processed_format = ''
!         whitespace_replacement = re_compile('\s+')
!         format = whitespace_replacement.sub('\s*', format)
          while format.find('%') != -1:
              directive_index = format.index('%')+1
***************
*** 395,407 ****
      def compile(self, format):
          """Return a compiled re object for the format string."""
-         format = "(?#%s)%s" % (self.locale_time.lang,format)
          return re_compile(self.pattern(format), IGNORECASE)
  
  
  def strptime(data_string, format="%a %b %d %H:%M:%S %Y"):
      """Return a time struct based on the input data and the format string."""
!     locale_time = LocaleTime()
!     compiled_re = TimeRE(locale_time).compile(format)
!     found = compiled_re.match(data_string)
      if not found:
          raise ValueError("time data did not match format")
--- 395,423 ----
      def compile(self, format):
          """Return a compiled re object for the format string."""
          return re_compile(self.pattern(format), IGNORECASE)
  
+ # Cached TimeRE; probably only need one instance ever so cache it for performance
+ _locale_cache = TimeRE()
+ # Cached regex objects; same reason as for TimeRE cache
+ _regex_cache = dict()
  
  def strptime(data_string, format="%a %b %d %H:%M:%S %Y"):
      """Return a time struct based on the input data and the format string."""
!     global _locale_cache
!     global _regex_cache
!     locale_time = _locale_cache.locale_time
!     # If the language changes, caches are invalidated, so clear them
!     if locale_time.lang != _getlang():
!         _locale_cache = TimeRE()
!         _regex_cache.clear()
!     format_regex = _regex_cache.get(format)
!     if not format_regex:
!         # Limit regex cache size to prevent major bloating of the module;
!         # The value 5 is arbitrary
!         if len(_regex_cache) > 5:
!             _regex_cache.clear()
!         format_regex = _locale_cache.compile(format)
!         _regex_cache[format] = format_regex
!     found = format_regex.match(data_string)
      if not found:
          raise ValueError("time data did not match format")