import wikipedia
from youtube_transcript_api import YouTubeTranscriptApi
import cv2
from pytube import YouTube
import re
import chess
import chess.engine
import pandas as pd
import requests
from bs4 import BeautifulSoup
import whisper
from imdb import IMDb
import subprocess
import sys
from typing import Optional, List, Dict, Any
from smolagents import tool

# === wikipedia_search ===
@tool
def wikipedia_search_call(query: str) -> Dict[str, Any]:
    """
    Search Wikipedia for information about a specific topic.
    
    Args:
        query (str): The search query/topic to look up on Wikipedia
        
    Returns:
        dict: Dictionary containing the page title, content, and sections
    """
    page = wikipedia.page(query)
    sections = {sec: page.section(sec) for sec in page.sections}
    return {"title": page.title, "content": page.content, "sections": sections}

# === youtube_transcript ===
@tool
def youtube_transcript_call(video_id: str) -> List[Dict[str, Any]]:
    """
    Get the transcript/subtitles from a YouTube video.
    
    Args:
        video_id (str): The YouTube video ID (the part after v= in the URL)
        
    Returns:
        list: List of transcript segments with text and timing information
    """
    return YouTubeTranscriptApi.get_transcript(video_id)

# === video_frame_analyzer ===
def download_and_sample(video_id: str, fps: int = 1) -> List[Any]:
    """
    Download a YouTube video and sample frames at specified FPS.
    
    Args:
        video_id (str): The YouTube video ID
        fps (int): Frames per second to sample (default: 1)
        
    Returns:
        list: List of video frames as numpy arrays
    """
    url = f"https://www.youtube.com/watch?v={video_id}"
    yt = YouTube(url)
    stream = yt.streams.filter(progressive=True, file_extension='mp4').first()
    path = stream.download(filename=f"{video_id}.mp4")
    cap = cv2.VideoCapture(path)
    frame_rate = cap.get(cv2.CAP_PROP_FPS) or 1
    step = max(1, int(frame_rate / fps))
    frames = []
    idx = 0
    while True:
        ret, frame = cap.read()
        if not ret:
            break
        if idx % step == 0:
            frames.append(frame)
        idx += 1
    cap.release()
    return frames

def detect_species(frame: Any) -> List[str]:
    """
    Detect bird species in a video frame.
    
    Args:
        frame: Video frame as numpy array
        
    Returns:
        list: List of detected bird species names
    """
    # TODO: integrate actual CV model for bird-species detection
    return []

@tool
def video_frame_analyzer_call(video_id: str) -> int:
    """
    Analyze video frames to count unique bird species.
    
    Args:
        video_id (str): The YouTube video ID to analyze
        
    Returns:
        int: Maximum number of unique bird species detected in any frame
    """
    frames = download_and_sample(video_id)
    counts = [len(set(detect_species(f))) for f in frames]
    return max(counts) if counts else 0

# === string_manipulator ===
@tool
def string_manipulator_call(text: str, operation: str = "reverse", pattern: Optional[str] = None, replacement: Optional[str] = None) -> Any:
    """
    Perform various string manipulation operations.
    
    Args:
        text (str): The input text to manipulate
        operation (str): The operation to perform ("reverse", "split", "regex_replace")
        pattern (str, optional): Regex pattern for replacement operations
        replacement (str, optional): Replacement string for regex operations
        
    Returns:
        Any: Result of the string operation (string or list)
    """
    if operation == "reverse":
        return text[::-1]
    if operation == "split":
        return text.split()
    if operation == "regex_replace" and pattern and replacement is not None:
        return re.sub(pattern, replacement, text)
    raise ValueError(f"Unsupported operation: {operation}")

# === vision_chess_engine ===
@tool
def vision_chess_engine_call(fen: str, depth: int = 20) -> str:
    """
    Analyze a chess position and suggest the best move using Stockfish engine.
    
    Args:
        fen (str): FEN notation representing the chess position
        depth (int): Search depth for the chess engine (default: 20)
        
    Returns:
        str: The best move in Standard Algebraic Notation (SAN)
    """
    engine = chess.engine.SimpleEngine.popen_uci("stockfish")
    board = chess.Board(fen)
    result = engine.play(board, chess.engine.Limit(depth=depth))
    engine.quit()
    return board.san(result.move)

# === table_parser ===
@tool
def table_parser_call(file_path: str, sheet_name: Optional[str] = None) -> pd.DataFrame:
    """
    Parse CSV or Excel files into a pandas DataFrame.
    
    Args:
        file_path (str): Path to the CSV or Excel file
        sheet_name (str, optional): Sheet name for Excel files
        
    Returns:
        pd.DataFrame: Parsed data as a pandas DataFrame
    """
    if file_path.lower().endswith('.csv'):
        return pd.read_csv(file_path)
    return pd.read_excel(file_path, sheet_name=sheet_name)

# === libretext_fetcher ===
@tool
def libretext_fetcher_call(url: str, section_id: str) -> List[str]:
    """
    Fetch content from LibreTexts website by section ID.
    
    Args:
        url (str): The LibreTexts page URL
        section_id (str): The HTML section ID to extract content from
        
    Returns:
        list: List of text items from the specified section
    """
    resp = requests.get(url)
    soup = BeautifulSoup(resp.text, "html.parser")
    sec = soup.find(id=section_id)
    if not sec:
        return []
    items = sec.find_next('ul')
    if items and hasattr(items, 'find_all'):
        items = items.find_all('li')
        return [li.get_text(strip=True) for li in items]
    return []

# === audio_transcriber ===
@tool
def audio_transcriber_call(audio_path: str) -> str:
    """
    Transcribe audio files to text using OpenAI Whisper.
    
    Args:
        audio_path (str): Path to the audio file to transcribe
        
    Returns:
        str: Transcribed text from the audio
    """
    model = whisper.load_model("base")
    result = model.transcribe(audio_path)
    return result.get("text", "")

# === botanical_classifier ===
BOTANICAL_VEGETABLES = {"tomato", "eggplant", "pepper", "squash"}

@tool
def botanical_classifier_call(items: List[str]) -> List[str]:
    """
    Classify items as botanical vegetables.
    
    Args:
        items (list): List of items to classify
        
    Returns:
        list: Items that are classified as botanical vegetables
    """
    return [item for item in items if item.lower() in BOTANICAL_VEGETABLES]

# === imdb_lookup ===
@tool
def imdb_lookup_call(person_name: str) -> Dict[str, Any]:
    """
    Look up information about a person on IMDb.
    
    Args:
        person_name (str): Name of the person to search for
        
    Returns:
        dict: Dictionary containing person's name and filmography
    """
    ia = IMDb()
    results = ia.search_person(person_name)
    if not results:
        return {}
    person = results[0]
    ia.update(person, 'filmography')
    return {"name": person['name'], "filmography": person.get('filmography', {})}

# === python_executor ===
@tool
def python_executor_call(script_path: str) -> str:
    """
    Execute a Python script and return its output.
    
    Args:
        script_path (str): Path to the Python script to execute
        
    Returns:
        str: Standard output from the script execution
    """
    proc = subprocess.run([sys.executable, script_path], capture_output=True, text=True, check=True)
    return proc.stdout.strip()

# === sports_stats_api ===
@tool
def sports_stats_api_call(season: int, team: str, stat: str = "BB") -> Dict[str, Any]:
    """
    Get sports statistics for a team in a specific season.
    
    Args:
        season (int): The sports season year
        team (str): The team name
        stat (str): The statistic type to retrieve (default: "BB")
        
    Returns:
        dict: Sports statistics data
    """
    raise NotImplementedError("sports_stats_api integration not configured")

# === web_scraper ===
@tool
def web_scraper_call(url: str, css_selector: str) -> List[str]:
    """
    Scrape content from a website using CSS selectors.
    
    Args:
        url (str): The URL to scrape
        css_selector (str): CSS selector to find elements
        
    Returns:
        list: List of text content from matching elements
    """
    resp = requests.get(url)
    soup = BeautifulSoup(resp.text, "html.parser")
    return [el.get_text(strip=True) for el in soup.select(css_selector)]

# === excel_reader ===
@tool
def excel_reader_call(file_path: str, sheet_name: Optional[str] = None) -> pd.DataFrame:
    """
    Read Excel files into a pandas DataFrame.
    
    Args:
        file_path (str): Path to the Excel file
        sheet_name (str, optional): Specific sheet name to read
        
    Returns:
        pd.DataFrame: Data from the Excel file as a pandas DataFrame
    """
    return pd.read_excel(file_path, sheet_name=sheet_name)

# === competition_db ===
@tool
def competition_db_call(year_start: int, year_end: int) -> List[Dict[str, Any]]:
    """
    Query competition database for events between specified years.
    
    Args:
        year_start (int): Start year for the query range
        year_end (int): End year for the query range
        
    Returns:
        list: List of competition events in the specified year range
    """
    raise NotImplementedError("competition_db integration not configured")

# === japanese_baseball_api ===
@tool
def japanese_baseball_api_call(team: str, date: str) -> List[Dict[str, Any]]:
    """
    Get Japanese baseball data for a specific team and date.
    
    Args:
        team (str): The baseball team name
        date (str): The date in YYYY-MM-DD format
        
    Returns:
        list: List of baseball game data for the specified team and date
    """
    raise NotImplementedError("japanese_baseball_api integration not configured")



tools_list = [
    wikipedia_search_call,
    youtube_transcript_call,
    video_frame_analyzer_call,
    string_manipulator_call,
    vision_chess_engine_call,
    table_parser_call,
    libretext_fetcher_call,
    audio_transcriber_call,
    botanical_classifier_call,
    imdb_lookup_call,
    python_executor_call,
    sports_stats_api_call,
    web_scraper_call,
    excel_reader_call,
    competition_db_call,
    japanese_baseball_api_call,
]