mirror of
https://github.com/Kareadita/Kavita.git
synced 2025-06-03 05:34:21 -04:00
* Adding some code for Robbie * See more on series detail metadata area is now at the bottom on the section * Cleaned up subtitle headings to use a single class for offset with actionables * Added some markup for the new design, waiting for Robbie to finish it off * styling age-rating badge * Started hooking up basic analyze file service and hooks in the UI. Basic code to implement the count is implemented and in benchmarks. * Hooked up analyze ui to backend * Refactored Series Detail metadata area to use a new icon/title design * Cleaned up the new design * Pushing for robbie to do css * Massive performance improvement to scan series where we only need to scan folders reported that have series in them, rather than the whole library. * Removed theme page as we no longer need it. Added WordCount to DTOs so the UI can show them. Added new pipe to format numbers in compact mode. * Hooked up actual reading time based on user's words per hour * Refactor some magic numbers to consts * Hooked in progress reporting for series word count * Hooked up analyze files * Re-implemented time to read on comics * Removed the word Last Read * Show proper language name instead of iso tag on series detail page. Added some error handling on word count code. * Reworked error handling * Fixed some security vulnerabilities in npm. * Handle a case where there are no text nodes and instead of returning an empty list, htmlagilitypack returns null. * Tweaked the styles a bit on the icon-and-title * Code cleanup Co-authored-by: Robbie Davis <robbie@therobbiedavis.com>
69 lines
2.3 KiB
C#
69 lines
2.3 KiB
C#
using System;
|
|
using System.Linq;
|
|
using System.Threading.Tasks;
|
|
using API.Services;
|
|
using BenchmarkDotNet.Attributes;
|
|
using BenchmarkDotNet.Order;
|
|
using HtmlAgilityPack;
|
|
using VersOne.Epub;
|
|
|
|
namespace API.Benchmark;
|
|
|
|
[MemoryDiagnoser]
|
|
[Orderer(SummaryOrderPolicy.FastestToSlowest)]
|
|
[RankColumn]
|
|
[SimpleJob(launchCount: 1, warmupCount: 3, targetCount: 5, invocationCount: 100, id: "Epub"), ShortRunJob]
|
|
public class EpubBenchmark
|
|
{
|
|
[Benchmark]
|
|
public async Task GetWordCount_PassByString()
|
|
{
|
|
using var book = await EpubReader.OpenBookAsync("Data/book-test.epub", BookService.BookReaderOptions);
|
|
foreach (var bookFile in book.Content.Html.Values)
|
|
{
|
|
Console.WriteLine(GetBookWordCount_PassByString(await bookFile.ReadContentAsTextAsync()));
|
|
;
|
|
}
|
|
}
|
|
|
|
[Benchmark]
|
|
public async Task GetWordCount_PassByRef()
|
|
{
|
|
using var book = await EpubReader.OpenBookAsync("Data/book-test.epub", BookService.BookReaderOptions);
|
|
foreach (var bookFile in book.Content.Html.Values)
|
|
{
|
|
Console.WriteLine(await GetBookWordCount_PassByRef(bookFile));
|
|
}
|
|
}
|
|
|
|
private static int GetBookWordCount_PassByString(string fileContents)
|
|
{
|
|
var doc = new HtmlDocument();
|
|
doc.LoadHtml(fileContents);
|
|
var delimiter = new char[] {' '};
|
|
|
|
return doc.DocumentNode.SelectNodes("//body//text()[not(parent::script)]")
|
|
.Select(node => node.InnerText)
|
|
.Select(text => text.Split(delimiter, StringSplitOptions.RemoveEmptyEntries)
|
|
.Where(s => char.IsLetter(s[0])))
|
|
.Select(words => words.Count())
|
|
.Where(wordCount => wordCount > 0)
|
|
.Sum();
|
|
}
|
|
|
|
private static async Task<int> GetBookWordCount_PassByRef(EpubContentFileRef bookFile)
|
|
{
|
|
var doc = new HtmlDocument();
|
|
doc.LoadHtml(await bookFile.ReadContentAsTextAsync());
|
|
var delimiter = new char[] {' '};
|
|
|
|
return doc.DocumentNode.SelectNodes("//body//text()[not(parent::script)]")
|
|
.Select(node => node.InnerText)
|
|
.Select(text => text.Split(delimiter, StringSplitOptions.RemoveEmptyEntries)
|
|
.Where(s => char.IsLetter(s[0])))
|
|
.Select(words => words.Count())
|
|
.Where(wordCount => wordCount > 0)
|
|
.Sum();
|
|
}
|
|
}
|