import os
import json
from google import genai
from google.genai import types
from pydantic import BaseModel
from typing import Optional, Union, BinaryIO
from application.utils import logger
from application.schemas.response_schema import GEMINI_RESPONSE_FORMAT

logger = logger.get_logger()

PROMPT = (
    """You are a PDF parsing agent.
    Your job is to extract from a company’s sustainability or ESG report in PDF format:
    If the values are not found in the document, please return json null for that value.
    """
)

class Parameter(BaseModel):
    """
    A generic class to hold details for a sustainability metric.
    """
    synonym: str
    uom: str
    description: str
    value: str

class GreenhouseGasGHGProtocolParameters(BaseModel):
    Total_GHG_Emissions: Parameter
    Scope_1_Emissions: Parameter
    Scope_2_Emissions: Parameter
    Scope_3_Emissions: Parameter
    CO2_Emissions: Parameter
    CH4_Emissions: Parameter
    N2O_Emissions: Parameter
    HFC_Emissions: Parameter
    PFC_Emissions: Parameter
    SF6_Emissions: Parameter
    NF3_Emissions: Parameter
    Biogenic_CO2_Emissions: Parameter
    Emissions_Intensity_per_Revenue: Parameter
    Emissions_Intensity_per_Employee: Parameter
    Base_Year_Emissions: Parameter
    Emissions_Reduction_Target: Parameter
    Emissions_Reduction_Achieved: Parameter
    Energy_Consumption: Parameter
    Renewable_Energy_Consumption: Parameter
    Non_Renewable_Energy_Consumption: Parameter
    Energy_Intensity_per_Revenue: Parameter
    Energy_Intensity_per_Employee: Parameter
    Fuel_Consumption: Parameter
    Electricity_Consumption: Parameter
    Heat_Consumption: Parameter
    Steam_Consumption: Parameter
    Cooling_Consumption: Parameter
    Purchased_Goods_and_Services_Emissions: Parameter
    Capital_Goods_Emissions: Parameter
    Fuel_and_Energy_Related_Activities_Emissions: Parameter
    Upstream_Transportation_and_Distribution_Emissions: Parameter
    Waste_Generated_in_Operations_Emissions: Parameter
    Business_Travel_Emissions: Parameter
    Employee_Commuting_Emissions: Parameter
    Upstream_Leased_Assets_Emissions: Parameter
    # Downstream_Transportation_and_Distribution_Emissions: Parameter
    # Processing_of_Sold_Products_Emissions: Parameter
    # Use_of_Sold_Products_Emissions: Parameter
    # End_of_Life_Treatment_of_Sold_Products_Emissions: Parameter
    # Downstream_Leased_Assets_Emissions: Parameter
    # Franchises_Emissions: Parameter
    # Investments_Emissions: Parameter
    # Carbon_Offsets_Purchased: Parameter
    # Net_GHG_Emissions: Parameter
    # Carbon_Sequestration: Parameter

class EmissionData(BaseModel):
    GreenhouseGasGHGProtocolParameters: GreenhouseGasGHGProtocolParameters

# print(json.dumps(EmissionData.model_json_schema(), indent=2))

def extract_emissions_data_as_json(
    api: str,
    model: str,
    file_input: Union[BinaryIO, bytes]
) -> Optional[dict]:
    """
    Extract ESG data from PDF using OpenAI or Gemini APIs.

    Args:
        api: 'openai' or 'gemini'
        model: Model name (e.g. gpt-4o, gemini-pro)
        file_input: File-like object or bytes of the PDF.

    Returns:
        Parsed ESG data as dict or None if failed.
    """
    try:

        client = genai.Client(api_key=os.getenv("gemini_api_key"))

        file_bytes = file_input.read()
        logger.info("[Gemini] Sending content for generation...")

        response = client.models.generate_content(
            model=model,
            contents=[
                types.Part.from_bytes(data=file_bytes, mime_type="application/pdf"),
                PROMPT
            ],
            config={
                'response_mime_type': 'application/json',
                'response_schema': GEMINI_RESPONSE_FORMAT,
            }
        )
        logger.info("[Gemini] Response received.")
        try:
            return json.loads(response.text)
        except json.JSONDecodeError:
            logger.warning("Failed to parse JSON, returning raw response.")
            return {"raw_response": response.text}

    except Exception as e:
        logger.exception(f"Error during ESG data extraction.{e}")
        return None

# import os
# from google import genai
# from pydantic import BaseModel, Field, ValidationError
# from dotenv import load_dotenv
# from typing import Optional
# from google.genai import types

# load_dotenv()
# client = genai.Client(api_key=os.getenv("gemini_api_key"))

# schema= """{
#   "parameters": [
#     {
#       "parameter": "Total GHG Emissions",
#       "dataType": "Numeric",
#       "synonyms": ["Carbon Footprint"],
#       "uom": "Metric Tons CO₂e",
#       "description": "Total greenhouse gases emitted by the organization."
#     },
#     {
#       "parameter": "Scope 1 Emissions",
#       "dataType": "Numeric",
#       "synonyms": ["Direct Emissions"],
#       "uom": "Metric Tons CO₂e",
#       "description": "Direct GHG emissions from owned or controlled sources."
#     },
#     {
#       "parameter": "Scope 2 Emissions",
#       "dataType": "Numeric",
#       "synonyms": ["Indirect Energy Emissions"],
#       "uom": "Metric Tons CO₂e",
#       "description": "Indirect GHG emissions from the consumption of purchased electricity, steam, heating, and cooling."
#     },
#     {
#       "parameter": "Scope 3 Emissions",
#       "dataType": "Numeric",
#       "synonyms": ["Value Chain Emissions"],
#       "uom": "Metric Tons CO₂e",
#       "description": "Other indirect emissions occurring in the value chain, including both upstream and downstream emissions."
#     },
#     {
#       "parameter": "CO₂ Emissions",
#       "dataType": "Numeric",
#       "synonyms": ["Carbon Emissions"],
#       "uom": "Metric Tons CO₂",
#       "description": "Emissions of carbon dioxide."
#     },
#     {
#       "parameter": "CH₄ Emissions",
#       "dataType": "Numeric",
#       "synonyms": ["Methane Emissions"],
#       "uom": "Metric Tons CH₄",
#       "description": "Emissions of methane."
#     },
#     {
#       "parameter": "N₂O Emissions",
#       "dataType": "Numeric",
#       "synonyms": ["Nitrous Oxide Emissions"],
#       "uom": "Metric Tons N₂O",
#       "description": "Emissions of nitrous oxide."
#     },
#     {
#       "parameter": "HFC Emissions",
#       "dataType": "Numeric",
#       "synonyms": ["Hydrofluorocarbon Emissions"],
#       "uom": "Metric Tons HFCs",
#       "description": "Emissions of hydrofluorocarbons."
#     },
#     {
#       "parameter": "PFC Emissions",
#       "dataType": "Numeric",
#       "synonyms": ["Perfluorocarbon Emissions"],
#       "uom": "Metric Tons PFCs",
#       "description": "Emissions of perfluorocarbons."
#     },
#     {
#       "parameter": "SF₆ Emissions",
#       "dataType": "Numeric",
#       "synonyms": ["Sulfur Hexafluoride Emissions"],
#       "uom": "Metric Tons SF₆",
#       "description": "Emissions of sulfur hexafluoride."
#     },
#     {
#       "parameter": "NF₃ Emissions",
#       "dataType": "Numeric",
#       "synonyms": ["Nitrogen Trifluoride Emissions"],
#       "uom": "Metric Tons NF₃",
#       "description": "Emissions of nitrogen trifluoride."
#     },
#     {
#       "parameter": "Biogenic CO₂ Emissions",
#       "dataType": "Numeric",
#       "synonyms": ["Biogenic Carbon Emissions"],
#       "uom": "Metric Tons CO₂",
#       "description": "CO₂ emissions from biological sources."
#     },
#     {
#       "parameter": "Emissions Intensity per Revenue",
#       "dataType": "Numeric",
#       "synonyms": ["Carbon Intensity"],
#       "uom": "Metric Tons CO₂e / Revenue",
#       "description": "GHG emissions per unit of revenue."
#     },
#     {
#       "parameter": "Emissions Intensity per Employee",
#       "dataType": "Numeric",
#       "synonyms": ["Emissions per Employee"],
#       "uom": "Metric Tons CO₂e / Employee",
#       "description": "GHG emissions per employee."
#     },
#     {
#       "parameter": "Base Year Emissions",
#       "dataType": "Numeric",
#       "synonyms": ["Baseline Emissions"],
#       "uom": "Metric Tons CO₂e",
#       "description": "GHG emissions in the base year for comparison."
#     },
#     {
#       "parameter": "Emissions Reduction Target",
#       "dataType": "Numeric",
#       "synonyms": ["Emission Reduction Goal"],
#       "uom": "Percentage (%)",
#       "description": "Targeted percentage reduction in GHG emissions."
#     },
#     {
#       "parameter": "Emissions Reduction Achieved",
#       "dataType": "Numeric",
#       "synonyms": ["Emission Reduction Accomplished"],
#       "uom": "Percentage (%)",
#       "description": "Actual percentage reduction in GHG emissions achieved."
#     },
#     {
#       "parameter": "Energy Consumption",
#       "dataType": "Numeric",
#       "synonyms": ["Energy Use"],
#       "uom": "MWh or GJ",
#       "description": "Total energy consumed by the organization."
#     },
#     {
#       "parameter": "Renewable Energy Consumption",
#       "dataType": "Numeric",
#       "synonyms": ["Green Energy Use"],
#       "uom": "MWh or GJ",
#       "description": "Amount of energy consumed from renewable sources."
#     },
#     {
#       "parameter": "Non-Renewable Energy Consumption",
#       "dataType": "Numeric",
#       "synonyms": ["Fossil Energy Use"],
#       "uom": "MWh or GJ",
#       "description": "Amount of energy consumed from non-renewable sources."
#     },
#     {
#       "parameter": "Carbon Offsets Purchased",
#       "dataType": "Numeric",
#       "synonyms": ["Carbon Credits"],
#       "uom": "Metric Tons CO₂e",
#       "description": "Amount of carbon offsets purchased."
#     },
#     {
#       "parameter": "Net GHG Emissions",
#       "dataType": "Numeric",
#       "synonyms": ["Net Carbon Emissions"],
#       "uom": "Metric Tons CO₂e",
#       "description": "GHG emissions after accounting for offsets."
#     },
#     {
#       "parameter": "Carbon Sequestration",
#       "dataType": "Numeric",
#       "synonyms": ["Carbon Capture"],
#       "uom": "Metric Tons CO₂e",
#       "description": "Amount of CO₂ sequestered or captured."
#     }
#   ]
# }"""