Add Intervals.noIntervals() method (#13389)

Parsers may sometimes want to create an IntervalsSource that returns no intervals. This adds a new factory method to `Intervals` that will create one, and changes `IntervalBuilder` to use it in place of its custom empty intervals source.
apache · May 21, 2024 · f1398ce · f1398ce
1 parent 26fca9e
commit f1398ce
Show file tree

Hide file tree

Showing 4 changed files with 19 additions and 109 deletions.
diff --git a/lucene/CHANGES.txt b/lucene/CHANGES.txt
@@ -69,6 +69,9 @@ Improvements
 
 * GITHUB#13362: Add sub query explanations to DisjunctionMaxQuery, if the overall query didn't match. (Tim Grein)
 
+* GITHUB#13385: Add Intervals.noIntervals() method to produce an empty IntervalsSource.
+  (Aniketh Jain, Uwe Schindler, Alan Woodward))
+
 Optimizations
 ---------------------
 
@@ -162,7 +165,6 @@ Other
 
 * GITHUB#13077: Add public getter for SynonymQuery#field (Andrey Bozhko)
 
-* GITHUB#13385: Make NO_INTERVALS source as public to be used by Lucene clients instead of creating clones themselves (Aniketh Jain)
 
 ======================== Lucene 9.10.0 =======================
 

diff --git a/lucene/queries/src/java/org/apache/lucene/queries/intervals/IntervalBuilder.java b/lucene/queries/src/java/org/apache/lucene/queries/intervals/IntervalBuilder.java
@@ -41,18 +41,14 @@
 
 import java.io.IOException;
 import java.util.ArrayList;
-import java.util.Collection;
-import java.util.Collections;
 import java.util.Iterator;
 import java.util.List;
 import org.apache.lucene.analysis.CachingTokenFilter;
 import org.apache.lucene.analysis.TokenStream;
 import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
 import org.apache.lucene.analysis.tokenattributes.PositionLengthAttribute;
 import org.apache.lucene.analysis.tokenattributes.TermToBytesRefAttribute;
-import org.apache.lucene.index.LeafReaderContext;
 import org.apache.lucene.search.BooleanQuery;
-import org.apache.lucene.search.QueryVisitor;
 import org.apache.lucene.util.BytesRef;
 import org.apache.lucene.util.graph.GraphTokenStreamFiniteStrings;
 
@@ -66,6 +62,10 @@
  *     "https://github.com/elastic/elasticsearch/blob/7.10/server/src/main/java/org/elasticsearch/index/query/IntervalBuilder.java"
  */
 final class IntervalBuilder {
+
+  private static final IntervalsSource NO_INTERVALS =
+      Intervals.noIntervals("No terms in analyzed text");
+
   static IntervalsSource analyzeText(CachingTokenFilter stream, int maxGaps, boolean ordered)
       throws IOException {
     assert stream != null;
@@ -236,94 +236,4 @@ private static List<IntervalsSource> analyzeGraph(TokenStream source) throws IOE
     }
     return clauses;
   }
-
-  public static final IntervalsSource NO_INTERVALS =
-      new IntervalsSource() {
-        @Override
-        public IntervalIterator intervals(String field, LeafReaderContext ctx) {
-          return new IntervalIterator() {
-            boolean exhausted = false;
-
-            @Override
-            public int start() {
-              return NO_MORE_INTERVALS;
-            }
-
-            @Override
-            public int end() {
-              return NO_MORE_INTERVALS;
-            }
-
-            @Override
-            public int gaps() {
-              throw new UnsupportedOperationException();
-            }
-
-            @Override
-            public int nextInterval() {
-              return NO_MORE_INTERVALS;
-            }
-
-            @Override
-            public float matchCost() {
-              return 0;
-            }
-
-            @Override
-            public int docID() {
-              return exhausted ? NO_MORE_DOCS : -1;
-            }
-
-            @Override
-            public int nextDoc() {
-              exhausted = true;
-              return NO_MORE_DOCS;
-            }
-
-            @Override
-            public int advance(int target) {
-              exhausted = true;
-              return NO_MORE_DOCS;
-            }
-
-            @Override
-            public long cost() {
-              return 0;
-            }
-          };
-        }
-
-        @Override
-        public IntervalMatchesIterator matches(String field, LeafReaderContext ctx, int doc) {
-          return null;
-        }
-
-        @Override
-        public void visit(String field, QueryVisitor visitor) {}
-
-        @Override
-        public int minExtent() {
-          return 0;
-        }
-
-        @Override
-        public Collection<IntervalsSource> pullUpDisjunctions() {
-          return Collections.emptyList();
-        }
-
-        @Override
-        public int hashCode() {
-          return 0;
-        }
-
-        @Override
-        public boolean equals(Object other) {
-          return other == this;
-        }
-
-        @Override
-        public String toString() {
-          return "no_match";
-        }
-      };
 }
diff --git a/lucene/queries/src/java/org/apache/lucene/queries/intervals/Intervals.java b/lucene/queries/src/java/org/apache/lucene/queries/intervals/Intervals.java
@@ -502,6 +502,15 @@ public static IntervalsSource after(IntervalsSource source, IntervalsSource refe
         Intervals.extend(new OffsetIntervalsSource(reference, false), 0, Integer.MAX_VALUE));
   }
 
+  /**
+   * Returns a source that produces no intervals
+   *
+   * @param reason A reason string that will appear in the toString output of this source
+   */
+  public static IntervalsSource noIntervals(String reason) {
+    return new NoMatchIntervalsSource(reason);
+  }
+
   /**
    * Returns intervals that correspond to tokens from a {@link TokenStream} returned for {@code
    * text} by applying the provided {@link Analyzer} as if {@code text} was the content of the given

diff --git a/lucene/queries/src/test/org/apache/lucene/queries/intervals/TestIntervalBuilder.java b/lucene/queries/src/test/org/apache/lucene/queries/intervals/TestIntervalBuilder.java
@@ -46,7 +46,6 @@
 import org.apache.lucene.index.DirectoryReader;
 import org.apache.lucene.index.IndexReader;
 import org.apache.lucene.index.LeafReaderContext;
-import org.apache.lucene.search.DocIdSetIterator;
 import org.apache.lucene.store.Directory;
 import org.apache.lucene.tests.analysis.CannedTokenStream;
 import org.apache.lucene.tests.analysis.Token;
@@ -115,7 +114,7 @@ public void testPhraseWithStopword() throws IOException {
   public void testEmptyTokenStream() throws IOException {
     CannedTokenStream ts = new CannedTokenStream();
     IntervalsSource source = IntervalBuilder.analyzeText(new CachingTokenFilter(ts), 0, true);
-    assertSame(IntervalBuilder.NO_INTERVALS, source);
+    assertEquals(Intervals.noIntervals("No terms in analyzed text"), source);
   }
 
   public void testSimpleSynonyms() throws IOException {
@@ -235,18 +234,8 @@ public void testEmptyIntervals() throws IOException {
     IndexReader reader = DirectoryReader.open(directory);
     LeafReaderContext ctx = reader.leaves().get(0);
 
-    {
-      IntervalIterator it = source.intervals("field", ctx);
-      assertEquals(-1, it.docID());
-      it.nextDoc();
-      assertEquals(DocIdSetIterator.NO_MORE_DOCS, it.docID());
-    }
-    {
-      IntervalIterator it = source.intervals("field", ctx);
-      assertEquals(-1, it.docID());
-      it.advance(1);
-      assertEquals(DocIdSetIterator.NO_MORE_DOCS, it.docID());
-    }
+    IntervalIterator it = source.intervals("field", ctx);
+    assertNull(it);
 
     reader.close();
     directory.close();