Changeset 26162 for main

Timestamp:

2012-09-11T11:30:29+12:00 (12 years ago)

Author:

kjdon

Message:

in unicode_to_utf8_word, the max_output_length is the maximum length of the actual string, not including the length, so shouldn't add one to the length

Location:

main/trunk/greenstone2/common-src/indexers/mgpp

Files:

• lib/simplefrenchstem.cpp (modified) (1 diff)
• text/stemmer.cpp (modified) (1 diff)

main/trunk/greenstone2/common-src/indexers/mgpp/lib/simplefrenchstem.cpp

@@ -67 +67 @@
 
   /* re-code, make sure the result is not longer than the input */
-  unicode_to_utf8_word (out, word, word[0]+1);
+  //unicode_to_utf8_word (out, word, word[0]+1);
+  // The max_output_length (3rd param) for unicode_to_utf8 is the max length of
+  // the string, not including the length
+  unicode_to_utf8_word (out, word, word[0]);
 }

main/trunk/greenstone2/common-src/indexers/mgpp/text/stemmer.cpp

@@ -53 +53 @@
 
   /* re-code */
-  unicode_to_utf8_word (out, word, word[0]+1);
+  //unicode_to_utf8_word (out, word, word[0]+1);
+  // The max_output_length (3rd param) for unicode_to_utf8 is the max length of
+  // the string, not including the length
+  unicode_to_utf8_word (out, word, word[0]);
 }