pylucene 3.5.0-3

[pylucene.git] / lucene-java-3.5.0 / lucene / contrib / grouping / src / java / org / apache / lucene / search / grouping / TermAllGroupsCollector.java

diff --git a/lucene-java-3.5.0/lucene/contrib/grouping/src/java/org/apache/lucene/search/grouping/TermAllGroupsCollector.java b/lucene-java-3.5.0/lucene/contrib/grouping/src/java/org/apache/lucene/search/grouping/TermAllGroupsCollector.java
new file mode 100644 (file)
index 0000000..2494276
--- /dev/null
+++ b/lucene-java-3.5.0/lucene/contrib/grouping/src/java/org/apache/lucene/search/grouping/TermAllGroupsCollector.java
@@ -0,0 +1,109 @@
+package org.apache.lucene.search.grouping;
+
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import org.apache.lucene.index.IndexReader;
+import org.apache.lucene.search.FieldCache;
+
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.Collection;
+import java.util.List;
+
+/**
+ * A collector that collects all groups that match the
+ * query. Only the group value is collected, and the order
+ * is undefined.  This collector does not determine
+ * the most relevant document of a group.
+ *
+ * <p/>
+ * Implementation detail: an int hash set (SentinelIntSet)
+ * is used to detect if a group is already added to the
+ * total count.  For each segment the int set is cleared and filled
+ * with previous counted groups that occur in the new
+ * segment.
+ *
+ * @lucene.experimental
+ */
+public class TermAllGroupsCollector extends AbstractAllGroupsCollector<String> {
+
+  private static final int DEFAULT_INITIAL_SIZE = 128;
+
+  private final String groupField;
+  private final SentinelIntSet ordSet;
+  private final List<String> groups;
+
+  private FieldCache.StringIndex index;
+
+  /**
+   * Expert: Constructs a {@link AbstractAllGroupsCollector}
+   *
+   * @param groupField  The field to group by
+   * @param initialSize The initial allocation size of the
+   *                    internal int set and group list
+   *                    which should roughly match the total
+   *                    number of expected unique groups. Be aware that the
+   *                    heap usage is 4 bytes * initialSize.
+   */
+  public TermAllGroupsCollector(String groupField, int initialSize) {
+    ordSet = new SentinelIntSet(initialSize, -1);
+    groups = new ArrayList<String>(initialSize);
+    this.groupField = groupField;
+  }
+
+  /**
+   * Constructs a {@link AbstractAllGroupsCollector}. This sets the
+   * initial allocation size for the internal int set and group
+   * list to 128.
+   *
+   * @param groupField The field to group by
+   */
+  public TermAllGroupsCollector(String groupField) {
+    this(groupField, DEFAULT_INITIAL_SIZE);
+  }
+
+  public void collect(int doc) throws IOException {
+    int key = index.order[doc];
+    if (!ordSet.exists(key)) {
+      ordSet.put(key);
+      String term = key == 0 ? null : index.lookup[key];
+      groups.add(term);
+    }
+  }
+
+  /**
+   * {@inheritDoc}
+   */
+  public Collection<String> getGroups() {
+    return groups;
+  }
+
+  public void setNextReader(IndexReader reader, int docBase) throws IOException {
+    index = FieldCache.DEFAULT.getStringIndex(reader, groupField);
+
+    // Clear ordSet and fill it with previous encountered groups that can occur in the current segment.
+    ordSet.clear();
+    for (String countedGroup : groups) {
+      int ord = index.binarySearchLookup(countedGroup);
+      if (ord >= 0) {
+        ordSet.put(ord);
+      }
+    }
+  }
+
+}