hyungi_document_server/tests/test_paper_doi_units.py

"""B-3 PR1 — 논문 DOI 코어 순수 단위 테스트 (plan safety-library-b3-1).

holder.find_paper_holder(DB 조회)는 PR2 arXiv 실수집 시 라이브 검증 — 여기선 순수 함수만.
"""

import sys
from pathlib import Path

sys.path.insert(0, str(Path(__file__).parent.parent / "app"))

from services.papers.doi import (  # noqa: E402
    arxiv_doi,
    normalize_doi,
    paper_doi_hash,
    parse_arxiv_id,
    parse_doi_from_text,
    read_paper_doi,
    with_paper_doi,
    with_parent_doi,
)


# ─── normalize_doi: 단일 함수(저장=조회) ───

def test_normalize_strips_url_and_lowercases():
    assert normalize_doi("https://doi.org/10.1585/PFR.15.2402039") == "10.1585/pfr.15.2402039"
    assert normalize_doi("http://dx.doi.org/10.1115/1.4045678") == "10.1115/1.4045678"
    assert normalize_doi("doi:10.1016/j.jlp.2020.104321") == "10.1016/j.jlp.2020.104321"
    assert normalize_doi("DOI: 10.1234/ABC") == "10.1234/abc"


def test_normalize_trims_whitespace_and_citation_noise():
    assert normalize_doi("  https://doi.org/10.1234/abc  ") == "10.1234/abc"
    assert normalize_doi("10.1234/abc.") == "10.1234/abc"
    assert normalize_doi("10.1234/abc;") == "10.1234/abc"


def test_normalize_preserves_parens_in_doi():
    # 괄호는 DOI 일부일 수 있어 보존 (과삭제 = 다른 논문 병합 = 데이터 손상, near-dup 보다 위험)
    assert normalize_doi("10.1016/s0010-8650(00)80003-2") == "10.1016/s0010-8650(00)80003-2"
    assert normalize_doi("https://doi.org/10.1016/S0010-8650(00)80003-2") == "10.1016/s0010-8650(00)80003-2"


def test_normalize_rejects_non_doi():
    assert normalize_doi(None) is None
    assert normalize_doi("") is None
    assert normalize_doi("   ") is None
    assert normalize_doi("not-a-doi") is None
    assert normalize_doi("arXiv:2606.08108") is None  # arXiv id 는 DOI 아님


def test_normalize_is_idempotent_store_equals_lookup():
    # 저장측·조회측이 같은 함수를 거치면 표기 차이가 한 값으로 붕괴 (dedup 성립 조건)
    forms = [
        "https://doi.org/10.1/X",
        "doi:10.1/x",
        "10.1/X",
        "  HTTPS://DOI.ORG/10.1/x ",
    ]
    assert {normalize_doi(f) for f in forms} == {"10.1/x"}
    assert normalize_doi(normalize_doi("https://doi.org/10.1/X")) == "10.1/x"  # 멱등


# ─── paper_doi_hash: holder file_hash 키 ───

def test_paper_doi_hash_deterministic_len32():
    h = paper_doi_hash("10.1234/abc")
    assert len(h) == 32
    assert h == paper_doi_hash("10.1234/abc")


def test_paper_doi_hash_distinct_per_doi():
    assert paper_doi_hash("10.1/a") != paper_doi_hash("10.1/b")


# ─── 2-Document extract_meta 계약 (holder doi / child parent_doi 상호 배타) ───

def test_with_paper_doi_holder_shape_and_merge_safe():
    meta = with_paper_doi({"license": {"scheme": "cc_by"}, "source_id": 7}, "10.1/x")
    assert meta["paper"]["doi"] == "10.1/x"
    assert "parent_doi" not in meta["paper"]
    assert meta["license"]["scheme"] == "cc_by"  # 타 키 보존
    assert meta["source_id"] == 7


def test_with_parent_doi_child_shape_no_doi():
    meta = with_parent_doi({"license": {"scheme": "proprietary"}}, "10.1/holder")
    assert meta["paper"]["parent_doi"] == "10.1/holder"
    assert "doi" not in meta["paper"]  # child 는 doi 미보유 (partial-unique 인덱스 밖)
    assert meta["license"]["scheme"] == "proprietary"


def test_holder_child_mutually_exclusive():
    child = with_parent_doi({}, "10.1/p")
    promoted = with_paper_doi(child, "10.1/self")
    assert promoted["paper"]["doi"] == "10.1/self"
    assert "parent_doi" not in promoted["paper"]


def test_input_not_mutated():
    src = {"paper": {"doi": "10.1/old"}}
    with_parent_doi(src, "10.1/new")
    assert src["paper"]["doi"] == "10.1/old"  # 원본 dict 불변


# ─── read_paper_doi: 인덱스 식의 조회측 거울 ───

def test_read_paper_doi():
    assert read_paper_doi({"paper": {"doi": "10.1/x"}}) == "10.1/x"
    assert read_paper_doi({"paper": {"doi": "https://doi.org/10.1/X"}}) == "10.1/x"  # 방어적 재정규화
    assert read_paper_doi({}) is None
    assert read_paper_doi(None) is None
    assert read_paper_doi({"paper": {"parent_doi": "10.1/p"}}) is None  # child 는 doi 없음
    assert read_paper_doi({"paper": {}}) is None


# ─── PR4: arXiv id 파싱 + arXiv DataCite DOI (교차소스 dedup 통일 키) ───

def test_parse_arxiv_id():
    assert parse_arxiv_id("Title arXiv:2606.10236v1 Announce Type: new Abstract") == "2606.10236"
    assert parse_arxiv_id("see arXiv:2601.02852 for details") == "2601.02852"
    assert parse_arxiv_id("arXiv:cond-mat/0703470v2") == "cond-mat/0703470"
    assert parse_arxiv_id("no arxiv here") is None
    assert parse_arxiv_id(None) is None


def test_arxiv_doi_canonical():
    # OpenAlex canonical 실측 일치: 10.48550/arxiv.{id} (소문자)
    assert arxiv_doi("2606.10236") == "10.48550/arxiv.2606.10236"
    assert arxiv_doi(None) is None
    # 수집기·reconcile 가 같은 함수 → 같은 paper.doi (교차소스 dedup 성립)
    assert arxiv_doi(parse_arxiv_id("x arXiv:2606.10236v1 y")) == "10.48550/arxiv.2606.10236"


# ─── PR5: 구매 PDF 본문 DOI 파싱 (parent_doi 링크용, PDF 구조 무관) ───

def test_parse_doi_from_text():
    assert parse_doi_from_text("ref https://doi.org/10.1016/j.jlp.2024.105474 end") == "10.1016/j.jlp.2024.105474"
    assert parse_doi_from_text("DOI 10.1115/1.4045678. Next.") == "10.1115/1.4045678"
    assert parse_doi_from_text("no doi here") is None
    assert parse_doi_from_text(None) is None