From 747f22438da5076cc62879c6d776a60fd59a9656 Mon Sep 17 00:00:00 2001
From: Marcus van Elst <marcusvebo@gmail.com>
Date: Thu, 2 Apr 2026 15:10:47 +0200
Subject: [PATCH] Inhaltsfehler bei PDF-Extraktion korrekt klassifiziert

---
 .../service/DocumentProcessingService.java          | 13 ++++++++-----
 .../service/DocumentProcessingServiceTest.java      | 10 +++++-----
 2 files changed, 13 insertions(+), 10 deletions(-)

diff --git a/pdf-umbenenner-application/src/main/java/de/gecheckt/pdf/umbenenner/application/service/DocumentProcessingService.java b/pdf-umbenenner-application/src/main/java/de/gecheckt/pdf/umbenenner/application/service/DocumentProcessingService.java
index 7144b0a..25fe918 100644
--- a/pdf-umbenenner-application/src/main/java/de/gecheckt/pdf/umbenenner/application/service/DocumentProcessingService.java
+++ b/pdf-umbenenner-application/src/main/java/de/gecheckt/pdf/umbenenner/application/service/DocumentProcessingService.java
@@ -2,6 +2,7 @@ package de.gecheckt.pdf.umbenenner.application.service;
 
 import de.gecheckt.pdf.umbenenner.application.config.StartConfiguration;
 import de.gecheckt.pdf.umbenenner.domain.model.DocumentProcessingOutcome;
+import de.gecheckt.pdf.umbenenner.domain.model.PreCheckFailed;
 import de.gecheckt.pdf.umbenenner.domain.model.TechnicalDocumentError;
 import de.gecheckt.pdf.umbenenner.domain.model.PdfExtractionContentError;
 import de.gecheckt.pdf.umbenenner.domain.model.PdfExtractionResult;
@@ -16,7 +17,8 @@ import java.util.Objects;
  * <p>
  * Converts technical extraction results into processing outcomes through this pipeline:
  * <ol>
- *   <li>If extraction fails (content or technical): {@link TechnicalDocumentError}</li>
+ *   <li>If extraction fails (technical): {@link TechnicalDocumentError}</li>
+ *   <li>If extraction fails (content): {@link PreCheckFailed}</li>
  *   <li>If extraction succeeds: Evaluate pre-checks via {@link PreCheckEvaluator}</li>
  * </ol>
  * <p>
@@ -24,7 +26,7 @@ import java.util.Objects;
  * all document processing outcomes:
  * <ul>
  *   <li>Pre-check passed (document ready for further processing)</li>
- *   <li>Pre-check failed (deterministic content error: no usable text, page limit exceeded)</li>
+ *   <li>Pre-check failed (deterministic content error: no usable text, page limit exceeded, content not extractable)</li>
  *   <li>Technical document error (I/O, access, PDF parsing, etc.)</li>
  * </ul>
  * <p>
@@ -38,7 +40,8 @@ public class DocumentProcessingService {
      * Pipeline:
      * <ol>
      *   <li>Extract text and page count from the PDF candidate</li>
-     *   <li>If extraction fails (technical or content): classify as technical document error</li>
+     *   <li>If extraction fails (technical): classify as technical document error</li>
+     *   <li>If extraction fails (content): classify as pre-check failed (deterministic content error)</li>
      *   <li>If extraction succeeds: evaluate pre-checks</li>
      * </ol>
      *
@@ -63,8 +66,8 @@ public class DocumentProcessingService {
                 PreCheckEvaluator.evaluate(candidate, success, configuration);
 
             case PdfExtractionContentError contentError ->
-                // PDF content not extractable: classify as technical document error
-                new TechnicalDocumentError(candidate, "PDF content not extractable: " + contentError.reason(), null);
+                // PDF content not extractable: classify as pre-check failed (deterministic content error)
+                new PreCheckFailed(candidate, "PDF content not extractable: " + contentError.reason());
 
             case PdfExtractionTechnicalError technicalError ->
                 // Technical failure during extraction: potentially retryable
diff --git a/pdf-umbenenner-application/src/test/java/de/gecheckt/pdf/umbenenner/application/service/DocumentProcessingServiceTest.java b/pdf-umbenenner-application/src/test/java/de/gecheckt/pdf/umbenenner/application/service/DocumentProcessingServiceTest.java
index 8fc1bc4..eeda255 100644
--- a/pdf-umbenenner-application/src/test/java/de/gecheckt/pdf/umbenenner/application/service/DocumentProcessingServiceTest.java
+++ b/pdf-umbenenner-application/src/test/java/de/gecheckt/pdf/umbenenner/application/service/DocumentProcessingServiceTest.java
@@ -119,18 +119,18 @@ class DocumentProcessingServiceTest {
 
     @Test
     void testProcessDocument_WithContentError() {
-        // Arrange: PDF content not extractable (classified as technical document error)
+        // Arrange: PDF content not extractable (classified as pre-check failed)
         var contentError = new PdfExtractionContentError("PDF is corrupted");
 
         // Act
         DocumentProcessingOutcome outcome = DocumentProcessingService.processDocument(
                 candidate, contentError, configuration);
 
-        // Assert: Should produce TechnicalDocumentError
-        assertInstanceOf(TechnicalDocumentError.class, outcome);
-        TechnicalDocumentError result = (TechnicalDocumentError) outcome;
+        // Assert: Should produce PreCheckFailed
+        assertInstanceOf(PreCheckFailed.class, outcome);
+        PreCheckFailed result = (PreCheckFailed) outcome;
         assertEquals(candidate, result.candidate());
-        assertTrue(result.errorMessage().contains("PDF is corrupted"));
+        assertTrue(result.failureReason().contains("PDF is corrupted"));
     }
 
     @Test