Kavita/API.Tests/Services/ArchiveServiceTests.cs
Joseph Milazzo a01613f80f
EPUB Support (#178)
* Added book filetype detection and reorganized tests due to size of file

* Added ability to get basic Parse Info from Book and Pages.

* We can now scan books and get them in a library with cover images.

* Take the first image in the epub if the cover isn't set.

* Implemented the ability to unzip the ebup to cache. Implemented a test api to load html files.

* Just some test code to figure out how to approach this.

* Fixed some merge conflicts

* Removed some dead code from merge

* Snapshot: I can now load everything properly into the UI by rewriting the urls before I send them back. I don't notice any lag from this method. It can be optimized further.

* Implemented a way to load the content in the browser not via an iframe.

* Added a note

* Anchor mappings is complete. New anchors are updated so references now resolve to javascript:void() for UI to take care of internally loading and the appropriate page is mapped to it. Anchors that are external have target="_blank" added so they don't force you out of the app and styles are of course inlined.

* Oops i need this

* Table of contents api implemented (rough) and some small enhancements to codebase for books.

* GetBookPageResources now only loads files from within the book. Nested chapter list support and images now use html parsing instead of string parsing.

* Fonts now are remapped to load from endpoint.

* book-resources now uses a key, ensuring the file is in proper format for lookup. Changed chapter list based on structure with one HEADER and nested chapters.

* Properly handle svg resource requests and when there are part anchors that are clickable, make sure we handle them in the UI by adding a kavita-page handler.

* Add Chapter group page even if one isn't set by using first page (without part) from nestedChildren.

* Added extra debug code for issue #163.

* Added new user preferences for books and updated the css so we scope it to our reading section.

* Cleaned up style code

* Implemented ability to save book preferences and some cleanup on existing apis.

* Added an api for checking if a user has read something in a library type before.

* Forgot to make sure the has reading progress is against a user lol.

* Remove cacheservice code for books, sine we use an in-memory method

* Handle svg images as well

* Enhanced cover image extraction to check for a "cover" image if the cover image wasn't set in OPF before falling back to the first image.

* Fixed an issue with special books not properly generating metadata due to not having filename set.

* Cleanup, removed warmup task code from statup/program and changed taskscheduler to schedule tasks on startup only (or if tasks are changed from UI).

* Code cleanup

* Code cleanup

* So much code. Lots of refactors to try to test scanner service. Moved a lot of the queries into Extensions to allow to easier test, even though it's hacky. Support @font-face src:url swaps with ' and ". Source summary information from epubs.

* Well...baseURL needs to come from BE and not from UI lol.

* Adjusted migrations so default values match Entity

* Removed comment

* I think I finally fixed #163! The issue was that when i checked if it had a parserInfo, i wasn't considering that the chapter range might have a - in it (0-6) and so when the code to check if range could parse out a number failed, it treated it like a special and checked range against info's filename.

* Some bugfixes

* Lots of testing, extracting code to make it easier to test. This code is buggy, but fixed a bug where 1) If we changed the normalization code, we would remove the whole db during a scan and 2) We weren't actually removing series properly.

Other than that, code is being extracted to remove duplication and centralize logic.

* More code cleanup and test cleanup to ensure scan loop is working as expected and matches expectaions from tests.

* Cleaned up the code and made it so if I change normalization, which I do in this branch, it wont break existing DBs.

* Some comic parser changes for partial chapter support.

* Added some code for directory service and scanner service along with python code to generate test files (not used yet). Fixed up all the tests.

* Code smells
2021-04-28 16:16:22 -05:00

207 lines
11 KiB
C#

using System.Diagnostics;
using System.IO;
using System.IO.Compression;
using API.Archive;
using API.Services;
using Microsoft.Extensions.Logging;
using NSubstitute;
using NSubstitute.Extensions;
using Xunit;
using Xunit.Abstractions;
namespace API.Tests.Services
{
public class ArchiveServiceTests
{
private readonly ITestOutputHelper _testOutputHelper;
private readonly ArchiveService _archiveService;
private readonly ILogger<ArchiveService> _logger = Substitute.For<ILogger<ArchiveService>>();
public ArchiveServiceTests(ITestOutputHelper testOutputHelper)
{
_testOutputHelper = testOutputHelper;
_archiveService = new ArchiveService(_logger);
}
[Theory]
[InlineData("flat file.zip", false)]
[InlineData("file in folder in folder.zip", true)]
[InlineData("file in folder.zip", true)]
[InlineData("file in folder_alt.zip", true)]
public void ArchiveNeedsFlatteningTest(string archivePath, bool expected)
{
var testDirectory = Path.Join(Directory.GetCurrentDirectory(), "../../../Services/Test Data/ArchiveService/Archives");
var file = Path.Join(testDirectory, archivePath);
using ZipArchive archive = ZipFile.OpenRead(file);
Assert.Equal(expected, _archiveService.ArchiveNeedsFlattening(archive));
}
[Theory]
[InlineData("non existent file.zip", false)]
[InlineData("winrar.rar", true)]
[InlineData("empty.zip", true)]
[InlineData("flat file.zip", true)]
[InlineData("file in folder in folder.zip", true)]
[InlineData("file in folder.zip", true)]
[InlineData("file in folder_alt.zip", true)]
public void IsValidArchiveTest(string archivePath, bool expected)
{
var testDirectory = Path.Join(Directory.GetCurrentDirectory(), "../../../Services/Test Data/ArchiveService/Archives");
Assert.Equal(expected, _archiveService.IsValidArchive(Path.Join(testDirectory, archivePath)));
}
[Theory]
[InlineData("non existent file.zip", 0)]
[InlineData("winrar.rar", 0)]
[InlineData("empty.zip", 0)]
[InlineData("flat file.zip", 1)]
[InlineData("file in folder in folder.zip", 1)]
[InlineData("file in folder.zip", 1)]
[InlineData("file in folder_alt.zip", 1)]
[InlineData("macos_none.zip", 0)]
[InlineData("macos_one.zip", 1)]
[InlineData("macos_native.zip", 21)]
public void GetNumberOfPagesFromArchiveTest(string archivePath, int expected)
{
var testDirectory = Path.Join(Directory.GetCurrentDirectory(), "../../../Services/Test Data/ArchiveService/Archives");
var sw = Stopwatch.StartNew();
Assert.Equal(expected, _archiveService.GetNumberOfPagesFromArchive(Path.Join(testDirectory, archivePath)));
_testOutputHelper.WriteLine($"Processed Original in {sw.ElapsedMilliseconds} ms");
}
[Theory]
[InlineData("non existent file.zip", ArchiveLibrary.NotSupported)]
[InlineData("winrar.rar", ArchiveLibrary.SharpCompress)]
[InlineData("empty.zip", ArchiveLibrary.Default)]
[InlineData("flat file.zip", ArchiveLibrary.Default)]
[InlineData("file in folder in folder.zip", ArchiveLibrary.Default)]
[InlineData("file in folder.zip", ArchiveLibrary.Default)]
[InlineData("file in folder_alt.zip", ArchiveLibrary.Default)]
public void CanOpenArchive(string archivePath, ArchiveLibrary expected)
{
var sw = Stopwatch.StartNew();
var testDirectory = Path.Join(Directory.GetCurrentDirectory(), "../../../Services/Test Data/ArchiveService/Archives");
Assert.Equal(expected, _archiveService.CanOpen(Path.Join(testDirectory, archivePath)));
_testOutputHelper.WriteLine($"Processed Original in {sw.ElapsedMilliseconds} ms");
}
[Theory]
[InlineData("non existent file.zip", 0)]
[InlineData("winrar.rar", 0)]
[InlineData("empty.zip", 0)]
[InlineData("flat file.zip", 1)]
[InlineData("file in folder in folder.zip", 1)]
[InlineData("file in folder.zip", 1)]
[InlineData("file in folder_alt.zip", 1)]
public void CanExtractArchive(string archivePath, int expectedFileCount)
{
var testDirectory = Path.Join(Directory.GetCurrentDirectory(), "../../../Services/Test Data/ArchiveService/Archives");
var extractDirectory = Path.Join(Directory.GetCurrentDirectory(), "../../../Services/Test Data/ArchiveService/Archives/Extraction");
DirectoryService.ClearAndDeleteDirectory(extractDirectory);
Stopwatch sw = Stopwatch.StartNew();
_archiveService.ExtractArchive(Path.Join(testDirectory, archivePath), extractDirectory);
var di1 = new DirectoryInfo(extractDirectory);
Assert.Equal(expectedFileCount, di1.Exists ? di1.GetFiles().Length : 0);
_testOutputHelper.WriteLine($"Processed in {sw.ElapsedMilliseconds} ms");
DirectoryService.ClearAndDeleteDirectory(extractDirectory);
}
[Theory]
[InlineData(new [] {"folder.jpg"}, "folder.jpg")]
[InlineData(new [] {"vol1/"}, "")]
[InlineData(new [] {"folder.jpg", "vol1/folder.jpg"}, "folder.jpg")]
[InlineData(new [] {"cover.jpg", "vol1/folder.jpg"}, "cover.jpg")]
[InlineData(new [] {"__MACOSX/cover.jpg", "vol1/page 01.jpg"}, "")]
[InlineData(new [] {"Akame ga KILL! ZERO - c055 (v10) - p000 [Digital] [LuCaZ].jpg", "Akame ga KILL! ZERO - c055 (v10) - p000 [Digital] [LuCaZ].jpg", "Akame ga KILL! ZERO - c060 (v10) - p200 [Digital] [LuCaZ].jpg", "folder.jpg"}, "folder.jpg")]
public void FindFolderEntry(string[] files, string expected)
{
var foundFile = _archiveService.FindFolderEntry(files);
Assert.Equal(expected, string.IsNullOrEmpty(foundFile) ? "" : foundFile);
}
[Theory]
[InlineData(new [] {"folder.jpg"}, "folder.jpg")]
[InlineData(new [] {"vol1/"}, "")]
[InlineData(new [] {"folder.jpg", "vol1/folder.jpg"}, "folder.jpg")]
[InlineData(new [] {"cover.jpg", "vol1/folder.jpg"}, "cover.jpg")]
[InlineData(new [] {"page 2.jpg", "page 10.jpg"}, "page 2.jpg")]
[InlineData(new [] {"__MACOSX/cover.jpg", "vol1/page 01.jpg"}, "vol1/page 01.jpg")]
[InlineData(new [] {"Akame ga KILL! ZERO - c055 (v10) - p000 [Digital] [LuCaZ].jpg", "Akame ga KILL! ZERO - c055 (v10) - p000 [Digital] [LuCaZ].jpg", "Akame ga KILL! ZERO - c060 (v10) - p200 [Digital] [LuCaZ].jpg", "folder.jpg"}, "Akame ga KILL! ZERO - c055 (v10) - p000 [Digital] [LuCaZ].jpg")]
public void FindFirstEntry(string[] files, string expected)
{
var foundFile = _archiveService.FirstFileEntry(files);
Assert.Equal(expected, string.IsNullOrEmpty(foundFile) ? "" : foundFile);
}
[Theory]
[InlineData("v10.cbz", "v10.expected.jpg")]
[InlineData("v10 - with folder.cbz", "v10 - with folder.expected.jpg")]
[InlineData("v10 - nested folder.cbz", "v10 - nested folder.expected.jpg")]
//[InlineData("png.zip", "png.PNG")]
[InlineData("macos_native.zip", "macos_native.jpg")]
[InlineData("v10 - duplicate covers.cbz", "v10 - duplicate covers.expected.jpg")]
[InlineData("sorting.zip", "sorting.expected.jpg")]
public void GetCoverImage_Default_Test(string inputFile, string expectedOutputFile)
{
var archiveService = Substitute.For<ArchiveService>(_logger);
var testDirectory = Path.Join(Directory.GetCurrentDirectory(), "../../../Services/Test Data/ArchiveService/CoverImages");
var expectedBytes = File.ReadAllBytes(Path.Join(testDirectory, expectedOutputFile));
archiveService.Configure().CanOpen(Path.Join(testDirectory, inputFile)).Returns(ArchiveLibrary.Default);
Stopwatch sw = Stopwatch.StartNew();
Assert.Equal(expectedBytes, archiveService.GetCoverImage(Path.Join(testDirectory, inputFile)));
_testOutputHelper.WriteLine($"Processed in {sw.ElapsedMilliseconds} ms");
}
[Theory]
[InlineData("v10.cbz", "v10.expected.jpg")]
[InlineData("v10 - with folder.cbz", "v10 - with folder.expected.jpg")]
[InlineData("v10 - nested folder.cbz", "v10 - nested folder.expected.jpg")]
//[InlineData("png.zip", "png.PNG")]
[InlineData("macos_native.zip", "macos_native.jpg")]
[InlineData("v10 - duplicate covers.cbz", "v10 - duplicate covers.expected.jpg")]
[InlineData("sorting.zip", "sorting.expected.jpg")]
public void GetCoverImage_SharpCompress_Test(string inputFile, string expectedOutputFile)
{
var archiveService = Substitute.For<ArchiveService>(_logger);
var testDirectory = Path.Join(Directory.GetCurrentDirectory(), "../../../Services/Test Data/ArchiveService/CoverImages");
var expectedBytes = File.ReadAllBytes(Path.Join(testDirectory, expectedOutputFile));
archiveService.Configure().CanOpen(Path.Join(testDirectory, inputFile)).Returns(ArchiveLibrary.SharpCompress);
Stopwatch sw = Stopwatch.StartNew();
Assert.Equal(expectedBytes, archiveService.GetCoverImage(Path.Join(testDirectory, inputFile)));
_testOutputHelper.WriteLine($"Processed in {sw.ElapsedMilliseconds} ms");
}
[Theory]
[InlineData("Archives/macos_native.zip")]
[InlineData("Formats/One File with DB_Supported.zip")]
public void CanParseCoverImage(string inputFile)
{
var testDirectory = Path.Join(Directory.GetCurrentDirectory(), "../../../Services/Test Data/ArchiveService/");
Assert.NotEmpty(_archiveService.GetCoverImage(Path.Join(testDirectory, inputFile)));
}
[Fact]
public void ShouldHaveComicInfo()
{
var testDirectory = Path.Join(Directory.GetCurrentDirectory(), "../../../Services/Test Data/ArchiveService/ComicInfos");
var archive = Path.Join(testDirectory, "file in folder.zip");
var summaryInfo = "By all counts, Ryouta Sakamoto is a loser when he's not holed up in his room, bombing things into oblivion in his favorite online action RPG. But his very own uneventful life is blown to pieces when he's abducted and taken to an uninhabited island, where he soon learns the hard way that he's being pitted against others just like him in a explosives-riddled death match! How could this be happening? Who's putting them up to this? And why!? The name, not to mention the objective, of this very real survival game is eerily familiar to Ryouta, who has mastered its virtual counterpart-BTOOOM! Can Ryouta still come out on top when he's playing for his life!?";
Assert.Equal(summaryInfo, _archiveService.GetSummaryInfo(archive));
}
}
}