Парсер: поддержка латиницы (международные турниры) + таблица: колонки Рейт и Доп1

bots/client_bot.py

@@ -78,10 +78,12 @@ def format_pairings(pairings_data: dict, tournament_name: str) -> str:
     pairings = pairings_data['pairings']
     rnd = pairings_data['round']
 
-    w_board, w_name, w_pts = 2, 17, 4
+    w_board, w_name, w_rating, w_pts, w_tb1 = 2, 17, 4, 4, 5
-    border = '+'.join('-' * w for w in [w_board, w_name, w_pts])
+    border = '+'.join('-' * w for w in [w_board, w_name, w_rating, w_pts, w_tb1])
 
-    header = f'{_pad_col("#", w_board)}|{_pad_col("Игрок", w_name)}|{_pad_col("О", w_pts)}'
+    header = (f'{_pad_col("#", w_board)}|{_pad_col("Игрок", w_name)}|'
+              f'{_pad_col("Рейт", w_rating)}|{_pad_col("О", w_pts)}|'
+              f'{_pad_col("Доп1", w_tb1)}')
     table_header = f'```\n{header}\n{border}\n'
 
     source = pairings_data.get('source', 'algorithm')
@@ -90,14 +92,20 @@ def format_pairings(pairings_data: dict, tournament_name: str) -> str:
 
     return {
         'title': f'📋 *Тур {rnd}* — пары',
-        'rows': _build_table_rows(pairings, w_board, w_name, w_pts, border),
+        'rows': _build_table_rows(pairings, w_board, w_name, w_rating, w_pts, w_tb1, border),
         'table_header': table_header,
         'footer': footer,
     }
 
 
-def _build_table_rows(pairings: list, w_board: int, w_name: int, w_pts: int,
+def _build_table_rows(pairings: list, w_board: int, w_name: int, w_rating: int,
-                      border: str) -> list:
+                      w_pts: int, w_tb1: int, border: str) -> list:
+    def _rating_str(p):
+        return str(p.rating) if p.rating else ''
+
+    def _tb1_str(p):
+        return f"{p.tb[0]:.1f}" if p.tb else ''
+
     rows = []
     board = 1
     for pi, pairing in enumerate(pairings):
@@ -109,12 +117,16 @@ def _build_table_rows(pairings: list, w_board: int, w_name: int, w_pts: int,
             rows.append(
                 f'{_pad_col(str(board), w_board)}|'
                 f'{_pad_col(p1.name, w_name)}|'
-                f'{_pad_col(f"{p1.points:.1f}", w_pts)}'
+                f'{_pad_col(_rating_str(p1), w_rating)}|'
+                f'{_pad_col(f"{p1.points:.1f}", w_pts)}|'
+                f'{_pad_col(_tb1_str(p1), w_tb1)}'
             )
             rows.append(
                 f'{_pad_col("", w_board)}|'
                 f'{_pad_col("— BYE —", w_name)}|'
-                f'{_pad_col("", w_pts)}'
+                f'{_pad_col("", w_rating)}|'
+                f'{_pad_col("", w_pts)}|'
+                f'{_pad_col("", w_tb1)}'
             )
             board += 1
             if pi + 1 < len(pairings):
@@ -129,12 +141,16 @@ def _build_table_rows(pairings: list, w_board: int, w_name: int, w_pts: int,
         rows.append(
             f'{_pad_col(str(board), w_board)}|'
             f'{_pad_col(white.name, w_name)}|'
-            f'{_pad_col(f"{white.points:.1f}", w_pts)}'
+            f'{_pad_col(_rating_str(white), w_rating)}|'
+            f'{_pad_col(f"{white.points:.1f}", w_pts)}|'
+            f'{_pad_col(_tb1_str(white), w_tb1)}'
         )
         rows.append(
             f'{_pad_col("", w_board)}|'
             f'{_pad_col(black.name, w_name)}|'
-            f'{_pad_col(f"{black.points:.1f}", w_pts)}'
+            f'{_pad_col(_rating_str(black), w_rating)}|'
+            f'{_pad_col(f"{black.points:.1f}", w_pts)}|'
+            f'{_pad_col(_tb1_str(black), w_tb1)}'
         )
         board += 1
 

swiss_calc/parser.py

@@ -82,6 +82,19 @@ 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.
 
@@ -110,11 +123,11 @@ def parse_standings(html: str) -> List[Dict]:
             if sno < 1 or sno > 300:
                 continue
 
-            # Find name: look for Cyrillic text
+            # Find name: look for player name (Latin or Cyrillic)
             name = ''
             name_idx = -1
             for ci, t in enumerate(texts):
-                if _has_cyrillic(t) and len(t) > 5:
+                if _is_player_name(t):
                     name = t
                     name_idx = ci
                     break
@@ -517,7 +530,7 @@ def parse_start_list(html: str) -> dict:
         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 _has_cyrillic(' '.join(texts)):
+            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
@@ -531,7 +544,7 @@ def parse_start_list(html: str) -> dict:
             fed = ''
             rating = 0
             for ci, t in enumerate(texts[1:], 1):
-                if _has_cyrillic(t) and len(t) > 5 and not name:
+                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]