Files
miem_workers/app/services/publication_vak.py
T

72 lines
3.7 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
"""Match a publication's journal to the supplied K1/K2 category snapshots."""
from collections import defaultdict
from datetime import date
from functools import lru_cache
import hashlib
import json
from pathlib import Path
import re
from app.services.council_catalog import issn
from app.services.council_source import _name
DATA = Path(__file__).resolve().parents[1] / "data"
def journal_key(value):
return " ".join(re.findall(r"\w+", _name(value)))
@lru_cache(maxsize=1)
def category_index():
files = {category: DATA / filename for category, filename in
(("К1", "k1_journals.json"), ("К2", "k2_journals.json"))}
documents = {category: json.loads(path.read_text(encoding="utf8")) for category, path in files.items()}
if documents["К1"]["source_sha256"] != documents["К2"]["source_sha256"]:
raise ValueError("VAK category source mismatch")
identities = json.loads((DATA / "k1_specialties.json").read_text(encoding="utf8"))
if identities["k1_source_sha256"] != hashlib.sha256(files["К1"].read_bytes().replace(b"\r\n", b"\n")).hexdigest():
raise ValueError("VAK journal identity source mismatch")
known = {item["name"]: sorted({issn(entry["issn"]) for entry in item["vak_entries"]})
for item in identities["journals"] if item.get("status") == "matched"}
by_name, by_issn = defaultdict(list), defaultdict(list)
for category, document in documents.items():
for journal in document["journals"]:
record = {"category": category, "journal": journal["name"], "source": document["source"],
"source_sha256": document["source_sha256"], "source_row": journal["source_row"],
"categorized_on": journal["categorized_on"], "issns": known.get(journal["name"], []) if category == "К1" else []}
if record["issns"]:
record.update(identity_source=identities["source"], identity_source_sha256=identities["source_sha256"],
identity_as_of=identities["as_of"])
for name in [journal["name"], *journal.get("aliases", [])]:
by_name[journal_key(name)].append(record)
for identifier in record["issns"]:
by_issn[identifier].append(record)
return dict(by_name), dict(by_issn)
def assess_vak(names, identifiers):
by_name, by_issn = category_index()
matches = {}
normalized = {issn(value) for value in identifiers} - {""}
for identifier in normalized:
for record in by_issn.get(identifier, []):
matches[(record["category"], record["source_row"])] = {**record, "match_method": "issn", "identity_confirmed": True}
for name in names:
for record in by_name.get(journal_key(name), []):
if record["issns"] and normalized and not normalized.intersection(record["issns"]):
return {"schema_version": 1, "entries": [], "status": "journal_identity_conflict",
"scope": "supplied_category_snapshot", "historical_category_confirmed": False, "checked_on": date.today().isoformat()}
key = record["category"], record["source_row"]
matches.setdefault(key, {**record, "match_method": "normalized_name", "identity_confirmed": False})
if len(matches) > 1:
status, output = "ambiguous_journal", []
elif matches:
status, output = "found", list(matches.values())
else:
status, output = ("not_found_in_k1_k2" if names or identifiers else "unknown_journal"), []
return {"schema_version": 1, "entries": output, "status": status,
"scope": "supplied_category_snapshot", "historical_category_confirmed": False,
"checked_on": date.today().isoformat()}