#!/usr/bin/env python3
"""Extract the git commit census of the troupe-standup repo.

Lane: Extract -- data extraction and tables.

Source (single source of truth):
  git (local clone, branch main) -- every commit reachable from HEAD.

Artifacts written beside this script (all re-derivable, none hand-typed):
  - commits-census.csv   commits per author (unique author name)
  - commits-by-day.csv   commits per calendar day (author date)
  - commits-full.csv     one row per commit: hash, author, email, date, subject
  - README-commits-census.md

Verification: verify_commits_census.py re-derives every table cell from git
and exits 0 iff the committed tables match. The CHECK file runs that script.

Run:  python3 extract_commits_census.py
"""
import csv
import os
import subprocess
import sys
from collections import Counter

REPO = "/root/troupe-standup"
OUT = "/root/troupe-standup/wizard-work/ledger"

# Pinned revision so the census is deterministic: other agents keep pushing to
# main while this artifact is being produced. Verify against this hash only.
PIN = "d8d8e3292db6c435b174e39a3ca18792874f9c19"
REPO_HEAD = "HEAD"  # value only; PIN below overrides where git is invoked

# Separator guaranteed not to appear in any git field value.
SEP = "\x1f"
# Format: hash \x1f author \x1f email \x1f author-date \x1f subject
FMT = "%H" + SEP + "%an" + SEP + "%ae" + SEP + "%aI" + SEP + "%s"


def git_log():
    cmd = ["git", "-C", REPO, "log",
           "--pretty=format:" + FMT, "--date=iso-strict", PIN]
    out = subprocess.run(cmd, check=True, capture_output=True, text=True).stdout
    rows = []
    for c in out.splitlines():
        if not c:
            continue
        h, an, ae, ad, s = c.split(SEP)
        rows.append({"hash": h, "author": an, "email": ae,
                     "author_date": ad, "subject": s})
    return rows


def write_csv(name, header, data):
    path = os.path.join(OUT, name)
    with open(path, "w", newline="", encoding="utf-8") as f:
        w = csv.writer(f)
        w.writerow(header)
        w.writerows(data)
    return path


def main():
    rows = git_log()
    total = len(rows)
    by_author = Counter(r["author"] for r in rows)
    by_day = Counter(r["author_date"][:10] for r in rows)  # YYYY-MM-DD

    census_rows = sorted(by_author.items(), key=lambda kv: (-kv[1], kv[0]))
    day_rows = sorted(by_day.items(), key=lambda kv: kv[0])

    os.makedirs(OUT, exist_ok=True)

    write_csv("commits-census.csv",
              ["author", "commits"], [(a, c) for a, c in census_rows])
    write_csv("commits-by-day.csv",
              ["date", "commits"], [(d, c) for d, c in day_rows])
    write_csv("commits-full.csv",
              ["hash", "author", "email", "author_date", "subject"],
              [(r["hash"], r["author"], r["email"], r["author_date"], r["subject"]) for r in rows])

    lines = []
    lines.append("# Git commit census — troupe-standup")
    lines.append("")
    lines.append("Source: `git log --pretty=format:` over the pinned revision %s (fields: "
                 "hash, author, email, author-date, subject)." % PIN)
    lines.append("")
    lines.append("Pinned revision (sha): `%s`" % PIN)
    lines.append("Total commits: **%d**" % total)
    lines.append("")
    lines.append("## Commits by author")
    lines.append("")
    lines.append("| author | commits |")
    lines.append("|---|---|")
    for a, c in census_rows:
        lines.append("| %s | %d |" % (a, c))
    lines.append("| **total** | **%d** |" % total)
    lines.append("")
    lines.append("## Commits by calendar day")
    lines.append("")
    lines.append("| date | commits |")
    lines.append("|---|---|")
    for d, c in day_rows:
        lines.append("| %s | %d |" % (d, c))
    lines.append("| **total** | **%d** |" % total)
    lines.append("")

    with open(os.path.join(OUT, "README-commits-census.md"), "w", encoding="utf-8") as f:
        f.write("\n".join(lines))

    print("commits:", total)
    print("authors:", len(census_rows))
    print("days:", len(day_rows))
    print("wrote: commits-census.csv, commits-by-day.csv, commits-full.csv, README-commits-census.md")


if __name__ == "__main__":
    sys.exit(main())