AZEN-SGG/Kavita
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

EPUB CSS Parsing Issues (#690)

Browse source 
* 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
This commit is contained in:
Joseph Milazzo 2021-10-18 16:28:07 -07:00 • committed by GitHub
parent 22497645a9
commit 60dd66f6ae
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
6 changed files with 81 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

30
API/Services/BookService.cs
View file

@ -140,13 +140,18 @@ namespace API.Services
}
stylesheetHtml = stylesheetHtml.Insert(0, importBuilder.ToString());
stylesheetHtml =
Parser.Parser.CssImportUrlRegex.Replace(stylesheetHtml, "$1" + apiBase + prepend + "$2" + "$3");
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 =
Parser.Parser.FontSrcUrlRegex.Replace(styleContent, "$1" + apiBase + "$2" + "$3");
styleContent = styleContent.Replace("body", ".reading-section");
var stylesheet = await _cssParser.ParseAsync(styleContent);
@ -165,6 +170,21 @@ namespace API.Services
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;