ChessCalcNextTour/swiss_calc/parser.py

"""
Parser for chess-results.com tournament pages.

Fetches and parses:
- Starting list (players with ratings)
- Round pairings/results
- Standings with tiebreakers
"""

import re
import requests
from bs4 import BeautifulSoup
from typing import Optional

HEADERS = {
    'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
}

RESULT_MAP = {
    '1': 1.0,
    '0': 0.0,
    '½': 0.5,
    '0,5': 0.5,
    '+': 1.0,   # win by forfeit
    '-': 0.0,   # loss by forfeit
}


def fetch_url(url: str) -> str:
    """Fetch HTML page from chess-results.com."""
    resp = requests.get(url, headers=HEADERS, timeout=20)
    resp.raise_for_status()
    resp.encoding = 'utf-8'
    return resp.text


def parse_result(cell: str):
    """Parse a round result cell like '27b1', '15w½', '42b0'.

    Returns (opponent_sno: int, color: str, points: float) or None.
    """
    cell = cell.strip()
    if not cell:
        return None
    m = re.match(r'^(\d+)([bw])([10½]+|0,5)$', cell)
    if m:
        sno = int(m.group(1))
        color = 'b' if m.group(2) == 'b' else 'w'
        pts_str = m.group(3).replace(',', '.')
        pts = float(pts_str) if '.' in pts_str else (0.5 if pts_str == '½' else float(pts_str))
        return sno, color, pts
    # Handle forfeit results like '27b+' 
    m = re.match(r'^(\d+)([bw])([+\-])$', cell)
    if m:
        sno = int(m.group(1))
        color = 'b' if m.group(2) == 'b' else 'w'
        pts = 1.0 if m.group(3) == '+' else 0.0
        return sno, color, pts
    return None


def parse_start_list(html: str) -> dict:
    """Parse art=5 page: returns dict of {sno: {'name': str, 'rating': int, 'fed': str}}"""
    soup = BeautifulSoup(html, 'html.parser')
    players = {}

    # Find the main table with player data (largest table with starting numbers)
    tables = soup.find_all('table')
    for table in tables:
        rows = table.find_all('tr')
        if len(rows) < 5:
            continue
        for row in rows:
            cells = row.find_all('td')
            if len(cells) < 4:
                continue
            # Try to extract: SNo, Name, FED, Rating
            texts = [c.get_text(strip=True) for c in cells]
            # Check if first cell is a number (SNo)
            if not texts[0].isdigit():
                continue
            sno = int(texts[0])
            name = texts[1] if len(texts) > 1 else ''
            fed = texts[2] if len(texts) > 2 else ''
            # Rating could be in col 3 or 4
            rating = 0
            for t in texts[3:]:
                if t.isdigit() and len(t) >= 3:
                    rating = int(t)
                    break
            if name:
                players[sno] = {
                    'name': name,
                    'rating': rating,
                    'fed': fed,
                }
        if players:
            break

    return players


def parse_standings(html: str, current_round: int) -> list:
    """Parse art=4 page (standings).

    Returns list of dicts:
    {
        'sno': int,
        'rank': int,
        'name': str,
        'fed': str,
        'points': float,
        'results': [(opponent_sno, color, score), ...],  # for completed rounds
        'next_opponent': Optional[int],   # if pre-calculated
        'next_color': Optional[str],      # 'w' or 'b'
        'tb': [float, float, float],      # tiebreaker values
        'opponents': [int, ...],           # all opponents so far
    }
    """
    soup = BeautifulSoup(html, 'html.parser')
    players = []

    tables = soup.find_all('table')
    for table in tables:
        rows = table.find_all('tr')
        if len(rows) < 10:
            continue

        for row in rows:
            cells = row.find_all('td')
            texts = [c.get_text(strip=True) for c in cells]

            # Filter: first cell should be a rank number
            if not texts or not texts[0].isdigit():
                continue
            # Skip if not enough cols for a player row (at least rank + name + results)
            if len(texts) < 8:
                continue

            rank = int(texts[0])
            # Usually: rank, (empty), name, fed, rd1, rd2, ..., pts, tb1, tb2, tb3
            # The empty column sometimes joins with rank
            col_offset = 0
            if rank == 0 or rank > 200:
                continue

            # Find name column
            # Typical: rank | (empty) | name | fed | results...
            name = ''
            fed = ''
            name_idx = 1
            for ci in range(1, min(5, len(texts))):
                t = texts[ci]
                if t and not t.isdigit() and len(t) > 2 and not t.startswith('http'):
                    if ci > 1 or not texts[0].isdigit():
                        # Check if this name contains 2+ words in Russian or English
                        if re.search(r'[а-яА-Яa-zA-Z]', t):
                            name = t
                            name_idx = ci
                            # Next column after name is usually federation
                            if ci + 1 < len(texts):
                                fed = texts[ci + 1]
                            break
                    if ci == name_idx:
                        name = t
                        if ci + 1 < len(texts):
                            fed = texts[ci + 1]
                        break

            if not name:
                continue

            # Results start after federation column
            # fed is at name_idx+1, so results start at name_idx+2
            result_start = name_idx + 2 if name_idx + 2 < len(texts) else name_idx + 1
            results = []
            opponents = []
            next_opponent = None
            next_color = None
            pts_found = False
            tb_values = []

            # Process each column from result_start
            result_cols = texts[result_start:]
            pts_col_idx = -1

            # Find result cells (format: XXX or XXb1, XXw½ etc)
            for ci, col in enumerate(result_cols):
                if not col:
                    continue
                # Check for next opponent format (e.g., "4w", "12b")
                m = re.match(r'^(\d+)([bw])$', col)
                if m and not pts_found:
                    # This could be a result (if it has 1/0/½) or next opponent
                    # Check if there are more cells and the next one is numeric (points)
                    pass

                # Try to parse as round result
                parsed = parse_result(col)
                if parsed:
                    opp, color, pts = parsed
                    results.append({'opponent': opp, 'color': color, 'score': pts})
                    opponents.append(opp)
                    continue

                # Check for next opponent (just "12w" format without 1/0/½)
                m2 = re.match(r'^(\d+)([bw])$', col)
                if m2:
                    next_opponent = int(m2.group(1))
                    next_color = m2.group(2)
                    continue

                # Check if it's the points column
                if re.match(r'^\d+(?:[.,]\d)?$', col) and not pts_found:
                    pts_str = col.replace(',', '.')
                    points = float(pts_str)
                    pts_found = True
                    pts_col_idx = ci
                    continue

                # Tiebreaker columns (after points)
                if pts_found and re.match(r'^\d+(?:[.,]\d)?$', col):
                    tb_values.append(float(col.replace(',', '.')))

            # If we didn't find special next-opponent format, check results for unplayed
            # Also check for pre-calculated pairing at position current_round (0-indexed in results)
            # If there are results for rounds > current_round, that's the next pairing

            player = {
                'sno': rank,  # In standings view, rank = current position (not starting number!)
                'rank': rank,
                'name': name,
                'fed': fed,
                'points': float(texts[-len(tb_values)-1].replace(',', '.')) if texts else 0,
                'results': results,
                'next_opponent': next_opponent,
                'next_color': next_color,
                'tb': tb_values,
                'opponents': opponents,
            }
            players.append(player)

        if players:
            break

    return players


def parse_round_pairings(html: str, round_num: int) -> list:
    """Parse art=2 page for a specific round.

    Returns list of dicts:
    {
        'board': int,
        'white_sno': int,
        'white_name': str,
        'white_rating': int,
        'white_pts': float,
        'black_sno': int,
        'black_name': str,
        'black_rating': int,
        'black_pts': float,
        'result': Optional[str],  # '1-0', '½-½', '0-1'
    }
    """
    soup = BeautifulSoup(html, 'html.parser')
    pairings = []

    tables = soup.find_all('table')
    for table in tables:
        rows = table.find_all('tr')
        if len(rows) < 5:
            continue

        for row in rows:
            cells = row.find_all('td')
            texts = [c.get_text(strip=True) for c in cells]
            if len(texts) < 10:
                continue

            # Format: Board | WhiteSNo | | WhiteName | WhiteRating | WhitePts | Result | BlackPts | | BlackName | BlackRating | BlackSNo
            # Or: Board | SNo | | Name | Rating | Pts | Result | Pts | | Name | Rating | SNo
            # First cell should be a board number
            if not texts[0].isdigit():
                continue

            board = int(texts[0])
            # Try to find the result indicator
            result_idx = -1
            for ci, t in enumerate(texts):
                if t in ('1-0', '½-½', '0-1', '0 : 0', '1 : 0', '½ : ½', '0 : 1', '+ -', '- +'):
                    result_idx = ci
                    break
                if ':' in t:
                    result_idx = ci

            if result_idx == -1:
                continue

            # White player info is before result, Black is after
            white_texts = texts[1:result_idx]
            black_texts = texts[result_idx+1:]

            # White: SNo is usually last in white section, name somewhere in the middle
            white_sno = 0
            white_name = ''
            white_rating = 0
            white_pts = 0.0
            for t in white_texts:
                if t.isdigit() and len(t) <= 3:
                    white_sno = int(t)
                if re.search(r'[а-яА-Яa-zA-Z]{3,}', t) and len(t) > 3:
                    white_name = t
                if t.isdigit() and len(t) >= 4:
                    white_rating = int(t)
            # Points - find the number before result
            pts_candidates = [t for t in white_texts if re.match(r'^\d+(?:[.,]\d)?$', t) and len(t) <= 4]
            if pts_candidates:
                white_pts = float(pts_candidates[-1].replace(',', '.'))

            for t in black_texts:
                if t.isdigit() and len(t) <= 3:
                    black_sno = int(t)
                if re.search(r'[а-яА-Яa-zA-Z]{3,}', t) and len(t) > 3:
                    black_name = t
                if t.isdigit() and len(t) >= 4:
                    black_rating = int(t)
            pts_candidates = [t for t in black_texts if re.match(r'^\d+(?:[.,]\d)?$', t) and len(t) <= 4]
            if pts_candidates:
                black_pts = float(pts_candidates[0].replace(',', '.'))

            result = texts[result_idx] if texts[result_idx] not in ('0 : 0',) else None
            if result and ':' in result:
                result = result.replace(' : ', '-')

            pairings.append({
                'board': board,
                'white_sno': white_sno,
                'white_name': white_name,
                'white_rating': white_rating,
                'white_pts': white_pts,
                'black_sno': black_sno,
                'black_name': black_name,
                'black_rating': black_rating,
                'black_pts': black_pts,
                'result': result,
            })

        if pairings:
            break

    return pairings


def extract_tournament_meta(html: str) -> dict:
    """Extract tournament metadata (name, number of rounds) from any page HTML."""
    soup = BeautifulSoup(html, 'html.parser')
    info = {'name': '', 'num_rounds': 0, 'current_round': 1}

    h2 = soup.find('h2')
    if h2:
        info['name'] = h2.get_text(strip=True)

    # Find "Number of rounds" row in tables - but be specific
    # Look in the info table cells where first cell says "Number of rounds"
    for table in soup.find_all('table'):
        rows = table.find_all('tr')
        found_rounds = False
        for row in rows:
            cells = row.find_all('td')
            texts = [c.get_text(strip=True) for c in cells]
            for ci, t in enumerate(texts):
                if t == 'Number of rounds' and ci + 1 < len(texts):
                    m = re.search(r'^(\d+)$', texts[ci + 1])
                    if m:
                        info['num_rounds'] = int(m.group(1))
                        found_rounds = True
                        break
            if found_rounds:
                break
        if found_rounds:
            break

    # Detect current round from navigation: "Тур4/9" or "Round X/Y"
    nav_text = soup.get_text()
    m = re.search(r'Тур(\d+)/\d+|Round\s*(\d+)\s*/\s*\d+', nav_text)
    if m:
        info['current_round'] = int(m.group(1) or m.group(2))

    return info


def detect_current_round(url: str) -> int:
    """Detect current round by checking which rd parameter has results."""
    for rd in range(1, 12):
        rd_url = url.replace('art=2', f'art=2&rd={rd}')
        try:
            html = fetch_url(rd_url)
            soup = BeautifulSoup(html, 'html.parser')
            # Find tables with pairings
            tables = soup.find_all('table')
            has_pairings = False
            for table in tables:
                rows = table.find_all('tr')
                if len(rows) > 3:
                    texts = rows[0].find_all('td')
                    txt = ' '.join(t.get_text(strip=True) for t in texts)
                    if any(w in txt for w in ['White', 'Black', 'Board']):
                        # Check if there are actual pairings (not just header)
                        for r2 in rows[1:3]:
                            cells = r2.find_all('td')
                            if len(cells) > 5:
                                has_pairings = True
                                break
                if has_pairings:
                    break
            if not has_pairings:
                return rd - 1
        except Exception:
            return rd - 1
    return 1


def fetch_tournament(url: str) -> dict:
    """Full tournament data fetch.

    Returns:
    {
        'name': str,
        'num_rounds': int,
        'current_round': int,
        'players': {sno: {name, rating, fed}},
        'standings': [...],       # players sorted by rank
        'pairings': {rd: [...]},  # completed round pairings
    }
    """
    # Normalize URL: strip art/rd params, keep only base URL with tnr
    base_url = re.sub(r'[&?]art=\d+', '', url)
    base_url = re.sub(r'[&?]rd=\d+', '', base_url)
    base_url = re.sub(r'[&?]turdet=\w+', '', base_url)
    base_url = re.sub(r'[&?]SNode=\w+', '', base_url)

    # Standings page (art=4) - this page has ALL the info we need
    standings_url = base_url + '&art=4&turdet=YES'

    try:
        html = fetch_url(standings_url)
    except Exception as e:
        raise RuntimeError(f'Не удалось загрузить турнир: {e}')

    # Extract metadata from same HTML
    meta = extract_tournament_meta(html)
    num_rounds = meta['num_rounds']

    # Parse standings
    standings = parse_standings(html, 0)
    if standings:
        current_round = len(standings[0].get('results', []))
    else:
        current_round = 1

    # Override current_round from navigation if available
    # Navigation "Тур4/9" means round 4 is current/playing → 3 completed
    if meta['current_round'] > 1:
        current_round = meta['current_round']  # this is the current playing round
        # But we want the last COMPLETED round for calculations
        # If results show N entries, N rounds are completed

    # Reconcile: completed rounds = len(results for first player)
    if standings and len(standings[0].get('results', [])) < current_round:
        current_round = len(standings[0].get('results', []))

    # Fetch starting list (art=5) for ratings
    start_url = base_url + '&art=5&turdet=YES'
    try:
        html_start = fetch_url(start_url)
        players = parse_start_list(html_start)
    except Exception:
        players = {}

    # Match ratings from start list into standings
    for s in standings:
        # Find by name match
        for sno, p in players.items():
            if p['name'].lower() == s['name'].lower():
                s['rating'] = p['rating']
                s['starting_sno'] = sno
                break
        else:
            s['rating'] = 0
            s['starting_sno'] = s['rank']

    return {
        'name': meta['name'],
        'num_rounds': num_rounds if num_rounds else 9,  # fallback
        'current_round': current_round,
        'players': players,
        'standings': standings,
    }