#!/usr/bin/env python3
"""Build the Stackchain Library drops catalog from the source folder.

Source: /root/stackchain-library-updates/drops (42 top-level entries:
39 day-drop folders, one probe JSON, and two global checksum files).

One row per entry with a recursive file-type breakdown. Idempotent:
re-running re-derives the same numbers from the same files.

Artifacts written to BOTH:
  - /root/.hermes/profiles/ledger/wizard-outputs/ledger/        (profile outputs)
  - /root/troupe-standup/wizard-work/ledger/                    (troupe repo)
"""
import csv
import os
from collections import Counter

DROPS = "/root/stackchain-library-updates/drops"
OUT_JSON = None  # not used here
OUT_CSV = "drops-catalog.csv"
OUT_MD = "drops-catalog.md"

TARGETS = (
    "/root/.hermes/profiles/ledger/wizard-outputs/ledger",
    "/root/troupe-standup/wizard-work/ledger",
)

# Explicit top-level entries that are files, not folders.
FILE_ENTRIES = (
    "2026-10-23-probe-blocks.json",
    "checksums.sha256",
    "checksums.sha256.NOTES.md",
)


def classify(name):
    """Return a category key for a filename."""
    low = name.lower()
    if low.endswith(".mp4"):
        return "mp4"
    if low.endswith(".json"):
        return "json"
    if low.endswith(".txt"):
        return "txt"
    if low.endswith(".md"):
        return "md"
    if low.endswith((".jpg", ".jpeg", ".png", ".gif", ".webp", ".webm")):
        return "jpg"
    return "other"


def catalog_entry(path):
    is_file = os.path.isfile(path)
    if is_file:
        try:
            size = os.path.getsize(path)
        except OSError:
            size = 0
        return {
            "path": os.path.basename(path),
            "kind": "file",
            "total_files": 1,
            "mp4": 0, "json": 0, "txt": 0, "md": 0, "jpg": 0, "other": 0,
            "size_bytes": size,
        }
    total = 0
    counts = Counter()
    size = 0
    for root, _dirs, files in os.walk(path):
        for fn in files:
            fp = os.path.join(root, fn)
            total += 1
            counts[classify(fn)] += 1
            try:
                size += os.path.getsize(fp)
            except OSError:
                pass
    return {
        "path": os.path.basename(path.rstrip("/")),
        "kind": "dir",
        "total_files": total,
        "mp4": counts["mp4"],
        "json": counts["json"],
        "txt": counts["txt"],
        "md": counts["md"],
        "jpg": counts["jpg"],
        "other": counts["other"],
        "size_bytes": size,
    }


def build_rows():
    rows = []
    if os.path.isdir(DROPS):
        for name in sorted(os.listdir(DROPS)):
            p = os.path.join(DROPS, name)
            rows.append(catalog_entry(p))
    for name in sorted(FILE_ENTRIES):
        p = os.path.join(DROPS, name)
        if os.path.isfile(p) and not any(r["path"] == name for r in rows):
            rows.append(catalog_entry(p))
    return rows


def write_csv(rows, target):
    path = os.path.join(target, OUT_CSV)
    with open(path, "w", encoding="utf-8", newline="") as f:
        writer = csv.DictWriter(f, fieldnames=list(rows[0].keys()))
        writer.writeheader()
        writer.writerows(rows)
    return path


def write_md(rows, target):
    path = os.path.join(target, OUT_MD)
    lines = []
    lines.append("# Stackchain library drops catalog")
    lines.append("")
    lines.append("Source: `%s`. One row per top-level entry (39 day-drop folders, "
                 "one probe JSON, two checksum files). `md` counts reproduced "
                 "`MANIFEST.md` files." % DROPS)
    lines.append("")
    lines.append("| Path | Kind | Files | MP4 | JSON | TXT | MANIFEST(md) | JPG | Other | Size(B) |")
    lines.append("|---|------|-------|-----|------|-----|--------------|-----|-----|---------|")
    for r in rows:
        lines.append(
            "| `{path}` | {kind} | {total} | {mp4} | {json} | {txt} | {md} | {jpg} | "
            "{other} | {size} |".format(
                path=r["path"], kind=r["kind"], total=r["total_files"],
                mp4=r["mp4"], json=r["json"], txt=r["txt"], md=r["md"],
                jpg=r["jpg"], other=r["other"], size=r["size_bytes"]))
    lines.append("")
    totals = {k: sum(r[k] for r in rows) for k in
              ("total_files", "mp4", "json", "txt", "md", "jpg", "other", "size_bytes")}
    lines.append("**Summary:** {n} entries · {files} total files · {md} with "
                 "MANIFEST.md · {mp4} mp4 · {json} json · {txt} txt · {jpg} jpg · "
                 "{other} other · {size} bytes.".format(
                 n=len(rows), files=totals["total_files"], md=totals["md"],
                 mp4=totals["mp4"], json=totals["json"], txt=totals["txt"],
                 jpg=totals["jpg"], other=totals["other"], size=totals["size_bytes"]))
    lines.append("")
    with open(path, "w", encoding="utf-8") as f:
        f.write("\n".join(lines))
    return path


def main():
    rows = build_rows()
    for target in TARGETS:
        os.makedirs(target, exist_ok=True)
        csv_path = write_csv(rows, target)
        md_path = write_md(rows, target)
        print("wrote", csv_path)
        print("wrote", md_path)
    print("total entries:", len(rows))
    print("by kind:", {k: sum(1 for r in rows if r["kind"] == k)
                        for k in ("dir", "file")})


if __name__ == "__main__":
    main()