ChessCalcNextTour/swiss_calc/parser.py

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

Handles all page states:
- Before pairings: standings with completed rounds
- After pairings published: standings + next-round column
- After games played: updated standings
- art=2 pairings pages in compact format
"""

import re
import requests
from bs4 import BeautifulSoup
from typing import Optional, List, Dict, Tuple

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


def fetch_url(url: str) -> str:
    resp = requests.get(url, headers=HEADERS, timeout=20)
    resp.raise_for_status()
    resp.encoding = 'utf-8'
    return resp.text


# ── Result parsing ────────────────────────────────────────────

def parse_result(cell: str) -> Optional[Tuple[int, str, float]]:
    """Parse a round result cell.

    Returns (opponent_sno, color, score) or None.
    sno=0 means bye/forfeit; color='-' means no color.
    """
    cell = cell.strip()
    if not cell:
        return None

    # Standard: '27b1', '15w½'
    m = re.match(r'^(\d+)([bw])([10½=]+|0[,.]5)$', cell)
    if m:
        sno = int(m.group(1))
        color = 'w' if m.group(2) == 'w' else 'b'
        pts_str = m.group(3).replace(',', '.').replace('=', '0.5').replace('½', '0.5')
        pts = float(pts_str)
        return sno, color, pts

    # Forfeit with opponent: '27b+'
    m = re.match(r'^(\d+)([bw])([+\-])$', cell)
    if m:
        sno = int(m.group(1))
        color = 'w' if m.group(2) == 'w' else 'b'
        pts = 1.0 if m.group(3) == '+' else 0.0
        return sno, color, pts

    # Bye/forfeit: '-0', '-1', '-'
    m = re.match(r'^-([01½]?)$', cell)
    if m:
        pts_str = m.group(1).replace('½', '0.5')
        pts = float(pts_str) if pts_str else 0.0
        return 0, '-', pts

    return None


def parse_next_opponent(cell: str) -> Optional[Tuple[int, str]]:
    """Parse '4w' or '12b' — next opponent and color."""
    m = re.match(r'^(\d+)([bw])$', cell.strip())
    if m:
        return int(m.group(1)), m.group(2)
    return None


# ── Standings parsing ─────────────────────────────────────────

def _normalize_name(name: str) -> str:
    """Normalize name for matching: remove commas, collapse whitespace."""
    return re.sub(r'\s+', ' ', name.replace(',', '')).strip()

def _has_cyrillic(s: str) -> bool:
    return bool(re.search(r'[а-яА-ЯёЁ]', s))


def _is_player_name(t: str) -> bool:
    """Check if text looks like a player name (Latin or Cyrillic)."""
    if len(t) <= 5:
        return False
    if re.match(r'^\d+$', t):
        return False
    if re.match(r'^[A-Z]{3}$', t):
        return False
    if re.match(r'^\d+[bw][½\d]?$', t):
        return False
    return bool(re.search(r'[A-Za-zА-Яа-я]', t))


def parse_standings(html: str) -> List[Dict]:
    """Parse standings from art=4 or art=5 page.

    Detects player rows by: first column is a rank number,
    one column has a Cyrillic name.
    """
    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]

            if len(texts) < 6:
                continue
            if not texts[0].isdigit():
                continue

            sno = int(texts[0])
            if sno < 1 or sno > 300:
                continue

            # Find name: look for player name (Latin or Cyrillic)
            name = ''
            name_idx = -1
            for ci, t in enumerate(texts):
                if _is_player_name(t):
                    name = t
                    name_idx = ci
                    break
            if not name:
                continue

            # Federation is usually the next column, if it looks like a code
            fed = ''
            if name_idx + 1 < len(texts):
                t = texts[name_idx + 1]
                if re.match(r'^[A-Z]{3}$', t):
                    fed = t

            # Process columns after name+federation for results and points
            data_cols = texts[name_idx + (2 if fed else 1):]

            results = []
            next_opponent = None
            next_color = None
            points = 0.0
            tb_values = []
            found_points = False

            for col in data_cols:
                if not col:
                    continue

                # Try result
                res = parse_result(col)
                if res:
                    opp, color, pts = res
                    results.append({'opponent': opp, 'color': color, 'score': pts})
                    continue

                # Try next opponent
                no = parse_next_opponent(col)
                if no:
                    next_opponent, next_color = no
                    continue

                # Points: first numeric with optional decimal after results
                if re.match(r'^\d+([,.]\d)?$', col) and not found_points:
                    points = float(col.replace(',', '.'))
                    found_points = True
                    continue

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

            players.append({
                'rank': len(players) + 1,  # position in list = current rank
                'name': name,
                'fed': fed,
                'points': points,
                'starting_sno': sno,  # from first column
                'results': results,
                'next_opponent': next_opponent,
                'next_color': next_color,
                'tb': tb_values,
            })

        if players:
            break

    return players


# ── Round pairings (art=2 compact format) ─────────────────────

def parse_game_row(texts: List[str], board: int) -> Optional[Dict]:
    """Parse one game row from art=2 page.

    Format A (12 columns — newer tournaments):
    [0]=db_id, [1]=w_sno, [2]=_, [3]=w_name, [4]=w_rating, [5]=w_pts,
    [6]=result, [7]=b_pts, [8]=_, [9]=b_name, [10]=b_rating, [11]=b_sno

    Format B (10 columns — older tournaments, no SNo in table):
    [0]=seq_id, [1]=_, [2]=w_name, [3]=w_rating, [4]=w_pts,
    [5]=result, [6]=b_pts, [7]=_, [8]=b_name, [9]=b_rating

    result_str is empty for unplayed rounds.
    """
    if len(texts) < 10:
        return None
    if not texts[0].isdigit():
        return None

    fmt_b = (len(texts) <= 11)  # Older format without SNo columns or empty last cols

    if fmt_b:
        result_str = texts[5]
        w_sno = 0   # Unknown — matched by name in fetch_tournament
        b_sno = 0
        w_name_idx, w_rating_idx, w_pts_idx = 2, 3, 4
        b_pts_idx, b_name_idx, b_rating_idx = 6, 8, 9
    else:
        result_str = texts[6]
        w_sno = int(texts[1]) if texts[1].isdigit() else 0
        try:
            b_sno = int(texts[11]) if texts[11].strip().isdigit() else 0
        except (IndexError, ValueError):
            b_sno = 0
        w_name_idx, w_rating_idx, w_pts_idx = 3, 4, 5
        b_pts_idx, b_name_idx, b_rating_idx = 7, 9, 10

    # For completed rounds, result must have digits/½ or be a forfeit (+/-)
    # For unplayed rounds, result is empty — that's valid
    if result_str:
        if not re.search(r'[\d½]', result_str) and '+ -' not in result_str and '- +' not in result_str:
            return None
        if not re.search(r'[-:]', result_str) and '+ -' not in result_str and '- +' not in result_str:
            return None

    try:
        w_name = texts[w_name_idx]
        w_rating = int(texts[w_rating_idx]) if texts[w_rating_idx].isdigit() else 0
        w_pts = float(texts[w_pts_idx].replace(',', '.').replace('½', '.5'))
        b_pts = float(texts[b_pts_idx].replace(',', '.').replace('½', '.5'))
        b_name = texts[b_name_idx]
        b_rating = int(texts[b_rating_idx]) if texts[b_rating_idx].isdigit() else 0

        # Parse result
        if not result_str:
            w_score, b_score = None, None  # unplayed
        elif '1 - 0' in result_str or '1:0' in result_str or '+ -' in result_str:
            w_score, b_score = 1.0, 0.0
        elif '0 - 1' in result_str or '0:1' in result_str or '- +' in result_str:
            w_score, b_score = 0.0, 1.0
        else:
            w_score, b_score = 0.5, 0.5

        return {
            'board': board,
            'white_sno': w_sno, 'white_name': w_name, 'white_rating': w_rating,
            'white_pts': w_pts, 'white_score': w_score,
            'black_sno': b_sno, 'black_name': b_name, 'black_rating': b_rating,
            'black_pts': b_pts, 'black_score': b_score,
            'result': result_str.strip() if result_str else '',
        }
    except (ValueError, IndexError):
        return None


def parse_round_pairings(html: str, round_num: int) -> List[Dict]:
    """Parse pairings/results from art=2&rd=N page.

    Board number is derived from row position in the table.
    """
    soup = BeautifulSoup(html, 'html.parser')
    games = []

    tables = soup.find_all('table')
    for table in tables:
        rows = table.find_all('tr')
        board = 0
        for row in rows:
            cells = row.find_all('td')
            texts = [c.get_text(strip=True) for c in cells]
            if len(texts) >= 10 and texts[0].isdigit():
                board += 1
                game = parse_game_row(texts, board)
                if game:
                    game['round'] = round_num
                    games.append(game)

        if games:
            break

    return games


# ── Tournament meta ───────────────────────────────────────────

def extract_tournament_meta(html: str) -> dict:
    """Extract name, num_rounds, current_round."""
    soup = BeautifulSoup(html, 'html.parser')
    info = {'name': '', 'num_rounds': 9, 'current_round': 1}

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

    text = soup.get_text()

    # Number of rounds
    m = re.search(r'Number of rounds\s*(\d+)', text)
    if m:
        info['num_rounds'] = int(m.group(1))

    # Current round: "Положение после тура N"
    m = re.search(r'Положение после тура\s*(\d+)', text)
    if m:
        info['current_round'] = int(m.group(1))
    else:
        # Try "Round X/Y" navigation
        m = re.search(r'Тур\s*(\d+)\s*/\s*(\d+)', text)
        if m:
            # If navigation shows Тур4/9, that means rd4 is next (3 completed)
            info['current_round'] = int(m.group(1)) - 1

    return info


# ── Full tournament fetch ─────────────────────────────────────

def fetch_tournament(url: str) -> dict:
    """Fetch full tournament data from any chess-results.com URL.

    Detects current state automatically (any number of completed rounds).
    """
    # Normalize URL to base
    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)

    # Fetch standings
    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}')

    meta = extract_tournament_meta(html)
    standings = parse_standings(html)

    if not standings:
        raise RuntimeError('Не удалось распарсить таблицу положения')

    # Completed rounds: use page metadata ("Положение после тура N")
    current_round = meta['current_round']
    # Sanity check against actual results
    max_results = max(len(s['results']) for s in standings)
    if current_round < 2 and max_results > current_round:
        current_round = max_results
    elif max_results < current_round:
        current_round = max_results

    # Starting list for ratings
    try:
        start_html = fetch_url(base_url + '&art=5&turdet=YES')
        start_players = parse_start_list(start_html)
    except Exception:
        start_players = {}

    # Match real SNo and rating from start list
    # Build name→sno lookup (normalized)
    name_to_sno = {}
    for sno, info in start_players.items():
        name_to_sno[_normalize_name(info['name'])] = sno

    for s in standings:
        sname = _normalize_name(s['name'])
        # Try exact match first
        real_sno = name_to_sno.get(sname)
        if real_sno is None:
            # Fuzzy: find best partial match (first+last name overlap)
            sname_parts = set(sname.split())
            best_sno = None
            best_overlap = 0
            for sl_name, sl_sno in name_to_sno.items():
                sl_parts = set(sl_name.split())
                overlap = len(sname_parts & sl_parts)
                if overlap > best_overlap:
                    best_overlap = overlap
                    best_sno = sl_sno
            real_sno = best_sno

        s['starting_sno'] = real_sno if real_sno else s.get('starting_sno', s['rank'])

        # Get real rating from start list
        if real_sno and real_sno in start_players:
            s['rating'] = start_players[real_sno].get('rating', s.get('rating', 0))
        elif 'rating' not in s:
            s['rating'] = 0

    # Keep original results from standings as backup (for byes/forfeits)
    for s in standings:
        s['_orig_results'] = list(s.get('results', []))
        s['results'] = []  # Clear — will rebuild from pairings

    # Rebuild results from art=2 pairings (correct SNo, unlike standings cells)
    sno_to_standing = {s['starting_sno']: s for s in standings if s.get('starting_sno')}
    name_to_standing = {_normalize_name(s['name']): s for s in standings}

    for rd in range(1, current_round + 1):
        try:
            rd_html = fetch_url(f'{base_url}&art=2&rd={rd}&turdet=YES')
            games = parse_round_pairings(rd_html, rd)
        except Exception:
            continue

        for g in games:
            ws, bs = g['white_sno'], g['black_sno']
            ws_result = g.get('white_score')
            bs_result = g.get('black_score')

            if ws_result is not None:
                # Completed game
                ws_val = float(ws_result)
                bs_val = float(bs_result)
            else:
                # Unplayed — skip
                continue

            # Resolve players by SNo or name (normalized)
            wp = sno_to_standing.get(ws) or name_to_standing.get(_normalize_name(g.get('white_name', '')))
            bp = sno_to_standing.get(bs) or name_to_standing.get(_normalize_name(g.get('black_name', '')))

            if wp:
                opp_sno = bs if bs != 0 else (bp.get('starting_sno') if bp else 0)
                existing = [r for r in wp.get('results', []) if r.get('round') != rd]
                existing.append({'opponent': opp_sno, 'color': 'w', 'score': ws_val, 'round': rd})
                wp['results'] = existing

            if bp:
                opp_sno = ws if ws != 0 else (wp.get('starting_sno') if wp else 0)
                existing = [r for r in bp.get('results', []) if r.get('round') != rd]
                existing.append({'opponent': opp_sno, 'color': 'b', 'score': bs_val, 'round': rd})
                bp['results'] = existing

        # For byes/forfeits not captured by pairings, use original standings results
        for s in standings:
            sno = s.get('starting_sno')
            if sno and len(s.get('results', [])) < rd:
                orig_results = s.get('_orig_results', [])
                if len(orig_results) >= rd:
                    res = orig_results[rd - 1]
                    res['round'] = rd
                    s['results'] = list(s.get('results', []))
                    s['results'].append(res)

    # Final pass: fill any remaining gaps from _orig_results (forfeit losers, byes)
    for s in standings:
        existing_rounds = {r.get('round', 0) for r in s.get('results', [])}
        orig = s.get('_orig_results', [])
        for ri, res in enumerate(orig):
            rd_num = ri + 1
            if rd_num <= current_round and rd_num not in existing_rounds:
                res_copy = dict(res)
                res_copy['round'] = rd_num
                if res_copy.get('opponent') and res_copy['opponent'] > 0:
                    opp_sno = res_copy['opponent']
                    if opp_sno not in sno_to_standing:
                        for s2 in standings:
                            if s2['rank'] == opp_sno and s2.get('starting_sno'):
                                res_copy['opponent'] = s2['starting_sno']
                                break
                s['results'].append(res_copy)

    for s in standings:
        s['points'] = sum(r.get('score', 0) for r in s.get('results', []))

    return {
        'name': meta['name'],
        'num_rounds': meta['num_rounds'],
        'current_round': current_round,
        'players': start_players,
        'standings': standings,
    }


def parse_start_list(html: str) -> dict:
    """Parse starting list from art=0 or art=5 page.

    Two formats supported:
    1. art=0 text: SNo Name FIDE_ID National_ID FED Rating Region
    2. art=5 table: SNo, Name, FED, Rating columns
    """
    soup = BeautifulSoup(html, 'html.parser')

    # Try art=0 text format first
    text = soup.get_text()
    players = {}

    # Pattern: SNo (1-3 digits), Full Name (3 words), two IDs, FED, Rating
    pattern = re.compile(
        r'(?:^|\s)(\d{1,3})\s+'
        r'([А-ЯЁ][а-яё]+\s+[А-ЯЁ][а-яё]+\s+[А-ЯЁ][а-яё]+)'
        r'\s+\d+\s+\d+\s+'
        r'([A-Z]{3})\s+'
        r'(\d{3,4})'
    )
    for m in pattern.finditer(text):
        sno = int(m.group(1))
        name = m.group(2).strip()
        fed = m.group(3)
        rating = int(m.group(4))
        players[sno] = {'name': name, 'rating': rating, 'fed': fed}

    if len(players) >= 10:
        return players

    # Fallback: try art=5 table format
    tables = soup.find_all('table')
    for table in tables:
        rows = table.find_all('tr')
        data_rows = 0
        for row in rows:
            cells = row.find_all('td')
            texts = [c.get_text(strip=True) for c in cells]
            if len(texts) >= 4 and texts[0].isdigit() and any(_is_player_name(t) for t in texts):
                data_rows += 1
        if data_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) < 4 or not texts[0].isdigit():
                continue
            sno = int(texts[0])
            name = ''
            fed = ''
            rating = 0
            for ci, t in enumerate(texts[1:], 1):
                if _is_player_name(t) and not name:
                    name = t
                    if ci + 1 < len(texts) and re.match(r'^[A-Z]{3}$', texts[ci + 1]):
                        fed = texts[ci + 1]
                    continue
                if t.isdigit() and len(t) >= 3 and not rating:
                    rating = int(t)
            if name:
                players[sno] = {'name': name, 'rating': rating, 'fed': fed}
        if players:
            break

    return players