markitdown-pro 1.0.3__tar.gz → 1.0.4__tar.gz

{markitdown_pro-1.0.3 → markitdown_pro-1.0.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: markitdown-pro
-Version: 1.0.3
+Version: 1.0.4
 Summary: A package that converts almost any file format to Markdown.
 Author: Developer
 Classifier: Programming Language :: Python :: 3

{markitdown_pro-1.0.3 → markitdown_pro-1.0.4}/markitdown_pro/conversion_pipeline.py

@@ -186,14 +186,12 @@ class ConversionPipeline:
             raise RuntimeError(f"No handler for extension '{extension}'.")
 
         try:
-            logger.debug(f"convert_document_to_md: Using handler for extension '{extension}'")
             md_content = await handler.handle(str(file_path))
             if not md_content or not ensure_minimum_content(md_content):
                 return None
 
             logger.debug(
-                "convert_document_to_md: Handler returned %d characters",
-                len(md_content),
+                f"convert_document_to_md: {file_path} returned {len(md_content)} characters"
             )
             return _write_md(output_md, md_content) if output_md else md_content
 

{markitdown_pro-1.0.3 → markitdown_pro-1.0.4}/markitdown_pro/handlers/pdf_handler.py

@@ -164,8 +164,12 @@ class PDFHandler(BaseHandler):
                         if page.get_images(full=True):
                             pages_with_images += 1
 
-                    logger.debug(f"Pages with text: {pages_with_text}/{total_pages}")
-                    logger.debug(f"Pages with images: {pages_with_images}/{total_pages}")
+                    logger.debug(
+                        f"PDFHandler: Pages with text for {file_path}: {pages_with_text}/{total_pages}"
+                    )
+                    logger.debug(
+                        f"PDFHandler: Pages with images for {file_path}: {pages_with_images}/{total_pages}"
+                    )
 
                     is_text_only = pages_with_text == total_pages and pages_with_images == 0
                     is_all_images = pages_with_images == total_pages and pages_with_text == 0

{markitdown_pro-1.0.3 → markitdown_pro-1.0.4}/markitdown_pro/services/openai_services.py

@@ -436,7 +436,7 @@ class GPTVision:
                                 )
                             except asyncio.TimeoutError:
                                 logger.error(
-                                    f"ocr_page: Page {page_index} timed out after {self.page_timeout_s}s"
+                                    f"ocr_page: {file_stem} - page {page_index} timed out after {self.page_timeout_s}s"
                                 )
                                 partial_md = "[Timed out]"
 
@@ -448,7 +448,7 @@ class GPTVision:
                                 logger.warning(
                                     f"ocr_page: {file_stem} - page {page_index}: no OCR result"
                                 )
-                                partial_md = "[No OCR result]"
+                                partial_md = ""
                             return (page_index, f"## Page {page_index + 1}\n\n{partial_md}")
                         finally:
                             await self._safe_unlink(png_path)

{markitdown_pro-1.0.3 → markitdown_pro-1.0.4}/markitdown_pro.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: markitdown-pro
-Version: 1.0.3
+Version: 1.0.4
 Summary: A package that converts almost any file format to Markdown.
 Author: Developer
 Classifier: Programming Language :: Python :: 3

{markitdown_pro-1.0.3 → markitdown_pro-1.0.4}/setup.py

@@ -2,7 +2,7 @@ from setuptools import find_packages, setup
 
 setup(
     name="markitdown-pro",
-    version="1.0.3",
+    version="1.0.4",
     author="Developer",
     description="A package that converts almost any file format to Markdown.",
     long_description=open("README.md").read(),