#!/usr/bin/env python3
"""Extract the dated check-in census for the troupe repo into CSV.

One row per dated check-in file under checkins/ (README.md is repo docs, not a
check-in, and is excluded). Columns: date, wizard, path, size_bytes, blob_sha1.
The re-derivation is from git itself (ls-tree), so the CSV is a faithful
extraction of the committed tree, independent of the working-tree state.
"""
import csv
import os
import subprocess
import sys


def git(repo, *args):
    return subprocess.run(
        ["git", "-C", repo] + list(args), check=True, capture_output=True, text=True
    ).stdout


def main():
    repo = sys.argv[1] if len(sys.argv) > 1 else "/root/troupe-standup"
    out_csv = (
        sys.argv[2]
        if len(sys.argv) > 2
        else os.path.join(repo, "wizard-work/ledger/2026-11-05-checkin-census.csv")
    )

    names = git(repo, "ls-tree", "-r", "--name-only", "HEAD").splitlines()
    longs = git(repo, "ls-tree", "-r", "-l", "HEAD").splitlines()

    long_by_path = {}
    for ln in longs:
        tab = ln.find("\t")
        head, path = ln[:tab], ln[tab + 1:]
        tok = head.split()
        sha, size = tok[2], int(tok[3])
        long_by_path[path] = (size, sha)

    rows = []
    for p in names:
        if not p.startswith("checkins/") or p == "checkins/README.md":
            continue
        rel = p[len("checkins/"):]
        date = rel[:10]
        wizard = rel[11:-3] if rel.endswith(".md") else rel[11:]
        size, sha = long_by_path[p]
        rows.append([date, wizard, p, size, sha])

    rows.sort(key=lambda r: (r[0], r[1], r[2]))

    os.makedirs(os.path.dirname(out_csv), exist_ok=True)
    with open(out_csv, "w", newline="") as f:
        w = csv.writer(f)
        w.writerow(["date", "wizard", "path", "size_bytes", "blob_sha1"])
        w.writerows(rows)

    print("rows=%d" % len(rows))
    print("output=%s" % out_csv)
    print("sample:")
    for r in rows[:3]:
        print(" ", r)


if __name__ == "__main__":
    main()