Make tika extension work as per the vanilla Camel component

Fixes #5234
Fixes #5393

docs/modules/ROOT/pages/reference/extensions/tika.adoc

@@ -44,37 +44,3 @@ Or add the coordinates to your existing project:
 ifeval::[{doc-show-user-guide-link} == true]
 Check the xref:user-guide/index.adoc[User guide] for more information about writing Camel Quarkus applications.
 endif::[]
-
-[id="extensions-tika-camel-quarkus-limitations"]
-== Camel Quarkus limitations
-
-Parameters `tikaConfig` and `tikaConfigUri` are not available in quarkus camel tika extension. Configuration
-can be changed only via `application.properties`.
-
-While you can use any of the available https://tika.apache.org/1.24.1/formats.html[Tika parsers] in JVM mode,
-only some of those are supported in native mode - see the https://quarkiverse.github.io/quarkiverse-docs/quarkus-tika/dev/index.html[Quarkus Tika guide].
-
-PDF and ODF parsers can not be used both in JVM mode or in the native mode. Pdf extension is suggested for purposes of pdf consumption to avoid a version conflict between Camel and Quarkus-tika extension involving PdfBox dependency.
-
-Use of the Tika parser without any configuration will initialize all available parsers. Unfortunately as some of them
-don't work in the native mode, the whole execution will fail.
-
-In order to make the Tika parser work in the native mode, selection of parsers for initialization should be used.
-
-* `quarkus.tika.parsers` Comma separated list of parsers (abbreviations). There are two predefined parsers:
-`pdf` and `odf`.
-* `quarkus.tika.parser.*` Adds new parser abbreviation to be used with previous property. Value is the full class of
-the parser.
-
-Example of `application.properties`:
-[source,properties]
-----
-quarkus.tika.parsers = pdf,odf,office
-quarkus.tika.parser.office = org.apache.tika.parser.microsoft.OfficeParser
-----
-
-For more information about selecting parsers see the https://quarkiverse.github.io/quarkiverse-docs/quarkus-tika/dev/index.html[Quarkus Tika guide].
-
-You may need to add the `quarkus-awt` extension to build the native image. For more information, see https://quarkiverse.github.io/quarkiverse-docs/quarkus-tika/dev/index.html[Quarkus Tika guide].
-
-

extensions/tika/deployment/pom.xml

@@ -30,6 +30,14 @@
     <name>Camel Quarkus :: Tika :: Deployment</name>
 
     <dependencies>
+        <dependency>
+            <groupId>io.quarkus</groupId>
+            <artifactId>quarkus-netty-deployment</artifactId>
+        </dependency>
+        <dependency>
+            <groupId>io.quarkus</groupId>
+            <artifactId>quarkus-awt-deployment</artifactId>
+        </dependency>
         <dependency>
             <groupId>org.apache.camel.quarkus</groupId>
             <artifactId>camel-quarkus-core-deployment</artifactId>
@@ -38,10 +46,6 @@
             <groupId>org.apache.camel.quarkus</groupId>
             <artifactId>camel-quarkus-tika</artifactId>
         </dependency>
-        <dependency>
-            <groupId>io.quarkiverse.tika</groupId>
-            <artifactId>quarkus-tika-deployment</artifactId>
-        </dependency>
         <dependency>
             <groupId>org.apache.camel.quarkus</groupId>
             <artifactId>camel-quarkus-support-xalan-deployment</artifactId>

extensions/tika/deployment/src/main/java/org/apache/camel/quarkus/component/tika/deployment/TikaProcessor.java

@@ -16,49 +16,40 @@
  */
 package org.apache.camel.quarkus.component.tika.deployment;
 
-import io.quarkus.arc.deployment.BeanContainerBuildItem;
+import java.util.Set;
+
+import io.quarkus.deployment.annotations.BuildProducer;
 import io.quarkus.deployment.annotations.BuildStep;
-import io.quarkus.deployment.annotations.ExecutionTime;
-import io.quarkus.deployment.annotations.Record;
 import io.quarkus.deployment.builditem.FeatureBuildItem;
-import io.quarkus.deployment.builditem.nativeimage.RuntimeInitializedClassBuildItem;
-import org.apache.camel.component.tika.TikaComponent;
-import org.apache.camel.quarkus.component.tika.TikaRecorder;
-import org.apache.camel.quarkus.core.deployment.spi.CamelRuntimeBeanBuildItem;
-import org.apache.camel.quarkus.core.deployment.spi.CamelServiceFilter;
-import org.apache.camel.quarkus.core.deployment.spi.CamelServiceFilterBuildItem;
-import org.jboss.logging.Logger;
+import io.quarkus.deployment.builditem.nativeimage.NativeImageResourceBuildItem;
+import io.quarkus.deployment.builditem.nativeimage.ServiceProviderBuildItem;
+import io.quarkus.deployment.util.ServiceUtil;
+import org.apache.tika.detect.EncodingDetector;
+import org.apache.tika.parser.Parser;
 
 class TikaProcessor {
-
-    private static final Logger LOG = Logger.getLogger(TikaProcessor.class);
     private static final String FEATURE = "camel-tika";
 
     @BuildStep
     FeatureBuildItem feature() {
         return new FeatureBuildItem(FEATURE);
     }
 
-    /*
-     * The tika component is programmatically configured by the extension thus
-     * we can safely prevent camel to instantiate a default instance.
-     */
     @BuildStep
-    CamelServiceFilterBuildItem serviceFilter() {
-        return new CamelServiceFilterBuildItem(CamelServiceFilter.forComponent("tika"));
+    void registerTikaCoreResources(BuildProducer<NativeImageResourceBuildItem> resource) {
+        resource.produce(new NativeImageResourceBuildItem("org/apache/tika/mime/tika-mimetypes.xml"));
+        resource.produce(new NativeImageResourceBuildItem("org/apache/tika/parser/external/tika-external-parsers.xml"));
     }
 
-    @Record(ExecutionTime.STATIC_INIT)
     @BuildStep
-    CamelRuntimeBeanBuildItem tikaComponent(BeanContainerBuildItem beanContainer, TikaRecorder recorder) {
-        return new CamelRuntimeBeanBuildItem(
-                "tika",
-                TikaComponent.class.getName(),
-                recorder.createTikaComponent(beanContainer.getValue()));
+    void registerTikaServices(BuildProducer<ServiceProviderBuildItem> serviceProvider) throws Exception {
+        serviceProvider.produce(new ServiceProviderBuildItem(EncodingDetector.class.getName(),
+                getProviderNames(EncodingDetector.class.getName())));
+        serviceProvider.produce(new ServiceProviderBuildItem(Parser.class.getName(), getProviderNames(Parser.class.getName())));
     }
 
-    @BuildStep
-    RuntimeInitializedClassBuildItem runtimeInitializedClasses() {
-        return new RuntimeInitializedClassBuildItem("org.apache.pdfbox.text.LegacyPDFStreamEngine");
+    private Set<String> getProviderNames(String serviceProviderName) throws Exception {
+        return ServiceUtil.classNamesNamedIn(Thread.currentThread().getContextClassLoader(),
+                "META-INF/services/" + serviceProviderName);
     }
 }

extensions/tika/runtime/pom.xml

@@ -36,6 +36,14 @@
     </properties>
 
     <dependencies>
+        <dependency>
+            <groupId>io.quarkus</groupId>
+            <artifactId>quarkus-netty</artifactId>
+        </dependency>
+        <dependency>
+            <groupId>io.quarkus</groupId>
+            <artifactId>quarkus-awt</artifactId>
+        </dependency>
         <dependency>
             <groupId>org.apache.camel.quarkus</groupId>
             <artifactId>camel-quarkus-core</artifactId>
@@ -48,10 +56,6 @@
             <groupId>org.apache.camel.quarkus</groupId>
             <artifactId>camel-quarkus-support-xalan</artifactId>
         </dependency>
-        <dependency>
-            <groupId>io.quarkiverse.tika</groupId>
-            <artifactId>quarkus-tika</artifactId>
-        </dependency>
     </dependencies>
 
     <build>

integration-tests/tika/pom.xml

@@ -17,7 +17,8 @@
     limitations under the License.
 
 -->
-<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
     <modelVersion>4.0.0</modelVersion>
     <parent>
         <groupId>org.apache.camel.quarkus</groupId>
@@ -53,7 +54,7 @@
         <dependency>
             <groupId>io.quarkus</groupId>
             <artifactId>quarkus-junit5</artifactId>
-	    <scope>test</scope>
+            <scope>test</scope>
             <exclusions>
                 <exclusion>
                     <groupId>org.jsoup</groupId>
@@ -68,7 +69,6 @@
         </dependency>
     </dependencies>
 
-
     <profiles>
         <profile>
             <id>native</id>

integration-tests/tika/src/main/java/org/apache/camel/quarkus/component/tika/it/TikaResource.java

@@ -26,15 +26,12 @@
 import jakarta.ws.rs.Produces;
 import jakarta.ws.rs.core.MediaType;
 import jakarta.ws.rs.core.Response;
+import org.apache.camel.Exchange;
 import org.apache.camel.ProducerTemplate;
-import org.jboss.logging.Logger;
 
 @Path("/tika")
 @ApplicationScoped
 public class TikaResource {
-
-    private static final Logger LOG = Logger.getLogger(TikaResource.class);
-
     @Inject
     ProducerTemplate producerTemplate;
 
@@ -43,23 +40,11 @@ public class TikaResource {
     @Consumes(MediaType.APPLICATION_OCTET_STREAM)
     @Produces(MediaType.TEXT_PLAIN)
     public Response parse(byte[] message) throws Exception {
-        final String response = producerTemplate.requestBody("tika:parse", message, String.class);
-        return Response
-                .created(new URI("https://camel.apache.org/"))
-                .entity(response)
-                .build();
-    }
-
-    @Path("/parseAsText")
-    @POST
-    @Consumes(MediaType.APPLICATION_OCTET_STREAM)
-    @Produces(MediaType.TEXT_PLAIN)
-    public Response parseAsTxt(byte[] message) throws Exception {
-        final String response = producerTemplate.requestBody("tika:parse?tikaParseOutputFormat=text", message,
-                String.class);
+        final Exchange response = producerTemplate.request("tika:parse", exchange -> exchange.getMessage().setBody(message));
         return Response
                 .created(new URI("https://camel.apache.org/"))
-                .entity(response)
+                .header("Parsed-Content-Type", response.getMessage().getHeader(Exchange.CONTENT_TYPE))
+                .entity(response.getMessage().getBody(String.class))
                 .build();
     }
 

integration-tests/tika/src/main/resources/application.properties

@@ -15,8 +15,4 @@
 ## limitations under the License.
 ## ---------------------------------------------------------------------------
 
-#quarkus.tika.parsers= pdf,odf,office,xml,image //Requires new release of quarkiverse-tike, which adopts tika with pdfBox 3.x
-quarkus.tika.parsers= odf,office,xml,image
-quarkus.tika.parser.office = org.apache.tika.parser.microsoft.OfficeParser
-quarkus.tika.parser.image = org.apache.tika.parser.image.ImageParser
-quarkus.tika.parser.xml = org.apache.tika.parser.xml.DcXMLParser
+quarkus.native.resources.includes=assets/*

integration-tests/tika/src/test/java/org/apache/camel/quarkus/component/tika/it/TikaIT.java

@@ -17,12 +17,8 @@
 package org.apache.camel.quarkus.component.tika.it;
 
 import io.quarkus.test.junit.QuarkusIntegrationTest;
-import org.junit.jupiter.api.condition.DisabledOnOs;
-import org.junit.jupiter.api.condition.OS;
 
 @QuarkusIntegrationTest
-//https://github.com/apache/camel-quarkus/issues/3417
-@DisabledOnOs(OS.MAC)
 class TikaIT extends TikaTest {
 
 }