fix(ocr): emit valid Markdown newlines for PPTX conversion

packages/markitdown-ocr/src/markitdown_ocr/_pptx_converter_with_ocr.py

@@ -80,7 +80,7 @@ def convert(
 
         for slide in presentation.slides:
             slide_num += 1
-            md_content += f"\\n\\n<!-- Slide number: {slide_num} -->\\n"
+            md_content += f"\n\n<!-- Slide number: {slide_num} -->\n"
 
             title = slide.shapes.title
 
@@ -96,7 +96,7 @@ def get_shape_content(shape, **kwargs):
                     llm_description = ""
                     if llm_client and kwargs.get("llm_model"):
                         try:
-                            from ._llm_caption import llm_caption
+                            from markitdown.converters._llm_caption import llm_caption
 
                             image_filename = shape.image.filename
                             image_extension = None
@@ -148,9 +148,9 @@ def get_shape_content(shape, **kwargs):
                 # Text areas
                 elif shape.has_text_frame:
                     if shape == title:
-                        md_content += "# " + shape.text.lstrip() + "\\n"
+                        md_content += "# " + shape.text.lstrip() + "\n"
                     else:
-                        md_content += shape.text + "\\n"
+                        md_content += shape.text + "\n"
 
                 # Group Shapes
                 if shape.shape_type == pptx.enum.shapes.MSO_SHAPE_TYPE.GROUP:
@@ -177,7 +177,7 @@ def get_shape_content(shape, **kwargs):
             md_content = md_content.strip()
 
             if slide.has_notes_slide:
-                md_content += "\\n\\n### Notes:\\n"
+                md_content += "\n\n### Notes:\n"
                 notes_frame = slide.notes_slide.notes_text_frame
                 if notes_frame is not None:
                     md_content += notes_frame.text
@@ -216,15 +216,15 @@ def _convert_table_to_markdown(self, table, **kwargs):
 
         return (
             self._html_converter.convert_string(html_table, **kwargs).markdown.strip()
-            + "\\n"
+            + "\n"
         )
 
     def _convert_chart_to_markdown(self, chart):
         try:
-            md = "\\n\\n### Chart"
+            md = "\n\n### Chart"
             if chart.has_title:
                 md += f": {chart.chart_title.text_frame.text}"
-            md += "\\n\\n"
+            md += "\n\n"
             data = []
             category_names = [c.label for c in chart.plots[0].categories]
             series_names = [s.name for s in chart.series]
@@ -241,9 +241,9 @@ def _convert_chart_to_markdown(self, chart):
                 markdown_table.append("| " + " | ".join(map(str, row)) + " |")
             header = markdown_table[0]
             separator = "|" + "|".join(["---"] * len(data[0])) + "|"
-            return md + "\\n".join([header, separator] + markdown_table[1:])
+            return md + "\n".join([header, separator] + markdown_table[1:])
         except ValueError as e:
             if "unsupported plot type" in str(e):
-                return "\\n\\n[unsupported chart]\\n\\n"
+                return "\n\n[unsupported chart]\n\n"
         except Exception:
-            return "\\n\\n[unsupported chart]\\n\\n"
+            return "\n\n[unsupported chart]\n\n"

packages/markitdown-ocr/tests/test_pptx_converter.py

@@ -9,13 +9,12 @@
     MOCK_OCR_TEXT_12345
     [End OCR]*
 
-Note: PPTX slide text uses literal backslash-n (\\n) sequences from the
-underlying PPTX converter template; OCR blocks use real newlines.
 """
 
 import sys
 from pathlib import Path
 from typing import Any
+from unittest.mock import patch
 
 import pytest
 
@@ -66,8 +65,8 @@ def _convert(filename: str, ocr_service: MockOCRService) -> str:
 def test_pptx_image_start(svc: MockOCRService) -> None:
     # Slide 1: title "Welcome" followed by an image
     expected = (
-        "\\n\\n<!-- Slide number: 1 -->\\n# Welcome\\n\\n"
-        "\n*[Image OCR]\nMOCK_OCR_TEXT_12345\n[End OCR]*"
+        "<!-- Slide number: 1 -->\n# Welcome\n\n\n"
+        "*[Image OCR]\nMOCK_OCR_TEXT_12345\n[End OCR]*"
     )
     assert _convert("pptx_image_start.pptx", svc) == expected
 
@@ -80,10 +79,10 @@ def test_pptx_image_start(svc: MockOCRService) -> None:
 def test_pptx_image_middle(svc: MockOCRService) -> None:
     # Slide 1: Introduction | Slide 2: Architecture + image | Slide 3: Conclusion  # noqa: E501
     expected = (
-        "\\n\\n<!-- Slide number: 1 -->\\n# Introduction"
-        "\\n\\n\\n\\n<!-- Slide number: 2 -->\\n# Architecture\\n\\n"
-        "\n*[Image OCR]\nMOCK_OCR_TEXT_12345\n[End OCR]*"
-        "\\n\\n<!-- Slide number: 3 -->\\n# Conclusion\\n\\n"
+        "<!-- Slide number: 1 -->\n# Introduction"
+        "\n\n<!-- Slide number: 2 -->\n# Architecture\n\n\n"
+        "*[Image OCR]\nMOCK_OCR_TEXT_12345\n[End OCR]*"
+        "\n\n<!-- Slide number: 3 -->\n# Conclusion"
     )
     assert _convert("pptx_image_middle.pptx", svc) == expected
 
@@ -96,9 +95,9 @@ def test_pptx_image_middle(svc: MockOCRService) -> None:
 def test_pptx_image_end(svc: MockOCRService) -> None:
     # Slide 1: Presentation | Slide 2: Thank You + image
     expected = (
-        "\\n\\n<!-- Slide number: 1 -->\\n# Presentation"
-        "\\n\\n\\n\\n<!-- Slide number: 2 -->\\n# Thank You\\n\\n"
-        "\n*[Image OCR]\nMOCK_OCR_TEXT_12345\n[End OCR]*"
+        "<!-- Slide number: 1 -->\n# Presentation"
+        "\n\n<!-- Slide number: 2 -->\n# Thank You\n\n\n"
+        "*[Image OCR]\nMOCK_OCR_TEXT_12345\n[End OCR]*"
     )
     assert _convert("pptx_image_end.pptx", svc) == expected
 
@@ -111,8 +110,8 @@ def test_pptx_image_end(svc: MockOCRService) -> None:
 def test_pptx_multiple_images(svc: MockOCRService) -> None:
     # Slide 1: two images, no title text
     expected = (
-        "\\n\\n<!-- Slide number: 1 -->\\n# \\n"
-        "\n*[Image OCR]\nMOCK_OCR_TEXT_12345\n[End OCR]*"
+        "<!-- Slide number: 1 -->\n# \n\n"
+        "*[Image OCR]\nMOCK_OCR_TEXT_12345\n[End OCR]*"
         "\n\n*[Image OCR]\nMOCK_OCR_TEXT_12345\n[End OCR]*"
     )
     assert _convert("pptx_multiple_images.pptx", svc) == expected
@@ -125,9 +124,9 @@ def test_pptx_multiple_images(svc: MockOCRService) -> None:
 
 def test_pptx_complex_layout(svc: MockOCRService) -> None:
     expected = (
-        "\\n\\n<!-- Slide number: 1 -->\\n# Product Comparison"
-        "\\n\\nOur products lead the market\\n"
-        "\n*[Image OCR]\nMOCK_OCR_TEXT_12345\n[End OCR]*"
+        "<!-- Slide number: 1 -->\n# Product Comparison"
+        "\n\nOur products lead the market\n\n"
+        "*[Image OCR]\nMOCK_OCR_TEXT_12345\n[End OCR]*"
     )
     assert _convert("pptx_complex_layout.pptx", svc) == expected
 
@@ -146,3 +145,29 @@ def test_pptx_no_ocr_service_no_tags() -> None:
         md = converter.convert(f, StreamInfo(extension=".pptx")).text_content
     assert "*[Image OCR]" not in md
     assert "[End OCR]*" not in md
+
+
+def test_pptx_output_does_not_contain_literal_newlines(svc: MockOCRService) -> None:
+    md = _convert("pptx_image_start.pptx", svc)
+    assert "\\n" not in md
+
+
+def test_pptx_uses_core_llm_caption() -> None:
+    path = TEST_DATA_DIR / "pptx_image_start.pptx"
+    if not path.exists():
+        pytest.skip(f"Test file not found: {path}")
+
+    converter = PptxConverterWithOCR()
+    with patch(
+        "markitdown.converters._llm_caption.llm_caption", return_value="MOCK_CAPTION"
+    ) as mock_caption:
+        with open(path, "rb") as f:
+            md = converter.convert(
+                f,
+                StreamInfo(extension=".pptx"),
+                llm_client=object(),
+                llm_model="test-model",
+            ).text_content
+
+    assert "MOCK_CAPTION" in md
+    mock_caption.assert_called_once()