Apache Jackrabbit JCA 2.7.5 .docx 和 .xlsx 索引

Question

我正在使用 Appache Jackrabbit JCA 2.7.5，问题是文件 .docx 和 .xlsx 没有索引。

我的步骤：

在 glassfish

resource adapter

为 resource adapter 创建一个 Connector Connection Pool 表示 ConfigFile=path/to/the/repository.xml 和 HomeDir=path/to/the //miss the repository.xml
为连接器池（jndi）创建一个Connector Resources
创建网络应用程序

创建 class 以从连接器资源（下面的代码）获取会话

import java.io.Serializable;
import java.net.MalformedURLException;
import javax.annotation.Resource;
import javax.ejb.Stateless;
import javax.jcr.LoginException;
import javax.jcr.Repository;
import javax.jcr.RepositoryException;
import javax.jcr.Session;
import javax.jcr.SimpleCredentials;
import javax.naming.InitialContext;
import javax.naming.NamingException;
@Stateless
public class OcmRepository implements Serializable {

    public Repository repository;
    public Session session;

    public OcmRepository() {
    }

    public Session getSession(String log, String mdp) throws LoginException, RepositoryException, NamingException, MalformedURLException {
        InitialContext initalContext = new InitialContext();
        repository = (Repository) initalContext.lookup("jndi/jca");
        session = repository.login(new SimpleCredentials(log, mdp.toCharArray()), null);
        return session;
    }
}

创建自定义文件类型

import javax.jcr.PropertyType;
import javax.jcr.Session;
import javax.jcr.nodetype.NodeType;
import javax.jcr.nodetype.NodeTypeManager;
import javax.jcr.nodetype.NodeTypeTemplate;
import javax.jcr.nodetype.PropertyDefinitionTemplate;

/**
 *
 * @author nathan
 */
public class FileType {
    public static void RegisterFileType(Session session) throws Exception {        
        NodeTypeManager nodeTypeManager = session.getWorkspace().getNodeTypeManager();

        NodeTypeTemplate nodeType = nodeTypeManager.createNodeTypeTemplate();
        nodeType.setName("FileType");
        String[] str = {"nt:resource"};        
        nodeType.setDeclaredSuperTypeNames(str);
        nodeType.setMixin(false);
        nodeType.setQueryable(true);


        PropertyDefinitionTemplate path = nodeTypeManager.createPropertyDefinitionTemplate();
        path.setName("jcr:path");
        path.setRequiredType(PropertyType.PATH);
        path.setQueryOrderable(false);
        path.setFullTextSearchable(false);
        nodeType.getPropertyDefinitionTemplates().add(path);

        PropertyDefinitionTemplate nom = nodeTypeManager.createPropertyDefinitionTemplate();
        nom.setName("jcr:nom");
        nom.setRequiredType(PropertyType.STRING);
        nom.setQueryOrderable(true);
        nom.setFullTextSearchable(true);
        nodeType.getPropertyDefinitionTemplates().add(nom);

        PropertyDefinitionTemplate description = nodeTypeManager.createPropertyDefinitionTemplate();
        description.setName("jcr:description");
        description.setRequiredType(PropertyType.STRING);
        description.setQueryOrderable(true);
        description.setFullTextSearchable(true);
        nodeType.getPropertyDefinitionTemplates().add(description);

        PropertyDefinitionTemplate motsCles = nodeTypeManager.createPropertyDefinitionTemplate();
        motsCles.setName("jcr:motsCles");
        motsCles.setRequiredType(PropertyType.STRING);
        motsCles.setQueryOrderable(true);
        motsCles.setFullTextSearchable(true);
        nodeType.getPropertyDefinitionTemplates().add(motsCles);

        PropertyDefinitionTemplate size = nodeTypeManager.createPropertyDefinitionTemplate();
        size.setName("jcr:size");
        size.setRequiredType(PropertyType.STRING);
        size.setQueryOrderable(true);
        size.setFullTextSearchable(false);
        nodeType.getPropertyDefinitionTemplates().add(size);

        PropertyDefinitionTemplate users = nodeTypeManager.createPropertyDefinitionTemplate();
        users.setName("jcr:users");
        users.setRequiredType(PropertyType.STRING);
        users.setQueryOrderable(true);
        users.setFullTextSearchable(false);
        nodeType.getPropertyDefinitionTemplates().add(users);

        PropertyDefinitionTemplate groupe = nodeTypeManager.createPropertyDefinitionTemplate();
        groupe.setName("jcr:groupe");
        groupe.setRequiredType(PropertyType.STRING);
        groupe.setQueryOrderable(true);
        groupe.setFullTextSearchable(false);
        nodeType.getPropertyDefinitionTemplates().add(groupe);

        NodeType newnodetype = nodeTypeManager.registerNodeType(nodeType, true);             
        session.save();        
    }

}

为持久性创建摘要class

import java.util.ArrayList;
import java.util.List;
import java.util.Map;

import javax.jcr.Session;

import org.apache.jackrabbit.ocm.query.Filter;
import org.apache.jackrabbit.ocm.query.impl.FilterImpl;
import org.apache.jackrabbit.ocm.query.impl.QueryImpl;
import org.apache.jackrabbit.ocm.query.Query;
import org.apache.jackrabbit.ocm.query.QueryManager;

import org.apache.jackrabbit.ocm.manager.ObjectContentManager;
import org.apache.jackrabbit.ocm.manager.impl.ObjectContentManagerImpl;

import org.apache.jackrabbit.ocm.mapper.Mapper;
import org.apache.jackrabbit.ocm.mapper.impl.annotation.AnnotationMapperImpl;

import org.apache.jackrabbit.ocm.reflection.ReflectionUtils;


/**
 *
 * @author nathan
 */
public abstract class AbstractBean<T> {

    private Class<T> entityClass;
    private ObjectContentManager ocm;
    private Mapper mapper;

    public AbstractBean(Class<T> entityClass){
        this.entityClass = entityClass;
    }

    /**
     * Construct the Bean according to the extended class
     * This will be also construct the ObjectContentManager nammed ocm with the default Mapper
     * @param session javax.jcr.Session attached to the Bean
     * @return The mapping class found for the desired java bean class
     */
    public AbstractBean(Class<T> entityClass,Session session){
        this.entityClass = entityClass;
        ocm = new ObjectContentManagerImpl(session, this.getDefaultMapper());
    }

    /**
     * @return ObjectContentManager of the Bean
     */
    public ObjectContentManager getOcm() throws Exception{
        return ocm;
    }

    /**
     * Construct the Bean according to the extended class
     * This will be also construct the ObjectContentManager nammed ocm with the param Mapper given
     * @param session from "javax.jcr.Session" attached to the Bean
     * @param map from "org.apache.jackrabbit.ocm.mapper.Mapper" which 
     * is the use to map entity between apllication and The repository
     * @return ObjectContentManager of the Bean
     */   
    public ObjectContentManager getOcm(Session session, Mapper map) throws Exception{
        return new ObjectContentManagerImpl(session, map);
    }

    public void setOcm(ObjectContentManager ocm) {
        this.ocm = ocm;
    }

    private Mapper getDefaultMapper(){
        ReflectionUtils.setClassLoader(com.ged.ocm.entity.Groupe.class.getClassLoader());
        List<Class> classes = new ArrayList<Class>();
        classes.add(com.ged.ocm.entity.Fichier.class);
        classes.add(com.ged.ocm.entity.Dossier.class);
        classes.add(com.ged.ocm.entity.Groupe.class);
        classes.add(com.ged.ocm.entity.SimpleNode.class);
        return new AnnotationMapperImpl(classes);
    }

    public Mapper getMapper() {
        return mapper;
    }

    public void setMapper(Mapper mapper) {
        this.mapper = mapper;
    }

    public void setLoader(Class classe){        
        ReflectionUtils.setClassLoader(classe.getClassLoader());
    }

    public void create(T entity) {
        ocm.insert(entity);
        ocm.save();
    }

    public void edit(T entity) {
        ocm.update(entity);
        ocm.save();
    }

    public void remove(T entity) {
        ocm.remove(entity);
        ocm.save();
    }

    public void refresh(){
        ocm.refresh(true);
        ocm.save();
    }

    public void copy(String orgPath, String destPath){
        ocm.copy(orgPath, destPath);
        ocm.save();
    }

    public void move(String orgPath, String destPath){
        ocm.move(orgPath, destPath);
        ocm.save();
    }
    public void removeByPath(String path) {
        ocm.remove(path);
        ocm.save();
    }

    public void removeAllByEqual(Map<String,String> filters){
        QueryManager queryManager = ocm.getQueryManager();

        Filter filter;
        filter = queryManager.createFilter(entityClass);
        for (String key : filters.keySet())filter.addEqualTo(key, filters.get(key));

        Query query = queryManager.createQuery(filter);

        ocm.remove(query);
        ocm.save();
    }

    public void removeAllByEqual(String nodePath,Map<String,String> filters){
        QueryManager queryManager = ocm.getQueryManager();

        Filter filter;
        filter = queryManager.createFilter(entityClass);
        filter.setScope(nodePath);
        for (String key : filters.keySet())filter.addEqualTo(key, filters.get(key));

        Query query = queryManager.createQuery(filter);

        ocm.remove(query);
        ocm.save();
    }

    public boolean isPathExist(String path){
        return ocm.objectExists(path);
    }

    public T findByPath(String path) {
        try {            
            return (T)ocm.getObject(path);
        } catch (Exception e) {
            return null;
        }
    }

    public T findOneByEqual(Map<String,String> filters){
        QueryManager queryManager = ocm.getQueryManager();

        Filter filter;
        filter = queryManager.createFilter(entityClass);
        for (String key : filters.keySet())filter.addEqualTo(key, filters.get(key));

        Query query = queryManager.createQuery(filter);

        List<T> results = (List<T>) ocm.getObjects(query);

        T result = null;
        try {            
            result = results.get(0);
        } catch (Exception e) {
        }

        return result;
    }

    public List<T> findAllByEqual(Map<String,String> filters){
        QueryManager queryManager = ocm.getQueryManager();

        Filter filter;
        filter = queryManager.createFilter(entityClass);
        filter.setScope("//");
        for (String key : filters.keySet())filter.addEqualTo(key, filters.get(key));

        Query query = queryManager.createQuery(filter);

        List<T> results = (List<T>) ocm.getObjects(query);
        return results;
    }


    public List<T> findAllByLike(Map<String,String> filters){
        QueryManager queryManager = ocm.getQueryManager();

        Filter filter;
        filter = queryManager.createFilter(entityClass);
        filter.setScope("//");
        for (String key : filters.keySet())filter.addLike(key, filters.get(key));

        Query query = queryManager.createQuery(filter);

        List<T> results = (List<T>) ocm.getObjects(query);
        return results;
    }

    public List<T> findAllByLikeScoped(String scope,Map<String,String> filters){
        QueryManager queryManager = ocm.getQueryManager();

        Filter filter;
        filter = queryManager.createFilter(entityClass);
        filter.setScope(scope);
        for (String key : filters.keySet())filter.addLike(key, filters.get(key));

        Query query = queryManager.createQuery(filter);

        List<T> results = (List<T>) ocm.getObjects(query);
        return results;
    }

    public List<T> findAllByOrLike(String attr,String[] val){
        QueryManager queryManager = ocm.getQueryManager();

        Filter filter;
        filter = queryManager.createFilter(entityClass);
        filter.setScope("//");
        filter.addOrFilter(attr, val);

        Query query = queryManager.createQuery(filter);

        List<T> results = (List<T>) ocm.getObjects(query);
        return results;
    }

    public T findOneByEqual(String nodePath, Map<String,String> filters){
        QueryManager queryManager = ocm.getQueryManager();

        Filter filter;
        filter = queryManager.createFilter(entityClass);
        filter.setScope(nodePath);
        for (String key : filters.keySet())filter.addEqualTo(key, filters.get(key));

        Query query = queryManager.createQuery(filter);

        List<T> results = (List<T>) ocm.getObjects(query);
        T result = results.get(0);
        return result;
    }

    public List<T> findAllByEqual(String nodePath, Map<String,String> filters){
        QueryManager queryManager = ocm.getQueryManager();

        Filter filter;
        filter = queryManager.createFilter(entityClass);
        filter.setScope(nodePath);
        for (String key : filters.keySet())filter.addEqualTo(key, filters.get(key));

        Query query = queryManager.createQuery(filter);

        List<T> results = (List<T>) ocm.getObjects(query);
        return results;
    }

    public List<T> findAllByString(String query){        
        List<T> results = (List<T>) ocm.getObjects(query,javax.jcr.query.Query.JCR_SQL2);
        return results;
    } 


    public List<T> findAllByParentPath(String nodePath){
        QueryManager queryManager = ocm.getQueryManager();

        Filter filter;
        filter = queryManager.createFilter(entityClass);
        filter.setScope(nodePath);

        Query query = queryManager.createQuery(filter);
        List<T> results = (List<T>) ocm.getObjects(query);
        return results;

    }
    public List<T> findAllByParentPathOrder(String nodePath, String ordering){
        QueryManager queryManager = ocm.getQueryManager();

        Filter filter;
        filter = queryManager.createFilter(entityClass);
        filter.setScope(nodePath);

        Query query = queryManager.createQuery(filter);
//        query.addOrderByDescending(ordering);
        query.addOrderByAscending(ordering);

        List<T> results = (List<T>) ocm.getObjects(query);
        return results;

    }

    public int coutChild(String nodePath){
        QueryManager queryManager = ocm.getQueryManager();

        Filter filter;
        filter = queryManager.createFilter(entityClass);
        filter.setScope(nodePath);

        Query query = queryManager.createQuery(filter);

        List<T> results = (List<T>) ocm.getObjects(query);
        return results.size();
    }

    public boolean ifExistByPath(String path){
        return ocm.objectExists(path);
    }

    public String getParentPath(String path){
        String parent="";
        String[] tmp=path.split("/");
        for (int i = 1; i < (tmp.length-1); i++) {
            parent+="/"+tmp[i];
        }
        return parent;                
    }
}

创建 bean

import javax.ejb.Stateless;
import com.ged.ocm.entity.Fichier;
import java.io.InputStream;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;
import javax.jcr.Node;
import javax.jcr.NodeIterator;
import javax.jcr.Session;
import javax.jcr.Workspace;
import javax.jcr.query.QueryResult;
import javax.jcr.query.qom.FullTextSearch;
import javax.jcr.query.qom.StaticOperand;
import org.apache.jackrabbit.ocm.query.Filter;
import org.apache.jackrabbit.ocm.query.Query;
import org.apache.jackrabbit.ocm.query.QueryManager;

@Stateless
public class FichierBean extends AbstractBean<Fichier>{    
    public FichierBean() {
        super(Fichier.class);
    }
    public FichierBean(Session session) {
        super(Fichier.class,session);
    }

    public List<Fichier> findAllByContains(String motCles) throws Exception {
        String requette = "SELECT * FROM FileType AS Res WHERE CONTAINS (Res.*, '*"+motCles+"*')";
        List<Fichier> results = (List<Fichier>) this.getOcm().getObjects(requette, javax.jcr.query.Query.JCR_SQL2);
        return results;                
    }
    public List<Fichier> findAllByContains(String path,String motCles) throws Exception {
        String requette = "SELECT * FROM FileType AS Res WHERE CONTAINS (Res.*, '*"+motCles+"*') ORDER BY Res.nom";
        List<Fichier> tmp = (List<Fichier>) this.getOcm().getObjects(requette, javax.jcr.query.Query.JCR_SQL2);

        List<Fichier> results = new ArrayList<Fichier>();
        for (Fichier fichier : tmp) {
            if(fichier.getPath().startsWith(path))results.add(fichier);
        }
        return results;                
    }


    public List<Fichier> fulltextByOCM(String motCles) throws Exception {
        QueryManager queryManager = this.getOcm().getQueryManager();

        Filter filter;
        filter = queryManager.createFilter(com.ged.ocm.entity.Fichier.class);
        filter.addContains(".", "*"+motCles+"*");

        Query query = queryManager.createQuery(filter);

        List<Fichier> results = (List<Fichier>) this.getOcm().getObjects(query);
        return results;
    }

}

我的配置文件：

repository.xml

<?xml version="1.0"?>
<!DOCTYPE Repository PUBLIC "-//The Apache Software Foundation//DTD Jackrabbit 1.6//EN"
                        "http://jackrabbit.apache.org/dtd/repository-1.6.dtd">
<Repository>        
<FileSystem class="org.apache.jackrabbit.core.fs.local.LocalFileSystem">
    <param name="path" value="${rep.home}/repository"/>
</FileSystem>
-->

<FileSystem class="org.apache.jackrabbit.core.fs.db.DbFileSystem">
    <param name="driver" value="com.mysql.jdbc.jdbc2.optional.MysqlDataSource"/>
    <param name="url" value="jdbc:mysql://:3306/db_ged_mysql" />
    <param name="user" value="root" />
    <param name="password" value="root" />
    <param name="schema" value="mysql"/>
    <param name="schemaObjectPrefix" value="J_R_FS_"/>
</FileSystem>

<!--
    security configuration
-->
<Security appName="Jackrabbit">
    <AccessManager class="org.apache.jackrabbit.core.security.SimpleAccessManager" />
    <LoginModule class="org.apache.jackrabbit.core.security.SimpleLoginModule">
        <param name="anonymousId" value="anonymous" />
    </LoginModule>
</Security>

<!--
    location of workspaces root directory and name of default workspace
-->
<Workspaces rootPath="${rep.home}/workspaces" defaultWorkspace="default"/>
<!--
    workspace configuration template:
    used to create the initial workspace if there's no workspace yet
-->
<Workspace name="${wsp.name}">

    <PersistenceManager class="org.apache.jackrabbit.core.state.db.SimpleDbPersistenceManager">
        <param name="driver" value="com.mysql.jdbc.jdbc2.optional.MysqlDataSource"/>
        <param name="url" value="jdbc:mysql://:3306/db_ged_mysql" />
        <param name="user" value="root" />
        <param name="password" value="root" />
        <param name="schema" value="mysql" />
        <param name="schemaObjectPrefix" value="J_PM_${wsp.name}_" />
        <param name="externalBLOBs" value="false" />
    </PersistenceManager>
    <FileSystem class="org.apache.jackrabbit.core.fs.db.DbFileSystem">
        <param name="driver" value="com.mysql.jdbc.jdbc2.optional.MysqlDataSource"/>
        <param name="url" value="jdbc:mysql://:3306/db_ged_mysql" />
        <param name="user" value="root" />
        <param name="password" value="root" />
        <param name="schema" value="mysql"/>
        <param name="schemaObjectPrefix" value="J_FS_${wsp.name}_"/>
    </FileSystem>

    <!--
        Search index and the file system it uses.
        class: FQN of class implementing the QueryHandler interface
    -->
    <SearchIndex class="org.apache.jackrabbit.core.query.lucene.SearchIndex">
        <param name="path" value="${rep.home}/workspaces/${wsp.name}/index"/>
        <param name="tikaConfigPath" value="${rep.home}/tika-config.xml"/>
        <param name="useCompoundFile" value="true"/>
        <param name="minMergeDocs" value="100"/>
        <param name="volatileIdleTime" value="3"/>
        <param name="maxMergeDocs" value="2147483647"/>
        <param name="mergeFactor" value="10"/>
        <param name="maxFieldLength" value="10000"/>
        <param name="bufferSize" value="10"/>
        <param name="cacheSize" value="1000"/>
        <param name="forceConsistencyCheck" value="false"/>
        <param name="enableConsistencyCheck" value="false"/>
        <param name="autoRepair" value="true"/>
        <param name="analyzer" value="org.apache.lucene.analysis.standard.StandardAnalyzer"/>
        <param name="queryClass" value="org.apache.jackrabbit.core.query.QueryImpl"/>
        <param name="respectDocumentOrder" value="true"/>
        <param name="resultFetchSize" value="2147483647"/>
        <param name="extractorPoolSize" value="0"/>
        <param name="extractorTimeout" value="100"/>
        <param name="extractorBackLogSize" value="100"/>
        <param name="supportHighlighting" value="true"/>
        <param name="excerptProviderClass" value="org.apache.jackrabbit.core.query.lucene.DefaultXMLExcerpt"/>
    </SearchIndex>
</Workspace>

<!--
    Configures the versioning
-->
<Versioning rootPath="${rep.home}/version">
    <FileSystem class="org.apache.jackrabbit.core.fs.db.DbFileSystem">
        <param name="driver" value="com.mysql.jdbc.jdbc2.optional.MysqlDataSource"/>
        <param name="url" value="jdbc:mysql://:3306/db_ged_mysql" />
        <param name="user" value="root" />
        <param name="password" value="root" />
        <param name="schema" value="mysql"/>
        <param name="schemaObjectPrefix" value="J_V_FS_"/>
    </FileSystem>
    <PersistenceManager class="org.apache.jackrabbit.core.state.db.SimpleDbPersistenceManager">
        <param name="driver" value="com.mysql.jdbc.jdbc2.optional.MysqlDataSource"/>
        <param name="url" value="jdbc:mysql://:3306/db_ged_mysql" />
        <param name="user" value="root" />
        <param name="password" value="root" />
        <param name="schema" value="mysql" />
        <param name="schemaObjectPrefix" value="J_V_PM_" />
        <param name="externalBLOBs" value="false" />
    </PersistenceManager>
</Versioning>

<!--
    Search index for content that is shared repository wide
    (/jcr:system tree, contains mainly versions)

<SearchIndex class="org.apache.jackrabbit.core.query.lucene.SearchIndex">
    <param name="path" value="${rep.home}/repository/index"/>
    <param name="extractorPoolSize" value="2"/>
    <param name="supportHighlighting" value="true"/>
</SearchIndex>
-->

<!--
    Cluster configuration with system variables.

-->

<RepositoryLockMechanism class="org.apache.jackrabbit.core.util.CooperativeFileLock" />

</Repository>

蒂卡-config.xml

<?xml version="1.0" encoding="UTF-8"?>
<properties>

<mimeTypeRepository resource="/org/apache/tika/mime/tika-mimetypes.xml" magic="false"/>

<parsers>

<parser name="parse-dcxml" class="org.apache.tika.parser.xml.DcXMLParser">
  <mime>application/xml</mime>
  <mime>image/svg+xml</mime>
</parser>

<parser name="parse-office" class="org.apache.tika.parser.microsoft.OfficeParser">
  <mime>application/x-tika-msoffice</mime>
  <mime>application/msword</mime>
  <mime>application/vnd.ms-excel</mime>
  <mime>application/vnd.ms-excel.sheet.binary.macroenabled.12</mime>
  <mime>application/vnd.ms-powerpoint</mime>
  <mime>application/vnd.visio</mime>
  <mime>application/vnd.ms-outlook</mime>
</parser>

<parser name="parse-ooxml" class="org.apache.tika.parser.microsoft.ooxml.OOXMLParser">
  <mime>application/x-tika-ooxml</mime>
  <mime>application/vnd.openxmlformats-package.core-properties+xml</mime>
  <mime>application/vnd.openxmlformats-officedocument.spreadsheetml.sheet</mime>
  <mime>application/vnd.openxmlformats-officedocument.spreadsheetml.template</mime>
  <mime>application/vnd.ms-excel.sheet.macroenabled.12</mime>
  <mime>application/vnd.ms-excel.template.macroenabled.12</mime>
  <mime>application/vnd.ms-excel.addin.macroenabled.12</mime>
  <mime>application/vnd.openxmlformats-officedocument.presentationml.presentation</mime>
  <mime>application/vnd.openxmlformats-officedocument.presentationml.template</mime>
  <mime>application/vnd.openxmlformats-officedocument.presentationml.slideshow</mime>
  <mime>application/vnd.ms-powerpoint.presentation.macroenabled.12</mime>
  <mime>application/vnd.ms-powerpoint.slideshow.macroenabled.12</mime>
  <mime>application/vnd.ms-powerpoint.addin.macroenabled.12</mime>
  <mime>application/vnd.openxmlformats-officedocument.wordprocessingml.document</mime>
  <mime>application/vnd.openxmlformats-officedocument.wordprocessingml.template</mime>
  <mime>application/vnd.ms-word.document.macroenabled.12</mime>
  <mime>application/vnd.ms-word.template.macroenabled.12</mime>
</parser>

<parser name="parse-html" class="org.apache.tika.parser.html.HtmlParser">
  <mime>text/html</mime>
  <mime>application/xhtml+xml</mime>
  <mime>application/x-asp</mime>
</parser>

<parser mame="parse-rtf" class="org.apache.tika.parser.rtf.RTFParser">
  <mime>application/rtf</mime>
</parser>

<parser name="parse-pdf" class="org.apache.tika.parser.pdf.PDFParser">
  <mime>application/pdf</mime>
</parser>

<parser name="parse-txt" class="org.apache.tika.parser.txt.TXTParser">
  <mime>text/plain</mime>
</parser>

<parser name="parse-openoffice" class="org.apache.tika.parser.opendocument.OpenOfficeParser">
  <mime>application/vnd.sun.xml.writer</mime>
  <mime>application/vnd.oasis.opendocument.text</mime>
  <mime>application/vnd.oasis.opendocument.graphics</mime>
  <mime>application/vnd.oasis.opendocument.presentation</mime>
  <mime>application/vnd.oasis.opendocument.spreadsheet</mime>
  <mime>application/vnd.oasis.opendocument.chart</mime>
  <mime>application/vnd.oasis.opendocument.image</mime>
  <mime>application/vnd.oasis.opendocument.formula</mime>
  <mime>application/vnd.oasis.opendocument.text-master</mime>
  <mime>application/vnd.oasis.opendocument.text-web</mime>
  <mime>application/vnd.oasis.opendocument.text-template</mime>
  <mime>application/vnd.oasis.opendocument.graphics-template</mime>
  <mime>application/vnd.oasis.opendocument.presentation-template</mime>
  <mime>application/vnd.oasis.opendocument.spreadsheet-template</mime>
  <mime>application/vnd.oasis.opendocument.chart-template</mime>
  <mime>application/vnd.oasis.opendocument.image-template</mime>
  <mime>application/vnd.oasis.opendocument.formula-template</mime>
  <mime>application/x-vnd.oasis.opendocument.text</mime>
  <mime>application/x-vnd.oasis.opendocument.graphics</mime>
  <mime>application/x-vnd.oasis.opendocument.presentation</mime>
  <mime>application/x-vnd.oasis.opendocument.spreadsheet</mime>
  <mime>application/x-vnd.oasis.opendocument.chart</mime>
  <mime>application/x-vnd.oasis.opendocument.image</mime>
  <mime>application/x-vnd.oasis.opendocument.formula</mime>
  <mime>application/x-vnd.oasis.opendocument.text-master</mime>
  <mime>application/x-vnd.oasis.opendocument.text-web</mime>
  <mime>application/x-vnd.oasis.opendocument.text-template</mime>
  <mime>application/x-vnd.oasis.opendocument.graphics-template</mime>
  <mime>application/x-vnd.oasis.opendocument.presentation-template</mime>
  <mime>application/x-vnd.oasis.opendocument.spreadsheet-template</mime>
  <mime>application/x-vnd.oasis.opendocument.chart-template</mime>
  <mime>application/x-vnd.oasis.opendocument.image-template</mime>
  <mime>application/x-vnd.oasis.opendocument.formula-template</mime>
</parser>

<parser name="parse-image" class="org.apache.tika.parser.image.ImageParser">
  <mime>image/bmp</mime>
  <mime>image/gif</mime>
  <mime>image/jpeg</mime>
  <mime>image/png</mime>
  <mime>image/tiff</mime>
  <mime>image/vnd.wap.wbmp</mime>
  <mime>image/x-icon</mime>
  <mime>image/x-psd</mime>
  <mime>image/x-xcf</mime>
</parser>

<parser name="parse-class" class="org.apache.tika.parser.asm.ClassParser">
  <mime>application/x-tika-java-class</mime>
</parser>

<parser name="parse-mp3" class="org.apache.tika.parser.mp3.Mp3Parser">
  <mime>audio/mpeg</mime>
</parser>

<parser name="parse-midi" class="org.apache.tika.parser.audio.MidiParser">
  <mime>application/x-midi</mime>
  <mime>audio/midi</mime>
</parser>

<parser name="parse-audio" class="org.apache.tika.parser.audio.AudioParser">
  <mime>audio/basic</mime>
  <mime>audio/x-wav</mime>
  <mime>audio/x-aiff</mime>
</parser>

</parsers>

</properties>

除了我调用函数 public List<Fichier> findAllByContains(String path,String motCles) 对 .docx 和 .xslx 文档进行全文搜索时，bean 的所有查询都有效。对 .pdf、.txt、.xml、.xls、.doc 等的全文搜索完美无缺。

Answer 1

参考：http://jackrabbit.510166.n4.nabble.com/Office-2007-documents-not-being-indexed-in-Jackrabbit-2-4-3-td4657380.html

On the same line, I have observed commons-compress-1.5.jar is required by Tika parser in case of OOXML types of documents (i.e. office 2007 documents).

Now, I am able to index & search most of types of documents (office 2007 - docx, pptx, xlsx , office 2003 - doc, ppt, xls, PDF) using below 2 steps:

(1) Updated repository.xml & added Further details can be found at https://issues.apache.org/jira/browse/JCR-3287

(2) Added commons-compress-1.5.jar classpath while running jackrabbit-standalone-2.6.2.jar

Answer 2

解决方案主要针对 jackrabbit-jca-2.7.5.rar!

的 JAR

依赖性存在错误，因此我进行了这些更改：

添加 apache-mime4j-0。6.jar
添加 apache-mime4j-core-0.7.jar
添加 commons-compress-1。5.jar

在 jackrabbit-jca-2.7 中添加这些 JAR。5.rar 在部署之前！

并且 .docx、.xlsx、... 的索引编制成功！

感谢@Ashok Felix

Apache Jackrabbit JCA 2.7.5 .docx 和 .xlsx 索引

Apache Jackrabbit JCA 2.7.5 .docx and .xlsx indexing

java

jackrabbit

jcr

jcr-sql2

jakarta-ee