This is an automated email from the ASF dual-hosted git repository.
jamesnetherton pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/camel-quarkus.git
The following commit(s) were added to refs/heads/main by this push:
new e1b1a8970e4 Fixes #9087. Native PDF parsing support in
camel-quarkus-tika
e1b1a8970e4 is described below
commit e1b1a8970e465d4a253feea2ee42d9a5271c210e
Author: Jiří Ondrušek <[email protected]>
AuthorDate: Tue Oct 20 08:08:39 2026 +0200
Fixes #9087. Native PDF parsing support in camel-quarkus-tika
Move the PDFBox/Tika PDF native configuration from langchain4j-ingest to
camel-quarkus-tika, active when tika-parser-pdf-module is present.
- Embed FontBox CMaps, PDFs with Identity-H fonts failed in native mode
- Depend on support-commons-logging: PDFBox logs via commons-logging,
which the BOM excludes from tika-parser-pdf-module
- Drop the org.apache.tika.parser.pdf runtime init, not needed by Tika 4.1
- Test PDFs with an Identity-H font, a non-embedded standard 14 font and
encryption; document the parser modules
Co-authored-by: jiriOndrusek-agent <[email protected]>
Co-authored-by: Claude Opus 5.5 <[email protected]>
---
.../ROOT/pages/reference/extensions/tika.adoc | 22 +++++++
.../deployment/Langchain4jIngestProcessor.java | 71 ---------------------
extensions/tika/deployment/pom.xml | 4 ++
.../component/tika/deployment/TikaProcessor.java | 52 +++++++++++++++
extensions/tika/runtime/pom.xml | 5 ++
extensions/tika/runtime/src/main/doc/usage.adoc | 17 +++++
integration-tests/tika/pom.xml | 4 ++
.../quarkus/component/tika/it/TikaResource.java | 3 +
.../camel/quarkus/component/tika/it/TikaTest.java | 74 ++++++++++++++++++++++
poms/bom/pom.xml | 5 +-
10 files changed, 183 insertions(+), 74 deletions(-)
diff --git a/docs/modules/ROOT/pages/reference/extensions/tika.adoc
b/docs/modules/ROOT/pages/reference/extensions/tika.adoc
index 3a0c3c1408a..bcd09a59c34 100644
--- a/docs/modules/ROOT/pages/reference/extensions/tika.adoc
+++ b/docs/modules/ROOT/pages/reference/extensions/tika.adoc
@@ -44,3 +44,25 @@ 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-usage"]
+== Usage
+[id="extensions-tika-usage-parser-modules"]
+=== Parser modules
+
+Tika parses only the formats whose parser module is on the classpath.
+`camel-tika` brings the HTML and plain text modules. For any other format, add
its module to your application, e.g. for PDF:
+
+[source,xml]
+----
+<dependency>
+ <groupId>org.apache.tika</groupId>
+ <artifactId>tika-parser-pdf-module</artifactId>
+</dependency>
+----
+
+The Camel Quarkus BOM manages the version of `tika-parser-pdf-module` only.
+For other modules, use the version of `org.apache.tika:tika-core` that
`camel-tika` brings.
+
+In native mode, the HTML, plain text and PDF modules are supported.
+
diff --git
a/extensions/langchain4j-ingest/deployment/src/main/java/org/apache/camel/quarkus/component/langchain4j/ingest/deployment/Langchain4jIngestProcessor.java
b/extensions/langchain4j-ingest/deployment/src/main/java/org/apache/camel/quarkus/component/langchain4j/ingest/deployment/Langchain4jIngestProcessor.java
index 51bded43594..25f6554f7c6 100644
---
a/extensions/langchain4j-ingest/deployment/src/main/java/org/apache/camel/quarkus/component/langchain4j/ingest/deployment/Langchain4jIngestProcessor.java
+++
b/extensions/langchain4j-ingest/deployment/src/main/java/org/apache/camel/quarkus/component/langchain4j/ingest/deployment/Langchain4jIngestProcessor.java
@@ -28,7 +28,6 @@ import io.quarkus.arc.deployment.AdditionalBeanBuildItem;
import io.quarkus.arc.deployment.SyntheticBeanBuildItem;
import io.quarkus.arc.deployment.SyntheticBeansRuntimeInitBuildItem;
import
io.quarkus.arc.deployment.ValidationPhaseBuildItem.ValidationErrorBuildItem;
-import io.quarkus.bootstrap.classloading.QuarkusClassLoader;
import io.quarkus.deployment.annotations.BuildProducer;
import io.quarkus.deployment.annotations.BuildStep;
import io.quarkus.deployment.annotations.Consume;
@@ -37,11 +36,7 @@ import io.quarkus.deployment.annotations.Record;
import io.quarkus.deployment.builditem.ApplicationArchivesBuildItem;
import io.quarkus.deployment.builditem.CombinedIndexBuildItem;
import io.quarkus.deployment.builditem.FeatureBuildItem;
-import io.quarkus.deployment.builditem.nativeimage.ExcludeConfigBuildItem;
-import
io.quarkus.deployment.builditem.nativeimage.NativeImageResourceDirectoryBuildItem;
import io.quarkus.deployment.builditem.nativeimage.ReflectiveClassBuildItem;
-import
io.quarkus.deployment.builditem.nativeimage.RuntimeInitializedClassBuildItem;
-import
io.quarkus.deployment.builditem.nativeimage.RuntimeInitializedPackageBuildItem;
import io.quarkus.runtime.configuration.ConfigurationException;
import jakarta.inject.Singleton;
import org.apache.camel.quarkus.component.langchain4j.ingest.Ingest;
@@ -78,72 +73,6 @@ class Langchain4jIngestProcessor {
.build();
}
- /**
- * The documented PDF recipe adds {@code tika-parser-pdf-module}, which
drags
- * {@code jaxb-runtime} → {@code angus-activation} into the image. Angus'
own GraalVM
- * feature then reflects over every registered data-content handler and
crashes on
- * BouncyCastle's S/MIME handlers ({@code bcjmail}'s mailcap references
- * {@code jakarta.mail.Part}, and jakarta.mail is not on the classpath).
The feature only
- * registers mailcap handlers, which nothing on the ingest path uses, so
its registration
- * is excluded — but only in the constellation that crashes: PDFBox
present (the recipe) and
- * jakarta.mail absent. An application that uses mail and angus for real
keeps its feature.
- *
- * TODO: move to camel-quarkus-tika, see #9087.
- */
- @BuildStep
- void excludeAngusActivationFeature(BuildProducer<ExcludeConfigBuildItem>
excludeConfig) {
- if
(!QuarkusClassLoader.isClassPresentAtRuntime("org.apache.pdfbox.pdmodel.PDDocument")
- ||
QuarkusClassLoader.isClassPresentAtRuntime("jakarta.mail.Part")) {
- return;
- }
- excludeConfig.produce(new
ExcludeConfigBuildItem("org\\.eclipse\\.angus\\.angus-activation-.*\\.jar",
-
"/META-INF/native-image/org.eclipse.angus/angus-activation/native-image.properties"));
- }
-
- /**
- * The same recipe brings PDFBox itself. Native image needs its
AWT-touching classes
- * initialized at run time and its resource tree — font metrics, glyph
lists, ICC profile —
- * embedded. The camel-quarkus-pdf extension embeds the same files as a
hand-listed constant;
- * this registers the {@code org/apache/pdfbox/resources} directory
wholesale instead, so the
- * set cannot drift when a PDFBox upgrade adds or renames a resource. The
runtime-init side is
- * widened past camel-pdf to the rendering and graphics packages Tika's
text extraction
- * reaches. Produced only when PDFBox is on the classpath.
- *
- * TODO: move to camel-quarkus-tika (#9087) and align camel-quarkus-pdf
with it (#9091).
- */
- @BuildStep
- void pdfboxInNative(
- BuildProducer<RuntimeInitializedClassBuildItem> runtimeInitialized,
- BuildProducer<RuntimeInitializedPackageBuildItem>
runtimeInitializedPackages,
- BuildProducer<NativeImageResourceDirectoryBuildItem>
nativeResourceDirectories,
- BuildProducer<ReflectiveClassBuildItem> reflectiveClasses) {
- if
(!QuarkusClassLoader.isClassPresentAtRuntime("org.apache.pdfbox.pdmodel.PDDocument"))
{
- return;
- }
- for (String className : new String[] {
- "org.apache.pdfbox.pdmodel.font.PDType1Font",
- "org.apache.pdfbox.pdmodel.PDDocument",
- "org.apache.pdfbox.pdmodel.encryption.StandardSecurityHandler"
}) {
- runtimeInitialized.produce(new
RuntimeInitializedClassBuildItem(className));
- }
- // text extraction reaches AWT-holding statics across the rendering
and graphics trees
- // (SoftMask's DirectColorModel, the CIE color spaces'
ICC_ColorSpace), and Tika's own
- // PDF classes embed them in enum constants
(PDFParserConfig$TikaImageType wraps
- // rendering.ImageType), so the packages are deferred wholesale rather
than chasing one
- // class at a time
- for (String packageName : new String[] {
- "org.apache.pdfbox.rendering",
- "org.apache.pdfbox.pdmodel.graphics",
- "org.apache.tika.parser.pdf" }) {
- runtimeInitializedPackages.produce(new
RuntimeInitializedPackageBuildItem(packageName));
- }
- reflectiveClasses.produce(ReflectiveClassBuildItem
-
.builder("org.apache.pdfbox.pdmodel.encryption.StandardSecurityHandler",
-
"org.apache.pdfbox.pdmodel.documentinterchange.logicalstructure.PDParentTreeValue")
- .constructors().methods().build());
- nativeResourceDirectories.produce(new
NativeImageResourceDirectoryBuildItem("org/apache/pdfbox/resources"));
- }
-
/**
* {@code #class:} beans are instantiated reflectively, which native mode
allows only for
* registered classes: the two camel-core repositories the documentation
recommends, plus
diff --git a/extensions/tika/deployment/pom.xml
b/extensions/tika/deployment/pom.xml
index 619b5e221a1..81e73f6c611 100644
--- a/extensions/tika/deployment/pom.xml
+++ b/extensions/tika/deployment/pom.xml
@@ -46,6 +46,10 @@
<groupId>org.apache.camel.quarkus</groupId>
<artifactId>camel-quarkus-tika</artifactId>
</dependency>
+ <dependency>
+ <groupId>org.apache.camel.quarkus</groupId>
+
<artifactId>camel-quarkus-support-commons-logging-deployment</artifactId>
+ </dependency>
</dependencies>
<build>
diff --git
a/extensions/tika/deployment/src/main/java/org/apache/camel/quarkus/component/tika/deployment/TikaProcessor.java
b/extensions/tika/deployment/src/main/java/org/apache/camel/quarkus/component/tika/deployment/TikaProcessor.java
index 39654ce2eba..ef7a3b2cc60 100644
---
a/extensions/tika/deployment/src/main/java/org/apache/camel/quarkus/component/tika/deployment/TikaProcessor.java
+++
b/extensions/tika/deployment/src/main/java/org/apache/camel/quarkus/component/tika/deployment/TikaProcessor.java
@@ -18,10 +18,16 @@ package org.apache.camel.quarkus.component.tika.deployment;
import java.util.Set;
+import io.quarkus.bootstrap.classloading.QuarkusClassLoader;
import io.quarkus.deployment.annotations.BuildProducer;
import io.quarkus.deployment.annotations.BuildStep;
import io.quarkus.deployment.builditem.FeatureBuildItem;
+import io.quarkus.deployment.builditem.nativeimage.ExcludeConfigBuildItem;
import
io.quarkus.deployment.builditem.nativeimage.NativeImageResourceBuildItem;
+import
io.quarkus.deployment.builditem.nativeimage.NativeImageResourceDirectoryBuildItem;
+import io.quarkus.deployment.builditem.nativeimage.ReflectiveClassBuildItem;
+import
io.quarkus.deployment.builditem.nativeimage.RuntimeInitializedClassBuildItem;
+import
io.quarkus.deployment.builditem.nativeimage.RuntimeInitializedPackageBuildItem;
import io.quarkus.deployment.builditem.nativeimage.ServiceProviderBuildItem;
import io.quarkus.deployment.util.ServiceUtil;
import org.apache.tika.detect.EncodingDetector;
@@ -48,6 +54,52 @@ class TikaProcessor {
serviceProvider.produce(new
ServiceProviderBuildItem(Parser.class.getName(),
getProviderNames(Parser.class.getName())));
}
+ /**
+ * Native support for {@code tika-parser-pdf-module} and the PDFBox it
brings, when the application adds it. The
+ * PDFBox part is similar to {@code PdfProcessor} of camel-quarkus-pdf,
keep them aligned.
+ */
+ @BuildStep
+ void pdfParserModule(
+ BuildProducer<NativeImageResourceDirectoryBuildItem>
resourceDirectory,
+ BuildProducer<RuntimeInitializedClassBuildItem>
runtimeInitializedClass,
+ BuildProducer<RuntimeInitializedPackageBuildItem>
runtimeInitializedPackage,
+ BuildProducer<ReflectiveClassBuildItem> reflectiveClass,
+ BuildProducer<ExcludeConfigBuildItem> excludeConfig) {
+ if
(!QuarkusClassLoader.isClassPresentAtRuntime("org.apache.tika.parser.pdf.PDFParser"))
{
+ return;
+ }
+ // Font metrics, glyph lists, the ICC profile etc. The whole
directory, so PDFBox upgrades need no list updates
+ resourceDirectory.produce(new
NativeImageResourceDirectoryBuildItem("org/apache/pdfbox/resources"));
+ // FontBox loads predefined CMaps (e.g. Identity-H) by names computed
at runtime
+ resourceDirectory.produce(new
NativeImageResourceDirectoryBuildItem("org/apache/fontbox/cmap"));
+
+ for (String className : new String[] {
+ "org.apache.pdfbox.pdmodel.font.PDType1Font",
+ "org.apache.pdfbox.pdmodel.PDDocument",
+ "org.apache.pdfbox.pdmodel.encryption.StandardSecurityHandler"
}) {
+ runtimeInitializedClass.produce(new
RuntimeInitializedClassBuildItem(className));
+ }
+ // Text extraction reaches AWT-holding statics in PDFBox's rendering
and graphics packages (SoftMask's
+ // ColorModel, the CIE color spaces' ColorSpace), so the packages are
deferred wholesale
+ for (String packageName : new String[] {
+ "org.apache.pdfbox.rendering",
+ "org.apache.pdfbox.pdmodel.graphics" }) {
+ runtimeInitializedPackage.produce(new
RuntimeInitializedPackageBuildItem(packageName));
+ }
+ reflectiveClass.produce(ReflectiveClassBuildItem.builder(
+ "org.apache.pdfbox.pdmodel.encryption.StandardSecurityHandler",
+
"org.apache.pdfbox.pdmodel.documentinterchange.logicalstructure.PDParentTreeValue")
+ .constructors().methods().build());
+
+ // The module brings BouncyCastle's bcjmail, whose mailcap S/MIME
handlers need jakarta.mail. Without it, the
+ // GraalVM feature of angus-activation (e.g. brought by RESTEasy)
fails reflecting over them. Nothing here
+ // needs the mailcap handlers, so the feature is skipped in that case
+ if (!QuarkusClassLoader.isClassPresentAtRuntime("jakarta.mail.Part")) {
+ excludeConfig.produce(new
ExcludeConfigBuildItem("org\\.eclipse\\.angus\\.angus-activation-.*\\.jar",
+
"/META-INF/native-image/org.eclipse.angus/angus-activation/native-image.properties"));
+ }
+ }
+
private Set<String> getProviderNames(String serviceProviderName) throws
Exception {
return
ServiceUtil.classNamesNamedIn(Thread.currentThread().getContextClassLoader(),
"META-INF/services/" + serviceProviderName);
diff --git a/extensions/tika/runtime/pom.xml b/extensions/tika/runtime/pom.xml
index 0b4204e42b6..873e5d77913 100644
--- a/extensions/tika/runtime/pom.xml
+++ b/extensions/tika/runtime/pom.xml
@@ -52,6 +52,11 @@
<groupId>org.apache.camel</groupId>
<artifactId>camel-tika</artifactId>
</dependency>
+ <!-- PDFBox, brought by tika-parser-pdf-module, logs via
commons-logging -->
+ <dependency>
+ <groupId>org.apache.camel.quarkus</groupId>
+ <artifactId>camel-quarkus-support-commons-logging</artifactId>
+ </dependency>
</dependencies>
<build>
diff --git a/extensions/tika/runtime/src/main/doc/usage.adoc
b/extensions/tika/runtime/src/main/doc/usage.adoc
new file mode 100644
index 00000000000..abb0973b281
--- /dev/null
+++ b/extensions/tika/runtime/src/main/doc/usage.adoc
@@ -0,0 +1,17 @@
+=== Parser modules
+
+Tika parses only the formats whose parser module is on the classpath.
+`camel-tika` brings the HTML and plain text modules. For any other format, add
its module to your application, e.g. for PDF:
+
+[source,xml]
+----
+<dependency>
+ <groupId>org.apache.tika</groupId>
+ <artifactId>tika-parser-pdf-module</artifactId>
+</dependency>
+----
+
+The Camel Quarkus BOM manages the version of `tika-parser-pdf-module` only.
+For other modules, use the version of `org.apache.tika:tika-core` that
`camel-tika` brings.
+
+In native mode, the HTML, plain text and PDF modules are supported.
diff --git a/integration-tests/tika/pom.xml b/integration-tests/tika/pom.xml
index 2099891b831..2343e1065b0 100644
--- a/integration-tests/tika/pom.xml
+++ b/integration-tests/tika/pom.xml
@@ -35,6 +35,10 @@
<groupId>org.apache.camel.quarkus</groupId>
<artifactId>camel-quarkus-tika</artifactId>
</dependency>
+ <dependency>
+ <groupId>org.apache.tika</groupId>
+ <artifactId>tika-parser-pdf-module</artifactId>
+ </dependency>
<dependency>
<groupId>io.quarkus</groupId>
<artifactId>quarkus-resteasy</artifactId>
diff --git
a/integration-tests/tika/src/main/java/org/apache/camel/quarkus/component/tika/it/TikaResource.java
b/integration-tests/tika/src/main/java/org/apache/camel/quarkus/component/tika/it/TikaResource.java
index 4b8ef5d87cf..d312e443dde 100644
---
a/integration-tests/tika/src/main/java/org/apache/camel/quarkus/component/tika/it/TikaResource.java
+++
b/integration-tests/tika/src/main/java/org/apache/camel/quarkus/component/tika/it/TikaResource.java
@@ -41,6 +41,9 @@ public class TikaResource {
@Produces(MediaType.TEXT_PLAIN)
public Response parse(byte[] message) throws Exception {
final Exchange response = producerTemplate.request("tika:parse",
exchange -> exchange.getMessage().setBody(message));
+ if (response.getException() != null) {
+ throw response.getException();
+ }
return Response
.created(new URI("https://camel.apache.org/";))
.header("Parsed-Content-Type",
response.getMessage().getHeader(Exchange.CONTENT_TYPE))
diff --git
a/integration-tests/tika/src/test/java/org/apache/camel/quarkus/component/tika/it/TikaTest.java
b/integration-tests/tika/src/test/java/org/apache/camel/quarkus/component/tika/it/TikaTest.java
index 91033308b15..9420aa5eddf 100644
---
a/integration-tests/tika/src/test/java/org/apache/camel/quarkus/component/tika/it/TikaTest.java
+++
b/integration-tests/tika/src/test/java/org/apache/camel/quarkus/component/tika/it/TikaTest.java
@@ -16,14 +16,26 @@
*/
package org.apache.camel.quarkus.component.tika.it;
+import java.io.ByteArrayOutputStream;
+import java.io.IOException;
import java.io.InputStream;
import io.quarkus.test.junit.QuarkusTest;
import io.restassured.RestAssured;
import io.restassured.http.ContentType;
import io.restassured.response.ValidatableResponse;
+import org.apache.pdfbox.pdmodel.PDDocument;
+import org.apache.pdfbox.pdmodel.PDPage;
+import org.apache.pdfbox.pdmodel.PDPageContentStream;
+import org.apache.pdfbox.pdmodel.encryption.AccessPermission;
+import org.apache.pdfbox.pdmodel.encryption.StandardProtectionPolicy;
+import org.apache.pdfbox.pdmodel.font.PDFont;
+import org.apache.pdfbox.pdmodel.font.PDType0Font;
+import org.apache.pdfbox.pdmodel.font.PDType1Font;
+import org.apache.pdfbox.pdmodel.font.Standard14Fonts;
import org.junit.jupiter.api.Test;
+import static org.hamcrest.Matchers.containsString;
import static org.hamcrest.Matchers.containsStringIgnoringCase;
import static org.hamcrest.Matchers.is;
import static org.hamcrest.Matchers.startsWith;
@@ -45,6 +57,42 @@ class TikaTest {
testParse("quarkus.xml", "application/xml", "Hello Quarkus");
}
+ @Test
+ public void testPdf() throws Exception {
+ testParse("quarkus.pdf", "application/pdf", "Hello Quarkus");
+ }
+
+ @Test
+ public void testPdfWithIdentityHFont() throws Exception {
+ // PDType0Font embeds the font with the Identity-H encoding, a
predefined CMap which FontBox loads by name
+ try (PDDocument doc = new PDDocument();
+ InputStream font = TikaTest.class
+
.getResourceAsStream("/org/apache/pdfbox/resources/ttf/LiberationSans-Regular.ttf"))
{
+ testParsePdf(createPdf(doc, PDType0Font.load(doc, font), "Hello
Identity-H"), "Hello Identity-H");
+ }
+ }
+
+ @Test
+ public void testPdfWithNonEmbeddedFont() throws Exception {
+ // A standard 14 font is not embedded, PDFBox reads its metrics from
the AFM files in its resources
+ try (PDDocument doc = new PDDocument()) {
+ PDFont helvetica = new
PDType1Font(Standard14Fonts.FontName.HELVETICA);
+ testParsePdf(createPdf(doc, helvetica, "Hello Helvetica"), "Hello
Helvetica");
+ }
+ }
+
+ @Test
+ public void testEncryptedPdf() throws Exception {
+ // Only an owner password, so Tika opens the document with the empty
user password
+ try (PDDocument doc = new PDDocument()) {
+ StandardProtectionPolicy policy = new
StandardProtectionPolicy("owner", "", new AccessPermission());
+ policy.setEncryptionKeyLength(256);
+ doc.protect(policy);
+ PDFont helvetica = new
PDType1Font(Standard14Fonts.FontName.HELVETICA);
+ testParsePdf(createPdf(doc, helvetica, "Hello encrypted"), "Hello
encrypted");
+ }
+ }
+
@Test
public void testDetectDoc() throws Exception {
testDetect("test.doc", "application/x-tika-msoffice");
@@ -68,6 +116,17 @@ class TikaTest {
.body(containsStringIgnoringCase(expectedBody == null ?
"<body/>" : expectedBody));
}
+ private void testParsePdf(byte[] pdf, String expectedText) {
+ RestAssured.given()
+ .contentType(ContentType.BINARY)
+ .body(pdf)
+ .post("/tika/parse")
+ .then()
+ .statusCode(201)
+ .header("Parsed-Content-Type", startsWith("application/pdf"))
+ .body(containsString(expectedText));
+ }
+
private void testDetect(String fileName, String expectedContentType)
throws Exception {
post(fileName, "/tika/detect")
.body(is(expectedContentType));
@@ -82,6 +141,21 @@ class TikaTest {
.statusCode(201);
}
+ private static byte[] createPdf(PDDocument doc, PDFont font, String text)
throws IOException {
+ PDPage page = new PDPage();
+ doc.addPage(page);
+ try (PDPageContentStream content = new PDPageContentStream(doc, page))
{
+ content.beginText();
+ content.setFont(font, 12);
+ content.newLineAtOffset(50, 700);
+ content.showText(text);
+ content.endText();
+ }
+ ByteArrayOutputStream pdf = new ByteArrayOutputStream();
+ doc.save(pdf);
+ return pdf.toByteArray();
+ }
+
private byte[] readQuarkusFile(String fileName) throws Exception {
try (InputStream is =
getClass().getClassLoader().getResourceAsStream("assets/" + fileName)) {
if (is == null) {
diff --git a/poms/bom/pom.xml b/poms/bom/pom.xml
index 5bab737c159..417f981d6cf 100644
--- a/poms/bom/pom.xml
+++ b/poms/bom/pom.xml
@@ -8638,9 +8638,8 @@
<resolutionEntryPointInclude>com.ibm.icu:icu4j</resolutionEntryPointInclude>
<resolutionEntryPointInclude>com.sun.xml.fastinfoset:FastInfoset</resolutionEntryPointInclude>
<resolutionEntryPointInclude>org.mapstruct:mapstruct-processor</resolutionEntryPointInclude>
- <!-- Tika parses only the formats whose parser
modules are present; applications
- using the langchain4j-ingest tika parser
add the modules for their formats;
- moves to camel-quarkus-tika together with
the native build steps, see #9087 -->
+ <!-- Tika parses only the formats whose parser
modules are present; camel-quarkus-tika
+ applications add the modules for their
formats -->
<resolutionEntryPointInclude>org.apache.tika:tika-parser-pdf-module</resolutionEntryPointInclude>
</resolutionEntryPointIncludes>
<resolutionExcludes>
