mirror of
https://github.com/Kareadita/Kavita.git
synced 2025-12-11 07:35:16 -05:00
* Bump versions by dotnet-bump-version. * Bump versions by dotnet-bump-version. * Workflow updates (#658) # Added - Added: Added automatic character parsing for discord notifier. Now if the PR is over a certain character limit, it will trim and add an appropriate link to the full changelog. (Release for Stable, PR for Dev) # Removed - Removed: Removed Sentry map task from the workflow since Sentry is no longer used. * Bump versions by dotnet-bump-version. * Misc Updates (#665) * Do not allow non-admins to change their passwords when authentication is disabled * Clean up the login page so that input field text is black * cleanup some resizing when typing a password and having a lot of users * Changed the LastActive for a user to not just be login, but also when they open an already authenticated session. * Bump versions by dotnet-bump-version. * Logging Cleanup (#668) * Do not allow non-admins to change their passwords when authentication is disabled * Clean up the login page so that input field text is black * cleanup some resizing when typing a password and having a lot of users * Changed the LastActive for a user to not just be login, but also when they open an already authenticated session. * Removed some verbose debugging statements and moved some debug to information to be more prevelant to logs for default installs. * In Progress now sends progress information on the Series * Add ability to add cards to recently added when new series are added in backend * Implemented the ability to click the glasses icon to turn off incognito mode from within the reader so you can start tracking progress * Don't warn the user about authentication when they don't touch that control * Bump versions by dotnet-bump-version. * Changed the stats that are sent back to stat server from installed server. * Revert "Changed the stats that are sent back to stat server from installed server." This reverts commit 644cb6d1f67de9531ea1a1dfd3853709e0329ce7. * Bump versions by dotnet-bump-version. * Bump versions by dotnet-bump-version. * Bulk Add to Collection (#674) * Fixed the typeahead not having the same size input box as other inputs * Implemented the ability to add multiple series to a collection through bulk operations flow. Updated book parser to handle "@import url('...');" syntax as well as @import '...'; * Implemented the ability to create a new Collection tag via bulk operations flow. * Bump versions by dotnet-bump-version. * Bulk Operations for In Progress and Recently Added (#677) * Don't log a message about bad match if the file is a cover image * Enable bulk operations for In Progress and Recently Added * Fixed a bad logic case * Bump versions by dotnet-bump-version. * Regression Fix (#680) * Ensure we mount the backups directory for Docker users * Fixed a huge logic bug that deleted files in users libraries * Bump versions by dotnet-bump-version. * Change chunk size to be a fixed 50 to validate if it's causing issue with refresh. Added some try catches to see if exceptions are causing issues. (#681) * Bump versions by dotnet-bump-version. * Fixed a bug where searching on localized name would fail to show on the search. Fixed a bug where extra spaces would cause the search results not to show properly. (#682) * Bump versions by dotnet-bump-version. * When we have a special marker, ensure we fall back to folder parsing to try and group correctly to the actual series before just accepting what we parsed. (#684) Fixed a missed parsing case where comic special parsing wasn't being called on comic libraries. * Bump versions by dotnet-bump-version. * iOS Admin page dropdown fix (#686) # Fixed: - Fixed: Fixed an issue where the dropdown on the admin server page would not work on Safari or other iOS browsers. * When the DB fails to save, log out all the series the user should look into for constraint issues and push a message to the admins connected to webui. (#687) * Bump versions by dotnet-bump-version. * Bump versions by dotnet-bump-version. * Stat upload will now schedule itself between midnight and 6am in server time for upload. (#688) * Bump versions by dotnet-bump-version. * EPUB CSS Parsing Issues (#690) * WIP. Rewrote some of the Regex to better support css escaping. We now escape background-image, border-image, and list-style-image within css files. * Added position relative to help with positioning on books that are just absolute positioned elements. * When there is absolute positioning, like in some epub based comics, supress the bottom action bar since it wont render in the correct location. * Fixed tests * Commented out tests * Bump versions by dotnet-bump-version. * More EPUB Scoping Fixes (#691) * Added better handling around when importing css files that are empty. Moved comment removal on css files to before some css whitespace cleanup to get better matches. * Some enhancements on the checks to see if we need the bottom action bar on reader. Now we don't query DOM and have something that works more reliably. * Bump versions by dotnet-bump-version. * Fixed an issue where docker users were not properly backing up the database. Removed an empty File for when covers/ had nothing in it. (#692) * Bump versions by dotnet-bump-version. * Fallback to Folder Parsing Issue (#694) * Fixed a bug in the scanner where we fall back to parsing from folders for poorly named files. The code was exiting early if a chapter or volume could be parsed out. * Fixed a unit test by tweaking a regex for fallback * Bump versions by dotnet-bump-version. * KavitaStats Cleanup (#695) * Refactored Stats code to be much cleaner and user better naming. * Cleaned up the actual http code to use Flurl and to return if the upload was successful or not so we can delete the file where appropriate. * More refactoring for the stats code to clean it up and keep it consistent with our standards. * Removed a confusing log statement * Added support for old api key header from original stat server * Use the correct endpoint, not the new one. * Code smell * Bump versions by dotnet-bump-version. * Bulk Deletion (#697) * Implemented bulk deletion of series * Don't show unauthorized exception on UI, just redirect to the login page. * Bump versions by dotnet-bump-version. * Cover Image Picking + Forwarding Headers with EPUBs (#700) * Ensure Kavita knows about forwarding headers (fixes issue with epub urls not going through https with reverse proxy). Fixed a case where cover image selection preferred nested folders vs files in root directory. * Fixed broken unit test * Added bug that I fixed to the unit tests * Cover Image Picking + Forwarding Headers with EPUBs (#702) * Updating GA Bump version temporarily for fix (#703) * Bump versions by dotnet-bump-version. * Cover Image Picking + Forwarding Headers with EPUBs (GA Fix) (#704) * Bump versions by dotnet-bump-version. * Vacation Fixes (#709) * Ignore system and hidden folders when performing directory scan. * Fixed the comic parser tests not using Comic mode for parsing. * Accept all forwarded headers and use them. * Ignore some changes from another branch * Bump versions by dotnet-bump-version. * Breaking Changes: Docker Parity (#698) * Refactored all the config files for Kavita to be loaded from config/. This will allow docker to just mount one folder and for Update functionality to be trivial. * Cleaned up documentation around new update method. * Updated docker files to support config directory * Removed entrypoint, no longer needed * Update appsettings to point to config directory for logs * Updated message for docker users that are upgrading * Ensure that docker users that have not updated their mount points from upgrade cannot start the server * Code smells * More cleanup * Added entrypoint to fix bind mount issues * Updated README with new folder structure * Fixed build system for new setup * Updated string path if user is docker * Updated the migration flow for docker to work properly and Fixed LogFile configuration updating. * Migrating docker images is now working 100% * Fixed config from bad code * Code cleanup Co-authored-by: Chris Plaatjes <kizaing@gmail.com> * Bump versions by dotnet-bump-version. * Feature/docker parity (#714) * Refactored all the config files for Kavita to be loaded from config/. This will allow docker to just mount one folder and for Update functionality to be trivial. * Cleaned up documentation around new update method. * Updated docker files to support config directory * Removed entrypoint, no longer needed * Update appsettings to point to config directory for logs * Updated message for docker users that are upgrading * Ensure that docker users that have not updated their mount points from upgrade cannot start the server * Code smells * More cleanup * Added entrypoint to fix bind mount issues * Updated README with new folder structure * Fixed build system for new setup * Updated string path if user is docker * Updated the migration flow for docker to work properly and Fixed LogFile configuration updating. * Migrating docker images is now working 100% * Fixed config from bad code * Code cleanup * Fixed monorepo-build.sh Co-authored-by: Chris Plaatjes <kizaing@gmail.com> * Breaking Changes: Docker Parity (#715) * Fixed a bug in the copy directory to directory in the migration * Somehow GetFiles lost static modifier. * Bump versions by dotnet-bump-version. * Build issue (#716) * Fixed a bug in the copy directory to directory in the migration * Somehow GetFiles lost static modifier. * Please work * Bump versions by dotnet-bump-version. * Bump versions by dotnet-bump-version. * Shakeout Changes (#717) * Make the appsettings public on Configuration and change how we detect when to migrate for non-docker users. * Fixed up non-docker copy command and removed duplicate check on source directory for a copy. * Don't delete files unless we know we are successful * Bump versions by dotnet-bump-version. * Fixed a migration issue on docker happening too many times or throwing exception when source wasn't there. (#719) * Bump versions by dotnet-bump-version. * Version bump for release (#718) * Bump versions by dotnet-bump-version. Co-authored-by: Robbie Davis <robbie@therobbiedavis.com> Co-authored-by: YEGCSharpDev <89283498+YEGCSharpDev@users.noreply.github.com> Co-authored-by: Chris Plaatjes <kizaing@gmail.com>
541 lines
21 KiB
C#
541 lines
21 KiB
C#
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;
|
|
using System.Web;
|
|
using API.Data.Metadata;
|
|
using API.Entities.Enums;
|
|
using API.Interfaces.Services;
|
|
using API.Parser;
|
|
using Docnet.Core;
|
|
using Docnet.Core.Converters;
|
|
using Docnet.Core.Models;
|
|
using Docnet.Core.Readers;
|
|
using ExCSS;
|
|
using HtmlAgilityPack;
|
|
using Microsoft.Extensions.Logging;
|
|
using Microsoft.IO;
|
|
using VersOne.Epub;
|
|
|
|
namespace API.Services
|
|
{
|
|
public class BookService : IBookService
|
|
{
|
|
private readonly ILogger<BookService> _logger;
|
|
private readonly StylesheetParser _cssParser = new ();
|
|
private static readonly RecyclableMemoryStreamManager StreamManager = new ();
|
|
|
|
public BookService(ILogger<BookService> logger)
|
|
{
|
|
_logger = logger;
|
|
|
|
}
|
|
|
|
private static bool HasClickableHrefPart(HtmlNode anchor)
|
|
{
|
|
return anchor.GetAttributeValue("href", string.Empty).Contains("#")
|
|
&& anchor.GetAttributeValue("tabindex", string.Empty) != "-1"
|
|
&& anchor.GetAttributeValue("role", string.Empty) != "presentation";
|
|
}
|
|
|
|
public static string GetContentType(EpubContentType type)
|
|
{
|
|
string contentType;
|
|
switch (type)
|
|
{
|
|
case EpubContentType.IMAGE_GIF:
|
|
contentType = "image/gif";
|
|
break;
|
|
case EpubContentType.IMAGE_PNG:
|
|
contentType = "image/png";
|
|
break;
|
|
case EpubContentType.IMAGE_JPEG:
|
|
contentType = "image/jpeg";
|
|
break;
|
|
case EpubContentType.FONT_OPENTYPE:
|
|
contentType = "font/otf";
|
|
break;
|
|
case EpubContentType.FONT_TRUETYPE:
|
|
contentType = "font/ttf";
|
|
break;
|
|
case EpubContentType.IMAGE_SVG:
|
|
contentType = "image/svg+xml";
|
|
break;
|
|
default:
|
|
contentType = "application/octet-stream";
|
|
break;
|
|
}
|
|
|
|
return contentType;
|
|
}
|
|
|
|
public static void UpdateLinks(HtmlNode anchor, Dictionary<string, int> mappings, int currentPage)
|
|
{
|
|
if (anchor.Name != "a") return;
|
|
var hrefParts = CleanContentKeys(anchor.GetAttributeValue("href", string.Empty))
|
|
.Split("#");
|
|
// Some keys get uri encoded when parsed, so replace any of those characters with original
|
|
var mappingKey = HttpUtility.UrlDecode(hrefParts[0]);
|
|
|
|
if (!mappings.ContainsKey(mappingKey))
|
|
{
|
|
if (HasClickableHrefPart(anchor))
|
|
{
|
|
var part = hrefParts.Length > 1
|
|
? hrefParts[1]
|
|
: anchor.GetAttributeValue("href", string.Empty);
|
|
anchor.Attributes.Add("kavita-page", $"{currentPage}");
|
|
anchor.Attributes.Add("kavita-part", part);
|
|
anchor.Attributes.Remove("href");
|
|
anchor.Attributes.Add("href", "javascript:void(0)");
|
|
}
|
|
else
|
|
{
|
|
anchor.Attributes.Add("target", "_blank");
|
|
anchor.Attributes.Add("rel", "noreferrer noopener");
|
|
}
|
|
|
|
return;
|
|
}
|
|
|
|
var mappedPage = mappings[mappingKey];
|
|
anchor.Attributes.Add("kavita-page", $"{mappedPage}");
|
|
if (hrefParts.Length > 1)
|
|
{
|
|
anchor.Attributes.Add("kavita-part",
|
|
hrefParts[1]);
|
|
}
|
|
|
|
anchor.Attributes.Remove("href");
|
|
anchor.Attributes.Add("href", "javascript:void(0)");
|
|
}
|
|
|
|
public async Task<string> ScopeStyles(string stylesheetHtml, string apiBase, string filename, EpubBookRef book)
|
|
{
|
|
// @Import statements will be handled by browser, so we must inline the css into the original file that request it, so they can be
|
|
// Scoped
|
|
var prepend = filename.Length > 0 ? filename.Replace(Path.GetFileName(filename), "") : string.Empty;
|
|
var importBuilder = new StringBuilder();
|
|
foreach (Match match in Parser.Parser.CssImportUrlRegex.Matches(stylesheetHtml))
|
|
{
|
|
if (!match.Success) continue;
|
|
|
|
var importFile = match.Groups["Filename"].Value;
|
|
var key = CleanContentKeys(importFile);
|
|
if (!key.Contains(prepend))
|
|
{
|
|
key = prepend + key;
|
|
}
|
|
if (!book.Content.AllFiles.ContainsKey(key)) continue;
|
|
|
|
var bookFile = book.Content.AllFiles[key];
|
|
var content = await bookFile.ReadContentAsBytesAsync();
|
|
importBuilder.Append(Encoding.UTF8.GetString(content));
|
|
}
|
|
|
|
stylesheetHtml = stylesheetHtml.Insert(0, importBuilder.ToString());
|
|
var importMatches = Parser.Parser.CssImportUrlRegex.Matches(stylesheetHtml);
|
|
foreach (Match match in importMatches)
|
|
{
|
|
if (!match.Success) continue;
|
|
var importFile = match.Groups["Filename"].Value;
|
|
stylesheetHtml = stylesheetHtml.Replace(importFile, apiBase + prepend + importFile);
|
|
}
|
|
|
|
// Check if there are any background images and rewrite those urls
|
|
EscapeCssImageReferences(ref stylesheetHtml, apiBase, book);
|
|
|
|
var styleContent = RemoveWhiteSpaceFromStylesheets(stylesheetHtml);
|
|
styleContent = styleContent.Replace("body", ".reading-section");
|
|
|
|
if (string.IsNullOrEmpty(styleContent)) return string.Empty;
|
|
|
|
var stylesheet = await _cssParser.ParseAsync(styleContent);
|
|
foreach (var styleRule in stylesheet.StyleRules)
|
|
{
|
|
if (styleRule.Selector.Text == ".reading-section") continue;
|
|
if (styleRule.Selector.Text.Contains(","))
|
|
{
|
|
styleRule.Text = styleRule.Text.Replace(styleRule.SelectorText,
|
|
string.Join(", ",
|
|
styleRule.Selector.Text.Split(",").Select(s => ".reading-section " + s)));
|
|
continue;
|
|
}
|
|
styleRule.Text = ".reading-section " + styleRule.Text;
|
|
}
|
|
return RemoveWhiteSpaceFromStylesheets(stylesheet.ToCss());
|
|
}
|
|
|
|
private static void EscapeCssImageReferences(ref string stylesheetHtml, string apiBase, EpubBookRef book)
|
|
{
|
|
var matches = Parser.Parser.CssImageUrlRegex.Matches(stylesheetHtml);
|
|
foreach (Match match in matches)
|
|
{
|
|
if (!match.Success) continue;
|
|
|
|
var importFile = match.Groups["Filename"].Value;
|
|
var key = CleanContentKeys(importFile);
|
|
if (!book.Content.AllFiles.ContainsKey(key)) continue;
|
|
|
|
stylesheetHtml = stylesheetHtml.Replace(importFile, apiBase + key);
|
|
}
|
|
}
|
|
|
|
public ComicInfo GetComicInfo(string filePath)
|
|
{
|
|
if (!IsValidFile(filePath) || Parser.Parser.IsPdf(filePath)) return null;
|
|
|
|
try
|
|
{
|
|
using var epubBook = EpubReader.OpenBook(filePath);
|
|
var publicationDate =
|
|
epubBook.Schema.Package.Metadata.Dates.FirstOrDefault(date => date.Event == "publication")?.Date;
|
|
|
|
var info = new ComicInfo()
|
|
{
|
|
Summary = epubBook.Schema.Package.Metadata.Description,
|
|
Writer = string.Join(",", epubBook.Schema.Package.Metadata.Creators),
|
|
Publisher = string.Join(",", epubBook.Schema.Package.Metadata.Publishers),
|
|
Month = !string.IsNullOrEmpty(publicationDate) ? DateTime.Parse(publicationDate).Month : 0,
|
|
Year = !string.IsNullOrEmpty(publicationDate) ? DateTime.Parse(publicationDate).Year : 0,
|
|
};
|
|
// Parse tags not exposed via Library
|
|
foreach (var metadataItem in epubBook.Schema.Package.Metadata.MetaItems)
|
|
{
|
|
switch (metadataItem.Name)
|
|
{
|
|
case "calibre:rating":
|
|
info.UserRating = float.Parse(metadataItem.Content);
|
|
break;
|
|
}
|
|
}
|
|
|
|
return info;
|
|
}
|
|
catch (Exception ex)
|
|
{
|
|
_logger.LogWarning(ex, "[GetComicInfo] There was an exception getting metadata");
|
|
}
|
|
|
|
return null;
|
|
}
|
|
|
|
private bool IsValidFile(string filePath)
|
|
{
|
|
if (!File.Exists(filePath))
|
|
{
|
|
_logger.LogWarning("[BookService] Book {EpubFile} could not be found", filePath);
|
|
return false;
|
|
}
|
|
|
|
if (Parser.Parser.IsBook(filePath)) return true;
|
|
|
|
_logger.LogWarning("[BookService] Book {EpubFile} is not a valid EPUB/PDF", filePath);
|
|
return false;
|
|
}
|
|
|
|
public int GetNumberOfPages(string filePath)
|
|
{
|
|
if (!IsValidFile(filePath)) return 0;
|
|
|
|
try
|
|
{
|
|
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)
|
|
{
|
|
_logger.LogWarning(ex, "[BookService] There was an exception getting number of pages, defaulting to 0");
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
public static string EscapeTags(string content)
|
|
{
|
|
content = Regex.Replace(content, @"<script(.*)(/>)", "<script$1></script>");
|
|
content = Regex.Replace(content, @"<title(.*)(/>)", "<title$1></title>");
|
|
return content;
|
|
}
|
|
|
|
public static string CleanContentKeys(string key)
|
|
{
|
|
return key.Replace("../", string.Empty);
|
|
}
|
|
|
|
public async Task<Dictionary<string, int>> CreateKeyToPageMappingAsync(EpubBookRef book)
|
|
{
|
|
var dict = new Dictionary<string, int>();
|
|
var pageCount = 0;
|
|
foreach (var contentFileRef in await book.GetReadingOrderAsync())
|
|
{
|
|
if (contentFileRef.ContentType != EpubContentType.XHTML_1_1) continue;
|
|
dict.Add(contentFileRef.FileName, pageCount);
|
|
pageCount += 1;
|
|
}
|
|
|
|
return dict;
|
|
}
|
|
|
|
/// <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. This expects only an epub file
|
|
/// </summary>
|
|
/// <param name="filePath"></param>
|
|
/// <returns></returns>
|
|
public ParserInfo ParseInfo(string filePath)
|
|
{
|
|
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
|
|
// <meta content="5.0" name="calibre:series_index"/>
|
|
// <meta content="The Dark Tower" name="calibre:series"/>
|
|
// <meta content="Wolves of the Calla" name="calibre:title_sort"/>
|
|
// If all three are present, we can take that over dc:title and format as:
|
|
// Series = The Dark Tower, Volume = 5, Filename as "Wolves of the Calla"
|
|
// In addition, the following can exist and should parse as a series (EPUB 3.2 spec)
|
|
// <meta property="belongs-to-collection" id="c01">
|
|
// The Lord of the Rings
|
|
// </meta>
|
|
// <meta refines="#c01" property="collection-type">set</meta>
|
|
// <meta refines="#c01" property="group-position">2</meta>
|
|
try
|
|
{
|
|
var seriesIndex = string.Empty;
|
|
var series = string.Empty;
|
|
var specialName = string.Empty;
|
|
var groupPosition = string.Empty;
|
|
|
|
|
|
foreach (var metadataItem in epubBook.Schema.Package.Metadata.MetaItems)
|
|
{
|
|
// EPUB 2 and 3
|
|
switch (metadataItem.Name)
|
|
{
|
|
case "calibre:series_index":
|
|
seriesIndex = metadataItem.Content;
|
|
break;
|
|
case "calibre:series":
|
|
series = metadataItem.Content;
|
|
break;
|
|
case "calibre:title_sort":
|
|
specialName = metadataItem.Content;
|
|
break;
|
|
}
|
|
|
|
// EPUB 3.2+ only
|
|
switch (metadataItem.Property)
|
|
{
|
|
case "group-position":
|
|
seriesIndex = metadataItem.Content;
|
|
break;
|
|
case "belongs-to-collection":
|
|
series = metadataItem.Content;
|
|
break;
|
|
case "collection-type":
|
|
groupPosition = metadataItem.Content;
|
|
break;
|
|
}
|
|
}
|
|
|
|
if (!string.IsNullOrEmpty(series) && !string.IsNullOrEmpty(seriesIndex) &&
|
|
(!string.IsNullOrEmpty(specialName) || groupPosition.Equals("series") || groupPosition.Equals("set")))
|
|
{
|
|
if (string.IsNullOrEmpty(specialName))
|
|
{
|
|
specialName = epubBook.Title;
|
|
}
|
|
return new ParserInfo()
|
|
{
|
|
Chapters = Parser.Parser.DefaultChapter,
|
|
Edition = string.Empty,
|
|
Format = MangaFormat.Epub,
|
|
Filename = Path.GetFileName(filePath),
|
|
Title = specialName.Trim(),
|
|
FullFilePath = filePath,
|
|
IsSpecial = false,
|
|
Series = series.Trim(),
|
|
Volumes = seriesIndex.Split(".")[0]
|
|
};
|
|
}
|
|
}
|
|
catch (Exception)
|
|
{
|
|
// Swallow exception
|
|
}
|
|
|
|
return new ParserInfo()
|
|
{
|
|
Chapters = Parser.Parser.DefaultChapter,
|
|
Edition = string.Empty,
|
|
Format = MangaFormat.Epub,
|
|
Filename = Path.GetFileName(filePath),
|
|
Title = epubBook.Title.Trim(),
|
|
FullFilePath = filePath,
|
|
IsSpecial = false,
|
|
Series = epubBook.Title.Trim(),
|
|
Volumes = Parser.Parser.DefaultVolume
|
|
};
|
|
}
|
|
catch (Exception ex)
|
|
{
|
|
_logger.LogWarning(ex, "[BookService] There was an exception when opening epub book: {FileName}", filePath);
|
|
}
|
|
|
|
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();
|
|
using var stream = StreamManager.GetStream("BookService.GetPdfPage");
|
|
for (var pageNumber = 0; pageNumber < pages; pageNumber++)
|
|
{
|
|
GetPdfPage(docReader, pageNumber, stream);
|
|
using var fileStream = File.Create(Path.Combine(targetDirectory, "Page-" + pageNumber + ".png"));
|
|
stream.Seek(0, SeekOrigin.Begin);
|
|
stream.CopyTo(fileStream);
|
|
}
|
|
}
|
|
|
|
/// <summary>
|
|
/// Extracts the cover image to covers directory and returns file path back
|
|
/// </summary>
|
|
/// <param name="fileFilePath"></param>
|
|
/// <param name="fileName">Name of the new file.</param>
|
|
/// <returns></returns>
|
|
public string GetCoverImage(string fileFilePath, string fileName)
|
|
{
|
|
if (!IsValidFile(fileFilePath)) return string.Empty;
|
|
|
|
if (Parser.Parser.IsPdf(fileFilePath))
|
|
{
|
|
return GetPdfCoverImage(fileFilePath, fileName);
|
|
}
|
|
|
|
using var epubBook = EpubReader.OpenBook(fileFilePath);
|
|
|
|
|
|
try
|
|
{
|
|
// Try to get the cover image from OPF file, if not set, try to parse it from all the files, then result to the first one.
|
|
var coverImageContent = epubBook.Content.Cover
|
|
?? epubBook.Content.Images.Values.FirstOrDefault(file => Parser.Parser.IsCoverImage(file.FileName))
|
|
?? epubBook.Content.Images.Values.FirstOrDefault();
|
|
|
|
if (coverImageContent == null) return string.Empty;
|
|
using var stream = coverImageContent.GetContentStream();
|
|
|
|
return ImageService.WriteCoverThumbnail(stream, fileName);
|
|
}
|
|
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 string.Empty;
|
|
}
|
|
|
|
|
|
private string GetPdfCoverImage(string fileFilePath, string fileName)
|
|
{
|
|
try
|
|
{
|
|
using var docReader = DocLib.Instance.GetDocReader(fileFilePath, new PageDimensions(1080, 1920));
|
|
if (docReader.GetPageCount() == 0) return string.Empty;
|
|
|
|
using var stream = StreamManager.GetStream("BookService.GetPdfPage");
|
|
GetPdfPage(docReader, 0, stream);
|
|
|
|
return ImageService.WriteCoverThumbnail(stream, fileName);
|
|
|
|
}
|
|
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 string.Empty;
|
|
}
|
|
|
|
private static void GetPdfPage(IDocReader docReader, int pageNumber, Stream stream)
|
|
{
|
|
using var pageReader = docReader.GetPageReader(pageNumber);
|
|
var rawBytes = pageReader.GetImage(new NaiveTransparencyRemover());
|
|
var width = pageReader.GetPageWidth();
|
|
var height = pageReader.GetPageHeight();
|
|
using var bmp = new Bitmap(width, height, PixelFormat.Format32bppArgb);
|
|
AddBytesToBitmap(bmp, rawBytes);
|
|
// Removes 1px margin on left/right side after bitmap is copied out
|
|
for (var y = 0; y < bmp.Height; y++)
|
|
{
|
|
bmp.SetPixel(bmp.Width - 1, y, bmp.GetPixel(bmp.Width - 2, y));
|
|
}
|
|
stream.Seek(0, SeekOrigin.Begin);
|
|
bmp.Save(stream, ImageFormat.Jpeg);
|
|
stream.Seek(0, SeekOrigin.Begin);
|
|
}
|
|
|
|
private static string RemoveWhiteSpaceFromStylesheets(string body)
|
|
{
|
|
if (string.IsNullOrEmpty(body))
|
|
{
|
|
return string.Empty;
|
|
}
|
|
|
|
// Remove comments from CSS
|
|
body = Regex.Replace(body, @"/\*[\d\D]*?\*/", string.Empty);
|
|
|
|
body = Regex.Replace(body, @"[a-zA-Z]+#", "#");
|
|
body = Regex.Replace(body, @"[\n\r]+\s*", string.Empty);
|
|
body = Regex.Replace(body, @"\s+", " ");
|
|
body = Regex.Replace(body, @"\s?([:,;{}])\s?", "$1");
|
|
try
|
|
{
|
|
body = body.Replace(";}", "}");
|
|
}
|
|
catch (Exception)
|
|
{
|
|
/* Swallow exception. Some css doesn't have style rules ending in ; */
|
|
}
|
|
|
|
body = Regex.Replace(body, @"([\s:]0)(px|pt|%|em)", "$1");
|
|
|
|
|
|
return body;
|
|
}
|
|
}
|
|
}
|