#!/usr/bin/env python3
"""Check a listener directory before a site build ships it.

  python3 tools/asr/check_packs.py DIR

DIR must hold what tools/asr/build_asr.py built for the committed catalogue
(data/asr/index.json): its index.json points at index.<sha12>.json, whose
bytes are the committed catalogue's, and every graph, weights file,
vocabulary and licence that catalogue names is there with its exact size and
SHA-256. Otherwise this exits non-zero and says what is wrong, so a build
never ships a model that disagrees with the catalogue, or that is incomplete.

Standard library only; Python 3.9 or later (macOS's own python3).
"""

import hashlib
import json
import sys
from pathlib import Path

HERE = Path(__file__).resolve().parent
COMMITTED = HERE.parents[1] / "data" / "asr" / "index.json"
SHOW = 10


def sha256(path):
    h = hashlib.sha256()
    with open(path, "rb") as f:
        for chunk in iter(lambda: f.read(1 << 22), b""):
            h.update(chunk)
    return h.hexdigest()


def model_files(model):
    """Every file a model names: its graphs, their weights, its vocabulary."""
    out = []
    for key in ("encoder", "step", "vad"):
        graph = model.get(key, {})
        if "file" in graph:
            out.append(graph["file"])
        out += graph.get("data", [])
    if "vocab" in model:
        out.append(model["vocab"])
    return [(f["url"], f["bytes"], f["sha256"]) for f in out]


def main(argv):
    if len(argv) != 2:
        print(__doc__, file=sys.stderr)
        return 2
    root = Path(argv[1])
    problems = []
    try:
        pointer = json.loads((root / "index.json").read_text(encoding="utf-8"))
        name = pointer["current"]
        cat_bytes = (root / name).read_bytes()
    except (OSError, ValueError, KeyError) as e:
        print(f"✗ {root}: no readable index.json and catalogue ({e})", file=sys.stderr)
        return 1
    if cat_bytes != COMMITTED.read_bytes():
        problems.append(f"{name} is not the committed catalogue ({COMMITTED})")
    if name != f"index.{hashlib.sha256(cat_bytes).hexdigest()[:12]}.json":
        problems.append(f"{name} is not named by its contents")
    cat = json.loads(cat_bytes)
    refs = []
    for model in cat.get("models", {}).values():
        refs += model_files(model)
        for credit in model.get("credits", []):
            lf = credit.get("licence_file")
            if lf:
                data = (root / lf).read_bytes() if (root / lf).is_file() else b""
                refs.append((lf, len(data) if data else -1, hashlib.sha256(data).hexdigest() if data else ""))
    if not (root / "LICENSES.md").is_file():
        problems.append("LICENSES.md is missing")
    for rel, size, digest in refs:
        f = root / rel
        if not f.is_file():
            problems.append(f"missing {rel}")
        elif f.stat().st_size != size:
            problems.append(f"{rel} is {f.stat().st_size} bytes, the catalogue says {size}")
        elif sha256(f) != digest:
            problems.append(f"{rel} does not match its SHA-256")
    if problems:
        for p in problems[:SHOW]:
            print(f"✗ {p}", file=sys.stderr)
        if len(problems) > SHOW:
            print(f"  … and {len(problems) - SHOW} more", file=sys.stderr)
        return 1
    print(f"✓ {root}: {len(refs)} files match {name}")
    return 0


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