#!/usr/bin/env python3
"""Generate the per-extension file census table from the wizardwork file manifest.

Reads : /root/troupe-standup/wizard-work/ledger/wizardwork-file-manifest.tsv
        tab-separated, NO header: path, size_bytes, extension, top_dir
Writes: /root/troupe-standup/wizard-work/ledger/ledger-extract.tsv
        tab-separated: extension, file_count, bytes_total, bytes_mean,
                         bytes_median, bytes_min, bytes_max
        sorted by file_count desc, then extension asc (deterministic).
"""
import csv
import statistics
from collections import defaultdict

MANIFEST = "/root/troupe-standup/wizard-work/ledger/wizardwork-file-manifest.tsv"
OUT = "/root/troupe-standup/wizard-work/ledger/ledger-extract.tsv"


def norm_ext(ext):
    return "(no ext)" if ext == "" else ext


def main():
    counts = defaultdict(int)
    sizes = defaultdict(list)
    with open(MANIFEST, newline="") as f:
        for line in f:
            parts = line.rstrip("\n").split("\t")
            if len(parts) < 3:
                continue
            try:
                size = int(parts[1])
            except ValueError:
                continue
            ext = norm_ext(parts[2])
            counts[ext] += 1
            sizes[ext].append(size)

    rows = []
    for ext, szs in sizes.items():
        total = sum(szs)
        mean = total / counts[ext]
        med = statistics.median(szs)
        rows.append((ext, counts[ext], total, mean, med, min(szs), max(szs)))

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

    with open(OUT, "w", newline="") as f:
        w = csv.writer(f, delimiter="\t", lineterminator="\n")
        w.writerow(["extension", "file_count", "bytes_total", "bytes_mean",
                    "bytes_median", "bytes_min", "bytes_max"])
        for ext, cnt, total, mean, med, mn, mx in rows:
            w.writerow([ext, cnt, total, "%.1f" % mean, "%.1f" % med, mn, mx])

    print("Wrote %d extension rows to %s" % (len(rows), OUT))


if __name__ == "__main__":
    main()