fix: match documented previous K1 journal names

This commit is contained in:
codex committed 2026-10-08 12:02:00 +03:00
1 parent 9324639c58
commit 5bda837ee2
8 files changed
+88 -14

No files matched your search

+13 -2
View File
@@ -8,6 +8,7 @@ from datetime import datetime
import hashlib
import json
from pathlib import Path
import re
import pdfplumber
@@ -28,8 +29,18 @@ def extract(source: Path) -> dict:
rows.append(row)
if not rows or [int(row[0]) for row in rows] != list(range(1, len(rows) + 1)):
raise ValueError("Journal numbering is incomplete or duplicated")
journals = [{"name": " ".join(row[1].split()), "categorized_on": row[3], "source_row": int(row[0])}
for row in rows if row[2] == "К1"]
journals = []
for row in rows:
if row[2] != "К1":
continue
name = " ".join(row[1].split())
journal = {"name": name, "categorized_on": row[3], "source_row": int(row[0])}
# Only an explicit administrative rename note supplies an alias.
# Parentheses in journal names (e.g. bilingual titles) stay unchanged.
rename = re.fullmatch(r"(.+?) \((до \d{2}\.\d{2}\.\d{4} г\. наименование в Перечне «(.+)»)\)", name)
if rename:
journal.update(name=rename[1], note=rename[2], aliases=[rename[3]])
journals.append(journal)
if not journals:
raise ValueError("No K1 journals found")
return {"source": source.name, "source_sha256": hashlib.sha256(source.read_bytes()).hexdigest(),