tests/test_persistence.py

from __future__ import annotations

import json
from pathlib import Path

import pytest

from gcmd_classifier.models import (
    ArticleClassificationOutcome,
    ArticleProcessingStatus,
    ArticleResult,
    OutputError,
    ProcessingMetadata,
    ReviewStatus,
    RunSummary,
)
from gcmd_classifier.persistence import JsonResultStore


def _result(doi: str, *, failed: bool = False) -> ArticleResult:
    if failed:
        return ArticleResult(
            DOI=doi,
            Title="Failed article",
            Year=2025,
            Abstract="Text.",
            processing_status=ArticleProcessingStatus.FAILED,
            classification_outcome=None,
            classifications=(),
            review_status=ReviewStatus.NOT_REQUIRED,
            errors=(OutputError(code="MODEL_FAILED", message="Model failed."),),
            processing_metadata=ProcessingMetadata(cache_used=False),
        )
    return ArticleResult(
        DOI=doi,
        Title="Completed article",
        Year=2025,
        Abstract="Text.",
        processing_status=ArticleProcessingStatus.COMPLETED,
        classification_outcome=ArticleClassificationOutcome.NOT_CLASSIFIED,
        classifications=(),
        no_classification_reason="No Topic selected.",
        review_status=ReviewStatus.NOT_REQUIRED,
        processing_metadata=ProcessingMetadata(cache_used=False),
    )


def test_article_result_is_saved_after_completion(tmp_path: Path) -> None:
    store = JsonResultStore(tmp_path)
    result = _result("10.example/done")

    store.save_article_result(result)

    loaded = store.load_article_result("10.example/done")
    assert loaded == result


def test_failed_article_result_is_saved(tmp_path: Path) -> None:
    store = JsonResultStore(tmp_path)
    result = _result("10.example/failed", failed=True)

    store.save_article_result(result)

    assert store.load_article_result("10.example/failed") == result


def test_previous_results_survive_simulated_later_failure(tmp_path: Path) -> None:
    store = JsonResultStore(tmp_path)
    first = _result("10.example/first")
    store.save_article_result(first)

    with pytest.raises(RuntimeError):
        raise RuntimeError("later article failed before save")

    assert store.load_article_result("10.example/first") == first


def test_loading_existing_results_works(tmp_path: Path) -> None:
    store = JsonResultStore(tmp_path)
    first = _result("10.example/first")
    second = _result("10.example/second", failed=True)
    store.save_article_result(first)
    store.save_article_result(second)

    loaded = store.load_all_results()

    assert {result.DOI for result in loaded} == {"10.example/first", "10.example/second"}


def test_duplicate_output_records_for_same_doi_are_avoided(tmp_path: Path) -> None:
    store = JsonResultStore(tmp_path)
    first = _result("10.example/same")
    second = _result("10.example/same", failed=True)

    store.save_article_result(first)
    store.save_article_result(second)

    loaded = store.load_all_results()
    assert len(loaded) == 1
    assert loaded[0].processing_status is ArticleProcessingStatus.FAILED


def test_consolidated_output_is_valid_json(tmp_path: Path) -> None:
    store = JsonResultStore(tmp_path)
    result = _result("10.example/done")
    summary = RunSummary(run_id="run-1", articles_received=1, articles_completed=1)

    output_path = store.write_consolidated(results=[result], summary=summary)

    payload = json.loads(output_path.read_text())
    assert payload["summary"]["run_id"] == "run-1"
    assert payload["articles"][0]["DOI"] == "10.example/done"


def test_atomic_checkpoint_temp_file_is_removed_after_success(tmp_path: Path) -> None:
    store = JsonResultStore(tmp_path)
    result = _result("10.example/done")

    store.save_article_result(result)

    assert store.article_path(result.DOI).exists()
    assert not list(store.article_path(result.DOI).parent.glob("*.tmp"))