Changeset 1456

Timestamp:

07/05/08 09:42:59 (5 months ago)

Author:

rob

Message:

Normalize the encoding name by running it through the standard python codec list

Location:

trunk

Files:

• peppy/stcbase.py (modified) (3 diffs)
• tests/test_unicode.py (modified) (4 diffs)

trunk/peppy/stcbase.py

@@ -1 +1 @@
 # peppy Copyright (c) 2006-2008 Rob McMullen
 # Licenced under the GPLv2; see http://peppy.flipturn.org for more info
-import os, re, time
+import os, re, time, codecs
 
 import wx
@@ -219 +219 @@
         
         if encoding:
-            self.refstc.encoding = encoding
+            # Normalize the encoding name by running it through the codecs list
+            self.refstc.encoding = codecs.lookup(encoding).name
         if not self.refstc.encoding:
             self.refstc.encoding = detectEncoding(header)
@@ -305 +306 @@
                     self.refstc.encoding = encoding
                     self.decodeText(txt)
+            elif self.refstc.encoding:
+                if self.refstc.encoding != 'utf-8':
+                    txt = txt.encode(self.refstc.encoding)
             else:
                 # Have to use GetStyledText because GetText will truncate the

trunk/tests/test_unicode.py

@@ -18 +18 @@
         self.utf8 = '# -*- coding: UTF-8 -*-\naacute:\xc3\xa1 ntilde:\xc3\xb1'
         self.latin1= '# -*- coding: latin-1 -*-\n' + ''.join([chr(i) for i in range(160, 255)])
+        self.latin1_unmarked= ''.join([chr(i) for i in range(160, 255)])
 
     def testUTF8(self):
@@ -27 +28 @@
     
     def testChangeLatin(self):
-        self.stc.encoding = detectEncoding(self.utf8)
-        print self.stc.encoding
+        self.stc.refstc.encoding = detectEncoding(self.utf8)
+        print self.stc.refstc.encoding
         self.stc.decodeText(self.utf8)
         unicode1 = self.stc.GetLine(1)
@@ -43 +44 @@
 
     def testLatin1(self):
-        self.stc.encoding = detectEncoding(self.latin1)
+        self.stc.refstc.encoding = detectEncoding(self.latin1)
         print repr(self.latin1)
         utf8 = unicode(self.latin1, "iso-8859-1").encode('utf-8')
@@ -51 +52 @@
         self.stc.decodeText(self.latin1)
         print repr(self.stc.GetText())
+        print self.stc.refstc.encoding
         self.stc.prepareEncoding()
         print "encoded: " + repr(self.stc.refstc.encoded)
         assert self.latin1 == self.stc.refstc.encoded
+
+    def testLatin1Unmarked(self):
+        self.stc.refstc.encoding = detectEncoding(self.latin1_unmarked)
+        print repr(self.latin1_unmarked)
+        utf8 = self.latin1_unmarked.decode('latin-1')
+        print repr(utf8)
+        print repr(utf8.encode('latin-1'))
+        assert utf8.encode('latin-1') == self.latin1_unmarked
+        self.stc.decodeText(self.latin1_unmarked)
+        print repr(self.stc.GetText())
+        # There's no encoding marker in the text, so there shouldn't be an
+        # encoding listed
+        assert self.stc.refstc.encoding == None
+        self.stc.prepareEncoding()
+        print "encoded: " + repr(self.stc.refstc.encoded)
+        assert self.latin1_unmarked == self.stc.refstc.encoded