requirements-as-code 0.3.0__tar.gz → 0.3.1__tar.gz

{requirements_as_code-0.3.0/requirements_as_code.egg-info → requirements_as_code-0.3.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: requirements-as-code
-Version: 0.3.0
+Version: 0.3.1
 Summary: RAC — lint and diff product requirements written in Markdown.
 Author: tcballard
 License-Expression: MIT
@@ -23,10 +23,19 @@ License-File: LICENSE
 Requires-Dist: markdown-it-py>=3.0
 Provides-Extra: ingest
 Requires-Dist: markitdown[docx]; extra == "ingest"
+Provides-Extra: ingest-pdf
+Requires-Dist: markitdown[pdf]; extra == "ingest-pdf"
+Provides-Extra: ingest-office
+Requires-Dist: markitdown[pptx,xls,xlsx]; extra == "ingest-office"
+Provides-Extra: ingest-all
+Requires-Dist: markitdown[docx,pdf,pptx,xls,xlsx]; extra == "ingest-all"
 Provides-Extra: dev
 Requires-Dist: pytest>=7.0; extra == "dev"
-Requires-Dist: markitdown[docx]; extra == "dev"
+Requires-Dist: markitdown[docx,pdf,pptx,xls,xlsx]; extra == "dev"
 Requires-Dist: python-docx; extra == "dev"
+Requires-Dist: python-pptx; extra == "dev"
+Requires-Dist: openpyxl; extra == "dev"
+Requires-Dist: reportlab; extra == "dev"
 Dynamic: license-file
 
 # RAC (Requirements-as-Code)
@@ -436,15 +445,25 @@ rac ingest spec.docx --json       # { source, converter, output, markdown }
 ```
 
 Conversion is powered by [MarkItDown](https://github.com/microsoft/markitdown),
-installed via the optional `ingest` extra:
+installed via optional extras — split by format so you only pull the readers you
+need:
+
+| Extra | Adds | Formats |
+|-------|------|---------|
+| `ingest` | `markitdown[docx]` | DOCX, HTML, Markdown |
+| `ingest-pdf` | `markitdown[pdf]` | + PDF |
+| `ingest-office` | `markitdown[pptx,xlsx,xls]` | + PPTX, XLSX, XLS |
+| `ingest-all` | everything above | all supported formats |
 
 ```bash
-pip install "requirements-as-code[ingest]"
+pip install "requirements-as-code[ingest]"       # DOCX + HTML + Markdown
+pip install "requirements-as-code[ingest-all]"    # everything
 ```
 
-Supported today: **DOCX** and **Markdown** (pass-through). HTML and PDF are
-planned for v0.3.x. Converters live behind a `DocumentConverter` abstraction, so
-new sources can be added without changing the CLI.
+HTML and Markdown need no extra (HTML is built into MarkItDown; Markdown is a
+pass-through). If a file's reader isn't installed, `rac ingest` tells you exactly
+which extra to install. Converters live behind a `DocumentConverter` abstraction,
+so new sources can be added without changing the CLI.
 
 `ingest` exits `0` on success, `1` if a recognized document fails to convert, and
 `2` for usage errors (file not found, unsupported type, missing `ingest` extra,

{requirements_as_code-0.3.0 → requirements_as_code-0.3.1}/README.md

@@ -405,15 +405,25 @@ rac ingest spec.docx --json       # { source, converter, output, markdown }
 ```
 
 Conversion is powered by [MarkItDown](https://github.com/microsoft/markitdown),
-installed via the optional `ingest` extra:
+installed via optional extras — split by format so you only pull the readers you
+need:
+
+| Extra | Adds | Formats |
+|-------|------|---------|
+| `ingest` | `markitdown[docx]` | DOCX, HTML, Markdown |
+| `ingest-pdf` | `markitdown[pdf]` | + PDF |
+| `ingest-office` | `markitdown[pptx,xlsx,xls]` | + PPTX, XLSX, XLS |
+| `ingest-all` | everything above | all supported formats |
 
 ```bash
-pip install "requirements-as-code[ingest]"
+pip install "requirements-as-code[ingest]"       # DOCX + HTML + Markdown
+pip install "requirements-as-code[ingest-all]"    # everything
 ```
 
-Supported today: **DOCX** and **Markdown** (pass-through). HTML and PDF are
-planned for v0.3.x. Converters live behind a `DocumentConverter` abstraction, so
-new sources can be added without changing the CLI.
+HTML and Markdown need no extra (HTML is built into MarkItDown; Markdown is a
+pass-through). If a file's reader isn't installed, `rac ingest` tells you exactly
+which extra to install. Converters live behind a `DocumentConverter` abstraction,
+so new sources can be added without changing the CLI.
 
 `ingest` exits `0` on success, `1` if a recognized document fails to convert, and
 `2` for usage errors (file not found, unsupported type, missing `ingest` extra,

requirements_as_code-0.3.1/planning/roadmap/v0.3.1-formats.md

@@ -0,0 +1,29 @@
+# v0.3.1 Ingestion Formats
+
+## Problem
+
+v0.3 shipped document ingestion for DOCX and Markdown only.
+
+Product knowledge also lives in HTML pages, PDFs, slide decks, and spreadsheets, and users should not have to convert those by hand before ingesting them.
+
+## Requirements
+
+[REQ-001] User can ingest HTML files
+[REQ-002] User can ingest PDF files
+[REQ-003] User can ingest PPTX files
+[REQ-004] User can ingest XLSX files
+[REQ-005] New formats reuse the existing DocumentConverter abstraction
+[REQ-006] Missing format dependencies produce a clear install message
+[REQ-007] Format readers install as granular optional extras
+
+## Success Metrics
+
+- Each supported format converts a sample file to Markdown
+- Adding a format requires no changes to the CLI
+- The ingest extra installs all supported format readers
+
+## Risks
+
+- Conversion quality varies by source document
+- PDF text extraction may lose structure
+- A heavier ingest extra increases install size

{requirements_as_code-0.3.0 → requirements_as_code-0.3.1}/pyproject.toml

@@ -33,10 +33,22 @@ Repository = "https://github.com/tcballard/requirements-as-code"
 Issues = "https://github.com/tcballard/requirements-as-code/issues"
 
 [project.optional-dependencies]
-# Document ingestion (rac ingest). Optional so the core install stays light.
-# markitdown[docx] pulls the DOCX reader; later formats add their own extras.
-ingest = ["markitdown[docx]"]
-dev = ["pytest>=7.0", "markitdown[docx]", "python-docx"]
+# Document ingestion (rac ingest). Optional so the core install stays light, and
+# split by format so users only pull the readers they need. HTML and Markdown
+# need no extra (HTML is built into MarkItDown; Markdown is pass-through).
+ingest = ["markitdown[docx]"]                        # DOCX (+ HTML, Markdown)
+ingest-pdf = ["markitdown[pdf]"]                     # + PDF
+ingest-office = ["markitdown[pptx,xlsx,xls]"]        # + PPTX / XLSX / XLS
+ingest-all = ["markitdown[docx,pdf,pptx,xlsx,xls]"]  # every supported format
+# dev also pulls the libraries used to *generate* fixture files in the tests.
+dev = [
+    "pytest>=7.0",
+    "markitdown[docx,pdf,pptx,xlsx,xls]",
+    "python-docx",
+    "python-pptx",
+    "openpyxl",
+    "reportlab",
+]
 
 [project.scripts]
 rac = "rac.cli:main"

{requirements_as_code-0.3.0 → requirements_as_code-0.3.1}/rac/cli.py

@@ -173,7 +173,7 @@ def build_parser() -> argparse.ArgumentParser:
 
     p_ingest = sub.add_parser(
         "ingest",
-        help="Convert a source document (DOCX, Markdown) to Markdown.",
+        help="Convert a document (DOCX, PDF, HTML, PPTX, XLSX, Markdown) to Markdown.",
         parents=[version_parent],
     )
     p_ingest.add_argument("file", help="Path to the source document.")

{requirements_as_code-0.3.0 → requirements_as_code-0.3.1}/rac/ingest.py

@@ -67,23 +67,62 @@ class MarkItDownConverter:
     """
 
     name = "markitdown"
-    extensions = (".docx",)  # v0.3.x will extend: .html, .pdf, ...
+    # HTML needs no extra (built into MarkItDown); the others come from the
+    # corresponding markitdown extras, exposed as our granular ingest extras.
+    extensions = (".docx", ".pdf", ".html", ".htm", ".pptx", ".xls", ".xlsx")
 
     def convert(self, path: Path) -> str:
         try:
             from markitdown import MarkItDown
         except ModuleNotFoundError as exc:
-            raise UnsupportedDocument(
-                f"converting '{path.suffix}' needs the ingest extra: "
-                "pip install 'requirements-as-code[ingest]'"
-            ) from exc
+            raise UnsupportedDocument(_missing_extra_message(path.suffix)) from exc
+
         try:
             result = MarkItDown().convert(str(path))
         except Exception as exc:  # MarkItDown raises a variety of errors
+            if _is_missing_dependency(exc):
+                # MarkItDown is installed but this format's reader extra isn't.
+                raise UnsupportedDocument(_missing_extra_message(path.suffix)) from exc
             raise ConversionError(f"could not convert {path.name}: {exc}") from exc
         return result.text_content
 
 
+# Which optional extra provides the reader for a given file type. HTML/HTM need
+# no extra (built into MarkItDown), so they fall back to the base `ingest`.
+_EXTRA_FOR_SUFFIX = {
+    ".docx": "ingest",
+    ".pdf": "ingest-pdf",
+    ".pptx": "ingest-office",
+    ".xls": "ingest-office",
+    ".xlsx": "ingest-office",
+}
+
+
+def _missing_extra_message(suffix: str) -> str:
+    extra = _EXTRA_FOR_SUFFIX.get(suffix.lower(), "ingest")
+    return (
+        f"converting '{suffix}' needs the {extra} extra: "
+        f"pip install 'requirements-as-code[{extra}]'"
+    )
+
+
+def _is_missing_dependency(exc: Exception) -> bool:
+    """True if ``exc`` is (or wraps) a MarkItDown missing-dependency error."""
+    try:
+        from markitdown._exceptions import MissingDependencyException
+    except Exception:  # pragma: no cover - defensive
+        return False
+    if isinstance(exc, MissingDependencyException):
+        return True
+    # MarkItDown wraps converter failures in FileConversionException(attempts=...),
+    # each attempt carrying the original error in .exc_info = (type, value, tb).
+    for attempt in getattr(exc, "attempts", None) or []:
+        info = getattr(attempt, "exc_info", None)
+        if info and isinstance(info[1], MissingDependencyException):
+            return True
+    return False
+
+
 # Registry — first converter whose extensions match wins. Order is not currently
 # significant since extension sets are disjoint, but kept explicit for clarity.
 _CONVERTERS: list[DocumentConverter] = [MarkdownConverter(), MarkItDownConverter()]

{requirements_as_code-0.3.0 → requirements_as_code-0.3.1/requirements_as_code.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: requirements-as-code
-Version: 0.3.0
+Version: 0.3.1
 Summary: RAC — lint and diff product requirements written in Markdown.
 Author: tcballard
 License-Expression: MIT
@@ -23,10 +23,19 @@ License-File: LICENSE
 Requires-Dist: markdown-it-py>=3.0
 Provides-Extra: ingest
 Requires-Dist: markitdown[docx]; extra == "ingest"
+Provides-Extra: ingest-pdf
+Requires-Dist: markitdown[pdf]; extra == "ingest-pdf"
+Provides-Extra: ingest-office
+Requires-Dist: markitdown[pptx,xls,xlsx]; extra == "ingest-office"
+Provides-Extra: ingest-all
+Requires-Dist: markitdown[docx,pdf,pptx,xls,xlsx]; extra == "ingest-all"
 Provides-Extra: dev
 Requires-Dist: pytest>=7.0; extra == "dev"
-Requires-Dist: markitdown[docx]; extra == "dev"
+Requires-Dist: markitdown[docx,pdf,pptx,xls,xlsx]; extra == "dev"
 Requires-Dist: python-docx; extra == "dev"
+Requires-Dist: python-pptx; extra == "dev"
+Requires-Dist: openpyxl; extra == "dev"
+Requires-Dist: reportlab; extra == "dev"
 Dynamic: license-file
 
 # RAC (Requirements-as-Code)
@@ -436,15 +445,25 @@ rac ingest spec.docx --json       # { source, converter, output, markdown }
 ```
 
 Conversion is powered by [MarkItDown](https://github.com/microsoft/markitdown),
-installed via the optional `ingest` extra:
+installed via optional extras — split by format so you only pull the readers you
+need:
+
+| Extra | Adds | Formats |
+|-------|------|---------|
+| `ingest` | `markitdown[docx]` | DOCX, HTML, Markdown |
+| `ingest-pdf` | `markitdown[pdf]` | + PDF |
+| `ingest-office` | `markitdown[pptx,xlsx,xls]` | + PPTX, XLSX, XLS |
+| `ingest-all` | everything above | all supported formats |
 
 ```bash
-pip install "requirements-as-code[ingest]"
+pip install "requirements-as-code[ingest]"       # DOCX + HTML + Markdown
+pip install "requirements-as-code[ingest-all]"    # everything
 ```
 
-Supported today: **DOCX** and **Markdown** (pass-through). HTML and PDF are
-planned for v0.3.x. Converters live behind a `DocumentConverter` abstraction, so
-new sources can be added without changing the CLI.
+HTML and Markdown need no extra (HTML is built into MarkItDown; Markdown is a
+pass-through). If a file's reader isn't installed, `rac ingest` tells you exactly
+which extra to install. Converters live behind a `DocumentConverter` abstraction,
+so new sources can be added without changing the CLI.
 
 `ingest` exits `0` on success, `1` if a recognized document fails to convert, and
 `2` for usage errors (file not found, unsupported type, missing `ingest` extra,

{requirements_as_code-0.3.0 → requirements_as_code-0.3.1}/requirements_as_code.egg-info/SOURCES.txt

@@ -23,6 +23,7 @@ planning/future/v1.4-claude-skills.md
 planning/future/v1.4-python-sdk.md
 planning/roadmap/v0.2-stats.md
 planning/roadmap/v0.3-ingest.md
+planning/roadmap/v0.3.1-formats.md
 planning/roadmap/v0.4-inspect.md
 planning/roadmap/v0.5-decisions.md
 planning/roadmap/v0.6-roadmaps.md

requirements_as_code-0.3.1/requirements_as_code.egg-info/requires.txt

@@ -0,0 +1,21 @@
+markdown-it-py>=3.0
+
+[dev]
+pytest>=7.0
+markitdown[docx,pdf,pptx,xls,xlsx]
+python-docx
+python-pptx
+openpyxl
+reportlab
+
+[ingest]
+markitdown[docx]
+
+[ingest-all]
+markitdown[docx,pdf,pptx,xls,xlsx]
+
+[ingest-office]
+markitdown[pptx,xls,xlsx]
+
+[ingest-pdf]
+markitdown[pdf]

{requirements_as_code-0.3.0 → requirements_as_code-0.3.1}/tests/test_ingest.py

@@ -26,13 +26,14 @@ from conftest import fixture_path
 def test_converter_selection_by_extension():
     assert isinstance(converter_for(Path("a.md")), MarkdownConverter)
     assert isinstance(converter_for(Path("a.markdown")), MarkdownConverter)
-    assert isinstance(converter_for(Path("a.docx")), MarkItDownConverter)
+    for ext in (".docx", ".pdf", ".html", ".htm", ".pptx", ".xls", ".xlsx"):
+        assert isinstance(converter_for(Path(f"a{ext}")), MarkItDownConverter), ext
     assert converter_for(Path("a.txt")) is None
 
 
 def test_supported_extensions():
-    assert ".docx" in supported_extensions()
-    assert ".md" in supported_extensions()
+    exts = set(supported_extensions())
+    assert {".md", ".docx", ".pdf", ".html", ".htm", ".pptx", ".xls", ".xlsx"} <= exts
 
 
 def test_markdown_passthrough():
@@ -48,6 +49,16 @@ def test_unsupported_type_raises(tmp_path):
         ingest(str(bad))
 
 
+def test_missing_extra_message_points_at_right_extra():
+    from rac.ingest import _missing_extra_message
+
+    assert "[ingest-pdf]" in _missing_extra_message(".pdf")
+    assert "[ingest-office]" in _missing_extra_message(".pptx")
+    assert "[ingest-office]" in _missing_extra_message(".xlsx")
+    assert "[ingest]" in _missing_extra_message(".docx")
+    assert "[ingest]" in _missing_extra_message(".html")  # html -> base markitdown
+
+
 # --- CLI: markdown / error paths (no optional deps needed) ------------------
 
 
@@ -127,3 +138,75 @@ def test_cli_ingest_docx_to_file(tmp_path):
     out = tmp_path / "spec.md"
     assert main(["ingest", str(src), "-o", str(out)]) == 0
     assert "# Bond Dashboard" in out.read_text()
+
+
+# --- Other formats added in v0.3.1 ------------------------------------------
+
+
+def test_html_conversion(tmp_path):
+    # HTML needs no extra dependency (built into MarkItDown).
+    src = tmp_path / "page.html"
+    src.write_text("<h1>Bond Dashboard</h1><p>Rate exposure.</p>")
+    result = ingest(str(src))
+    assert result.converter == "markitdown"
+    assert "# Bond Dashboard" in result.markdown
+
+
+def test_pptx_conversion(tmp_path):
+    pptx = pytest.importorskip("pptx")
+    src = tmp_path / "deck.pptx"
+    prs = pptx.Presentation()
+    slide = prs.slides.add_slide(prs.slide_layouts[5])
+    slide.shapes.title.text = "Deck Title"
+    prs.save(str(src))
+    result = ingest(str(src))
+    assert result.converter == "markitdown"
+    assert "Deck Title" in result.markdown
+
+
+def test_xlsx_conversion(tmp_path):
+    openpyxl = pytest.importorskip("openpyxl")
+    src = tmp_path / "data.xlsx"
+    wb = openpyxl.Workbook()
+    ws = wb.active
+    ws["A1"] = "Metric"
+    ws["A2"] = "MAU"
+    wb.save(str(src))
+    result = ingest(str(src))
+    assert result.converter == "markitdown"
+    assert "Metric" in result.markdown
+
+
+def test_pdf_conversion(tmp_path):
+    pytest.importorskip("reportlab")
+    from reportlab.pdfgen import canvas
+
+    src = tmp_path / "doc.pdf"
+    c = canvas.Canvas(str(src))
+    c.drawString(72, 720, "PDF heading and body text.")
+    c.save()
+    result = ingest(str(src))
+    assert result.converter == "markitdown"
+    assert "PDF heading and body text." in result.markdown
+
+
+def test_missing_dependency_detection():
+    # A per-format missing reader should be recognized so the CLI can map it to
+    # a clear "install the ingest extra" message (exit 2), direct or wrapped in
+    # MarkItDown's FileConversionException(attempts=...).
+    from types import SimpleNamespace
+
+    from markitdown._exceptions import (
+        FileConversionException,
+        MissingDependencyException,
+    )
+
+    from rac.ingest import _is_missing_dependency
+
+    assert _is_missing_dependency(MissingDependencyException("x")) is True
+    attempt = SimpleNamespace(
+        converter=object(),
+        exc_info=(MissingDependencyException, MissingDependencyException("y"), None),
+    )
+    assert _is_missing_dependency(FileConversionException(attempts=[attempt])) is True
+    assert _is_missing_dependency(ValueError("unrelated")) is False

requirements_as_code-0.3.0/requirements_as_code.egg-info/requires.txt

@@ -1,9 +0,0 @@
-markdown-it-py>=3.0
-
-[dev]
-pytest>=7.0
-markitdown[docx]
-python-docx
-
-[ingest]
-markitdown[docx]