A boatload of Bugs (#3704)

Co-authored-by: Amelia <77553571+Fesaa@users.noreply.github.com>

API/Services/Tasks/CleanupService.cs

@@ -8,8 +8,10 @@ using API.DTOs.Filtering;
 using API.Entities;
 using API.Entities.Enums;
 using API.Helpers;
+using API.Services.Tasks.Scanner.Parser;
 using API.SignalR;
 using Hangfire;
+using Microsoft.EntityFrameworkCore;
 using Microsoft.Extensions.Logging;
 
 namespace API.Services.Tasks;
@@ -35,6 +37,9 @@ public interface ICleanupService
     Task CleanupWantToRead();
 
     Task ConsolidateProgress();
+
+    Task CleanupMediaErrors();
+
 }
 /// <summary>
 /// Cleans up after operations on reoccurring basis
@@ -88,9 +93,11 @@ public class CleanupService : ICleanupService
         await CleanupBackups();
 
         await SendProgress(0.35F, "Consolidating Progress Events");
-        _logger.LogInformation("Consolidating Progress Events");
         await ConsolidateProgress();
 
+        await SendProgress(0.4F, "Consolidating Media Errors");
+        await CleanupMediaErrors();
+
         await SendProgress(0.50F, "Cleaning deleted cover images");
         _logger.LogInformation("Cleaning deleted cover images");
         await DeleteSeriesCoverImages();
@@ -241,6 +248,7 @@ public class CleanupService : ICleanupService
     /// </summary>
     public async Task ConsolidateProgress()
     {
+        _logger.LogInformation("Consolidating Progress Events");
         // AppUserProgress
         var allProgress = await _unitOfWork.AppUserProgressRepository.GetAllProgress();
 
@@ -291,6 +299,52 @@ public class CleanupService : ICleanupService
         await _unitOfWork.CommitAsync();
     }
 
+    /// <summary>
+    /// Scans through Media Error and removes any entries that have been fixed and are within the DB (proper files where wordcount/pagecount > 0)
+    /// </summary>
+    public async Task CleanupMediaErrors()
+    {
+        try
+        {
+            List<string> errorStrings = ["This archive cannot be read or not supported", "File format not supported"];
+            var mediaErrors = await _unitOfWork.MediaErrorRepository.GetAllErrorsAsync(errorStrings);
+            _logger.LogInformation("Beginning consolidation of {Count} Media Errors", mediaErrors.Count);
+
+            var pathToErrorMap = mediaErrors
+                .GroupBy(me => Parser.NormalizePath(me.FilePath))
+                .ToDictionary(
+                    group => group.Key,
+                    group => group.ToList() // The same file can be duplicated (rare issue when network drives die out midscan)
+                );
+
+            var normalizedPaths = pathToErrorMap.Keys.ToList();
+
+            // Find all files that are valid
+            var validFiles = await _unitOfWork.DataContext.MangaFile
+                .Where(f => normalizedPaths.Contains(f.FilePath) && f.Pages > 0)
+                .Select(f => f.FilePath)
+                .ToListAsync();
+
+            var removalCount = 0;
+            foreach (var validFilePath in validFiles)
+            {
+                if (!pathToErrorMap.TryGetValue(validFilePath, out var mediaError)) continue;
+
+                _unitOfWork.MediaErrorRepository.Remove(mediaError);
+                removalCount++;
+            }
+
+            await _unitOfWork.CommitAsync();
+
+            _logger.LogInformation("Finished consolidation of {Count} Media Errors, Removed: {RemovalCount}",
+                mediaErrors.Count, removalCount);
+        }
+        catch (Exception ex)
+        {
+            _logger.LogError(ex, "There was an exception consolidating media errors");
+        }
+    }
+
     public async Task CleanupLogs()
     {
         _logger.LogInformation("Performing cleanup of logs directory");

API/Services/Tasks/Metadata/WordCountAnalyzerService.cs

@@ -179,7 +179,7 @@ public class WordCountAnalyzerService : IWordCountAnalyzerService
                         var pageCounter = 1;
                         try
                         {
-                            using var book = await EpubReader.OpenBookAsync(filePath, BookService.BookReaderOptions);
+                            using var book = await EpubReader.OpenBookAsync(filePath, BookService.LenientBookReaderOptions);
 
                             var totalPages = book.Content.Html.Local;
                             foreach (var bookPage in totalPages)

API/Services/Tasks/Scanner/Parser/DefaultParser.cs

@@ -130,9 +130,9 @@ public abstract class DefaultParser(IDirectoryService directoryService) : IDefau
         }
 
         // Patch is SeriesSort from ComicInfo
-        if (!string.IsNullOrEmpty(info.ComicInfo.TitleSort))
+        if (!string.IsNullOrEmpty(info.ComicInfo.SeriesSort))
         {
-            info.SeriesSort = info.ComicInfo.TitleSort.Trim();
+            info.SeriesSort = info.ComicInfo.SeriesSort.Trim();
         }
 
     }

API/Services/Tasks/Scanner/Parser/Parser.cs

@@ -167,7 +167,7 @@ public static partial class Parser
             MatchOptions, RegexTimeout),
         // Korean Volume: 제n화|권|회|장 -> Volume n, n화|권|회|장 -> Volume n, 63권#200.zip -> Volume 63 (no chapter, #200 is just files inside)
         new Regex(
-            @"제?(?<Volume>\d+(\.\d)?)(권|회|화|장)",
+            @"제?(?<Volume>\d+(\.\d+)?)(권|회|화|장)",
             MatchOptions, RegexTimeout),
         // Korean Season: 시즌n -> Season n,
         new Regex(

API/Services/Tasks/ScannerService.cs

@@ -161,7 +161,7 @@ public class ScannerService : IScannerService
         {
             if (TaskScheduler.HasScanTaskRunningForSeries(series.Id))
             {
-                _logger.LogDebug("[ScannerService] Scan folder invoked for {Folder} but a task is already queued for this series. Dropping request", folder);
+                _logger.LogTrace("[ScannerService] Scan folder invoked for {Folder} but a task is already queued for this series. Dropping request", folder);
                 return;
             }
 
@@ -186,7 +186,7 @@ public class ScannerService : IScannerService
         {
             if (TaskScheduler.HasScanTaskRunningForLibrary(library.Id))
             {
-                _logger.LogDebug("[ScannerService] Scan folder invoked for {Folder} but a task is already queued for this library. Dropping request", folder);
+                _logger.LogTrace("[ScannerService] Scan folder invoked for {Folder} but a task is already queued for this library. Dropping request", folder);
                 return;
             }
             BackgroundJob.Schedule(() => ScanLibrary(library.Id, false, true), TimeSpan.FromMinutes(1));