bug in unicodedata.normalize: u1176

Modules/unicodedata.c

 /* ------------------------------------------------------------------------
 
    unicodedata -- Provides access to the Unicode database.
 
    Data was extracted from the UnicodeData.txt file.
    The current version number is reported in the unidata_version constant.
 
    Written by Marc-Andre Lemburg (mal@lemburg.com).
    Modified for Python 2.0 by Fredrik Lundh (fredrik@pythonware.com)
    Modified by Martin v. Löwis (martin@v.loewis.de)
@@ skipping 663 matching lines @@
               i++;
               goto again; /* continue while */
           }
       }
       /* Hangul Composition. We don't need to check for <LV,T>
          pairs, since we always have decomposed data. */
       code = PyUnicode_READ(kind, data, i);
       if (LBase <= code && code < (LBase+LCount) &&
           i + 1 < len &&
           VBase <= PyUnicode_READ(kind, data, i+1) &&
-          PyUnicode_READ(kind, data, i+1) < (VBase+VCount)) {
+          PyUnicode_READ(kind, data, i+1) <= (VBase+VCount)) {
           int LIndex, VIndex;
           LIndex = code - LBase;
           VIndex = PyUnicode_READ(kind, data, i+1) - VBase;
           code = SBase + (LIndex*VCount+VIndex)*TCount;
           i+=2;
           if (i < len &&
-              TBase <= PyUnicode_READ(kind, data, i) &&
-              PyUnicode_READ(kind, data, i) <= (TBase+TCount)) {
+              TBase < PyUnicode_READ(kind, data, i) &&
+              PyUnicode_READ(kind, data, i) < (TBase+TCount)) {
               code += PyUnicode_READ(kind, data, i)-TBase;
               i++;
           }
           output[o++] = code;
           continue;
       }
 
       /* code is still input[i] here */
       f = find_nfc_index(self, nfc_first, code);
       if (f == -1) {
@@ skipping 660 matching lines @@
         PyModule_AddObject(m, "ucnhash_CAPI", v);
     return m;
 }
 
 /*
 Local variables:
 c-basic-offset: 4
 indent-tabs-mode: nil
 End:
 */