From ca92e64f990ebe984408b0a5455b92250111d19f Mon Sep 17 00:00:00 2001
From: montanaro <montanaro@users.sourceforge.net>
Date: Tue, 21 Sep 2010 04:00:56 +0000
Subject: [PATCH] Try to catch problems with message processing.

---
 spambayes/contrib/tte.py | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/spambayes/contrib/tte.py b/spambayes/contrib/tte.py
index dfde7981..6d7aa481 100644
--- a/spambayes/contrib/tte.py
+++ b/spambayes/contrib/tte.py
@@ -152,8 +152,12 @@ def train(store, hambox, spambox, maxmsgs, maxrounds, tdict, reverse, verbose,
             sys.stdout.flush()
 
             tokens = list(tokenize(train_msg))
-            score = store.spamprob(tokens)
             selector = train_msg["message-id"] or train_msg["subject"]
+            try:
+                score = store.spamprob(tokens)
+            except UnicodeDecodeError:
+                print >> sys.stderr, "Unicode error while processing", selector
+                continue
 
             if misclassified(train_spam, score) and selector is not None:
                 if verbose: