from typing import List, Dict


def split_text_to_batches(text: str, batch_size: int) -> List[str]:
    return [text[i:i + batch_size] for i in range(0, len(text), batch_size)]


def split_list_to_batches(elements_list: List[str], batch_size: int) -> List[List[str]]:
    return [elements_list[i:i + batch_size] for i in range(0, len(elements_list), batch_size)]


def filter_special_simbols(text: str) -> str:
    return text.replace("\n", " ").replace("\xa0", " ")

import time
import asyncio
from typing import List, Dict

from yandex_gpt import YandexGPTConfigManagerForAPIKey, YandexGPT

from dotenv import load_dotenv
load_dotenv("./env/.env.api_key")


async def process_message(message, yandex_gpt, sem, start_time):
    try:
        async with sem:
            if time.time() - start_time > 55:
                return ""
            await asyncio.sleep(1)
            
            result = yandex_gpt.get_sync_completion(messages=message, temperature=0.0, max_tokens=1000)
            return result
        
    except Exception as e:
        print("Error in process_message:", e)
        return ""

      
async def extract_skills_from_pdf(resume_text: str, skills: List[Dict]):
    try:
        resume_batch_size = 300
        skills_batch_size = 30

        resume_text_batches = split_text_to_batches(resume_text, resume_batch_size)
        skills_batches = split_list_to_batches([skill["skill"] for skill in skills], skills_batch_size)
        messages = []

        for resume_text_batch in resume_text_batches:
            for skills_batch in skills_batches:
                messages.append([
                    {'role': 'system', 'text': (
                        'Ты опытный HR-консультант. '
                        f'Набор возможных навыков кандидата: {"; ".join([f"\"{skill}\"" for skill in skills_batch])}. '
                        'Из отрывка резюме кандидата выдели упоминаемые им компетенции и навыки, если они присутствуют в списке возможных навыков кандидата. '
                        "Ищи не только прямые упоминания навыков, но и косвенные признаки их наличия. "
                        "Для ответа используй точные формулировки из набора навыков. "
                        'Ответ дай в формате списка навыков, отделяя каждый навык точкой с запятой (";"): "навык1; навык2; навык3; ...". '
                        'Если данный отрывок не относится к информации о навыках, верни пустую строку ("").'
                    )},
                    {'role': 'user', 'text': (
                        f'Отрывок резюме кандидата: "{filter_special_simbols(resume_text_batch)}".'
                    )}
                ])

        sem = asyncio.Semaphore(1)
        tasks = [process_message(message, yandex_gpt, sem, start_time=start_time) for message in messages]
        results = await asyncio.gather(*tasks)

        res = set()
        for skill in [find_elements_in_text([skill["skill"] for skill in skills], text) for text
                      in results]:
            res = res | set(skill)

        reverse_skills_mapping = {skill["skill"]: skill["id"] for skill in skills}
        return [(reverse_skills_mapping[skill], skill) for skill in res]

    except Exception as e:
        print("Error in extract_skills_from_pdf:", e)
        return []

import time
import asyncio
from typing import List, Dict


def find_elements_in_text(elements_list: List[str], text: str) -> List[str]:
    lower_text = text.lower().replace("\n", " ").replace("*", " ").replace('"', "")
    words = lower_text.split("; ")

    elements_count = {element.lower(): words.count(element.lower()) for element in elements_list}

    elements_mapping = {element.lower(): element for element in elements_list}
    filtered_elements = [elements_mapping[element] for element, count in elements_count.items() if count > 0]

    return filtered_elements

import time
import asyncio
from typing import List, Dict

from yandex_gpt import YandexGPTConfigManagerForAPIKey, YandexGPT

from dotenv import load_dotenv
load_dotenv("./env/.env.api_key")


def split_text_to_batches(text: str, batch_size: int) -> List[str]:
    return [text[i:i + batch_size] for i in range(0, len(text), batch_size)]


def split_list_to_batches(elements_list: List[str], batch_size: int) -> List[List[str]]:
    return [elements_list[i:i + batch_size] for i in range(0, len(elements_list), batch_size)]


def filter_special_simbols(text: str) -> str:
    return text.replace("\n", " ").replace("\xa0", " ")


async def process_message(message, yandex_gpt, sem, start_time):
    try:
        async with sem:
            if time.time() - start_time > 55:
                return ""
            await asyncio.sleep(1)
            
            result = yandex_gpt.get_sync_completion(messages=message, temperature=0.0, max_tokens=1000)
            return result
        
    except Exception as e:
        print("Error in process_message:", e)
        return ""

      
def find_elements_in_text(elements_list: List[str], text: str) -> List[str]:
    lower_text = text.lower().replace("\n", " ").replace("*", " ").replace('"', "")
    words = lower_text.split("; ")

    elements_count = {element.lower(): words.count(element.lower()) for element in elements_list}

    elements_mapping = {element.lower(): element for element in elements_list}
    filtered_elements = [elements_mapping[element] for element, count in elements_count.items() if count > 0]

    return filtered_elements

      
async def extract_skills_from_pdf(resume_text: str, skills: List[Dict]):
    try:
        resume_batch_size = 300
        skills_batch_size = 30

        resume_text_batches = split_text_to_batches(resume_text, resume_batch_size)
        skills_batches = split_list_to_batches([skill["skill"] for skill in skills], skills_batch_size)
        messages = []

        for resume_text_batch in resume_text_batches:
            for skills_batch in skills_batches:
                messages.append([
                    {'role': 'system', 'text': (
                        'Ты опытный HR-консультант. '
                        f'Набор возможных навыков кандидата: {"; ".join([f"\"{skill}\"" for skill in skills_batch])}. '
                        'Из отрывка резюме кандидата выдели упоминаемые им компетенции и навыки, если они присутствуют в списке возможных навыков кандидата. '
                        "Ищи не только прямые упоминания навыков, но и косвенные признаки их наличия. "
                        "Для ответа используй точные формулировки из набора навыков. "
                        'Ответ дай в формате списка навыков, отделяя каждый навык точкой с запятой (";"): "навык1; навык2; навык3; ...". '
                        'Если данный отрывок не относится к информации о навыках, верни пустую строку ("").'
                    )},
                    {'role': 'user', 'text': (
                        f'Отрывок резюме кандидата: "{filter_special_simbols(resume_text_batch)}".'
                    )}
                ])

        sem = asyncio.Semaphore(1)
        tasks = [process_message(message, yandex_gpt, sem, start_time=start_time) for message in messages]
        results = await asyncio.gather(*tasks)

        res = set()
        for skill in [find_elements_in_text([skill["skill"] for skill in skills], text) for text
                      in results]:
            res = res | set(skill)

        reverse_skills_mapping = {skill["skill"]: skill["id"] for skill in skills}
        return [(reverse_skills_mapping[skill], skill) for skill in res]

    except Exception as e:
        print("Error in extract_skills_from_pdf:", e)
        return []