PDF Support + MORE!!!! (#416)
# Added - Added support for PDFs within Kavita. PDFs will open in the Manga reader and you can read through them as images. PDFs are heavier than archives, so they may take longer to open for reading. (Fixes #187) # Changed - Changed: Major change in how Kavita libraries work. Kavita libraries will now allow for mixed media types, that means you can have raw images, archives, epubs, and pdfs all within your Manga library. In the case that the same Series exists between 2 different types of medias, they will be separated and an icon will show to help you identify the types. The correct reader will open regardless of what library you are on. Note: Nightly users need to delete their Raw Images libraries before updating. # Fixed - Fixed: Fixed an issue where checking if a file was modified since last scan always returned true, meaning we would do more I/O than was needed (Fixes #415) - Fixed: There wasn't enough spacing on the top menu bar on the Manga reader - Fixed: Fixed a bug where user preferences dark mode control always showed true, even if you were not using dark mode # Dev stuff - For image extraction, if there is only 1 image we will extract just that, else we will extract only images - Refactored all the Parser code out of the ScannerService into a self contained class. The class should be created for any scans, allowing multiple tasks to run without any chance of cross over. * Fixed indentation for cs files * Fixed an issue where the logic for if a file had been modified or not was not working and always saying modified, meaning we were doing more file I/O than needed. * Implemented the ability to have PDF books. No reader functionality. * Implemented a basic form of scanning for PDF files. Reworked Image based libraries to remove the need to separate in a special library and instead just work within the Manga/Comic library. * Removed the old library types. * Removed some extra code around old raw library types * Fully implemented PDF support into Kavita by using docnet. Removed old libraries we tried that did not work. PDFs take about 200ms to save the file to disk, so they are much slower than reading archives. * Refactored Libraries so that they can have any file extension and the UI will decide which reader to use. * Reworked the Series Parsing code. We now use a separate instance for each task call, so there should be no cross over if 2 tasks are running at the same time. Second, we now store Format with the Series, so we can have duplicate Series with the same name, but a different type of files underneath. * Fixed PDF transparency issues - Used this code to fix an issue when a PDF page doesn't have a background. https://github.com/GowenGit/docnet/issues/8#issuecomment-538985672 - This also fixes the same issue for cover images * Fixed an issue where if a raw image was in a directory with non-image files, those would get moved to cache when trying to open the file. * For image extraction, if there is only 1 image, just copy that to cache instead of everything else in the directory that is an image. * Add some spacing to the top menu bar * Added an icon to the card to showcase the type of file * Added a tag badge to the series detail page * Fixed a bug in user preferences where dark mode control would default to true, even if you weren't on it * Fixed some tests up * Some code smells Co-authored-by: Robbie Davis <robbie@therobbiedavis.com>
This commit is contained in:
Joseph Milazzo
GitHub
parent
b8165b311c
commit
b0df67cdda
43 changed files with 1725 additions and 577 deletions
|
|
@ -1,7 +1,10 @@
|
|||
using System;
|
||||
using System.Collections.Generic;
|
||||
using System.Drawing;
|
||||
using System.Drawing.Imaging;
|
||||
using System.IO;
|
||||
using System.Linq;
|
||||
using System.Runtime.InteropServices;
|
||||
using System.Text;
|
||||
using System.Text.RegularExpressions;
|
||||
using System.Threading.Tasks;
|
||||
|
|
@ -9,11 +12,14 @@ using System.Web;
|
|||
using API.Entities.Enums;
|
||||
using API.Interfaces.Services;
|
||||
using API.Parser;
|
||||
using Docnet.Core;
|
||||
using Docnet.Core.Models;
|
||||
using ExCSS;
|
||||
using HtmlAgilityPack;
|
||||
using Microsoft.Extensions.Logging;
|
||||
using NetVips;
|
||||
using VersOne.Epub;
|
||||
using Image = NetVips.Image;
|
||||
using Point = System.Drawing.Point;
|
||||
|
||||
namespace API.Services
|
||||
{
|
||||
|
|
@ -25,6 +31,7 @@ namespace API.Services
|
|||
public BookService(ILogger<BookService> logger)
|
||||
{
|
||||
_logger = logger;
|
||||
|
||||
}
|
||||
|
||||
private static bool HasClickableHrefPart(HtmlNode anchor)
|
||||
|
|
@ -157,7 +164,8 @@ namespace API.Services
|
|||
|
||||
public string GetSummaryInfo(string filePath)
|
||||
{
|
||||
if (!IsValidFile(filePath)) return string.Empty;
|
||||
if (!IsValidFile(filePath) || Parser.Parser.IsPdf(filePath)) return string.Empty;
|
||||
|
||||
|
||||
try
|
||||
{
|
||||
|
|
@ -182,18 +190,24 @@ namespace API.Services
|
|||
|
||||
if (Parser.Parser.IsBook(filePath)) return true;
|
||||
|
||||
_logger.LogWarning("[BookService] Book {EpubFile} is not a valid EPUB", filePath);
|
||||
_logger.LogWarning("[BookService] Book {EpubFile} is not a valid EPUB/PDF", filePath);
|
||||
return false;
|
||||
}
|
||||
|
||||
public int GetNumberOfPages(string filePath)
|
||||
{
|
||||
if (!IsValidFile(filePath) || !Parser.Parser.IsEpub(filePath)) return 0;
|
||||
if (!IsValidFile(filePath)) return 0;
|
||||
|
||||
try
|
||||
{
|
||||
using var epubBook = EpubReader.OpenBook(filePath);
|
||||
return epubBook.Content.Html.Count;
|
||||
if (Parser.Parser.IsPdf(filePath))
|
||||
{
|
||||
using var docReader = DocLib.Instance.GetDocReader(filePath, new PageDimensions(1080, 1920));
|
||||
return docReader.GetPageCount();
|
||||
}
|
||||
|
||||
using var epubBook = EpubReader.OpenBook(filePath);
|
||||
return epubBook.Content.Html.Count;
|
||||
}
|
||||
catch (Exception ex)
|
||||
{
|
||||
|
|
@ -231,14 +245,16 @@ namespace API.Services
|
|||
|
||||
/// <summary>
|
||||
/// Parses out Title from book. Chapters and Volumes will always be "0". If there is any exception reading book (malformed books)
|
||||
/// then null is returned.
|
||||
/// then null is returned. This expects only an epub file
|
||||
/// </summary>
|
||||
/// <param name="filePath"></param>
|
||||
/// <returns></returns>
|
||||
public ParserInfo ParseInfo(string filePath)
|
||||
{
|
||||
try
|
||||
{
|
||||
if (!Parser.Parser.IsEpub(filePath)) return null;
|
||||
|
||||
try
|
||||
{
|
||||
using var epubBook = EpubReader.OpenBook(filePath);
|
||||
|
||||
// If the epub has the following tags, we can group the books as Volumes
|
||||
|
|
@ -301,9 +317,9 @@ namespace API.Services
|
|||
}
|
||||
return new ParserInfo()
|
||||
{
|
||||
Chapters = "0",
|
||||
Edition = "",
|
||||
Format = MangaFormat.Book,
|
||||
Chapters = Parser.Parser.DefaultChapter,
|
||||
Edition = string.Empty,
|
||||
Format = MangaFormat.Epub,
|
||||
Filename = Path.GetFileName(filePath),
|
||||
Title = specialName,
|
||||
FullFilePath = filePath,
|
||||
|
|
@ -320,23 +336,63 @@ namespace API.Services
|
|||
|
||||
return new ParserInfo()
|
||||
{
|
||||
Chapters = "0",
|
||||
Edition = "",
|
||||
Format = MangaFormat.Book,
|
||||
Chapters = Parser.Parser.DefaultChapter,
|
||||
Edition = string.Empty,
|
||||
Format = MangaFormat.Epub,
|
||||
Filename = Path.GetFileName(filePath),
|
||||
Title = epubBook.Title,
|
||||
FullFilePath = filePath,
|
||||
IsSpecial = false,
|
||||
Series = epubBook.Title,
|
||||
Volumes = "0"
|
||||
Volumes = Parser.Parser.DefaultVolume
|
||||
};
|
||||
}
|
||||
catch (Exception ex)
|
||||
{
|
||||
_logger.LogWarning(ex, "[BookService] There was an exception when opening epub book: {FileName}", filePath);
|
||||
}
|
||||
}
|
||||
catch (Exception ex)
|
||||
{
|
||||
_logger.LogWarning(ex, "[BookService] There was an exception when opening epub book: {FileName}", filePath);
|
||||
}
|
||||
|
||||
return null;
|
||||
return null;
|
||||
}
|
||||
|
||||
private static void AddBytesToBitmap(Bitmap bmp, byte[] rawBytes)
|
||||
{
|
||||
var rect = new Rectangle(0, 0, bmp.Width, bmp.Height);
|
||||
|
||||
var bmpData = bmp.LockBits(rect, ImageLockMode.WriteOnly, bmp.PixelFormat);
|
||||
var pNative = bmpData.Scan0;
|
||||
|
||||
Marshal.Copy(rawBytes, 0, pNative, rawBytes.Length);
|
||||
bmp.UnlockBits(bmpData);
|
||||
}
|
||||
|
||||
public void ExtractPdfImages(string fileFilePath, string targetDirectory)
|
||||
{
|
||||
DirectoryService.ExistOrCreate(targetDirectory);
|
||||
|
||||
using var docReader = DocLib.Instance.GetDocReader(fileFilePath, new PageDimensions(1080, 1920));
|
||||
var pages = docReader.GetPageCount();
|
||||
for (var pageNumber = 0; pageNumber < pages; pageNumber++)
|
||||
{
|
||||
using var pageReader = docReader.GetPageReader(pageNumber);
|
||||
var rawBytes = pageReader.GetImage();
|
||||
var width = pageReader.GetPageWidth();
|
||||
var height = pageReader.GetPageHeight();
|
||||
using var doc = new Bitmap(width, height, PixelFormat.Format32bppArgb);
|
||||
using var bmp = new Bitmap(width, height, PixelFormat.Format32bppArgb);
|
||||
AddBytesToBitmap(bmp, rawBytes);
|
||||
for (int y = 0; y < bmp.Height; y++)
|
||||
{
|
||||
bmp.SetPixel(bmp.Width - 1, y, bmp.GetPixel(bmp.Width - 2, y));
|
||||
}
|
||||
var g = Graphics.FromImage(doc);
|
||||
g.FillRegion(Brushes.White, new Region(new Rectangle(0, 0, width, height)));
|
||||
g.DrawImage(bmp, new Point(0, 0));
|
||||
g.Save();
|
||||
using var stream = new MemoryStream();
|
||||
doc.Save(stream, ImageFormat.Jpeg);
|
||||
File.WriteAllBytes(Path.Combine(targetDirectory, "Page-" + pageNumber + ".png"), stream.ToArray());
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
|
@ -344,6 +400,11 @@ namespace API.Services
|
|||
{
|
||||
if (!IsValidFile(fileFilePath)) return Array.Empty<byte>();
|
||||
|
||||
if (Parser.Parser.IsPdf(fileFilePath))
|
||||
{
|
||||
return GetPdfCoverImage(fileFilePath, createThumbnail);
|
||||
}
|
||||
|
||||
using var epubBook = EpubReader.OpenBook(fileFilePath);
|
||||
|
||||
|
||||
|
|
@ -374,6 +435,50 @@ namespace API.Services
|
|||
return Array.Empty<byte>();
|
||||
}
|
||||
|
||||
private byte[] GetPdfCoverImage(string fileFilePath, bool createThumbnail)
|
||||
{
|
||||
try
|
||||
{
|
||||
using var docReader = DocLib.Instance.GetDocReader(fileFilePath, new PageDimensions(1080, 1920));
|
||||
if (docReader.GetPageCount() == 0) return Array.Empty<byte>();
|
||||
|
||||
using var pageReader = docReader.GetPageReader(0);
|
||||
var rawBytes = pageReader.GetImage();
|
||||
var width = pageReader.GetPageWidth();
|
||||
var height = pageReader.GetPageHeight();
|
||||
using var doc = new Bitmap(width, height, PixelFormat.Format32bppArgb);
|
||||
using var bmp = new Bitmap(width, height, PixelFormat.Format32bppArgb);
|
||||
AddBytesToBitmap(bmp, rawBytes);
|
||||
for (int y = 0; y < bmp.Height; y++)
|
||||
{
|
||||
bmp.SetPixel(bmp.Width - 1, y, bmp.GetPixel(bmp.Width - 2, y));
|
||||
}
|
||||
var g = Graphics.FromImage(doc);
|
||||
g.FillRegion(Brushes.White, new Region(new Rectangle(0, 0, width, height)));
|
||||
g.DrawImage(bmp, new Point(0, 0));
|
||||
g.Save();
|
||||
using var stream = new MemoryStream();
|
||||
doc.Save(stream, ImageFormat.Jpeg);
|
||||
stream.Seek(0, SeekOrigin.Begin);
|
||||
|
||||
if (createThumbnail)
|
||||
{
|
||||
using var thumbnail = Image.ThumbnailStream(stream, MetadataService.ThumbnailWidth);
|
||||
return thumbnail.WriteToBuffer(".png");
|
||||
}
|
||||
|
||||
return stream.ToArray();
|
||||
}
|
||||
catch (Exception ex)
|
||||
{
|
||||
_logger.LogWarning(ex,
|
||||
"[BookService] There was a critical error and prevented thumbnail generation on {BookFile}. Defaulting to no cover image",
|
||||
fileFilePath);
|
||||
}
|
||||
|
||||
return Array.Empty<byte>();
|
||||
}
|
||||
|
||||
private static string RemoveWhiteSpaceFromStylesheets(string body)
|
||||
{
|
||||
body = Regex.Replace(body, @"[a-zA-Z]+#", "#");
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue