#!/usr/bin/env python3
"""Нормализация исходных таблиц NORMY_* → JSON в data/seed/racion/."""

from __future__ import annotations

import json
import re
import sys
from pathlib import Path

ROOT = Path(__file__).resolve().parents[1]
DEFAULT_SOURCE = ROOT.parents[1] / "для разбора и внедрения /тест/RACION_EXPORT/tables/NORMY"
OUT_DIR = ROOT / "data/seed/racion"


def _parse_float_list(raw: str) -> list[float]:
    """POPR_K / Normy — элементы разделены «;», десятичная запятая внутри числа."""
    out: list[float] = []
    for part in raw.strip().split(";"):
        p = part.strip()
        if not p:
            continue
        p = p.replace(",", ".")
        try:
            out.append(float(p))
        except ValueError:
            continue
    return out


def _read_cp1251(path: Path) -> str:
    for enc in ("cp1251", "utf-8", "latin-1"):
        try:
            return path.read_text(encoding=enc)
        except UnicodeDecodeError:
            continue
    return path.read_text(encoding="latin-1", errors="replace")


def _parse_moskwa_lactir(text: str) -> dict:
    rows: list[dict] = []
    udoy_boundaries: list[float] = []
    for line in text.splitlines():
        line = line.strip()
        if not line or line.startswith("=") or "NPITV" in line or "Database:" in line:
            continue
        m = re.match(
            r"^\s*([\d.]+)\s+(\d+)\s+([\d.eE+-]+)\s+(.+)$",
            line,
        )
        if not m:
            continue
        npitv = int(float(m.group(1)))
        pom = int(m.group(2))
        koef = float(m.group(3))
        popr_k = _parse_float_list(m.group(4))
        rows.append({"npitv": npitv, "pom": pom, "koef": koef, "popr_k": popr_k})
        if npitv == 0 and pom == 2 and koef == 0.0:
            udoy_boundaries = popr_k
    return {"udoy_boundaries": udoy_boundaries, "rows": rows}


def _parse_piter_lactir(text: str, *, mass_kg_values: list[float] | None = None) -> dict:
    entries: list[dict] = []
    for line in text.splitlines():
        line = line.strip()
        if not line or line.startswith("=") or "NPITV" in line or "Database:" in line:
            continue
        m = re.match(
            r"^\s*([\d.]+)\s+([\d.eE+-]+)\s+([\d.eE+-]+)\s+(.+)$",
            line,
        )
        if not m:
            continue
        npitv = int(float(m.group(1)))
        konc = float(m.group(2))
        udoy = float(m.group(3))
        normy = _parse_float_list(m.group(4))
        entries.append({"npitv": npitv, "konc": konc, "udoy": udoy, "normy": normy})
    masses = mass_kg_values or [400, 450, 500, 550, 600, 650, 700, 750]
    return {"mass_kg_values": masses, "entries": entries}


def _parse_normy_info(text: str) -> dict:
    rows: list[dict] = []
    for line in text.splitlines():
        line = line.strip()
        if not line or line.startswith("=") or "NPEREM" in line or "Database:" in line:
            continue
        m = re.match(r"^\s*(\d+)\s+(.+)$", line)
        if not m:
            continue
        nperem = int(m.group(1))
        znachenie = _parse_float_list(m.group(2))
        rows.append({"nperem": nperem, "znachenie": znachenie})
    by_nperem = {r["nperem"]: r["znachenie"] for r in rows}
    mass_kg_values = by_nperem.get(14) or by_nperem.get(13) or [400, 450, 500, 550, 600, 650, 700, 750]
    return {"rows": rows, "mass_kg_values": mass_kg_values}


def main() -> int:
    source = Path(sys.argv[1]) if len(sys.argv) > 1 else DEFAULT_SOURCE
    if not source.is_dir():
        print(f"Source not found: {source}", file=sys.stderr)
        return 1
    OUT_DIR.mkdir(parents=True, exist_ok=True)

    moskwa_path = source / "NORMY_MOSKWA_LACTIR.txt"
    piter_path = source / "NORMY_PITER_LACTIR.txt"
    info_path = source / "NORMY_INFO.txt"
    if not moskwa_path.exists() or not piter_path.exists():
        print(f"Missing NORMY files in {source}", file=sys.stderr)
        return 1

    normy_info = _parse_normy_info(_read_cp1251(info_path)) if info_path.exists() else {
        "rows": [],
        "mass_kg_values": [400, 450, 500, 550, 600, 650, 700, 750],
    }
    moskwa = _parse_moskwa_lactir(_read_cp1251(moskwa_path))
    piter = _parse_piter_lactir(
        _read_cp1251(piter_path),
        mass_kg_values=normy_info.get("mass_kg_values"),
    )

    (OUT_DIR / "moskwa_lactir.json").write_text(
        json.dumps(moskwa, ensure_ascii=False, indent=2), encoding="utf-8"
    )
    (OUT_DIR / "piter_lactir.json").write_text(
        json.dumps(piter, ensure_ascii=False, indent=2), encoding="utf-8"
    )
    (OUT_DIR / "normy_info.json").write_text(
        json.dumps(normy_info, ensure_ascii=False, indent=2), encoding="utf-8"
    )
    print(f"Wrote {OUT_DIR}/moskwa_lactir.json ({len(moskwa['rows'])} rows)")
    print(f"Wrote {OUT_DIR}/piter_lactir.json ({len(piter['entries'])} entries)")
    print(f"Wrote {OUT_DIR}/normy_info.json ({len(normy_info['rows'])} rows)")
    return 0


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