CVS: tmda-cgi CharSetAlias.py,NONE,1.1 CgiUtil.py,1.14,1.15 PendList.py,1.12,1.13 Template.py,1.5,1.6 View.py,1.17,1.18 tmda-cgi.py,1.30,1.31

Update of /cvsroot/tmda/tmda-cgi
In directory sc8-pr-cvs1:/tmp/cvs-serv6401

Modified Files:
	CgiUtil.py PendList.py Template.py View.py tmda-cgi.py 
Added Files:
	CharSetAlias.py 
Log Message:
Call T.set_charset( "charset" ) instead of T["CharSet"] = "charset" to set the character encoding of a page - it now sets the META tag AND the actual HTTP header printed to the browser (fix for Apache2).

Using email.Charset (and CharSetAlias.py) for character set aliasing instead of a home-grown method.


--- NEW FILE ---
#!/usr/bin/env python
#
# Copyright (C) 2003 Jim Ramsay <[email protected]>
#
# This file is part of TMDA.
#
# TMDA is free software; you can redistribute it and/or modify it
# under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.  A copy of this license should
# be included in the file COPYING.
#
# TMDA is distributed in the hope that it will be useful, but WITHOUT
# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
# FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
# for more details.
#
# You should have received a copy of the GNU General Public License
# along with TMDA; if not, write to the Free Software Foundation, Inc.,
# 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA

"Sets up characterset aliases for email.Charset"

import email.Charset

# Aliases to gb2312
for cs in ("csgb2312", "gb_2312-80", "iso-ir-58", "chinese", "csiso58gb231280"):
  email.Charset.add_alias( cs, "gb2312" )

# Aliases to GBK
for cs in ("cp936", "ms936", "windows-936"):
  email.Charset.add_alias( cs, "gbk" )

# Aliases to Big5
for cs in ("big5-hkscs", "csbig5", "chinesebig5"):
  email.Charset.add_alias( cs, "big5" )

Index: CgiUtil.py
===================================================================
RCS file: /cvsroot/tmda/tmda-cgi/CgiUtil.py,v
retrieving revision 1.14
retrieving revision 1.15
diff -u -r1.14 -r1.15
--- CgiUtil.py	6 May 2003 21:50:39 -0000	1.14
+++ CgiUtil.py	12 May 2003 16:59:23 -0000	1.15
@@ -160,29 +160,18 @@
   P.write(MsgObj.msgobj.as_string(1))
   P.close()
 
-def AliasCharSet(CharSet):
-  "Recognize a charset's alias."
-  if CharSet in ("csgb2312", "gb_2312-80", "iso-ir-58", "chinese",
-    "csiso58gb231280"):
-    CharSet = "gb2312"
-  # Is it GBK?
-  elif CharSet in ("cp936", "ms936", "windows-936"):
-    CharSet = "gbk"
-  # Is it Big5?
-  elif CharSet in ("big5-hkscs", "csbig5", "chinesebig5"):
-    CharSet = "big5"
-  return CharSet
-
 def TranslateToUTF8(CharSet, Str, Errors):
   "Represent a string in UTF-8."
+  import email.Charset
 
   if not CharSet:
     return Str
-  CharSet = AliasCharSet(CharSet)
+  CS = email.Charset.Charset( CharSet )
+  RealCharset = CS.input_charset
 
   # Find appropriate decoder
   try:
-    Decoder = codecs.getdecoder(CharSet)
+    Decoder = codecs.getdecoder(RealCharset)
   except LookupError:
     try:
       # Is it GB2312?

Index: PendList.py
===================================================================
RCS file: /cvsroot/tmda/tmda-cgi/PendList.py,v
retrieving revision 1.12
retrieving revision 1.13
diff -u -r1.12 -r1.13
--- PendList.py	6 May 2003 21:50:40 -0000	1.12
+++ PendList.py	12 May 2003 16:59:23 -0000	1.13
@@ -93,7 +93,7 @@
 
   # Load the display template
   T = Template.Template("pending.html")
-  T["CharSet"] = "utf-8"
+  T.set_charset( "utf-8" )
 
   # Find the message numbers we'll display
   FirstMsg = PVars["Pager"]

Index: Template.py
===================================================================
RCS file: /cvsroot/tmda/tmda-cgi/Template.py,v
retrieving revision 1.5
retrieving revision 1.6
diff -u -r1.5 -r1.6
--- Template.py	22 Apr 2003 17:50:55 -0000	1.5
+++ Template.py	12 May 2003 16:59:23 -0000	1.6
@@ -109,18 +109,21 @@
 # <center>Form may not be submitted.</center>
 
 import copy, re
+import email.Charset
 from types import StringType
 
 class Template:
   # Members global across all instantiations:
-  Dict = {}
-  BaseDir = "."
-  VarSearchStr  = '<!--\s*var:\s*%s(?:="([^"]+)")?\s*-->'
-  VarEndSearch  = re.compile("<!--\s*/var[^-]*-->", re.I)
-  LonePctSearch = re.compile("([^%])%([^(%])")
-  LonePctRepl   = r"\1%%\2"
-  SearchDict    = {}
-  BeenExpanded  = 0
+  Dict            = {}
+  BaseDir         = "."
+  VarSearchStr    = '<!--\s*var:\s*%s(?:="([^"]+)")?\s*-->'
+  VarEndSearch    = re.compile("<!--\s*/var[^-]*-->", re.I)
+  LonePctSearch   = re.compile("([^%])%([^(%])")
+  LonePctRepl     = r"\1%%\2"
+  SearchDict      = {}
+  BeenExpanded    = 0
+  FallbackCharset = "utf-8"
+  charset = None
 
   def __init__ \
   (
@@ -139,12 +142,30 @@
       F.close()
     self.Items = {}
 
+  def set_charset(self, Charset = None ):
+    "Sets the characterset for this page."
+    if Charset is None: Charset = self.FallbackCharset
+    # If this is an alias, find the "real" charset:
+    chsetObj = email.Charset.Charset( Charset )
+    self.charset = chsetObj.input_charset
+    self["CharSet"] = self.charset
+
   def __setitem__(self, Index, Value):
     "Assign a substitution variable."
     if self.Items.has_key(Index):
       self.Items[Index].HTML = [Value]
     else:
       self.Dict[Index] = Value
+
+  def __str__(self):
+    "Convert to string for printing in browser. (Adds content-type header)"
+
+    if not self.charset:
+        self.set_charset()
+    addStr = "; charset=%s" % self.charset
+    RetVal = "Content-Type: text/html%s\n\n" % addStr
+    RetVal += self.__repr__()
+    return RetVal
 
   def __repr__(self):
     "Dump contents of object."

Index: View.py
===================================================================
RCS file: /cvsroot/tmda/tmda-cgi/View.py,v
retrieving revision 1.17
retrieving revision 1.18
diff -u -r1.17 -r1.18
--- View.py	6 May 2003 21:50:40 -0000	1.17
+++ View.py	12 May 2003 16:59:23 -0000	1.18
@@ -226,7 +226,7 @@
       for decoded in email.Header.decode_header( Line ):
         Headers += decoded[0] + " "
         if decoded[1]:
-          T["CharSet"] = CgiUtil.AliasCharSet(decoded[1])
+          T.set_charset( decoded[1] )
       Headers += "\n"
     T["Headers"] = '<pre class="Headers">%s</pre>' % Headers
   else:
@@ -241,7 +241,7 @@
       for decoded in email.Header.decode_header( MsgObj.msgobj[Header] ):
         value += decoded[0] + " "
         if decoded[1]:
-          T["CharSet"] = CgiUtil.AliasCharSet(decoded[1])
+          T.set_charset( decoded[1] )
       T["Value"] = CgiUtil.Escape(value)
       HeaderRow.Add()
 
@@ -285,9 +285,6 @@
   # text/html             - sterilize & display
   # other                 - show as an attachment
 
-  # Check if there's a character set for this part.
-  if Part.get_content_charset():
-    T["CharSet"] = CgiUtil.AliasCharSet(Part.get_content_charset())
 
   # Display this part
   if Part.is_multipart():
@@ -313,6 +310,9 @@
     Type = Part.get_type("text/plain")
     # Display the easily display-able parts
     if Type == "text/plain":
+      # Check if there's a character set for this part.
+      if Part.get_content_charset():
+        T.set_charset( Part.get_content_charset() )
       # Escape & display
       try:
         Str = Part.get_payload(decode=1).strip()
@@ -324,6 +324,9 @@
         pass
     elif Type == "text/html":
       # Sterilize & display
+      # Check if there's a character set for this part.
+      if Part.get_content_charset():
+        T.set_charset( Part.get_content_charset() )
       try:
         T["Content"] = \
           CgiUtil.Sterilize(Part.get_payload(decode=1), Allow, Remove)

Index: tmda-cgi.py
===================================================================
RCS file: /cvsroot/tmda/tmda-cgi/tmda-cgi.py,v
retrieving revision 1.30
retrieving revision 1.31
diff -u -r1.30 -r1.31
--- tmda-cgi.py	9 May 2003 05:04:59 -0000	1.30
+++ tmda-cgi.py	12 May 2003 16:59:23 -0000	1.31
@@ -22,6 +22,7 @@
 "Web interface to TMDA tools."
 
 import MyCgiTb
+import CharSetAlias
 
 import cgi
 import os
@@ -52,13 +53,12 @@
 Session.WebUID = os.getuid()
 
 # Prepare the traceback in case of uncaught exception
-MyCgiTb.Content()
 MyCgiTb.ErrTemplate = "prog_err2.html"
 
 # Make some global stuff available to all
 Template.Template.BaseDir = "%s/display/themes/Blue/template" % \
   os.path.abspath(os.path.split(sys.argv[0])[0])
-Template.Template.Dict["CharSet"]  = "iso-8859-1"
+#Template.Template.FallbackCharset  = "iso-8859-1"
 Template.Template.Dict["Script"]   = os.environ["SCRIPT_NAME"]
 Template.Template.Dict["SID"]      = ""
 Template.Template.Dict["DispDir"]  = os.environ["TMDA_CGI_DISP_DIR"]

_______________________________________
tmda-cvs mailing list
http://tmda.net/lists/listinfo/tmda-cvs