feat(detect): add .pptx extraction support

graphify/detect.py

@@ -31,7 +31,7 @@ class FileType(str, Enum):
 DOC_EXTENSIONS = {'.md', '.mdx', '.qmd', '.txt', '.rst', '.html', '.yaml', '.yml'}
 PAPER_EXTENSIONS = {'.pdf'}
 IMAGE_EXTENSIONS = {'.png', '.jpg', '.jpeg', '.gif', '.webp', '.svg'}
-OFFICE_EXTENSIONS = {'.docx', '.xlsx'}
+OFFICE_EXTENSIONS = {'.docx', '.xlsx', '.pptx'}
 VIDEO_EXTENSIONS = {'.mp4', '.mov', '.webm', '.mkv', '.avi', '.m4v', '.mp3', '.wav', '.m4a', '.ogg'}
 
 CORPUS_WARN_THRESHOLD = 50_000    # words - below this, warn "you may not need a graph"
@@ -621,8 +621,30 @@ def _edge(src: str, tgt: str, relation: str) -> None:
     return {"nodes": nodes, "edges": edges}
 
 
+def pptx_to_markdown(path: Path) -> str:
+    """Convert a .pptx file to markdown text using python-pptx."""
+    if not _zip_within_caps(path):
+        return ""
+    try:
+        from pptx import Presentation
+        prs = Presentation(str(path))
+        lines = []
+        for i, slide in enumerate(prs.slides, start=1):
+            lines.append(f"## Slide {i}")
+            for shape in slide.shapes:
+                if shape.has_text_frame:
+                    text = shape.text_frame.text.strip()
+                    if text:
+                        lines.append(text)
+        return "\n".join(lines)
+    except ImportError:
+        return ""
+    except Exception:
+        return ""
+
+
 def convert_office_file(path: Path, out_dir: Path) -> Path | None:
-    """Convert a .docx or .xlsx to a markdown sidecar in out_dir.
+    """Convert a .docx, .xlsx, or .pptx to a markdown sidecar in out_dir.
 
     Returns the path of the converted .md file, or None if conversion failed
     or the required library is not installed.
@@ -632,6 +654,8 @@ def convert_office_file(path: Path, out_dir: Path) -> Path | None:
         text = docx_to_markdown(path)
     elif ext == ".xlsx":
         text = xlsx_to_markdown(path)
+    elif ext == ".pptx":
+        text = pptx_to_markdown(path)
     else:
         return None
 
@@ -679,6 +703,8 @@ def count_words(path: Path) -> int:
             return len(docx_to_markdown(path).split())
         if ext == ".xlsx":
             return len(xlsx_to_markdown(path).split())
+        if ext == ".pptx":
+            return len(pptx_to_markdown(path).split())
         with open(_os_path(path), encoding="utf-8", errors="ignore") as f:
             return len(f.read().split())
     except Exception:

pyproject.toml

@@ -58,7 +58,7 @@ pdf = ["pypdf>=6.12.0", "markdownify"]
 watch = ["watchdog"]
 svg = ["matplotlib", "numpy>=2.0; python_version >= '3.13'"]
 leiden = ["graspologic; python_version < '3.13'"]
-office = ["python-docx", "openpyxl"]
+office = ["python-docx", "openpyxl", "python-pptx"]
 google = ["openpyxl"]
 postgres = ["psycopg[binary]"]
 video = ["faster-whisper; python_version >= '3.11'", "yt-dlp>=2026.6.9"]
@@ -80,7 +80,7 @@ pascal = ["tree-sitter-pascal"]
 # avoids breaking the default `uv tool install graphifyy` for everyone (#1104).
 dm = ["tree-sitter-dm"]
 terraform = ["tree-sitter-hcl"]
-all = ["mcp", "starlette>=1.3.1", "neo4j", "falkordb", "pypdf>=6.12.0", "markdownify", "watchdog", "graspologic; python_version < '3.13'", "python-docx", "openpyxl", "faster-whisper; python_version >= '3.11'", "yt-dlp>=2026.6.9", "matplotlib", "numpy>=2.0; python_version >= '3.13'", "openai", "tiktoken", "boto3", "anthropic", "tree-sitter-sql", "jieba", "tree-sitter-dm", "tree-sitter-hcl", "tree-sitter-pascal"]
+all = ["mcp", "starlette>=1.3.1", "neo4j", "falkordb", "pypdf>=6.12.0", "markdownify", "watchdog", "graspologic; python_version < '3.13'", "python-docx", "openpyxl", "python-pptx", "faster-whisper; python_version >= '3.11'", "yt-dlp>=2026.6.9", "matplotlib", "numpy>=2.0; python_version >= '3.13'", "openai", "tiktoken", "boto3", "anthropic", "tree-sitter-sql", "jieba", "tree-sitter-dm", "tree-sitter-hcl", "tree-sitter-pascal"]
 
 [project.scripts]
 graphify = "graphify.__main__:main"

tests/test_detect.py

@@ -1632,3 +1632,73 @@ def test_detect_surfaces_unreadable_dir_instead_of_silent_skip(tmp_path, capsys)
     assert any(f.endswith("a.py") for f in code)  # rest of tree still enumerated
     assert len(res["walk_errors"]) >= 1
     assert "could not scan" in capsys.readouterr().err
+
+def test_classify_docx():
+    assert classify_file(Path("report.docx")) == FileType.DOCUMENT
+
+def test_classify_xlsx():
+    assert classify_file(Path("data.xlsx")) == FileType.DOCUMENT
+
+def test_classify_pptx():
+    assert classify_file(Path("slides.pptx")) == FileType.DOCUMENT
+
+import pytest
+
+def test_docx_to_markdown(tmp_path):
+    pytest.importorskip("docx")
+    from docx import Document
+    from graphify.detect import docx_to_markdown
+    doc = Document()
+    doc.add_heading("Title", level=1)
+    doc.add_paragraph("Hello world content here.")
+    path = tmp_path / "test.docx"
+    doc.save(path)
+    text = docx_to_markdown(path)
+    assert "Hello" in text or "Title" in text
+
+def test_xlsx_to_markdown(tmp_path):
+    pytest.importorskip("openpyxl")
+    import openpyxl
+    from graphify.detect import xlsx_to_markdown
+    wb = openpyxl.Workbook()
+    ws = wb.active
+    ws.title = "Revenue"
+    ws.append(["Month", "Amount", "Region"])
+    ws.append(["Jan", 1000, "North"])
+    path = tmp_path / "data.xlsx"
+    wb.save(path)
+    text = xlsx_to_markdown(path)
+    assert "Revenue" in text
+    assert "Month" in text
+    assert "Amount" in text
+
+def test_pptx_to_markdown(tmp_path):
+    pytest.importorskip("pptx")
+    from pptx import Presentation
+    from graphify.detect import pptx_to_markdown
+    prs = Presentation()
+    slide = prs.slides.add_slide(prs.slide_layouts[0])
+    slide.shapes.title.text = "Q4 Strategy"
+    path = tmp_path / "deck.pptx"
+    prs.save(path)
+    text = pptx_to_markdown(path)
+    assert "Q4 Strategy" in text
+
+def test_pptx_to_markdown_returns_empty_on_error(tmp_path):
+    from graphify.detect import pptx_to_markdown
+    fake = tmp_path / "corrupt.pptx"
+    fake.write_bytes(b"not a real pptx")
+    result = pptx_to_markdown(fake)
+    assert isinstance(result, str)
+    assert result == ""
+
+def test_count_words_docx(tmp_path):
+    pytest.importorskip("docx")
+    from docx import Document
+    doc = Document()
+    doc.add_heading("Title", level=1)
+    doc.add_paragraph("This document has several words in it.")
+    docx = tmp_path / "test.docx"
+    doc.save(docx)
+    from graphify.detect import count_words
+    assert count_words(docx) > 5