av-parser/tests/AvParser.Core.Tests/Collecting/PatternMediaSourceTests.cs

using AvParser.Core.Collecting;
using AvParser.Core.Collecting.Sources;

namespace AvParser.Core.Tests.Collecting;

public class PatternMediaSourceTests
{
    private static PatternSourceConfig Config(
        int min = 6,
        int max = 8,
        IdAlphabet alphabet = IdAlphabet.Alphanumeric,
        string? custom = null,
        string? extension = ".jpg",
        string url = "https://imgtest.example/test1/",
        bool allowDirect = false
    )
    {
        PatternSourceConfig.TryCreate("Test", url, min, max, alphabet, custom, extension, allowDirect, out var config);
        return config!;
    }

    private static async Task<List<MediaCandidate>> Collect(IMediaSource source, int limit)
    {
        var list = new List<MediaCandidate>();
        await foreach (var outcome in source.ParseAsync(new MediaQuery(Limit: limit), null, CancellationToken.None))
        {
            if (outcome.IsSuccess)
            {
                list.Add(outcome.Value!);
            }
        }

        return list;
    }

    [Fact]
    public void A_pattern_source_needs_the_network()
    {
        new PatternMediaSource(Config()).RequiresNetwork.ShouldBeTrue();
    }

    [Fact]
    public async Task Generated_ids_stay_within_the_length_range_and_alphabet()
    {
        var source = new PatternMediaSource(Config(min: 4, max: 6, alphabet: IdAlphabet.Digits, extension: null));

        var candidates = await Collect(source, 300);

        candidates.Count.ShouldBe(300);
        foreach (var candidate in candidates)
        {
            var id = candidate.ExternalId.ShouldNotBeNull();
            id.Length.ShouldBeInRange(4, 6);
            id.ShouldAllBe(c => char.IsAsciiDigit(c));
        }
    }

    [Fact]
    public async Task Candidates_hang_the_id_off_the_base_url_with_the_extension()
    {
        var source = new PatternMediaSource(Config(min: 6, max: 6, alphabet: IdAlphabet.HexLower, extension: ".png"));

        var candidate = (await Collect(source, 1)).ShouldHaveSingleItem();

        candidate.SourceId.ShouldBe(source.Id);
        candidate.Url.AbsoluteUri.ShouldBe($"https://imgtest.example/test1/{candidate.ExternalId}.png");
    }

    [Fact]
    public async Task An_unset_extension_still_lands_on_a_jpg_address()
    {
        var source = new PatternMediaSource(Config(min: 6, max: 6, alphabet: IdAlphabet.HexLower, extension: null));

        var candidate = (await Collect(source, 1)).ShouldHaveSingleItem();

        candidate.Url.AbsoluteUri.ShouldBe($"https://imgtest.example/test1/{candidate.ExternalId}.jpg");
    }

    [Fact]
    public async Task Several_extensions_become_one_candidate_with_fallbacks_in_order()
    {
        // One id is one picture: three candidates for three suffixes would fetch the hit and then
        // hunt for its imaginary twins, and count one find as three attempts.
        var source = new PatternMediaSource(
            Config(min: 6, max: 6, alphabet: IdAlphabet.HexLower, extension: ".jpg, png;.gif")
        );

        var candidate = (await Collect(source, 1)).ShouldHaveSingleItem();
        var id = candidate.ExternalId;

        candidate.Url.AbsoluteUri.ShouldBe($"https://imgtest.example/test1/{id}.jpg");
        candidate
            .Alternatives.Select(url => url.AbsoluteUri)
            .ShouldBe([$"https://imgtest.example/test1/{id}.png", $"https://imgtest.example/test1/{id}.gif"]);

        candidate.Addresses.First().ShouldBe(candidate.Url);
        candidate.Addresses.Count().ShouldBe(3);
    }

    [Fact]
    public async Task A_single_extension_leaves_the_candidate_without_fallbacks()
    {
        var source = new PatternMediaSource(Config(min: 6, max: 6, extension: ".png"));

        var candidate = (await Collect(source, 1)).ShouldHaveSingleItem();

        candidate.Alternatives.ShouldBeEmpty();
        candidate.Addresses.ShouldHaveSingleItem().ShouldBe(candidate.Url);
    }

    [Fact]
    public async Task The_attempt_budget_bounds_how_many_are_generated()
    {
        var source = new PatternMediaSource(Config(min: 6, max: 8, alphabet: IdAlphabet.Alphanumeric));

        (await Collect(source, 40)).Count.ShouldBe(40);
    }

    [Fact]
    public async Task A_small_space_is_never_exceeded_however_large_the_budget()
    {
        // Digits of length 2 is a hundred ids; asking for a thousand must not loop forever.
        var source = new PatternMediaSource(Config(min: 2, max: 2, alphabet: IdAlphabet.Digits, extension: null));

        var candidates = await Collect(source, 1000);

        candidates.Count.ShouldBeLessThanOrEqualTo(100);
        candidates.Select(c => c.ExternalId).Distinct().Count().ShouldBe(candidates.Count);
    }

    [Fact]
    public async Task No_budget_means_the_source_keeps_going_until_it_is_stopped()
    {
        // A limit of zero used to mean "one candidate", which made an unlimited run collect nothing.
        var source = new PatternMediaSource(Config(min: 8, max: 8, alphabet: IdAlphabet.Alphanumeric));
        using var stop = new CancellationTokenSource();

        var seen = 0;

        try
        {
            await foreach (var outcome in source.ParseAsync(new MediaQuery(), null, stop.Token))
            {
                outcome.IsSuccess.ShouldBeTrue();

                if (++seen >= 5_000)
                {
                    await stop.CancelAsync();
                }
            }
        }
        catch (OperationCanceledException)
        {
            // The only way an unbounded run ends.
        }

        seen.ShouldBe(5_000);
    }

    [Fact]
    public async Task A_small_space_still_bounds_an_unlimited_run()
    {
        // Two digits is a hundred ids: with no budget the run must end at the space, not spin on
        // collisions for ever.
        var source = new PatternMediaSource(Config(min: 2, max: 2, alphabet: IdAlphabet.Digits, extension: null));

        var candidates = await Collect(source, 0);

        // Not exactly a hundred: the draw is random, so the last few ids may be given up on rather
        // than waited for. What matters is that the run ends and never repeats itself.
        candidates.Count.ShouldBeInRange(90, 100);
        candidates.Select(c => c.ExternalId).Distinct().Count().ShouldBe(candidates.Count);
    }

    [Fact]
    public async Task Generated_ids_are_unique_within_a_run()
    {
        var source = new PatternMediaSource(Config(min: 8, max: 8, alphabet: IdAlphabet.Alphanumeric, extension: null));

        var candidates = await Collect(source, 500);

        candidates.Select(c => c.ExternalId).Distinct().Count().ShouldBe(500);
    }
}

public class PatternAlphabetTests
{
    [Theory]
    [InlineData(IdAlphabet.LettersLower, "abcdefghijklmnopqrstuvwxyz")]
    [InlineData(IdAlphabet.Digits, "0123456789")]
    [InlineData(IdAlphabet.HexLower, "0123456789abcdef")]
    public void Named_sets_resolve_to_their_characters(IdAlphabet alphabet, string expected)
    {
        PatternAlphabet.Resolve(alphabet).ShouldBe(expected);
    }

    [Fact]
    public void Letters_and_alphanumeric_combine_the_sets()
    {
        PatternAlphabet.Resolve(IdAlphabet.Letters).Length.ShouldBe(52);
        PatternAlphabet.Resolve(IdAlphabet.Alphanumeric).Length.ShouldBe(62);
    }

    [Fact]
    public void A_custom_set_is_de_duplicated_and_stripped_of_separators()
    {
        // Repeats would skew the draw; a slash would break the "one path segment" assumption.
        PatternAlphabet.Resolve(IdAlphabet.Custom, "aab/c c").ShouldBe("abc");
    }

    [Fact]
    public void An_empty_custom_set_resolves_to_nothing()
    {
        PatternAlphabet.Resolve(IdAlphabet.Custom, "   ").ShouldBeEmpty();
    }
}

public class PatternSourceConfigTests
{
    [Fact]
    public void A_valid_config_normalises_the_base_url_and_extension()
    {
        var error = PatternSourceConfig.TryCreate(
            "  My source ",
            "https://imgtest.example/test1",
            6,
            8,
            IdAlphabet.Alphanumeric,
            null,
            "jpg",
            allowDirectConnection: false,
            out var config
        );

        error.ShouldBe(PatternConfigError.None);
        config.ShouldNotBeNull();
        config.Name.ShouldBe("My source");
        config.BaseUrl.AbsoluteUri.ShouldBe("https://imgtest.example/test1/");
        config.Extension.ShouldBe(".jpg");
        config.Id.ShouldNotBeNullOrWhiteSpace();
    }

    [Theory]
    [InlineData(".jpg,.png", ".jpg,.png")]
    [InlineData("jpg png gif", ".jpg,.png,.gif")]
    [InlineData(".jpg; .PNG ;jpg", ".jpg,.PNG")]
    [InlineData("  ", ".jpg")]
    public void Extensions_are_normalised_into_an_ordered_list(string typed, string expected)
    {
        // Order is an instruction, not a detail: it is the order the fetcher will try. Repeats are
        // dropped because a repeat means fetching the same address twice before giving up on the id.
        PatternSourceConfig.TryCreate(
            "N",
            "https://h/x/",
            6,
            8,
            IdAlphabet.Digits,
            null,
            typed,
            allowDirectConnection: false,
            out var config
        );

        config.ShouldNotBeNull().Extension.ShouldBe(expected);
        config.Extensions.ShouldBe(expected.Split(','));
    }

    [Fact]
    public void A_doubled_trailing_slash_is_collapsed()
    {
        // "host//" is not "host/": ids resolve against it as //{id}, which most servers answer with
        // a 404 for every attempt in the run. Easy to paste, impossible to spot in the field.
        var error = PatternSourceConfig.TryCreate(
            "N",
            "https://imgtest.example/test1//",
            6,
            8,
            IdAlphabet.Digits,
            null,
            ".jpg",
            allowDirectConnection: false,
            out var config
        );

        error.ShouldBe(PatternConfigError.None);
        config.ShouldNotBeNull().BaseUrl.AbsoluteUri.ShouldBe("https://imgtest.example/test1/");
    }

    [Fact]
    public async Task Ids_hang_off_a_collapsed_base_url_without_a_doubled_slash()
    {
        PatternSourceConfig.TryCreate(
            "N",
            "https://imgtest.example/test1//",
            6,
            6,
            IdAlphabet.Digits,
            null,
            ".jpg",
            allowDirectConnection: false,
            out var config
        );

        var source = new PatternMediaSource(config!);

        await foreach (var outcome in source.ParseAsync(new MediaQuery(Limit: 1), null, CancellationToken.None))
        {
            var candidate = outcome.Value.ShouldNotBeNull();
            candidate.Url.AbsoluteUri.ShouldBe($"https://imgtest.example/test1/{candidate.ExternalId}.jpg");
        }
    }

    [Fact]
    public void A_blank_extension_becomes_the_default_one()
    {
        // The editor shows ".jpg" as the placeholder, so an untouched field means "the usual one",
        // not "no suffix" — the latter costs a whole run of 404s to discover.
        var error = PatternSourceConfig.TryCreate(
            "N",
            "https://h/x/",
            6,
            8,
            IdAlphabet.Digits,
            null,
            "   ",
            allowDirectConnection: false,
            out var config
        );

        error.ShouldBe(PatternConfigError.None);
        config.ShouldNotBeNull().Extension.ShouldBe(PatternSourceConfig.DefaultExtension);
    }

    [Fact]
    public void A_supplied_id_is_kept()
    {
        PatternSourceConfig.TryCreate(
            "N",
            "https://h/x/",
            6,
            8,
            IdAlphabet.Digits,
            null,
            null,
            allowDirectConnection: false,
            out var config,
            "fixed-id"
        );

        config.ShouldNotBeNull().Id.ShouldBe("fixed-id");
    }

    [Theory]
    [InlineData("", "https://h/x/", 6, 8, IdAlphabet.Digits, PatternConfigError.NameRequired)]
    [InlineData("N", "not-a-url", 6, 8, IdAlphabet.Digits, PatternConfigError.BaseUrlInvalid)]
    [InlineData("N", "ftp://h/x/", 6, 8, IdAlphabet.Digits, PatternConfigError.BaseUrlInvalid)]
    [InlineData("N", "https://h/x/", 0, 8, IdAlphabet.Digits, PatternConfigError.LengthRangeInvalid)]
    [InlineData("N", "https://h/x/", 8, 6, IdAlphabet.Digits, PatternConfigError.LengthRangeInvalid)]
    [InlineData("N", "https://h/x/", 6, 65, IdAlphabet.Digits, PatternConfigError.LengthRangeInvalid)]
    [InlineData("N", "https://h/x/", 6, 8, IdAlphabet.Custom, PatternConfigError.AlphabetEmpty)]
    public void Invalid_inputs_are_rejected_with_a_reason(
        string name,
        string url,
        int min,
        int max,
        IdAlphabet alphabet,
        PatternConfigError expected
    )
    {
        var error = PatternSourceConfig.TryCreate(
            name,
            url,
            min,
            max,
            alphabet,
            null,
            null,
            allowDirectConnection: false,
            out var config
        );

        error.ShouldBe(expected);
        config.ShouldBeNull();
    }
}