Feature/parse scanned files tests (#934)

* Fixed a bug in CleanupBookmarks where the Except was deleting all files because the path separators didn't match.

* Added unit tests for ParseScannedFiles.cs.

* Fixed some unit tests. Parser will now clear out multiple spaces in a row and replace with a single.

API.Tests/Parser/ComicParserTests.cs

@@ -68,8 +68,8 @@ namespace API.Tests.Parser
         [InlineData("Demon 012 (Sep 1973) c2c", "Demon")]
         [InlineData("Dragon Age - Until We Sleep 01 (of 03)", "Dragon Age - Until We Sleep")]
         [InlineData("Green Lantern v2 017 - The Spy-Eye that doomed Green Lantern v2", "Green Lantern")]
-        [InlineData("Green Lantern - Circle of Fire Special - Adam Strange (2000)", "Green Lantern - Circle of Fire  - Adam Strange")]
+        [InlineData("Green Lantern - Circle of Fire Special - Adam Strange (2000)", "Green Lantern - Circle of Fire - Adam Strange")]
-        [InlineData("Identity Crisis Extra - Rags Morales Sketches (2005)", "Identity Crisis  - Rags Morales Sketches")]
+        [InlineData("Identity Crisis Extra - Rags Morales Sketches (2005)", "Identity Crisis - Rags Morales Sketches")]
         [InlineData("Daredevil - t6 - 10 - (2019)", "Daredevil")]
         [InlineData("Batgirl T2000 #57", "Batgirl")]
         [InlineData("Teen Titans t1 001 (1966-02) (digital) (OkC.O.M.P.U.T.O.-Novus)", "Teen Titans")]

API.Tests/Services/ParseScannedFilesTests.cs

@@ -11,6 +11,7 @@ using API.Parser;
 using API.Services;
 using API.Services.Tasks.Scanner;
 using API.SignalR;
+using API.Tests.Helpers;
 using AutoMapper;
 using Microsoft.AspNetCore.SignalR;
 using Microsoft.Data.Sqlite;
@@ -24,19 +25,26 @@ namespace API.Tests.Services;
 
 internal class MockReadingItemService : IReadingItemService
 {
+    private readonly DefaultParser _defaultParser;
+
+    public MockReadingItemService(DefaultParser defaultParser)
+    {
+        _defaultParser = defaultParser;
+    }
+
     public ComicInfo GetComicInfo(string filePath)
     {
-        throw new System.NotImplementedException();
+        return null;
     }
 
     public int GetNumberOfPages(string filePath, MangaFormat format)
     {
-        throw new System.NotImplementedException();
+        return 1;
     }
 
     public string GetCoverImage(string fileFilePath, string fileName, MangaFormat format)
     {
-        throw new System.NotImplementedException();
+        return string.Empty;
     }
 
     public void Extract(string fileFilePath, string targetDirectory, MangaFormat format, int imageCount = 1)
@@ -46,7 +54,7 @@ internal class MockReadingItemService : IReadingItemService
 
     public ParserInfo Parse(string path, string rootPath, LibraryType type)
     {
-        throw new System.NotImplementedException();
+        return _defaultParser.Parse(path, rootPath, type);
     }
 }
 
@@ -145,8 +153,88 @@ public class ParseScannedFilesTests
     #region GetInfosByName
 
     [Fact]
-    public void GetInfosByName()
+    public void GetInfosByName_ShouldReturnGivenMatchingSeriesName()
     {
+        var fileSystem = new MockFileSystem();
+        var ds = new DirectoryService(Substitute.For<ILogger<DirectoryService>>(), fileSystem);
+        var psf = new ParseScannedFiles(Substitute.For<ILogger<ParseScannedFiles>>(), ds,
+            new MockReadingItemService(new DefaultParser(ds)));
+
+        var infos = new List<ParserInfo>()
+        {
+            ParserInfoFactory.CreateParsedInfo("Accel World", "1", "0", "Accel World v1.cbz", false),
+            ParserInfoFactory.CreateParsedInfo("Accel World", "2", "0", "Accel World v2.cbz", false)
+        };
+        var parsedSeries = new Dictionary<ParsedSeries, List<ParserInfo>>
+        {
+            {
+                new ParsedSeries()
+                {
+                    Format = MangaFormat.Archive,
+                    Name = "Accel World",
+                    NormalizedName = API.Parser.Parser.Normalize("Accel World")
+                },
+                infos
+            },
+            {
+                new ParsedSeries()
+                {
+                    Format = MangaFormat.Pdf,
+                    Name = "Accel World",
+                    NormalizedName = API.Parser.Parser.Normalize("Accel World")
+                },
+                new List<ParserInfo>()
+            }
+        };
+
+        var series = DbFactory.Series("Accel World");
+        series.Format = MangaFormat.Pdf;
+
+        Assert.Empty(ParseScannedFiles.GetInfosByName(parsedSeries, series));
+
+        series.Format = MangaFormat.Archive;
+        Assert.Equal(2, ParseScannedFiles.GetInfosByName(parsedSeries, series).Count());
+
+    }
+
+    [Fact]
+    public void GetInfosByName_ShouldReturnGivenMatchingNormalizedSeriesName()
+    {
+        var fileSystem = new MockFileSystem();
+        var ds = new DirectoryService(Substitute.For<ILogger<DirectoryService>>(), fileSystem);
+        var psf = new ParseScannedFiles(Substitute.For<ILogger<ParseScannedFiles>>(), ds,
+            new MockReadingItemService(new DefaultParser(ds)));
+
+        var infos = new List<ParserInfo>()
+        {
+            ParserInfoFactory.CreateParsedInfo("Accel World", "1", "0", "Accel World v1.cbz", false),
+            ParserInfoFactory.CreateParsedInfo("Accel World", "2", "0", "Accel World v2.cbz", false)
+        };
+        var parsedSeries = new Dictionary<ParsedSeries, List<ParserInfo>>
+        {
+            {
+                new ParsedSeries()
+                {
+                    Format = MangaFormat.Archive,
+                    Name = "Accel World",
+                    NormalizedName = API.Parser.Parser.Normalize("Accel World")
+                },
+                infos
+            },
+            {
+                new ParsedSeries()
+                {
+                    Format = MangaFormat.Pdf,
+                    Name = "Accel World",
+                    NormalizedName = API.Parser.Parser.Normalize("Accel World")
+                },
+                new List<ParserInfo>()
+            }
+        };
+
+        var series = DbFactory.Series("accel world");
+        series.Format = MangaFormat.Archive;
+        Assert.Equal(2, ParseScannedFiles.GetInfosByName(parsedSeries, series).Count());
 
     }
 
@@ -155,10 +243,72 @@ public class ParseScannedFilesTests
     #region MergeName
 
     [Fact]
-    public void MergeName_()
+    public void MergeName_ShouldMergeMatchingFormatAndName()
     {
+        var fileSystem = new MockFileSystem();
+        fileSystem.AddDirectory("C:/Data/");
+        fileSystem.AddFile("C:/Data/Accel World v1.cbz", new MockFileData(string.Empty));
+        fileSystem.AddFile("C:/Data/Accel World v2.cbz", new MockFileData(string.Empty));
+        fileSystem.AddFile("C:/Data/Accel World v2.pdf", new MockFileData(string.Empty));
 
+        var ds = new DirectoryService(Substitute.For<ILogger<DirectoryService>>(), fileSystem);
+        var psf = new ParseScannedFiles(Substitute.For<ILogger<ParseScannedFiles>>(), ds,
+            new MockReadingItemService(new DefaultParser(ds)));
+
+
+        psf.ScanLibrariesForSeries(LibraryType.Manga, new List<string>() {"C:/Data/"}, out _, out _);
+
+        Assert.Equal("Accel World", psf.MergeName(ParserInfoFactory.CreateParsedInfo("Accel World", "1", "0", "Accel World v1.cbz", false)));
+        Assert.Equal("Accel World", psf.MergeName(ParserInfoFactory.CreateParsedInfo("accel_world", "1", "0", "Accel World v1.cbz", false)));
+        Assert.Equal("Accel World", psf.MergeName(ParserInfoFactory.CreateParsedInfo("accelworld", "1", "0", "Accel World v1.cbz", false)));
+    }
+
+    [Fact]
+    public void MergeName_ShouldMerge_MismatchedFormatSameName()
+    {
+        var fileSystem = new MockFileSystem();
+        fileSystem.AddDirectory("C:/Data/");
+        fileSystem.AddFile("C:/Data/Accel World v1.cbz", new MockFileData(string.Empty));
+        fileSystem.AddFile("C:/Data/Accel World v2.cbz", new MockFileData(string.Empty));
+        fileSystem.AddFile("C:/Data/Accel World v2.pdf", new MockFileData(string.Empty));
+
+        var ds = new DirectoryService(Substitute.For<ILogger<DirectoryService>>(), fileSystem);
+        var psf = new ParseScannedFiles(Substitute.For<ILogger<ParseScannedFiles>>(), ds,
+            new MockReadingItemService(new DefaultParser(ds)));
+
+
+        psf.ScanLibrariesForSeries(LibraryType.Manga, new List<string>() {"C:/Data/"}, out _, out _);
+
+        Assert.Equal("Accel World", psf.MergeName(ParserInfoFactory.CreateParsedInfo("Accel World", "1", "0", "Accel World v1.epub", false)));
+        Assert.Equal("Accel World", psf.MergeName(ParserInfoFactory.CreateParsedInfo("accel_world", "1", "0", "Accel World v1.epub", false)));
     }
 
+    #endregion
+
+    #region ScanLibrariesForSeries
+
+    [Fact]
+    public void ScanLibrariesForSeries_ShouldFindFiles()
+    {
+        var fileSystem = new MockFileSystem();
+        fileSystem.AddDirectory("C:/Data/");
+        fileSystem.AddFile("C:/Data/Accel World v1.cbz", new MockFileData(string.Empty));
+        fileSystem.AddFile("C:/Data/Accel World v2.cbz", new MockFileData(string.Empty));
+        fileSystem.AddFile("C:/Data/Accel World v2.pdf", new MockFileData(string.Empty));
+        fileSystem.AddFile("C:/Data/Nothing.pdf", new MockFileData(string.Empty));
+
+        var ds = new DirectoryService(Substitute.For<ILogger<DirectoryService>>(), fileSystem);
+        var psf = new ParseScannedFiles(Substitute.For<ILogger<ParseScannedFiles>>(), ds,
+            new MockReadingItemService(new DefaultParser(ds)));
+
+
+        var parsedSeries = psf.ScanLibrariesForSeries(LibraryType.Manga, new List<string>() {"C:/Data/"}, out _, out _);
+
+        Assert.Equal(3, parsedSeries.Values.Count);
+        Assert.NotEmpty(parsedSeries.Keys.Where(p => p.Format == MangaFormat.Archive && p.Name.Equals("Accel World")));
+
+    }
+
+
     #endregion
 }

API/Parser/Parser.cs

@@ -502,6 +502,11 @@ namespace API.Parser
                 MatchOptions, RegexTimeout
         );
 
+        private static readonly Regex EmptySpaceRegex = new Regex(
+                @"(?!=.+)(\s{2,})(?!=.+)",
+                MatchOptions, RegexTimeout
+        );
+
         public static MangaFormat ParseFormat(string filePath)
         {
             if (IsArchive(filePath)) return MangaFormat.Archive;
@@ -841,6 +846,8 @@ namespace API.Parser
                 title = title.Substring(1);
             }
 
+            title = EmptySpaceRegex.Replace(title, " ");
+
             return title.Trim();
         }
 

API/Services/Tasks/Scanner/ParseScannedFiles.cs

@@ -4,7 +4,6 @@ using System.Collections.Generic;
 using System.Diagnostics;
 using System.IO;
 using System.Linq;
-using API.Data.Metadata;
 using API.Entities;
 using API.Entities.Enums;
 using API.Parser;
@@ -151,7 +150,7 @@ namespace API.Services.Tasks.Scanner
         /// same normalized name, it merges into the existing one. This is important as some manga may have a slight difference with punctuation or capitalization.
         /// </summary>
         /// <param name="info"></param>
-        /// <returns></returns>
+        /// <returns>Series Name to group this info into</returns>
         public string MergeName(ParserInfo info)
         {
             var normalizedSeries = Parser.Parser.Normalize(info.Series);
@@ -179,7 +178,6 @@ namespace API.Services.Tasks.Scanner
         {
             var sw = Stopwatch.StartNew();
             totalFiles = 0;
-            var searchPattern = Parser.Parser.SupportedExtensions;
             foreach (var folderPath in folders)
             {
                 try
@@ -194,7 +192,7 @@ namespace API.Services.Tasks.Scanner
                         {
                             _logger.LogError(exception, "The file {Filename} could not be found", f);
                         }
-                    }, searchPattern, _logger);
+                    }, Parser.Parser.SupportedExtensions, _logger);
                 }
                 catch (ArgumentException ex)
                 {