Improve BytesRefHash.add performance by optimize rehash operation

lucene/CHANGES.txt

@@ -241,6 +241,8 @@ Optimizations
 
 * GITHUB#15024: Improve prefix sum computation in Lucene99HnswVectorsReader for faster neighbor decoding. (Luis Negrin)
 
+* GITHUB#15779: Improve BytesRefHash.add performance by optimize rehash operation (tyronecai)
+
 Bug Fixes
 ---------------------
 * GITHUB#15754: Fix HTMLStripCharFilter to prevent tags from incorrectly consuming subsequent

lucene/core/src/java/org/apache/lucene/util/BytesRefHash.java

@@ -433,40 +433,37 @@ public int addByPoolOffset(int offset) {
   private void rehash(final int newSize, boolean hashOnData) {
     final int newMask = newSize - 1;
     final int newHighMask = ~newMask;
-    bytesUsed.addAndGet(Integer.BYTES * (long) newSize);
-    final int[] newHash = new int[newSize];
-    Arrays.fill(newHash, -1);
-    for (int i = 0; i < hashSize; i++) {
-      int e0 = ids[i];
-      if (e0 != -1) {
-        e0 &= hashMask;
-        final int hashcode;
-        int code;
-        if (hashOnData) {
-          hashcode = code = pool.hash(bytesStart[e0]);
-        } else {
-          code = bytesStart[e0];
-          hashcode = 0;
-        }
-
-        int hashPos = code & newMask;
-        assert hashPos >= 0;
-
-        // Conflict; use linear probe to find an open slot
-        // (see LUCENE-5604):
-        while (newHash[hashPos] != -1) {
-          code++;
-          hashPos = code & newMask;
-        }
-
-        newHash[hashPos] = e0 | (hashcode & newHighMask);
+    bytesUsed.addAndGet(Integer.BYTES * (long) (newSize - ids.length));
+
+    ids = new int[newSize];
+    Arrays.fill(ids, -1);
+
+    // rebuild ids from terms in pool pointed by bytesStart
+    for (int id = 0; id < count; id++) {
+      final int hashcode;
+      int code;
+      if (hashOnData) {
+        hashcode = code = pool.hash(bytesStart[id]);
+      } else {
+        code = bytesStart[id];
+        hashcode = 0;
       }
+
+      int hashPos = code & newMask;
+      assert hashPos >= 0;
+
+      // Conflict; use linear probe to find an open slot
+      // (see LUCENE-5604):
+      while (ids[hashPos] != -1) {
+        code++;
+        hashPos = code & newMask;
+      }
+
+      ids[hashPos] = id | (hashcode & newHighMask);
     }
 
     hashMask = newMask;
     highMask = newHighMask;
-    bytesUsed.addAndGet(Integer.BYTES * (long) -ids.length);
-    ids = newHash;
     hashSize = newSize;
     hashHalfSize = newSize / 2;
   }