from __future__ import annotations

import json
import re
from pathlib import Path
from typing import Any, Iterable

import yaml


ROOT = Path(__file__).resolve().parents[2]


def load_json(path: Path) -> dict[str, Any]:
    if not path.exists():
        return {}
    try:
        obj = json.loads(path.read_text(encoding="utf-8"))
    except Exception:
        return {}
    return obj if isinstance(obj, dict) else {}


def load_yaml(path: Path) -> dict[str, Any]:
    if not path.exists():
        return {}
    try:
        obj = yaml.safe_load(path.read_text(encoding="utf-8"))
    except Exception:
        return {}
    return obj if isinstance(obj, dict) else {}


def read_text(path: Path) -> str:
    if not path.exists():
        return ""
    return path.read_text(encoding="utf-8", errors="ignore")


def iter_files(*patterns: str) -> list[Path]:
    files: list[Path] = []
    for pattern in patterns:
        files.extend([p for p in ROOT.glob(pattern) if p.is_file()])
    return files


def collect_all_files() -> list[Path]:
    return [p for p in ROOT.rglob("*") if p.is_file()]


def collect_temp_files() -> list[Path]:
    temp = ROOT / "Temp"
    return [p for p in temp.rglob("*") if p.is_file()] if temp.exists() else []


def collect_gas_files() -> list[Path]:
    root_files = [ROOT / n for n in ("gas_apex_alpha_watch.gs", "gas_apex_runtime_core.gs", "gas_data_collect.gs", "gas_data_feed.gs", "gas_harness_rows.gs", "gas_lib.gs", "gas_report.gs") if (ROOT / n).exists()]
    adapter_parts_dir = ROOT / "src" / "gas_adapter_parts"
    adapter_files = sorted(adapter_parts_dir.glob("*.gs")) if adapter_parts_dir.exists() else []
    return root_files + adapter_files


def collect_prompt_files() -> list[Path]:
    prompt_root = ROOT / "prompts"
    if not prompt_root.exists():
        return []
    return [p for p in prompt_root.rglob("*.md") if p.is_file()]


def collect_tool_files() -> list[Path]:
    tool_root = ROOT / "tools"
    return [p for p in tool_root.rglob("*.py") if p.is_file()] if tool_root.exists() else []


def collect_spec_files() -> list[Path]:
    spec_root = ROOT / "spec"
    return [p for p in spec_root.rglob("*.yaml") if p.is_file()] if spec_root.exists() else []


def load_formula_registry() -> dict[str, Any]:
    payload = load_yaml(ROOT / "spec" / "13_formula_registry.yaml")
    return ((payload.get("formula_registry") or {}).get("formulas")) or {}


def extract_formula_ids() -> list[str]:
    return [str(fid) for fid in load_formula_registry().keys()]


def extract_formula_outputs() -> dict[str, list[str]]:
    outputs: dict[str, list[str]] = {}
    formulas = load_formula_registry()
    for fid, row in formulas.items():
        out_fields: list[str] = []
        output = row.get("output")
        if isinstance(output, dict):
            if isinstance(output.get("field"), str):
                out_fields.append(output["field"])
            if isinstance(output.get("fields"), list):
                for item in output["fields"]:
                    if isinstance(item, str):
                        out_fields.append(item)
                    elif isinstance(item, dict):
                        if isinstance(item.get("field"), str):
                            out_fields.append(item["field"])
                        elif isinstance(item.get("name"), str):
                            out_fields.append(item["name"])
            if isinstance(output.get("fields"), dict):
                out_fields.extend([str(k) for k in output["fields"].keys() if isinstance(k, str)])
            for key in output.keys():
                if key not in {"field", "fields", "note", "notes"} and isinstance(key, str):
                    out_fields.append(key)
        if isinstance(row.get("expected_outputs"), list):
            out_fields.extend([str(x) for x in row["expected_outputs"] if isinstance(x, str)])
        outputs[str(fid)] = sorted(set(out_fields))
    return outputs


def find_numbers(text: str) -> list[str]:
    return re.findall(r"(?<![A-Za-z])(?:\d{1,3}(?:,\d{3})+|\d+)(?:\.\d+)?", text)


def scan_text_for_terms(paths: Iterable[Path], terms: Iterable[str]) -> dict[str, list[str]]:
    result: dict[str, list[str]] = {}
    for path in paths:
        text = read_text(path)
        hits = [term for term in terms if term in text]
        if hits:
            result[str(path)] = hits
    return result