import json
from typing import Dict, Any
import spacy
from ai.sarvam_client import generate_response, extract_json
try:
    nlp = spacy.load("en_core_web_sm")
except OSError:
    raise OSError(
        "spaCy model not found. Run: python -m spacy download en_core_web_sm"
    )


def extract_context(text: str) -> Dict[str, list]:

    doc = nlp(text)

    entities = list(
        set(
            ent.text
            for ent in doc.ents
        )
    )

    keywords = []

    for token in doc:

        if (
            token.is_stop
            or token.is_punct
            or token.is_space
        ):
            continue

        if len(token.text) <= 2:
            continue

        keywords.append(
            token.lemma_.lower()
        )

    keywords = list(set(keywords))

    return {
        "entities": entities,
        "keywords": keywords
    }


def create_perspective_prompt(text: str) -> str:

    context = extract_context(text)

    prompt = f"""
        You are an expert media analysis assistant.

        Analyze the following content and determine:

        1. Whether expert opinions are missing.
        2. Whether opposing viewpoints are missing.
        3. Whether stakeholder perspectives are missing.
        4. Suggest additional perspectives that should be considered.
        5. Provide a short explanation.

        Definitions:

        Missing expert opinions:
        The content does not include insights from qualified experts.

        Missing opposing viewpoints:
        The content presents one side but omits reasonable alternative viewpoints.

        Missing stakeholder perspectives:
        The content ignores groups affected by the topic.

        Detected Entities:
        {context["entities"]}

        Detected Keywords:
        {context["keywords"]}
        Do not include markdown, code blocks, explanations, or additional text outside the JSON object.
        Return ONLY valid JSON:

        {{
            "missing_expert_opinions": false,
            "missing_opposing_viewpoints": false,
            "missing_stakeholder_perspectives": false,
            "additional_perspectives": [
                "Perspective 1",
                "Perspective 2"
            ],
            "explanation": "Short explanation."
        }}

        Text:
        {text}
        """

    return prompt


def get_perspective_from_model(text: str) -> str:

    prompt = create_perspective_prompt(text)

    return generate_response(prompt)


def parse_model_response(response: str) -> Dict[str, Any]:

    if response is None:
        return {
            "missing_expert_opinions": False,
            "missing_opposing_viewpoints": False,
            "missing_stakeholder_perspectives": False,
            "additional_perspectives": [],
            "explanation": "No response received from Sarvam AI."
        }

    parsed = extract_json(response)

    if parsed is None:
        return {
            "missing_expert_opinions": False,
            "missing_opposing_viewpoints": False,
            "missing_stakeholder_perspectives": False,
            "additional_perspectives": [],
            "explanation": "Could not parse model response."
        }

    return parsed


def analyze_perspectives(text: str) -> Dict[str, Any]:

    if not text or not text.strip():

        return {
            "missing_expert_opinions": False,
            "missing_opposing_viewpoints": False,
            "missing_stakeholder_perspectives": False,
            "additional_perspectives": [],
            "explanation": "Empty input text."
        }

    raw_response = get_perspective_from_model(text)

    return parse_model_response(raw_response)


if __name__ == "__main__":

    sample_text = """
    The government announced a new tax policy.
    Officials claim it will improve economic growth.
    """

    print(
        analyze_perspectives(sample_text)
    )