feat: filter employees by academic degree

app/services/admin_data.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import re
 from datetime import date, datetime, time
 from math import ceil
 from typing import Any
@@ -19,6 +20,8 @@ EMPLOYEE_SORTS = {
     "hse_start_year": Employee.current_data["hse_start_year"].as_integer(),
 }
 
+_ACADEMIC_DEGREE_PATTERN = re.compile(r"\b(?:кандидат|доктор)\s+[\w\s-]{0,80}?\s+наук\b|\bph\.?\s*d\.?\b", re.IGNORECASE)
+
 
 def employee_display_payload(employee: Employee) -> dict[str, Any]:
     data = _as_dict(employee.current_data)
@@ -28,6 +31,7 @@ def employee_display_payload(employee: Employee) -> dict[str, Any]:
     positions = _clean_list(data.get("positions"))
     emails = _clean_list(contacts.get("emails"))
     phones = _clean_list(contacts.get("phones"))
+    academic_degrees = _academic_degrees(sections)
     return {
         "id": employee.id,
         "full_name": employee.full_name,
@@ -42,6 +46,7 @@ def employee_display_payload(employee: Employee) -> dict[str, Any]:
         "phones": phones,
         "phone_text": ", ".join(phones),
         "address": contacts.get("address"),
+        "academic_degree_text": "; ".join(academic_degrees),
         "publications_count": _count_section_items(sections, "publications"),
         "courses_count": _count_section_items(sections, "courses_by_year"),
         "news_count": len(stored_news_links) or _count_section_items(sections, "news"),
@@ -81,6 +86,7 @@ def build_employee_query(
     started_from: date | None = None,
     started_to: date | None = None,
     has_email: bool | None = None,
+    has_academic_degree: bool | None = None,
 ) -> Select[tuple[Employee]]:
     stmt = select(Employee)
     filters = []
@@ -97,6 +103,15 @@ def build_employee_query(
         filters.append(Employee.current_data.cast(Text).ilike("%@%"))
     elif has_email is False:
         filters.append(or_(Employee.current_data.is_(None), ~Employee.current_data.cast(Text).ilike("%@%")))
+    if has_academic_degree is not None:
+        data_text = Employee.current_data.cast(Text)
+        degree_condition = or_(
+            and_(_json_text_contains(data_text, "кандидат"), _json_text_contains(data_text, "наук")),
+            and_(_json_text_contains(data_text, "доктор"), _json_text_contains(data_text, "наук")),
+            _json_text_contains(data_text, "phd"),
+            _json_text_contains(data_text, "ph.d."),
+        )
+        filters.append(degree_condition if has_academic_degree else or_(Employee.current_data.is_(None), ~degree_condition))
     if filters:
         stmt = stmt.where(and_(*filters))
     return stmt
@@ -110,6 +125,7 @@ def list_employees_page(
     started_from: date | None = None,
     started_to: date | None = None,
     has_email: bool | None = None,
+    has_academic_degree: bool | None = None,
     sort: str = "full_name",
     direction: str = "asc",
     limit: int = 50,
@@ -123,6 +139,7 @@ def list_employees_page(
         started_from=started_from,
         started_to=started_to,
         has_email=has_email,
+        has_academic_degree=has_academic_degree,
     )
     total = db.scalar(select(func.count()).select_from(base_stmt.subquery())) or 0
     sort_column = EMPLOYEE_SORTS.get(sort, Employee.full_name)
@@ -214,6 +231,36 @@ def format_admin_datetime(value: Any) -> str:
     return value.strftime("%d.%m.%Y %H:%M")
 
 
+def _academic_degrees(sections: list[Any]) -> list[str]:
+    degrees = []
+    for section in sections:
+        section_data = _as_dict(section)
+        title = str(section_data.get("title") or "")
+        if not re.search(r"уч[её]н.*степен|academic degree", title, re.IGNORECASE):
+            continue
+        values = [
+            *(_as_dict(entry).get("text") for entry in _as_list(section_data.get("year_entries"))),
+            *_clean_list(section_data.get("paragraphs")),
+            *_clean_list(section_data.get("items")),
+            section_data.get("raw_text"),
+        ]
+        for value in values:
+            text = str(value or "").strip()
+            if text and _ACADEMIC_DEGREE_PATTERN.search(text) and text not in degrees:
+                degrees.append(text)
+    return degrees
+
+
+def _json_text_contains(data_text: Any, value: str) -> Any:
+    escaped = value.encode("unicode_escape").decode("ascii")
+    escaped_capitalized = value.capitalize().encode("unicode_escape").decode("ascii")
+    return or_(
+        data_text.ilike(f"%{value}%"),
+        data_text.ilike(f"%{escaped}%"),
+        data_text.ilike(f"%{escaped_capitalized}%"),
+    )
+
+
 def _employee_status_display(status: str | None) -> str:
     labels = {"active": "Работает", "dismissed": "Уволен"}
     return labels.get(status or "", status or "Не указано")