From df15f54f4b762e17afcf6c9bc5b52c4b27277736 Mon Sep 17 00:00:00 2001 From: ValueOn AG Date: Sun, 12 Oct 2025 02:27:55 +0200 Subject: [PATCH] renderers html and md tested and fixed --- .../renderers/rendererHtml.py | 1 + test_document_processing.py | 23 +++++++++++++------ 2 files changed, 17 insertions(+), 7 deletions(-) diff --git a/modules/services/serviceGeneration/renderers/rendererHtml.py b/modules/services/serviceGeneration/renderers/rendererHtml.py index 79d9df1e..5cd9b691 100644 --- a/modules/services/serviceGeneration/renderers/rendererHtml.py +++ b/modules/services/serviceGeneration/renderers/rendererHtml.py @@ -156,6 +156,7 @@ class RendererHtml(BaseRenderer): self.logger.warning(f"Style validation failed: {str(e)}") return self._get_default_html_styles() + def _get_default_html_styles(self) -> Dict[str, Any]: """Default HTML styles.""" return { diff --git a/test_document_processing.py b/test_document_processing.py index b89b238f..53fbd80d 100644 --- a/test_document_processing.py +++ b/test_document_processing.py @@ -168,7 +168,7 @@ async def process_documents_and_generate_summary(): prompt=userPrompt, documents=documents, options=ai_options, - outputFormat="pdf", + outputFormat="html", title="Formulaire" ) @@ -270,13 +270,15 @@ async def process_documents_and_generate_summary(): file_ext = '.xlsx' elif 'pptx' in doc_mime.lower() or 'presentationml' in doc_mime.lower(): file_ext = '.pptx' + elif 'markdown' in doc_mime.lower() or 'md' in doc_mime.lower(): + file_ext = '.md' else: logger.warning(f"⚠️ Unknown MIME type: {doc_mime}, using .bin") # Also check filename for hints if doc_name and '.' in doc_name: name_ext = '.' + doc_name.split('.')[-1].lower() - if name_ext in ['.docx', '.pdf', '.txt', '.html', '.json', '.csv', '.xlsx', '.pptx']: + if name_ext in ['.docx', '.pdf', '.txt', '.html', '.json', '.csv', '.xlsx', '.pptx', '.md']: file_ext = name_ext logger.info(f"📄 Using extension from filename: {file_ext}") @@ -284,12 +286,19 @@ async def process_documents_and_generate_summary(): # Save document output_path = output_dir / f"{test_name}_{timestamp}{file_ext}" - doc_bytes = base64.b64decode(doc_data) - with open(output_path, 'wb') as f: - f.write(doc_bytes) - - logger.info(f"✅ Document saved: {output_path} ({len(doc_bytes)} bytes)") + # Handle different content types + if file_ext in ['.md', '.txt', '.html', '.json', '.csv']: + # Text-based formats - save directly as text + with open(output_path, 'w', encoding='utf-8') as f: + f.write(doc_data) + logger.info(f"✅ Document saved as text: {output_path} ({len(doc_data)} characters)") + else: + # Binary formats - decode from base64 + doc_bytes = base64.b64decode(doc_data) + with open(output_path, 'wb') as f: + f.write(doc_bytes) + logger.info(f"✅ Document saved as binary: {output_path} ({len(doc_bytes)} bytes)") # Also save raw content as text content = response.get('content', '')