tests/test_articles.py

from __future__ import annotations

import json
from pathlib import Path

import pytest

from gcmd_classifier.articles import (
    load_articles,
    read_article_json,
    validate_article_record,
    validate_article_records,
)
from gcmd_classifier.errors import (
    ArticleFileNotFoundError,
    ArticleJSONDecodeError,
    ArticleTopLevelTypeError,
)
from gcmd_classifier.models import ArticleRecord

VALID_FIXTURE = Path("tests/fixtures/articles_valid.json")
INVALID_FIXTURE = Path("tests/fixtures/articles_invalid.json")
FULL_ARTICLES_PATH = Path("data/articles.json")


def test_valid_article_loading() -> None:
    result = load_articles(VALID_FIXTURE)

    assert result.source_count == 3
    assert result.valid_count == 3
    assert result.errors == ()
    assert all(isinstance(article, ArticleRecord) for article in result.articles)


def test_preserves_source_order() -> None:
    result = load_articles(VALID_FIXTURE)

    assert [article.DOI for article in result.articles] == [
        "10.0001/ATMOS.TEST",
        "10.0002/MULTI.TEST",
        "10.0003/TITLEONLY.TEST",
    ]


def test_exact_source_value_preservation() -> None:
    raw = json.loads(VALID_FIXTURE.read_text())
    result = load_articles(VALID_FIXTURE)
    first = result.articles[0]

    assert first.DOI == raw[0]["DOI"]
    assert first.Title == raw[0]["Title"]
    assert first.Year == raw[0]["Year"]
    assert first.Abstract == raw[0]["Abstract"]
    assert first.Title.startswith("  ")
    assert first.Title.endswith("  ")


def test_empty_abstract_is_valid_and_preserved() -> None:
    result = load_articles(VALID_FIXTURE)
    article = result.articles[2]

    assert article.Abstract == ""
    assert article.Title == "Editorial: New instrumentation for environmental archives?"


def test_exact_serialization_field_names() -> None:
    article = load_articles(VALID_FIXTURE).articles[0]

    assert article.model_dump() == {
        "DOI": "10.0001/ATMOS.TEST",
        "Title": "  High-Resolution Rainfall Trends over Mountain Basins: A 20-Year Study  ",
        "Year": 2024,
        "Abstract": "Precipitation intensity, snowpack, and runoff timing are evaluated using "
        "station and satellite observations.",
    }


def test_invalid_fixture_reports_multiple_record_errors() -> None:
    result = load_articles(INVALID_FIXTURE)
    codes = [error.code for error in result.errors]

    assert result.source_count == 18
    assert result.has_errors is True
    assert "MISSING_REQUIRED_FIELD" in codes
    assert "EMPTY_REQUIRED_STRING" in codes
    assert "INVALID_FIELD_TYPE" in codes
    assert "ARTICLE_NOT_OBJECT" in codes
    assert "DUPLICATE_DOI" in codes
    assert "UNEXPECTED_FIELD" in codes
    assert len(result.errors) >= 17


@pytest.mark.parametrize(
    ("record", "field"),
    [
        ({"Title": "T", "Year": 2024, "Abstract": "A"}, "DOI"),
        ({"DOI": "10.x", "Year": 2024, "Abstract": "A"}, "Title"),
        ({"DOI": "10.x", "Title": "T", "Abstract": "A"}, "Year"),
        ({"DOI": "10.x", "Title": "T", "Year": 2024}, "Abstract"),
    ],
)
def test_missing_required_fields(record: dict, field: str) -> None:
    article, errors = validate_article_record(record, index=7)

    assert article is None
    assert any(error.code == "MISSING_REQUIRED_FIELD" and error.field == field for error in errors)
    assert all(error.index == 7 for error in errors)


@pytest.mark.parametrize(
    ("record", "field"),
    [
        ({"DOI": "", "Title": "T", "Year": 2024, "Abstract": "A"}, "DOI"),
        ({"DOI": "10.x", "Title": "", "Year": 2024, "Abstract": "A"}, "Title"),
    ],
)
def test_empty_required_strings(record: dict, field: str) -> None:
    article, errors = validate_article_record(record, index=1)

    assert article is None
    assert any(error.code == "EMPTY_REQUIRED_STRING" and error.field == field for error in errors)


def test_whitespace_only_title_is_preserved_not_normalized() -> None:
    record = {"DOI": "10.x/space", "Title": "   ", "Year": 2024, "Abstract": "A"}

    article, errors = validate_article_record(record, index=0)

    assert errors == ()
    assert article is not None
    assert article.Title == "   "


@pytest.mark.parametrize(
    ("field", "value"),
    [
        ("DOI", 123),
        ("Title", ["bad"]),
        ("Abstract", 42),
    ],
)
def test_non_string_fields_rejected(field: str, value: object) -> None:
    record = {"DOI": "10.x", "Title": "T", "Year": 2024, "Abstract": "A"}
    record[field] = value

    article, errors = validate_article_record(record, index=2)

    assert article is None
    assert any(error.code == "INVALID_FIELD_TYPE" and error.field == field for error in errors)


@pytest.mark.parametrize("year", ["2024", 2024.0, True, False])
def test_invalid_year_types_rejected(year: object) -> None:
    record = {"DOI": "10.x/year", "Title": "T", "Year": year, "Abstract": "A"}

    article, errors = validate_article_record(record, index=3)

    assert article is None
    assert any(error.code == "INVALID_FIELD_TYPE" and error.field == "Year" for error in errors)


def test_null_field_values_rejected() -> None:
    record = {"DOI": None, "Title": None, "Year": None, "Abstract": None}

    article, errors = validate_article_record(record, index=4)

    assert article is None
    assert len([error for error in errors if error.code == "INVALID_FIELD_TYPE"]) == 4


def test_duplicate_doi_detection_excludes_duplicate_records_from_valid_records() -> None:
    raw_records = [
        {"DOI": "10.same", "Title": "One", "Year": 2024, "Abstract": "A"},
        {"DOI": "10.same", "Title": "Two", "Year": 2025, "Abstract": "B"},
        {"DOI": "10.unique", "Title": "Three", "Year": 2026, "Abstract": "C"},
    ]

    result = validate_article_records(raw_records)

    assert [article.DOI for article in result.articles] == ["10.unique"]
    assert [error.index for error in result.errors if error.code == "DUPLICATE_DOI"] == [0, 1]


def test_non_object_article_entry() -> None:
    result = validate_article_records(["bad"])

    assert result.articles == ()
    assert result.errors[0].code == "ARTICLE_NOT_OBJECT"
    assert result.errors[0].index == 0


def test_top_level_non_list_json() -> None:
    with pytest.raises(ArticleTopLevelTypeError):
        validate_article_records({"DOI": "10.x"})


def test_invalid_json(tmp_path: Path) -> None:
    path = tmp_path / "invalid.json"
    path.write_text("[{bad json]")

    with pytest.raises(ArticleJSONDecodeError):
        read_article_json(path)


def test_file_not_found_behavior(tmp_path: Path) -> None:
    with pytest.raises(ArticleFileNotFoundError):
        load_articles(tmp_path / "missing.json")


def test_source_file_immutability() -> None:
    before = FULL_ARTICLES_PATH.read_bytes()
    load_articles(FULL_ARTICLES_PATH)
    after = FULL_ARTICLES_PATH.read_bytes()

    assert after == before


def test_full_data_smoke_current_articles_file() -> None:
    raw_records = json.loads(FULL_ARTICLES_PATH.read_text())
    result = load_articles(FULL_ARTICLES_PATH)

    assert isinstance(raw_records, list)
    assert result.source_count == len(raw_records)
    assert result.valid_count == len(raw_records) - len(result.errors)
    assert len({article.DOI for article in result.articles}) == result.valid_count

    if result.errors:
        assert result.has_errors is True
        assert all(error.code and error.message for error in result.errors)
        assert all(
            error.index is None or 0 <= error.index < len(raw_records) for error in result.errors
        )
    else:
        assert result.has_errors is False

    invalid_indices = {error.index for error in result.errors if error.index is not None}
    valid_raw_records = [
        record for index, record in enumerate(raw_records) if index not in invalid_indices
    ]
    assert [article.model_dump() for article in result.articles] == valid_raw_records