docassert 0.1.0__tar.gz → 0.2.0__tar.gz

{docassert-0.1.0/docassert.egg-info → docassert-0.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: docassert
-Version: 0.1.0
+Version: 0.2.0
 Summary: Unit testing for business documents — validate structured Markdown docs against a configurable audit standard.
 Author: C4G Enterprises Inc.
 License: Apache-2.0
@@ -38,6 +38,10 @@ Dynamic: license-file
 
 # docassert
 
+[![PyPI](https://img.shields.io/pypi/v/docassert)](https://pypi.org/project/docassert/)
+[![Python](https://img.shields.io/pypi/pyversions/docassert)](https://pypi.org/project/docassert/)
+[![License](https://img.shields.io/badge/license-Apache--2.0-blue)](LICENSE)
+
 **Unit testing for business documents.** Validate structured Markdown documents
 (charters, BRDs, PRDs, risk registers, …) against a configurable audit standard:
 deterministic structural checks that gate a merge, plus optional AI-graded
@@ -50,9 +54,11 @@ a vendor-neutral standard for running a PMO from version-controlled, declarative
 ## Install
 
 ```bash
-pip install "docassert @ git+https://github.com/c4g-john/docassert"   # PyPI release coming
+pipx install docassert          # recommended — installs the CLI in its own isolated env
+# or:
+pip install docassert
 # with the AI advisory extra:
-pip install "docassert[ai] @ git+https://github.com/c4g-john/docassert"
+pip install "docassert[ai]"
 ```
 
 ## Quickstart
@@ -81,6 +87,7 @@ you can customize them.
 | `docassert pages --out DIR` | Build the portfolio site (index + a page per project). |
 | `docassert projects [--out] [--check]` | Generate / verify the project registry. |
 | `docassert init [DIR]` | Scaffold the default config into a repo. |
+| `docassert extract <file>` | Extract plain text from a source `.docx` / `.pdf` / `.md` / `.txt` (the first step of doc-to-pmo conversion). Needs the `convert` extra: `pip install "docassert[convert]"`. |
 
 ## Document kinds
 

{docassert-0.1.0 → docassert-0.2.0}/README.md

@@ -1,5 +1,9 @@
 # docassert
 
+[![PyPI](https://img.shields.io/pypi/v/docassert)](https://pypi.org/project/docassert/)
+[![Python](https://img.shields.io/pypi/pyversions/docassert)](https://pypi.org/project/docassert/)
+[![License](https://img.shields.io/badge/license-Apache--2.0-blue)](LICENSE)
+
 **Unit testing for business documents.** Validate structured Markdown documents
 (charters, BRDs, PRDs, risk registers, …) against a configurable audit standard:
 deterministic structural checks that gate a merge, plus optional AI-graded
@@ -12,9 +16,11 @@ a vendor-neutral standard for running a PMO from version-controlled, declarative
 ## Install
 
 ```bash
-pip install "docassert @ git+https://github.com/c4g-john/docassert"   # PyPI release coming
+pipx install docassert          # recommended — installs the CLI in its own isolated env
+# or:
+pip install docassert
 # with the AI advisory extra:
-pip install "docassert[ai] @ git+https://github.com/c4g-john/docassert"
+pip install "docassert[ai]"
 ```
 
 ## Quickstart
@@ -43,6 +49,7 @@ you can customize them.
 | `docassert pages --out DIR` | Build the portfolio site (index + a page per project). |
 | `docassert projects [--out] [--check]` | Generate / verify the project registry. |
 | `docassert init [DIR]` | Scaffold the default config into a repo. |
+| `docassert extract <file>` | Extract plain text from a source `.docx` / `.pdf` / `.md` / `.txt` (the first step of doc-to-pmo conversion). Needs the `convert` extra: `pip install "docassert[convert]"`. |
 
 ## Document kinds
 

{docassert-0.1.0 → docassert-0.2.0}/docassert/__init__.py

@@ -5,4 +5,4 @@ standard: deterministic structural checks that gate a merge, plus optional
 AI-graded semantic checks that advise.
 """
 
-__version__ = "0.1.0"
+__version__ = "0.2.0"

{docassert-0.1.0 → docassert-0.2.0}/docassert/cli.py

@@ -232,6 +232,23 @@ def cmd_init(args: argparse.Namespace) -> int:
     return 0
 
 
+def cmd_extract(args: argparse.Namespace) -> int:
+    """Extract plain text from a source document (.docx/.pdf/.md/.txt) — the
+    deterministic first step of doc-to-pmo conversion."""
+    from . import extract as extract_mod
+    try:
+        text = extract_mod.extract(args.file)
+    except (FileNotFoundError, ValueError, ImportError) as exc:
+        print(f"docassert: {exc}", file=sys.stderr)
+        return 2
+    if args.out:
+        Path(args.out).write_text(text, encoding="utf-8")
+        print(f"docassert: wrote {args.out} ({len(text)} chars)")
+    else:
+        sys.stdout.write(text)
+    return 0
+
+
 def main(argv: list[str] | None = None) -> int:
     from . import __version__
     parser = argparse.ArgumentParser(prog="docassert",
@@ -283,6 +300,11 @@ def main(argv: list[str] | None = None) -> int:
     ini.add_argument("dir", nargs="?", default=".", help="Target directory (default: current).")
     ini.set_defaults(func=cmd_init)
 
+    ex = sub.add_parser("extract", help="Extract plain text from a source doc (.docx/.pdf/.md/.txt) for conversion.")
+    ex.add_argument("file", help="Source document (.docx / .pdf / .md / .txt).")
+    ex.add_argument("--out", help="Write to this path instead of stdout.")
+    ex.set_defaults(func=cmd_extract)
+
     args = parser.parse_args(argv)
     return args.func(args)
 

docassert-0.2.0/docassert/extract.py

@@ -0,0 +1,55 @@
+"""Extract plain text from a source document, for doc-to-pmo conversion.
+
+The deterministic first step of the conversion front-door: turn an arbitrary
+source file (.docx / .pdf / .md / .txt) into plain text that the doc-to-pmo
+skill then maps into a standard template. It does not interpret or reshape the
+content — that is the skill's job.
+
+.docx / .pdf support needs the optional `convert` extra:
+    pip install "docassert[convert]"
+"""
+from __future__ import annotations
+
+from pathlib import Path
+
+_NEED_CONVERT = 'extract needs the "convert" extra: pip install "docassert[convert]"'
+
+
+def extract(path: str | Path) -> str:
+    """Return the plain text of a source document.
+
+    Raises FileNotFoundError (missing file), ValueError (unsupported type), or
+    ImportError (a .docx/.pdf without the `convert` extra installed).
+    """
+    p = Path(path)
+    if not p.is_file():
+        raise FileNotFoundError(f"no such file: {p}")
+    ext = p.suffix.lower()
+
+    if ext in {".md", ".txt"}:
+        return p.read_text(encoding="utf-8")
+
+    if ext == ".docx":
+        try:
+            import docx  # python-docx
+        except ImportError as exc:
+            raise ImportError(_NEED_CONVERT) from exc
+        document = docx.Document(str(p))
+        blocks: list[str] = [para.text for para in document.paragraphs]
+        # include table cell text, which charters often use for milestones/risks
+        for table in document.tables:
+            for row in table.rows:
+                cells = [cell.text.strip() for cell in row.cells]
+                if any(cells):
+                    blocks.append(" | ".join(cells))
+        return "\n".join(blocks)
+
+    if ext == ".pdf":
+        try:
+            from pypdf import PdfReader
+        except ImportError as exc:
+            raise ImportError(_NEED_CONVERT) from exc
+        reader = PdfReader(str(p))
+        return "\n".join((page.extract_text() or "") for page in reader.pages)
+
+    raise ValueError(f"unsupported source type '{ext}' (supported: .docx, .pdf, .md, .txt)")

{docassert-0.1.0 → docassert-0.2.0/docassert.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: docassert
-Version: 0.1.0
+Version: 0.2.0
 Summary: Unit testing for business documents — validate structured Markdown docs against a configurable audit standard.
 Author: C4G Enterprises Inc.
 License: Apache-2.0
@@ -38,6 +38,10 @@ Dynamic: license-file
 
 # docassert
 
+[![PyPI](https://img.shields.io/pypi/v/docassert)](https://pypi.org/project/docassert/)
+[![Python](https://img.shields.io/pypi/pyversions/docassert)](https://pypi.org/project/docassert/)
+[![License](https://img.shields.io/badge/license-Apache--2.0-blue)](LICENSE)
+
 **Unit testing for business documents.** Validate structured Markdown documents
 (charters, BRDs, PRDs, risk registers, …) against a configurable audit standard:
 deterministic structural checks that gate a merge, plus optional AI-graded
@@ -50,9 +54,11 @@ a vendor-neutral standard for running a PMO from version-controlled, declarative
 ## Install
 
 ```bash
-pip install "docassert @ git+https://github.com/c4g-john/docassert"   # PyPI release coming
+pipx install docassert          # recommended — installs the CLI in its own isolated env
+# or:
+pip install docassert
 # with the AI advisory extra:
-pip install "docassert[ai] @ git+https://github.com/c4g-john/docassert"
+pip install "docassert[ai]"
 ```
 
 ## Quickstart
@@ -81,6 +87,7 @@ you can customize them.
 | `docassert pages --out DIR` | Build the portfolio site (index + a page per project). |
 | `docassert projects [--out] [--check]` | Generate / verify the project registry. |
 | `docassert init [DIR]` | Scaffold the default config into a repo. |
+| `docassert extract <file>` | Extract plain text from a source `.docx` / `.pdf` / `.md` / `.txt` (the first step of doc-to-pmo conversion). Needs the `convert` extra: `pip install "docassert[convert]"`. |
 
 ## Document kinds
 

{docassert-0.1.0 → docassert-0.2.0}/docassert.egg-info/SOURCES.txt

@@ -7,6 +7,7 @@ docassert/__main__.py
 docassert/cli.py
 docassert/config.py
 docassert/consistency.py
+docassert/extract.py
 docassert/graph.py
 docassert/loader.py
 docassert/models.py
@@ -89,6 +90,7 @@ docassert/_data/templates/test-cases.template.md
 docassert/_data/templates/user-story.template.md
 tests/test_config.py
 tests/test_consistency.py
+tests/test_extract.py
 tests/test_graph.py
 tests/test_kinds_delivery.py
 tests/test_kinds_governance.py

docassert-0.2.0/tests/test_extract.py

@@ -0,0 +1,65 @@
+"""Tests for the extract module and the `docassert extract` command."""
+import pytest
+
+from docassert import extract as E
+from docassert.cli import main
+
+
+# ── the extract() function ──────────────────────────────────────────────────
+def test_extract_md(tmp_path):
+    f = tmp_path / "s.md"
+    f.write_text("# Hello\nworld", encoding="utf-8")
+    assert E.extract(f) == "# Hello\nworld"
+
+
+def test_extract_txt(tmp_path):
+    f = tmp_path / "s.txt"
+    f.write_text("plain text", encoding="utf-8")
+    assert E.extract(str(f)) == "plain text"
+
+
+def test_missing_file_raises(tmp_path):
+    with pytest.raises(FileNotFoundError):
+        E.extract(tmp_path / "nope.md")
+
+
+def test_unsupported_type_raises(tmp_path):
+    f = tmp_path / "s.rtf"
+    f.write_text("x", encoding="utf-8")
+    with pytest.raises(ValueError):
+        E.extract(f)
+
+
+def test_extract_docx_paragraphs_and_tables(tmp_path):
+    docx = pytest.importorskip("docx")  # needs the 'convert' extra
+    d = docx.Document()
+    d.add_paragraph("First para.")
+    table = d.add_table(rows=1, cols=2)
+    table.rows[0].cells[0].text = "Milestone"
+    table.rows[0].cells[1].text = "2026-09-30"
+    path = tmp_path / "s.docx"
+    d.save(str(path))
+    text = E.extract(path)
+    assert "First para." in text
+    assert "Milestone | 2026-09-30" in text  # table cells joined
+
+
+# ── the CLI command ─────────────────────────────────────────────────────────
+def test_cli_extract_stdout(tmp_path, capsys):
+    f = tmp_path / "s.md"
+    f.write_text("hello cli", encoding="utf-8")
+    assert main(["extract", str(f)]) == 0
+    assert "hello cli" in capsys.readouterr().out
+
+
+def test_cli_extract_out_file(tmp_path):
+    src = tmp_path / "s.txt"
+    src.write_text("abc", encoding="utf-8")
+    out = tmp_path / "out.txt"
+    assert main(["extract", str(src), "--out", str(out)]) == 0
+    assert out.read_text() == "abc"
+
+
+def test_cli_extract_missing_returns_2(tmp_path, capsys):
+    assert main(["extract", str(tmp_path / "nope.md")]) == 2
+    assert "no such file" in capsys.readouterr().err