#86 One more attempt to fix a Windows Unicode heisenbug on Appveyor only

aboutcode-org · Mar 11, 2016 · a3c0e25 · a3c0e25
1 parent f0cbb0e
commit a3c0e25
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/src/licensedcode/index.py b/src/licensedcode/index.py
@@ -702,7 +702,7 @@ def renumber_token_ids(rules_tokens_ids, dictionary, tokens_by_tid, frequencies_
     # keep track of very common junk tokens: digits and single letters
     very_common = set()
     very_common_add = very_common.add
-    string_lowercase = unicode(string.lowercase)
+    string_lowercase = unicode(string.lowercase, encoding='utf-8')
     for tid, token in enumerate(tokens_by_tid):
         # DIGIT TOKENS: Treat tokens composed only of digits as common junk
         # SINGLE ASCII LETTER TOKENS: Treat single ASCII letter tokens as common junk