#!/usr/bin/env python3
"""Classify MOMO daily-sales source arrival from a read-only preflight log.

This parser never connects to MOMO, never imports files, never moves Drive
artifacts, and never authorizes DB / host / Drive writes. It turns the existing
`momo-drive-token-source-recovery-preflight.sh` evidence into a compact gate so
operators can tell whether they should keep waiting for a legitimate source or
start a separate safe-import preflight.
"""

from __future__ import annotations

import argparse
import json
import re
import sys
from pathlib import Path
from typing import Any


EXPECTED_IMPORT_CONFIG = "當日業績匯入|即時業績_當日"
SUMMARY_RE = re.compile(
    r"^MOMO_DRIVE_TOKEN_SOURCE_PREFLIGHT "
    r"PASS=(?P<pass>\d+) WARN=(?P<warn>\d+) BLOCKED=(?P<blocked>\d+) "
    r"HOST=(?P<host>\S+) FRESHNESS_MAX_DAYS=(?P<freshness_max_days>\d+)"
)


def parse_args() -> argparse.Namespace:
    parser = argparse.ArgumentParser(
        description="Classify MOMO source-arrival readiness from preflight output.",
    )
    parser.add_argument(
        "--preflight-log",
        required=True,
        help="Path to momo-drive-token-source-recovery-preflight output, or '-' for stdin.",
    )
    parser.add_argument("--json", action="store_true", help="Print JSON result.")
    return parser.parse_args()


def load_text(source: str) -> str:
    if source == "-":
        return sys.stdin.read()
    return Path(source).read_text(encoding="utf-8")


def parse_int(value: Any, default: int | None = None) -> int | None:
    try:
        return int(str(value).strip())
    except (TypeError, ValueError):
        return default


def parse_pipe(value: str, expected_parts: int) -> list[str]:
    parts = str(value or "").split("|")
    if len(parts) < expected_parts:
        parts.extend([""] * (expected_parts - len(parts)))
    return parts[:expected_parts]


def date_prefix(value: str) -> str:
    candidate = str(value or "")[:10]
    if re.match(r"^\d{4}-\d{2}-\d{2}$", candidate):
        return candidate
    return ""


def parse_preflight(text: str) -> dict[str, Any]:
    values: dict[str, str] = {}
    messages = {"ok": [], "warn": [], "blocked": []}
    summary: dict[str, Any] = {}

    for raw_line in text.splitlines():
        line = raw_line.strip()
        if not line:
            continue
        summary_match = SUMMARY_RE.match(line)
        if summary_match:
            summary = {
                key: parse_int(value) if key != "host" else value
                for key, value in summary_match.groupdict().items()
            }
            continue
        if line.startswith("OK: "):
            messages["ok"].append(line[4:])
            continue
        if line.startswith("WARN: "):
            messages["warn"].append(line[6:])
            continue
        if line.startswith("BLOCKED: "):
            messages["blocked"].append(line[9:])
            continue
        if re.match(r"^[A-Z][A-Z0-9_]+(?:\s|$)", line):
            key, _, value = line.partition(" ")
            values[key] = value.strip()

    return {"values": values, "messages": messages, "summary": summary}


def monthly_sync_ok(value: str) -> bool:
    snapshot_count, monthly_count, dmin, dmax, mmin, mmax = parse_pipe(value, 6)
    snapshot_n = parse_int(snapshot_count, 0) or 0
    return (
        snapshot_n > 0
        and snapshot_count == monthly_count
        and bool(dmin)
        and bool(dmax)
        and dmin == mmin
        and dmax == mmax
    )


def latest_import_clean(value: str) -> bool:
    job_id, status, _file_name, _created, _completed, total, success, errors = parse_pipe(
        value, 8
    )
    return (
        parse_int(job_id) is not None
        and status == "completed"
        and parse_int(total, -1) == parse_int(success, -2)
        and parse_int(errors, -1) == 0
    )


def no_newer_drive_source(values: dict[str, str], clean_import: bool) -> bool:
    if not clean_import:
        return False
    drive_intake_count = parse_int(values.get("DRIVE_INTAKE_COUNT"), 0) or 0
    drive_failed_count = parse_int(values.get("DRIVE_FAILED_COUNT"), 0) or 0
    if drive_intake_count > 0 or drive_failed_count > 0:
        return False
    global_latest = date_prefix(values.get("DRIVE_GLOBAL_LATEST_MODIFIED", ""))
    _job_id, _status, _file_name, _created, completed, *_rest = parse_pipe(
        values.get("DB_LATEST_DAILY_IMPORT_JOB", ""),
        8,
    )
    completed_date = date_prefix(completed)
    return bool(global_latest and completed_date and global_latest <= completed_date)


def monthly_sync_status(value: str, source_absent_clean: bool) -> str:
    if monthly_sync_ok(value):
        return "in_sync"
    snapshot_count, monthly_count, dmin, dmax, mmin, mmax = parse_pipe(value, 6)
    if (
        source_absent_clean
        and snapshot_count == "0"
        and monthly_count == "0"
        and dmin in {"", "-"}
        and dmax in {"", "-"}
        and mmin in {"", "-"}
        and mmax in {"", "-"}
    ):
        return "not_applicable_no_current_month_source"
    return "not_proven"


def classify(parsed: dict[str, Any]) -> dict[str, Any]:
    values = parsed["values"]
    summary = parsed["summary"]
    messages = parsed["messages"]

    freshness_days_text, latest_daily_date = parse_pipe(values.get("DB_DAILY_FRESHNESS", ""), 2)
    freshness_days = parse_int(freshness_days_text)
    freshness_max_days = parse_int(summary.get("freshness_max_days"), 2) or 2
    drive_intake_count = parse_int(values.get("DRIVE_INTAKE_COUNT"), 0) or 0
    drive_failed_count = parse_int(values.get("DRIVE_FAILED_COUNT"), 0) or 0
    drive_archive_latest = values.get("DRIVE_ARCHIVE_LATEST_MODIFIED", "none") or "none"
    drive_global_latest = values.get("DRIVE_GLOBAL_LATEST_MODIFIED", "none") or "none"

    service_ready = (
        values.get("MOMO_PUBLIC_HEALTH_CODE") == "200"
        and values.get("MOMO_HEALTH_CODE") == "200"
        and values.get("MOMO_APP_HEALTH") == "healthy"
        and values.get("SCHEDULER_RUNNING") == "true"
        and values.get("SCHEDULER_HEALTH") == "healthy"
    )
    import_config_ok = EXPECTED_IMPORT_CONFIG in values.get("IMPORT_CONFIG", "")
    clean_import = latest_import_clean(values.get("DB_LATEST_DAILY_IMPORT_JOB", ""))
    source_absent_clean = no_newer_drive_source(values, clean_import)
    sync_status = monthly_sync_status(
        values.get("DB_MONTHLY_SYNC", ""),
        source_absent_clean,
    )
    sync_ok = sync_status != "not_proven"
    freshness_green = (
        freshness_days is not None and 0 <= freshness_days <= freshness_max_days
    )
    freshness_stale = freshness_days is not None and freshness_days > freshness_max_days

    blockers: list[str] = []
    warnings: list[str] = []
    status = "blocked_preflight_evidence_incomplete"
    next_step = "rerun_momo_drive_token_source_recovery_preflight"
    safe_import_preflight_allowed = False
    exit_code = 2

    if not summary:
        blockers.append("preflight_summary_missing")
    if not service_ready:
        blockers.append("momo_service_or_scheduler_not_ready")
    if not import_config_ok:
        blockers.append("drive_import_config_not_expected_intake")
    if sync_status == "not_proven":
        blockers.append("current_month_snapshot_realtime_sync_not_proven")
    elif sync_status == "not_applicable_no_current_month_source":
        warnings.append("current_month_sync_not_applicable_no_current_month_source")
    if drive_failed_count > 0:
        warnings.append("drive_failed_folder_has_matching_candidates")

    if blockers:
        status = "blocked_service_or_evidence_not_ready"
        next_step = "repair_readonly_preflight_evidence_before_source_or_import_decision"
    elif freshness_green:
        status = "freshness_already_green_recheck_cold_start"
        next_step = "rerun_post_reboot_readiness_summary_with_same_evidence_chain"
        exit_code = 0
    elif drive_intake_count > 0 and freshness_stale:
        status = "source_arrived_ready_for_safe_import_preflight"
        next_step = "run_owner_approved_safe_import_preflight_no_db_or_drive_write_yet"
        safe_import_preflight_allowed = True
        exit_code = 0
    elif drive_intake_count > 0:
        status = "source_arrived_freshness_unknown_recheck_before_import"
        next_step = "rerun_momo_preflight_and_validate_freshness_before_import"
        safe_import_preflight_allowed = True
        exit_code = 1
    elif freshness_stale and source_absent_clean:
        status = "source_absent_no_newer_drive_waiting"
        next_step = "wait_for_legitimate_daily_sales_source_then_rerun_gate"
        exit_code = 1
    elif freshness_stale:
        status = "blocked_source_absent_fail_closed"
        next_step = "wait_for_legitimate_daily_sales_source_then_rerun_gate"
    else:
        status = "blocked_freshness_unknown_fail_closed"
        next_step = "rerun_preflight_or_repair_readonly_freshness_readback"

    if not clean_import:
        warnings.append("latest_daily_import_job_not_clean_completed")

    return {
        "schema_version": "momo_source_arrival_gate_v1",
        "status": status,
        "exit_code": exit_code,
        "next_step": next_step,
        "safe_import_preflight_allowed": safe_import_preflight_allowed,
        "runtime_write_authorized": False,
        "db_write_authorized": False,
        "drive_move_authorized": False,
        "manual_import_authorized": False,
        "secret_value_collection_allowed": False,
        "service_ready": service_ready,
        "import_config_ok": import_config_ok,
        "current_month_sync_ok": sync_ok,
        "current_month_sync_status": sync_status,
        "latest_import_clean": clean_import,
        "source_absent_without_newer_drive": source_absent_clean,
        "freshness_days": freshness_days,
        "freshness_latest_date": latest_daily_date or "unknown",
        "freshness_max_days": freshness_max_days,
        "drive_intake_count": drive_intake_count,
        "drive_archive_latest_modified": drive_archive_latest,
        "drive_global_latest_modified": drive_global_latest,
        "drive_failed_count": drive_failed_count,
        "preflight_pass": summary.get("pass", 0),
        "preflight_warn": summary.get("warn", len(messages["warn"])),
        "preflight_blocked": summary.get("blocked", len(messages["blocked"])),
        "blockers": blockers,
        "warnings": warnings,
        "no_false_green_rules": [
            "source_arrived_does_not_authorize_import",
            "safe_import_preflight_allowed_does_not_authorize_db_write",
            "freshness_green_requires_post_reboot_summary_recheck",
            "archive_or_local_old_file_does_not_count_as_new_source",
        ],
    }


def print_human(result: dict[str, Any]) -> None:
    print(
        "MOMO_SOURCE_ARRIVAL_GATE "
        f"status={result['status']} "
        f"source_intake={result['drive_intake_count']} "
        f"freshness={result['freshness_days']}|{result['freshness_latest_date']} "
        f"safe_import_preflight_allowed={int(result['safe_import_preflight_allowed'])} "
        "runtime_write_authorized=0 "
        "db_write_authorized=0 "
        "drive_move_authorized=0 "
        f"next_step={result['next_step']}"
    )


def main() -> int:
    args = parse_args()
    result = classify(parse_preflight(load_text(args.preflight_log)))
    if args.json:
        print(json.dumps(result, ensure_ascii=False, indent=2, sort_keys=True))
    else:
        print_human(result)
    return int(result["exit_code"])


if __name__ == "__main__":
    raise SystemExit(main())