commit 7f1fc3399340b6c017bad9a8a107616ea8ed0705
author „feldmueller“ <„feldmueller@posteo.de“> Mon Oct 21 18:05:57 2024 +0200
committer „feldmueller“ <„feldmueller@posteo.de“> Mon Oct 21 18:05:57 2024 +0200
tree 2de7b997211de50a4ffb0727e76737353bfd9ba4
parent 61485ad6c593da9675b0fa4302d478281609ed7e

Fix VocabCompare to prevent integer overflow during vocabulary sorting

Change-Id: I3796e5aef14b3de1200907e135952258a004d049

src/dereko2vec.c

diff --git a/src/dereko2vec.c b/src/dereko2vec.c
index 8c34179..5b8ef43 100644
--- a/src/dereko2vec.c
+++ b/src/dereko2vec.c
@@ -220,7 +220,11 @@
 
 // Used later for sorting by word counts
 int VocabCompare(const void *a, const void *b) {
-	return ((struct vocab_word *) b)->cn - ((struct vocab_word *) a)->cn;
+    long long freq1 = ((struct vocab_word *) a)->cn;
+    long long freq2 = ((struct vocab_word *) b)->cn;
+    if (freq1 < freq2) return 1;
+    else if (freq1 > freq2) return -1;
+    else return 0;
 }
 
 // Sorts the vocabulary by frequency using word counts