"""Analyzer: extracts a Sales Kit (product facts) + initial pain-fit from inputs.

Product data is used primarily to derive pains that persona generation can build
against. The result also carries a `scenario` prompt that frames persona creation.
"""
from __future__ import annotations

from typing import Any

from ..llm import LLMClient

SALES_KIT_SYSTEM = """You are an expert ecommerce/B2B analyst. Given product information
(typed in a form and/or extracted from uploaded files), produce a structured Sales Kit.

Rules:
- Output ONLY valid JSON with the exact keys requested.
- Pain-fit: judge which pains / customer pain categories the product can PLAUSIBLY solve,
  and clearly distinguish "strong fit" from "partial / weak fit".
- The product info is only initial grounding; personas may be reused across similar products.
- If some fields are unknown, leave them as empty lists / empty strings (never invent specifics).

Output schema:
{
  "productName": string,
  "category": string,
  "valueProps": [string],
  "features": [string],
  "pricingAnchors": [string],
  "targetAudience": { "segment": string, "demographics": string, "useCases": [string] },
  "objectionHandlers": [string],
  "initialPainFit": [
    { "pain": string, "fit": "strong"|"partial"|"weak", "evidence": string }
  ],
  "scenarioFrame": string
}
The scenarioFrame is a one-paragraph description of the selling situation (who the seller,
what channel, target segment) that will frame persona creation.
"""


class Analyzer:
    def __init__(self, llm: LLMClient) -> None:
        self.llm = llm

    def analyze(
        self,
        *,
        product: str = "",
        segment: str = "",
        description: str = "",
        file_text: str = "",
        channel: str = "facebook",
    ) -> dict[str, Any]:
        # Build the merged product context (form wins over file text)
        product_src = product.strip() or file_text.strip() or ""
        context = (
            f"PRODUCT (form/typed):\n{product}\n\n" if product.strip() else ""
        )
        if segment.strip():
            context += f"INITIAL CUSTOMER SEGMENT:\n{segment}\n\n"
        if description.strip():
            context += f"ADDITIONAL DESCRIPTION / SCENARIO:\n{description}\n\n"
        if file_text.strip():
            context += f"UPLOADED FILE CONTENT:\n{file_text[:12000]}\n"
        if not context.strip():
            raise ValueError("no product information provided (form or file)")

        user_prompt = (
            f"Channel: {channel}\n\n"
            f"Analyze the following and return the Sales Kit JSON:\n\n{context}"
        )
        result = self.llm.complete_json(
            SALES_KIT_SYSTEM, user_prompt, temperature=0.2, max_tokens=5000
        )

        # Normalize shape defensively
        result.setdefault("productName", product_src[:200] or "Untitled product")
        result.setdefault("category", "")
        result.setdefault("valueProps", [])
        result.setdefault("features", [])
        result.setdefault("pricingAnchors", [])
        result.setdefault("targetAudience", {
            "segment": segment or "",
            "demographics": "",
            "useCases": [],
        })
        result.setdefault("objectionHandlers", [])
        result.setdefault("initialPainFit", [])
        result.setdefault("scenarioFrame", description or "")

        for k in ("valueProps", "features", "pricingAnchors", "objectionHandlers"):
            if not isinstance(result[k], list):
                result[k] = []
        if not isinstance(result.get("initialPainFit"), list):
            result["initialPainFit"] = []
        return result