"""LLM prompt templates for relevance judging (keep wording changes here)."""

from __future__ import annotations

import json
from typing import Any, Dict, Sequence

_CLASSIFY_BATCH_SIMPLE_TEMPLATE = """You are a relevance evaluation assistant for an apparel e-commerce search system. 
Given the user query and each product's information, assign one relevance label to each product.

## Relevance Labels

### Exact
The product fully satisfies the user's search intent.

Use Exact when:
- The product matches the core product type named in the query.
- The key requirements explicitly stated in the query are satisfied.
- There is no clear conflict with any explicit user requirement.

Typical cases:
- The query is only a product type, and the product is exactly that product type.
- The query includes product type + attributes, and the product matches the type and those attributes.

### Partial
The product satisfies the user's primary intent, but does not fully satisfy all specified details.

Use Partial when:
- The core product type matches, but some requested attributes cannot be confirmed.
- The core product type matches, but only some secondary attributes are satisfied.
- The core product type matches, and there are minor or non-critical deviations from the query.
- The product does not clearly contradict the user's explicit requirements, but it also cannot be considered a full match.

Typical cases:
- Query: "red fitted t-shirt", product: "Women's T-Shirt" → color/fit cannot be confirmed.
- Query: "red fitted t-shirt", product: "Blue Fitted T-Shirt" → product type and fit match, but color differs.
- Query: "cotton long sleeve blouse", product: "Long Sleeve Blouse" → material not confirmed.

Important:
Partial should mainly be used when the core product type is correct, but the detailed requirements are incomplete, uncertain, or only partially matched.

### Irrelevant
The product does not satisfy the user's main shopping intent.

Use Irrelevant when:
- The core product type does not match the query.
- The product matches the general category but is a different product type that shoppers would not consider interchangeable.
- The core product type matches, but the product clearly contradicts an explicit and important requirement in the query.

Typical cases:
- Query: "pants", product: "shoes" → wrong product type.
- Query: "dress", product: "skirt" → different product type.
- Query: "fitted pants", product: "loose wide-leg pants" → explicit contradiction on fit.
- Query: "sleeveless dress", product: "long sleeve dress" → explicit contradiction on sleeve style.

## Decision Principles

1. Product type is the highest-priority factor.
   If the query clearly specifies a concrete product type, the result must match that product type to be Exact or Partial.
   A different product type is usually Irrelevant, not Partial.

2. Similar or related product types are not interchangeable when the query is specific.
   For example:
   - dress vs skirt vs jumpsuit
   - jeans vs pants
   - t-shirt vs blouse
   - cardigan vs sweater
   - boots vs shoes
   - bra vs top
   - backpack vs bag
   If the user explicitly searched for one of these, the others should usually be judged Irrelevant.

3. If the core product type matches, then evaluate attributes.
   - If attributes fully match → Exact
   - If attributes are missing, uncertain, or only partially matched → Partial
   - If attributes clearly contradict an explicit important requirement → Irrelevant

4. Distinguish carefully between "not mentioned" and "contradicted".
   - If an attribute is not mentioned or cannot be verified, prefer Partial.
   - If an attribute is explicitly opposite to the query, use Irrelevant.

5. Do not overuse Exact.
   Exact requires strong evidence that the product satisfies the user's stated intent, not just the general category.

Query: {query}

Products:
{lines}

## Output Format
Strictly output {n} lines, each line containing exactly one of:
Exact
Partial
Irrelevant

The lines must correspond sequentially to the products above.
Do not output any other information.
"""

_CLASSIFY_BATCH_SIMPLE_TEMPLATE__zh = """你是一个服装电商搜索系统的相关性评估助手。
给定用户查询和每个产品的信息，为每个产品分配一个相关性标签。

## 相关性标签

### 完全相关
该产品完全满足用户的搜索意图。

在以下情况使用完全相关：
- 产品与查询中指定的核心产品类型相匹配。
- 满足了查询中明确说明的关键要求。
- 与用户明确的任何要求没有明显冲突。

典型情况：
- 查询仅包含产品类型，而产品恰好是该产品类型。
- 查询包含产品类型 + 属性，而产品与该类型及这些属性相匹配。

### 部分相关
该产品满足了用户的主要意图，但并未完全满足所有指定的细节。

在以下情况使用部分相关：
- 核心产品类型匹配，但部分请求的属性无法确认。
- 核心产品类型匹配，但仅满足了部分次要属性。
- 核心产品类型匹配，但与查询存在微小或非关键的偏差。
- 产品未明显违背用户的明确要求，但也不能视为完全匹配。

典型情况：
- 查询："红色修身T恤"，产品："女士T恤" → 颜色/版型无法确认。
- 查询："红色修身T恤"，产品："蓝色修身T恤" → 产品类型和版型匹配，但颜色不同。
- 查询："棉质长袖衬衫"，产品："长袖衬衫" → 材质未确认。

重要提示：
部分相关主要应在核心产品类型正确，但详细要求不完整、不确定或仅部分匹配时使用。

### 不相关
该产品不满足用户的主要购物意图。

在以下情况使用不相关：
- 核心产品类型与查询不匹配。
- 产品匹配了大致类别，但属于购物者不会认为可互换的不同产品类型。
- 核心产品类型匹配，但产品明显违背了查询中一个明确且重要的要求。

典型情况：
- 查询："裤子"，产品："鞋子" → 错误的产品类型。
- 查询："连衣裙"，产品："半身裙" → 不同的产品类型。
- 查询："修身裤"，产品："宽松阔腿裤" → 版型上明显矛盾。
- 查询："无袖连衣裙"，产品："长袖连衣裙" → 袖型上明显矛盾。

## 决策原则

1. 产品类型是最高优先级的因素。
   如果查询明确指定了具体产品类型，结果必须匹配该产品类型才能被评为完全相关或部分相关。
   不同的产品类型通常是不相关，而非部分相关。

2. 当查询明确时，相似或相关的产品类型不可互换。
   例如：
   - 连衣裙 vs 半身裙 vs 连体裤
   - 牛仔裤 vs 裤子
   - T恤 vs 衬衫
   - 开衫 vs 毛衣
   - 靴子 vs 鞋子
   - 文胸 vs 上衣
   - 双肩包 vs 包
   如果用户明确搜索了其中一种，其他的通常应判断为不相关。

3. 如果核心产品类型匹配，则评估属性。
   - 如果属性完全匹配 → 完全相关
   - 如果属性缺失、不确定或仅部分匹配 → 部分相关
   - 如果属性明显违背明确的重点要求 → 不相关

4. 仔细区分“未提及”和“矛盾”。
   - 如果属性未提及或无法验证，倾向于部分相关。
   - 如果属性与查询明确相反，使用不相关。

5. 不要过度使用完全相关。
   完全相关需要强有力的证据表明产品满足了用户声明的意图，而不仅仅是通用类别。

查询: {query}

产品:
{lines}

## 输出格式
严格输出 {n} 行，每行包含以下之一：
Exact
Partial
Irrelevant

这些行必须按顺序对应上面的产品。
不要输出任何其他信息。
"""



def classify_batch_simple_prompt(query: str, numbered_doc_lines: Sequence[str]) -> str:
    lines = "\n".join(numbered_doc_lines)
    n = len(numbered_doc_lines)
    return _CLASSIFY_BATCH_SIMPLE_TEMPLATE.format(query=query, lines=lines, n=n)


_EXTRACT_QUERY_PROFILE_TEMPLATE = """You are building a structured intent profile for e-commerce relevance judging.
Use the original user query as the source of truth. Parser hints may help, but if a hint conflicts with the original query, trust the original query.
Be conservative: only mark an attribute as required if the user explicitly asked for it.

Return JSON with this schema:
{{
  "normalized_query_en": string,
  "primary_category": string,
  "allowed_categories": [string],
  "required_attributes": [
    {{"name": string, "required_terms": [string], "conflicting_terms": [string], "match_mode": "explicit"}}
  ],
  "notes": [string]
}}

Guidelines:
- Exact later will require explicit evidence for all required attributes.
- allowed_categories should contain only near-synonyms of the same product type, not substitutes. For example dress can allow midi dress/cocktail dress, but not skirt, top, jumpsuit, or outfit unless the query explicitly asks for them.
- If the query asks for dress/skirt/jeans/t-shirt, near but different product types are not Exact.
- If the query includes color, fit, silhouette, or length, include them as required_attributes.
- For fit words, include conflicting terms when obvious, e.g. fitted conflicts with oversized/loose; oversized conflicts with fitted/tight.
- For color, include conflicting colors only when clear from the query.

Original query: {query}
Parser hints JSON: {hints_json}
"""


def extract_query_profile_prompt(query: str, parser_hints: Dict[str, Any]) -> str:
    hints_json = json.dumps(parser_hints, ensure_ascii=False)
    return _EXTRACT_QUERY_PROFILE_TEMPLATE.format(query=query, hints_json=hints_json)


_CLASSIFY_BATCH_COMPLEX_TEMPLATE = """You are an e-commerce search relevance judge.
Judge each product against the structured query profile below.

Relevance rules:
- Exact: product type matches the target intent, and every explicit required attribute is positively supported by the title/options/tags/category. If an attribute is missing or only guessed, it is NOT Exact.
- Partial: main product type/use case matches, but some required attribute is missing, weaker, uncertain, or only approximately matched.
- Irrelevant: product type/use case mismatched, or an explicit required attribute clearly conflicts.
- Be conservative with Exact.
- Graphic/holiday/message tees are not Exact for a plain color/style tee query unless that graphic/theme was requested.
- Jumpsuit/romper/set is not Exact for dress/skirt/jeans queries.

Original query: {query}
Structured query profile JSON: {profile_json}

Products:
{lines}

Return JSON only, with schema:
{{"labels":[{{"index":1,"label":"Exact","reason":"short phrase"}}]}}
"""


def classify_batch_complex_prompt(
    query: str,
    query_profile: Dict[str, Any],
    numbered_doc_lines: Sequence[str],
) -> str:
    lines = "\n".join(numbered_doc_lines)
    profile_json = json.dumps(query_profile, ensure_ascii=False)
    return _CLASSIFY_BATCH_COMPLEX_TEMPLATE.format(
        query=query,
        profile_json=profile_json,
        lines=lines,
    )