34 lines
1.3 KiB
Python
34 lines
1.3 KiB
Python
import re
|
|
from typing import Any
|
|
|
|
|
|
_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"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)),
|
|
*(section.get("paragraphs") or []),
|
|
*(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()
|
|
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
|