More Fixes (#1993)

* Strip just isbn: from epub isbns and log when it's back (books)

* Tweaked to allow invalid GTINs but only valid ISBN 10/13s will be saved to Kavita.

* Fixed a bug with parsing series from a filename that is just a chapter range and no chapter/volume keywords.

* Show the media issue count before you open accordion

* Added a inpage filter for Media issues

* Cleanup styles

* Fixed up some code in epub isbn parsing when it's null

* Encode filenames when downloading so that non english characters can be passed properly to UI.

* Added support to parse ComicInfo's with Empty Tags.

* Reset development settings.

* Tweaked the code in generating reading lists to avoid extra work when not needed.

* Fix comicvine's favicon

* Fixed up a unit test

* Tweaked the favicon code to ignore icons that have query parameters

* More favicon work. Expanded ability to grab icons a bit. Added in ability to not keep requesting favicons when we failed to parse already.

* Added a note for later

* Fixed stats server url

* Added more debugging

* Fixed unit tests
This commit is contained in:
Joe Milazzo 2023-05-14 18:14:27 -05:00 committed by GitHub
parent cd8fca993b
commit 25703d6fe0
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
27 changed files with 171 additions and 75 deletions

View file

@ -4,6 +4,7 @@ using System.Diagnostics;
using System.IO;
using System.IO.Compression;
using System.Linq;
using System.Xml.Linq;
using System.Xml.Serialization;
using API.Archive;
using API.Data.Metadata;
@ -372,10 +373,7 @@ public class ArchiveService : IArchiveService
if (entry != null)
{
using var stream = entry.Open();
var serializer = new XmlSerializer(typeof(ComicInfo));
var info = (ComicInfo?) serializer.Deserialize(stream);
ComicInfo.CleanComicInfo(info);
return info;
return Deserialize(stream);
}
break;
@ -390,9 +388,7 @@ public class ArchiveService : IArchiveService
if (entry != null)
{
using var stream = entry.OpenEntryStream();
var serializer = new XmlSerializer(typeof(ComicInfo));
var info = (ComicInfo?) serializer.Deserialize(stream);
ComicInfo.CleanComicInfo(info);
var info = Deserialize(stream);
return info;
}
@ -418,6 +414,28 @@ public class ArchiveService : IArchiveService
return null;
}
/// <summary>
/// Strips out empty tags before deserializing
/// </summary>
/// <param name="stream"></param>
/// <returns></returns>
private static ComicInfo? Deserialize(Stream stream)
{
var comicInfoXml = XDocument.Load(stream);
comicInfoXml.Descendants()
.Where(e => e.IsEmpty || string.IsNullOrWhiteSpace(e.Value))
.Remove();
var serializer = new XmlSerializer(typeof(ComicInfo));
using var reader = comicInfoXml.Root?.CreateReader();
if (reader == null) return null;
var info = (ComicInfo?) serializer.Deserialize(reader);
ComicInfo.CleanComicInfo(info);
return info;
}
private void ExtractArchiveEntities(IEnumerable<IArchiveEntry> entries, string extractPath)
{

View file

@ -437,8 +437,13 @@ public class BookService : IBookService
foreach (var identifier in epubBook.Schema.Package.Metadata.Identifiers.Where(id => id.Scheme.Equals("ISBN")))
{
var isbn = identifier.Identifier.Replace("urn:isbn:", string.Empty);
if (!ArticleNumberHelper.IsValidIsbn10(isbn) && !ArticleNumberHelper.IsValidIsbn13(isbn)) continue;
if (string.IsNullOrEmpty(identifier.Identifier)) continue;
var isbn = identifier.Identifier.Replace("urn:isbn:", string.Empty).Replace("isbn:", string.Empty);
if (!ArticleNumberHelper.IsValidIsbn10(isbn) && !ArticleNumberHelper.IsValidIsbn13(isbn))
{
_logger.LogDebug("[BookService] {File} has invalid ISBN number", filePath);
continue;
}
info.Isbn = isbn;
break;
}

View file

@ -1,10 +1,12 @@
using System;
using System.Collections.Concurrent;
using System.Collections.Generic;
using System.IO;
using System.Linq;
using System.Threading.Tasks;
using API.Entities.Enums;
using API.Extensions;
using EasyCaching.Core;
using Flurl;
using Flurl.Http;
using HtmlAgilityPack;
@ -63,11 +65,13 @@ public class ImageService : IImageService
public const string Name = "BookmarkService";
private readonly ILogger<ImageService> _logger;
private readonly IDirectoryService _directoryService;
private readonly IEasyCachingProviderFactory _cacheFactory;
public const string ChapterCoverImageRegex = @"v\d+_c\d+";
public const string SeriesCoverImageRegex = @"series\d+";
public const string CollectionTagCoverImageRegex = @"tag\d+";
public const string ReadingListCoverImageRegex = @"readinglist\d+";
/// <summary>
/// Width of the Thumbnail generation
/// </summary>
@ -80,7 +84,8 @@ public class ImageService : IImageService
private static readonly string[] ValidIconRelations = {
"icon",
"apple-touch-icon",
"apple-touch-icon-precomposed"
"apple-touch-icon-precomposed",
"apple-touch-icon icon-precomposed" // ComicVine has it combined
};
/// <summary>
@ -91,10 +96,11 @@ public class ImageService : IImageService
["https://app.plex.tv"] = "https://plex.tv"
};
public ImageService(ILogger<ImageService> logger, IDirectoryService directoryService)
public ImageService(ILogger<ImageService> logger, IDirectoryService directoryService, IEasyCachingProviderFactory cacheFactory)
{
_logger = logger;
_directoryService = directoryService;
_cacheFactory = cacheFactory;
}
public void ExtractImages(string? fileFilePath, string targetDirectory, int fileCount = 1)
@ -207,6 +213,15 @@ public class ImageService : IImageService
var baseUrl = uri.Scheme + "://" + uri.Host;
var provider = _cacheFactory.GetCachingProvider("favicon");
var res = await provider.GetAsync<string>(baseUrl);
if (res.HasValue)
{
_logger.LogInformation("Kavita has already tried to fetch from {BaseUrl} and failed. Skipping duplicate check", baseUrl);
throw new KavitaException($"Kavita has already tried to fetch from {baseUrl} and failed. Skipping duplicate check");
}
await provider.SetAsync(baseUrl, string.Empty, TimeSpan.FromDays(10));
if (FaviconUrlMapper.TryGetValue(baseUrl, out var value))
{
url = value;
@ -220,7 +235,7 @@ public class ImageService : IImageService
var pngLinks = htmlDocument.DocumentNode.Descendants("link")
.Where(link => ValidIconRelations.Contains(link.GetAttributeValue("rel", string.Empty)))
.Select(link => link.GetAttributeValue("href", string.Empty))
.Where(href => href.EndsWith(".png") || href.EndsWith(".PNG"))
.Where(href => href.Split("?")[0].EndsWith(".png", StringComparison.InvariantCultureIgnoreCase))
.ToList();
if (pngLinks == null)
@ -234,7 +249,13 @@ public class ImageService : IImageService
}
var finalUrl = correctSizeLink;
if (!correctSizeLink.StartsWith(uri.Scheme))
// If starts with //, it's coming usually from an offsite cdn
if (correctSizeLink.StartsWith("//"))
{
finalUrl = Url.Combine("https:", correctSizeLink);
}
else if (!correctSizeLink.StartsWith(uri.Scheme))
{
finalUrl = Url.Combine(baseUrl, correctSizeLink);
}
@ -269,7 +290,7 @@ public class ImageService : IImageService
}
catch (Exception ex)
{
_logger.LogError(ex, "Error downloading favicon.png for ${Domain}", domain);
_logger.LogError(ex, "Error downloading favicon.png for {Domain}", domain);
throw;
}
}

View file

@ -496,12 +496,13 @@ public class ReadingListService : IReadingListService
}
readingList.Items = items;
if (!_unitOfWork.HasChanges()) continue;
await CalculateReadingListAgeRating(readingList);
if (_unitOfWork.HasChanges())
{
await _unitOfWork.CommitAsync();
}
await CalculateStartAndEndDates(await _unitOfWork.ReadingListRepository.GetReadingListByTitleAsync(arcPair.Item1, user.Id, ReadingListIncludes.Items | ReadingListIncludes.ItemChapter));
await _unitOfWork.CommitAsync(); // TODO: See if we can avoid this extra commit by reworking bottom logic
await CalculateStartAndEndDates(await _unitOfWork.ReadingListRepository.GetReadingListByTitleAsync(arcPair.Item1,
user.Id, ReadingListIncludes.Items | ReadingListIncludes.ItemChapter));
await _unitOfWork.CommitAsync();
}
}

View file

@ -321,13 +321,9 @@ public static class Parser
new Regex(
@"(?<Series>.*)( ?- ?)Ch\.\d+-?\d*",
MatchOptions, RegexTimeout),
// [BAA]_Darker_than_Black_Omake-1.zip
// [BAA]_Darker_than_Black_Omake-1, Bleach 001-002, Kodoja #001 (March 2016)
new Regex(
@"^(?!Vol)(?<Series>.*)(-)\d+-?\d*", // This catches a lot of stuff ^(?!Vol)(?<Series>.*)( |_)(\d+)
MatchOptions, RegexTimeout),
// Kodoja #001 (March 2016)
new Regex(
@"(?<Series>.*)(\s|_|-)#",
@"^(?!Vol)(?!Chapter)(?<Series>.+?)(-|_|\s|#)\d+(-\d+)?",
MatchOptions, RegexTimeout),
// Baketeriya ch01-05.zip, Akiiro Bousou Biyori - 01.jpg, Beelzebub_172_RHS.zip, Cynthia the Mission 29.rar, A Compendium of Ghosts - 031 - The Third Story_ Part 12 (Digital) (Cobalt001)
new Regex(

View file

@ -346,6 +346,8 @@ public class ProcessSeries : IProcessSeries
}
#region People
// Handle People
foreach (var chapter in chapters)
{
@ -490,6 +492,8 @@ public class ProcessSeries : IProcessSeries
}
});
#endregion
}
public void UpdateVolumes(Series series, IList<ParserInfo> parsedInfos, bool forceUpdate = false)

View file

@ -34,7 +34,7 @@ public class StatsService : IStatsService
private readonly IUnitOfWork _unitOfWork;
private readonly DataContext _context;
private readonly IStatisticService _statisticService;
private const string ApiUrl = "http://localhost:5003";
private const string ApiUrl = "https://stats.kavitareader.com";
public StatsService(ILogger<StatsService> logger, IUnitOfWork unitOfWork, DataContext context, IStatisticService statisticService)
{

View file

@ -90,12 +90,12 @@ public class TokenService : ITokenService
Token = await CreateToken(user),
RefreshToken = await CreateRefreshToken(user)
};
} catch (SecurityTokenExpiredException)
} catch (SecurityTokenExpiredException ex)
{
// Handle expired token
return null;
}
catch (Exception)
catch (Exception ex)
{
// Handle other exceptions
return null;