From 02808799686c1fc455639f14b774c6fa1e98b5e2 Mon Sep 17 00:00:00 2001
From: ValueOn AG <p.motsch@valueon.ch>
Date: Sun, 28 Dec 2025 14:08:28 +0100
Subject: [PATCH] module tests completed

---
 .../mainServiceExtraction.py                  |  2 +-
 .../renderers/rendererHtml.py                 | 30 ++++++++++++-------
 .../serviceGeneration/subDocumentUtility.py   | 10 +++++++
 3 files changed, 30 insertions(+), 12 deletions(-)

diff --git a/modules/services/serviceExtraction/mainServiceExtraction.py b/modules/services/serviceExtraction/mainServiceExtraction.py
index ba4bfb69..33edb6c7 100644
--- a/modules/services/serviceExtraction/mainServiceExtraction.py
+++ b/modules/services/serviceExtraction/mainServiceExtraction.py
@@ -240,7 +240,7 @@ class ExtractionService:
                             partSummary["dataPreview"] = f"[Large data: {len(part.data)} chars - truncated]"
                         extractionSummary["parts"].append(partSummary)
                     
-                    writeDebugFile(json.dumps(extractionSummary, indent=2, ensure_ascii=False), f"extraction_result_{doc.fileName}")
+                    writeDebugFile(json.dumps(extractionSummary, indent=2, ensure_ascii=False), f"extraction_result_{doc.fileName}.txt")
                 except Exception as e:
                     logger.debug(f"Failed to write extraction debug file: {str(e)}")
                 
diff --git a/modules/services/serviceGeneration/renderers/rendererHtml.py b/modules/services/serviceGeneration/renderers/rendererHtml.py
index 275302b6..17ac25b3 100644
--- a/modules/services/serviceGeneration/renderers/rendererHtml.py
+++ b/modules/services/serviceGeneration/renderers/rendererHtml.py
@@ -700,12 +700,19 @@ class RendererHtml(BaseRenderer):
             import base64
             import re
             
-            # Find all image data URIs in HTML (verschiedene MIME-Types unterstützen)
-            # Pattern: data:image/[type];base64,<base64>
-            dataUriPattern = r'data:image/[^;]+;base64,([A-Za-z0-9+/=]+)'
+            # Find entire img tags with data URIs and replace them
+            # Pattern: <img src="data:image/[type];base64,<base64>" [other attributes]>
+            imgTagPattern = r'<img\s+src="data:image/[^"]+"[^>]*>'
             
-            def replaceDataUri(match):
-                base64Data = match.group(1)
+            def replaceImgTag(match):
+                imgTag = match.group(0)
+                
+                # Extract base64 data from the img tag
+                base64Match = re.search(r'data:image/[^;]+;base64,([A-Za-z0-9+/=]+)', imgTag)
+                if not base64Match:
+                    return imgTag  # Return original if no base64 found
+                
+                base64Data = base64Match.group(1)
                 
                 # Find matching image in images list
                 matchingImage = None
@@ -721,12 +728,13 @@ class RendererHtml(BaseRenderer):
                     # Use filename from image data (generated from section ID)
                     filename = matchingImage.get("filename", f"image_{images.index(matchingImage) + 1}.png")
                     
-                    # Replace with relative path (ohne Pfad, nur Dateiname)
-                    # Escape HTML in altText and caption to prevent injection
-                    altText = html.escape(str(matchingImage.get("altText", "Image")))
+                    # Extract existing alt text or use from matchingImage
+                    altMatch = re.search(r'alt="([^"]*)"', imgTag)
+                    existingAlt = altMatch.group(1) if altMatch else ""
+                    altText = html.escape(str(matchingImage.get("altText", existingAlt or "Image")))
                     caption = html.escape(str(matchingImage.get("caption", ""))) if matchingImage.get("caption") else ""
                     
-                    # Entferne IMAGE_MARKER Kommentar falls vorhanden
+                    # Create new img tag with filename
                     imgTag = f'<img src="{filename}" alt="{altText}">'
                     
                     if caption:
@@ -737,8 +745,8 @@ class RendererHtml(BaseRenderer):
                     # Keep original if no match found
                     return match.group(0)
             
-            # Replace all data URIs (auch IMAGE_MARKER Kommentare entfernen)
-            updatedHtml = re.sub(dataUriPattern, replaceDataUri, htmlContent)
+            # Replace all img tags with data URIs (auch IMAGE_MARKER Kommentare entfernen)
+            updatedHtml = re.sub(imgTagPattern, replaceImgTag, htmlContent)
             # Entferne IMAGE_MARKER Kommentare die übrig geblieben sind
             updatedHtml = re.sub(r'<!--IMAGE_MARKER:[^>]+-->', '', updatedHtml)
             
diff --git a/modules/services/serviceGeneration/subDocumentUtility.py b/modules/services/serviceGeneration/subDocumentUtility.py
index abef95da..329f09f6 100644
--- a/modules/services/serviceGeneration/subDocumentUtility.py
+++ b/modules/services/serviceGeneration/subDocumentUtility.py
@@ -180,6 +180,16 @@ def convertDocumentDataToString(document_data: Any, file_extension: str) -> str:
     try:
         if document_data is None:
             return ""
+        if isinstance(document_data, bytes):
+            # WICHTIG: Decode bytes to string for text files (HTML, text, etc.)
+            try:
+                return document_data.decode('utf-8')
+            except UnicodeDecodeError:
+                # Fallback: try latin1 or return with error replacement
+                try:
+                    return document_data.decode('latin1')
+                except Exception:
+                    return document_data.decode('utf-8', errors='replace')
         if isinstance(document_data, str):
             return document_data
         if isinstance(document_data, dict):