├── .gitignore
├── bin
    └── config_upgrade.sh
├── validators
    ├── solr_4_to_5_processors.xml
    ├── solrconfig_5_to_6_transformer.xslt
    ├── schema_5_to_6_transformer.xslt
    ├── solrconfig_4_to_5_transformer.xslt
    ├── solrconfig_5_to_6_validator.xslt
    ├── schema_5_to_6_validator.xslt
    ├── solrconfig_4_to_5_validator.xslt
    └── schema_4_to_5_validator.xslt
├── src
    ├── main
    │   ├── java
    │   │   └── org
    │   │   │   └── apache
    │   │   │       └── solr
    │   │   │           └── config
    │   │   │               └── upgrade
    │   │   │                   ├── ValidationHandler.java
    │   │   │                   ├── UpgradeConfigException.java
    │   │   │                   ├── UpgradeProcessorsConfigFactory.java
    │   │   │                   ├── ConfigType.java
    │   │   │                   ├── SuppressCompilerWarnings.java
    │   │   │                   ├── UpgradeProcessorsConfig.java
    │   │   │                   ├── ConfigValidator.java
    │   │   │                   ├── ToolParams.java
    │   │   │                   ├── ConfigTransformer.java
    │   │   │                   ├── impl
    │   │   │                       └── DefaultValidationResultProcessor.java
    │   │   │                   └── ConfigUpgradeTool.java
    │   └── resources
    │   │   └── validation_result_summary.xslt
    ├── assembly
    │   └── bin.xml
    └── test
    │   └── resources
    │       ├── bad_config
    │           └── solr5
    │           │   ├── schema_2.xml
    │           │   └── schema_1.xml
    │       └── good_config
    │           └── schema.xml
├── pom.xml
├── README.md
└── LICENSE


/.gitignore:
--------------------------------------------------------------------------------
1 | # .
2 | /.project
3 | /.classpath
4 | /.settings
5 | target/*
6 | dependency-reduced-pom.xml
7 | /target/
8 | 


--------------------------------------------------------------------------------
/bin/config_upgrade.sh:
--------------------------------------------------------------------------------
 1 | #!/bin/bash
 2 | 
 3 | : ${JAVA_HOME:?"Please configure JAVA_HOME environment variable"}
 4 | 
 5 | JVM="java"
 6 | SCRIPT_DIR=$(dirname "$0")
 7 | 
 8 | PATH="${JAVA_HOME}/bin:${PATH}" ${JVM} $JAVA_OPTS -cp "${SCRIPT_DIR}/lib/*" org.apache.solr.config.upgrade.ConfigUpgradeTool "$@"
 9 | 
10 | 


--------------------------------------------------------------------------------
/validators/solr_4_to_5_processors.xml:
--------------------------------------------------------------------------------
1 | <?xml version="1.0" encoding="UTF-8"?>
2 | <upgradeProcessors inputVersion="4" outputVersion="5">
3 |   <processor configType="schema"
4 |              validatorPath="schema_4_to_5_validator.xslt" />
5 |   <processor configType="solrconfig"
6 |              validatorPath="solrconfig_4_to_5_validator.xslt"
7 |              transformerPath="solrconfig_4_to_5_transformer.xslt" />
8 | </upgradeProcessors>
9 | 


--------------------------------------------------------------------------------
/src/main/java/org/apache/solr/config/upgrade/ValidationHandler.java:
--------------------------------------------------------------------------------
 1 | /*
 2 |  * Licensed to the Apache Software Foundation (ASF) under one or more
 3 |  * contributor license agreements.  See the NOTICE file distributed with
 4 |  * this work for additional information regarding copyright ownership.
 5 |  * The ASF licenses this file to You under the Apache License, Version 2.0
 6 |  * (the "License"); you may not use this file except in compliance with
 7 |  * the License.  You may obtain a copy of the License at
 8 |  *
 9 |  *     http://www.apache.org/licenses/LICENSE-2.0
10 |  *
11 |  * Unless required by applicable law or agreed to in writing, software
12 |  * distributed under the License is distributed on an "AS IS" BASIS,
13 |  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 |  * See the License for the specific language governing permissions and
15 |  * limitations under the License.
16 |  */
17 | 
18 | package org.apache.solr.config.upgrade;
19 | 
20 | import org.w3c.dom.Document;
21 | 
22 | public interface ValidationHandler {
23 |   void begin(String confName);
24 |   boolean process (String confName, Document result);
25 | }
26 | 


--------------------------------------------------------------------------------
/src/assembly/bin.xml:
--------------------------------------------------------------------------------
 1 | <assembly xmlns="http://maven.apache.org/ASSEMBLY/2.0.0"
 2 |   xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
 3 |   xsi:schemaLocation="http://maven.apache.org/ASSEMBLY/2.0.0 http://maven.apache.org/xsd/assembly-2.0.0.xsd">
 4 |   <id>bin</id>
 5 |   <formats>
 6 |     <format>tar.gz</format>
 7 |   </formats>
 8 |   <fileSets>
 9 |     <fileSet>
10 |       <directory>${project.basedir}</directory>
11 |       <outputDirectory />
12 |       <includes>
13 |         <include>README*</include>
14 |         <include>LICENSE*</include>
15 |         <include>NOTICE*</include>
16 |       </includes>
17 |     </fileSet>
18 |     <fileSet>
19 |       <directory>${project.build.directory}</directory>
20 |       <outputDirectory>lib</outputDirectory>
21 |       <includes>
22 |         <include>${project.artifactId}-${project.version}.jar</include>
23 |       </includes>
24 |     </fileSet>
25 |     <fileSet>
26 |       <directory>${project.basedir}/bin</directory>
27 |       <outputDirectory />
28 |       <includes>
29 |         <include>*.sh</include>
30 |       </includes>
31 |     </fileSet>
32 |     <fileSet>
33 |       <directory>${project.basedir}/validators</directory>
34 |       <outputDirectory>validators</outputDirectory>
35 |       <includes>
36 |         <include>*</include>
37 |       </includes>
38 |     </fileSet>
39 |   </fileSets>
40 | </assembly>
41 | 


--------------------------------------------------------------------------------
/src/main/java/org/apache/solr/config/upgrade/UpgradeConfigException.java:
--------------------------------------------------------------------------------
 1 | /*
 2 |  * Licensed to the Apache Software Foundation (ASF) under one or more
 3 |  * contributor license agreements.  See the NOTICE file distributed with
 4 |  * this work for additional information regarding copyright ownership.
 5 |  * The ASF licenses this file to You under the Apache License, Version 2.0
 6 |  * (the "License"); you may not use this file except in compliance with
 7 |  * the License.  You may obtain a copy of the License at
 8 |  *
 9 |  *     http://www.apache.org/licenses/LICENSE-2.0
10 |  *
11 |  * Unless required by applicable law or agreed to in writing, software
12 |  * distributed under the License is distributed on an "AS IS" BASIS,
13 |  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 |  * See the License for the specific language governing permissions and
15 |  * limitations under the License.
16 |  */
17 | package org.apache.solr.config.upgrade;
18 | 
19 | @SuppressWarnings("serial")
20 | public class UpgradeConfigException extends RuntimeException {
21 | 
22 |   public UpgradeConfigException() {
23 |   }
24 | 
25 |   public UpgradeConfigException(String message, Throwable cause, boolean enableSuppression,
26 |       boolean writableStackTrace) {
27 |     super(message, cause, enableSuppression, writableStackTrace);
28 |   }
29 | 
30 |   public UpgradeConfigException(String message, Throwable cause) {
31 |     super(message, cause);
32 |   }
33 | 
34 |   public UpgradeConfigException(String message) {
35 |     super(message);
36 |   }
37 | 
38 |   public UpgradeConfigException(Throwable cause) {
39 |     super(cause);
40 |   }
41 | }
42 | 


--------------------------------------------------------------------------------
/src/main/java/org/apache/solr/config/upgrade/UpgradeProcessorsConfigFactory.java:
--------------------------------------------------------------------------------
 1 | /*
 2 |  * Licensed to the Apache Software Foundation (ASF) under one or more
 3 |  * contributor license agreements.  See the NOTICE file distributed with
 4 |  * this work for additional information regarding copyright ownership.
 5 |  * The ASF licenses this file to You under the Apache License, Version 2.0
 6 |  * (the "License"); you may not use this file except in compliance with
 7 |  * the License.  You may obtain a copy of the License at
 8 |  *
 9 |  *     http://www.apache.org/licenses/LICENSE-2.0
10 |  *
11 |  * Unless required by applicable law or agreed to in writing, software
12 |  * distributed under the License is distributed on an "AS IS" BASIS,
13 |  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 |  * See the License for the specific language governing permissions and
15 |  * limitations under the License.
16 |  */
17 | package org.apache.solr.config.upgrade;
18 | 
19 | import java.io.IOException;
20 | import java.nio.file.Path;
21 | 
22 | import com.fasterxml.jackson.core.JsonParseException;
23 | import com.fasterxml.jackson.databind.JsonMappingException;
24 | import com.fasterxml.jackson.dataformat.xml.JacksonXmlModule;
25 | import com.fasterxml.jackson.dataformat.xml.XmlMapper;
26 | 
27 | public class UpgradeProcessorsConfigFactory {
28 | 
29 |   public static UpgradeProcessorsConfig newInstance(Path configFilePath)
30 |       throws JsonParseException, JsonMappingException, IOException {
31 |     JacksonXmlModule module = new JacksonXmlModule();
32 |     module.setDefaultUseWrapper(false);
33 |     XmlMapper xmlMapper = new XmlMapper(module);
34 | 
35 |     return xmlMapper.readValue(configFilePath.toFile(), UpgradeProcessorsConfig.class);
36 |   }
37 | }
38 | 


--------------------------------------------------------------------------------
/validators/solrconfig_5_to_6_transformer.xslt:
--------------------------------------------------------------------------------
 1 | <xsl:stylesheet version="2.0" 
 2 |                 xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
 3 | 
 4 | <!--
 5 |  Licensed to the Apache Software Foundation (ASF) under one or more
 6 |  contributor license agreements.  See the NOTICE file distributed with
 7 |  this work for additional information regarding copyright ownership.
 8 |  The ASF licenses this file to You under the Apache License, Version 2.0
 9 |  (the "License"); you may not use this file except in compliance with
10 |  the License.  You may obtain a copy of the License at
11 | 
12 |      http://www.apache.org/licenses/LICENSE-2.0
13 | 
14 |  Unless required by applicable law or agreed to in writing, software
15 |  distributed under the License is distributed on an "AS IS" BASIS,
16 |  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
17 |  See the License for the specific language governing permissions and
18 |  limitations under the License.
19 | -->
20 | 
21 | <xsl:output method="xml" version="1.0" encoding="UTF-8" indent="true" standalone="yes" />
22 | <xsl:strip-space elements="*"/>
23 | 
24 | <!-- identity transform -->
25 | <xsl:template match="@* | node()">
26 |   <xsl:copy>
27 |     <xsl:apply-templates select="node() | @*"/>
28 |   </xsl:copy>
29 | </xsl:template>
30 | 
31 | <!-- Required to ensure proper indentation for the comments in the config file -->
32 | <xsl:template match="/comment()">
33 |   <xsl:text>&#10;</xsl:text>
34 |   <xsl:copy/>
35 | </xsl:template>
36 | 
37 | <xsl:template match="config">
38 |   <xsl:text>&#10;</xsl:text>
39 |   <xsl:copy>
40 |     <xsl:apply-templates select="child::node()"/>
41 |   </xsl:copy>
42 | </xsl:template>
43 | 
44 | <!-- Remove the following configuration sections from the result -->
45 | <xsl:template match="indexConfig/nrtMode">
46 |   <xsl:message>* Removed "nrtMode" configuration from "indexConfig" section</xsl:message>
47 | </xsl:template>
48 | 
49 | </xsl:stylesheet>
50 | 


--------------------------------------------------------------------------------
/src/main/java/org/apache/solr/config/upgrade/ConfigType.java:
--------------------------------------------------------------------------------
 1 | /*
 2 |  * Licensed to the Apache Software Foundation (ASF) under one or more
 3 |  * contributor license agreements.  See the NOTICE file distributed with
 4 |  * this work for additional information regarding copyright ownership.
 5 |  * The ASF licenses this file to You under the Apache License, Version 2.0
 6 |  * (the "License"); you may not use this file except in compliance with
 7 |  * the License.  You may obtain a copy of the License at
 8 |  *
 9 |  *     http://www.apache.org/licenses/LICENSE-2.0
10 |  *
11 |  * Unless required by applicable law or agreed to in writing, software
12 |  * distributed under the License is distributed on an "AS IS" BASIS,
13 |  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 |  * See the License for the specific language governing permissions and
15 |  * limitations under the License.
16 |  */
17 | package org.apache.solr.config.upgrade;
18 | 
19 | /**
20 |  * This enum defines Solr configuration which can be verified by compatibility checker
21 |  */
22 | public enum ConfigType {
23 |   SCHEMA_XML("schema"), SOLRCONFIG_XML("solrconfig"), CONFIGSET("configset");
24 | 
25 |   private String configType;
26 | 
27 |   private ConfigType(String configType) {
28 |     this.configType = configType;
29 |   }
30 | 
31 |   public String getConfigType() {
32 |     return configType;
33 |   }
34 | 
35 |   public static ConfigType getConfigType(String configType) {
36 |     if (SCHEMA_XML.getConfigType().equalsIgnoreCase(configType)) {
37 |       return ConfigType.SCHEMA_XML;
38 |     } else if (SOLRCONFIG_XML.getConfigType().equalsIgnoreCase(configType)) {
39 |       return ConfigType.SOLRCONFIG_XML;
40 |     }  else if (CONFIGSET.getConfigType().equalsIgnoreCase(configType)) {
41 |       return ConfigType.CONFIGSET;
42 |     }
43 |     throw new IllegalArgumentException("Invalid configType "+configType);
44 |   }
45 | 
46 |   @Override
47 |   public String toString() {
48 |     return configType;
49 |   }
50 | }
51 | 


--------------------------------------------------------------------------------
/validators/schema_5_to_6_transformer.xslt:
--------------------------------------------------------------------------------
 1 | <xsl:stylesheet version="2.0" 
 2 |                 xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
 3 | 
 4 | <!--
 5 |  Licensed to the Apache Software Foundation (ASF) under one or more
 6 |  contributor license agreements.  See the NOTICE file distributed with
 7 |  this work for additional information regarding copyright ownership.
 8 |  The ASF licenses this file to You under the Apache License, Version 2.0
 9 |  (the "License"); you may not use this file except in compliance with
10 |  the License.  You may obtain a copy of the License at
11 | 
12 |      http://www.apache.org/licenses/LICENSE-2.0
13 | 
14 |  Unless required by applicable law or agreed to in writing, software
15 |  distributed under the License is distributed on an "AS IS" BASIS,
16 |  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
17 |  See the License for the specific language governing permissions and
18 |  limitations under the License.
19 | -->
20 | 
21 | <xsl:output method="xml" version="1.0" encoding="UTF-8" indent="true" standalone="yes" />
22 | <xsl:strip-space elements="*"/>
23 | 
24 | <!-- identity transform -->
25 | <xsl:template match="@* | node()">
26 |   <xsl:copy>
27 |     <xsl:apply-templates select="@* | node()"/>
28 |   </xsl:copy>
29 | </xsl:template>
30 | 
31 | <!-- Required to ensure proper indentation for the comments in the config file -->
32 | <xsl:template match="/comment()">
33 |   <xsl:text>&#10;</xsl:text>
34 |   <xsl:copy/>
35 | </xsl:template>
36 | 
37 | <xsl:template match="schema">
38 |   <xsl:text>&#10;</xsl:text>
39 |   <xsl:copy>
40 |     <xsl:apply-templates select="child::node()"/>
41 |   </xsl:copy>
42 | </xsl:template>
43 | 
44 | <xsl:template match="similarity/@class">
45 |   <xsl:message>* Replacing usage of DefaultSimilarityFactory with ClassicSimilarityFactory</xsl:message>
46 |   <xsl:attribute name="class">
47 |     <xsl:choose>
48 |       <xsl:when test=".='solr.DefaultSimilarityFactory'">solr.ClassicSimilarityFactory</xsl:when>
49 |       <xsl:otherwise><xsl:value-of select="."/></xsl:otherwise>
50 |     </xsl:choose>
51 |   </xsl:attribute>
52 | </xsl:template>
53 | 
54 | </xsl:stylesheet>
55 | 


--------------------------------------------------------------------------------
/src/main/java/org/apache/solr/config/upgrade/SuppressCompilerWarnings.java:
--------------------------------------------------------------------------------
 1 | /*
 2 |  * Licensed to the Apache Software Foundation (ASF) under one or more
 3 |  * contributor license agreements.  See the NOTICE file distributed with
 4 |  * this work for additional information regarding copyright ownership.
 5 |  * The ASF licenses this file to You under the Apache License, Version 2.0
 6 |  * (the "License"); you may not use this file except in compliance with
 7 |  * the License.  You may obtain a copy of the License at
 8 |  *
 9 |  *     http://www.apache.org/licenses/LICENSE-2.0
10 |  *
11 |  * Unless required by applicable law or agreed to in writing, software
12 |  * distributed under the License is distributed on an "AS IS" BASIS,
13 |  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 |  * See the License for the specific language governing permissions and
15 |  * limitations under the License.
16 |  */
17 | package org.apache.solr.config.upgrade;
18 | 
19 | import javax.xml.transform.ErrorListener;
20 | import javax.xml.transform.TransformerException;
21 | 
22 | /**
23 |  * The Java XSLT compiler generates number of warnings which (generally) do not affect the result of
24 |  * the transformation. This class allows the upgrade tool to suppress such warnings. During the development
25 |  * of the upgrade rules, display of such warnings can be enabled by providing "-v" command line parameter.
26 |  */
27 | class SuppressCompilerWarnings implements ErrorListener {
28 |   private final boolean verbose;
29 | 
30 |   public SuppressCompilerWarnings(boolean verbose) {
31 |     this.verbose = verbose;
32 |   }
33 | 
34 |   @Override
35 |   public void warning(TransformerException exception) throws TransformerException {
36 |     if (verbose) {
37 |       System.err.println(exception.getMessageAndLocation());
38 |     }
39 |   }
40 | 
41 |   @Override
42 |   public void error(TransformerException exception) throws TransformerException {
43 |     System.err.println(exception.getMessageAndLocation());
44 |   }
45 | 
46 |   @Override
47 |   public void fatalError(TransformerException exception) throws TransformerException {
48 |     System.err.println(exception.getMessageAndLocation());
49 |   }
50 | }


--------------------------------------------------------------------------------
/pom.xml:
--------------------------------------------------------------------------------
 1 | <project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
 2 |   xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
 3 |   <modelVersion>4.0.0</modelVersion>
 4 |   <groupId>org.apache.solr</groupId>
 5 |   <artifactId>solr-upgrade-tool</artifactId>
 6 |   <version>0.0.1-SNAPSHOT</version>
 7 |   <properties>
 8 |     <maven.compiler.source>1.8</maven.compiler.source>
 9 |     <maven.compiler.target>1.8</maven.compiler.target>
10 |   </properties>
11 |   <dependencies>
12 |     <dependency>
13 |       <groupId>commons-cli</groupId>
14 |       <artifactId>commons-cli</artifactId>
15 |       <version>1.3</version>
16 |     </dependency>
17 |     <dependency>
18 |       <groupId>com.fasterxml.jackson.core</groupId>
19 |       <artifactId>jackson-databind</artifactId>
20 |       <version>2.8.9</version>
21 |     </dependency>
22 |     <dependency>
23 |       <groupId>com.fasterxml.jackson.core</groupId>
24 |       <artifactId>jackson-annotations</artifactId>
25 |       <version>2.8.9</version>
26 |     </dependency>
27 |     <dependency>
28 |       <groupId>com.fasterxml.jackson.dataformat</groupId>
29 |       <artifactId>jackson-dataformat-xml</artifactId>
30 |       <version>2.8.9</version>
31 |     </dependency>
32 |   </dependencies>
33 |   <build>
34 |     <plugins>
35 |       <plugin>
36 |         <groupId>org.apache.maven.plugins</groupId>
37 |         <artifactId>maven-shade-plugin</artifactId>
38 |         <version>3.0.0</version>
39 |         <executions>
40 |           <execution>
41 |             <phase>package</phase>
42 |             <goals>
43 |               <goal>shade</goal>
44 |             </goals>
45 |           </execution>
46 |         </executions>
47 |       </plugin>
48 |       <plugin>
49 |         <artifactId>maven-assembly-plugin</artifactId>
50 |         <version>3.1.0</version>
51 |         <configuration>
52 |           <descriptors>
53 |             <descriptor>src/assembly/bin.xml</descriptor>
54 |           </descriptors>
55 |         </configuration>
56 |         <executions>
57 |           <execution>
58 |             <id>create-archive</id>
59 |             <phase>package</phase>
60 |             <goals>
61 |               <goal>single</goal>
62 |             </goals>
63 |           </execution>
64 |         </executions>
65 |       </plugin>
66 |     </plugins>
67 |   </build>
68 | </project>
69 | 


--------------------------------------------------------------------------------
/src/main/java/org/apache/solr/config/upgrade/UpgradeProcessorsConfig.java:
--------------------------------------------------------------------------------
 1 | /*
 2 |  * Licensed to the Apache Software Foundation (ASF) under one or more
 3 |  * contributor license agreements.  See the NOTICE file distributed with
 4 |  * this work for additional information regarding copyright ownership.
 5 |  * The ASF licenses this file to You under the Apache License, Version 2.0
 6 |  * (the "License"); you may not use this file except in compliance with
 7 |  * the License.  You may obtain a copy of the License at
 8 |  *
 9 |  *     http://www.apache.org/licenses/LICENSE-2.0
10 |  *
11 |  * Unless required by applicable law or agreed to in writing, software
12 |  * distributed under the License is distributed on an "AS IS" BASIS,
13 |  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 |  * See the License for the specific language governing permissions and
15 |  * limitations under the License.
16 |  */
17 | package org.apache.solr.config.upgrade;
18 | 
19 | import java.util.Objects;
20 | import java.util.Optional;
21 | 
22 | import com.fasterxml.jackson.dataformat.xml.annotation.JacksonXmlProperty;
23 | import com.fasterxml.jackson.dataformat.xml.annotation.JacksonXmlRootElement;
24 | 
25 | @JacksonXmlRootElement(localName = "upgradeProcessors")
26 | public class UpgradeProcessorsConfig {
27 |   @JacksonXmlProperty(isAttribute = true)
28 |   private int inputVersion;
29 | 
30 |   @JacksonXmlProperty(isAttribute = true)
31 |   private int outputVersion;
32 | 
33 |   @JacksonXmlProperty(localName="processor")
34 |   private ProcessorConfig[] processors;
35 | 
36 |   public int getInputVersion() {
37 |     return inputVersion;
38 |   }
39 | 
40 |   public int getOutputVersion() {
41 |     return outputVersion;
42 |   }
43 | 
44 |   public Optional<ProcessorConfig> getProcessorByConfigType(ConfigType confType) {
45 |     for (ProcessorConfig p : processors) {
46 |       if (Objects.equals(confType.getConfigType(), p.getConfigType())) {
47 |         return Optional.of(p);
48 |       }
49 |     }
50 | 
51 |     return Optional.empty();
52 |   }
53 | 
54 |   public static class ProcessorConfig {
55 |     @JacksonXmlProperty(isAttribute = true)
56 |     private String configType;
57 | 
58 |     @JacksonXmlProperty(isAttribute=true)
59 |     private String validatorPath;
60 | 
61 |     @JacksonXmlProperty(isAttribute=true)
62 |     private String transformerPath;
63 | 
64 |     public String getConfigType() {
65 |       return configType;
66 |     }
67 | 
68 |     public String getValidatorPath() {
69 |       return validatorPath;
70 |     }
71 | 
72 |     public String getTransformerPath() {
73 |       return transformerPath;
74 |     }
75 |   }
76 | }
77 | 


--------------------------------------------------------------------------------
/validators/solrconfig_4_to_5_transformer.xslt:
--------------------------------------------------------------------------------
 1 | <xsl:stylesheet version="2.0" 
 2 |                 xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
 3 | 
 4 | <!--
 5 |  Licensed to the Apache Software Foundation (ASF) under one or more
 6 |  contributor license agreements.  See the NOTICE file distributed with
 7 |  this work for additional information regarding copyright ownership.
 8 |  The ASF licenses this file to You under the Apache License, Version 2.0
 9 |  (the "License"); you may not use this file except in compliance with
10 |  the License.  You may obtain a copy of the License at
11 | 
12 |      http://www.apache.org/licenses/LICENSE-2.0
13 | 
14 |  Unless required by applicable law or agreed to in writing, software
15 |  distributed under the License is distributed on an "AS IS" BASIS,
16 |  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
17 |  See the License for the specific language governing permissions and
18 |  limitations under the License.
19 | -->
20 | 
21 | <xsl:output method="xml" version="1.0" encoding="UTF-8" indent="true" standalone="yes" />
22 | <xsl:strip-space elements="*"/>
23 | 
24 | <!-- identity transform -->
25 | <xsl:template match="@* | node()">
26 |   <xsl:copy>
27 |     <xsl:apply-templates select="node() | @*"/>
28 |   </xsl:copy>
29 | </xsl:template>
30 | 
31 | <!-- Required to ensure proper indentation for the comments in the config file -->
32 | <xsl:template match="/comment()">
33 |   <xsl:text>&#10;</xsl:text>
34 |   <xsl:copy/>
35 | </xsl:template>
36 | 
37 | <xsl:template match="config">
38 |   <xsl:text>&#10;</xsl:text>
39 |   <xsl:copy>
40 |     <xsl:apply-templates select="child::node()"/>
41 |   </xsl:copy>
42 | </xsl:template>
43 | 
44 | <!-- Remove the following configuration sections from the result -->
45 | <xsl:template match="indexConfig/termIndexInterval">
46 |   <xsl:message>* Removed "termIndexInterval" configuration from "indexConfig" section</xsl:message>
47 | </xsl:template>
48 | <xsl:template match="indexConfig/checkIntegrityAtMerge">
49 |   <xsl:message>* Removed "checkIntegrityAtMerge" configuration from "indexConfig" section</xsl:message>
50 | </xsl:template>
51 | <xsl:template match="indexConfig/nrtMode">
52 |   <xsl:message>* Removed "nrtMode" configuration from "indexConfig" section</xsl:message>
53 | </xsl:template>
54 | 
55 | <!-- Update UniqFieldsUpdateProcessorFactory config section to use correct param name -->
56 | <xsl:template match="updateRequestProcessorChain/processor[@class='org.apache.solr.update.processor.UniqFieldsUpdateProcessorFactory']/lst[@name='fields']">
57 |   <xsl:message>* Using &lt;arr name="fieldName"&gt; init param style for UniqFieldsUpdateProcessorFactory</xsl:message>
58 |   <arr name="fieldName">
59 |     <xsl:copy>
60 |       <xsl:apply-templates select="child::node()"/>
61 |     </xsl:copy>
62 |   </arr>
63 | </xsl:template>
64 | 
65 | </xsl:stylesheet>
66 | 


--------------------------------------------------------------------------------
/src/main/java/org/apache/solr/config/upgrade/ConfigValidator.java:
--------------------------------------------------------------------------------
 1 | /*
 2 |  * Licensed to the Apache Software Foundation (ASF) under one or more
 3 |  * contributor license agreements.  See the NOTICE file distributed with
 4 |  * this work for additional information regarding copyright ownership.
 5 |  * The ASF licenses this file to You under the Apache License, Version 2.0
 6 |  * (the "License"); you may not use this file except in compliance with
 7 |  * the License.  You may obtain a copy of the License at
 8 |  *
 9 |  *     http://www.apache.org/licenses/LICENSE-2.0
10 |  *
11 |  * Unless required by applicable law or agreed to in writing, software
12 |  * distributed under the License is distributed on an "AS IS" BASIS,
13 |  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 |  * See the License for the specific language governing permissions and
15 |  * limitations under the License.
16 |  */
17 | package org.apache.solr.config.upgrade;
18 | 
19 | import java.nio.file.Files;
20 | import java.nio.file.Path;
21 | import java.nio.file.Paths;
22 | 
23 | import javax.xml.transform.Source;
24 | import javax.xml.transform.Transformer;
25 | import javax.xml.transform.TransformerConfigurationException;
26 | import javax.xml.transform.TransformerException;
27 | import javax.xml.transform.dom.DOMResult;
28 | import javax.xml.transform.stream.StreamSource;
29 | 
30 | import org.apache.solr.config.upgrade.UpgradeProcessorsConfig.ProcessorConfig;
31 | import org.w3c.dom.Document;
32 | 
33 | /**
34 |  * TODO
35 |  */
36 | public class ConfigValidator {
37 |   private final String confName;
38 |   private final Transformer transformer;
39 | 
40 |   public ConfigValidator(ToolParams params, String confName, ProcessorConfig procConfig) {
41 |     this.confName = confName;
42 |     this.transformer = buildTransformer(params, procConfig);
43 |   }
44 | 
45 |   public boolean validate(Source config, ValidationHandler handler) throws TransformerException {
46 |     handler.begin(confName);
47 |     DOMResult validationResult = new DOMResult();
48 |     transformer.transform(config, validationResult);
49 |     return handler.process(confName, (Document)validationResult.getNode());
50 |   }
51 | 
52 |   protected Transformer buildTransformer(ToolParams params, ProcessorConfig procConfig) {
53 |     Path scriptPath = Paths.get(procConfig.getValidatorPath());
54 |     if (!scriptPath.isAbsolute()) {
55 |       scriptPath = params.getProcessorConfPath().getParent().resolve(scriptPath);
56 |     }
57 |     if (!Files.exists(scriptPath)) {
58 |       throw new IllegalArgumentException("Unable to find validation script "+scriptPath);
59 |     }
60 |     try {
61 |       return params.getFactory().newTransformer(new StreamSource(scriptPath.toFile())) ;
62 |     } catch (TransformerConfigurationException e) {
63 |       throw new UpgradeConfigException(e);
64 |     }
65 |   }
66 | }
67 | 


--------------------------------------------------------------------------------
/validators/solrconfig_5_to_6_validator.xslt:
--------------------------------------------------------------------------------
 1 | <xsl:stylesheet version="2.0" 
 2 |                 xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
 3 | 
 4 | <!--
 5 |  Licensed to the Apache Software Foundation (ASF) under one or more
 6 |  contributor license agreements.  See the NOTICE file distributed with
 7 |  this work for additional information regarding copyright ownership.
 8 |  The ASF licenses this file to You under the Apache License, Version 2.0
 9 |  (the "License"); you may not use this file except in compliance with
10 |  the License.  You may obtain a copy of the License at
11 | 
12 |      http://www.apache.org/licenses/LICENSE-2.0
13 | 
14 |  Unless required by applicable law or agreed to in writing, software
15 |  distributed under the License is distributed on an "AS IS" BASIS,
16 |  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
17 |  See the License for the specific language governing permissions and
18 |  limitations under the License.
19 | -->
20 | 
21 | <xsl:output method="xml" version="1.0" encoding="UTF-8" indent="true" standalone="yes" />
22 | <xsl:strip-space elements="*"/>
23 | 
24 | <xsl:template match="/">
25 |   <xsl:element name="result">
26 |   <xsl:apply-templates/>
27 |   </xsl:element>
28 | </xsl:template>
29 | 
30 | <!-- identity transform -->
31 | <xsl:template match="@* | node()">
32 |   <xsl:apply-templates select="node() | @*"/>
33 | </xsl:template>
34 | 
35 | <xsl:template match="config">
36 |   <xsl:if test="not(./schemaFactory)">
37 |     <incompatibility>
38 |       <level>info</level>
39 |       <jira_number>TBD</jira_number>
40 |       <description>The implicit default schema factory is changed from ClassicIndexSchemaFactory to ManagedIndexSchemaFactory. This means that the Schema APIs ( /&lt;collection&gt;/schema ) are enabled and the schema is mutable.</description>
41 |       <recommendation>Users who wish to preserve back-compatible behavior should either explicitly configure schemaFactory to use ClassicIndexSchemaFactory, or ensure that the luceneMatchVersion for the collection is less then 6.0</recommendation>
42 |       <reindexing>no</reindexing>
43 |       <transform>no</transform>
44 |     </incompatibility>
45 |   </xsl:if>
46 |   <xsl:apply-templates select="child::node()"/>
47 | </xsl:template>
48 | 
49 | <xsl:template match="schemaFactory">
50 |   <xsl:message>Parent is : <xsl:value-of select="name(..)" /></xsl:message>
51 | </xsl:template>
52 | 
53 | <xsl:template match="indexConfig">
54 |   <xsl:if test="./nrtMode">
55 |     <incompatibility>
56 |       <level>info</level>
57 |       <jira_number>SOLR-6897</jira_number>
58 |       <description>The &lt;nrtMode&gt; configuration has been discontinued and should be removed</description>
59 |       <recommendation>Solr defaults to using NRT searchers and this configuration is not required</recommendation>
60 |       <reindexing>No</reindexing>
61 |       <transform>yes</transform>
62 |     </incompatibility>
63 |   </xsl:if>
64 | 
65 |   <xsl:apply-templates select="child::node()"/>
66 | </xsl:template>
67 | 
68 | </xsl:stylesheet>
69 | 


--------------------------------------------------------------------------------
/src/main/java/org/apache/solr/config/upgrade/ToolParams.java:
--------------------------------------------------------------------------------
 1 | /*
 2 |  * Licensed to the Apache Software Foundation (ASF) under one or more
 3 |  * contributor license agreements.  See the NOTICE file distributed with
 4 |  * this work for additional information regarding copyright ownership.
 5 |  * The ASF licenses this file to You under the Apache License, Version 2.0
 6 |  * (the "License"); you may not use this file except in compliance with
 7 |  * the License.  You may obtain a copy of the License at
 8 |  *
 9 |  *     http://www.apache.org/licenses/LICENSE-2.0
10 |  *
11 |  * Unless required by applicable law or agreed to in writing, software
12 |  * distributed under the License is distributed on an "AS IS" BASIS,
13 |  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 |  * See the License for the specific language governing permissions and
15 |  * limitations under the License.
16 |  */
17 | package org.apache.solr.config.upgrade;
18 | 
19 | import java.nio.file.Files;
20 | import java.nio.file.Path;
21 | 
22 | import javax.xml.transform.TransformerFactory;
23 | 
24 | public class ToolParams {
25 |   private final ConfigType confType;
26 |   private final Path solrConfPath;
27 |   private final Path processorConfPath;
28 |   private final Path resultDirPath;
29 |   private final boolean dryRun;
30 |   private final TransformerFactory factory;
31 |   private final UpgradeProcessorsConfig upgradeProcessorConf;
32 | 
33 |   public ToolParams(ConfigType confType, Path solrConfPath, Path processorConfPath,
34 |       Path resultDirPath, boolean dryRun, boolean verbose) throws Exception {
35 |     this.confType = confType;
36 |     this.solrConfPath = solrConfPath;
37 |     this.processorConfPath = processorConfPath;
38 |     this.resultDirPath = resultDirPath;
39 |     this.dryRun = dryRun;
40 |     this.factory = TransformerFactory.newInstance();
41 |     this.factory.setErrorListener(new SuppressCompilerWarnings(verbose));
42 |     this.upgradeProcessorConf = UpgradeProcessorsConfigFactory.newInstance(processorConfPath);
43 |   }
44 | 
45 |   public ConfigType getConfType() {
46 |     return confType;
47 |   }
48 | 
49 |   public Path getSolrConfPath() {
50 |     return solrConfPath;
51 |   }
52 | 
53 |   public Path getResultDirPath() {
54 |     return resultDirPath;
55 |   }
56 | 
57 |   public TransformerFactory getFactory() {
58 |     return factory;
59 |   }
60 | 
61 |   public boolean isDryRun() {
62 |     return dryRun;
63 |   }
64 | 
65 |   public Path getProcessorConfPath() {
66 |     return processorConfPath;
67 |   }
68 | 
69 |   public UpgradeProcessorsConfig getUpgradeProcessorConf() {
70 |     return upgradeProcessorConf;
71 |   }
72 | 
73 |   /**
74 |    * Validate the specified input parameters
75 |    */
76 |   public void checkArgs() {
77 |     if (!Files.exists(solrConfPath)) {
78 |       throw new IllegalStateException("Unable to locate the Solr configuration " + solrConfPath);
79 |     }
80 |     if (!Files.exists(processorConfPath)) {
81 |       throw new IllegalStateException("Unable to locate upgrade processor config file  " + processorConfPath);
82 |     }
83 |     if (!Files.exists(resultDirPath)) {
84 |       throw new IllegalArgumentException("The result directory ( " + resultDirPath+" ) does not exist.");
85 |     }
86 |   }
87 | 
88 | }
89 | 


--------------------------------------------------------------------------------
/src/main/resources/validation_result_summary.xslt:
--------------------------------------------------------------------------------
 1 | <xsl:stylesheet version="2.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
 2 | 
 3 | <!--
 4 |  Licensed to the Apache Software Foundation (ASF) under one or more
 5 |  contributor license agreements.  See the NOTICE file distributed with
 6 |  this work for additional information regarding copyright ownership.
 7 |  The ASF licenses this file to You under the Apache License, Version 2.0
 8 |  (the "License"); you may not use this file except in compliance with
 9 |  the License.  You may obtain a copy of the License at
10 | 
11 |      http://www.apache.org/licenses/LICENSE-2.0
12 | 
13 |  Unless required by applicable law or agreed to in writing, software
14 |  distributed under the License is distributed on an "AS IS" BASIS,
15 |  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
16 |  See the License for the specific language governing permissions and
17 |  limitations under the License.
18 | -->
19 | 
20 | <xsl:output method="text" version="1.0" encoding="UTF-8" indent="true"/>
21 | 
22 | <xsl:param name="solrOpVersion" />
23 | <xsl:param name="dryRun" />
24 | 
25 | <xsl:template match="result">
26 |   <xsl:choose>
27 |     <xsl:when test="/result/incompatibility[contains(level, 'error')]">
28 |       <xsl:text>&#10;</xsl:text>Following configuration errors found:
29 |       <xsl:for-each select="/result/incompatibility[contains(level, 'error')]">
30 |       * <xsl:value-of select="./description"/>
31 |       </xsl:for-each>
32 |       <xsl:text>&#10;</xsl:text><xsl:text>&#10;</xsl:text>
33 |     </xsl:when>
34 |     <xsl:otherwise><xsl:text>No configuration errors found...&#10;</xsl:text></xsl:otherwise>
35 |   </xsl:choose>
36 | 
37 |   <xsl:choose>
38 |     <xsl:when test="/result/incompatibility[contains(level, 'warn')]"><xsl:text>&#10;</xsl:text>Following configuration warnings found:
39 |       <xsl:for-each select="/result/incompatibility[contains(level, 'warn')]">
40 |       * <xsl:value-of select="./description"/>
41 |       </xsl:for-each>
42 |       <xsl:text>&#10;</xsl:text>
43 |     </xsl:when>
44 |     <xsl:otherwise><xsl:text>No configuration warnings found...&#10;</xsl:text></xsl:otherwise>
45 |   </xsl:choose>
46 | 
47 |   <xsl:if test="not($dryRun)">
48 |   <xsl:if test="/result/incompatibility[contains(level, 'info') and contains(transform, 'yes')]"><xsl:text>&#10;</xsl:text>Following incompatibilities will be fixed by auto-transformations (using --upgrade command):</xsl:if>
49 |   <xsl:for-each select="/result/incompatibility[contains(level, 'info') and contains(transform, 'yes')]">
50 |     * <xsl:value-of select="./description"/>
51 |   </xsl:for-each>
52 |   <xsl:if test="/result/incompatibility[contains(level, 'info') and contains(transform, 'yes')]"><xsl:text>&#10;</xsl:text></xsl:if>
53 |   </xsl:if>
54 | 
55 |   <xsl:if test="/result/incompatibility[contains(level, 'info') and contains(transform, 'no')]"><xsl:text>&#10;</xsl:text>Please note that in Solr <xsl:value-of select="$solrOpVersion"/>:</xsl:if>
56 |   <xsl:for-each select="/result/incompatibility[contains(level, 'info') and contains(transform, 'no')]">
57 |     * <xsl:value-of select="./description"/>
58 |   </xsl:for-each>
59 |   <xsl:if test="/result/incompatibility[contains(level, 'info') and contains(transform, 'no')]"><xsl:text>&#10;</xsl:text></xsl:if>
60 | </xsl:template>
61 | 
62 | </xsl:stylesheet>
63 | 


--------------------------------------------------------------------------------
/src/main/java/org/apache/solr/config/upgrade/ConfigTransformer.java:
--------------------------------------------------------------------------------
 1 | /*
 2 |  * Licensed to the Apache Software Foundation (ASF) under one or more
 3 |  * contributor license agreements.  See the NOTICE file distributed with
 4 |  * this work for additional information regarding copyright ownership.
 5 |  * The ASF licenses this file to You under the Apache License, Version 2.0
 6 |  * (the "License"); you may not use this file except in compliance with
 7 |  * the License.  You may obtain a copy of the License at
 8 |  *
 9 |  *     http://www.apache.org/licenses/LICENSE-2.0
10 |  *
11 |  * Unless required by applicable law or agreed to in writing, software
12 |  * distributed under the License is distributed on an "AS IS" BASIS,
13 |  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 |  * See the License for the specific language governing permissions and
15 |  * limitations under the License.
16 |  */
17 | package org.apache.solr.config.upgrade;
18 | 
19 | import java.nio.file.Files;
20 | import java.nio.file.Path;
21 | import java.nio.file.Paths;
22 | 
23 | import javax.xml.transform.OutputKeys;
24 | import javax.xml.transform.Source;
25 | import javax.xml.transform.Transformer;
26 | import javax.xml.transform.TransformerConfigurationException;
27 | import javax.xml.transform.TransformerException;
28 | import javax.xml.transform.stream.StreamResult;
29 | import javax.xml.transform.stream.StreamSource;
30 | 
31 | import org.apache.solr.config.upgrade.UpgradeProcessorsConfig.ProcessorConfig;
32 | 
33 | public class ConfigTransformer {
34 |   private final Transformer transformer;
35 |   private final Path resultFile;
36 | 
37 |   public ConfigTransformer(ToolParams params, ProcessorConfig procConfig) {
38 |     try {
39 |       this.transformer = buildTransformer(params, procConfig);
40 |     } catch (TransformerConfigurationException e) {
41 |       throw new UpgradeConfigException (e);
42 |     }
43 | 
44 |     String confFileName = params.getSolrConfPath().getFileName().toString();
45 |     this.resultFile = params.getResultDirPath().resolve(confFileName);
46 |   }
47 | 
48 |   public void transform (Source config) throws TransformerException {
49 |     System.out.println("Applying auto transformations...");
50 |     transformer.transform(config, new StreamResult(resultFile.toFile()));
51 |     System.out.println();
52 |     System.out.println("The upgraded configuration file is available at " + resultFile);
53 |   }
54 | 
55 |   protected Transformer buildTransformer(ToolParams params, ProcessorConfig procConfig)
56 |       throws TransformerConfigurationException {
57 |     Transformer result = params.getFactory().newTransformer(); // identity transform.
58 | 
59 |     if (procConfig.getTransformerPath() != null) {
60 |       Path scriptPath = Paths.get(procConfig.getTransformerPath());
61 |       if (!scriptPath.isAbsolute()) {
62 |         scriptPath = params.getProcessorConfPath().getParent().resolve(scriptPath);
63 |       }
64 |       if (!Files.exists(scriptPath)) {
65 |         throw new IllegalArgumentException("Unable to find transformation script "+scriptPath);
66 |       }
67 |       result = params.getFactory().newTransformer(new StreamSource(scriptPath.toFile()));
68 |     }
69 | 
70 |     result.setOutputProperty(OutputKeys.INDENT, "yes");
71 |     result.setOutputProperty("{http://xml.apache.org/xslt}indent-amount", "2");
72 |     return result;
73 |   }
74 | 
75 | }
76 | 


--------------------------------------------------------------------------------
/validators/schema_5_to_6_validator.xslt:
--------------------------------------------------------------------------------
 1 | <xsl:stylesheet version="2.0" 
 2 |                 xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
 3 | 
 4 | <!--
 5 |  Licensed to the Apache Software Foundation (ASF) under one or more
 6 |  contributor license agreements.  See the NOTICE file distributed with
 7 |  this work for additional information regarding copyright ownership.
 8 |  The ASF licenses this file to You under the Apache License, Version 2.0
 9 |  (the "License"); you may not use this file except in compliance with
10 |  the License.  You may obtain a copy of the License at
11 | 
12 |      http://www.apache.org/licenses/LICENSE-2.0
13 | 
14 |  Unless required by applicable law or agreed to in writing, software
15 |  distributed under the License is distributed on an "AS IS" BASIS,
16 |  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
17 |  See the License for the specific language governing permissions and
18 |  limitations under the License.
19 | -->
20 | 
21 | <xsl:output method="xml" version="1.0" encoding="UTF-8" indent="true" standalone="yes" />
22 | <xsl:strip-space elements="*"/>
23 | 
24 | <xsl:template match="/">
25 |   <xsl:element name="result">
26 |   <xsl:apply-templates/>
27 |   </xsl:element>
28 | </xsl:template>
29 | 
30 | <!-- identity transform -->
31 | <xsl:template match="@* | node()">
32 |   <xsl:apply-templates select="node() | @*"/>
33 | </xsl:template>
34 | 
35 | <xsl:template match="schema">
36 |   <xsl:if test="not(./similarity)">
37 |     <incompatibility>
38 |       <level>info</level>
39 |       <jira_number>SOLR-8270, SOLR-8271</jira_number>
40 |       <description>The implicit default Similarity is changed to SchemaSimilarityFactory</description>
41 |       <recommendation>Users who wish to preserve back-compatible behavior should either explicitly configure ClassicSimilarityFactory, or ensure that the luceneMatchVersion for the collection is less then 6.0</recommendation>
42 |       <reindexing>TBD</reindexing>
43 |       <transform>no</transform>
44 |     </incompatibility>
45 |   </xsl:if>
46 |   <xsl:apply-templates select="child::node()"/>
47 | </xsl:template>
48 | 
49 | <xsl:template match="similarity[@class='solr.DefaultSimilarityFactory']">
50 |     <incompatibility>
51 |       <level>info</level>
52 |       <jira_number>SOLR-8239</jira_number>
53 |       <description>DefaultSimilarityFactory has been removed</description>
54 |       <recommendation>If you currently have DefaultSimilarityFactory explicitly referenced in your schema.xml, edit your config to use the functionally identical ClassicSimilarityFactory</recommendation>
55 |       <reindexing>TBD</reindexing>
56 |       <transform>yes</transform>
57 |     </incompatibility>
58 | </xsl:template>
59 | 
60 | <xsl:template match="similarity[@class='solr.SchemaSimilarityFactory']">
61 |     <incompatibility>
62 |       <level>info</level>
63 |       <jira_number>SOLR-8261, SOLR-8329 </jira_number>
64 |       <description>SchemaSimilarityFactory has been modified to use BM25Similarity as the default for fieldTypes that do not explicitly declare a Similarity</description>
65 |       <recommendation>The legacy behavior of using ClassicSimilarity as the default will occur if the luceneMatchVersion for the collection is less then 6.0, or the 'defaultSimFromFieldType' configuration option may be used to specify any default of your choosing</recommendation>
66 |       <reindexing>TBD</reindexing>
67 |       <transform>no</transform>
68 |     </incompatibility>
69 | </xsl:template>
70 | 
71 | </xsl:stylesheet>
72 | 


--------------------------------------------------------------------------------
/validators/solrconfig_4_to_5_validator.xslt:
--------------------------------------------------------------------------------
  1 | <xsl:stylesheet version="2.0" 
  2 |                 xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
  3 | 
  4 | <!--
  5 |  Licensed to the Apache Software Foundation (ASF) under one or more
  6 |  contributor license agreements.  See the NOTICE file distributed with
  7 |  this work for additional information regarding copyright ownership.
  8 |  The ASF licenses this file to You under the Apache License, Version 2.0
  9 |  (the "License"); you may not use this file except in compliance with
 10 |  the License.  You may obtain a copy of the License at
 11 | 
 12 |      http://www.apache.org/licenses/LICENSE-2.0
 13 | 
 14 |  Unless required by applicable law or agreed to in writing, software
 15 |  distributed under the License is distributed on an "AS IS" BASIS,
 16 |  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 17 |  See the License for the specific language governing permissions and
 18 |  limitations under the License.
 19 | -->
 20 | 
 21 | <xsl:output method="xml" version="1.0" encoding="UTF-8" indent="true" standalone="yes" />
 22 | <xsl:strip-space elements="*"/>
 23 | 
 24 | <xsl:template match="/">
 25 |   <xsl:element name="result">
 26 |   <xsl:apply-templates/>
 27 |   </xsl:element>
 28 | </xsl:template>
 29 | 
 30 | <!-- identity transform -->
 31 | <xsl:template match="@* | node()">
 32 |   <xsl:apply-templates select="node() | @*"/>
 33 | </xsl:template>
 34 | 
 35 | <xsl:template match="indexConfig">
 36 |   <xsl:if test="./termIndexInterval">
 37 |     <incompatibility>
 38 |       <level>info</level> 
 39 |       <jira_number>SOLR-6560</jira_number>
 40 |       <description>The "termIndexInterval" option is a no-op and should be removed</description>
 41 |       <recommendation>TBD</recommendation>
 42 |       <reindexing>No</reindexing>
 43 |       <transform>yes</transform>
 44 |     </incompatibility>
 45 |   </xsl:if>
 46 | 
 47 |   <xsl:if test="./checkIntegrityAtMerge">
 48 |     <incompatibility>
 49 |       <level>info</level>
 50 |       <jira_number>SOLR-6834</jira_number>
 51 |       <description>The "checkIntegrityAtMerge" option is a no-op and should be removed</description>
 52 |       <recommendation>TBD</recommendation>
 53 |       <reindexing>No</reindexing>
 54 |       <transform>yes</transform>
 55 |     </incompatibility>
 56 |   </xsl:if>
 57 | 
 58 |   <xsl:if test="./nrtMode">
 59 |     <incompatibility>
 60 |       <level>info</level>
 61 |       <jira_number>SOLR-6897</jira_number>
 62 |       <description>The &lt;nrtMode&gt; configuration has been discontinued and should be removed</description>
 63 |       <recommendation>Solr defaults to using NRT searchers and this configuration is not required</recommendation>
 64 |       <reindexing>No</reindexing>
 65 |       <transform>yes</transform>
 66 |     </incompatibility>
 67 |   </xsl:if>
 68 | 
 69 |   <xsl:apply-templates select="child::node()"/>
 70 | </xsl:template>
 71 | 
 72 | <xsl:template match="infoStream">
 73 |   <xsl:if test="@file">
 74 |     <incompatibility>
 75 |       <level>error</level> 
 76 |       <jira_number>TBD</jira_number>
 77 |       <description>The "file" attribute of infoStream element is removed</description>
 78 |       <recommendation>Control this via your logging configuration (org.apache.solr.update.LoggingInfoStream) instead</recommendation>
 79 |       <reindexing>No</reindexing>
 80 |       <transform>no</transform>
 81 |     </incompatibility>
 82 |   </xsl:if>
 83 |   <xsl:apply-templates select="child::node()"/>
 84 | </xsl:template>
 85 | 
 86 | <xsl:template match="updateRequestProcessorChain">
 87 |   <xsl:if test="./processor[@class='org.apache.solr.update.processor.UniqFieldsUpdateProcessorFactory']/lst[@name='fields']">
 88 |     <incompatibility>
 89 |       <level>info</level>  
 90 |       <jira_number>SOLR-4249</jira_number>
 91 |       <description>UniqFieldsUpdateProcessorFactory no longer supports the &lt;lst named=&quot;fields&quot;&gt; init param style</description>
 92 |       <recommendation>Update your solrconfig.xml to use &lt;arr name=&quot;fieldName&quot;&gt; instead</recommendation>
 93 |       <reindexing>No</reindexing>
 94 |       <transform>yes</transform>
 95 |     </incompatibility>
 96 |   </xsl:if>
 97 |   <xsl:apply-templates select="child::node()"/>
 98 | </xsl:template>
 99 | 
100 | </xsl:stylesheet>
101 | 


--------------------------------------------------------------------------------
/src/main/java/org/apache/solr/config/upgrade/impl/DefaultValidationResultProcessor.java:
--------------------------------------------------------------------------------
 1 | /*
 2 |  * Licensed to the Apache Software Foundation (ASF) under one or more
 3 |  * contributor license agreements.  See the NOTICE file distributed with
 4 |  * this work for additional information regarding copyright ownership.
 5 |  * The ASF licenses this file to You under the Apache License, Version 2.0
 6 |  * (the "License"); you may not use this file except in compliance with
 7 |  * the License.  You may obtain a copy of the License at
 8 |  *
 9 |  *     http://www.apache.org/licenses/LICENSE-2.0
10 |  *
11 |  * Unless required by applicable law or agreed to in writing, software
12 |  * distributed under the License is distributed on an "AS IS" BASIS,
13 |  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 |  * See the License for the specific language governing permissions and
15 |  * limitations under the License.
16 |  */
17 | 
18 | package org.apache.solr.config.upgrade.impl;
19 | 
20 | import javax.xml.transform.OutputKeys;
21 | import javax.xml.transform.Transformer;
22 | import javax.xml.transform.TransformerFactory;
23 | import javax.xml.transform.dom.DOMSource;
24 | import javax.xml.transform.stream.StreamResult;
25 | import javax.xml.transform.stream.StreamSource;
26 | import javax.xml.xpath.XPath;
27 | import javax.xml.xpath.XPathConstants;
28 | import javax.xml.xpath.XPathExpressionException;
29 | import javax.xml.xpath.XPathFactory;
30 | 
31 | import org.apache.solr.config.upgrade.ConfigUpgradeTool;
32 | import org.apache.solr.config.upgrade.ToolParams;
33 | import org.apache.solr.config.upgrade.ValidationHandler;
34 | import org.w3c.dom.Document;
35 | import org.w3c.dom.NodeList;
36 | 
37 | public class DefaultValidationResultProcessor implements ValidationHandler {
38 |   private final ToolParams params;
39 | 
40 |   public DefaultValidationResultProcessor(ToolParams params) {
41 |     this.params = params;
42 |   }
43 | 
44 |   @Override
45 |   public void begin(String confName) {
46 |     System.out.println("Validating "+confName+"...");
47 |     //System.out.println();
48 |   }
49 | 
50 |   @Override
51 |   public boolean process(String confName, Document result) {
52 |     StreamSource resultSummaryProcessor = new StreamSource(
53 |         ConfigUpgradeTool.class.getClassLoader()
54 |                                .getResourceAsStream("validation_result_summary.xslt"));
55 | 
56 |     try {
57 |       Transformer summaryTransform =
58 |           TransformerFactory.newInstance().newTransformer(resultSummaryProcessor);
59 |       summaryTransform.setParameter("solrOpVersion", this.params.getUpgradeProcessorConf().getOutputVersion());
60 |       summaryTransform.setParameter("dryRun", this.params.isDryRun());
61 |       summaryTransform.transform(new DOMSource(result), new StreamResult(System.out));
62 | 
63 |       // Store the results in the specified directory.
64 |       Transformer saveTransform = TransformerFactory.newInstance().newTransformer();
65 |       saveTransform.setOutputProperty(OutputKeys.INDENT, "yes");
66 |       saveTransform.setOutputProperty("{http://xml.apache.org/xslt}indent-amount", "2");
67 |       saveTransform.transform(new DOMSource(result),
68 |           new StreamResult(this.params.getResultDirPath().resolve(confName+"_validation.xml").toFile()));
69 | 
70 |       if (evaluateXPathExpression(result, "/result/incompatibility[contains(level, 'error')]").getLength() == 0) {
71 |         System.out.println();
72 |         System.out.printf("Solr %s validation is successful. Please review %s for more details. \n",
73 |             confName, params.getResultDirPath().resolve(confName+"_validation.xml").toAbsolutePath());
74 |         System.out.println();
75 |         return true;
76 |       } else {
77 |         System.out.println();
78 |         System.out.printf("Solr %s validation failed. Please review %s for more details. \n",
79 |             confName, params.getResultDirPath().resolve(confName+"_validation.xml"));
80 |         System.out.println();
81 |         return false;
82 |       }
83 | 
84 |     } catch (Exception ex) {
85 |       throw new RuntimeException(ex);
86 |     }
87 |   }
88 | 
89 |   private static NodeList evaluateXPathExpression (Document doc, String expr) throws XPathExpressionException {
90 |     XPath xpath = XPathFactory.newInstance().newXPath();
91 |     return (NodeList)xpath.compile(expr).evaluate(doc, XPathConstants.NODESET);
92 |   }
93 | 
94 | 
95 | }
96 | 


--------------------------------------------------------------------------------
/validators/schema_4_to_5_validator.xslt:
--------------------------------------------------------------------------------
  1 | <xsl:stylesheet version="2.0" 
  2 |                 xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
  3 | 
  4 | <!--
  5 |  Licensed to the Apache Software Foundation (ASF) under one or more
  6 |  contributor license agreements.  See the NOTICE file distributed with
  7 |  this work for additional information regarding copyright ownership.
  8 |  The ASF licenses this file to You under the Apache License, Version 2.0
  9 |  (the "License"); you may not use this file except in compliance with
 10 |  the License.  You may obtain a copy of the License at
 11 | 
 12 |      http://www.apache.org/licenses/LICENSE-2.0
 13 | 
 14 |  Unless required by applicable law or agreed to in writing, software
 15 |  distributed under the License is distributed on an "AS IS" BASIS,
 16 |  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 17 |  See the License for the specific language governing permissions and
 18 |  limitations under the License.
 19 | -->
 20 | 
 21 | <xsl:output method="xml" version="1.0" encoding="UTF-8" indent="true" standalone="yes" />
 22 | <xsl:strip-space elements="*"/>
 23 | 
 24 | <xsl:template match="/">
 25 |   <xsl:element name="result">
 26 |   <xsl:apply-templates/>
 27 |   </xsl:element>
 28 | </xsl:template>
 29 | 
 30 | <!-- identity transform -->
 31 | <xsl:template match="@* | node()">
 32 |   <xsl:apply-templates select="node() | @*"/>
 33 | </xsl:template>
 34 | 
 35 | <xsl:template match="fieldType">
 36 |   <xsl:if test="@class='solr.SortableIntField'
 37 |                 or @class='solr.SortableLongField'
 38 |                 or @class='solr.SortableFloatField'
 39 |                 or @class='solr.SortableDoubleField'
 40 |                 or @class='solr.DateField'
 41 |                 or @class='solr.IntField'
 42 |                 or @class='solr.LongField'
 43 |                 or @class='solr.FloatField'
 44 |                 or @class='solr.DoubleField'
 45 |                 or @class='solr.BCDIntField'
 46 |                 or @class='solr.BCDLongField'
 47 |                 or @class='solr.BCDStrField'">
 48 |     <incompatibility>
 49 |       <level>error</level> 
 50 |       <jira_number>SOLR-5936</jira_number>
 51 |       <description>Legacy field type (name = <xsl:value-of select="attribute::name"/> and class = <xsl:value-of select="attribute::class"/>) is removed.</description>
 52 |       <recommendation>TBD</recommendation>
 53 |       <reindexing>Required</reindexing>
 54 |       <transform>no</transform> 
 55 |     </incompatibility>
 56 |   </xsl:if>
 57 | 
 58 |   <xsl:if test="(@class='solr.SpatialRecursivePrefixTreeFieldType'
 59 |                  or @class='solr.SpatialPointVectorFieldType'
 60 |                  or @class='solr.BBoxField') and @units">
 61 |     <warning>
 62 |       <level>error</level>
 63 |       <jira_number>SOLR-6797</jira_number>
 64 |       <description>'units' attribute for spatial field type (name = <xsl:value-of select="attribute::name"/> and class = <xsl:value-of select
 65 | ="attribute::class"/>) is deprecated</description>
 66 |       <recommendation>
 67 |         Spatial fields originating from Solr 4 (e.g. SpatialRecursivePrefixTreeFieldType, BBoxField)
 68 |         have the 'units' attribute deprecated, now replaced with 'distanceUnits'.  If you change it to
 69 |         a unit other than 'degrees' (or if you don't specify it, which will default to kilometers if
 70 |         geo=true), then be sure to update maxDistErr as it's in those units.  If you keep units=degrees
 71 |         then it should be backwards compatible but you'll get a deprecation warning on startup.
 72 |       </recommendation>
 73 |       <reindexing>Required</reindexing>
 74 |       <transform>no</transform>
 75 |     </warning>
 76 |   </xsl:if>
 77 | 
 78 |   <xsl:apply-templates select="child::node()"/>
 79 | </xsl:template>
 80 | 
 81 | <xsl:template match="filter">
 82 |   <xsl:if test="@class='solr.BeiderMorseFilterFactory' and //field/@type=../../@name">
 83 |     <incompatibility>
 84 |       <level>info</level>
 85 |       <jira_number>LUCENE-6058</jira_number>
 86 |       <description>Users of the BeiderMorseFilterFactory will need to rebuild their indexes after upgrading</description>
 87 |       <recommendation>
 88 |         Due to changes in the underlying commons-codec package, users of the BeiderMorseFilterFactory will need to rebuild their indexes after upgrading.
 89 |       </recommendation>
 90 |       <reindexing>Required</reindexing>
 91 |       <transform>no</transform>
 92 |     </incompatibility>
 93 |   </xsl:if>
 94 | 
 95 |   <xsl:if test="@class='solr.LegacyHTMLStripCharFilter'">
 96 |     <incompatibility>
 97 |       <level>error</level>
 98 |       <jira_number>TODO</jira_number>
 99 |       <description>LegacyHTMLStripCharFilter has been removed</description>
100 |       <recommendation>TBD</recommendation>
101 |       <reindexing>Required</reindexing>
102 |       <transform>no</transform>
103 |     </incompatibility>
104 |   </xsl:if>
105 | 
106 |   <xsl:apply-templates select="child::node()"/>
107 | </xsl:template>
108 | 
109 | </xsl:stylesheet>
110 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # Solr config upgrade tool
 2 | 
 3 | Despite widespread enterprise adoption, Solr lacks automated upgrade tooling. It has long been a challenge for users to understand the implications of a Solr upgrade. Users must manually review the Solr release notes to identify configuration changes either to fix backwards incompatibilities or to utilize latest features in the new version. Additionally, users must identify a way to migrate existing index data to the new version (either via an index upgrade or re-indexing the raw data).
 4 | 
 5 | Solr config upgrade tool aims to simplify the upgrade process by providing upgrade instructions tailored to your configuration. These instuctions can help you to answer following questions
 6 | 
 7 | - Does my Solr configuration have any backwards incompatible sections? If yes which ones?
 8 | - For each of the incompatibility - what do I need to do to fix this incompatibility? Where can I get more information about why this incompatibility was introduced (e.g. references to Lucene/Solr jiras)?
 9 | - Are there any changes in Lucene/Solr which would require me to do a full reindexing OR can I get away with an index upgrade?
10 | 
11 |  ## High level design
12 | 
13 | This tool is built using [Extensible Stylesheet Language Transformations](https://en.wikipedia.org/wiki/XSLT) engine. The upgrade rules, implemented in the form of XSLT transformations, can identify backwards incompatibilities and in some cases can even fix them automatically.
14 | 
15 |  In general, an incompatibility can be categorized as follows,
16 |  - An incompatibility due to removal of Lucene/Solr configuration element (e.g. a field type) is marked as ERROR in the validation result. Typically this will result in failure to start the Solr server (or load the core). User must make changes to Solr configuration using application specific knowledge to fix such incompatibility.
17 |  - An incompatibility due to deprecation of a configuration section in the new Solr version is marked as WARNING in the validation result. Typically this will not result in any failure during Solr server startup (or core loading), but may prevent application from utilizing new Lucene/Solr features (or bug-fixes). User may choose to make changes to Solr configuration using application specific knowledge to fix such incompatibility.
18 |  - An incompatibility which can be fixed automatically (e.g. by rewriting the Solr configuration section) and do not require any manual intervention is marked as INFO in the validation result. This also includes incompatibilities in the underlying Lucene implementation (e.g. [LUCENE-6058](https://issues.apache.org/jira/browse/LUCENE-6058)) which would require rebuilding the index (instead of index upgrade). Typically such incompatibility will not result in failure during Solr server startup (or core loading), but may affect the accuracy of the query results or consistency of underlying indexed data.
19 | 
20 | ## Steps to run this tool
21 | 
22 | - Build this project using maven (mvn clean install)
23 | - Run the config upgrade tool as follows
24 | ```bash
25 | ./bin/config_upgrade.sh --help
26 | usage: ConfigUpgradeTool
27 |  -t <arg>       This parameter specifies the type of Solr configuration to
28 |                 be validated and transformed.The tool currently supports
29 |                 schema.xml, solrconfig.xml and solr.xml
30 |     --help      This command will print the help message for the Solr
31 |                 config upgrade related commands.
32 |     --dry-run   This command will perform compatibility checks for the
33 |                 specified Solr config file.
34 |  -c <arg>       This parameter specifies the path of Solr configuration to
35 |                 be upgraded.
36 |  -u <arg>       This parameter specifies the path of the file providing
37 |                 Solr upgrade processor configurations.
38 |  -d <arg>       This parameter specifies the directory path where
39 |                 tansformed Solr configuration should be stored.
40 |  -v             This parameter enables printing XSLT compiler warnings on
41 |                 the command output.
42 | ```
43 | 
44 | e.g. following command runs the upgrade tool on a Solr schema.xml of version 4.x to identify incomatibilities before upgrade to Solr 5
45 | 
46 | ```bash
47 | ./bin/config_upgrade.sh -t schema -c src/test/resources/bad_config/solr4/schema.xml -u validators/solr_4_to_5_processors.xml -d /tmp
48 | Validating schema...
49 | 
50 | Following configuration errors found:
51 | 
52 |       * Legacy field type (name = pint and class = solr.IntField) is removed.
53 |       * Legacy field type (name = plong and class = solr.LongField) is removed.
54 |       * Legacy field type (name = pfloat and class = solr.FloatField) is removed.
55 |       * Legacy field type (name = pdouble and class = solr.DoubleField) is removed.
56 |       * Legacy field type (name = pdate and class = solr.DateField) is removed.
57 |       * Legacy field type (name = sint and class = solr.SortableIntField) is removed.
58 | 
59 | No configuration warnings found...
60 | 
61 | Please note that in Solr 5:
62 |     * Users of the BeiderMorseFilterFactory will need to rebuild their indexes after upgrading
63 | 
64 | Solr schema validation failed. Please review /tmp/schema_validation.xml for more details.
65 | ```
66 | 
67 | ## TODO
68 | - Add logic to handle the Solr config set (which includes overlay configurations) as well as solr.xml
69 | - Add upgrade rules to identify plugin deprecations (and removals)
70 | - Add rules for Solr 6 -> Solr 7 upgrade
71 | 
72 | 


--------------------------------------------------------------------------------
/src/main/java/org/apache/solr/config/upgrade/ConfigUpgradeTool.java:
--------------------------------------------------------------------------------
  1 | /*
  2 |  * Licensed to the Apache Software Foundation (ASF) under one or more
  3 |  * contributor license agreements.  See the NOTICE file distributed with
  4 |  * this work for additional information regarding copyright ownership.
  5 |  * The ASF licenses this file to You under the Apache License, Version 2.0
  6 |  * (the "License"); you may not use this file except in compliance with
  7 |  * the License.  You may obtain a copy of the License at
  8 |  *
  9 |  *     http://www.apache.org/licenses/LICENSE-2.0
 10 |  *
 11 |  * Unless required by applicable law or agreed to in writing, software
 12 |  * distributed under the License is distributed on an "AS IS" BASIS,
 13 |  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 14 |  * See the License for the specific language governing permissions and
 15 |  * limitations under the License.
 16 |  */
 17 | package org.apache.solr.config.upgrade;
 18 | 
 19 | import java.nio.file.Path;
 20 | import java.nio.file.Paths;
 21 | import java.util.Arrays;
 22 | import java.util.Comparator;
 23 | import java.util.List;
 24 | import java.util.Optional;
 25 | 
 26 | import javax.xml.transform.Source;
 27 | import javax.xml.transform.stream.StreamSource;
 28 | 
 29 | import org.apache.commons.cli.CommandLine;
 30 | import org.apache.commons.cli.CommandLineParser;
 31 | import org.apache.commons.cli.HelpFormatter;
 32 | import org.apache.commons.cli.Option;
 33 | import org.apache.commons.cli.Options;
 34 | import org.apache.commons.cli.ParseException;
 35 | import org.apache.commons.cli.PosixParser;
 36 | import org.apache.solr.config.upgrade.UpgradeProcessorsConfig.ProcessorConfig;
 37 | import org.apache.solr.config.upgrade.impl.DefaultValidationResultProcessor;
 38 | 
 39 | /**
 40 |  * A configuration compatibility checker tool for Solr. This tool is capable of detecting (and fixing)
 41 |  * compatibility errors in the Solr configuration files (specifically schema.xml, solrconfig.xml and
 42 |  * solr.xml).
 43 |  */
 44 | public class ConfigUpgradeTool {
 45 |   private static final String HELP_CMD = "help";
 46 |   private static final String DRY_RUN = "dry-run";
 47 |   private static final String SOLR_CONF_PATH = "c";
 48 |   private static final String UPGRADE_PROCESSORS_CONF_FILE = "u";
 49 |   public static final String SOLR_CONFIG_TYPE = "t";
 50 |   public static final String RESULT_DIR_PATH = "d";
 51 |   public static final String VERBOSE_OUTPUT = "v";
 52 | 
 53 |   private static final List<String> OPTION_HELP_ORDER = Arrays.asList(HELP_CMD, DRY_RUN,
 54 |       SOLR_CONF_PATH, UPGRADE_PROCESSORS_CONF_FILE, RESULT_DIR_PATH, VERBOSE_OUTPUT);
 55 | 
 56 |   public static void main(String[] args) {
 57 |     CommandLineParser parser = new PosixParser();
 58 |     Options options = new Options();
 59 | 
 60 |     options.addOption(null, DRY_RUN, false, "This command will perform compatibility checks for the specified Solr config file.");
 61 |     options.addOption(null, HELP_CMD, false, "This command will print the help message for the Solr config upgrade related commands.");
 62 |     options.addOption(UPGRADE_PROCESSORS_CONF_FILE, true, "This parameter specifies the path of the file providing Solr upgrade processor configurations.");
 63 |     options.addOption(SOLR_CONF_PATH, true, "This parameter specifies the path of Solr configuration to be upgraded.");
 64 |     options.addOption(SOLR_CONFIG_TYPE, true, "This parameter specifies the type of Solr configuration to be validated and transformed."
 65 |         + "The tool currently supports schema.xml, solrconfig.xml and solr.xml");
 66 |     options.addOption(RESULT_DIR_PATH, true,
 67 |         "This parameter specifies the directory path where tansformed Solr configuration should be stored.");
 68 |     options.addOption(VERBOSE_OUTPUT, false, "This parameter enables printing XSLT compiler warnings on the command output.");
 69 | 
 70 |     CommandLine cmd = null;
 71 |     try {
 72 |       cmd = parser.parse(options, args);
 73 |       if (cmd.hasOption(HELP_CMD)) {
 74 |         printHelp(options);
 75 |       } else {
 76 |         boolean dryRun = cmd.hasOption(DRY_RUN);
 77 |         Path processorConfPath = Paths.get(requiredArg(options, cmd, UPGRADE_PROCESSORS_CONF_FILE));
 78 |         ConfigType confType = ConfigType.getConfigType(requiredArg(options, cmd, SOLR_CONFIG_TYPE).toLowerCase());
 79 |         Path solrConfPath = Paths.get(requiredArg(options, cmd, SOLR_CONF_PATH));
 80 |         Path resultDirPath = Paths.get(requiredArg(options, cmd, RESULT_DIR_PATH));
 81 |         boolean verbose = cmd.hasOption(VERBOSE_OUTPUT);
 82 | 
 83 |         ToolParams params = new ToolParams(confType, solrConfPath, processorConfPath, resultDirPath, dryRun, verbose);
 84 |         System.exit((new ConfigUpgradeTool()).runTool(params));
 85 |       }
 86 |     } catch (ParseException e) {
 87 |       System.out.println(e.getLocalizedMessage());
 88 |       printHelp(options);
 89 |       System.exit(1);
 90 |     } catch (Exception e) {
 91 |       System.out.println(e.getLocalizedMessage());
 92 |       System.exit(1);
 93 |     }
 94 |   }
 95 | 
 96 |   /**
 97 |    * Invoke the compatibility checker
 98 |    *
 99 |    * @throws Exception in case of errors
100 |    */
101 |   public int runTool(ToolParams params) throws Exception {
102 |     params.checkArgs();
103 | 
104 |     boolean result = true;
105 |     ValidationHandler handler = new DefaultValidationResultProcessor(params);
106 |     Optional<ConfigValidator> validator = getConfigValidator(params);
107 |     if (validator.isPresent()) {
108 |       result = validator.get().validate(getConfigSource(params), handler);
109 |       // Note we expect the transformation rules to be present in the validation script
110 |       // at an info level. When validation script is not present, there is no need for
111 |       // transformation as well.
112 |       if (result && !params.isDryRun()) {
113 |         Optional<ConfigTransformer> transformer = getConfigTransformer(params);
114 |         if (transformer.isPresent()) {
115 |           transformer.get().transform(getConfigSource(params));
116 |         }
117 |       }
118 |     } else {
119 |       System.out.println("No validation rules found for config type : " + params.getConfType()
120 |       + " in processor configuration " + params.getProcessorConfPath() );
121 |     }
122 | 
123 |     return result ? 0 : 1;
124 |   }
125 | 
126 |   private Source getConfigSource(ToolParams params) {
127 |     ConfigType confType = params.getConfType();
128 |     switch (confType) {
129 |       case SCHEMA_XML:
130 |       case SOLRCONFIG_XML: {
131 |         return new StreamSource(params.getSolrConfPath().toFile());
132 |       }
133 | 
134 |       case CONFIGSET: {
135 |         throw new UnsupportedOperationException();
136 |       }
137 |       default: {
138 |         throw new UnsupportedOperationException();
139 |       }
140 |     }
141 |   }
142 | 
143 |   private Optional<ConfigValidator> getConfigValidator(ToolParams params) {
144 |     ConfigType confType = params.getConfType();
145 |     UpgradeProcessorsConfig conf = params.getUpgradeProcessorConf();
146 | 
147 |     switch (confType) {
148 |       case SCHEMA_XML:
149 |       case SOLRCONFIG_XML: {
150 |         Optional<ProcessorConfig> procConf = conf.getProcessorByConfigType(confType);
151 |         if (procConf.isPresent() && (procConf.get().getValidatorPath() != null)) {
152 |           return Optional.of(new ConfigValidator(params, confType.getConfigType(), procConf.get()));
153 |         }
154 |         break;
155 |       }
156 | 
157 |       case CONFIGSET: {
158 |         throw new UnsupportedOperationException();
159 |       }
160 |     }
161 | 
162 |     return Optional.empty();
163 |   }
164 | 
165 |   private Optional<ConfigTransformer> getConfigTransformer(ToolParams params) {
166 |     ConfigType confType = params.getConfType();
167 |     UpgradeProcessorsConfig conf = params.getUpgradeProcessorConf();
168 | 
169 |     switch (confType) {
170 |       case SCHEMA_XML:
171 |       case SOLRCONFIG_XML: {
172 |         Optional<ProcessorConfig> procConf = conf.getProcessorByConfigType(confType);
173 |         if (procConf.isPresent()) {
174 |           return Optional.of(new ConfigTransformer(params, procConf.get()));
175 |         }
176 |         break;
177 |       }
178 | 
179 |       case CONFIGSET: {
180 |         throw new UnsupportedOperationException();
181 |       }
182 |     }
183 | 
184 |     return Optional.empty();
185 |   }
186 | 
187 |   private static String requiredArg(Options options, CommandLine cmd, String optVal) {
188 |     if (!cmd.hasOption(optVal)) {
189 |       System.out.println("Please specify the value for option " + optVal);
190 |       printHelp(options);
191 |       System.exit(1);
192 |     }
193 |     return cmd.getOptionValue(optVal);
194 |   }
195 | 
196 |   @SuppressWarnings({"rawtypes", "unchecked"})
197 |   private static void printHelp(Options options) {
198 |     StringBuilder helpFooter = new StringBuilder();
199 |     helpFooter.append("Examples: \n");
200 |     helpFooter.append("config_upgrade.sh -c schema.xml -t schema -u solr_4_to_5_processors.xml -d /tmp/result-dir \n");
201 |     helpFooter.append("config_upgrade.sh --dry-run -c schema.xml -t schema -u solr_4_to_5_processors.xml -d /tmp/result-dir \n");
202 | 
203 |     HelpFormatter formatter = new HelpFormatter();
204 |     formatter.setOptionComparator(new OptionComarator());
205 |     formatter.printHelp("ConfigUpgradeTool", null, options, helpFooter.toString(), false);
206 |   }
207 | 
208 |   private static class OptionComarator<T extends Option> implements Comparator<T> {
209 |     public int compare(T o1, T o2) {
210 |       String s1 = o1.hasLongOpt() ? o1.getLongOpt() : o1.getOpt();
211 |       String s2 = o2.hasLongOpt() ? o2.getLongOpt() : o2.getOpt();
212 |         return OPTION_HELP_ORDER.indexOf(s1) - OPTION_HELP_ORDER.indexOf(s2);
213 |     }
214 |   }
215 | }
216 | 


--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
  1 |                                  Apache License
  2 |                            Version 2.0, January 2004
  3 |                         http://www.apache.org/licenses/
  4 | 
  5 |    TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
  6 | 
  7 |    1. Definitions.
  8 | 
  9 |       "License" shall mean the terms and conditions for use, reproduction,
 10 |       and distribution as defined by Sections 1 through 9 of this document.
 11 | 
 12 |       "Licensor" shall mean the copyright owner or entity authorized by
 13 |       the copyright owner that is granting the License.
 14 | 
 15 |       "Legal Entity" shall mean the union of the acting entity and all
 16 |       other entities that control, are controlled by, or are under common
 17 |       control with that entity. For the purposes of this definition,
 18 |       "control" means (i) the power, direct or indirect, to cause the
 19 |       direction or management of such entity, whether by contract or
 20 |       otherwise, or (ii) ownership of fifty percent (50%) or more of the
 21 |       outstanding shares, or (iii) beneficial ownership of such entity.
 22 | 
 23 |       "You" (or "Your") shall mean an individual or Legal Entity
 24 |       exercising permissions granted by this License.
 25 | 
 26 |       "Source" form shall mean the preferred form for making modifications,
 27 |       including but not limited to software source code, documentation
 28 |       source, and configuration files.
 29 | 
 30 |       "Object" form shall mean any form resulting from mechanical
 31 |       transformation or translation of a Source form, including but
 32 |       not limited to compiled object code, generated documentation,
 33 |       and conversions to other media types.
 34 | 
 35 |       "Work" shall mean the work of authorship, whether in Source or
 36 |       Object form, made available under the License, as indicated by a
 37 |       copyright notice that is included in or attached to the work
 38 |       (an example is provided in the Appendix below).
 39 | 
 40 |       "Derivative Works" shall mean any work, whether in Source or Object
 41 |       form, that is based on (or derived from) the Work and for which the
 42 |       editorial revisions, annotations, elaborations, or other modifications
 43 |       represent, as a whole, an original work of authorship. For the purposes
 44 |       of this License, Derivative Works shall not include works that remain
 45 |       separable from, or merely link (or bind by name) to the interfaces of,
 46 |       the Work and Derivative Works thereof.
 47 | 
 48 |       "Contribution" shall mean any work of authorship, including
 49 |       the original version of the Work and any modifications or additions
 50 |       to that Work or Derivative Works thereof, that is intentionally
 51 |       submitted to Licensor for inclusion in the Work by the copyright owner
 52 |       or by an individual or Legal Entity authorized to submit on behalf of
 53 |       the copyright owner. For the purposes of this definition, "submitted"
 54 |       means any form of electronic, verbal, or written communication sent
 55 |       to the Licensor or its representatives, including but not limited to
 56 |       communication on electronic mailing lists, source code control systems,
 57 |       and issue tracking systems that are managed by, or on behalf of, the
 58 |       Licensor for the purpose of discussing and improving the Work, but
 59 |       excluding communication that is conspicuously marked or otherwise
 60 |       designated in writing by the copyright owner as "Not a Contribution."
 61 | 
 62 |       "Contributor" shall mean Licensor and any individual or Legal Entity
 63 |       on behalf of whom a Contribution has been received by Licensor and
 64 |       subsequently incorporated within the Work.
 65 | 
 66 |    2. Grant of Copyright License. Subject to the terms and conditions of
 67 |       this License, each Contributor hereby grants to You a perpetual,
 68 |       worldwide, non-exclusive, no-charge, royalty-free, irrevocable
 69 |       copyright license to reproduce, prepare Derivative Works of,
 70 |       publicly display, publicly perform, sublicense, and distribute the
 71 |       Work and such Derivative Works in Source or Object form.
 72 | 
 73 |    3. Grant of Patent License. Subject to the terms and conditions of
 74 |       this License, each Contributor hereby grants to You a perpetual,
 75 |       worldwide, non-exclusive, no-charge, royalty-free, irrevocable
 76 |       (except as stated in this section) patent license to make, have made,
 77 |       use, offer to sell, sell, import, and otherwise transfer the Work,
 78 |       where such license applies only to those patent claims licensable
 79 |       by such Contributor that are necessarily infringed by their
 80 |       Contribution(s) alone or by combination of their Contribution(s)
 81 |       with the Work to which such Contribution(s) was submitted. If You
 82 |       institute patent litigation against any entity (including a
 83 |       cross-claim or counterclaim in a lawsuit) alleging that the Work
 84 |       or a Contribution incorporated within the Work constitutes direct
 85 |       or contributory patent infringement, then any patent licenses
 86 |       granted to You under this License for that Work shall terminate
 87 |       as of the date such litigation is filed.
 88 | 
 89 |    4. Redistribution. You may reproduce and distribute copies of the
 90 |       Work or Derivative Works thereof in any medium, with or without
 91 |       modifications, and in Source or Object form, provided that You
 92 |       meet the following conditions:
 93 | 
 94 |       (a) You must give any other recipients of the Work or
 95 |           Derivative Works a copy of this License; and
 96 | 
 97 |       (b) You must cause any modified files to carry prominent notices
 98 |           stating that You changed the files; and
 99 | 
100 |       (c) You must retain, in the Source form of any Derivative Works
101 |           that You distribute, all copyright, patent, trademark, and
102 |           attribution notices from the Source form of the Work,
103 |           excluding those notices that do not pertain to any part of
104 |           the Derivative Works; and
105 | 
106 |       (d) If the Work includes a "NOTICE" text file as part of its
107 |           distribution, then any Derivative Works that You distribute must
108 |           include a readable copy of the attribution notices contained
109 |           within such NOTICE file, excluding those notices that do not
110 |           pertain to any part of the Derivative Works, in at least one
111 |           of the following places: within a NOTICE text file distributed
112 |           as part of the Derivative Works; within the Source form or
113 |           documentation, if provided along with the Derivative Works; or,
114 |           within a display generated by the Derivative Works, if and
115 |           wherever such third-party notices normally appear. The contents
116 |           of the NOTICE file are for informational purposes only and
117 |           do not modify the License. You may add Your own attribution
118 |           notices within Derivative Works that You distribute, alongside
119 |           or as an addendum to the NOTICE text from the Work, provided
120 |           that such additional attribution notices cannot be construed
121 |           as modifying the License.
122 | 
123 |       You may add Your own copyright statement to Your modifications and
124 |       may provide additional or different license terms and conditions
125 |       for use, reproduction, or distribution of Your modifications, or
126 |       for any such Derivative Works as a whole, provided Your use,
127 |       reproduction, and distribution of the Work otherwise complies with
128 |       the conditions stated in this License.
129 | 
130 |    5. Submission of Contributions. Unless You explicitly state otherwise,
131 |       any Contribution intentionally submitted for inclusion in the Work
132 |       by You to the Licensor shall be under the terms and conditions of
133 |       this License, without any additional terms or conditions.
134 |       Notwithstanding the above, nothing herein shall supersede or modify
135 |       the terms of any separate license agreement you may have executed
136 |       with Licensor regarding such Contributions.
137 | 
138 |    6. Trademarks. This License does not grant permission to use the trade
139 |       names, trademarks, service marks, or product names of the Licensor,
140 |       except as required for reasonable and customary use in describing the
141 |       origin of the Work and reproducing the content of the NOTICE file.
142 | 
143 |    7. Disclaimer of Warranty. Unless required by applicable law or
144 |       agreed to in writing, Licensor provides the Work (and each
145 |       Contributor provides its Contributions) on an "AS IS" BASIS,
146 |       WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147 |       implied, including, without limitation, any warranties or conditions
148 |       of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149 |       PARTICULAR PURPOSE. You are solely responsible for determining the
150 |       appropriateness of using or redistributing the Work and assume any
151 |       risks associated with Your exercise of permissions under this License.
152 | 
153 |    8. Limitation of Liability. In no event and under no legal theory,
154 |       whether in tort (including negligence), contract, or otherwise,
155 |       unless required by applicable law (such as deliberate and grossly
156 |       negligent acts) or agreed to in writing, shall any Contributor be
157 |       liable to You for damages, including any direct, indirect, special,
158 |       incidental, or consequential damages of any character arising as a
159 |       result of this License or out of the use or inability to use the
160 |       Work (including but not limited to damages for loss of goodwill,
161 |       work stoppage, computer failure or malfunction, or any and all
162 |       other commercial damages or losses), even if such Contributor
163 |       has been advised of the possibility of such damages.
164 | 
165 |    9. Accepting Warranty or Additional Liability. While redistributing
166 |       the Work or Derivative Works thereof, You may choose to offer,
167 |       and charge a fee for, acceptance of support, warranty, indemnity,
168 |       or other liability obligations and/or rights consistent with this
169 |       License. However, in accepting such obligations, You may act only
170 |       on Your own behalf and on Your sole responsibility, not on behalf
171 |       of any other Contributor, and only if You agree to indemnify,
172 |       defend, and hold each Contributor harmless for any liability
173 |       incurred by, or claims asserted against, such Contributor by reason
174 |       of your accepting any such warranty or additional liability.
175 | 
176 |    END OF TERMS AND CONDITIONS
177 | 
178 |    APPENDIX: How to apply the Apache License to your work.
179 | 
180 |       To apply the Apache License to your work, attach the following
181 |       boilerplate notice, with the fields enclosed by brackets "{}"
182 |       replaced with your own identifying information. (Don't include
183 |       the brackets!)  The text should be enclosed in the appropriate
184 |       comment syntax for the file format. We also recommend that a
185 |       file or class name and description of purpose be included on the
186 |       same "printed page" as the copyright notice for easier
187 |       identification within third-party archives.
188 | 
189 |    Copyright {yyyy} {name of copyright owner}
190 | 
191 |    Licensed under the Apache License, Version 2.0 (the "License");
192 |    you may not use this file except in compliance with the License.
193 |    You may obtain a copy of the License at
194 | 
195 |        http://www.apache.org/licenses/LICENSE-2.0
196 | 
197 |    Unless required by applicable law or agreed to in writing, software
198 |    distributed under the License is distributed on an "AS IS" BASIS,
199 |    WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
200 |    See the License for the specific language governing permissions and
201 |    limitations under the License.
202 | 


--------------------------------------------------------------------------------
/src/test/resources/bad_config/solr5/schema_2.xml:
--------------------------------------------------------------------------------
  1 | <?xml version="1.0" encoding="UTF-8" ?>
  2 | <!--
  3 |  Licensed to the Apache Software Foundation (ASF) under one or more
  4 |  contributor license agreements.  See the NOTICE file distributed with
  5 |  this work for additional information regarding copyright ownership.
  6 |  The ASF licenses this file to You under the Apache License, Version 2.0
  7 |  (the "License"); you may not use this file except in compliance with
  8 |  the License.  You may obtain a copy of the License at
  9 | 
 10 |      http://www.apache.org/licenses/LICENSE-2.0
 11 | 
 12 |  Unless required by applicable law or agreed to in writing, software
 13 |  distributed under the License is distributed on an "AS IS" BASIS,
 14 |  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 15 |  See the License for the specific language governing permissions and
 16 |  limitations under the License.
 17 | -->
 18 | 
 19 | <!--  
 20 |  This is the Solr schema file. This file should be named "schema.xml" and
 21 |  should be in the conf directory under the solr home
 22 |  (i.e. ./solr/conf/schema.xml by default) 
 23 |  or located where the classloader for the Solr webapp can find it.
 24 | 
 25 |  This example schema is the recommended starting point for users.
 26 |  It should be kept correct and concise, usable out-of-the-box.
 27 | 
 28 |  For more information, on how to customize this file, please see
 29 |  http://wiki.apache.org/solr/SchemaXml
 30 | -->
 31 | 
 32 | <schema name="example" version="1.5">
 33 |   <!-- attribute "name" is the name of this schema and is only used for display purposes.
 34 |        version="x.y" is Solr's version number for the schema syntax and 
 35 |        semantics.  It should not normally be changed by applications.
 36 | 
 37 |        1.0: multiValued attribute did not exist, all fields are multiValued 
 38 |             by nature
 39 |        1.1: multiValued attribute introduced, false by default 
 40 |        1.2: omitTermFreqAndPositions attribute introduced, true by default 
 41 |             except for text fields.
 42 |        1.3: removed optional field compress feature
 43 |        1.4: autoGeneratePhraseQueries attribute introduced to drive QueryParser
 44 |             behavior when a single string produces multiple tokens.  Defaults 
 45 |             to off for version >= 1.4
 46 |        1.5: omitNorms defaults to true for primitive field types 
 47 |             (int, float, boolean, string...)
 48 |      -->
 49 | 
 50 | 
 51 |    <!-- Valid attributes for fields:
 52 |      name: mandatory - the name for the field
 53 |      type: mandatory - the name of a field type from the 
 54 |        <types> fieldType section
 55 |      indexed: true if this field should be indexed (searchable or sortable)
 56 |      stored: true if this field should be retrievable
 57 |      docValues: true if this field should have doc values. Doc values are
 58 |        useful for faceting, grouping, sorting and function queries. Although not
 59 |        required, doc values will make the index faster to load, more
 60 |        NRT-friendly and more memory-efficient. They however come with some
 61 |        limitations: they are currently only supported by StrField, UUIDField
 62 |        and all Trie*Fields, and depending on the field type, they might
 63 |        require the field to be single-valued, be required or have a default
 64 |        value (check the documentation of the field type you're interested in
 65 |        for more information)
 66 |      multiValued: true if this field may contain multiple values per document
 67 |      omitNorms: (expert) set to true to omit the norms associated with
 68 |        this field (this disables length normalization and index-time
 69 |        boosting for the field, and saves some memory).  Only full-text
 70 |        fields or fields that need an index-time boost need norms.
 71 |        Norms are omitted for primitive (non-analyzed) types by default.
 72 |      termVectors: [false] set to true to store the term vector for a
 73 |        given field.
 74 |        When using MoreLikeThis, fields used for similarity should be
 75 |        stored for best performance.
 76 |      termPositions: Store position information with the term vector.  
 77 |        This will increase storage costs.
 78 |      termOffsets: Store offset information with the term vector. This 
 79 |        will increase storage costs.
 80 |      required: The field is required.  It will throw an error if the
 81 |        value does not exist
 82 |      default: a value that should be used if no value is specified
 83 |        when adding a document.
 84 |    -->
 85 | 
 86 |    <!-- field names should consist of alphanumeric or underscore characters only and
 87 |       not start with a digit.  This is not currently strictly enforced,
 88 |       but other field names will not have first class support from all components
 89 |       and back compatibility is not guaranteed.  Names with both leading and
 90 |       trailing underscores (e.g. _version_) are reserved.
 91 |    -->
 92 | 
 93 |    <!-- If you remove this field, you must _also_ disable the update log in solrconfig.xml
 94 |       or Solr won't start. _version_ and update log are required for SolrCloud
 95 |    --> 
 96 |    <field name="_version_" type="long" indexed="true" stored="true"/>
 97 |    
 98 |    <!-- points to the root document of a block of nested documents. Required for nested
 99 |       document support, may be removed otherwise
100 |    -->
101 |    <field name="_root_" type="string" indexed="true" stored="false"/>
102 | 
103 |    <!-- Only remove the "id" field if you have a very good reason to. While not strictly
104 |      required, it is highly recommended. A <uniqueKey> is present in almost all Solr 
105 |      installations. See the <uniqueKey> declaration below where <uniqueKey> is set to "id".
106 |    -->   
107 |    <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" /> 
108 | 
109 |    <!-- Dynamic field definitions allow using convention over configuration
110 |        for fields via the specification of patterns to match field names. 
111 |        EXAMPLE:  name="*_i" will match any field ending in _i (like myid_i, z_i)
112 |        RESTRICTION: the glob-like pattern in the name attribute must have
113 |        a "*" only at the start or the end.  -->
114 |    
115 |    <dynamicField name="*_i"  type="int"    indexed="true"  stored="true"/>
116 |    <dynamicField name="*_is" type="int"    indexed="true"  stored="true"  multiValued="true"/>
117 |    <dynamicField name="*_s"  type="string"  indexed="true"  stored="true" />
118 |    <dynamicField name="*_ss" type="string"  indexed="true"  stored="true" multiValued="true"/>
119 |    <dynamicField name="*_l"  type="long"   indexed="true"  stored="true"/>
120 |    <dynamicField name="*_ls" type="long"   indexed="true"  stored="true"  multiValued="true"/>
121 |    <dynamicField name="*_t"  type="text_general"    indexed="true"  stored="true"/>
122 |    <dynamicField name="*_txt" type="text_general"   indexed="true"  stored="true" multiValued="true"/>
123 |    <dynamicField name="*_en"  type="text_en"    indexed="true"  stored="true" multiValued="true"/>
124 |    <dynamicField name="*_b"  type="boolean" indexed="true" stored="true"/>
125 |    <dynamicField name="*_bs" type="boolean" indexed="true" stored="true"  multiValued="true"/>
126 |    <dynamicField name="*_f"  type="float"  indexed="true"  stored="true"/>
127 |    <dynamicField name="*_fs" type="float"  indexed="true"  stored="true"  multiValued="true"/>
128 |    <dynamicField name="*_d"  type="double" indexed="true"  stored="true"/>
129 |    <dynamicField name="*_ds" type="double" indexed="true"  stored="true"  multiValued="true"/>
130 | 
131 |    <!-- Type used to index the lat and lon components for the "location" FieldType -->
132 |    <dynamicField name="*_coordinate"  type="tdouble" indexed="true"  stored="false" />
133 | 
134 |    <dynamicField name="*_dt"  type="date"    indexed="true"  stored="true"/>
135 |    <dynamicField name="*_dts" type="date"    indexed="true"  stored="true" multiValued="true"/>
136 |    <dynamicField name="*_p"  type="location" indexed="true" stored="true"/>
137 | 
138 |    <!-- some trie-coded dynamic fields for faster range queries -->
139 |    <dynamicField name="*_ti" type="tint"    indexed="true"  stored="true"/>
140 |    <dynamicField name="*_tl" type="tlong"   indexed="true"  stored="true"/>
141 |    <dynamicField name="*_tf" type="tfloat"  indexed="true"  stored="true"/>
142 |    <dynamicField name="*_td" type="tdouble" indexed="true"  stored="true"/>
143 |    <dynamicField name="*_tdt" type="tdate"  indexed="true"  stored="true"/>
144 | 
145 |    <dynamicField name="*_c"   type="currency" indexed="true"  stored="true"/>
146 | 
147 |    <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
148 |    <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
149 | 
150 |    <dynamicField name="random_*" type="random" />
151 | 
152 |    <!-- uncomment the following to ignore any fields that don't already match an existing 
153 |         field name or dynamic field, rather than reporting them as an error. 
154 |         alternately, change the type="ignored" to some other type e.g. "text" if you want 
155 |         unknown fields indexed and/or stored by default --> 
156 |    <!--dynamicField name="*" type="ignored" multiValued="true" /-->
157 | 
158 |  <!-- Field to use to determine and enforce document uniqueness. 
159 |       Unless this field is marked with required="false", it will be a required field
160 |    -->
161 |  <uniqueKey>id</uniqueKey>
162 | 
163 |   <!-- copyField commands copy one field to another at the time a document
164 |         is added to the index.  It's used either to index the same field differently,
165 |         or to add multiple fields to the same field for easier/faster searching.  -->
166 | 
167 |   <!--
168 |    <copyField source="title" dest="text"/>
169 |    <copyField source="body" dest="text"/>
170 |   -->
171 |   
172 |     <!-- field type definitions. The "name" attribute is
173 |        just a label to be used by field definitions.  The "class"
174 |        attribute and any other attributes determine the real
175 |        behavior of the fieldType.
176 |          Class names starting with "solr" refer to java classes in a
177 |        standard package such as org.apache.solr.analysis
178 |     -->
179 | 
180 |     <!-- The StrField type is not analyzed, but indexed/stored verbatim.
181 |        It supports doc values but in that case the field needs to be
182 |        single-valued and either required or have a default value.
183 |       -->
184 |     <fieldType name="string" class="solr.StrField" sortMissingLast="true" />
185 | 
186 |     <!-- boolean type: "true" or "false" -->
187 |     <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
188 | 
189 |     <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
190 |          currently supported on types that are sorted internally as strings
191 |          and on numeric types.
192 | 	     This includes "string","boolean", and, as of 3.5 (and 4.x),
193 | 	     int, float, long, date, double, including the "Trie" variants.
194 |        - If sortMissingLast="true", then a sort on this field will cause documents
195 |          without the field to come after documents with the field,
196 |          regardless of the requested sort order (asc or desc).
197 |        - If sortMissingFirst="true", then a sort on this field will cause documents
198 |          without the field to come before documents with the field,
199 |          regardless of the requested sort order.
200 |        - If sortMissingLast="false" and sortMissingFirst="false" (the default),
201 |          then default lucene sorting will be used which places docs without the
202 |          field first in an ascending sort and last in a descending sort.
203 |     -->    
204 | 
205 |     <!--
206 |       Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
207 | 
208 |       These fields support doc values, but they require the field to be
209 |       single-valued and either be required or have a default value.
210 |     -->
211 |     <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
212 |     <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
213 |     <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
214 |     <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
215 | 
216 |     <!--
217 |      Numeric field types that index each value at various levels of precision
218 |      to accelerate range queries when the number of values between the range
219 |      endpoints is large. See the javadoc for NumericRangeQuery for internal
220 |      implementation details.
221 | 
222 |      Smaller precisionStep values (specified in bits) will lead to more tokens
223 |      indexed per value, slightly larger index size, and faster range queries.
224 |      A precisionStep of 0 disables indexing at different precision levels.
225 |     -->
226 |     <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
227 |     <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
228 |     <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
229 |     <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
230 | 
231 |     <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
232 |          is a more restricted form of the canonical representation of dateTime
233 |          http://www.w3.org/TR/xmlschema-2/#dateTime    
234 |          The trailing "Z" designates UTC time and is mandatory.
235 |          Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
236 |          All other components are mandatory.
237 | 
238 |          Expressions can also be used to denote calculations that should be
239 |          performed relative to "NOW" to determine the value, ie...
240 | 
241 |                NOW/HOUR
242 |                   ... Round to the start of the current hour
243 |                NOW-1DAY
244 |                   ... Exactly 1 day prior to now
245 |                NOW/DAY+6MONTHS+3DAYS
246 |                   ... 6 months and 3 days in the future from the start of
247 |                       the current day
248 |                       
249 |          Consult the TrieDateField javadocs for more information.
250 | 
251 |          Note: For faster range queries, consider the tdate type
252 |       -->
253 |     <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
254 | 
255 |     <!-- A Trie based date field for faster date range queries and date faceting. -->
256 |     <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
257 | 
258 | 
259 |     <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
260 |     <fieldType name="binary" class="solr.BinaryField"/>
261 | 
262 |     <!-- The "RandomSortField" is not used to store or search any
263 |          data.  You can declare fields of this type it in your schema
264 |          to generate pseudo-random orderings of your docs for sorting 
265 |          or function purposes.  The ordering is generated based on the field
266 |          name and the version of the index. As long as the index version
267 |          remains unchanged, and the same field name is reused,
268 |          the ordering of the docs will be consistent.  
269 |          If you want different psuedo-random orderings of documents,
270 |          for the same version of the index, use a dynamicField and
271 |          change the field name in the request.
272 |      -->
273 |     <fieldType name="random" class="solr.RandomSortField" indexed="true" />
274 | 
275 |     <!-- solr.TextField allows the specification of custom text analyzers
276 |          specified as a tokenizer and a list of token filters. Different
277 |          analyzers may be specified for indexing and querying.
278 | 
279 |          The optional positionIncrementGap puts space between multiple fields of
280 |          this type on the same document, with the purpose of preventing false phrase
281 |          matching across fields.
282 | 
283 |          For more info on customizing your analyzer chain, please see
284 |          http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
285 |      -->
286 | 
287 |     <!-- One can also specify an existing Analyzer class that has a
288 |          default constructor via the class attribute on the analyzer element.
289 |          Example:
290 |     <fieldType name="text_greek" class="solr.TextField">
291 |       <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
292 |     </fieldType>
293 |     -->
294 | 
295 |     <!-- A text field that only splits on whitespace for exact matching of words -->
296 |     <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
297 |       <analyzer>
298 |         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
299 |       </analyzer>
300 |     </fieldType>
301 | 
302 |     <!-- A general text field that has reasonable, generic
303 |          cross-language defaults: it tokenizes with StandardTokenizer,
304 | 	 removes stop words from case-insensitive "stopwords.txt"
305 | 	 (empty by default), and down cases.  At query time only, it
306 | 	 also applies synonyms. -->
307 |     <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
308 |       <analyzer type="index">
309 |         <tokenizer class="solr.StandardTokenizerFactory"/>
310 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
311 |         <!-- in this example, we will only use synonyms at query time
312 |         <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
313 |         -->
314 |         <filter class="solr.LowerCaseFilterFactory"/>
315 |       </analyzer>
316 |       <analyzer type="query">
317 |         <tokenizer class="solr.StandardTokenizerFactory"/>
318 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
319 |         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
320 |         <filter class="solr.LowerCaseFilterFactory"/>
321 |       </analyzer>
322 |     </fieldType>
323 | 
324 |     <!-- A text field with defaults appropriate for English: it
325 |          tokenizes with StandardTokenizer, removes English stop words
326 |          (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
327 |          finally applies Porter's stemming.  The query time analyzer
328 |          also applies synonyms from synonyms.txt. -->
329 |     <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
330 |       <analyzer type="index">
331 |         <tokenizer class="solr.StandardTokenizerFactory"/>
332 |         <!-- in this example, we will only use synonyms at query time
333 |         <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
334 |         -->
335 |         <!-- Case insensitive stop word removal.
336 |         -->
337 |         <filter class="solr.StopFilterFactory"
338 |                 ignoreCase="true"
339 |                 words="lang/stopwords_en.txt"
340 |                 />
341 |         <filter class="solr.LowerCaseFilterFactory"/>
342 | 	<filter class="solr.EnglishPossessiveFilterFactory"/>
343 |         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
344 | 	<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
345 |         <filter class="solr.EnglishMinimalStemFilterFactory"/>
346 | 	-->
347 |         <filter class="solr.PorterStemFilterFactory"/>
348 |       </analyzer>
349 |       <analyzer type="query">
350 |         <tokenizer class="solr.StandardTokenizerFactory"/>
351 |         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
352 |         <filter class="solr.StopFilterFactory"
353 |                 ignoreCase="true"
354 |                 words="lang/stopwords_en.txt"
355 |                 />
356 |         <filter class="solr.LowerCaseFilterFactory"/>
357 | 	<filter class="solr.EnglishPossessiveFilterFactory"/>
358 |         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
359 | 	<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
360 |         <filter class="solr.EnglishMinimalStemFilterFactory"/>
361 | 	-->
362 |         <filter class="solr.PorterStemFilterFactory"/>
363 |       </analyzer>
364 |     </fieldType>
365 | 
366 |     <!-- A text field with defaults appropriate for English, plus
367 | 	 aggressive word-splitting and autophrase features enabled.
368 | 	 This field is just like text_en, except it adds
369 | 	 WordDelimiterFilter to enable splitting and matching of
370 | 	 words on case-change, alpha numeric boundaries, and
371 | 	 non-alphanumeric chars.  This means certain compound word
372 | 	 cases will work, for example query "wi fi" will match
373 | 	 document "WiFi" or "wi-fi".
374 |         -->
375 |     <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
376 |       <analyzer type="index">
377 |         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
378 |         <!-- in this example, we will only use synonyms at query time
379 |         <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
380 |         -->
381 |         <!-- Case insensitive stop word removal.
382 |         -->
383 |         <filter class="solr.StopFilterFactory"
384 |                 ignoreCase="true"
385 |                 words="lang/stopwords_en.txt"
386 |                 />
387 |         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
388 |         <filter class="solr.LowerCaseFilterFactory"/>
389 |         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
390 |         <filter class="solr.PorterStemFilterFactory"/>
391 |       </analyzer>
392 |       <analyzer type="query">
393 |         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
394 |         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
395 |         <filter class="solr.StopFilterFactory"
396 |                 ignoreCase="true"
397 |                 words="lang/stopwords_en.txt"
398 |                 />
399 |         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
400 |         <filter class="solr.LowerCaseFilterFactory"/>
401 |         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
402 |         <filter class="solr.PorterStemFilterFactory"/>
403 |       </analyzer>
404 |     </fieldType>
405 | 
406 |     <!-- Less flexible matching, but less false matches.  Probably not ideal for product names,
407 |          but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
408 |     <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
409 |       <analyzer>
410 |         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
411 |         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
412 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
413 |         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
414 |         <filter class="solr.LowerCaseFilterFactory"/>
415 |         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
416 |         <filter class="solr.EnglishMinimalStemFilterFactory"/>
417 |         <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
418 |              possible with WordDelimiterFilter in conjuncton with stemming. -->
419 |         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
420 |       </analyzer>
421 |     </fieldType>
422 | 
423 |     <!-- Just like text_general except it reverses the characters of
424 | 	 each token, to enable more efficient leading wildcard queries. -->
425 |     <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
426 |       <analyzer type="index">
427 |         <tokenizer class="solr.StandardTokenizerFactory"/>
428 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
429 |         <filter class="solr.LowerCaseFilterFactory"/>
430 |         <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
431 |            maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
432 |       </analyzer>
433 |       <analyzer type="query">
434 |         <tokenizer class="solr.StandardTokenizerFactory"/>
435 |         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
436 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
437 |         <filter class="solr.LowerCaseFilterFactory"/>
438 |       </analyzer>
439 |     </fieldType>
440 | 
441 |     <!-- This is an example of using the KeywordTokenizer along
442 |          With various TokenFilterFactories to produce a sortable field
443 |          that does not include some properties of the source text
444 |       -->
445 |     <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
446 |       <analyzer>
447 |         <!-- KeywordTokenizer does no actual tokenizing, so the entire
448 |              input string is preserved as a single token
449 |           -->
450 |         <tokenizer class="solr.KeywordTokenizerFactory"/>
451 |         <!-- The LowerCase TokenFilter does what you expect, which can be
452 |              when you want your sorting to be case insensitive
453 |           -->
454 |         <filter class="solr.LowerCaseFilterFactory" />
455 |         <!-- The TrimFilter removes any leading or trailing whitespace -->
456 |         <filter class="solr.TrimFilterFactory" />
457 |         <!-- The PatternReplaceFilter gives you the flexibility to use
458 |              Java Regular expression to replace any sequence of characters
459 |              matching a pattern with an arbitrary replacement string, 
460 |              which may include back references to portions of the original
461 |              string matched by the pattern.
462 |              
463 |              See the Java Regular Expression documentation for more
464 |              information on pattern and replacement string syntax.
465 |              
466 |              http://docs.oracle.com/javase/7/docs/api/java/util/regex/package-summary.html
467 |           -->
468 |         <filter class="solr.PatternReplaceFilterFactory"
469 |                 pattern="([^a-z])" replacement="" replace="all"
470 |         />
471 |       </analyzer>
472 |     </fieldType>
473 | 
474 |     <!-- lowercases the entire field value, keeping it as a single token.  -->
475 |     <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
476 |       <analyzer>
477 |         <tokenizer class="solr.KeywordTokenizerFactory"/>
478 |         <filter class="solr.LowerCaseFilterFactory" />
479 |       </analyzer>
480 |     </fieldType>
481 | 
482 |     <!-- since fields of this type are by default not stored or indexed,
483 |          any data added to them will be ignored outright.  --> 
484 |     <fieldType name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
485 | 
486 |     <!-- This point type indexes the coordinates as separate fields (subFields)
487 |       If subFieldType is defined, it references a type, and a dynamic field
488 |       definition is created matching *___<typename>.  Alternately, if 
489 |       subFieldSuffix is defined, that is used to create the subFields.
490 |       Example: if subFieldType="double", then the coordinates would be
491 |         indexed in fields myloc_0___double,myloc_1___double.
492 |       Example: if subFieldSuffix="_d" then the coordinates would be indexed
493 |         in fields myloc_0_d,myloc_1_d
494 |       The subFields are an implementation detail of the fieldType, and end
495 |       users normally should not need to know about them.
496 |      -->
497 |     <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
498 | 
499 |     <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
500 |     <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
501 | 
502 |     <!-- An alternative geospatial field type new to Solr 4.  It supports multiValued and polygon shapes.
503 |       For more information about this and other Spatial fields new to Solr 4, see:
504 |       http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
505 |     -->
506 |     <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
507 |         geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers" />
508 | 
509 |     <!-- Spatial rectangle (bounding box) field. It supports most spatial predicates, and has
510 |      special relevancy modes: score=overlapRatio|area|area2D (local-param to the query).  DocValues is recommended for
511 |      relevancy. -->
512 |     <fieldType name="bbox" class="solr.BBoxField"
513 |                geo="true" distanceUnits="kilometers" numberType="_bbox_coord" />
514 |     <fieldType name="_bbox_coord" class="solr.TrieDoubleField" precisionStep="8" docValues="true" stored="false"/>
515 | 
516 |    <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
517 |         Parameters:
518 |           defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
519 |           precisionStep:   Specifies the precisionStep for the TrieLong field used for the amount
520 |           providerClass:   Lets you plug in other exchange provider backend:
521 |                            solr.FileExchangeRateProvider is the default and takes one parameter:
522 |                              currencyConfig: name of an xml file holding exchange rates
523 |                            solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org:
524 |                              ratesFileLocation: URL or path to rates JSON file (default latest.json on the web)
525 |                              refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60)
526 |    -->
527 |     <fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />
528 | 
529 | </schema>
530 | 


--------------------------------------------------------------------------------
/src/test/resources/bad_config/solr5/schema_1.xml:
--------------------------------------------------------------------------------
  1 | <?xml version="1.0" encoding="UTF-8" ?>
  2 | <!--
  3 |  Licensed to the Apache Software Foundation (ASF) under one or more
  4 |  contributor license agreements.  See the NOTICE file distributed with
  5 |  this work for additional information regarding copyright ownership.
  6 |  The ASF licenses this file to You under the Apache License, Version 2.0
  7 |  (the "License"); you may not use this file except in compliance with
  8 |  the License.  You may obtain a copy of the License at
  9 | 
 10 |      http://www.apache.org/licenses/LICENSE-2.0
 11 | 
 12 |  Unless required by applicable law or agreed to in writing, software
 13 |  distributed under the License is distributed on an "AS IS" BASIS,
 14 |  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 15 |  See the License for the specific language governing permissions and
 16 |  limitations under the License.
 17 | -->
 18 | 
 19 | <!--  
 20 |  This is the Solr schema file. This file should be named "schema.xml" and
 21 |  should be in the conf directory under the solr home
 22 |  (i.e. ./solr/conf/schema.xml by default) 
 23 |  or located where the classloader for the Solr webapp can find it.
 24 | 
 25 |  This example schema is the recommended starting point for users.
 26 |  It should be kept correct and concise, usable out-of-the-box.
 27 | 
 28 |  For more information, on how to customize this file, please see
 29 |  http://wiki.apache.org/solr/SchemaXml
 30 | -->
 31 | 
 32 | <schema name="example" version="1.5">
 33 |   <!-- attribute "name" is the name of this schema and is only used for display purposes.
 34 |        version="x.y" is Solr's version number for the schema syntax and 
 35 |        semantics.  It should not normally be changed by applications.
 36 | 
 37 |        1.0: multiValued attribute did not exist, all fields are multiValued 
 38 |             by nature
 39 |        1.1: multiValued attribute introduced, false by default 
 40 |        1.2: omitTermFreqAndPositions attribute introduced, true by default 
 41 |             except for text fields.
 42 |        1.3: removed optional field compress feature
 43 |        1.4: autoGeneratePhraseQueries attribute introduced to drive QueryParser
 44 |             behavior when a single string produces multiple tokens.  Defaults 
 45 |             to off for version >= 1.4
 46 |        1.5: omitNorms defaults to true for primitive field types 
 47 |             (int, float, boolean, string...)
 48 |      -->
 49 | 
 50 | 
 51 |    <!-- Valid attributes for fields:
 52 |      name: mandatory - the name for the field
 53 |      type: mandatory - the name of a field type from the 
 54 |        <types> fieldType section
 55 |      indexed: true if this field should be indexed (searchable or sortable)
 56 |      stored: true if this field should be retrievable
 57 |      docValues: true if this field should have doc values. Doc values are
 58 |        useful for faceting, grouping, sorting and function queries. Although not
 59 |        required, doc values will make the index faster to load, more
 60 |        NRT-friendly and more memory-efficient. They however come with some
 61 |        limitations: they are currently only supported by StrField, UUIDField
 62 |        and all Trie*Fields, and depending on the field type, they might
 63 |        require the field to be single-valued, be required or have a default
 64 |        value (check the documentation of the field type you're interested in
 65 |        for more information)
 66 |      multiValued: true if this field may contain multiple values per document
 67 |      omitNorms: (expert) set to true to omit the norms associated with
 68 |        this field (this disables length normalization and index-time
 69 |        boosting for the field, and saves some memory).  Only full-text
 70 |        fields or fields that need an index-time boost need norms.
 71 |        Norms are omitted for primitive (non-analyzed) types by default.
 72 |      termVectors: [false] set to true to store the term vector for a
 73 |        given field.
 74 |        When using MoreLikeThis, fields used for similarity should be
 75 |        stored for best performance.
 76 |      termPositions: Store position information with the term vector.  
 77 |        This will increase storage costs.
 78 |      termOffsets: Store offset information with the term vector. This 
 79 |        will increase storage costs.
 80 |      required: The field is required.  It will throw an error if the
 81 |        value does not exist
 82 |      default: a value that should be used if no value is specified
 83 |        when adding a document.
 84 |    -->
 85 | 
 86 |    <!-- field names should consist of alphanumeric or underscore characters only and
 87 |       not start with a digit.  This is not currently strictly enforced,
 88 |       but other field names will not have first class support from all components
 89 |       and back compatibility is not guaranteed.  Names with both leading and
 90 |       trailing underscores (e.g. _version_) are reserved.
 91 |    -->
 92 | 
 93 |    <!-- If you remove this field, you must _also_ disable the update log in solrconfig.xml
 94 |       or Solr won't start. _version_ and update log are required for SolrCloud
 95 |    --> 
 96 |    <field name="_version_" type="long" indexed="true" stored="true"/>
 97 |    
 98 |    <!-- points to the root document of a block of nested documents. Required for nested
 99 |       document support, may be removed otherwise
100 |    -->
101 |    <field name="_root_" type="string" indexed="true" stored="false"/>
102 | 
103 |    <!-- Only remove the "id" field if you have a very good reason to. While not strictly
104 |      required, it is highly recommended. A <uniqueKey> is present in almost all Solr 
105 |      installations. See the <uniqueKey> declaration below where <uniqueKey> is set to "id".
106 |    -->   
107 |    <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" /> 
108 | 
109 |    <!-- Dynamic field definitions allow using convention over configuration
110 |        for fields via the specification of patterns to match field names. 
111 |        EXAMPLE:  name="*_i" will match any field ending in _i (like myid_i, z_i)
112 |        RESTRICTION: the glob-like pattern in the name attribute must have
113 |        a "*" only at the start or the end.  -->
114 |    
115 |    <dynamicField name="*_i"  type="int"    indexed="true"  stored="true"/>
116 |    <dynamicField name="*_is" type="int"    indexed="true"  stored="true"  multiValued="true"/>
117 |    <dynamicField name="*_s"  type="string"  indexed="true"  stored="true" />
118 |    <dynamicField name="*_ss" type="string"  indexed="true"  stored="true" multiValued="true"/>
119 |    <dynamicField name="*_l"  type="long"   indexed="true"  stored="true"/>
120 |    <dynamicField name="*_ls" type="long"   indexed="true"  stored="true"  multiValued="true"/>
121 |    <dynamicField name="*_t"  type="text_general"    indexed="true"  stored="true"/>
122 |    <dynamicField name="*_txt" type="text_general"   indexed="true"  stored="true" multiValued="true"/>
123 |    <dynamicField name="*_en"  type="text_en"    indexed="true"  stored="true" multiValued="true"/>
124 |    <dynamicField name="*_b"  type="boolean" indexed="true" stored="true"/>
125 |    <dynamicField name="*_bs" type="boolean" indexed="true" stored="true"  multiValued="true"/>
126 |    <dynamicField name="*_f"  type="float"  indexed="true"  stored="true"/>
127 |    <dynamicField name="*_fs" type="float"  indexed="true"  stored="true"  multiValued="true"/>
128 |    <dynamicField name="*_d"  type="double" indexed="true"  stored="true"/>
129 |    <dynamicField name="*_ds" type="double" indexed="true"  stored="true"  multiValued="true"/>
130 | 
131 |    <!-- Type used to index the lat and lon components for the "location" FieldType -->
132 |    <dynamicField name="*_coordinate"  type="tdouble" indexed="true"  stored="false" />
133 | 
134 |    <dynamicField name="*_dt"  type="date"    indexed="true"  stored="true"/>
135 |    <dynamicField name="*_dts" type="date"    indexed="true"  stored="true" multiValued="true"/>
136 |    <dynamicField name="*_p"  type="location" indexed="true" stored="true"/>
137 | 
138 |    <!-- some trie-coded dynamic fields for faster range queries -->
139 |    <dynamicField name="*_ti" type="tint"    indexed="true"  stored="true"/>
140 |    <dynamicField name="*_tl" type="tlong"   indexed="true"  stored="true"/>
141 |    <dynamicField name="*_tf" type="tfloat"  indexed="true"  stored="true"/>
142 |    <dynamicField name="*_td" type="tdouble" indexed="true"  stored="true"/>
143 |    <dynamicField name="*_tdt" type="tdate"  indexed="true"  stored="true"/>
144 | 
145 |    <dynamicField name="*_c"   type="currency" indexed="true"  stored="true"/>
146 | 
147 |    <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
148 |    <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
149 | 
150 |    <dynamicField name="random_*" type="random" />
151 | 
152 |    <!-- uncomment the following to ignore any fields that don't already match an existing 
153 |         field name or dynamic field, rather than reporting them as an error. 
154 |         alternately, change the type="ignored" to some other type e.g. "text" if you want 
155 |         unknown fields indexed and/or stored by default --> 
156 |    <!--dynamicField name="*" type="ignored" multiValued="true" /-->
157 | 
158 |  <!-- Field to use to determine and enforce document uniqueness. 
159 |       Unless this field is marked with required="false", it will be a required field
160 |    -->
161 |  <uniqueKey>id</uniqueKey>
162 | 
163 |   <!-- copyField commands copy one field to another at the time a document
164 |         is added to the index.  It's used either to index the same field differently,
165 |         or to add multiple fields to the same field for easier/faster searching.  -->
166 | 
167 |   <!--
168 |    <copyField source="title" dest="text"/>
169 |    <copyField source="body" dest="text"/>
170 |   -->
171 |   
172 |     <!-- field type definitions. The "name" attribute is
173 |        just a label to be used by field definitions.  The "class"
174 |        attribute and any other attributes determine the real
175 |        behavior of the fieldType.
176 |          Class names starting with "solr" refer to java classes in a
177 |        standard package such as org.apache.solr.analysis
178 |     -->
179 | 
180 |     <!-- The StrField type is not analyzed, but indexed/stored verbatim.
181 |        It supports doc values but in that case the field needs to be
182 |        single-valued and either required or have a default value.
183 |       -->
184 |     <fieldType name="string" class="solr.StrField" sortMissingLast="true" />
185 | 
186 |     <!-- boolean type: "true" or "false" -->
187 |     <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
188 | 
189 |     <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
190 |          currently supported on types that are sorted internally as strings
191 |          and on numeric types.
192 | 	     This includes "string","boolean", and, as of 3.5 (and 4.x),
193 | 	     int, float, long, date, double, including the "Trie" variants.
194 |        - If sortMissingLast="true", then a sort on this field will cause documents
195 |          without the field to come after documents with the field,
196 |          regardless of the requested sort order (asc or desc).
197 |        - If sortMissingFirst="true", then a sort on this field will cause documents
198 |          without the field to come before documents with the field,
199 |          regardless of the requested sort order.
200 |        - If sortMissingLast="false" and sortMissingFirst="false" (the default),
201 |          then default lucene sorting will be used which places docs without the
202 |          field first in an ascending sort and last in a descending sort.
203 |     -->    
204 | 
205 |     <!--
206 |       Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
207 | 
208 |       These fields support doc values, but they require the field to be
209 |       single-valued and either be required or have a default value.
210 |     -->
211 |     <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
212 |     <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
213 |     <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
214 |     <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
215 | 
216 |     <!--
217 |      Numeric field types that index each value at various levels of precision
218 |      to accelerate range queries when the number of values between the range
219 |      endpoints is large. See the javadoc for NumericRangeQuery for internal
220 |      implementation details.
221 | 
222 |      Smaller precisionStep values (specified in bits) will lead to more tokens
223 |      indexed per value, slightly larger index size, and faster range queries.
224 |      A precisionStep of 0 disables indexing at different precision levels.
225 |     -->
226 |     <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
227 |     <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
228 |     <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
229 |     <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
230 | 
231 |     <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
232 |          is a more restricted form of the canonical representation of dateTime
233 |          http://www.w3.org/TR/xmlschema-2/#dateTime    
234 |          The trailing "Z" designates UTC time and is mandatory.
235 |          Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
236 |          All other components are mandatory.
237 | 
238 |          Expressions can also be used to denote calculations that should be
239 |          performed relative to "NOW" to determine the value, ie...
240 | 
241 |                NOW/HOUR
242 |                   ... Round to the start of the current hour
243 |                NOW-1DAY
244 |                   ... Exactly 1 day prior to now
245 |                NOW/DAY+6MONTHS+3DAYS
246 |                   ... 6 months and 3 days in the future from the start of
247 |                       the current day
248 |                       
249 |          Consult the TrieDateField javadocs for more information.
250 | 
251 |          Note: For faster range queries, consider the tdate type
252 |       -->
253 |     <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
254 | 
255 |     <!-- A Trie based date field for faster date range queries and date faceting. -->
256 |     <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
257 | 
258 | 
259 |     <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
260 |     <fieldType name="binary" class="solr.BinaryField"/>
261 | 
262 |     <!-- The "RandomSortField" is not used to store or search any
263 |          data.  You can declare fields of this type it in your schema
264 |          to generate pseudo-random orderings of your docs for sorting 
265 |          or function purposes.  The ordering is generated based on the field
266 |          name and the version of the index. As long as the index version
267 |          remains unchanged, and the same field name is reused,
268 |          the ordering of the docs will be consistent.  
269 |          If you want different psuedo-random orderings of documents,
270 |          for the same version of the index, use a dynamicField and
271 |          change the field name in the request.
272 |      -->
273 |     <fieldType name="random" class="solr.RandomSortField" indexed="true" />
274 | 
275 |     <!-- solr.TextField allows the specification of custom text analyzers
276 |          specified as a tokenizer and a list of token filters. Different
277 |          analyzers may be specified for indexing and querying.
278 | 
279 |          The optional positionIncrementGap puts space between multiple fields of
280 |          this type on the same document, with the purpose of preventing false phrase
281 |          matching across fields.
282 | 
283 |          For more info on customizing your analyzer chain, please see
284 |          http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
285 |      -->
286 | 
287 |     <!-- One can also specify an existing Analyzer class that has a
288 |          default constructor via the class attribute on the analyzer element.
289 |          Example:
290 |     <fieldType name="text_greek" class="solr.TextField">
291 |       <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
292 |     </fieldType>
293 |     -->
294 | 
295 |     <!-- A text field that only splits on whitespace for exact matching of words -->
296 |     <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
297 |       <analyzer>
298 |         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
299 |       </analyzer>
300 |     </fieldType>
301 | 
302 |     <!-- A general text field that has reasonable, generic
303 |          cross-language defaults: it tokenizes with StandardTokenizer,
304 | 	 removes stop words from case-insensitive "stopwords.txt"
305 | 	 (empty by default), and down cases.  At query time only, it
306 | 	 also applies synonyms. -->
307 |     <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
308 |       <analyzer type="index">
309 |         <tokenizer class="solr.StandardTokenizerFactory"/>
310 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
311 |         <!-- in this example, we will only use synonyms at query time
312 |         <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
313 |         -->
314 |         <filter class="solr.LowerCaseFilterFactory"/>
315 |       </analyzer>
316 |       <analyzer type="query">
317 |         <tokenizer class="solr.StandardTokenizerFactory"/>
318 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
319 |         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
320 |         <filter class="solr.LowerCaseFilterFactory"/>
321 |       </analyzer>
322 |     </fieldType>
323 | 
324 |     <!-- A text field with defaults appropriate for English: it
325 |          tokenizes with StandardTokenizer, removes English stop words
326 |          (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
327 |          finally applies Porter's stemming.  The query time analyzer
328 |          also applies synonyms from synonyms.txt. -->
329 |     <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
330 |       <analyzer type="index">
331 |         <tokenizer class="solr.StandardTokenizerFactory"/>
332 |         <!-- in this example, we will only use synonyms at query time
333 |         <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
334 |         -->
335 |         <!-- Case insensitive stop word removal.
336 |         -->
337 |         <filter class="solr.StopFilterFactory"
338 |                 ignoreCase="true"
339 |                 words="lang/stopwords_en.txt"
340 |                 />
341 |         <filter class="solr.LowerCaseFilterFactory"/>
342 | 	<filter class="solr.EnglishPossessiveFilterFactory"/>
343 |         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
344 | 	<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
345 |         <filter class="solr.EnglishMinimalStemFilterFactory"/>
346 | 	-->
347 |         <filter class="solr.PorterStemFilterFactory"/>
348 |       </analyzer>
349 |       <analyzer type="query">
350 |         <tokenizer class="solr.StandardTokenizerFactory"/>
351 |         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
352 |         <filter class="solr.StopFilterFactory"
353 |                 ignoreCase="true"
354 |                 words="lang/stopwords_en.txt"
355 |                 />
356 |         <filter class="solr.LowerCaseFilterFactory"/>
357 | 	<filter class="solr.EnglishPossessiveFilterFactory"/>
358 |         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
359 | 	<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
360 |         <filter class="solr.EnglishMinimalStemFilterFactory"/>
361 | 	-->
362 |         <filter class="solr.PorterStemFilterFactory"/>
363 |       </analyzer>
364 |     </fieldType>
365 | 
366 |     <!-- A text field with defaults appropriate for English, plus
367 | 	 aggressive word-splitting and autophrase features enabled.
368 | 	 This field is just like text_en, except it adds
369 | 	 WordDelimiterFilter to enable splitting and matching of
370 | 	 words on case-change, alpha numeric boundaries, and
371 | 	 non-alphanumeric chars.  This means certain compound word
372 | 	 cases will work, for example query "wi fi" will match
373 | 	 document "WiFi" or "wi-fi".
374 |         -->
375 |     <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
376 |       <analyzer type="index">
377 |         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
378 |         <!-- in this example, we will only use synonyms at query time
379 |         <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
380 |         -->
381 |         <!-- Case insensitive stop word removal.
382 |         -->
383 |         <filter class="solr.StopFilterFactory"
384 |                 ignoreCase="true"
385 |                 words="lang/stopwords_en.txt"
386 |                 />
387 |         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
388 |         <filter class="solr.LowerCaseFilterFactory"/>
389 |         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
390 |         <filter class="solr.PorterStemFilterFactory"/>
391 |       </analyzer>
392 |       <analyzer type="query">
393 |         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
394 |         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
395 |         <filter class="solr.StopFilterFactory"
396 |                 ignoreCase="true"
397 |                 words="lang/stopwords_en.txt"
398 |                 />
399 |         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
400 |         <filter class="solr.LowerCaseFilterFactory"/>
401 |         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
402 |         <filter class="solr.PorterStemFilterFactory"/>
403 |       </analyzer>
404 |     </fieldType>
405 | 
406 |     <!-- Less flexible matching, but less false matches.  Probably not ideal for product names,
407 |          but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
408 |     <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
409 |       <analyzer>
410 |         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
411 |         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
412 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
413 |         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
414 |         <filter class="solr.LowerCaseFilterFactory"/>
415 |         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
416 |         <filter class="solr.EnglishMinimalStemFilterFactory"/>
417 |         <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
418 |              possible with WordDelimiterFilter in conjuncton with stemming. -->
419 |         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
420 |       </analyzer>
421 |     </fieldType>
422 | 
423 |     <!-- Just like text_general except it reverses the characters of
424 | 	 each token, to enable more efficient leading wildcard queries. -->
425 |     <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
426 |       <analyzer type="index">
427 |         <tokenizer class="solr.StandardTokenizerFactory"/>
428 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
429 |         <filter class="solr.LowerCaseFilterFactory"/>
430 |         <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
431 |            maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
432 |       </analyzer>
433 |       <analyzer type="query">
434 |         <tokenizer class="solr.StandardTokenizerFactory"/>
435 |         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
436 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
437 |         <filter class="solr.LowerCaseFilterFactory"/>
438 |       </analyzer>
439 |     </fieldType>
440 | 
441 |     <!-- This is an example of using the KeywordTokenizer along
442 |          With various TokenFilterFactories to produce a sortable field
443 |          that does not include some properties of the source text
444 |       -->
445 |     <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
446 |       <analyzer>
447 |         <!-- KeywordTokenizer does no actual tokenizing, so the entire
448 |              input string is preserved as a single token
449 |           -->
450 |         <tokenizer class="solr.KeywordTokenizerFactory"/>
451 |         <!-- The LowerCase TokenFilter does what you expect, which can be
452 |              when you want your sorting to be case insensitive
453 |           -->
454 |         <filter class="solr.LowerCaseFilterFactory" />
455 |         <!-- The TrimFilter removes any leading or trailing whitespace -->
456 |         <filter class="solr.TrimFilterFactory" />
457 |         <!-- The PatternReplaceFilter gives you the flexibility to use
458 |              Java Regular expression to replace any sequence of characters
459 |              matching a pattern with an arbitrary replacement string, 
460 |              which may include back references to portions of the original
461 |              string matched by the pattern.
462 |              
463 |              See the Java Regular Expression documentation for more
464 |              information on pattern and replacement string syntax.
465 |              
466 |              http://docs.oracle.com/javase/7/docs/api/java/util/regex/package-summary.html
467 |           -->
468 |         <filter class="solr.PatternReplaceFilterFactory"
469 |                 pattern="([^a-z])" replacement="" replace="all"
470 |         />
471 |       </analyzer>
472 |     </fieldType>
473 | 
474 |     <!-- lowercases the entire field value, keeping it as a single token.  -->
475 |     <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
476 |       <analyzer>
477 |         <tokenizer class="solr.KeywordTokenizerFactory"/>
478 |         <filter class="solr.LowerCaseFilterFactory" />
479 |       </analyzer>
480 |     </fieldType>
481 | 
482 |     <!-- since fields of this type are by default not stored or indexed,
483 |          any data added to them will be ignored outright.  --> 
484 |     <fieldType name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
485 | 
486 |     <!-- This point type indexes the coordinates as separate fields (subFields)
487 |       If subFieldType is defined, it references a type, and a dynamic field
488 |       definition is created matching *___<typename>.  Alternately, if 
489 |       subFieldSuffix is defined, that is used to create the subFields.
490 |       Example: if subFieldType="double", then the coordinates would be
491 |         indexed in fields myloc_0___double,myloc_1___double.
492 |       Example: if subFieldSuffix="_d" then the coordinates would be indexed
493 |         in fields myloc_0_d,myloc_1_d
494 |       The subFields are an implementation detail of the fieldType, and end
495 |       users normally should not need to know about them.
496 |      -->
497 |     <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
498 | 
499 |     <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
500 |     <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
501 | 
502 |     <!-- An alternative geospatial field type new to Solr 4.  It supports multiValued and polygon shapes.
503 |       For more information about this and other Spatial fields new to Solr 4, see:
504 |       http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
505 |     -->
506 |     <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
507 |         geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers" />
508 | 
509 |     <!-- Spatial rectangle (bounding box) field. It supports most spatial predicates, and has
510 |      special relevancy modes: score=overlapRatio|area|area2D (local-param to the query).  DocValues is recommended for
511 |      relevancy. -->
512 |     <fieldType name="bbox" class="solr.BBoxField"
513 |                geo="true" distanceUnits="kilometers" numberType="_bbox_coord" />
514 |     <fieldType name="_bbox_coord" class="solr.TrieDoubleField" precisionStep="8" docValues="true" stored="false"/>
515 | 
516 |    <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
517 |         Parameters:
518 |           defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
519 |           precisionStep:   Specifies the precisionStep for the TrieLong field used for the amount
520 |           providerClass:   Lets you plug in other exchange provider backend:
521 |                            solr.FileExchangeRateProvider is the default and takes one parameter:
522 |                              currencyConfig: name of an xml file holding exchange rates
523 |                            solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org:
524 |                              ratesFileLocation: URL or path to rates JSON file (default latest.json on the web)
525 |                              refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60)
526 |    -->
527 |     <fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />
528 | 
529 |     <similarity class="solr.DefaultSimilarityFactory">
530 |        <bool name="discountOverlaps">false</bool>
531 |     </similarity>
532 | 
533 | </schema>
534 | 


--------------------------------------------------------------------------------
/src/test/resources/good_config/schema.xml:
--------------------------------------------------------------------------------
   1 | <?xml version="1.0" encoding="UTF-8" ?>
   2 | <!--
   3 |  Licensed to the Apache Software Foundation (ASF) under one or more
   4 |  contributor license agreements.  See the NOTICE file distributed with
   5 |  this work for additional information regarding copyright ownership.
   6 |  The ASF licenses this file to You under the Apache License, Version 2.0
   7 |  (the "License"); you may not use this file except in compliance with
   8 |  the License.  You may obtain a copy of the License at
   9 | 
  10 |      http://www.apache.org/licenses/LICENSE-2.0
  11 | 
  12 |  Unless required by applicable law or agreed to in writing, software
  13 |  distributed under the License is distributed on an "AS IS" BASIS,
  14 |  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  15 |  See the License for the specific language governing permissions and
  16 |  limitations under the License.
  17 | -->
  18 | 
  19 | <!--  
  20 |  This is the Solr schema file. This file should be named "schema.xml" and
  21 |  should be in the conf directory under the solr home
  22 |  (i.e. ./solr/conf/schema.xml by default) 
  23 |  or located where the classloader for the Solr webapp can find it.
  24 | 
  25 |  This example schema is the recommended starting point for users.
  26 |  It should be kept correct and concise, usable out-of-the-box.
  27 | 
  28 |  For more information, on how to customize this file, please see
  29 |  http://wiki.apache.org/solr/SchemaXml
  30 | 
  31 |  PERFORMANCE NOTE: this schema includes many optional features and should not
  32 |  be used for benchmarking.  To improve performance one could
  33 |   - set stored="false" for all fields possible (esp large fields) when you
  34 |     only need to search on the field but don't need to return the original
  35 |     value.
  36 |   - set indexed="false" if you don't need to search on the field, but only
  37 |     return the field as a result of searching on other indexed fields.
  38 |   - remove all unneeded copyField statements
  39 |   - for best index size and searching performance, set "index" to false
  40 |     for all general text fields, use copyField to copy them to the
  41 |     catchall "text" field, and use that for searching.
  42 |   - For maximum indexing performance, use the StreamingUpdateSolrServer
  43 |     java client.
  44 |   - Remember to run the JVM in server mode, and use a higher logging level
  45 |     that avoids logging every request
  46 | -->
  47 | 
  48 | <schema name="example" version="1.5">
  49 |   <!-- attribute "name" is the name of this schema and is only used for display purposes.
  50 |        version="x.y" is Solr's version number for the schema syntax and 
  51 |        semantics.  It should not normally be changed by applications.
  52 | 
  53 |        1.0: multiValued attribute did not exist, all fields are multiValued 
  54 |             by nature
  55 |        1.1: multiValued attribute introduced, false by default 
  56 |        1.2: omitTermFreqAndPositions attribute introduced, true by default 
  57 |             except for text fields.
  58 |        1.3: removed optional field compress feature
  59 |        1.4: autoGeneratePhraseQueries attribute introduced to drive QueryParser
  60 |             behavior when a single string produces multiple tokens.  Defaults 
  61 |             to off for version >= 1.4
  62 |        1.5: omitNorms defaults to true for primitive field types 
  63 |             (int, float, boolean, string...)
  64 |      -->
  65 | 
  66 |  <fields>
  67 |    <!-- Valid attributes for fields:
  68 |      name: mandatory - the name for the field
  69 |      type: mandatory - the name of a field type from the 
  70 |        <types> fieldType section
  71 |      indexed: true if this field should be indexed (searchable or sortable)
  72 |      stored: true if this field should be retrievable
  73 |      docValues: true if this field should have doc values. Doc values are
  74 |        useful for faceting, grouping, sorting and function queries. Although not
  75 |        required, doc values will make the index faster to load, more
  76 |        NRT-friendly and more memory-efficient. They however come with some
  77 |        limitations: they are currently only supported by StrField, UUIDField
  78 |        and all Trie*Fields, and depending on the field type, they might
  79 |        require the field to be single-valued, be required or have a default
  80 |        value (check the documentation of the field type you're interested in
  81 |        for more information)
  82 |      multiValued: true if this field may contain multiple values per document
  83 |      omitNorms: (expert) set to true to omit the norms associated with
  84 |        this field (this disables length normalization and index-time
  85 |        boosting for the field, and saves some memory).  Only full-text
  86 |        fields or fields that need an index-time boost need norms.
  87 |        Norms are omitted for primitive (non-analyzed) types by default.
  88 |      termVectors: [false] set to true to store the term vector for a
  89 |        given field.
  90 |        When using MoreLikeThis, fields used for similarity should be
  91 |        stored for best performance.
  92 |      termPositions: Store position information with the term vector.  
  93 |        This will increase storage costs.
  94 |      termOffsets: Store offset information with the term vector. This 
  95 |        will increase storage costs.
  96 |      required: The field is required.  It will throw an error if the
  97 |        value does not exist
  98 |      default: a value that should be used if no value is specified
  99 |        when adding a document.
 100 |    -->
 101 | 
 102 |    <!-- field names should consist of alphanumeric or underscore characters only and
 103 |       not start with a digit.  This is not currently strictly enforced,
 104 |       but other field names will not have first class support from all components
 105 |       and back compatibility is not guaranteed.  Names with both leading and
 106 |       trailing underscores (e.g. _version_) are reserved.
 107 |    -->
 108 |         
 109 |    <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" /> 
 110 |    
 111 |    <!-- points to the root document of a block of nested documents. Required for nested
 112 |         document support, may be removed otherwise
 113 |    -->
 114 |    <field name="_root_" type="string" indexed="true" stored="false"/>
 115 |    
 116 |    <field name="sku" type="text_en_splitting_tight" indexed="true" stored="true" omitNorms="true"/>
 117 |    <field name="name" type="text_general" indexed="true" stored="true"/>
 118 |    <field name="manu" type="text_general" indexed="true" stored="true" omitNorms="true"/>
 119 |    <field name="cat" type="string" indexed="true" stored="true" multiValued="true"/>
 120 |    <field name="features" type="text_general" indexed="true" stored="true" multiValued="true"/>
 121 |    <field name="includes" type="text_general" indexed="true" stored="true" termVectors="true" termPositions="true" termOffsets="true" />
 122 | 
 123 |    <field name="weight" type="float" indexed="true" stored="true"/>
 124 |    <field name="price"  type="float" indexed="true" stored="true"/>
 125 |    <field name="popularity" type="int" indexed="true" stored="true" />
 126 |    <field name="inStock" type="boolean" indexed="true" stored="true" />
 127 | 
 128 |    <field name="store" type="location" indexed="true" stored="true"/>
 129 | 
 130 |    <!-- Common metadata fields, named specifically to match up with
 131 |      SolrCell metadata when parsing rich documents such as Word, PDF.
 132 |      Some fields are multiValued only because Tika currently may return
 133 |      multiple values for them. Some metadata is parsed from the documents,
 134 |      but there are some which come from the client context:
 135 |        "content_type": From the HTTP headers of incoming stream
 136 |        "resourcename": From SolrCell request param resource.name
 137 |    -->
 138 |    <field name="title" type="text_general" indexed="true" stored="true" multiValued="true"/>
 139 |    <field name="subject" type="text_general" indexed="true" stored="true"/>
 140 |    <field name="description" type="text_general" indexed="true" stored="true"/>
 141 |    <field name="comments" type="text_general" indexed="true" stored="true"/>
 142 |    <field name="author" type="text_general" indexed="true" stored="true"/>
 143 |    <field name="keywords" type="text_general" indexed="true" stored="true"/>
 144 |    <field name="category" type="text_general" indexed="true" stored="true"/>
 145 |    <field name="resourcename" type="text_general" indexed="true" stored="true"/>
 146 |    <field name="url" type="text_general" indexed="true" stored="true"/>
 147 |    <field name="content_type" type="string" indexed="true" stored="true" multiValued="true"/>
 148 |    <field name="last_modified" type="date" indexed="true" stored="true"/>
 149 |    <field name="links" type="string" indexed="true" stored="true" multiValued="true"/>
 150 | 
 151 |    <field name="upgrade_test_bm" type="text_bm" indexed="true" stored="true" multiValued="true"/>
 152 | 
 153 |    <!-- Main body of document extracted by SolrCell.
 154 |         NOTE: This field is not indexed by default, since it is also copied to "text"
 155 |         using copyField below. This is to save space. Use this field for returning and
 156 |         highlighting document content. Use the "text" field to search the content. -->
 157 |    <field name="content" type="text_general" indexed="false" stored="true" multiValued="true"/>
 158 |    
 159 | 
 160 |    <!-- catchall field, containing all other searchable text fields (implemented
 161 |         via copyField further on in this schema  -->
 162 |    <field name="text" type="text_general" indexed="true" stored="false" multiValued="true"/>
 163 | 
 164 |    <!-- catchall text field that indexes tokens both normally and in reverse for efficient
 165 |         leading wildcard queries. -->
 166 |    <field name="text_rev" type="text_general_rev" indexed="true" stored="false" multiValued="true"/>
 167 | 
 168 |    <!-- non-tokenized version of manufacturer to make it easier to sort or group
 169 |         results by manufacturer.  copied from "manu" via copyField -->
 170 |    <field name="manu_exact" type="string" indexed="true" stored="false"/>
 171 | 
 172 |    <field name="payloads" type="payloads" indexed="true" stored="true"/>
 173 | 
 174 |    <field name="_version_" type="long" indexed="true" stored="true"/>
 175 | 
 176 |    <!--
 177 |      Some fields such as popularity and manu_exact could be modified to
 178 |      leverage doc values:
 179 |      <field name="popularity" type="int" indexed="true" stored="true" docValues="true" default="0" />
 180 |      <field name="manu_exact" type="string" indexed="false" stored="false" docValues="true" default="" />
 181 | 
 182 |      Although it would make indexing slightly slower and the index bigger, it
 183 |      would also make the index faster to load, more memory-efficient and more
 184 |      NRT-friendly.
 185 |      -->
 186 | 
 187 |    <!-- Dynamic field definitions allow using convention over configuration
 188 |        for fields via the specification of patterns to match field names. 
 189 |        EXAMPLE:  name="*_i" will match any field ending in _i (like myid_i, z_i)
 190 |        RESTRICTION: the glob-like pattern in the name attribute must have
 191 |        a "*" only at the start or the end.  -->
 192 |    
 193 |    <dynamicField name="*_i"  type="int"    indexed="true"  stored="true"/>
 194 |    <dynamicField name="*_is" type="int"    indexed="true"  stored="true"  multiValued="true"/>
 195 |    <dynamicField name="*_s"  type="string"  indexed="true"  stored="true" />
 196 |    <dynamicField name="*_ss" type="string"  indexed="true"  stored="true" multiValued="true"/>
 197 |    <dynamicField name="*_l"  type="long"   indexed="true"  stored="true"/>
 198 |    <dynamicField name="*_ls" type="long"   indexed="true"  stored="true"  multiValued="true"/>
 199 |    <dynamicField name="*_t"  type="text_general"    indexed="true"  stored="true"/>
 200 |    <dynamicField name="*_txt" type="text_general"   indexed="true"  stored="true" multiValued="true"/>
 201 |    <dynamicField name="*_en"  type="text_en"    indexed="true"  stored="true" multiValued="true"/>
 202 |    <dynamicField name="*_b"  type="boolean" indexed="true" stored="true"/>
 203 |    <dynamicField name="*_bs" type="boolean" indexed="true" stored="true"  multiValued="true"/>
 204 |    <dynamicField name="*_f"  type="float"  indexed="true"  stored="true"/>
 205 |    <dynamicField name="*_fs" type="float"  indexed="true"  stored="true"  multiValued="true"/>
 206 |    <dynamicField name="*_d"  type="double" indexed="true"  stored="true"/>
 207 |    <dynamicField name="*_ds" type="double" indexed="true"  stored="true"  multiValued="true"/>
 208 | 
 209 |    <!-- Type used to index the lat and lon components for the "location" FieldType -->
 210 |    <dynamicField name="*_coordinate"  type="tdouble" indexed="true"  stored="false" />
 211 | 
 212 |    <dynamicField name="*_dt"  type="date"    indexed="true"  stored="true"/>
 213 |    <dynamicField name="*_dts" type="date"    indexed="true"  stored="true" multiValued="true"/>
 214 |    <dynamicField name="*_p"  type="location" indexed="true" stored="true"/>
 215 | 
 216 |    <!-- some trie-coded dynamic fields for faster range queries -->
 217 |    <dynamicField name="*_ti" type="tint"    indexed="true"  stored="true"/>
 218 |    <dynamicField name="*_tl" type="tlong"   indexed="true"  stored="true"/>
 219 |    <dynamicField name="*_tf" type="tfloat"  indexed="true"  stored="true"/>
 220 |    <dynamicField name="*_td" type="tdouble" indexed="true"  stored="true"/>
 221 |    <dynamicField name="*_tdt" type="tdate"  indexed="true"  stored="true"/>
 222 | 
 223 |    <dynamicField name="*_c"   type="currency" indexed="true"  stored="true"/>
 224 | 
 225 |    <!-- dynamic field for auth tokens -->
 226 |    <dynamicField name="*_auth" type="string" indexed="true" stored="false" multiValued="true"/>
 227 | 
 228 |    <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
 229 |    <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
 230 | 
 231 |    <dynamicField name="random_*" type="random" />
 232 | 
 233 |    <!-- uncomment the following to ignore any fields that don't already match an existing 
 234 |         field name or dynamic field, rather than reporting them as an error. 
 235 |         alternately, change the type="ignored" to some other type e.g. "text" if you want 
 236 |         unknown fields indexed and/or stored by default --> 
 237 |    <!--dynamicField name="*" type="ignored" multiValued="true" /-->
 238 |    
 239 |  </fields>
 240 | 
 241 | 
 242 |  <!-- Field to use to determine and enforce document uniqueness. 
 243 |       Unless this field is marked with required="false", it will be a required field
 244 |    -->
 245 |  <uniqueKey>id</uniqueKey>
 246 | 
 247 |  <!-- DEPRECATED: The defaultSearchField is consulted by various query parsers when
 248 |   parsing a query string that isn't explicit about the field.  Machine (non-user)
 249 |   generated queries are best made explicit, or they can use the "df" request parameter
 250 |   which takes precedence over this.
 251 |   Note: Un-commenting defaultSearchField will be insufficient if your request handler
 252 |   in solrconfig.xml defines "df", which takes precedence. That would need to be removed.
 253 |  <defaultSearchField>text</defaultSearchField> -->
 254 | 
 255 |  <!-- DEPRECATED: The defaultOperator (AND|OR) is consulted by various query parsers
 256 |   when parsing a query string to determine if a clause of the query should be marked as
 257 |   required or optional, assuming the clause isn't already marked by some operator.
 258 |   The default is OR, which is generally assumed so it is not a good idea to change it
 259 |   globally here.  The "q.op" request parameter takes precedence over this.
 260 |  <solrQueryParser defaultOperator="OR"/> -->
 261 | 
 262 |   <!-- copyField commands copy one field to another at the time a document
 263 |         is added to the index.  It's used either to index the same field differently,
 264 |         or to add multiple fields to the same field for easier/faster searching.  -->
 265 | 
 266 |    <copyField source="cat" dest="text"/>
 267 |    <copyField source="name" dest="text"/>
 268 |    <copyField source="manu" dest="text"/>
 269 |    <copyField source="features" dest="text"/>
 270 |    <copyField source="includes" dest="text"/>
 271 |    <copyField source="manu" dest="manu_exact"/>
 272 | 
 273 |    <!-- Copy the price into a currency enabled field (default USD) -->
 274 |    <copyField source="price" dest="price_c"/>
 275 | 
 276 |    <!-- Text fields from SolrCell to search by default in our catch-all field -->
 277 |    <copyField source="title" dest="text"/>
 278 |    <copyField source="author" dest="text"/>
 279 |    <copyField source="description" dest="text"/>
 280 |    <copyField source="keywords" dest="text"/>
 281 |    <copyField source="content" dest="text"/>
 282 |    <copyField source="content_type" dest="text"/>
 283 |    <copyField source="resourcename" dest="text"/>
 284 |    <copyField source="url" dest="text"/>
 285 | 
 286 |    <!-- Create a string version of author for faceting -->
 287 |    <copyField source="author" dest="author_s"/>
 288 | 	
 289 |    <!-- Above, multiple source fields are copied to the [text] field. 
 290 | 	  Another way to map multiple source fields to the same 
 291 | 	  destination field is to use the dynamic field syntax. 
 292 | 	  copyField also supports a maxChars to copy setting.  -->
 293 | 	   
 294 |    <!-- <copyField source="*_t" dest="text" maxChars="3000"/> -->
 295 | 
 296 |    <!-- copy name to alphaNameSort, a field designed for sorting by name -->
 297 |    <!-- <copyField source="name" dest="alphaNameSort"/> -->
 298 |  
 299 |   <types>
 300 |     <!-- field type definitions. The "name" attribute is
 301 |        just a label to be used by field definitions.  The "class"
 302 |        attribute and any other attributes determine the real
 303 |        behavior of the fieldType.
 304 |          Class names starting with "solr" refer to java classes in a
 305 |        standard package such as org.apache.solr.analysis
 306 |     -->
 307 | 
 308 |     <!-- The StrField type is not analyzed, but indexed/stored verbatim.
 309 |        It supports doc values but in that case the field needs to be
 310 |        single-valued and either required or have a default value.
 311 |       -->
 312 |     <fieldType name="string" class="solr.StrField" sortMissingLast="true" />
 313 | 
 314 |     <!-- boolean type: "true" or "false" -->
 315 |     <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
 316 | 
 317 |     <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
 318 |          currently supported on types that are sorted internally as strings
 319 |          and on numeric types.
 320 | 	     This includes "string","boolean", and, as of 3.5 (and 4.x),
 321 | 	     int, float, long, date, double, including the "Trie" variants.
 322 |        - If sortMissingLast="true", then a sort on this field will cause documents
 323 |          without the field to come after documents with the field,
 324 |          regardless of the requested sort order (asc or desc).
 325 |        - If sortMissingFirst="true", then a sort on this field will cause documents
 326 |          without the field to come before documents with the field,
 327 |          regardless of the requested sort order.
 328 |        - If sortMissingLast="false" and sortMissingFirst="false" (the default),
 329 |          then default lucene sorting will be used which places docs without the
 330 |          field first in an ascending sort and last in a descending sort.
 331 |     -->    
 332 | 
 333 |     <!--
 334 |       Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
 335 | 
 336 |       These fields support doc values, but they require the field to be
 337 |       single-valued and either be required or have a default value.
 338 |     -->
 339 |     <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
 340 |     <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
 341 |     <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
 342 |     <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
 343 | 
 344 |     <!--
 345 |      Numeric field types that index each value at various levels of precision
 346 |      to accelerate range queries when the number of values between the range
 347 |      endpoints is large. See the javadoc for NumericRangeQuery for internal
 348 |      implementation details.
 349 | 
 350 |      Smaller precisionStep values (specified in bits) will lead to more tokens
 351 |      indexed per value, slightly larger index size, and faster range queries.
 352 |      A precisionStep of 0 disables indexing at different precision levels.
 353 |     -->
 354 |     <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
 355 |     <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
 356 |     <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
 357 |     <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
 358 | 
 359 |     <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
 360 |          is a more restricted form of the canonical representation of dateTime
 361 |          http://www.w3.org/TR/xmlschema-2/#dateTime    
 362 |          The trailing "Z" designates UTC time and is mandatory.
 363 |          Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
 364 |          All other components are mandatory.
 365 | 
 366 |          Expressions can also be used to denote calculations that should be
 367 |          performed relative to "NOW" to determine the value, ie...
 368 | 
 369 |                NOW/HOUR
 370 |                   ... Round to the start of the current hour
 371 |                NOW-1DAY
 372 |                   ... Exactly 1 day prior to now
 373 |                NOW/DAY+6MONTHS+3DAYS
 374 |                   ... 6 months and 3 days in the future from the start of
 375 |                       the current day
 376 |                       
 377 |          Consult the DateField javadocs for more information.
 378 | 
 379 |          Note: For faster range queries, consider the tdate type
 380 |       -->
 381 |     <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
 382 | 
 383 |     <!-- A Trie based date field for faster date range queries and date faceting. -->
 384 |     <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
 385 | 
 386 | 
 387 |     <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
 388 |     <fieldtype name="binary" class="solr.BinaryField"/>
 389 | 
 390 |     <!-- The "RandomSortField" is not used to store or search any
 391 |          data.  You can declare fields of this type it in your schema
 392 |          to generate pseudo-random orderings of your docs for sorting 
 393 |          or function purposes.  The ordering is generated based on the field
 394 |          name and the version of the index. As long as the index version
 395 |          remains unchanged, and the same field name is reused,
 396 |          the ordering of the docs will be consistent.  
 397 |          If you want different psuedo-random orderings of documents,
 398 |          for the same version of the index, use a dynamicField and
 399 |          change the field name in the request.
 400 |      -->
 401 |     <fieldType name="random" class="solr.RandomSortField" indexed="true" />
 402 | 
 403 |     <!-- solr.TextField allows the specification of custom text analyzers
 404 |          specified as a tokenizer and a list of token filters. Different
 405 |          analyzers may be specified for indexing and querying.
 406 | 
 407 |          The optional positionIncrementGap puts space between multiple fields of
 408 |          this type on the same document, with the purpose of preventing false phrase
 409 |          matching across fields.
 410 | 
 411 |          For more info on customizing your analyzer chain, please see
 412 |          http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
 413 |      -->
 414 | 
 415 |     <!-- One can also specify an existing Analyzer class that has a
 416 |          default constructor via the class attribute on the analyzer element.
 417 |          Example:
 418 |     <fieldType name="text_greek" class="solr.TextField">
 419 |       <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
 420 |     </fieldType>
 421 |     -->
 422 | 
 423 |     <!-- A text field that only splits on whitespace for exact matching of words -->
 424 |     <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
 425 |       <analyzer>
 426 |         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
 427 |       </analyzer>
 428 |     </fieldType>
 429 | 
 430 |     <!-- A general text field that has reasonable, generic
 431 |          cross-language defaults: it tokenizes with StandardTokenizer,
 432 | 	 removes stop words from case-insensitive "stopwords.txt"
 433 | 	 (empty by default), and down cases.  At query time only, it
 434 | 	 also applies synonyms. -->
 435 |     <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
 436 |       <analyzer type="index">
 437 |         <tokenizer class="solr.StandardTokenizerFactory"/>
 438 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
 439 |         <!-- in this example, we will only use synonyms at query time
 440 |         <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
 441 |         -->
 442 |         <filter class="solr.LowerCaseFilterFactory"/>
 443 |       </analyzer>
 444 |       <analyzer type="query">
 445 |         <tokenizer class="solr.StandardTokenizerFactory"/>
 446 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
 447 |         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
 448 |         <filter class="solr.LowerCaseFilterFactory"/>
 449 |       </analyzer>
 450 |     </fieldType>
 451 | 
 452 |     <!-- A text field with defaults appropriate for English: it
 453 |          tokenizes with StandardTokenizer, removes English stop words
 454 |          (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
 455 |          finally applies Porter's stemming.  The query time analyzer
 456 |          also applies synonyms from synonyms.txt. -->
 457 |     <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
 458 |       <analyzer type="index">
 459 |         <tokenizer class="solr.StandardTokenizerFactory"/>
 460 |         <!-- in this example, we will only use synonyms at query time
 461 |         <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
 462 |         -->
 463 |         <!-- Case insensitive stop word removal.
 464 |         -->
 465 |         <filter class="solr.StopFilterFactory"
 466 |                 ignoreCase="true"
 467 |                 words="lang/stopwords_en.txt"
 468 |                 />
 469 |         <filter class="solr.LowerCaseFilterFactory"/>
 470 | 	<filter class="solr.EnglishPossessiveFilterFactory"/>
 471 |         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
 472 | 	<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
 473 |         <filter class="solr.EnglishMinimalStemFilterFactory"/>
 474 | 	-->
 475 |         <filter class="solr.PorterStemFilterFactory"/>
 476 |       </analyzer>
 477 |       <analyzer type="query">
 478 |         <tokenizer class="solr.StandardTokenizerFactory"/>
 479 |         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
 480 |         <filter class="solr.StopFilterFactory"
 481 |                 ignoreCase="true"
 482 |                 words="lang/stopwords_en.txt"
 483 |                 />
 484 |         <filter class="solr.LowerCaseFilterFactory"/>
 485 | 	<filter class="solr.EnglishPossessiveFilterFactory"/>
 486 |         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
 487 | 	<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
 488 |         <filter class="solr.EnglishMinimalStemFilterFactory"/>
 489 | 	-->
 490 |         <filter class="solr.PorterStemFilterFactory"/>
 491 |       </analyzer>
 492 |     </fieldType>
 493 | 
 494 |     <!-- A text field with defaults appropriate for English, plus
 495 | 	 aggressive word-splitting and autophrase features enabled.
 496 | 	 This field is just like text_en, except it adds
 497 | 	 WordDelimiterFilter to enable splitting and matching of
 498 | 	 words on case-change, alpha numeric boundaries, and
 499 | 	 non-alphanumeric chars.  This means certain compound word
 500 | 	 cases will work, for example query "wi fi" will match
 501 | 	 document "WiFi" or "wi-fi".
 502 |         -->
 503 |     <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
 504 |       <analyzer type="index">
 505 |         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
 506 |         <!-- in this example, we will only use synonyms at query time
 507 |         <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
 508 |         -->
 509 |         <!-- Case insensitive stop word removal.
 510 |         -->
 511 |         <filter class="solr.StopFilterFactory"
 512 |                 ignoreCase="true"
 513 |                 words="lang/stopwords_en.txt"
 514 |                 />
 515 |         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
 516 |         <filter class="solr.LowerCaseFilterFactory"/>
 517 |         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
 518 |         <filter class="solr.PorterStemFilterFactory"/>
 519 |       </analyzer>
 520 |       <analyzer type="query">
 521 |         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
 522 |         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
 523 |         <filter class="solr.StopFilterFactory"
 524 |                 ignoreCase="true"
 525 |                 words="lang/stopwords_en.txt"
 526 |                 />
 527 |         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
 528 |         <filter class="solr.LowerCaseFilterFactory"/>
 529 |         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
 530 |         <filter class="solr.PorterStemFilterFactory"/>
 531 |       </analyzer>
 532 |     </fieldType>
 533 | 
 534 |     <!-- Less flexible matching, but less false matches.  Probably not ideal for product names,
 535 |          but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
 536 |     <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
 537 |       <analyzer>
 538 |         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
 539 |         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
 540 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
 541 |         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
 542 |         <filter class="solr.LowerCaseFilterFactory"/>
 543 |         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
 544 |         <filter class="solr.EnglishMinimalStemFilterFactory"/>
 545 |         <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
 546 |              possible with WordDelimiterFilter in conjuncton with stemming. -->
 547 |         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
 548 |       </analyzer>
 549 |     </fieldType>
 550 | 
 551 |     <!-- Just like text_general except it reverses the characters of
 552 | 	 each token, to enable more efficient leading wildcard queries. -->
 553 |     <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
 554 |       <analyzer type="index">
 555 |         <tokenizer class="solr.StandardTokenizerFactory"/>
 556 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
 557 |         <filter class="solr.LowerCaseFilterFactory"/>
 558 |         <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
 559 |            maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
 560 |       </analyzer>
 561 |       <analyzer type="query">
 562 |         <tokenizer class="solr.StandardTokenizerFactory"/>
 563 |         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
 564 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
 565 |         <filter class="solr.LowerCaseFilterFactory"/>
 566 |       </analyzer>
 567 |     </fieldType>
 568 | 
 569 |     <!-- charFilter + WhitespaceTokenizer  -->
 570 |     <!--
 571 |     <fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" >
 572 |       <analyzer>
 573 |         <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
 574 |         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
 575 |       </analyzer>
 576 |     </fieldType>
 577 |     -->
 578 | 
 579 |     <!-- This is an example of using the KeywordTokenizer along
 580 |          With various TokenFilterFactories to produce a sortable field
 581 |          that does not include some properties of the source text
 582 |       -->
 583 |     <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
 584 |       <analyzer>
 585 |         <!-- KeywordTokenizer does no actual tokenizing, so the entire
 586 |              input string is preserved as a single token
 587 |           -->
 588 |         <tokenizer class="solr.KeywordTokenizerFactory"/>
 589 |         <!-- The LowerCase TokenFilter does what you expect, which can be
 590 |              when you want your sorting to be case insensitive
 591 |           -->
 592 |         <filter class="solr.LowerCaseFilterFactory" />
 593 |         <!-- The TrimFilter removes any leading or trailing whitespace -->
 594 |         <filter class="solr.TrimFilterFactory" />
 595 |         <!-- The PatternReplaceFilter gives you the flexibility to use
 596 |              Java Regular expression to replace any sequence of characters
 597 |              matching a pattern with an arbitrary replacement string, 
 598 |              which may include back references to portions of the original
 599 |              string matched by the pattern.
 600 |              
 601 |              See the Java Regular Expression documentation for more
 602 |              information on pattern and replacement string syntax.
 603 |              
 604 |              http://java.sun.com/j2se/1.6.0/docs/api/java/util/regex/package-summary.html
 605 |           -->
 606 |         <filter class="solr.PatternReplaceFilterFactory"
 607 |                 pattern="([^a-z])" replacement="" replace="all"
 608 |         />
 609 |       </analyzer>
 610 |     </fieldType>
 611 |     
 612 |     <fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
 613 |       <analyzer>
 614 |         <tokenizer class="solr.StandardTokenizerFactory"/>
 615 |         <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
 616 |       </analyzer>
 617 |     </fieldtype>
 618 | 
 619 |     <fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" >
 620 |       <analyzer>
 621 |         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
 622 |         <!--
 623 |         The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
 624 |         a token of "foo|1.4"  would be indexed as "foo" with a payload of 1.4f
 625 |         Attributes of the DelimitedPayloadTokenFilterFactory : 
 626 |          "delimiter" - a one character delimiter. Default is | (pipe)
 627 | 	 "encoder" - how to encode the following value into a playload
 628 | 	    float -> org.apache.lucene.analysis.payloads.FloatEncoder,
 629 | 	    integer -> o.a.l.a.p.IntegerEncoder
 630 | 	    identity -> o.a.l.a.p.IdentityEncoder
 631 |             Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
 632 |          -->
 633 |         <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
 634 |       </analyzer>
 635 |     </fieldtype>
 636 | 
 637 |     <!-- lowercases the entire field value, keeping it as a single token.  -->
 638 |     <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
 639 |       <analyzer>
 640 |         <tokenizer class="solr.KeywordTokenizerFactory"/>
 641 |         <filter class="solr.LowerCaseFilterFactory" />
 642 |       </analyzer>
 643 |     </fieldType>
 644 | 
 645 |     <!-- 
 646 |       Example of using PathHierarchyTokenizerFactory at index time, so
 647 |       queries for paths match documents at that path, or in descendent paths
 648 |     -->
 649 |     <fieldType name="descendent_path" class="solr.TextField">
 650 |       <analyzer type="index">
 651 | 	<tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
 652 |       </analyzer>
 653 |       <analyzer type="query">
 654 | 	<tokenizer class="solr.KeywordTokenizerFactory" />
 655 |       </analyzer>
 656 |     </fieldType>
 657 |     <!-- 
 658 |       Example of using PathHierarchyTokenizerFactory at query time, so
 659 |       queries for paths match documents at that path, or in ancestor paths
 660 |     -->
 661 |     <fieldType name="ancestor_path" class="solr.TextField">
 662 |       <analyzer type="index">
 663 | 	<tokenizer class="solr.KeywordTokenizerFactory" />
 664 |       </analyzer>
 665 |       <analyzer type="query">
 666 | 	<tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
 667 |       </analyzer>
 668 |     </fieldType>
 669 | 
 670 |     <!-- since fields of this type are by default not stored or indexed,
 671 |          any data added to them will be ignored outright.  --> 
 672 |     <fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
 673 | 
 674 |     <!-- This point type indexes the coordinates as separate fields (subFields)
 675 |       If subFieldType is defined, it references a type, and a dynamic field
 676 |       definition is created matching *___<typename>.  Alternately, if 
 677 |       subFieldSuffix is defined, that is used to create the subFields.
 678 |       Example: if subFieldType="double", then the coordinates would be
 679 |         indexed in fields myloc_0___double,myloc_1___double.
 680 |       Example: if subFieldSuffix="_d" then the coordinates would be indexed
 681 |         in fields myloc_0_d,myloc_1_d
 682 |       The subFields are an implementation detail of the fieldType, and end
 683 |       users normally should not need to know about them.
 684 |      -->
 685 |     <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
 686 | 
 687 |     <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
 688 |     <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
 689 | 
 690 |     <!-- An alternative geospatial field type new to Solr 4.  It supports multiValued and polygon shapes.
 691 |       For more information about this and other Spatial fields new to Solr 4, see:
 692 |       http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
 693 |     -->
 694 |     <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
 695 |         geo="true" distErrPct="0.025" maxDistErr="0.000009" units="degrees" />
 696 | 
 697 |    <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
 698 |         Parameters:
 699 |           defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
 700 |           precisionStep:   Specifies the precisionStep for the TrieLong field used for the amount
 701 |           providerClass:   Lets you plug in other exchange provider backend:
 702 |                            solr.FileExchangeRateProvider is the default and takes one parameter:
 703 |                              currencyConfig: name of an xml file holding exchange rates
 704 |                            solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org:
 705 |                              ratesFileLocation: URL or path to rates JSON file (default latest.json on the web)
 706 |                              refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60)
 707 |    -->
 708 |     <fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />
 709 |              
 710 | 
 711 | 
 712 |    <!-- some examples for different languages (generally ordered by ISO code) -->
 713 | 
 714 |     <!-- Arabic -->
 715 |     <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
 716 |       <analyzer> 
 717 |         <tokenizer class="solr.StandardTokenizerFactory"/>
 718 |         <!-- for any non-arabic -->
 719 |         <filter class="solr.LowerCaseFilterFactory"/>
 720 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" />
 721 |         <!-- normalizes ﻯ to ﻱ, etc -->
 722 |         <filter class="solr.ArabicNormalizationFilterFactory"/>
 723 |         <filter class="solr.ArabicStemFilterFactory"/>
 724 |       </analyzer>
 725 |     </fieldType>
 726 | 
 727 |     <!-- Added to verify upgrade tooling -->
 728 |     <fieldType name="text_bm" class="solr.TextField" positionIncrementGap="100">
 729 |       <analyzer>
 730 |         <tokenizer class="solr.StandardTokenizerFactory"/>
 731 |         <filter class="solr.BeiderMorseFilterFactory"
 732 |                 nameType="GENERIC" ruleType="APPROX" 
 733 |                 concat="true" languageSet="auto">
 734 |         </filter>
 735 |       </analyzer>
 736 |     </fieldType>
 737 | 
 738 |     <!-- Bulgarian -->
 739 |     <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
 740 |       <analyzer> 
 741 |         <tokenizer class="solr.StandardTokenizerFactory"/> 
 742 |         <filter class="solr.LowerCaseFilterFactory"/>
 743 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" /> 
 744 |         <filter class="solr.BulgarianStemFilterFactory"/>       
 745 |       </analyzer>
 746 |     </fieldType>
 747 |     
 748 |     <!-- Catalan -->
 749 |     <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
 750 |       <analyzer> 
 751 |         <tokenizer class="solr.StandardTokenizerFactory"/>
 752 |         <!-- removes l', etc -->
 753 |         <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
 754 |         <filter class="solr.LowerCaseFilterFactory"/>
 755 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" />
 756 |         <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>       
 757 |       </analyzer>
 758 |     </fieldType>
 759 |     
 760 |     <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
 761 |     <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
 762 |       <analyzer>
 763 |         <tokenizer class="solr.StandardTokenizerFactory"/>
 764 |         <!-- normalize width before bigram, as e.g. half-width dakuten combine  -->
 765 |         <filter class="solr.CJKWidthFilterFactory"/>
 766 |         <!-- for any non-CJK -->
 767 |         <filter class="solr.LowerCaseFilterFactory"/>
 768 |         <filter class="solr.CJKBigramFilterFactory"/>
 769 |       </analyzer>
 770 |     </fieldType>
 771 | 
 772 |     <!-- Czech -->
 773 |     <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
 774 |       <analyzer> 
 775 |         <tokenizer class="solr.StandardTokenizerFactory"/>
 776 |         <filter class="solr.LowerCaseFilterFactory"/>
 777 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" />
 778 |         <filter class="solr.CzechStemFilterFactory"/>       
 779 |       </analyzer>
 780 |     </fieldType>
 781 |     
 782 |     <!-- Danish -->
 783 |     <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
 784 |       <analyzer> 
 785 |         <tokenizer class="solr.StandardTokenizerFactory"/>
 786 |         <filter class="solr.LowerCaseFilterFactory"/>
 787 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" />
 788 |         <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>       
 789 |       </analyzer>
 790 |     </fieldType>
 791 |     
 792 |     <!-- German -->
 793 |     <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
 794 |       <analyzer> 
 795 |         <tokenizer class="solr.StandardTokenizerFactory"/>
 796 |         <filter class="solr.LowerCaseFilterFactory"/>
 797 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" />
 798 |         <filter class="solr.GermanNormalizationFilterFactory"/>
 799 |         <filter class="solr.GermanLightStemFilterFactory"/>
 800 |         <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
 801 |         <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
 802 |       </analyzer>
 803 |     </fieldType>
 804 |     
 805 |     <!-- Greek -->
 806 |     <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
 807 |       <analyzer> 
 808 |         <tokenizer class="solr.StandardTokenizerFactory"/>
 809 |         <!-- greek specific lowercase for sigma -->
 810 |         <filter class="solr.GreekLowerCaseFilterFactory"/>
 811 |         <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" />
 812 |         <filter class="solr.GreekStemFilterFactory"/>
 813 |       </analyzer>
 814 |     </fieldType>
 815 |     
 816 |     <!-- Spanish -->
 817 |     <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
 818 |       <analyzer> 
 819 |         <tokenizer class="solr.StandardTokenizerFactory"/>
 820 |         <filter class="solr.LowerCaseFilterFactory"/>
 821 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" />
 822 |         <filter class="solr.SpanishLightStemFilterFactory"/>
 823 |         <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
 824 |       </analyzer>
 825 |     </fieldType>
 826 |     
 827 |     <!-- Basque -->
 828 |     <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
 829 |       <analyzer> 
 830 |         <tokenizer class="solr.StandardTokenizerFactory"/>
 831 |         <filter class="solr.LowerCaseFilterFactory"/>
 832 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" />
 833 |         <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
 834 |       </analyzer>
 835 |     </fieldType>
 836 |     
 837 |     <!-- Persian -->
 838 |     <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
 839 |       <analyzer>
 840 |         <!-- for ZWNJ -->
 841 |         <charFilter class="solr.PersianCharFilterFactory"/>
 842 |         <tokenizer class="solr.StandardTokenizerFactory"/>
 843 |         <filter class="solr.LowerCaseFilterFactory"/>
 844 |         <filter class="solr.ArabicNormalizationFilterFactory"/>
 845 |         <filter class="solr.PersianNormalizationFilterFactory"/>
 846 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" />
 847 |       </analyzer>
 848 |     </fieldType>
 849 |     
 850 |     <!-- Finnish -->
 851 |     <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
 852 |       <analyzer> 
 853 |         <tokenizer class="solr.StandardTokenizerFactory"/>
 854 |         <filter class="solr.LowerCaseFilterFactory"/>
 855 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" />
 856 |         <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
 857 |         <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
 858 |       </analyzer>
 859 |     </fieldType>
 860 |     
 861 |     <!-- French -->
 862 |     <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
 863 |       <analyzer> 
 864 |         <tokenizer class="solr.StandardTokenizerFactory"/>
 865 |         <!-- removes l', etc -->
 866 |         <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
 867 |         <filter class="solr.LowerCaseFilterFactory"/>
 868 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" />
 869 |         <filter class="solr.FrenchLightStemFilterFactory"/>
 870 |         <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
 871 |         <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
 872 |       </analyzer>
 873 |     </fieldType>
 874 |     
 875 |     <!-- Irish -->
 876 |     <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
 877 |       <analyzer> 
 878 |         <tokenizer class="solr.StandardTokenizerFactory"/>
 879 |         <!-- removes d', etc -->
 880 |         <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
 881 |         <!-- removes n-, etc. position increments is intentionally false! -->
 882 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt"/>
 883 |         <filter class="solr.IrishLowerCaseFilterFactory"/>
 884 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt"/>
 885 |         <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
 886 |       </analyzer>
 887 |     </fieldType>
 888 |     
 889 |     <!-- Galician -->
 890 |     <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
 891 |       <analyzer> 
 892 |         <tokenizer class="solr.StandardTokenizerFactory"/>
 893 |         <filter class="solr.LowerCaseFilterFactory"/>
 894 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" />
 895 |         <filter class="solr.GalicianStemFilterFactory"/>
 896 |         <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
 897 |       </analyzer>
 898 |     </fieldType>
 899 |     
 900 |     <!-- Hindi -->
 901 |     <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
 902 |       <analyzer> 
 903 |         <tokenizer class="solr.StandardTokenizerFactory"/>
 904 |         <filter class="solr.LowerCaseFilterFactory"/>
 905 |         <!-- normalizes unicode representation -->
 906 |         <filter class="solr.IndicNormalizationFilterFactory"/>
 907 |         <!-- normalizes variation in spelling -->
 908 |         <filter class="solr.HindiNormalizationFilterFactory"/>
 909 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" />
 910 |         <filter class="solr.HindiStemFilterFactory"/>
 911 |       </analyzer>
 912 |     </fieldType>
 913 |     
 914 |     <!-- Hungarian -->
 915 |     <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
 916 |       <analyzer> 
 917 |         <tokenizer class="solr.StandardTokenizerFactory"/>
 918 |         <filter class="solr.LowerCaseFilterFactory"/>
 919 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" />
 920 |         <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
 921 |         <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->   
 922 |       </analyzer>
 923 |     </fieldType>
 924 |     
 925 |     <!-- Armenian -->
 926 |     <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
 927 |       <analyzer> 
 928 |         <tokenizer class="solr.StandardTokenizerFactory"/>
 929 |         <filter class="solr.LowerCaseFilterFactory"/>
 930 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" />
 931 |         <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
 932 |       </analyzer>
 933 |     </fieldType>
 934 |     
 935 |     <!-- Indonesian -->
 936 |     <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
 937 |       <analyzer> 
 938 |         <tokenizer class="solr.StandardTokenizerFactory"/>
 939 |         <filter class="solr.LowerCaseFilterFactory"/>
 940 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" />
 941 |         <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
 942 |         <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
 943 |       </analyzer>
 944 |     </fieldType>
 945 |     
 946 |     <!-- Italian -->
 947 |     <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
 948 |       <analyzer> 
 949 |         <tokenizer class="solr.StandardTokenizerFactory"/>
 950 |         <!-- removes l', etc -->
 951 |         <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
 952 |         <filter class="solr.LowerCaseFilterFactory"/>
 953 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" />
 954 |         <filter class="solr.ItalianLightStemFilterFactory"/>
 955 |         <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
 956 |       </analyzer>
 957 |     </fieldType>
 958 |     
 959 |     <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
 960 | 
 961 |          NOTE: If you want to optimize search for precision, use default operator AND in your query
 962 |          parser config with <solrQueryParser defaultOperator="AND"/> further down in this file.  Use 
 963 |          OR if you would like to optimize for recall (default).
 964 |     -->
 965 |     <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
 966 |       <analyzer>
 967 |       <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
 968 | 
 969 |            Kuromoji has a search mode (default) that does segmentation useful for search.  A heuristic
 970 |            is used to segment compounds into its parts and the compound itself is kept as synonym.
 971 | 
 972 |            Valid values for attribute mode are:
 973 |               normal: regular segmentation
 974 |               search: segmentation useful for search with synonyms compounds (default)
 975 |             extended: same as search mode, but unigrams unknown words (experimental)
 976 | 
 977 |            For some applications it might be good to use search mode for indexing and normal mode for
 978 |            queries to reduce recall and prevent parts of compounds from being matched and highlighted.
 979 |            Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.
 980 | 
 981 |            Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
 982 |            model with your own entries for segmentation, part-of-speech tags and readings without a need
 983 |            to specify weights.  Notice that user dictionaries have not been subject to extensive testing.
 984 | 
 985 |            User dictionary attributes are:
 986 |                      userDictionary: user dictionary filename
 987 |              userDictionaryEncoding: user dictionary encoding (default is UTF-8)
 988 | 
 989 |            See lang/userdict_ja.txt for a sample user dictionary file.
 990 | 
 991 |            Punctuation characters are discarded by default.  Use discardPunctuation="false" to keep them.
 992 | 
 993 |            See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
 994 |         -->
 995 |         <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
 996 |         <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
 997 |         <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
 998 |         <filter class="solr.JapaneseBaseFormFilterFactory"/>
 999 |         <!-- Removes tokens with certain part-of-speech tags -->
1000 |         <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
1001 |         <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
1002 |         <filter class="solr.CJKWidthFilterFactory"/>
1003 |         <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
1004 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" />
1005 |         <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
1006 |         <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
1007 |         <!-- Lower-cases romaji characters -->
1008 |         <filter class="solr.LowerCaseFilterFactory"/>
1009 |       </analyzer>
1010 |     </fieldType>
1011 |     
1012 |     <!-- Latvian -->
1013 |     <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
1014 |       <analyzer> 
1015 |         <tokenizer class="solr.StandardTokenizerFactory"/>
1016 |         <filter class="solr.LowerCaseFilterFactory"/>
1017 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" />
1018 |         <filter class="solr.LatvianStemFilterFactory"/>
1019 |       </analyzer>
1020 |     </fieldType>
1021 |     
1022 |     <!-- Dutch -->
1023 |     <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
1024 |       <analyzer> 
1025 |         <tokenizer class="solr.StandardTokenizerFactory"/>
1026 |         <filter class="solr.LowerCaseFilterFactory"/>
1027 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" />
1028 |         <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
1029 |         <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
1030 |       </analyzer>
1031 |     </fieldType>
1032 |     
1033 |     <!-- Norwegian -->
1034 |     <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
1035 |       <analyzer> 
1036 |         <tokenizer class="solr.StandardTokenizerFactory"/>
1037 |         <filter class="solr.LowerCaseFilterFactory"/>
1038 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" />
1039 |         <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
1040 |         <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory" variant="nb"/> -->
1041 |         <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory" variant="nb"/> -->
1042 |         <!-- The "light" and "minimal" stemmers support variants: nb=Bokmål, nn=Nynorsk, no=Both -->
1043 |       </analyzer>
1044 |     </fieldType>
1045 |     
1046 |     <!-- Portuguese -->
1047 |     <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
1048 |       <analyzer> 
1049 |         <tokenizer class="solr.StandardTokenizerFactory"/>
1050 |         <filter class="solr.LowerCaseFilterFactory"/>
1051 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" />
1052 |         <filter class="solr.PortugueseLightStemFilterFactory"/>
1053 |         <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
1054 |         <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
1055 |         <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
1056 |       </analyzer>
1057 |     </fieldType>
1058 |     
1059 |     <!-- Romanian -->
1060 |     <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
1061 |       <analyzer> 
1062 |         <tokenizer class="solr.StandardTokenizerFactory"/>
1063 |         <filter class="solr.LowerCaseFilterFactory"/>
1064 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" />
1065 |         <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
1066 |       </analyzer>
1067 |     </fieldType>
1068 |     
1069 |     <!-- Russian -->
1070 |     <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
1071 |       <analyzer> 
1072 |         <tokenizer class="solr.StandardTokenizerFactory"/>
1073 |         <filter class="solr.LowerCaseFilterFactory"/>
1074 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
1075 |         <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
1076 |         <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
1077 |       </analyzer>
1078 |     </fieldType>
1079 |     
1080 |     <!-- Swedish -->
1081 |     <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
1082 |       <analyzer> 
1083 |         <tokenizer class="solr.StandardTokenizerFactory"/>
1084 |         <filter class="solr.LowerCaseFilterFactory"/>
1085 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" />
1086 |         <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
1087 |         <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
1088 |       </analyzer>
1089 |     </fieldType>
1090 |     
1091 |     <!-- Thai -->
1092 |     <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
1093 |       <analyzer> 
1094 |         <tokenizer class="solr.StandardTokenizerFactory"/>
1095 |         <filter class="solr.LowerCaseFilterFactory"/>
1096 |         <filter class="solr.ThaiWordFilterFactory"/>
1097 |         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" />
1098 |       </analyzer>
1099 |     </fieldType>
1100 |     
1101 |     <!-- Turkish -->
1102 |     <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
1103 |       <analyzer> 
1104 |         <tokenizer class="solr.StandardTokenizerFactory"/>
1105 |         <filter class="solr.TurkishLowerCaseFilterFactory"/>
1106 |         <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" />
1107 |         <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
1108 |       </analyzer>
1109 |     </fieldType>
1110 | 
1111 |  </types>
1112 |   
1113 |   <!-- Similarity is the scoring routine for each document vs. a query.
1114 |        A custom Similarity or SimilarityFactory may be specified here, but 
1115 |        the default is fine for most applications.  
1116 |        For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
1117 |     -->
1118 |   <!--
1119 |      <similarity class="com.example.solr.CustomSimilarityFactory">
1120 |        <str name="paramkey">param value</str>
1121 |      </similarity>
1122 |     -->
1123 | 
1124 | </schema>
1125 | 


--------------------------------------------------------------------------------