Configuring OCR in Alfresco - Alfresco Community 5.2

[anuradha1]

Hi,

I am successfully configured OCR with my alfresco (windows installation). But, it only working for PNG, TIFF, JPG & GPEG. But i need it for PDF extension also because most of scanned files are in pdf format.

My tesseract-ocr-transform-context.xml is,

<?xml version='1.0' encoding='UTF-8'?>
<!DOCTYPE beans PUBLIC '-//SPRING//DTD BEAN//EN' 'http://www.springframework.org/dtd/spring-beans.dtd'>
<beans default-lazy-init="false" default-autowire="no" default-dependency-check="none">
<bean id="transformer.worker.ocr.tiff" class="org.alfresco.repo.content.transform.RuntimeExecutableContentTransformerWorker" lazy-init="default" autowire="default" dependency-check="default">
<property name="mimetypeService">
<ref bean="mimetypeService" />
</property>
<property name="checkCommand">
<bean class="org.alfresco.util.exec.RuntimeExec" lazy-init="default" autowire="default" dependency-check="default">
<property name="commandsAndArguments">
<map>
<entry key="Windows.*">
<list>
<value>C:\Windows\System32\cmd.exe</value>
<value>/C</value>
<value>dir C:\alfresco-community\ocr.bat</value>
</list>
</entry>
</map>
</property>
<property name="errorCodes">
<value>1</value>
</property>
</bean>
</property>
<property name="transformCommand">
<bean class="org.alfresco.util.exec.RuntimeExec" lazy-init="default" autowire="default" dependency-check="default">
<property name="commandsAndArguments">
<map>
<entry key="Windows.*">
<list>
<value>C:\Windows\System32\cmd.exe</value>
<value>/C</value>
<value>C:\alfresco-community\ocr.bat</value>
<value>"${source}"</value>
<value>"${target}"</value>
</list>
</entry>
</map>
</property>
<property name="errorCodes">
<value>1,2</value>
</property>
</bean>
</property>
<property name="explicitTransformations">
<list>
<bean class="org.alfresco.repo.content.transform.ExplictTransformationDetails" lazy-init="default" autowire="default" dependency-check="default">
<property name="sourceMimetype">
<value>image/tiff</value>
</property>
<property name="targetMimetype">
<value>text/plain</value>
</property>
</bean>
<bean class="org.alfresco.repo.content.transform.ExplictTransformationDetails" lazy-init="default" autowire="default" dependency-check="default">
<property name="sourceMimetype">
<value>image/png</value>
</property>
<property name="targetMimetype">
<value>text/plain</value>
</property>
</bean>
<bean class="org.alfresco.repo.content.transform.ExplictTransformationDetails" lazy-init="default" autowire="default" dependency-check="default">
<property name="sourceMimetype">
<value>image/jpeg</value>
</property>
<property name="targetMimetype">
<value>text/plain</value>
</property>
</bean>
<bean class="org.alfresco.repo.content.transform.ExplictTransformationDetails" lazy-init="default" autowire="default" dependency-check="default">
<property name="sourceMimetype">
<value>image/jpg</value>
</property>
<property name="targetMimetype">
<value>text/plain</value>
</property>
</bean>
</list>
</property>
</bean>
<bean id="transformer.ocr.tiff" class="org.alfresco.repo.content.transform.ProxyContentTransformer" parent="baseContentTransformer" lazy-init="default" autowire="default" dependency-check="default">
<property name="worker">
<ref bean="transformer.worker.ocr.tiff" />
</property>
</bean>
</beans>

I changed it into this including another bean (red colored),

<?xml version='1.0' encoding='UTF-8'?>
<!DOCTYPE beans PUBLIC '-//SPRING//DTD BEAN//EN' 'http://www.springframework.org/dtd/spring-beans.dtd'>
<beans default-lazy-init="false" default-autowire="no" default-dependency-check="none">
<bean id="transformer.worker.ocr.tiff" class="org.alfresco.repo.content.transform.RuntimeExecutableContentTransformerWorker" lazy-init="default" autowire="default" dependency-check="default">
<property name="mimetypeService">
<ref bean="mimetypeService" />
</property>
<property name="checkCommand">
<bean class="org.alfresco.util.exec.RuntimeExec" lazy-init="default" autowire="default" dependency-check="default">
<property name="commandsAndArguments">
<map>
<entry key="Windows.*">
<list>
<value>C:\Windows\System32\cmd.exe</value>
<value>/C</value>
<value>dir C:\alfresco-community\ocr.bat</value>
</list>
</entry>
</map>
</property>
<property name="errorCodes">
<value>1</value>
</property>
</bean>
</property>
<property name="transformCommand">
<bean class="org.alfresco.util.exec.RuntimeExec" lazy-init="default" autowire="default" dependency-check="default">
<property name="commandsAndArguments">
<map>
<entry key="Windows.*">
<list>
<value>C:\Windows\System32\cmd.exe</value>
<value>/C</value>
<value>C:\alfresco-community\ocr.bat</value>
<value>"${source}"</value>
<value>"${target}"</value>
</list>
</entry>
</map>
</property>
<property name="errorCodes">
<value>1,2</value>
</property>
</bean>
</property>
<property name="explicitTransformations">
<list>
<bean class="org.alfresco.repo.content.transform.ExplictTransformationDetails" lazy-init="default" autowire="default" dependency-check="default">
<property name="sourceMimetype">
<value>image/tiff</value>
</property>
<property name="targetMimetype">
<value>text/plain</value>
</property>
</bean>
<bean class="org.alfresco.repo.content.transform.ExplictTransformationDetails" lazy-init="default" autowire="default" dependency-check="default">
<property name="sourceMimetype">
<value>image/png</value>
</property>
<property name="targetMimetype">
<value>text/plain</value>
</property>
</bean>
<bean class="org.alfresco.repo.content.transform.ExplictTransformationDetails" lazy-init="default" autowire="default" dependency-check="default">
<property name="sourceMimetype">
<value>image/pdf</value>
</property>
<property name="targetMimetype">
<value>text/plain</value>
</property>
</bean>
<bean class="org.alfresco.repo.content.transform.ExplictTransformationDetails" lazy-init="default" autowire="default" dependency-check="default">
<property name="sourceMimetype">
<value>image/jpeg</value>
</property>
<property name="targetMimetype">
<value>text/plain</value>
</property>
</bean>
<bean class="org.alfresco.repo.content.transform.ExplictTransformationDetails" lazy-init="default" autowire="default" dependency-check="default">
<property name="sourceMimetype">
<value>image/jpg</value>
</property>
<property name="targetMimetype">
<value>text/plain</value>
</property>
</bean>
</list>
</property>
</bean>
<bean id="transformer.ocr.tiff" class="org.alfresco.repo.content.transform.ProxyContentTransformer" parent="baseContentTransformer" lazy-init="default" autowire="default" dependency-check="default">
<property name="worker">
<ref bean="transformer.worker.ocr.tiff" />
</property>
</bean>
</beans>

but, it gives me bellow error.

org.springframework.beans.factory.BeanCreationException: Error creating bean with name 'transformer.ocr.tiff' defined in file [C:\alfresco-community\tomcat\shared\classes\alfresco\extension\tesseract-ocr-transform-context.xml]: Invocation of init method failed; nested exception is java.lang.IllegalArgumentException: content.transformer.ocr.tiff.extensions.bin.txt.priority has been specified more than once
2019-06-02 20:00:46,019 INFO [org.alfresco.repo.management.subsystems.ChildApplicationContextFactory] [localhost-startStop-1] Stopping 'Transformers' subsystem, ID: [Transformers, default]
2019-06-02 20:00:46,020 INFO [org.alfresco.repo.management.subsystems.ChildApplicationContextFactory] [localhost-startStop-1] Stopped 'Transformers' subsystem, ID: [Transformers, default]
2019-06-02 20:00:46,021 INFO [org.alfresco.repo.management.subsystems.ChildApplicationContextFactory] [localhost-startStop-1] Stopping 'Authentication' subsystem, ID: [Authentication, managed, alfrescoNtlm1]
2019-06-02 20:00:46,021 INFO [org.alfresco.repo.management.subsystems.ChildApplicationContextFactory] [localhost-startStop-1] Stopped 'Authentication' subsystem, ID: [Authentication, managed, alfrescoNtlm1]
2019-06-02 20:00:46,030 ERROR [org.springframework.web.context.ContextLoader] [localhost-startStop-1] Context initialization failed
org.springframework.beans.factory.BeanCreationException: Error creating bean with name 'transformer.ocr.tiff' defined in file [C:\alfresco-community\tomcat\shared\classes\alfresco\extension\tesseract-ocr-transform-context.xml]: Invocation of init method failed; nested exception is java.lang.IllegalArgumentException: content.transformer.ocr.tiff.extensions.bin.txt.priority has been specified more than once
at org.springframework.beans.factory.support.AbstractAutowireCapableBeanFactory.initializeBean(AbstractAutowireCapableBeanFactory.java:1514)
at org.springframework.beans.factory.support.AbstractAutowireCapableBeanFactory.doCreateBean(AbstractAutowireCapableBeanFactory.java:521)
at org.springframework.beans.factory.support.AbstractAutowireCapableBeanFactory.createBean(AbstractAutowireCapableBeanFactory.java:458)
at org.springframework.beans.factory.support.AbstractBeanFactory$1.getObject(AbstractBeanFactory.java:293)
at org.springframework.beans.factory.support.DefaultSingletonBeanRegistry.getSingleton(DefaultSingletonBeanRegistry.java:223)
at org.springframework.beans.factory.support.AbstractBeanFactory.doGetBean(AbstractBeanFactory.java:290)
at org.springframework.beans.factory.support.AbstractBeanFactory.getBean(AbstractBeanFactory.java:191)
at org.springframework.beans.factory.support.DefaultListableBeanFactory.preInstantiateSingletons(DefaultListableBeanFactory.java:636)
at org.springframework.context.support.AbstractApplicationContext.finishBeanFactoryInitialization(AbstractApplicationContext.java:938)
at org.springframework.context.support.AbstractApplicationContext.refresh(AbstractApplicationContext.java:479)
at org.springframework.web.context.ContextLoader.configureAndRefreshWebApplicationContext(ContextLoader.java:410)
at org.springframework.web.context.ContextLoader.initWebApplicationContext(ContextLoader.java:306)
at org.springframework.web.context.ContextLoaderListener.contextInitialized(ContextLoaderListener.java:112)
at org.alfresco.web.app.ContextLoaderListener.contextInitialized(ContextLoaderListener.java:70)
at org.apache.catalina.core.StandardContext.listenerStart(StandardContext.java:5118)
at org.apache.catalina.core.StandardContext.startInternal(StandardContext.java:5634)
at org.apache.catalina.util.LifecycleBase.start(LifecycleBase.java:145)
at org.apache.catalina.core.ContainerBase.addChildInternal(ContainerBase.java:899)
at org.apache.catalina.core.ContainerBase.addChild(ContainerBase.java:875)
at org.apache.catalina.core.StandardHost.addChild(StandardHost.java:652)
at org.apache.catalina.startup.HostConfig.deployDescriptor(HostConfig.java:679)
at org.apache.catalina.startup.HostConfig$DeployDescriptor.run(HostConfig.java:1966)
at java.util.concurrent.Executors$RunnableAdapter.call(Unknown Source)
at java.util.concurrent.FutureTask.run(Unknown Source)
at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.lang.Thread.run(Unknown Source)
Caused by: java.lang.IllegalArgumentException: content.transformer.ocr.tiff.extensions.bin.txt.priority has been specified more than once
at org.alfresco.repo.content.transform.TransformerPropertySetter.setProperties(TransformerPropertySetter.java:119)
at org.alfresco.repo.content.transform.TransformerConfigImpl.setProperties(TransformerConfigImpl.java:239)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
at java.lang.reflect.Method.invoke(Unknown Source)
at org.alfresco.repo.management.subsystems.SubsystemProxyFactory$1.invoke(SubsystemProxyFactory.java:79)
at org.springframework.aop.framework.ReflectiveMethodInvocation.proceed(ReflectiveMethodInvocation.java:172)
at org.springframework.aop.framework.JdkDynamicAopProxy.invoke(JdkDynamicAopProxy.java:204)
at com.sun.proxy.$Proxy25.setProperties(Unknown Source)
at org.alfresco.repo.content.transform.ContentTransformerHelper.logDeprecatedSetter(ContentTransformerHelper.java:251)
at org.alfresco.repo.content.transform.ProxyContentTransformer.register(ProxyContentTransformer.java:74)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
at java.lang.reflect.Method.invoke(Unknown Source)
at org.springframework.beans.factory.support.AbstractAutowireCapableBeanFactory.invokeCustomInitMethod(AbstractAutowireCapableBeanFactory.java:1640)
at org.springframework.beans.factory.support.AbstractAutowireCapableBeanFactory.invokeInitMethods(AbstractAutowireCapableBeanFactory.java:1581)
at org.springframework.beans.factory.support.AbstractAutowireCapableBeanFactory.initializeBean(AbstractAutowireCapableBeanFactory.java:1511)
... 26 more

Did i missed anything or there is another way to do this?

please help me.

Sorry for my English.

Thank you.

[vidhipanchal]

Hi,

Please refer Configuring OCR in Alfresco | ContCentric .

Thanks,

Vidhi

ContCentric