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

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]