Merge pull request #33 from nyosegawa/feature/add-pptx-chart-support

Add PPTX chart support

src/markitdown/_markitdown.py

@@ -582,6 +582,10 @@ class PptxConverter(HtmlConverter):
                         "\n" + self._convert(html_table).text_content.strip() + "\n"
                     )
 
+                # Charts
+                if shape.has_chart:
+                    md_content += self._convert_chart_to_markdown(shape.chart)
+
                 # Text areas
                 elif shape.has_text_frame:
                     if shape == title:
@@ -616,6 +620,29 @@ class PptxConverter(HtmlConverter):
             return True
         return False
 
+    def _convert_chart_to_markdown(self, chart):
+        md = "\n\n### Chart"
+        if chart.has_title:
+            md += f": {chart.chart_title.text_frame.text}"
+        md += "\n\n"
+        data = []
+        category_names = [c.label for c in chart.plots[0].categories]
+        series_names = [s.name for s in chart.series]
+        data.append(["Category"] + series_names)
+
+        for idx, category in enumerate(category_names):
+            row = [category]
+            for series in chart.series:
+                row.append(series.values[idx])
+            data.append(row)
+
+        markdown_table = []
+        for row in data:
+            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:])
+
 
 class MediaConverter(DocumentConverter):
     """

tests/test_markitdown.py

@@ -57,6 +57,8 @@ PPTX_TEST_STRINGS = [
     "44bf7d06-5e7a-4a40-a2e1-a2e42ef28c8a",
     "1b92870d-e3b5-4e65-8153-919f4ff45592",
     "AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation",
+    "a3f6004b-6f4f-4ea8-bee3-3741f4dc385f",  # chart title
+    "2003",  # chart value
 ]
 
 BLOG_TEST_URL = "https://microsoft.github.io/autogen/blog/2023/04/21/LLM-tuning-math"