incubator-directmemory-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From tomm...@apache.org
Subject svn commit: r1224830 [1/2] - in /incubator/directmemory/trunk/examples: ./ src/ src/main/ src/main/java/ src/main/java/org/ src/main/java/org/apache/ src/main/java/org/apache/directmemory/ src/main/java/org/apache/directmemory/examples/ src/main/java/o...
Date Mon, 26 Dec 2011 22:51:21 GMT
Author: tommaso
Date: Mon Dec 26 22:51:20 2011
New Revision: 1224830

URL: http://svn.apache.org/viewvc?rev=1224830&view=rev
Log:
[DIRECTMEMORY-39] - create an example module, specifically adding a SolrCache using DM

Added:
    incubator/directmemory/trunk/examples/   (with props)
    incubator/directmemory/trunk/examples/pom.xml
    incubator/directmemory/trunk/examples/src/
    incubator/directmemory/trunk/examples/src/main/
    incubator/directmemory/trunk/examples/src/main/java/
    incubator/directmemory/trunk/examples/src/main/java/org/
    incubator/directmemory/trunk/examples/src/main/java/org/apache/
    incubator/directmemory/trunk/examples/src/main/java/org/apache/directmemory/
    incubator/directmemory/trunk/examples/src/main/java/org/apache/directmemory/examples/
    incubator/directmemory/trunk/examples/src/main/java/org/apache/directmemory/examples/solr/
    incubator/directmemory/trunk/examples/src/main/java/org/apache/directmemory/examples/solr/SolrOffHeapCache.java
    incubator/directmemory/trunk/examples/src/test/
    incubator/directmemory/trunk/examples/src/test/java/
    incubator/directmemory/trunk/examples/src/test/java/org/
    incubator/directmemory/trunk/examples/src/test/java/org/apache/
    incubator/directmemory/trunk/examples/src/test/java/org/apache/directmemory/
    incubator/directmemory/trunk/examples/src/test/java/org/apache/directmemory/examples/
    incubator/directmemory/trunk/examples/src/test/java/org/apache/directmemory/examples/solr/
    incubator/directmemory/trunk/examples/src/test/java/org/apache/directmemory/examples/solr/SolrOffHeapIntegrationTest.java
    incubator/directmemory/trunk/examples/src/test/resources/
    incubator/directmemory/trunk/examples/src/test/resources/solr/
    incubator/directmemory/trunk/examples/src/test/resources/solr/config/
    incubator/directmemory/trunk/examples/src/test/resources/solr/config/admin-extra.html
    incubator/directmemory/trunk/examples/src/test/resources/solr/config/elevate.xml
    incubator/directmemory/trunk/examples/src/test/resources/solr/config/mapping-ISOLatin1Accent.txt
    incubator/directmemory/trunk/examples/src/test/resources/solr/config/protwords.txt
    incubator/directmemory/trunk/examples/src/test/resources/solr/config/schema.xml
    incubator/directmemory/trunk/examples/src/test/resources/solr/config/scripts.conf
    incubator/directmemory/trunk/examples/src/test/resources/solr/config/solrconfig.xml
    incubator/directmemory/trunk/examples/src/test/resources/solr/config/stopwords.txt
    incubator/directmemory/trunk/examples/src/test/resources/solr/config/synonyms.txt
    incubator/directmemory/trunk/examples/src/test/resources/solr/config/xslt/
    incubator/directmemory/trunk/examples/src/test/resources/solr/config/xslt/example.xsl
    incubator/directmemory/trunk/examples/src/test/resources/solr/config/xslt/example_atom.xsl
    incubator/directmemory/trunk/examples/src/test/resources/solr/config/xslt/example_rss.xsl
    incubator/directmemory/trunk/examples/src/test/resources/solr/config/xslt/luke.xsl
    incubator/directmemory/trunk/examples/src/test/resources/solr/protwords.txt
    incubator/directmemory/trunk/examples/src/test/resources/solr/stopwords.txt
    incubator/directmemory/trunk/examples/src/test/resources/solr/synonyms.txt

Propchange: incubator/directmemory/trunk/examples/
------------------------------------------------------------------------------
--- svn:ignore (added)
+++ svn:ignore Mon Dec 26 22:51:20 2011
@@ -0,0 +1,3 @@
+target
+
+*.iml

Added: incubator/directmemory/trunk/examples/pom.xml
URL: http://svn.apache.org/viewvc/incubator/directmemory/trunk/examples/pom.xml?rev=1224830&view=auto
==============================================================================
--- incubator/directmemory/trunk/examples/pom.xml (added)
+++ incubator/directmemory/trunk/examples/pom.xml Mon Dec 26 22:51:20 2011
@@ -0,0 +1,104 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!--
+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.
+-->
+<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+
+  <modelVersion>4.0.0</modelVersion>
+
+  <parent>
+    <groupId>org.apache.directmemory</groupId>
+    <artifactId>directmemory-parent</artifactId>
+    <version>0.5.5-SNAPSHOT</version>
+    <relativePath>../</relativePath>
+  </parent>
+
+  <artifactId>directmemory-examples</artifactId>
+  <name>Apache DirectMemory :: Cache</name>
+  <packaging>bundle</packaging>
+
+  <properties>
+    <osgi.import>
+      org.apache.directmemory.*,
+      org.apache.solr.*
+    </osgi.import>
+    <osgi.export>org.apache.directmemory.examples.*;version="${project.version}</osgi.export>
+  </properties>
+
+
+  <build>
+    <plugins>
+      <plugin>
+        <groupId>org.apache.maven.plugins</groupId>
+        <artifactId>maven-clean-plugin</artifactId>
+        <configuration>
+          <filesets>
+            <fileset>
+              <directory>logs</directory>
+              <followSymlinks>false</followSymlinks>
+            </fileset>
+          </filesets>
+        </configuration>
+      </plugin>
+
+      <plugin>
+        <groupId>org.apache.maven.plugins</groupId>
+        <artifactId>maven-surefire-plugin</artifactId>
+        <version>2.9</version>
+        <configuration>
+          <argLine>-Xmx512m -Xms512m -XX:MaxDirectMemorySize=512m</argLine>
+        </configuration>
+      </plugin>
+    </plugins>
+  </build>
+
+  <dependencies>
+    <dependency>
+      <groupId>org.slf4j</groupId>
+      <artifactId>slf4j-simple</artifactId>
+      <version>1.6.1</version>
+    </dependency>
+
+    <dependency>
+      <groupId>org.apache.directmemory</groupId>
+      <artifactId>directmemory-cache</artifactId>
+      <version>0.5.5-SNAPSHOT</version>
+    </dependency>
+
+    <dependency>
+      <groupId>junit</groupId>
+      <artifactId>junit</artifactId>
+      <version>4.8.2</version>
+      <scope>test</scope>
+    </dependency>
+
+    <dependency>
+      <groupId>org.apache.solr</groupId>
+      <artifactId>solr-core</artifactId>
+      <version>3.5.0</version>
+    </dependency>
+
+    <dependency>
+      <groupId>org.apache.solr</groupId>
+      <artifactId>solr-test-framework</artifactId>
+      <version>3.5.0</version>
+    </dependency>
+  </dependencies>
+
+</project>

Added: incubator/directmemory/trunk/examples/src/main/java/org/apache/directmemory/examples/solr/SolrOffHeapCache.java
URL: http://svn.apache.org/viewvc/incubator/directmemory/trunk/examples/src/main/java/org/apache/directmemory/examples/solr/SolrOffHeapCache.java?rev=1224830&view=auto
==============================================================================
--- incubator/directmemory/trunk/examples/src/main/java/org/apache/directmemory/examples/solr/SolrOffHeapCache.java (added)
+++ incubator/directmemory/trunk/examples/src/main/java/org/apache/directmemory/examples/solr/SolrOffHeapCache.java Mon Dec 26 22:51:20 2011
@@ -0,0 +1,208 @@
+/**
+ * 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.
+ */
+package org.apache.directmemory.examples.solr;
+
+import org.apache.directmemory.cache.Cache;
+import org.apache.directmemory.measures.Ram;
+import org.apache.solr.common.util.NamedList;
+import org.apache.solr.common.util.SimpleOrderedMap;
+import org.apache.solr.core.SolrCore;
+import org.apache.solr.search.CacheRegenerator;
+import org.apache.solr.search.SolrCache;
+import org.apache.solr.search.SolrIndexSearcher;
+
+import java.io.IOException;
+import java.net.URL;
+import java.util.Map;
+import java.util.concurrent.atomic.AtomicLong;
+
+/**
+ * A {@link SolrCache} based on Apache DirectMemory
+ */
+public class SolrOffHeapCache<K, V> implements SolrCache<K, V> {
+
+  private static class CumulativeStats {
+    AtomicLong lookups = new AtomicLong();
+    AtomicLong hits = new AtomicLong();
+    AtomicLong inserts = new AtomicLong();
+    AtomicLong evictions = new AtomicLong();
+  }
+
+  private CumulativeStats stats;
+
+  private long lookups;
+  private long hits;
+  private long inserts;
+  private long evictions;
+
+  private long warmupTime = 0;
+
+  private String name;
+  private int autowarmCount;
+  private State state;
+  private CacheRegenerator regenerator;
+  private String description = "DM Cache";
+
+  @Override
+  public Object init(Map args, Object persistence, CacheRegenerator regenerator) {
+    Object buffers = args.get("buffers");
+    String size = String.valueOf(args.get("size"));
+    Cache.init(buffers != null ? Integer.valueOf(String.valueOf(buffers)) : 1, Ram.Mb(Double.valueOf(size) / 512));
+
+    state = State.CREATED;
+    this.regenerator = regenerator;
+    name = (String) args.get("name");
+    String str = size;
+    final int limit = str == null ? 1024 : Integer.parseInt(str);
+    str = (String) args.get("initialSize");
+    final int initialSize = Math.min(str == null ? 1024 : Integer.parseInt(str), limit);
+    str = (String) args.get("autowarmCount");
+    autowarmCount = str == null ? 0 : Integer.parseInt(str);
+
+    description = "Solr OffHeap Cache(maxSize=" + limit + ", initialSize=" + initialSize;
+    if (autowarmCount > 0) {
+      description += ", autowarmCount=" + autowarmCount
+              + ", regenerator=" + regenerator;
+    }
+    description += ')';
+
+    if (persistence == null) {
+      // must be the first time a cache of this type is being created
+      persistence = new CumulativeStats();
+    }
+
+    stats = (CumulativeStats) persistence;
+
+    return persistence;
+  }
+
+  @Override
+  public String name() {
+    return name;
+  }
+
+  @Override
+  public int size() {
+    return Long.valueOf(Cache.entries()).intValue();
+  }
+
+  // START SNIPPET: solrcache
+  @Override
+  public V put(K key, V value) {
+    return (V) Cache.put(String.valueOf(key), value);
+  }
+
+  @Override
+  public V get(K key) {
+    return (V) Cache.retrieve(String.valueOf(key));
+  }
+  // END SNIPPET: solrcache
+
+  @Override
+  public void clear() {
+    synchronized (this) {
+      Cache.clear();
+    }
+  }
+
+  @Override
+  public void setState(State state) {
+    this.state = state;
+  }
+
+  @Override
+  public State getState() {
+    return state;
+  }
+
+  @Override
+  public void warm(SolrIndexSearcher searcher, SolrCache<K, V> old) throws IOException {
+    // it looks like there is no point in warming an off heap item
+  }
+
+  @Override
+  public void close() {
+  }
+
+  @Override
+  public String getName() {
+    return SolrOffHeapCache.class.getName();
+  }
+
+  @Override
+  public String getVersion() {
+    return SolrCore.version;
+  }
+
+  public String getDescription() {
+    return description;
+  }
+
+  public Category getCategory() {
+    return Category.CACHE;
+  }
+
+  @Override
+  public String getSourceId() {
+    return null;
+  }
+
+  @Override
+  public String getSource() {
+    return null;
+  }
+
+  @Override
+  public URL[] getDocs() {
+    return new URL[0];
+  }
+
+  public NamedList getStatistics() {
+    NamedList lst = new SimpleOrderedMap();
+    synchronized (this) {
+      lst.add("lookups", lookups);
+      lst.add("hits", hits);
+      lst.add("hitratio", calcHitRatio(lookups, hits));
+      lst.add("inserts", inserts);
+      lst.add("evictions", evictions);
+      lst.add("size", Cache.entries());
+    }
+
+    lst.add("warmupTime", warmupTime);
+
+    long clookups = stats.lookups.get();
+    long chits = stats.hits.get();
+    lst.add("cumulative_lookups", clookups);
+    lst.add("cumulative_hits", chits);
+    lst.add("cumulative_hitratio", calcHitRatio(clookups, chits));
+    lst.add("cumulative_inserts", stats.inserts.get());
+    lst.add("cumulative_evictions", stats.evictions.get());
+
+    return lst;
+  }
+
+  private Object calcHitRatio(long clookups, long chits) {
+    int ones = (int) (hits * 100 / lookups);
+    int tenths = (int) (hits * 1000 / lookups) - ones * 10;
+    return Integer.toString(ones) + '.' + tenths;
+  }
+
+  @Override
+  public String toString() {
+    return name + getStatistics().toString();
+  }
+}

Added: incubator/directmemory/trunk/examples/src/test/java/org/apache/directmemory/examples/solr/SolrOffHeapIntegrationTest.java
URL: http://svn.apache.org/viewvc/incubator/directmemory/trunk/examples/src/test/java/org/apache/directmemory/examples/solr/SolrOffHeapIntegrationTest.java?rev=1224830&view=auto
==============================================================================
--- incubator/directmemory/trunk/examples/src/test/java/org/apache/directmemory/examples/solr/SolrOffHeapIntegrationTest.java (added)
+++ incubator/directmemory/trunk/examples/src/test/java/org/apache/directmemory/examples/solr/SolrOffHeapIntegrationTest.java Mon Dec 26 22:51:20 2011
@@ -0,0 +1,61 @@
+/**
+ * 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.
+ */
+package org.apache.directmemory.examples.solr;
+
+import org.apache.directmemory.cache.Cache;
+import org.apache.solr.request.LocalSolrQueryRequest;
+import org.apache.solr.util.TestHarness;
+import org.junit.Before;
+import org.junit.Test;
+
+import static org.junit.Assert.assertTrue;
+import static org.junit.Assert.fail;
+
+/**
+ */
+public class SolrOffHeapIntegrationTest {
+  private TestHarness h;
+
+  @Before
+  public void setUp() {
+    String data = "target/data/expand";
+    String config = this.getClass().getResource("/solr/config/solrconfig.xml").getFile();
+    String schema = this.getClass().getResource("/solr/config/schema.xml").getFile();
+    this.h = new TestHarness(data, config, schema);
+  }
+
+  @Test
+  public void testSimpleQuery() {
+    try {
+      // add a doc to Solr
+      h.validateAddDoc("id", "1", "text", "something is happening here");
+
+      // make the query
+      LocalSolrQueryRequest request = h.getRequestFactory("standard", 0, 100).makeRequest("q", "something");
+      String response = h.query("standard", request);
+      assertTrue(response != null);
+      assertTrue(!response.contains("error"));
+
+      // check the cache has been hit
+      assertTrue(Cache.entries() > 0);
+
+    } catch (Throwable e) {
+      e.printStackTrace();
+      fail(e.getLocalizedMessage());
+    }
+  }
+}

Added: incubator/directmemory/trunk/examples/src/test/resources/solr/config/admin-extra.html
URL: http://svn.apache.org/viewvc/incubator/directmemory/trunk/examples/src/test/resources/solr/config/admin-extra.html?rev=1224830&view=auto
==============================================================================
--- incubator/directmemory/trunk/examples/src/test/resources/solr/config/admin-extra.html (added)
+++ incubator/directmemory/trunk/examples/src/test/resources/solr/config/admin-extra.html Mon Dec 26 22:51:20 2011
@@ -0,0 +1,31 @@
+<!--
+ 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.
+-->
+
+<!-- The content of this page will be statically included into the top
+of the admin page.  Uncomment this as an example to see there the content
+will show up.
+
+<hr>
+<i>This line will appear before the first table</i>
+<tr>
+<td colspan="2">
+This row will be appended to the end of the first table
+</td>
+</tr>
+<hr>
+
+-->

Added: incubator/directmemory/trunk/examples/src/test/resources/solr/config/elevate.xml
URL: http://svn.apache.org/viewvc/incubator/directmemory/trunk/examples/src/test/resources/solr/config/elevate.xml?rev=1224830&view=auto
==============================================================================
--- incubator/directmemory/trunk/examples/src/test/resources/solr/config/elevate.xml (added)
+++ incubator/directmemory/trunk/examples/src/test/resources/solr/config/elevate.xml Mon Dec 26 22:51:20 2011
@@ -0,0 +1,38 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ 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.
+-->
+
+<!-- If this file is found in the config directory, it will only be
+     loaded once at startup.  If it is found in Solr's data
+     directory, it will be re-loaded every commit.
+-->
+
+<elevate>
+  <query text="foo bar">
+    <doc id="1"/>
+    <doc id="2"/>
+    <doc id="3"/>
+  </query>
+
+  <query text="ipod">
+    <doc id="MA147LL/A"/>
+    <!-- put the actual ipod at the top -->
+    <doc id="IW-02" exclude="true"/>
+    <!-- exclude this cable -->
+  </query>
+
+</elevate>

Added: incubator/directmemory/trunk/examples/src/test/resources/solr/config/mapping-ISOLatin1Accent.txt
URL: http://svn.apache.org/viewvc/incubator/directmemory/trunk/examples/src/test/resources/solr/config/mapping-ISOLatin1Accent.txt?rev=1224830&view=auto
==============================================================================
--- incubator/directmemory/trunk/examples/src/test/resources/solr/config/mapping-ISOLatin1Accent.txt (added)
+++ incubator/directmemory/trunk/examples/src/test/resources/solr/config/mapping-ISOLatin1Accent.txt Mon Dec 26 22:51:20 2011
@@ -0,0 +1,246 @@
+# 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.
+
+# Syntax:
+#   "source" => "target"
+#     "source".length() > 0 (source cannot be empty.)
+#     "target".length() >= 0 (target can be empty.)
+
+# example:
+#   "À" => "A"
+#   "\u00C0" => "A"
+#   "\u00C0" => "\u0041"
+#   "ß" => "ss"
+#   "\t" => " "
+#   "\n" => ""
+
+# À => A
+"\u00C0" => "A"
+
+# Á => A
+"\u00C1" => "A"
+
+# Â => A
+"\u00C2" => "A"
+
+# Ã => A
+"\u00C3" => "A"
+
+# Ä => A
+"\u00C4" => "A"
+
+# Å => A
+"\u00C5" => "A"
+
+# Æ => AE
+"\u00C6" => "AE"
+
+# Ç => C
+"\u00C7" => "C"
+
+# È => E
+"\u00C8" => "E"
+
+# É => E
+"\u00C9" => "E"
+
+# Ê => E
+"\u00CA" => "E"
+
+# Ë => E
+"\u00CB" => "E"
+
+# Ì => I
+"\u00CC" => "I"
+
+# Í => I
+"\u00CD" => "I"
+
+# Î => I
+"\u00CE" => "I"
+
+# Ï => I
+"\u00CF" => "I"
+
+# IJ => IJ
+"\u0132" => "IJ"
+
+# Ð => D
+"\u00D0" => "D"
+
+# Ñ => N
+"\u00D1" => "N"
+
+# Ò => O
+"\u00D2" => "O"
+
+# Ó => O
+"\u00D3" => "O"
+
+# Ô => O
+"\u00D4" => "O"
+
+# Õ => O
+"\u00D5" => "O"
+
+# Ö => O
+"\u00D6" => "O"
+
+# Ø => O
+"\u00D8" => "O"
+
+# Π=> OE
+"\u0152" => "OE"
+
+# Þ
+"\u00DE" => "TH"
+
+# Ù => U
+"\u00D9" => "U"
+
+# Ú => U
+"\u00DA" => "U"
+
+# Û => U
+"\u00DB" => "U"
+
+# Ü => U
+"\u00DC" => "U"
+
+# Ý => Y
+"\u00DD" => "Y"
+
+# Ÿ => Y
+"\u0178" => "Y"
+
+# à => a
+"\u00E0" => "a"
+
+# á => a
+"\u00E1" => "a"
+
+# â => a
+"\u00E2" => "a"
+
+# ã => a
+"\u00E3" => "a"
+
+# ä => a
+"\u00E4" => "a"
+
+# å => a
+"\u00E5" => "a"
+
+# æ => ae
+"\u00E6" => "ae"
+
+# ç => c
+"\u00E7" => "c"
+
+# è => e
+"\u00E8" => "e"
+
+# é => e
+"\u00E9" => "e"
+
+# ê => e
+"\u00EA" => "e"
+
+# ë => e
+"\u00EB" => "e"
+
+# ì => i
+"\u00EC" => "i"
+
+# í => i
+"\u00ED" => "i"
+
+# î => i
+"\u00EE" => "i"
+
+# ï => i
+"\u00EF" => "i"
+
+# ij => ij
+"\u0133" => "ij"
+
+# ð => d
+"\u00F0" => "d"
+
+# ñ => n
+"\u00F1" => "n"
+
+# ò => o
+"\u00F2" => "o"
+
+# ó => o
+"\u00F3" => "o"
+
+# ô => o
+"\u00F4" => "o"
+
+# õ => o
+"\u00F5" => "o"
+
+# ö => o
+"\u00F6" => "o"
+
+# ø => o
+"\u00F8" => "o"
+
+# œ => oe
+"\u0153" => "oe"
+
+# ß => ss
+"\u00DF" => "ss"
+
+# þ => th
+"\u00FE" => "th"
+
+# ù => u
+"\u00F9" => "u"
+
+# ú => u
+"\u00FA" => "u"
+
+# û => u
+"\u00FB" => "u"
+
+# ü => u
+"\u00FC" => "u"
+
+# ý => y
+"\u00FD" => "y"
+
+# ÿ => y
+"\u00FF" => "y"
+
+# ff => ff
+"\uFB00" => "ff"
+
+# fi => fi
+"\uFB01" => "fi"
+
+# fl => fl
+"\uFB02" => "fl"
+
+# ffi => ffi
+"\uFB03" => "ffi"
+
+# ffl => ffl
+"\uFB04" => "ffl"
+
+# ſt => ft
+"\uFB05" => "ft"
+
+# st => st
+"\uFB06" => "st"

Added: incubator/directmemory/trunk/examples/src/test/resources/solr/config/protwords.txt
URL: http://svn.apache.org/viewvc/incubator/directmemory/trunk/examples/src/test/resources/solr/config/protwords.txt?rev=1224830&view=auto
==============================================================================
--- incubator/directmemory/trunk/examples/src/test/resources/solr/config/protwords.txt (added)
+++ incubator/directmemory/trunk/examples/src/test/resources/solr/config/protwords.txt Mon Dec 26 22:51:20 2011
@@ -0,0 +1,21 @@
+# 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.
+
+#-----------------------------------------------------------------------
+# Use a protected word file to protect against the stemmer reducing two
+# unrelated words to the same base word.
+
+# Some non-words that normally won't be encountered,
+# just to test that they won't be stemmed.
+dontstems
+zwhacky
+

Added: incubator/directmemory/trunk/examples/src/test/resources/solr/config/schema.xml
URL: http://svn.apache.org/viewvc/incubator/directmemory/trunk/examples/src/test/resources/solr/config/schema.xml?rev=1224830&view=auto
==============================================================================
--- incubator/directmemory/trunk/examples/src/test/resources/solr/config/schema.xml (added)
+++ incubator/directmemory/trunk/examples/src/test/resources/solr/config/schema.xml Mon Dec 26 22:51:20 2011
@@ -0,0 +1,581 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ 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.
+-->
+
+<!--  
+ This is the Solr schema file. This file should be named "schema.xml" and
+ should be in the conf directory under the solr home
+ (i.e. ./solr/conf/schema.xml by default) 
+ or located where the classloader for the Solr webapp can find it.
+
+ This example schema is the recommended starting point for users.
+ It should be kept correct and concise, usable out-of-the-box.
+
+ For more information, on how to customize this file, please see
+ http://wiki.apache.org/solr/SchemaXml
+
+ PERFORMANCE NOTE: this schema includes many optional features and should not
+ be used for benchmarking.  To improve performance one could
+  - set stored="false" for all fields possible (esp large fields) when you
+    only need to search on the field but don't need to return the original
+    value.
+  - set indexed="false" if you don't need to search on the field, but only
+    return the field as a result of searching on other indexed fields.
+  - remove all unneeded copyField statements
+  - for best index size and searching performance, set "index" to false
+    for all general text fields, use copyField to copy them to the
+    catchall "text" field, and use that for searching.
+  - For maximum indexing performance, use the StreamingUpdateSolrServer
+    java client.
+  - Remember to run the JVM in server mode, and use a higher logging level
+    that avoids logging every request
+-->
+
+<schema name="example" version="1.2">
+  <!-- attribute "name" is the name of this schema and is only used for display purposes.
+       Applications should change this to reflect the nature of the search collection.
+       version="1.2" is Solr's version number for the schema syntax and semantics.  It should
+       not normally be changed by applications.
+       1.0: multiValued attribute did not exist, all fields are multiValued by nature
+       1.1: multiValued attribute introduced, false by default 
+       1.2: omitTermFreqAndPositions attribute introduced, true by default except for text fields.
+     -->
+
+  <types>
+    <!-- field type definitions. The "name" attribute is
+       just a label to be used by field definitions.  The "class"
+       attribute and any other attributes determine the real
+       behavior of the fieldType.
+         Class names starting with "solr" refer to java classes in the
+       org.apache.solr.analysis package.
+    -->
+
+    <!-- The StrField type is not analyzed, but indexed/stored verbatim.  
+       - StrField and TextField support an optional compressThreshold which
+       limits compression (if enabled in the derived fields) to values which
+       exceed a certain size (in characters).
+    -->
+    <fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
+
+    <!-- boolean type: "true" or "false" -->
+    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
+    <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
+    <fieldtype name="binary" class="solr.BinaryField"/>
+
+    <!-- The optional sortMissingLast and sortMissingFirst attributes are
+         currently supported on types that are sorted internally as strings.
+	       This includes "string","boolean","sint","slong","sfloat","sdouble","pdate"
+       - If sortMissingLast="true", then a sort on this field will cause documents
+         without the field to come after documents with the field,
+         regardless of the requested sort order (asc or desc).
+       - If sortMissingFirst="true", then a sort on this field will cause documents
+         without the field to come before documents with the field,
+         regardless of the requested sort order.
+       - If sortMissingLast="false" and sortMissingFirst="false" (the default),
+         then default lucene sorting will be used which places docs without the
+         field first in an ascending sort and last in a descending sort.
+    -->
+
+    <!--
+      Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
+    -->
+    <fieldType name="int" class="solr.TrieIntField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
+    <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
+    <fieldType name="long" class="solr.TrieLongField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
+    <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
+
+    <!--
+     Numeric field types that index each value at various levels of precision
+     to accelerate range queries when the number of values between the range
+     endpoints is large. See the javadoc for NumericRangeQuery for internal
+     implementation details.
+
+     Smaller precisionStep values (specified in bits) will lead to more tokens
+     indexed per value, slightly larger index size, and faster range queries.
+     A precisionStep of 0 disables indexing at different precision levels.
+    -->
+    <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
+    <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
+    <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
+    <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
+
+    <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
+         is a more restricted form of the canonical representation of dateTime
+         http://www.w3.org/TR/xmlschema-2/#dateTime    
+         The trailing "Z" designates UTC time and is mandatory.
+         Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
+         All other components are mandatory.
+
+         Expressions can also be used to denote calculations that should be
+         performed relative to "NOW" to determine the value, ie...
+
+               NOW/HOUR
+                  ... Round to the start of the current hour
+               NOW-1DAY
+                  ... Exactly 1 day prior to now
+               NOW/DAY+6MONTHS+3DAYS
+                  ... 6 months and 3 days in the future from the start of
+                      the current day
+                      
+         Consult the DateField javadocs for more information.
+
+         Note: For faster range queries, consider the tdate type
+      -->
+    <fieldType name="date" class="solr.TrieDateField" omitNorms="true" precisionStep="0" positionIncrementGap="0"/>
+
+    <!-- A Trie based date field for faster date range queries and date faceting. -->
+    <fieldType name="tdate" class="solr.TrieDateField" omitNorms="true" precisionStep="6" positionIncrementGap="0"/>
+
+
+    <!--
+      Note:
+      These should only be used for compatibility with existing indexes (created with older Solr versions)
+      or if "sortMissingFirst" or "sortMissingLast" functionality is needed. Use Trie based fields instead.
+
+      Plain numeric field types that store and index the text
+      value verbatim (and hence don't support range queries, since the
+      lexicographic ordering isn't equal to the numeric ordering)
+    -->
+    <fieldType name="pint" class="solr.IntField" omitNorms="true"/>
+    <fieldType name="plong" class="solr.LongField" omitNorms="true"/>
+    <fieldType name="pfloat" class="solr.FloatField" omitNorms="true"/>
+    <fieldType name="pdouble" class="solr.DoubleField" omitNorms="true"/>
+    <fieldType name="pdate" class="solr.DateField" sortMissingLast="true" omitNorms="true"/>
+
+
+    <!--
+      Note:
+      These should only be used for compatibility with existing indexes (created with older Solr versions)
+      or if "sortMissingFirst" or "sortMissingLast" functionality is needed. Use Trie based fields instead.
+
+      Numeric field types that manipulate the value into
+      a string value that isn't human-readable in its internal form,
+      but with a lexicographic ordering the same as the numeric ordering,
+      so that range queries work correctly.
+    -->
+    <fieldType name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true"/>
+    <fieldType name="slong" class="solr.SortableLongField" sortMissingLast="true" omitNorms="true"/>
+    <fieldType name="sfloat" class="solr.SortableFloatField" sortMissingLast="true" omitNorms="true"/>
+    <fieldType name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true" omitNorms="true"/>
+
+
+    <!-- The "RandomSortField" is not used to store or search any
+         data.  You can declare fields of this type it in your schema
+         to generate pseudo-random orderings of your docs for sorting 
+         purposes.  The ordering is generated based on the field name 
+         and the version of the index, As long as the index version
+         remains unchanged, and the same field name is reused,
+         the ordering of the docs will be consistent.  
+         If you want different psuedo-random orderings of documents,
+         for the same version of the index, use a dynamicField and
+         change the name
+     -->
+    <fieldType name="random" class="solr.RandomSortField" indexed="true"/>
+
+    <!-- solr.TextField allows the specification of custom text analyzers
+         specified as a tokenizer and a list of token filters. Different
+         analyzers may be specified for indexing and querying.
+
+         The optional positionIncrementGap puts space between multiple fields of
+         this type on the same document, with the purpose of preventing false phrase
+         matching across fields.
+
+         For more info on customizing your analyzer chain, please see
+         http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
+     -->
+
+    <!-- One can also specify an existing Analyzer class that has a
+         default constructor via the class attribute on the analyzer element
+    <fieldType name="text_greek" class="solr.TextField">
+      <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
+    </fieldType>
+    -->
+
+    <!-- A text field that only splits on whitespace for exact matching of words -->
+    <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- A text field that uses WordDelimiterFilter to enable splitting and matching of
+        words on case-change, alpha numeric boundaries, and non-alphanumeric chars,
+        so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
+        Synonyms and stopwords are customized by external files, and stemming is enabled.
+        -->
+    <fieldType name="text" class="solr.TextField" positionIncrementGap="100">
+      <analyzer type="index">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <!-- in this example, we will only use synonyms at query time
+        <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+        -->
+        <!-- Case insensitive stop word removal.
+          add enablePositionIncrements=true in both the index and query
+          analyzers to leave a 'gap' for more accurate phrase queries.
+        -->
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="solr/stopwords.txt"
+                enablePositionIncrements="true"
+                />
+        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+                catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.SnowballPorterFilterFactory" language="English" protected="solr/protwords.txt"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymFilterFactory" synonyms="solr/synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="solr/stopwords.txt"
+                enablePositionIncrements="true"
+                />
+        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+                catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.SnowballPorterFilterFactory" language="English" protected="solr/protwords.txt"/>
+      </analyzer>
+    </fieldType>
+
+
+    <!-- Less flexible matching, but less false matches.  Probably not ideal for product names,
+         but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
+    <fieldType name="textTight" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymFilterFactory" synonyms="solr/synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="solr/stopwords.txt"/>
+        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+                catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.SnowballPorterFilterFactory" language="English" protected="solr/protwords.txt"/>
+        <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+             possible with WordDelimiterFilter in conjuncton with stemming. -->
+        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+
+    <!-- A general unstemmed text field - good if one does not know the language of the field -->
+    <fieldType name="textgen" class="solr.TextField" positionIncrementGap="100">
+      <analyzer type="index">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="solr/stopwords.txt"
+                enablePositionIncrements="true"/>
+        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+                catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymFilterFactory" synonyms="solr/synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="solr/stopwords.txt"
+                enablePositionIncrements="true"
+                />
+        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+                catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+
+    <!-- A general unstemmed text field that indexes tokens normally and also
+         reversed (via ReversedWildcardFilterFactory), to enable more efficient 
+	 leading wildcard queries. -->
+    <fieldType name="text_rev" class="solr.TextField" positionIncrementGap="100">
+      <analyzer type="index">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="solr/stopwords.txt"
+                enablePositionIncrements="true"/>
+        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+                catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
+                maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymFilterFactory" synonyms="solr/synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="solr/stopwords.txt"
+                enablePositionIncrements="true"
+                />
+        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+                catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- charFilter + WhitespaceTokenizer  -->
+    <!--
+    <fieldType name="textCharNorm" class="solr.TextField" positionIncrementGap="100" >
+      <analyzer>
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+      </analyzer>
+    </fieldType>
+    -->
+
+    <!-- This is an example of using the KeywordTokenizer along
+         With various TokenFilterFactories to produce a sortable field
+         that does not include some properties of the source text
+      -->
+    <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
+      <analyzer>
+        <!-- KeywordTokenizer does no actual tokenizing, so the entire
+             input string is preserved as a single token
+          -->
+        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <!-- The LowerCase TokenFilter does what you expect, which can be
+             when you want your sorting to be case insensitive
+          -->
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <!-- The TrimFilter removes any leading or trailing whitespace -->
+        <filter class="solr.TrimFilterFactory"/>
+        <!-- The PatternReplaceFilter gives you the flexibility to use
+             Java Regular expression to replace any sequence of characters
+             matching a pattern with an arbitrary replacement string, 
+             which may include back references to portions of the original
+             string matched by the pattern.
+             
+             See the Java Regular Expression documentation for more
+             information on pattern and replacement string syntax.
+             
+             http://java.sun.com/j2se/1.5.0/docs/api/java/util/regex/package-summary.html
+          -->
+        <filter class="solr.PatternReplaceFilterFactory"
+                pattern="([^a-z])" replacement="" replace="all"
+                />
+      </analyzer>
+    </fieldType>
+
+    <fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
+      </analyzer>
+    </fieldtype>
+
+    <fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <!--
+        The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
+        a token of "foo|1.4"  would be indexed as "foo" with a payload of 1.4f
+        Attributes of the DelimitedPayloadTokenFilterFactory : 
+         "delimiter" - a one character delimiter. Default is | (pipe)
+	 "encoder" - how to encode the following value into a playload
+	    float -> org.apache.lucene.analysis.payloads.FloatEncoder,
+	    integer -> o.a.l.a.p.IntegerEncoder
+	    identity -> o.a.l.a.p.IdentityEncoder
+            Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
+         -->
+        <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
+      </analyzer>
+    </fieldtype>
+
+    <!-- lowercases the entire field value, keeping it as a single token.  -->
+    <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+
+    <!-- since fields of this type are by default not stored or indexed,
+         any data added to them will be ignored outright.  -->
+    <fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField"/>
+
+  </types>
+
+
+  <fields>
+    <!-- Valid attributes for fields:
+      name: mandatory - the name for the field
+      type: mandatory - the name of a previously defined type from the
+        <types> section
+      indexed: true if this field should be indexed (searchable or sortable)
+      stored: true if this field should be retrievable
+      compressed: [false] if this field should be stored using gzip compression
+        (this will only apply if the field type is compressable; among
+        the standard field types, only TextField and StrField are)
+      multiValued: true if this field may contain multiple values per document
+      omitNorms: (expert) set to true to omit the norms associated with
+        this field (this disables length normalization and index-time
+        boosting for the field, and saves some memory).  Only full-text
+        fields or fields that need an index-time boost need norms.
+      termVectors: [false] set to true to store the term vector for a
+        given field.
+        When using MoreLikeThis, fields used for similarity should be
+        stored for best performance.
+      termPositions: Store position information with the term vector.
+        This will increase storage costs.
+      termOffsets: Store offset information with the term vector. This
+        will increase storage costs.
+      default: a value that should be used if no value is specified
+        when adding a document.
+    -->
+
+    <field name="id" type="string" indexed="true" stored="true" required="true"/>
+    <field name="sku" type="textTight" indexed="true" stored="true" omitNorms="true"/>
+    <field name="name" type="textgen" indexed="true" stored="true"/>
+    <field name="alphaNameSort" type="alphaOnlySort" indexed="true" stored="false"/>
+    <field name="manu" type="textgen" indexed="true" stored="true" omitNorms="true"/>
+    <field name="cat" type="text_ws" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
+    <field name="features" type="text" indexed="true" stored="true" multiValued="true"/>
+    <field name="includes" type="text" indexed="true" stored="true" termVectors="true" termPositions="true"
+           termOffsets="true"/>
+
+    <field name="weight" type="float" indexed="true" stored="true"/>
+    <field name="price" type="float" indexed="true" stored="true"/>
+    <field name="popularity" type="int" indexed="true" stored="true"/>
+    <field name="inStock" type="boolean" indexed="true" stored="true"/>
+
+
+    <!-- Common metadata fields, named specifically to match up with
+      SolrCell metadata when parsing rich documents such as Word, PDF.
+      Some fields are multiValued only because Tika currently may return
+      multiple values for them.
+    -->
+    <field name="title" type="text" indexed="true" stored="true" multiValued="true"/>
+    <field name="subject" type="text" indexed="true" stored="true"/>
+    <field name="description" type="text" indexed="true" stored="true"/>
+    <field name="comments" type="text" indexed="true" stored="true"/>
+    <field name="author" type="textgen" indexed="true" stored="true"/>
+    <field name="keywords" type="textgen" indexed="true" stored="true"/>
+    <field name="category" type="textgen" indexed="true" stored="true"/>
+    <field name="content_type" type="string" indexed="true" stored="true" multiValued="true"/>
+    <field name="last_modified" type="date" indexed="true" stored="true"/>
+    <field name="links" type="string" indexed="true" stored="true" multiValued="true"/>
+
+
+    <!-- catchall field, containing all other searchable text fields (implemented
+via copyField further on in this schema  -->
+    <field name="text" type="text" indexed="true" stored="false" multiValued="true"/>
+
+    <!-- catchall text field that indexes tokens both normally and in reverse for efficient
+ leading wildcard queries. -->
+    <field name="text_rev" type="text_rev" indexed="true" stored="false" multiValued="true"/>
+
+    <!-- non-tokenized version of manufacturer to make it easier to sort or group
+results by manufacturer.  copied from "manu" via copyField -->
+    <field name="manu_exact" type="string" indexed="true" stored="false"/>
+
+    <field name="payloads" type="payloads" indexed="true" stored="true"/>
+
+    <!-- Uncommenting the following will create a "timestamp" field using
+       a default value of "NOW" to indicate when each document was indexed.
+    -->
+    <!--
+  <field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
+    -->
+    <field name="inserto" type="textgen" indexed="true" stored="true"/>
+    <field name="sezione" type="textgen" indexed="true" stored="true"/>
+    <field name="colonna" type="textgen" indexed="true" stored="true"/>
+    <dynamicField name="*_strict" type="textgen" indexed="true" stored="false" multiValued="true"/>
+    <!-- Dynamic field definitions.  If a field name is not found, dynamicFields
+will be used if the name matches any of the patterns.
+RESTRICTION: the glob-like pattern in the name attribute must have
+a "*" only at the start or the end.
+EXAMPLE:  name="*_i" will match any field ending in _i (like myid_i, z_i)
+Longer patterns will be matched first.  if equal size patterns
+both match, the first appearing in the schema will be used.  -->
+    <dynamicField name="*_i" type="int" indexed="true" stored="true"/>
+    <dynamicField name="*_s" type="string" indexed="true" stored="true"/>
+    <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
+    <dynamicField name="*_t" type="text" indexed="true" stored="true"/>
+    <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
+    <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
+    <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
+    <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
+
+    <!-- some trie-coded dynamic fields for faster range queries -->
+    <dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
+    <dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
+    <dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
+    <dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
+    <dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
+
+    <dynamicField name="*_pi" type="pint" indexed="true" stored="true"/>
+
+    <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
+    <dynamicField name="attr_*" type="textgen" indexed="true" stored="true" multiValued="true"/>
+
+    <dynamicField name="random_*" type="random"/>
+
+    <!-- uncomment the following to ignore any fields that don't already match an existing
+field name or dynamic field, rather than reporting them as an error.
+alternately, change the type="ignored" to some other type e.g. "text" if you want
+unknown fields indexed and/or stored by default -->
+    <!--dynamicField name="*" type="ignored" multiValued="true" /-->
+
+  </fields>
+
+  <!-- Field to use to determine and enforce document uniqueness.
+     Unless this field is marked with required="false", it will be a required field
+  -->
+  <uniqueKey>id</uniqueKey>
+
+  <!-- field for the QueryParser to use when an explicit fieldname is absent -->
+  <defaultSearchField>text</defaultSearchField>
+
+  <!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
+  <solrQueryParser defaultOperator="OR"/>
+
+  <!-- copyField commands copy one field to another at the time a document
+        is added to the index.  It's used either to index the same field differently,
+        or to add multiple fields to the same field for easier/faster searching.  -->
+
+  <copyField source="cat" dest="text"/>
+  <copyField source="name" dest="text"/>
+  <copyField source="manu" dest="text"/>
+  <copyField source="features" dest="text"/>
+  <copyField source="includes" dest="text"/>
+  <copyField source="manu" dest="manu_exact"/>
+
+  <!-- Above, multiple source fields are copied to the [text] field.
+     Another way to map multiple source fields to the same
+     destination field is to use the dynamic field syntax.
+     copyField also supports a maxChars to copy setting.  -->
+
+  <!-- <copyField source="*_t" dest="text" maxChars="3000"/> -->
+
+  <!-- copy name to alphaNameSort, a field designed for sorting by name -->
+  <!-- <copyField source="name" dest="alphaNameSort"/> -->
+
+
+  <!-- Similarity is the scoring routine for each document vs. a query.
+A custom similarity may be specified here, but the default is fine
+for most applications.  -->
+  <!-- <similarity class="org.apache.lucene.search.DefaultSimilarity"/> -->
+  <!-- ... OR ...
+       Specify a SimilarityFactory class name implementation
+       allowing parameters to be used.
+  -->
+  <!--
+  <similarity class="com.example.solr.CustomSimilarityFactory">
+    <str name="paramkey">param value</str>
+  </similarity>
+  -->
+
+
+</schema>

Added: incubator/directmemory/trunk/examples/src/test/resources/solr/config/scripts.conf
URL: http://svn.apache.org/viewvc/incubator/directmemory/trunk/examples/src/test/resources/solr/config/scripts.conf?rev=1224830&view=auto
==============================================================================
--- incubator/directmemory/trunk/examples/src/test/resources/solr/config/scripts.conf (added)
+++ incubator/directmemory/trunk/examples/src/test/resources/solr/config/scripts.conf Mon Dec 26 22:51:20 2011
@@ -0,0 +1,24 @@
+# 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.
+
+user=
+solr_hostname=localhost
+solr_port=8983
+rsyncd_port=18983
+data_dir=
+webapp_name=solr
+master_host=
+master_data_dir=
+master_status_dir=

Added: incubator/directmemory/trunk/examples/src/test/resources/solr/config/solrconfig.xml
URL: http://svn.apache.org/viewvc/incubator/directmemory/trunk/examples/src/test/resources/solr/config/solrconfig.xml?rev=1224830&view=auto
==============================================================================
--- incubator/directmemory/trunk/examples/src/test/resources/solr/config/solrconfig.xml (added)
+++ incubator/directmemory/trunk/examples/src/test/resources/solr/config/solrconfig.xml Mon Dec 26 22:51:20 2011
@@ -0,0 +1,669 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+
+<!--
+  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.
+-->
+<!--
+  For more details about configurations options that may appear in
+  this file, see http://wiki.apache.org/solr/SolrConfigXml.
+
+  Specifically, the Solr Config can support XInclude, which may make
+  it easier to manage the configuration. See
+  https://issues.apache.org/jira/browse/SOLR-1167
+-->
+<config xmlns:xi="http://www.w3.org/2001/XInclude">
+  <!--
+    Set this to 'false' if you want solr to continue working after it
+    has encountered an severe configuration error. In a production
+    environment, you may want solr to keep working even if one handler
+    is mis-configured. You may also set this to false using by setting
+    the system property: -Dsolr.abortOnConfigurationError=false
+  -->
+  <abortOnConfigurationError>${solr.abortOnConfigurationError:true}</abortOnConfigurationError>
+
+  <!--
+    lib directives can be used to instruct Solr to load an Jars
+    identified and use them to resolve any "plugins" specified in your
+    solrconfig.xml or schema.xml (ie: Analyzers, Request Handlers,
+    etc...). All directories and paths are resolved relative the
+    instanceDir. If a "./lib" directory exists in your instanceDir, all
+    files found in it are included as if you had used the following
+    syntax... <lib dir="./lib" />
+  -->
+  <!--
+    A dir option by itself adds any files found in the directory to the
+    classpath, this is useful for including all jars in a directory.
+  -->
+  <lib dir="../../contrib/extraction/lib"/>
+  <!--
+    When a regex is specified in addition to a directory, only the files
+    in that directory which completely match the regex (anchored on both
+    ends) will be included.
+  -->
+  <lib dir="../../dist/" regex="apache-solr-cell-\d.*\.jar"/>
+  <lib dir="../../dist/" regex="apache-solr-clustering-\d.*\.jar"/>
+  <!--
+    If a dir option (with or without a regex) is used and nothing is
+    found that matches, it will be ignored
+  -->
+  <lib dir="../../contrib/clustering/lib/downloads/"/>
+  <lib dir="../../contrib/clustering/lib/"/>
+  <lib dir="/total/crap/dir/ignored"/>
+  <!--
+    an exact path can be used to specify a specific file. This will
+    cause a serious error to be logged if it can't be loaded. <lib
+    path="../a-jar-that-does-not-exist.jar" />
+  -->
+
+
+  <!--
+    Used to specify an alternate directory to hold all index data other
+    than the default ./data under the Solr home. If replication is in
+    use, this should match the replication configuration.
+  -->
+  <dataDir>${solr.data.dir:./solr/data}</dataDir>
+
+
+  <!--
+    WARNING: this <indexDefaults> section only provides defaults for
+    index writers in general. See also the <mainIndex> section after
+    that when changing parameters for Solr's main Lucene index.
+  -->
+  <indexDefaults>
+    <!--
+      Values here affect all index writers and act as a default unless
+      overridden.
+    -->
+    <useCompoundFile>false</useCompoundFile>
+
+    <mergeFactor>10</mergeFactor>
+    <!--
+      If both ramBufferSizeMB and maxBufferedDocs is set, then Lucene
+      will flush based on whichever limit is hit first.
+    -->
+    <!--<maxBufferedDocs>1000</maxBufferedDocs>-->
+
+    <!--
+      Sets the amount of RAM that may be used by Lucene indexing for
+      buffering added documents and deletions before they are flushed to
+      the Directory.
+    -->
+    <ramBufferSizeMB>32</ramBufferSizeMB>
+    <!-- <maxMergeDocs>2147483647</maxMergeDocs> -->
+    <maxFieldLength>10000</maxFieldLength>
+    <writeLockTimeout>1000</writeLockTimeout>
+    <commitLockTimeout>10000</commitLockTimeout>
+
+    <!--
+      Expert: Turn on Lucene's auto commit capability. This causes
+      intermediate segment flushes to write a new lucene index
+      descriptor, enabling it to be opened by an external IndexReader.
+      This can greatly slow down indexing speed. NOTE: Despite the name,
+      this value does not have any relation to Solr's autoCommit
+      functionality
+    -->
+    <!--<luceneAutoCommit>false</luceneAutoCommit>-->
+
+    <!--
+      Expert: The Merge Policy in Lucene controls how merging is handled
+      by Lucene. The default in 2.3 is the LogByteSizeMergePolicy,
+      previous versions used LogDocMergePolicy. LogByteSizeMergePolicy
+      chooses segments to merge based on their size. The Lucene 2.2
+      default, LogDocMergePolicy chose when to merge based on number of
+      documents Other implementations of MergePolicy must have a
+      no-argument constructor
+    -->
+    <!--
+      <mergePolicy
+      class="org.apache.lucene.index.LogByteSizeMergePolicy"/>
+    -->
+
+    <!--
+      Expert: The Merge Scheduler in Lucene controls how merges are
+      performed. The ConcurrentMergeScheduler (Lucene 2.3 default) can
+      perform merges in the background using separate threads. The
+      SerialMergeScheduler (Lucene 2.2 default) does not.
+    -->
+    <!--
+      <mergeScheduler
+      class="org.apache.lucene.index.ConcurrentMergeScheduler"/>
+    -->
+
+
+    <!--
+      This option specifies which Lucene LockFactory implementation to
+      use. single = SingleInstanceLockFactory - suggested for a
+      read-only index or when there is no possibility of another process
+      trying to modify the index. native = NativeFSLockFactory - uses OS
+      native file locking simple = SimpleFSLockFactory - uses a plain
+      file for locking (For backwards compatibility with Solr 1.2,
+      'simple' is the default if not specified.)
+    -->
+    <lockType>native</lockType>
+    <!--
+      Expert: Controls how often Lucene loads terms into memory
+    -->
+    <!--<termIndexInterval>256</termIndexInterval>-->
+  </indexDefaults>
+
+  <mainIndex>
+    <!-- options specific to the main on-disk lucene index -->
+    <useCompoundFile>false</useCompoundFile>
+    <ramBufferSizeMB>32</ramBufferSizeMB>
+    <mergeFactor>10</mergeFactor>
+    <!-- Deprecated -->
+    <!--<maxBufferedDocs>1000</maxBufferedDocs>-->
+    <!--<maxMergeDocs>2147483647</maxMergeDocs>-->
+
+    <!--
+      inherit from indexDefaults <maxFieldLength>10000</maxFieldLength>
+    -->
+
+    <!--
+      If true, unlock any held write or commit locks on startup. This
+      defeats the locking mechanism that allows multiple processes to
+      safely access a lucene index, and should be used with care. This
+      is not needed if lock type is 'none' or 'single'
+    -->
+    <unlockOnStartup>false</unlockOnStartup>
+
+    <!--
+      If true, IndexReaders will be reopened (often more efficient)
+      instead of closed and then opened.
+    -->
+    <reopenReaders>true</reopenReaders>
+
+    <!--
+      Expert: Controls how often Lucene loads terms into memory. Default
+      is 128 and is likely good for most everyone.
+    -->
+    <!--<termIndexInterval>256</termIndexInterval>-->
+
+    <!--
+      Custom deletion policies can specified here. The class must
+      implement org.apache.lucene.index.IndexDeletionPolicy.
+
+      http://lucene.apache.org/java/2_3_2/api/org/apache/lucene/index/IndexDeletionPolicy.html
+
+      The standard Solr IndexDeletionPolicy implementation supports
+      deleting index commit points on number of commits, age of commit
+      point and optimized status. The latest commit point should always
+      be preserved regardless of the criteria.
+    -->
+    <deletionPolicy class="solr.SolrDeletionPolicy">
+      <!-- The number of commit points to be kept -->
+      <str name="maxCommitsToKeep">1</str>
+      <!-- The number of optimized commit points to be kept -->
+      <str name="maxOptimizedCommitsToKeep">0</str>
+      <!--
+        Delete all commit points once they have reached the given age.
+        Supports DateMathParser syntax e.g. <str
+        name="maxCommitAge">30MINUTES</str> <str
+        name="maxCommitAge">1DAY</str>
+      -->
+    </deletionPolicy>
+
+    <!--
+      To aid in advanced debugging, you may turn on IndexWriter debug
+      logging. Setting to true will set the file that the underlying
+      Lucene IndexWriter will write its debug infostream to.
+    -->
+    <infoStream file="INFOSTREAM.txt">false</infoStream>
+
+  </mainIndex>
+
+  <!--
+    Enables JMX if and only if an existing MBeanServer is found, use
+    this if you want to configure JMX through JVM parameters. Remove
+    this to disable exposing Solr configuration and statistics to JMX.
+
+    If you want to connect to a particular server, specify the agentId
+    e.g. <jmx agentId="myAgent" /> If you want to start a new
+    MBeanServer, specify the serviceUrl e.g <jmx
+    serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/> For
+    more details see http://wiki.apache.org/solr/SolrJmx
+  -->
+  <jmx/>
+
+  <!-- the default high-performance update handler -->
+  <updateHandler class="solr.DirectUpdateHandler2">
+    <!--
+      A prefix of "solr." for class names is an alias that causes solr
+      to search appropriate packages, including
+      org.apache.solr.(search|update|request|core|analysis)
+    -->
+
+    <!--
+      Perform a <commit/> automatically under certain conditions:
+      maxDocs - number of updates since last commit is greater than this
+      maxTime - oldest uncommited update (in ms) is this long ago
+      Instead of enabling autoCommit, consider using "commitWithin" when
+      adding documents. http://wiki.apache.org/solr/UpdateXmlMessages
+      <autoCommit> <maxDocs>10000</maxDocs> <maxTime>1000</maxTime>
+      </autoCommit>
+    -->
+
+
+    <!--
+      The RunExecutableListener executes an external command from a hook
+      such as postCommit or postOptimize. exe - the name of the
+      executable to run dir - dir to use as the current working
+      directory. default="." wait - the calling thread waits until the
+      executable returns. default="true" args - the arguments to pass to
+      the program. default=nothing env - environment variables to set.
+      default=nothing
+    -->
+    <!--
+      A postCommit event is fired after every commit or optimize command
+      <listener event="postCommit" class="solr.RunExecutableListener">
+      <str name="exe">solr/bin/snapshooter</str> <str name="dir">.</str>
+      <bool name="wait">true</bool> <arr name="args"> <str>arg1</str>
+      <str>arg2</str> </arr> <arr name="env"> <str>MYVAR=val1</str>
+      </arr> </listener>
+    -->
+    <!--
+      A postOptimize event is fired only after every optimize command
+      <listener event="postOptimize" class="solr.RunExecutableListener">
+      <str name="exe">snapshooter</str> <str name="dir">solr/bin</str>
+      <bool name="wait">true</bool> </listener>
+    -->
+
+  </updateHandler>
+
+  <!--
+    Use the following format to specify a custom IndexReaderFactory -
+    allows for alternate IndexReader implementations. ** Experimental
+    Feature ** Please note - Using a custom IndexReaderFactory may
+    prevent certain other features from working. The API to
+    IndexReaderFactory may change without warning or may even be removed
+    from future releases if the problems cannot be resolved. ** Features
+    that may not work with custom IndexReaderFactory ** The
+    ReplicationHandler assumes a disk-resident index. Using a custom
+    IndexReader implementation may cause incompatibility with
+    ReplicationHandler and may cause replication to not work correctly.
+    See SOLR-1366 for details. <indexReaderFactory
+    name="IndexReaderFactory" class="package.class"> Parameters as
+    required by the implementation </indexReaderFactory >
+  -->
+  <!-- To set the termInfosIndexDivisor, do this: -->
+  <!--
+    <indexReaderFactory name="IndexReaderFactory"
+    class="org.apache.solr.core.StandardIndexReaderFactory"> <int
+    name="termInfosIndexDivisor">12</int> </indexReaderFactory >
+  -->
+
+
+  <query>
+    <!--
+      Maximum number of clauses in a boolean query... in the past, this
+      affected range or prefix queries that expanded to big boolean
+      queries - built in Solr query parsers no longer create queries
+      with this limitation. An exception is thrown if exceeded.
+    -->
+    <maxBooleanClauses>1024</maxBooleanClauses>
+
+
+    <!--
+      There are two implementations of cache available for Solr,
+      LRUCache, based on a synchronized LinkedHashMap, and FastLRUCache,
+      based on a ConcurrentHashMap. FastLRUCache has faster gets and
+      slower puts in single threaded operation and thus is generally
+      faster than LRUCache when the hit ratio of the cache is high (>
+      75%), and may be faster under other scenarios on multi-cpu
+      systems.
+    -->
+    <!--
+      Cache used by SolrIndexSearcher for filters (DocSets), unordered
+      sets of *all* documents that match a query. When a new searcher is
+      opened, its caches may be prepopulated or "autowarmed" using data
+      from caches in the old searcher. autowarmCount is the number of
+      items to prepopulate. For LRUCache, the autowarmed items will be
+      the most recently accessed items. Parameters: class - the
+      SolrCache implementation LRUCache or FastLRUCache size - the
+      maximum number of entries in the cache initialSize - the initial
+      capacity (number of entries) of the cache. (seel
+      java.util.HashMap) autowarmCount - the number of entries to
+      prepopulate from and old cache.
+    -->
+    <filterCache class="solr.FastLRUCache" size="512"
+                 initialSize="512" autowarmCount="0"/>
+
+    <!--
+      Cache used to hold field values that are quickly accessible by
+      document id. The fieldValueCache is created by default even if not
+      configured here. <fieldValueCache class="solr.FastLRUCache"
+      size="512" autowarmCount="128" showItems="32" />
+    -->
+
+    <!--
+      queryResultCache caches results of searches - ordered lists of
+      document ids (DocList) based on a query, a sort, and the range of
+      documents requested.
+    -->
+    <documentCache class="solr.LRUCache" size="512"
+                   initialSize="512" autowarmCount="0"/>
+
+    <!--
+      documentCache caches Lucene Document objects (the stored fields
+      for each document). Since Lucene internal document ids are
+      transient, this cache will not be autowarmed.
+    -->
+    <queryResultCache class="org.apache.directmemory.examples.solr.SolrOffHeapCache" size="512"
+                      initialSize="512" autowarmCount="0" buffers="10"/>
+
+    <!--
+      If true, stored fields that are not requested will be loaded
+      lazily. This can result in a significant speed improvement if the
+      usual case is to not load all stored fields, especially if the
+      skipped fields are large compressed text fields.
+    -->
+    <enableLazyFieldLoading>true</enableLazyFieldLoading>
+
+    <!--
+      Example of a generic cache. These caches may be accessed by name
+      through SolrIndexSearcher.getCache(),cacheLookup(), and
+      cacheInsert(). The purpose is to enable easy caching of
+      user/application level data. The regenerator argument should be
+      specified as an implementation of solr.search.CacheRegenerator if
+      autowarming is desired.
+    -->
+    <!--
+      <cache name="myUserCache" class="solr.LRUCache" size="4096"
+      initialSize="1024" autowarmCount="1024"
+      regenerator="org.mycompany.mypackage.MyRegenerator" />
+    -->
+
+    <!--
+      An optimization that attempts to use a filter to satisfy a search.
+      If the requested sort does not include score, then the filterCache
+      will be checked for a filter matching the query. If found, the
+      filter will be used as the source of document ids, and then the
+      sort will be applied to that.
+      <useFilterForSortedQuery>true</useFilterForSortedQuery>
+    -->
+
+    <!--
+      An optimization for use with the queryResultCache. When a search
+      is requested, a superset of the requested number of document ids
+      are collected. For example, if a search for a particular query
+      requests matching documents 10 through 19, and queryWindowSize is
+      50, then documents 0 through 49 will be collected and cached. Any
+      further requests in that range can be satisfied via the cache.
+    -->
+    <queryResultWindowSize>20</queryResultWindowSize>
+
+    <!--
+      Maximum number of documents to cache for any entry in the
+      queryResultCache.
+    -->
+    <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
+
+    <!--
+      a newSearcher event is fired whenever a new searcher is being
+      prepared and there is a current searcher handling requests (aka
+      registered). It can be used to prime certain caches to prevent
+      long request times for certain requests.
+    -->
+    <!--
+      QuerySenderListener takes an array of NamedList and executes a
+      local query request for each NamedList in sequence.
+    -->
+    <listener event="newSearcher" class="solr.QuerySenderListener">
+      <arr name="queries">
+        <!--
+          <lst> <str name="q">solr</str> <str name="start">0</str> <str
+          name="rows">10</str> </lst> <lst> <str name="q">rocks</str>
+          <str name="start">0</str> <str name="rows">10</str> </lst>
+          <lst><str name="q">static newSearcher warming query from
+          solrconfig.xml</str></lst>
+        -->
+      </arr>
+    </listener>
+
+    <!--
+      a firstSearcher event is fired whenever a new searcher is being
+      prepared but there is no current registered searcher to handle
+      requests or to gain autowarming data from.
+    -->
+    <listener event="firstSearcher" class="solr.QuerySenderListener">
+      <arr name="queries">
+        <lst>
+          <str name="q">solr rocks</str>
+          <str name="start">0</str>
+          <str name="rows">10</str>
+        </lst>
+        <lst>
+          <str name="q">static firstSearcher warming query from
+            solrconfig.xml
+          </str>
+        </lst>
+      </arr>
+    </listener>
+
+    <!--
+      If a search request comes in and there is no current registered
+      searcher, then immediately register the still warming searcher and
+      use it. If "false" then all requests will block until the first
+      searcher is done warming.
+    -->
+    <useColdSearcher>false</useColdSearcher>
+
+    <!--
+      Maximum number of searchers that may be warming in the background
+      concurrently. An error is returned if this limit is exceeded.
+      Recommend 1-2 for read-only slaves, higher for masters w/o cache
+      warming.
+    -->
+    <maxWarmingSearchers>2</maxWarmingSearchers>
+
+  </query>
+
+  <!--
+    Let the dispatch filter handler /select?qt=XXX handleSelect=true
+    will use consistent error handling for /select and /update
+    handleSelect=false will use solr1.1 style error formatting
+  -->
+  <requestDispatcher handleSelect="true">
+    <!--
+      Make sure your system has some authentication before enabling
+      remote streaming!
+    -->
+    <requestParsers enableRemoteStreaming="true"
+                    multipartUploadLimitInKB="2048000"/>
+
+    <!--
+      Set HTTP caching related parameters (for proxy caches and
+      clients). To get the behaviour of Solr 1.2 (ie: no caching related
+      headers) use the never304="true" option and do not specify a value
+      for <cacheControl>
+    -->
+    <!-- <httpCaching never304="true"> -->
+    <httpCaching lastModifiedFrom="openTime" etagSeed="Solr">
+      <!--
+        lastModFrom="openTime" is the default, the Last-Modified value
+        (and validation against If-Modified-Since requests) will all be
+        relative to when the current Searcher was opened. You can change
+        it to lastModFrom="dirLastMod" if you want the value to exactly
+        corrispond to when the physical index was last modified.
+
+        etagSeed="..." is an option you can change to force the ETag
+        header (and validation against If-None-Match requests) to be
+        differnet even if the index has not changed (ie: when making
+        significant changes to your config file) lastModifiedFrom and
+        etagSeed are both ignored if you use the never304="true" option.
+      -->
+      <!--
+        If you include a <cacheControl> directive, it will be used to
+        generate a Cache-Control header, as well as an Expires header if
+        the value contains "max-age=" By default, no Cache-Control
+        header is generated. You can use the <cacheControl> option even
+        if you have set never304="true"
+      -->
+      <!-- <cacheControl>max-age=30, public</cacheControl> -->
+    </httpCaching>
+  </requestDispatcher>
+
+
+  <!--
+    requestHandler plugins... incoming queries will be dispatched to the
+    correct handler based on the path or the qt (query type) param.
+    Names starting with a '/' are accessed with the a path equal to the
+    registered name. Names without a leading '/' are accessed with:
+    http://host/app/select?qt=name If no qt is defined, the
+    requestHandler that declares default="true" will be used.
+  -->
+  <requestHandler name="standard" class="solr.SearchHandler"
+                  default="true">
+    <!-- default values for query parameters -->
+    <lst name="defaults">
+      <str name="echoParams">explicit</str>
+      <!--
+        <int name="rows">10</int> <str name="fl">*</str> <str
+        name="version">2.1</str>
+      -->
+    </lst>
+  </requestHandler>
+
+  <requestHandler name="/admin/"
+                  class="org.apache.solr.handler.admin.AdminHandlers"/>
+
+  <!-- ping/healthcheck -->
+  <requestHandler name="/admin/ping" class="PingRequestHandler">
+    <lst name="defaults">
+      <str name="qt">standard</str>
+      <str name="q">solrpingquery</str>
+      <str name="echoParams">all</str>
+    </lst>
+  </requestHandler>
+
+  <!-- Echo the request contents back to the client -->
+  <requestHandler name="/debug/dump" class="solr.DumpRequestHandler">
+    <lst name="defaults">
+      <str name="echoParams">explicit</str>
+      <!-- for all params (including the default etc) use: 'all' -->
+      <str name="echoHandler">true</str>
+    </lst>
+  </requestHandler>
+
+  <highlighting>
+    <!-- Configure the standard fragmenter -->
+    <!-- This could most likely be commented out in the "default" case -->
+    <fragmenter name="gap"
+                class="org.apache.solr.highlight.GapFragmenter" default="true">
+      <lst name="defaults">
+        <int name="hl.fragsize">100</int>
+      </lst>
+    </fragmenter>
+
+    <!--
+      A regular-expression-based fragmenter (f.i., for sentence
+      extraction)
+    -->
+    <fragmenter name="regex"
+                class="org.apache.solr.highlight.RegexFragmenter">
+      <lst name="defaults">
+        <!-- slightly smaller fragsizes work better because of slop -->
+        <int name="hl.fragsize">70</int>
+        <!-- allow 50% slop on fragment sizes -->
+        <float name="hl.regex.slop">0.5</float>
+        <!-- a basic sentence pattern -->
+        <str name="hl.regex.pattern">[-\w ,/\n\"']{20,200}</str>
+      </lst>
+    </fragmenter>
+
+    <!-- Configure the standard formatter -->
+    <formatter name="html" class="org.apache.solr.highlight.HtmlFormatter"
+               default="true">
+      <lst name="defaults">
+        <str name="hl.simple.pre"><![CDATA[<em>]]></str>
+        <str name="hl.simple.post"><![CDATA[</em>]]></str>
+      </lst>
+    </formatter>
+  </highlighting>
+
+  <!--
+    An example dedup update processor that creates the "id" field on the
+    fly based on the hash code of some other fields. This example has
+    overwriteDupes set to false since we are using the id field as the
+    signatureField and Solr will maintain uniqueness based on that
+    anyway. You have to link the chain to an update handler above to use
+    it ie: <requestHandler name="/update
+    "class="solr.XmlUpdateRequestHandler"> <lst name="defaults"> <str
+    name="update.processor">dedupe</str> </lst> </requestHandler>
+  -->
+  <!--
+    <updateRequestProcessorChain name="dedupe"> <processor
+    class="org.apache.solr.update.processor.SignatureUpdateProcessorFactory">
+    <bool name="enabled">true</bool> <str name="signatureField">id</str>
+    <bool name="overwriteDupes">false</bool> <str
+    name="fields">name,features,cat</str> <str
+    name="signatureClass">org.apache.solr.update.processor.Lookup3Signature</str>
+    </processor> <processor class="solr.LogUpdateProcessorFactory" />
+    <processor class="solr.RunUpdateProcessorFactory" />
+    </updateRequestProcessorChain>
+  -->
+
+
+  <!--
+    queryResponseWriter plugins... query responses will be written using
+    the writer specified by the 'wt' request parameter matching the name
+    of a registered writer. The "default" writer is the default and will
+    be used if 'wt' is not specified in the request. XMLResponseWriter
+    will be used if nothing is specified here. The json, python, and
+    ruby writers are also available by default. <queryResponseWriter
+    name="xml" class="org.apache.solr.request.XMLResponseWriter"
+    default="true"/> <queryResponseWriter name="json"
+    class="org.apache.solr.request.JSONResponseWriter"/>
+    <queryResponseWriter name="python"
+    class="org.apache.solr.request.PythonResponseWriter"/>
+    <queryResponseWriter name="ruby"
+    class="org.apache.solr.request.RubyResponseWriter"/>
+    <queryResponseWriter name="php"
+    class="org.apache.solr.request.PHPResponseWriter"/>
+    <queryResponseWriter name="phps"
+    class="org.apache.solr.request.PHPSerializedResponseWriter"/>
+
+    <queryResponseWriter name="custom"
+    class="com.example.MyResponseWriter"/>
+  -->
+
+  <!--
+    XSLT response writer transforms the XML output by any xslt file
+    found in Solr's conf/xslt directory. Changes to xslt files are
+    checked for every xsltCacheLifetimeSeconds.
+  -->
+  <queryResponseWriter name="xslt"
+                       class="org.apache.solr.request.XSLTResponseWriter">
+    <int name="xsltCacheLifetimeSeconds">5</int>
+  </queryResponseWriter>
+
+
+  <!--
+    example of registering a custom function parser <valueSourceParser
+    name="myfunc" class="com.mycompany.MyValueSourceParser" />
+  -->
+
+  <!-- config for the admin interface -->
+  <admin>
+    <defaultQuery>*</defaultQuery>
+
+    <!--
+      configure a healthcheck file for servers behind a loadbalancer
+      <healthcheck type="file">server-enabled</healthcheck>
+    -->
+  </admin>
+
+
+</config>

Added: incubator/directmemory/trunk/examples/src/test/resources/solr/config/stopwords.txt
URL: http://svn.apache.org/viewvc/incubator/directmemory/trunk/examples/src/test/resources/solr/config/stopwords.txt?rev=1224830&view=auto
==============================================================================
--- incubator/directmemory/trunk/examples/src/test/resources/solr/config/stopwords.txt (added)
+++ incubator/directmemory/trunk/examples/src/test/resources/solr/config/stopwords.txt Mon Dec 26 22:51:20 2011
@@ -0,0 +1,58 @@
+# 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.
+
+#-----------------------------------------------------------------------
+# a couple of test stopwords to test that the words are really being
+# configured from this file:
+stopworda
+stopwordb
+
+#Standard english stop words taken from Lucene's StopAnalyzer
+a
+an
+and
+are
+as
+at
+be
+but
+by
+for
+if
+in
+into
+is
+it
+no
+not
+of
+on
+or
+s
+such
+t
+that
+the
+their
+then
+there
+these
+they
+this
+to
+was
+will
+with
+

Added: incubator/directmemory/trunk/examples/src/test/resources/solr/config/synonyms.txt
URL: http://svn.apache.org/viewvc/incubator/directmemory/trunk/examples/src/test/resources/solr/config/synonyms.txt?rev=1224830&view=auto
==============================================================================
--- incubator/directmemory/trunk/examples/src/test/resources/solr/config/synonyms.txt (added)
+++ incubator/directmemory/trunk/examples/src/test/resources/solr/config/synonyms.txt Mon Dec 26 22:51:20 2011
@@ -0,0 +1,31 @@
+# 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.
+
+#-----------------------------------------------------------------------
+#some test synonym mappings unlikely to appear in real input text
+aaa => aaaa
+bbb => bbbb1 bbbb2
+ccc => cccc1,cccc2
+a\=>a => b\=>b
+a\,a => b\,b
+fooaaa,baraaa,bazaaa
+
+# Some synonym groups specific to this example
+GB,gib,gigabyte,gigabytes
+MB,mib,megabyte,megabytes
+Television, Televisions, TV, TVs
+#notice we use "gib" instead of "GiB" so any WordDelimiterFilter coming
+#after us won't split it into two words.
+
+# Synonym mappings can be used for spelling correction too
+pixima => pixma
+



Mime
View raw message