No More Sort Prefixes (#3895)

API/Controllers/LibraryController.cs

@@ -624,6 +624,8 @@ public class LibraryController : BaseApiController
         library.AllowScrobbling = dto.AllowScrobbling;
         library.AllowMetadataMatching = dto.AllowMetadataMatching;
         library.EnableMetadata = dto.EnableMetadata;
+        library.RemovePrefixForSortName = dto.RemovePrefixForSortName;
+
         library.LibraryFileTypes = dto.FileGroupTypes
             .Select(t => new LibraryFileTypeGroup() {FileTypeGroup = t, LibraryId = library.Id})
             .Distinct()

API/DTOs/LibraryDto.cs

@@ -70,4 +70,8 @@ public sealed record LibraryDto
     /// Allow Kavita to read metadata (ComicInfo.xml, Epub, PDF)
     /// </summary>
     public bool EnableMetadata { get; set; } = true;
+    /// <summary>
+    /// Should Kavita remove sort articles "The" for the sort name
+    /// </summary>
+    public bool RemovePrefixForSortName { get; set; } = false;
 }

API/DTOs/UpdateLibraryDto.cs

@@ -30,6 +30,8 @@ public sealed record UpdateLibraryDto
     public bool AllowMetadataMatching { get; init; }
     [Required]
     public bool EnableMetadata { get; init; }
+    [Required]
+    public bool RemovePrefixForSortName { get; init; }
     /// <summary>
     /// What types of files to allow the scanner to pickup
     /// </summary>

API/Data/Migrations/20250629153840_LibraryRemoveSortPrefix.cs

@@ -0,0 +1,29 @@
+using Microsoft.EntityFrameworkCore.Migrations;
+
+#nullable disable
+
+namespace API.Data.Migrations
+{
+    /// <inheritdoc />
+    public partial class LibraryRemoveSortPrefix : Migration
+    {
+        /// <inheritdoc />
+        protected override void Up(MigrationBuilder migrationBuilder)
+        {
+            migrationBuilder.AddColumn<bool>(
+                name: "RemovePrefixForSortName",
+                table: "Library",
+                type: "INTEGER",
+                nullable: false,
+                defaultValue: false);
+        }
+
+        /// <inheritdoc />
+        protected override void Down(MigrationBuilder migrationBuilder)
+        {
+            migrationBuilder.DropColumn(
+                name: "RemovePrefixForSortName",
+                table: "Library");
+        }
+    }
+}

API/Data/Migrations/DataContextModelSnapshot.cs

@@ -1341,6 +1341,9 @@ namespace API.Data.Migrations
                     b.Property<string>("PrimaryColor")
                         .HasColumnType("TEXT");
 
+                    b.Property<bool>("RemovePrefixForSortName")
+                        .HasColumnType("INTEGER");
+
                     b.Property<string>("SecondaryColor")
                         .HasColumnType("TEXT");
 

API/Entities/Library.cs

@@ -52,6 +52,10 @@ public class Library : IEntityDate, IHasCoverImage
     /// Should Kavita read metadata files from the library
     /// </summary>
     public bool EnableMetadata { get; set; } = true;
+    /// <summary>
+    /// Should Kavita remove sort articles "The" for the sort name
+    /// </summary>
+    public bool RemovePrefixForSortName { get; set; } = false;
 
 
     public DateTime Created { get; set; }

API/Helpers/BookSortTitlePrefixHelper.cs

@@ -0,0 +1,101 @@
+using System;
+using System.Collections.Generic;
+using System.Runtime.CompilerServices;
+
+namespace API.Helpers;
+
+/// <summary>
+/// Responsible for parsing book titles "The man on the street" and removing the prefix -> "man on the street".
+/// </summary>
+/// <remarks>This code is performance sensitive</remarks>
+public static class BookSortTitlePrefixHelper
+{
+    private static readonly Dictionary<string, byte> PrefixLookup;
+    private static readonly Dictionary<char, List<string>> PrefixesByFirstChar;
+
+    static BookSortTitlePrefixHelper()
+    {
+        var prefixes = new[]
+        {
+            // English
+            "the", "a", "an",
+            // Spanish
+            "el", "la", "los", "las", "un", "una", "unos", "unas",
+            // French
+            "le", "la", "les", "un", "une", "des",
+            // German
+            "der", "die", "das", "den", "dem", "ein", "eine", "einen", "einer",
+            // Italian
+            "il", "lo", "la", "gli", "le", "un", "uno", "una",
+            // Portuguese
+            "o", "a", "os", "as", "um", "uma", "uns", "umas",
+            // Russian (transliterated common ones)
+            "в", "на", "с", "к", "от", "для",
+        };
+
+        // Build lookup structures
+        PrefixLookup = new Dictionary<string, byte>(prefixes.Length, StringComparer.OrdinalIgnoreCase);
+        PrefixesByFirstChar = new Dictionary<char, List<string>>();
+
+        foreach (var prefix in prefixes)
+        {
+            PrefixLookup[prefix] = 1;
+
+            var firstChar = char.ToLowerInvariant(prefix[0]);
+            if (!PrefixesByFirstChar.TryGetValue(firstChar, out var list))
+            {
+                list = [];
+                PrefixesByFirstChar[firstChar] = list;
+            }
+            list.Add(prefix);
+        }
+    }
+
+    [MethodImpl(MethodImplOptions.AggressiveInlining)]
+    public static ReadOnlySpan<char> GetSortTitle(ReadOnlySpan<char> title)
+    {
+        if (title.IsEmpty) return title;
+
+        // Fast detection of script type by first character
+        var firstChar = title[0];
+
+        // CJK Unicode ranges - no processing needed for most cases
+        if ((firstChar >= 0x4E00 && firstChar <= 0x9FFF) ||   // CJK Unified
+            (firstChar >= 0x3040 && firstChar <= 0x309F) ||   // Hiragana
+            (firstChar >= 0x30A0 && firstChar <= 0x30FF))     // Katakana
+        {
+            return title;
+        }
+
+        var firstSpaceIndex = title.IndexOf(' ');
+        if (firstSpaceIndex <= 0) return title;
+
+        var potentialPrefix = title.Slice(0, firstSpaceIndex);
+
+        // Fast path: check if first character could match any prefix
+        firstChar = char.ToLowerInvariant(potentialPrefix[0]);
+        if (!PrefixesByFirstChar.ContainsKey(firstChar))
+            return title;
+
+        // Only do the expensive lookup if first character matches
+        if (PrefixLookup.ContainsKey(potentialPrefix.ToString()))
+        {
+            var remainder = title.Slice(firstSpaceIndex + 1);
+            return remainder.IsEmpty ? title : remainder;
+        }
+
+        return title;
+    }
+
+    /// <summary>
+    /// Removes the sort prefix
+    /// </summary>
+    /// <param name="title"></param>
+    /// <returns></returns>
+    public static string GetSortTitle(string title)
+    {
+        var result = GetSortTitle(title.AsSpan());
+
+        return result.ToString();
+    }
+}

API/Services/Tasks/Scanner/ProcessSeries.cs

@@ -126,13 +126,17 @@ public class ProcessSeries : IProcessSeries
                 series.Format = firstParsedInfo.Format;
             }
 
+            var removePrefix = library.RemovePrefixForSortName;
+            var sortName = removePrefix ? BookSortTitlePrefixHelper.GetSortTitle(series.Name) : series.Name;
+
             if (string.IsNullOrEmpty(series.SortName))
             {
-                series.SortName = series.Name;
+                series.SortName = sortName;
             }
+
             if (!series.SortNameLocked)
             {
-                series.SortName = series.Name;
+                series.SortName = sortName;
                 if (!string.IsNullOrEmpty(firstParsedInfo.SeriesSort))
                 {
                     series.SortName = firstParsedInfo.SeriesSort;