feat(python): add coverage-summary to the Python bundle

Second language in the coverage-summary fan-out, after the Elisp pilot. Same kernel: a module no test imports never appears in coverage.py's report, so a line-weighted total skips it silently and the suite looks healthier than it is. This counts every source file on disk that's absent from the report as 0% and weights the project number by file, so untested modules stay visible.

The script at languages/python/claude/scripts/coverage-summary.py parses coverage.py's JSON (files[path].summary.covered_lines / num_statements), resolves report paths against the report's directory since coverage records them relative to where it ran, and recurses the source dir for *.py. Unlike the Elisp version it doesn't print a per-file table, because coverage.py's own coverage report already does. The script adds the missing-file accounting that report lacks. It uses only the standard library, parsing the report rather than importing coverage.

The Python run confirmed the plumbing from the pilot is genuinely generic. install-lang and sync deliver the script and the project-owned coverage-makefile.txt with no Python-specific code. The one gap I had to close: the Python bundle shipped without a gitignore-add.txt, so the .claude/ footprint wasn't ignored and the script would have been committable. Added one mirroring the Elisp footprint plus Python artifacts (__pycache__, .coverage, coverage.json). make test gained a languages/*/tests/test_*.py discovery path alongside the existing Elisp ERT one.

Tests: 12 pytest covering the parser, the file-weighted number, and the missing-file detection including subpackage recursion, plus an install-lang check that the script lands in the gitignored footprint. I proved it against a report matching coverage.py's documented schema and the CLI end to end, but not against a live coverage json run, because coverage.py isn't installed in this repo's env. The first project to adopt it should sanity-check against a real report.

1 files changed, 157 insertions, 0 deletions

diff --git a/languages/python/claude/scripts/coverage-summary.py b/languages/python/claude/scripts/coverage-summary.py
new file mode 100755
index 0000000..a869fff
--- /dev/null
+++ b/languages/python/claude/scripts/coverage-summary.py
@@ -0,0 +1,157 @@
+#!/usr/bin/env python3
+"""Whole-project coverage summary from a coverage.py JSON report.
+
+Batch helper for `make coverage-summary`. After `make coverage` writes a
+coverage.py JSON report (`coverage json`), this prints a file-weighted project
+number and the source files present on disk but absent from the report.
+
+The value here is the missing-file detection: a module no test imports never
+appears in coverage.py's output, so a line-weighted total silently skips it and
+the suite looks healthier than it is. This counts such a file as 0% and weights
+the project number by file rather than by line, so untested modules stay
+visible. coverage.py's own `coverage report` prints the per-file table, so this
+deliberately doesn't reimplement that — it adds the accounting `report` lacks.
+
+Self-contained on the standard library (json only); it parses the report, it
+does not import coverage. The coverage.py JSON shape it reads is:
+  { "files": { "<path>": { "summary": { "covered_lines": N,
+                                         "num_statements": M, ... } } } }
+Paths are relative to the directory coverage ran in (the project root).
+
+CLI:
+  coverage-summary.py REPORT SOURCE_DIR [PROJECT_ROOT]
+    REPORT       path to the coverage.py JSON report
+    SOURCE_DIR   the package/source directory to account for
+    PROJECT_ROOT defaults to the current directory
+"""
+from __future__ import annotations
+
+import json
+import sys
+from pathlib import Path
+from typing import NoReturn
+
+
+def _die(msg: str) -> NoReturn:
+    print(f"coverage-summary: {msg}", file=sys.stderr)
+    raise SystemExit(1)
+
+
+def parse_report(report_path) -> dict:
+    """Parse a coverage.py JSON report into {abspath: (covered, total)}.
+
+    COVERED is the file's covered_lines, TOTAL its num_statements. coverage.py
+    records paths relative to the directory it ran in, which is where the report
+    is written, so relative paths resolve against the report's parent. Exits with
+    a clear message when the report is missing or malformed.
+    """
+    p = Path(report_path)
+    if not p.is_file():
+        _die(f"coverage report not found: {p}")
+    base = p.resolve().parent
+    try:
+        data = json.loads(p.read_text())
+    except (ValueError, OSError) as e:
+        _die(f"malformed coverage JSON in {p}: {e}")
+    result: dict = {}
+    for path, entry in (data.get("files") or {}).items():
+        summary = entry.get("summary", {}) if isinstance(entry, dict) else {}
+        covered = int(summary.get("covered_lines", 0))
+        total = int(summary.get("num_statements", 0))
+        fp = Path(path)
+        abspath = fp.resolve() if fp.is_absolute() else (base / fp).resolve()
+        result[str(abspath)] = (covered, total)
+    return result
+
+
+def under_dir(table: dict, source_dir, project_root) -> dict:
+    """Filter TABLE to files under SOURCE_DIR, re-keyed relative to PROJECT_ROOT."""
+    source_dir = Path(source_dir).resolve()
+    project_root = Path(project_root).resolve()
+    result: dict = {}
+    for abspath, counts in table.items():
+        ap = Path(abspath)
+        if source_dir == ap or source_dir in ap.parents:
+            result[str(ap.relative_to(project_root))] = counts
+    return result
+
+
+def source_files(source_dir, project_root) -> list:
+    """Return *.py files under SOURCE_DIR (recursive), relative to PROJECT_ROOT.
+
+    Packages nest, so this recurses; __pycache__ is skipped. The caller scopes
+    coverage by choosing SOURCE_DIR.
+    """
+    source_dir = Path(source_dir).resolve()
+    project_root = Path(project_root).resolve()
+    out = []
+    for p in source_dir.rglob("*.py"):
+        if "__pycache__" in p.parts:
+            continue
+        out.append(str(p.resolve().relative_to(project_root)))
+    return sorted(out)
+
+
+def missing(tracked, source_dir, project_root) -> list:
+    """Source files on disk but absent from TRACKED (the report's keys)."""
+    tracked_set = set(tracked)
+    return [f for f in source_files(source_dir, project_root) if f not in tracked_set]
+
+
+def file_pct(covered: int, total: int) -> float:
+    """COVERED/TOTAL as a percentage. A file with no statements is 100%."""
+    return (100.0 * covered / total) if total > 0 else 100.0
+
+
+def project_pct(report_path, source_dir, project_root) -> float:
+    """File-weighted project coverage: every tracked file contributes its own
+    percentage, every source file missing from the report contributes 0%, and
+    the result is the mean over all files under SOURCE_DIR."""
+    tracked = under_dir(parse_report(report_path), source_dir, project_root)
+    miss = missing(list(tracked), source_dir, project_root)
+    total_count = len(tracked) + len(miss)
+    if total_count == 0:
+        return 0.0
+    score = sum(file_pct(c, t) for c, t in tracked.values())
+    return score / total_count
+
+
+def summary_text(report_path, source_dir, project_root) -> str:
+    """Render the project number and the missing-file list (not the per-file
+    table — `coverage report` already prints that)."""
+    tracked = under_dir(parse_report(report_path), source_dir, project_root)
+    miss = missing(list(tracked), source_dir, project_root)
+    pct = project_pct(report_path, source_dir, project_root)
+    rel_src = Path(source_dir).resolve().relative_to(Path(project_root).resolve())
+    total = len(tracked) + len(miss)
+    lines = [
+        f"Coverage summary for {rel_src}",
+        "",
+        f"Project coverage: {pct:.1f}% ({len(tracked)} tracked, {len(miss)} "
+        f"missing, {total} total; missing files count as 0%)",
+        "",
+        f"Not in coverage report: {len(miss)} file{'' if len(miss) == 1 else 's'}",
+    ]
+    if miss:
+        lines.append("These files had no coverage entry; they count as 0% in project coverage.")
+        lines += [f"  {m}" for m in sorted(miss)]
+    else:
+        lines.append("Every source file appears in the coverage report.")
+    lines.append("")
+    lines.append("(Per-file table: run `coverage report`.)")
+    return "\n".join(lines) + "\n"
+
+
+def main(argv) -> int:
+    if not 2 <= len(argv) <= 3:
+        print("usage: coverage-summary.py REPORT SOURCE_DIR [PROJECT_ROOT]", file=sys.stderr)
+        return 2
+    report, source_dir = argv[0], argv[1]
+    project_root = argv[2] if len(argv) == 3 else "."
+    print()
+    print(summary_text(report, source_dir, project_root), end="")
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main(sys.argv[1:]))