fix: display all academic degrees

app/services/academic_degrees.py

@@ -2,13 +2,16 @@ import re
 from typing import Any
 
 
-_PATTERN = re.compile(r"\b(?:кандидат|доктор)\s+[\w\s-]{0,80}?\s+наук\b|\bph\.?\s*d\.?\b", re.IGNORECASE)
+_PATTERN = re.compile(r"\b(?:кандидат|доктор)(?:\s+[\w-]+){0,12}\s+наук\b|\bph\.?\s*d\.?(?!\w)", re.IGNORECASE)
 
 
 def academic_degrees(data: dict[str, Any] | None) -> list[str]:
     degrees = []
+    seen = set()
     for section in (data or {}).get("sections") or []:
-        if not isinstance(section, dict) or not re.search(r"уч[её]н.*степен|academic degree", str(section.get("title") or ""), re.IGNORECASE):
+        if not isinstance(section, dict) or not re.search(
+            r"образован|степен|academic degree|education", str(section.get("title") or ""), re.IGNORECASE
+        ):
             continue
         values = [
             *(entry.get("text") for entry in section.get("year_entries") or [] if isinstance(entry, dict)),
@@ -16,8 +19,15 @@ def academic_degrees(data: dict[str, Any] | None) -> list[str]:
             *(section.get("items") or []),
             section.get("raw_text"),
         ]
+        table = section.get("table") or {}
+        for row in table.get("rows") or []:
+            if isinstance(row, dict):
+                values.extend(row.get("cells") or [])
         for value in values:
             text = str(value or "").strip()
-            if text and _PATTERN.search(text) and text not in degrees:
-                degrees.append(text)
+            for match in _PATTERN.finditer(text):
+                degree = match.group(0).strip()
+                if degree.casefold() not in seen:
+                    seen.add(degree.casefold())
+                    degrees.append(degree)
     return degrees