Match scanned files when the on-disk name drops "The" or author credentials

listenarr.infrastructure/Library/Scanning/ScanFileDiscovery.cs

@@ -103,20 +103,81 @@ private static List<string> CollectCandidates(string scanRoot, Guid jobId, ILogg
         return candidates;
     }
 
-    private static bool Matches(
+    internal static bool Matches(
         string file,
         string directoryName,
         string titleToken,
         string authorToken)
     {
+        var fileStem = Path.GetFileNameWithoutExtension(file);
+
+        // Original case-insensitive substring checks (behavior preserved).
         var fileNameMatchesTitle = !string.IsNullOrEmpty(titleToken)
-            && Path.GetFileNameWithoutExtension(file)
-                .Contains(titleToken, StringComparison.OrdinalIgnoreCase);
+            && fileStem.Contains(titleToken, StringComparison.OrdinalIgnoreCase);
         var filePathMatchesAuthor = !string.IsNullOrEmpty(authorToken)
             && file.Contains(authorToken, StringComparison.OrdinalIgnoreCase);
         var directoryMatchesTitle = !string.IsNullOrEmpty(directoryName)
             && !string.IsNullOrEmpty(titleToken)
             && directoryName.Contains(titleToken, StringComparison.OrdinalIgnoreCase);
-        return fileNameMatchesTitle || filePathMatchesAuthor || directoryMatchesTitle;
+        if (fileNameMatchesTitle || filePathMatchesAuthor || directoryMatchesTitle)
+        {
+            return true;
+        }
+
+        // Tolerant title matching: allow a file to match when the on-disk name differs from the
+        // recorded title only by a leading article and punctuation (e.g. "Language of Emotions" for
+        // "The Language of Emotions"). This is deliberately TITLE-ONLY and requires the full token
+        // set to match. It intentionally does not fall back to matching on author alone: doing so
+        // attributes any file that merely shares an author's shelf to this book (e.g. linking Henry
+        // James' "The Turn of the Screw" to M. R. James' "Ghost Stories of an Antiquary").
+        var titleTokens = TokenSet(NormalizeTitle(titleToken));
+        if (titleTokens.Count == 0)
+        {
+            return false;
+        }
+
+        return titleTokens.SetEquals(TokenSet(NormalizeTitle(fileStem)))
+            || (!string.IsNullOrEmpty(directoryName)
+                && titleTokens.SetEquals(TokenSet(NormalizeTitle(directoryName))));
     }
+
+    private static string NormalizeText(string value)
+    {
+        if (string.IsNullOrEmpty(value))
+        {
+            return string.Empty;
+        }
+
+        var builder = new System.Text.StringBuilder(value.Length);
+        foreach (var ch in value)
+        {
+            if (char.IsLetterOrDigit(ch))
+            {
+                builder.Append(char.ToLowerInvariant(ch));
+            }
+            else if (builder.Length > 0 && builder[^1] != ' ')
+            {
+                builder.Append(' ');
+            }
+        }
+
+        return builder.ToString().Trim();
+    }
+
+    private static string NormalizeTitle(string value)
+    {
+        var text = NormalizeText(value);
+        foreach (var article in new[] { "the ", "a ", "an " })
+        {
+            if (text.StartsWith(article, StringComparison.Ordinal))
+            {
+                return text[article.Length..];
+            }
+        }
+
+        return text;
+    }
+
+    private static HashSet<string> TokenSet(string normalized) =>
+        new(normalized.Split(' ', StringSplitOptions.RemoveEmptyEntries), StringComparer.Ordinal);
 }

tests/Features/Infrastructure/Library/Scanning/ScanFileDiscoveryMatchTests.cs

@@ -0,0 +1,72 @@
+/*
+ * Listenarr - Audiobook Management System
+ * Copyright (C) 2024-2026 Listenarr Contributors
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published
+ * by the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with this program. If not, see <https://www.gnu.org/licenses/>.
+ */
+using Listenarr.Infrastructure.Library.Scanning;
+
+namespace Listenarr.Tests.Features.Infrastructure.Library.Scanning
+{
+    public class ScanFileDiscoveryMatchTests
+    {
+        [Fact]
+        public void Matches_ExactTitleInFilename_StillMatches()
+        {
+            // Baseline: unchanged existing behavior.
+            var file = @"E:\Audiobooks\Frank Herbert\Dune Messiah\Dune Messiah.m4b";
+            Assert.True(ScanFileDiscovery.Matches(file, "Dune Messiah", "Dune Messiah", "Frank Herbert"));
+        }
+
+        [Fact]
+        public void Matches_FileDropsLeadingThe_StillMatches()
+        {
+            // File/folder omit the leading "The" that the library title carries.
+            var file = @"E:\Audiobooks\Karla McLaren\Language of Emotions\Language of Emotions.m4b";
+            Assert.True(ScanFileDiscovery.Matches(file, "Language of Emotions", "The Language of Emotions", "M.Ed. Karla McLaren"));
+        }
+
+        [Fact]
+        public void Matches_AuthorHasCredentials_FolderDoesNot_StillMatches()
+        {
+            // Title matches nothing (file has none of it), but the author (minus credentials) does.
+            var file = @"E:\Audiobooks\Gabor Mate\Myth of Normal\Myth of Normal.m4b";
+            Assert.True(ScanFileDiscovery.Matches(file, "Myth of Normal", "The Myth of Normal", "Gabor Mate MD"));
+        }
+
+        [Fact]
+        public void Matches_AuthorWithMiddleInitial_StillMatches()
+        {
+            // Path keeps the middle initial; library author dropped it (and vice-versa).
+            var file = @"E:\Audiobooks\John M. Gottman\Relationship Cure\Relationship Cure.m4b";
+            Assert.True(ScanFileDiscovery.Matches(file, "Relationship Cure", "The Relationship Cure", "John Gottman PhD"));
+        }
+
+        [Fact]
+        public void Matches_UnrelatedFile_DoesNotMatch()
+        {
+            var file = @"E:\Audiobooks\Someone Else\Totally Different Book\Totally Different Book.m4b";
+            Assert.False(ScanFileDiscovery.Matches(file, "Totally Different Book", "The Language of Emotions", "Karla McLaren"));
+        }
+
+        [Fact]
+        public void Matches_DifferentBookSharingAnAuthorSurname_DoesNotMatch()
+        {
+            // Regression guard: matching must not fall back to author-only. A file for a different
+            // book that merely shares an author surname on its shelf must NOT be attributed here.
+            var file = @"E:\Audiobooks\Henry James\The Turn of the Screw\The Turn of the Screw.m4b";
+            Assert.False(ScanFileDiscovery.Matches(file, "The Turn of the Screw", "Ghost Stories of an Antiquary", "M. R. James"));
+        }
+    }
+}