Custom metadata extraction from MS Word

As we transition to the new Hyland Community, some post links may be temporarily disrupted as we finalize redirects. We apologize for the inconvenience and are working to resolve this as quickly as possible. Details.

col_edinburgh

OK after a couple of weeks I'm close to giving up now. All I want to do is extend the Office Metadata extractor to allow me to collect a custom property called projectID.

I have followed the example in the Book, Alfresco Developer Guide (2008) chapter 4 and the WIKI page

http://wiki.alfresco.com/wiki/Metadata_Extraction‍

but I can't do it.

Following the example in the book I can successfully map the 'keywords' property but I am lost on the 'digging into the extractor class' example . I can't seem to be able to customise the class using the steps laid out

I fear I am going to have to abandon this project as I just can't seem to make it work

Regards

col_edinburgh

I have tried to alter OfficeMetadataExtracter.class using OpenDocumentMetadataExtracter.class as the template.

custom:user1 is the custom property

Here is my code:

EnhancedOfficeExtracter.java

package com.mpb.extracter;

import java.io.Serializable;
import java.text.ParseException;
import java.text.SimpleDateFormat;
import java.util.ArrayList;
import java.util.Date;
import java.util.Map;
import java.util.Set;

import org.alfresco.repo.content.MimetypeMap;
import org.alfresco.repo.content.metadata.TikaPoweredMetadataExtracter;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.Parser;
import org.apache.tika.parser.microsoft.OfficeParser;
import org.alfresco.service.namespace.QName;

/**
 * Office file format Metadata Extracter.  This extracter uses the POI library to extract
 * the following:
 * <pre>
 *   <b>author:</b>             –      cm:author
 *   <b>title:</b>              –      cm:title
 *   <b>subject:</b>            –      cm:description
 *   <b>createDateTime:</b>     –      cm:created
 *   <b>lastSaveDateTime:</b>   –      cm:modified
 *   <b>comments:</b>
 *   <b>editTime:</b>
 *   <b>format:</b>
 *   <b>keywords:</b>
 *   <b>lastAuthor:</b>
 *   <b>lastPrinted:</b>
 *   <b>osVersion:</b>
 *   <b>thumbnail:</b>
 *   <b>pageCount:</b>
 *   <b>wordCount:</b>
 * </pre>
 * 
 * Uses Apache Tika
 *
 * @author Derek Hulley
 * @author Nick Burch
 */
public class EnhancedOfficeExtracter extends TikaPoweredMetadataExtracter
{
    private static final String KEY_CREATION_DATE = "creationDate";
    private static final String KEY_CREATOR = "creator";
    private static final String KEY_DATE = "date";
    private static final String KEY_GENERATOR = "generator";
    private static final String KEY_INITIAL_CREATOR = "initialCreator";
    private static final String KEY_KEYWORD = "keyword";
    private static final String KEY_LANGUAGE = "language";
    private static final String KEY_PRINT_DATE = "printDate";
    private static final String KEY_PRINTED_BY = "printedBy";
    
    private static final String CUSTOM_PREFIX = "custom:";

    public static ArrayList<String> SUPPORTED_MIMETYPES = buildSupportedMimetypes(
            new String[] {
                MimetypeMap.MIMETYPE_WORD,
                MimetypeMap.MIMETYPE_EXCEL,
                MimetypeMap.MIMETYPE_PPT},
            new OfficeParser()
      );
      static {
         // Outlook has it's own one!
         SUPPORTED_MIMETYPES.remove(MimetypeMap.MIMETYPE_OUTLOOK_MSG);
      }
      private static final SimpleDateFormat dateFormat = new SimpleDateFormat("yyyy-MM-dd'T'hh:mm:ss");
      public EnhancedOfficeExtracter()
      {
          super(SUPPORTED_MIMETYPES);
      }
    
      @Override
      protected Parser getParser() {
        return new OfficeParser();
      }

    @Override
    protected Map<String, Serializable> extractSpecific(Metadata metadata,
         Map<String, Serializable> properties, Map<String, String> headers) {
       putRawValue(KEY_CREATION_DATE, getDateOrNull(metadata.get(Metadata.CREATION_DATE)), properties);
       putRawValue(KEY_CREATOR, metadata.get(Metadata.CREATOR), properties);
       putRawValue(KEY_DATE, getDateOrNull(metadata.get(Metadata.DATE)), properties);
       putRawValue(KEY_DESCRIPTION, metadata.get(Metadata.DESCRIPTION), properties);
       putRawValue(KEY_GENERATOR, metadata.get("generator"), properties);
       putRawValue(KEY_INITIAL_CREATOR, metadata.get("initial-creator"), properties);
       putRawValue(KEY_KEYWORD, metadata.get(Metadata.KEYWORDS), properties);
       putRawValue(KEY_LANGUAGE, metadata.get(Metadata.LANGUAGE), properties);
//     putRawValue(KEY_PRINT_DATE, getDateOrNull(metadata.get(Metadata.)), rawProperties);
//     putRawValue(KEY_PRINTED_BY, metadata.get(Metadata.), rawProperties);
           
       // Handle user-defined properties dynamically
       Map<String, Set<QName>> mapping = super.getMapping();
       for (String key : mapping.keySet())
       {
           if (metadata.get(CUSTOM_PREFIX + key) != null)
           {
                putRawValue(key, metadata.get(CUSTOM_PREFIX + key), properties);
           }
       }
       
       return properties;
    }
    private Date getDateOrNull(String dateString)
    {
        if (dateString != null && dateString.length() != 0)
        {
            try {
               return dateFormat.parse(dateString);
            } catch(ParseException e) {}
        }

        return null;
    }
}‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍

EnhancedOfficeExtracter.properties

#
# OpenDocumentMetadataExtracter - default mapping
#
# author: Derek Hulley

# Namespaces
namespace.prefix.customm=custom.model

# Mappings
creationDate=cm:created
creator=cm:author
date=
description=
generator=
initialCreator=
keyword=
language=
printDate=
printedBy=
subject=cm:description
title=cm:title
# mine
user1=custom:user1
Keywords=custom:keywords
‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍

customModel.xml

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

<!– Custom Model –>

<!– Note: This model is pre-configured to load at startup of the Repository.  So, all custom –>
<!–       types and aspects added here will automatically be registered –>

<model name="custom:customModel" xmlns="http://www.alfresco.org/model/dictionary/1.0">

   <!– Optional meta-data about the model –>   
   <description>Custom Model</description>
   <author>Colin Sneddon</author>
   <version>1.0</version>

   <imports>
        <!– Import Alfresco Dictionary Definitions –>
      <import uri="http://www.alfresco.org/model/dictionary/1.0" prefix="d"/>
      <!– Import Alfresco Content Domain Model Definitions –>
      <import uri="http://www.alfresco.org/model/content/1.0" prefix="cm"/>
   </imports>

   <!– Introduction of new namespaces defined by this model –>
   <!– NOTE: The following namespace custom.model should be changed to reflect your own namespace –>
   <namespaces>
      <namespace uri="custom.model" prefix="custom"/>
   </namespaces>
    <aspects>
   <!– Definition of new Content Aspect: myprojectbrowser generic forms –>
      <aspect name="custom:genericForm">
      <title>myForm</title>
          <properties>
          <property name="custom:keywords">
             <title>keywords</title>
             <type>d:text</type>
             <protected>false</protected>
             <mandatory>false</mandatory>
             <multiple>false</multiple>
             </property>
             <property name="custom:user1">
             <title>ProjectID</title>
             <type>d:text</type>
             <protected>false</protected>
             <mandatory>false</mandatory>
             <multiple>false</multiple>
             </property>
</properties>
</aspect>
</aspects>   
</model>‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍

custom-metadata-extractors-context.xml

<?xml version='1.0' encoding='UTF-8'?>
<!DOCTYPE beans PUBLIC '-//SPRING//DTD BEAN//EN' 'http://www.springframework.org/dtd/spring-beans.dtd'>

<!–
       This sample show how to modify the mappings properties of the new V2.1 Metadata Extractors.
       In this example, in addition to the default mappings, the field 'user1' is mapped to
       'cm:description'.  The available source properties is described on the Javadocs of the
       extracter class.
–>
<beans>

    <!– This adds in the extra mapping for the Open Document extractor –>
    <bean id="extracter.Office" class="com.mpb.extracter.EnhancedOfficeExtracter" parent="baseMetadataExtracter" >
        <property name="inheritDefaultMapping">
            <value>true</value>
        </property>
        <property name="mappingProperties">
            <props>
                <prop key="namespace.prefix.custom">custom.model</prop>
                <prop key="user1">custom:user1</prop>
                <prop key="keywords">custom:keywords</prop>
            </props>
        </property>
    </bean>

   
</beans>‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍

custom-model-context.xml

<?xml version='1.0' encoding='UTF-8'?>
<!DOCTYPE beans PUBLIC '-//SPRING//DTD BEAN//EN' ' http://www.springframework.org/dtd/spring-beans.dtd'>
<beans>
<!– Registration of new models –>
<bean id="mpb.dictionaryBootstrap" parent="dictionaryModelBootstrap" depends-on="dictionaryBootstrap">
<property name="models">
<list>
<value>alfresco/extension/model/customModel.xml</value>
</list>
</property>
</bean>
</beans>‍‍‍‍‍‍‍‍‍‍‍‍

web-client-config-custom.xml

<alfresco-config>

   <!– Example of overriding the from email address –>
   <!–
   <config>
      <client>
         <from-email-address>someone@your-domain.com</from-email-address>
         <search-max-results>100</search-max-results>
      </client>
   </config>
   –>

   <!– Example of adding languages to the list in the login page –>
   <!–
   <config evaluator="string-compare" condition="Languages">
      <languages>
         <language locale="ca_ES">Catalan</language>
         <language locale="hr_HR">Croatian</language>
         <language locale="cs_CZ">Czech</language>
         <language locale="da_DK">Danish</language>
         <language locale="de_DE">German</language>
         <language locale="es_ES">Spanish</language>
         <language locale="el_GR">Greek</language>
         <language locale="fi_FI">Finnish</language>
         <language locale="fr_FR">French</language>
         <language locale="it_IT">Italian</language>
         <language locale="ja_JP">Japanese</language>
         <language locale="du_NL">Dutch</language>
         <language locale="pl_PL">Polish</language>
         <language locale="pt_PT">Portuguese</language>
         <language locale="pt_BR">Portuguese (Brazilian)</language>
         <language locale="ru_RU">Russian</language>
         <language locale="sv_SV">Swedish</language>
         <language locale="tr_TR">Turkish</language>
         <language locale="zh_CN">Simplified Chinese</language>
      </languages>
   </config>
   –>
   
   <!– Example of configuring advanced search –>
   <!–
   <config evaluator="string-compare" condition="Advanced Search">
      <advanced-search>
         <content-types>
         </content-types>
         <custom-properties>
            <meta-data aspect="app:simpleworkflow" property="app:approveStep" />
         </custom-properties>
      </advanced-search>
   </config>
   –>

   <!– Example of changing the sort direction for a view in the client –>
   <!–
   <config evaluator="string-compare" condition="Views">
      <views>
         <view-defaults>
            <topic>
               <sort-direction>ascending</sort-direction>
            </topic>
         </view-defaults>
      </views>
   </config>
   –>

   <!– Example of adding a custom icon to the Create Space dialog –>
   <!–
   <config evaluator="string-compare" condition="cm:folder icons">
      <icons>
         <icon name="space-icon-custom" path="/images/icons/space-icon-custom.gif" />
      </icons>
   </config>
   –>

   <!– The config below shows how to incorporate the example model–>
   <!– into the web client, for this to work you will need to –>
   <!– rename example-model-context.xml.sample to example-model-context.xml –>
   <!–
   <config evaluator="string-compare" condition="Content Wizards">
      <content-types>
         <type name="my:sop" />
      </content-types>
   </config>

   <config evaluator="node-type" condition="my:sop">
      <property-sheet>
         <show-property name="mimetype" display-label-id="content_type" 
                        component-generator="MimeTypeSelectorGenerator" />
         <show-property name="size" display-label-id="size" 
                        converter="org.alfresco.faces.ByteSizeConverter" 
                        show-in-edit-mode="false" />               
         <show-property name="my:publishedDate" />
         <show-association name="my:signOff" />
         <show-property name="my:authorisedBy" />
         <show-child-association name="my:processSteps" />
      </property-sheet>
   </config>

   <config evaluator="aspect-name" condition="my:imageClassification">
      <property-sheet>
         <show-property name="my:width"/>
         <show-property name="my:height"/>
         <show-property name="my:resolution"/>
      </property-sheet>
   </config>

   <config evaluator="aspect-name" condition="cm:storeSelector">
      <property-sheet>
         <show-property name="cm:storeName" />
      </property-sheet>
   </config>
   <config evaluator="string-compare" condition="Action Wizards">
      <aspects>
         <aspect name="cm:storeSelector"/>
      </aspects>
   </config>

   <config evaluator="string-compare" condition="Action Wizards">
      <aspects>
         <aspect name="my:imageClassification"/>
      </aspects>
   </config>

   <config evaluator="string-compare" condition="Advanced Search">
      <advanced-search>
         <content-types>
            <type name="my:sop" />
         </content-types>
         <custom-properties>
            <meta-data type="my:sop" property="my:authorisedBy" />
            <meta-data aspect="my:imageClassification" property="my:resolution" />
         </custom-properties>
      </advanced-search>
   </config>
   –>
<!– Lists the custom aspect in business rules Action wizard –> 
<config evaluator="string-compare" condition="Action Wizards"> 
<aspects> 
<aspect name="custom:genericForm"/> 
</aspects> 
</config>
<!– Displays the properties in view details page –> 
<config evaluator="aspect-name" condition="custom:genericForm"> 
<property-sheet> 
<separator name="sepCust1" display-label="My Forms" component-generator="HeaderSeparatorGenerator" /> 
<show-property name="custom:keywords"/>
<show-property name="custom:user1"/>
</property-sheet> 
</config> 
</alfresco-config>‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍