Moved the encoding map building logic from the individual mapping

codec files to codecs.py and added logic so that multi mappings
in the decoding maps now result in mappings to None (undefined mapping)
in the encoding maps.

1 files changed, 21 insertions, 0 deletions

diff --git a/Lib/codecs.py b/Lib/codecs.py
index b2eab1d..bdc8d02 100644
--- a/Lib/codecs.py
+++ b/Lib/codecs.py
@@ -554,6 +554,27 @@ def make_identity_dict(rng):
         res[i]=i
     return res
 
+def make_encoding_map(decoding_map):
+
+    """ Creates an encoding map from a decoding map.
+
+        If a target mapping in the decoding map occurrs multiple
+        times, then that target is mapped to None (undefined mapping),
+        causing an exception when encountered by the charmap codec
+        during translation.
+
+        One example where this happens is cp875.py which decodes
+        multiple character to \u001a.
+
+    """
+    m = {}
+    for k,v in decoding_map.items():
+        if not m.has_key(v):
+            m[v] = k
+        else:
+            m[v] = None
+    return m
+    
 ### Tests
 
 if __name__ == '__main__':