services.py

import json
import math
import os
import tempfile
from datetime import datetime

import pandas as pd

from catalog_resolver import resolve_items
from config import call_llm, llm_available
from data import SAMPLE_CATALOG
from parser_fallback import parse_po_fallback
from po_normalizer import normalize_po_text
from prompts import DELIVERY_SYSTEM, BESTSELLER_SYSTEM, build_parse_po_system


def _extract_json_from_llm(raw: str) -> dict | None:
    json_str = raw.strip()
    if "```" in json_str:
        json_str = "\n".join(
            line for line in json_str.split("\n")
            if not line.strip().startswith("```")
        )
    try:
        return json.loads(json_str)
    except json.JSONDecodeError:
        start, end = raw.find("{"), raw.rfind("}") + 1
        if start != -1 and end > start:
            try:
                return json.loads(raw[start:end])
            except json.JSONDecodeError:
                return None
    return None


def _validate_po_data(data: dict) -> dict:
    """Stage 3a — enforce structured schema before catalog anchoring."""
    items = data.get("items") or []
    clean = []
    for it in items:
        if not isinstance(it, dict):
            continue
        qty = it.get("quantity", 0)
        try:
            qty = int(qty)
        except (TypeError, ValueError):
            qty = 0
        product = str(it.get("product", "")).strip()
        if product and qty > 0:
            clean.append({
                "product": product,
                "quantity": qty,
                "notes": str(it.get("notes", "")).strip(),
            })
    return {"items": clean, "store_notes": str(data.get("store_notes", "")).strip()}


def parse_po(store_name: str, po_text: str, all_pos: dict) -> tuple:
    if not po_text.strip():
        return pd.DataFrame(columns=["Product", "Qty", "Notes"]), "Please paste a PO first.", all_pos

    used_fallback = False
    data = None

    # Stage 1: normalize Indonesian/English code-mixed slang
    normalized, slang_fixes = normalize_po_text(po_text)

    # Stage 2: Qwen extracts strict JSON (temperature=0.1 in config)
    raw = call_llm(
        f"Store: {store_name}\n\nPO text:\n{normalized}",
        system=build_parse_po_system(SAMPLE_CATALOG),
    )
    if not raw.startswith("[LLM Error"):
        data = _extract_json_from_llm(raw)

    if data is None:
        data = parse_po_fallback(normalized)
        used_fallback = True
        if not data.get("items"):
            err = raw[:300] if raw.startswith("[LLM Error") else "No line items detected."
            return (
                pd.DataFrame(columns=["Product", "Qty", "Notes"]),
                f"Could not parse PO. {err}",
                all_pos,
            )

    data = _validate_po_data(data)

    # Stage 3b: anchor product names to official catalog (fuzzy match)
    raw_items = data.get("items", [])
    items = resolve_items(raw_items, SAMPLE_CATALOG)
    catalog_hits = sum(
        1 for before, after in zip(raw_items, items)
        if before.get("product", "").strip().lower() != after.get("product", "").strip().lower()
    )
    store_notes = data.get("store_notes", "")
    rows = [
        {
            "Product": it.get("product", ""),
            "Qty": it.get("quantity", 0),
            "Notes": it.get("notes", ""),
        }
        for it in items
    ]
    df = pd.DataFrame(rows) if rows else pd.DataFrame(columns=["Product", "Qty", "Notes"])

    all_pos[store_name] = {
        "timestamp": datetime.now().strftime("%Y-%m-%d %H:%M"),
        "items": rows,
        "store_notes": store_notes,
    }

    total_qty = sum(r["Qty"] for r in rows)
    engine = "offline rules" if used_fallback else "Qwen 2.5-7B"
    pipeline = "normalize → extract JSON → catalog anchor"
    status = (
        f"Parsed {len(rows)} items ({total_qty} stickers) from {store_name} | "
        f"Pipeline: {pipeline} | Engine: {engine}"
    )
    if slang_fixes:
        status += f" | Slang normalized: {', '.join(slang_fixes[:4])}"
        if len(slang_fixes) > 4:
            status += f" +{len(slang_fixes) - 4} more"
    if catalog_hits:
        status += f" | Catalog matched: {catalog_hits} name(s)"
    if store_notes:
        status += f" | Notes: {store_notes}"
    return df, status, all_pos


def save_po(store_name: str, edited_table, all_pos: dict) -> tuple:
    if edited_table is None or (isinstance(edited_table, pd.DataFrame) and edited_table.empty):
        return all_pos, "Nothing to save."
    if isinstance(edited_table, pd.DataFrame):
        rows = edited_table.to_dict("records")
    else:
        rows = [{"Product": r[0], "Qty": r[1], "Notes": r[2]} for r in edited_table]
    all_pos[store_name] = all_pos.get(
        store_name,
        {"timestamp": datetime.now().strftime("%Y-%m-%d %H:%M"), "store_notes": ""},
    )
    all_pos[store_name]["items"] = rows
    return all_pos, f"Saved {len(rows)} items for {store_name}."


def build_demand_table(all_pos: dict, stock_df) -> tuple:
    if isinstance(stock_df, list):
        stock_df = pd.DataFrame(stock_df, columns=["Product", "In Stock"])

    demand: dict[str, int] = {}
    stores_with_po: list[str] = []
    for store, po_data in all_pos.items():
        stores_with_po.append(store)
        for item in po_data.get("items", []):
            qty = item["Qty"] if isinstance(item["Qty"], (int, float)) else 0
            demand[item["Product"]] = demand.get(item["Product"], 0) + int(qty)

    if not demand:
        return (
            pd.DataFrame(columns=["Product", "Total Demand", "In Stock", "Shortage"]),
            "No POs parsed yet. Go to the PO Intake tab first.",
        )

    stock_map = {}
    if stock_df is not None and not stock_df.empty:
        stock_map = {row["Product"]: int(row["In Stock"]) for _, row in stock_df.iterrows()}

    rows = [
        {
            "Product": p,
            "Total Demand": d,
            "In Stock": stock_map.get(p, 0),
            "Shortage": max(0, d - stock_map.get(p, 0)),
        }
        for p, d in sorted(demand.items())
    ]
    df = pd.DataFrame(rows)
    shortage_total = sum(r["Shortage"] for r in rows)
    summary = (
        f"POs from {len(stores_with_po)} stores | "
        f"{len(rows)} products | "
        f"Shortage: {shortage_total} stickers to produce"
    )
    return df, summary


def calculate_printing(demand_df) -> tuple:
    if demand_df is None or (isinstance(demand_df, pd.DataFrame) and demand_df.empty):
        return (
            pd.DataFrame(columns=["Product", "Qty to Print", "A3 Sheets (8 per sheet)"]),
            "No shortage data. Check the Demand tab first.",
            None,
        )
    if isinstance(demand_df, list):
        demand_df = pd.DataFrame(demand_df, columns=["Product", "Total Demand", "In Stock", "Shortage"])

    rows: list[dict] = []
    total_sheets = 0
    for _, row in demand_df.iterrows():
        shortage = int(row.get("Shortage", 0))
        if shortage > 0:
            sheets = math.ceil(shortage / 8)
            total_sheets += sheets
            rows.append({
                "Product": row["Product"],
                "Qty to Print": shortage,
                "A3 Sheets (8 per sheet)": sheets,
            })

    if not rows:
        return (
            pd.DataFrame(columns=["Product", "Qty to Print", "A3 Sheets (8 per sheet)"]),
            "No printing needed -- stock covers all demand!",
            None,
        )

    df = pd.DataFrame(rows)
    path = os.path.join(tempfile.gettempdir(), f"print_order_{datetime.now():%Y%m%d_%H%M%S}.csv")
    df.to_csv(path, index=False)

    total_qty = sum(r["Qty to Print"] for r in rows)
    summary = f"Print {total_qty} stickers across {len(rows)} varieties | Total A3 sheets: {total_sheets}"
    return df, summary, path


def _delivery_doc_fallback(store_name: str, items: list, language: str) -> str:
    lang = "id" if language.lower().startswith("indo") else "en"
    date_str = datetime.now().strftime("%d %B %Y")
    lines = items if lang == "en" else items
    header = (
        f"PAPERAIN STUDIO — DELIVERY NOTE\n{'=' * 40}\n"
        f"{'Store' if lang == 'en' else 'Toko'}: {store_name}\n"
        f"{'Date' if lang == 'en' else 'Tanggal'}: {date_str}\n\n"
        f"{'Items' if lang == 'en' else 'Daftar barang'}:\n"
    )
    body = ""
    total = 0
    for i, it in enumerate([x for x in items if x.get("Qty", 0) > 0], 1):
        qty = int(it.get("Qty", 0))
        total += qty
        body += f"  {i}. {it['Product']} — {qty} pcs\n"
    footer = (
        f"\n{'Total stickers' if lang == 'en' else 'Total stiker'}: {total} pcs\n\n"
        + (
            "Please verify receipt and contact us if anything is missing.\n— Paperain Studio, Yogyakarta"
            if lang == "en"
            else "Mohon periksa barang saat diterima. Hubungi kami jika ada yang kurang.\n— Paperain Studio, Yogyakarta"
        )
    )
    return header + body + footer


def generate_delivery_doc(store_name: str, all_pos: dict, language: str) -> str:
    if store_name not in all_pos or not all_pos[store_name].get("items"):
        return f"No PO data for {store_name}. Parse their PO first in the PO Intake tab."

    items = all_pos[store_name]["items"]
    items_text = "\n".join(
        f"- {it['Product']}: {it['Qty']} pcs"
        for it in items if it.get("Qty", 0) > 0
    )
    total = sum(it.get("Qty", 0) for it in items)

    prompt = (
        f"Store: {store_name}\n"
        f"Date: {datetime.now():%B %d, %Y}\n"
        f"Language: {language}\n"
        f"Total items: {total}\n\n"
        f"Items to deliver:\n{items_text}"
    )
    raw = call_llm(prompt, system=DELIVERY_SYSTEM)
    if raw.startswith("[LLM Error"):
        return _delivery_doc_fallback(store_name, items, language)
    return raw


def generate_bestseller_report(all_pos: dict, language: str) -> str:
    if not all_pos:
        return "No PO data yet. Parse some store POs first to generate recommendations."

    demand: dict[str, int] = {}
    store_demand: dict[str, dict[str, int]] = {}
    for store, po_data in all_pos.items():
        store_demand[store] = {}
        for item in po_data.get("items", []):
            qty = int(item.get("Qty", 0)) if isinstance(item.get("Qty", 0), (int, float)) else 0
            demand[item["Product"]] = demand.get(item["Product"], 0) + qty
            store_demand[store][item["Product"]] = qty

    if not demand:
        return "No order data to analyze."

    sales_text = "Aggregated demand across all stores:\n"
    for product, total in sorted(demand.items(), key=lambda x: x[1], reverse=True):
        stores = [
            f"{s} ({store_demand[s].get(product, 0)})"
            for s in store_demand if store_demand[s].get(product, 0) > 0
        ]
        sales_text += f"- {product}: {total} total ({', '.join(stores)})\n"

    raw = call_llm(f"Language: {language}\n\n{sales_text}", system=BESTSELLER_SYSTEM)
    if raw.startswith("[LLM Error"):
        return _bestseller_fallback(demand, store_demand, language)
    return raw


def _bestseller_fallback(demand: dict, store_demand: dict, language: str) -> str:
    lang = "id" if language.lower().startswith("indo") else "en"
    top = sorted(demand.items(), key=lambda x: x[1], reverse=True)[:8]
    title = "Piper's Best Seller Report" if lang == "en" else "Laporan Best Seller dari Piper"
    lines = [f"{title}\n{'=' * 36}\n"]
    for rank, (product, total) in enumerate(top, 1):
        stores = [s for s, d in store_demand.items() if d.get(product, 0) > 0]
        if lang == "en":
            lines.append(f"{rank}. {product} — {total} ordered across {len(stores)} store(s)")
        else:
            lines.append(f"{rank}. {product} — {total} dipesan dari {len(stores)} toko")
    lines.append(
        "\nThese designs sell consistently — great for restock and new partner onboarding."
        if lang == "en"
        else "\nDesain ini laris — cocok untuk restock dan rekomendasi ke toko baru."
    )
    return "\n".join(lines)


def run_full_workflow(all_pos: dict, stock_df) -> tuple:
    """Demand + print in one click (uses existing PO state)."""
    demand_df, demand_summary = build_demand_table(all_pos, stock_df)
    print_df, print_summary, print_csv = calculate_printing(demand_df)
    combined = f"{demand_summary}\n\n{print_summary}"
    return demand_df, combined, print_df, print_summary, print_csv


def format_po_log(all_pos: dict) -> str:
    if not all_pos:
        return "*No POs parsed yet.*"
    md = ""
    for store, data in all_pos.items():
        md += f"### {store} ({data.get('timestamp', '')})\n"
        for it in data.get("items", []):
            md += f"- {it.get('Product', '')} x{it.get('Qty', 0)}\n"
        if data.get("store_notes"):
            md += f"\n*Notes: {data['store_notes']}*\n"
        md += "\n---\n\n"
    return md


def export_all_pos_csv(all_pos: dict):
    if not all_pos:
        return None
    rows = []
    for store, data in all_pos.items():
        for item in data.get("items", []):
            rows.append({
                "Store": store,
                "Product": item.get("Product", ""),
                "Qty": item.get("Qty", 0),
                "Notes": item.get("Notes", ""),
                "Parsed At": data.get("timestamp", ""),
            })
    if not rows:
        return None
    df = pd.DataFrame(rows)
    path = os.path.join(tempfile.gettempdir(), f"all_pos_{datetime.now():%Y%m%d_%H%M%S}.csv")
    df.to_csv(path, index=False)
    return path