Remove vInt-like encoding in ByteBlockPool and BytesRefHash and switc…

…h to native byte order for the length
apache · May 13, 2022 · c1b626c · c1b626c
1 parent 36de2bb
commit c1b626c
Show file tree

Hide file tree

Showing 2 changed files with 10 additions and 47 deletions.
diff --git a/lucene/core/src/java/org/apache/lucene/util/ByteBlockPool.java b/lucene/core/src/java/org/apache/lucene/util/ByteBlockPool.java
@@ -301,15 +301,8 @@ void setBytesRef(BytesRefBuilder builder, BytesRef result, long offset, int leng
   public void setBytesRef(BytesRef term, int textStart) {
     final byte[] bytes = term.bytes = buffers[textStart >> BYTE_BLOCK_SHIFT];
     int pos = textStart & BYTE_BLOCK_MASK;
-    if ((bytes[pos] & 0x80) == 0) {
-      // length is 1 byte
-      term.length = bytes[pos];
-      term.offset = pos + 1;
-    } else {
-      // length is 2 bytes
-      term.length = ((short) BitUtil.VH_BE_SHORT.get(bytes, pos)) & 0x7FFF;
-      term.offset = pos + 2;
-    }
+    term.length = ((short) BitUtil.VH_NATIVE_SHORT.get(bytes, pos)) & 0x7FFF;
+    term.offset = pos + 2;
     assert term.length >= 0;
   }
 

diff --git a/lucene/core/src/java/org/apache/lucene/util/BytesRefHash.java b/lucene/core/src/java/org/apache/lucene/util/BytesRefHash.java
@@ -173,17 +173,8 @@ private boolean equals(int id, BytesRef b) {
     final int textStart = bytesStart[id];
     final byte[] bytes = pool.buffers[textStart >> BYTE_BLOCK_SHIFT];
     int pos = textStart & BYTE_BLOCK_MASK;
-    final int length;
-    final int offset;
-    if ((bytes[pos] & 0x80) == 0) {
-      // length is 1 byte
-      length = bytes[pos];
-      offset = pos + 1;
-    } else {
-      // length is 2 bytes
-      length = ((short) BitUtil.VH_BE_SHORT.get(bytes, pos)) & 0x7FFF;
-      offset = pos + 2;
-    }
+    final int length = ((short) BitUtil.VH_NATIVE_SHORT.get(bytes, pos)) & 0x7FFF;
+    final int offset = pos + 2;
     return Arrays.equals(bytes, offset, offset + length, b.bytes, b.offset, b.offset + b.length);
   }
 
@@ -270,22 +261,10 @@ public int add(BytesRef bytes) {
 
       bytesStart[e] = bufferUpto + pool.byteOffset;
 
-      // We first encode the length, followed by the
-      // bytes. Length is encoded as vInt, but will consume
-      // 1 or 2 bytes at most (we reject too-long terms,
-      // above).
-      if (length < 128) {
-        // 1 byte to store length
-        buffer[bufferUpto] = (byte) length;
-        pool.byteUpto += length + 1;
-        assert length >= 0 : "Length must be positive: " + length;
-        System.arraycopy(bytes.bytes, bytes.offset, buffer, bufferUpto + 1, length);
-      } else {
-        // 2 byte to store length
-        BitUtil.VH_BE_SHORT.set(buffer, bufferUpto, (short) (length | 0x8000));
-        pool.byteUpto += length + 2;
-        System.arraycopy(bytes.bytes, bytes.offset, buffer, bufferUpto + 2, length);
-      }
+      BitUtil.VH_NATIVE_SHORT.set(buffer, bufferUpto, (short) (length | 0x8000));
+      pool.byteUpto += length + 2;
+      System.arraycopy(bytes.bytes, bytes.offset, buffer, bufferUpto + 2, length);
+
       assert ids[hashPos] == -1;
       ids[hashPos] = e;
 
@@ -384,17 +363,8 @@ private void rehash(final int newSize, boolean hashOnData) {
           final int off = bytesStart[e0];
           final int start = off & BYTE_BLOCK_MASK;
           final byte[] bytes = pool.buffers[off >> BYTE_BLOCK_SHIFT];
-          final int len;
-          int pos;
-          if ((bytes[start] & 0x80) == 0) {
-            // length is 1 byte
-            len = bytes[start];
-            pos = start + 1;
-          } else {
-            len = ((short) BitUtil.VH_BE_SHORT.get(bytes, start)) & 0x7FFF;
-            pos = start + 2;
-          }
-          code = doHash(bytes, pos, len);
+          final int len = ((short) BitUtil.VH_NATIVE_SHORT.get(bytes, start)) & 0x7FFF;
+          code = doHash(bytes, start + 2, len);
         } else {
           code = bytesStart[e0];
         }