feat(search): improve filename normalization for better auto results

importer/templates/base.html

@@ -204,6 +204,11 @@
             margin: 0;
           }
 
+          .book-description {
+            overflow-wrap: anywhere;
+            hyphens: auto;
+          }
+
           {% block style %}{% endblock %}
     </style>
 </head>

importer/templates/book_list.html

@@ -27,7 +27,7 @@
                         {% if book.status.status == 'Error' %}
                         <p>{{ book.status.message }}</p>
                         {% else %}
-                        <p>
+                        <p class="book-description">
                         {{ book.long_desc|safe }}
                         </p>
                         {% endif %}

importer/templates/book_tabs.html

@@ -1,22 +1,22 @@
 {% extends "base.html" %}
 {% block content %}
 <div class="box">
-    <div class="tabs is-fullwidth is-toggle" style="background: white;" data-default={{ default_view }}>
+    <div class="tabs is-fullwidth is-toggle" style="background: white;" data-default={{ default_view }} role="tablist">
         <ul>
-            <li class="tab is-active" id="done-tab" onclick="openTab('done')"><a>Done</a></li>
-            <li class="tab" id="processing-tab" onclick="openTab('processing')"><a>Processing</a></li>
-            <li class="tab" id="error-tab" onclick="openTab('error')"><a>Error</a></li>
+            <li class="tab is-active" id="done-tab" onclick="openTab('done')"><a role="tab" aria-selected="true" aria-controls="done" aria-label="Done - {{ done_books|length }} book{{ done_books|length|pluralize }}">Done ({{ done_books|length }})</a></li>
+            <li class="tab" id="processing-tab" onclick="openTab('processing')"><a role="tab" aria-selected="false" aria-controls="processing" aria-label="Processing - {{ processing_books|length }} book{{ processing_books|length|pluralize }}">Processing ({{ processing_books|length }})</a></li>
+            <li class="tab" id="error-tab" onclick="openTab('error')"><a role="tab" aria-selected="false" aria-controls="error" aria-label="Error - {{ error_books|length }} book{{ error_books|length|pluralize }}">Error ({{ error_books|length }})</a></li>
         </ul>
     </div>
 
     <div class="tab-content">
-        <div class="tab-pane" id="done">
+        <div class="tab-pane" id="done" role="tabpanel" aria-labelledby="done-tab">
             {% include "book_list.html" with books=done_books %}
         </div>
-        <div class="tab-pane" id="processing" style="display: none;">
+        <div class="tab-pane" id="processing" role="tabpanel" aria-labelledby="processing-tab" style="display: none;">
             {% include "book_list.html" with books=processing_books %}
         </div>
-        <div class="tab-pane" id="error" style="display: none;">
+        <div class="tab-pane" id="error" role="tabpanel" aria-labelledby="error-tab" style="display: none;">
             {% include "book_list.html" with books=error_books %}
         </div>
     </div>

importer/templates/book_tabs.js

@@ -11,6 +11,15 @@ function openTab(tabId) {
 
     document.getElementById(tabId).style.display = "block";
     document.getElementById(`${tabId}-tab`).classList.add("is-active");
+
+    const tabAnchors = document.querySelectorAll('.tab a[role="tab"]');
+    tabAnchors.forEach(anchor => {
+        if (anchor.getAttribute('aria-controls') === tabId) {
+            anchor.setAttribute('aria-selected', 'true');
+        } else {
+            anchor.setAttribute('aria-selected', 'false');
+        }
+    });
 }
 
 window.addEventListener('load', function () {

utils/search_tools.py

@@ -83,6 +83,22 @@ def normalize_name(self, name) -> str:
             name,
             flags=re.IGNORECASE,
         )
+        # Remove "read by" / "narrated by" patterns
+        name = re.sub(
+            r"\b(read|narrated)\s+by\s+\w+(?:\s+\w+){1,2}",
+            "",
+            name,
+            flags=re.IGNORECASE,
+        )
+        # Remove part/volume/book/chapter indicators
+        name = re.sub(
+            r"\b(part|vol|volume|book|chapter)\s*\d+\s*(of\s*\d+)?\b",
+            "",
+            name,
+            flags=re.IGNORECASE,
+        )
+        # Remove years
+        name = re.sub(r"[\(\[]\s*\d{4}\s*[\)\]]|\b(19|20)\d{2}\b", "", name)
         # Remove unwanted whitespaces
         name = re.sub(r"\s+", " ", name)
         # Remove leading and trailing whitespaces

utils/tests.py

@@ -8,6 +8,7 @@
 
 from importer.models import Book, Setting, Status, StatusChoices
 from utils.merge import run_m4b_merge
+from utils.search_tools import SearchTool
 
 
 class TestSubprocessMerge(TestCase):
@@ -276,3 +277,73 @@ def test_output_path_parsing_failure(self, mock_subprocess_run):
 
         # Verify ValueError was raised with correct message
         self.assertIn("Could not parse output path", str(context.exception))
+
+
+class TestSearchToolNormalizeName(TestCase):
+    """Unit tests for SearchTool.normalize_name method."""
+
+    def setUp(self):
+        """Set up test fixtures."""
+        self.tool = SearchTool(filename="test")
+
+    def test_normalize_name_removes_read_by(self):
+        """Verify 'read by' and narrator names are removed."""
+        result = self.tool.normalize_name("Great Book read by John Smith")
+        self.assertNotIn("read by", result.lower())
+        self.assertNotIn("john smith", result.lower())
+        self.assertIn("great", result.lower())
+        self.assertIn("book", result.lower())
+
+    def test_normalize_name_removes_part_indicators(self):
+        """Verify part/volume indicators are removed."""
+        result = self.tool.normalize_name("Series Book Part 1 of 3")
+        self.assertNotIn("part 1", result.lower())
+        self.assertNotIn("of 3", result.lower())
+        self.assertIn("series", result.lower())
+        self.assertIn("book", result.lower())
+
+    def test_normalize_name_removes_years(self):
+        """Verify years in parentheses are removed."""
+        result = self.tool.normalize_name("Book Title (2020)")
+        self.assertNotIn("2020", result)
+        self.assertIn("book", result.lower())
+        self.assertIn("title", result.lower())
+
+    def test_normalize_name_keeps_title_words(self):
+        """Verify actual title words are preserved."""
+        result = self.tool.normalize_name("The Great Gatsby")
+        self.assertIn("great", result.lower())
+        self.assertIn("gatsby", result.lower())
+
+    def test_normalize_name_removes_narrated_by(self):
+        """Verify 'narrated by' and narrator names are removed."""
+        result = self.tool.normalize_name("Great Book narrated by Jane Doe")
+        self.assertNotIn("narrated by", result.lower())
+        self.assertNotIn("jane doe", result.lower())
+        self.assertIn("great", result.lower())
+        self.assertIn("book", result.lower())
+
+    def test_normalize_name_removes_standalone_years(self):
+        """Verify standalone years are removed but other text preserved."""
+        result = self.tool.normalize_name("Book Title 2020 Edition")
+        self.assertNotIn("2020", result)
+        self.assertIn("book", result.lower())
+        self.assertIn("title", result.lower())
+        self.assertIn("edition", result.lower())
+
+    def test_normalize_name_removes_volume_indicators(self):
+        """Verify volume/chapter indicators are removed."""
+        result = self.tool.normalize_name("Epic Saga Volume 2")
+        self.assertNotIn("volume 2", result.lower())
+        self.assertNotIn("vol 2", result.lower())
+        self.assertIn("epic", result.lower())
+        self.assertIn("saga", result.lower())
+
+    def test_normalize_name_preserves_trailing_text_after_narrator(self):
+        """Verify trailing text after narrator is preserved."""
+        result = self.tool.normalize_name("Great Book read by John Smith The Sequel")
+        self.assertNotIn("read by", result.lower())
+        self.assertNotIn("john smith", result.lower())
+        self.assertIn("great", result.lower())
+        self.assertIn("book", result.lower())
+        self.assertIn("sequel", result.lower())