(lucene) branch main updated: Clean up UnCompiledNode.inputCount (#12735)

[mi...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

mikemccand pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/lucene.git


The following commit(s) were added to refs/heads/main by this push:
     new cdc7d87fcc3 Clean up UnCompiledNode.inputCount (#12735)
cdc7d87fcc3 is described below

commit cdc7d87fcc321f63b6e9d9f8eceb295b1c919bd5
Author: Dzung Bui <du...@gmail.com>
AuthorDate: Thu Nov 2 17:34:36 2023 +0900

    Clean up UnCompiledNode.inputCount (#12735)
    
    * Clean up inputCount
    
    * Update CHANGES.txt
---
 lucene/CHANGES.txt                                       |  4 +++-
 .../src/java/org/apache/lucene/util/fst/FSTCompiler.java | 16 ----------------
 .../src/test/org/apache/lucene/util/fst/TestFSTs.java    |  1 -
 3 files changed, 3 insertions(+), 18 deletions(-)

diff --git a/lucene/CHANGES.txt b/lucene/CHANGES.txt
index 76293f6dbbd..09e34a55e3e 100644
--- a/lucene/CHANGES.txt
+++ b/lucene/CHANGES.txt
@@ -62,9 +62,11 @@ API Changes
 
 * GITHUB#12599: Add RandomAccessInput#readBytes method to the RandomAccessInput interface. (Ignacio Vera)
 
-* GITHUB#12709 Consolidate FSTStore and BytesStore in FST. Created FSTReader which contains the common methods
+* GITHUB#12709: Consolidate FSTStore and BytesStore in FST. Created FSTReader which contains the common methods
   of the two (Anh Dung Bui)
 
+* GITHUB#12735: Remove FSTCompiler#getTermCount() and FSTCompiler.UnCompiledNode#inputCount (Anh Dung Bui)
+
 New Features
 ---------------------
 
diff --git a/lucene/core/src/java/org/apache/lucene/util/fst/FSTCompiler.java b/lucene/core/src/java/org/apache/lucene/util/fst/FSTCompiler.java
index f17c220f83d..3af62410070 100644
--- a/lucene/core/src/java/org/apache/lucene/util/fst/FSTCompiler.java
+++ b/lucene/core/src/java/org/apache/lucene/util/fst/FSTCompiler.java
@@ -270,10 +270,6 @@ public class FSTCompiler<T> {
     return directAddressingMaxOversizingFactor;
   }
 
-  public long getTermCount() {
-    return frontier[0].inputCount;
-  }
-
   public long getNodeCount() {
     // 1+ in order to count the -1 implicit final node
     return 1 + nodeCount;
@@ -749,7 +745,6 @@ public class FSTCompiler<T> {
       // format cannot represent the empty input since
       // 'finalness' is stored on the incoming arc, not on
       // the node
-      frontier[0].inputCount++;
       frontier[0].isFinal = true;
       fst.setEmptyOutput(output);
       return;
@@ -760,9 +755,6 @@ public class FSTCompiler<T> {
     int pos2 = input.offset;
     final int pos1Stop = Math.min(lastInput.length(), input.length);
     while (true) {
-      frontier[pos1].inputCount++;
-      // System.out.println("  incr " + pos1 + " ct=" + frontier[pos1].inputCount + " n=" +
-      // frontier[pos1]);
       if (pos1 >= pos1Stop || lastInput.intAt(pos1) != input.ints[pos2]) {
         break;
       }
@@ -786,7 +778,6 @@ public class FSTCompiler<T> {
     // init tail states for current input
     for (int idx = prefixLenPlus1; idx <= input.length; idx++) {
       frontier[idx - 1].addArc(input.ints[input.offset + idx - 1], frontier[idx]);
-      frontier[idx].inputCount++;
     }
 
     final UnCompiledNode<T> lastNode = frontier[input.length];
@@ -835,8 +826,6 @@ public class FSTCompiler<T> {
 
     // save last input
     lastInput.copyInts(input);
-
-    // System.out.println("  count[0]=" + frontier[0].inputCount);
   }
 
   private boolean validOutput(T output) {
@@ -906,10 +895,6 @@ public class FSTCompiler<T> {
     T output;
     boolean isFinal;
 
-    // TODO: remove this tracking?  we used to use it for confusingly pruning NodeHash, but
-    // we switched to LRU by RAM usage instead:
-    long inputCount;
-
     /** This node's depth, starting from the automaton root. */
     final int depth;
 
@@ -935,7 +920,6 @@ public class FSTCompiler<T> {
       numArcs = 0;
       isFinal = false;
       output = owner.NO_OUTPUT;
-      inputCount = 0;
 
       // We don't clear the depth here because it never changes
       // for nodes on the frontier (even when reused).
diff --git a/lucene/core/src/test/org/apache/lucene/util/fst/TestFSTs.java b/lucene/core/src/test/org/apache/lucene/util/fst/TestFSTs.java
index 927fe058ef0..f6dd84efd0e 100644
--- a/lucene/core/src/test/org/apache/lucene/util/fst/TestFSTs.java
+++ b/lucene/core/src/test/org/apache/lucene/util/fst/TestFSTs.java
@@ -568,7 +568,6 @@ public class TestFSTs extends LuceneTestCase {
         System.out.println(
             ((tMid - tStart) / (double) TimeUnit.SECONDS.toNanos(1)) + " sec to add all terms");
 
-        assert fstCompiler.getTermCount() == ord;
         FST<T> fst = fstCompiler.compile();
         long tEnd = System.nanoTime();
         System.out.println(