Merge branch 'dev' into beta

.github/workflows/ci-frontend.yml

@@ -191,7 +191,7 @@ jobs:
     runs-on: ubuntu-24.04
     permissions:
       contents: read
-    container: mcr.microsoft.com/playwright:v1.61.1-noble
+    container: mcr.microsoft.com/playwright:v1.60.0-noble
     env:
       PLAYWRIGHT_BROWSERS_PATH: /ms-playwright
       PLAYWRIGHT_SKIP_BROWSER_DOWNLOAD: 1

src-ui/package.json

@@ -11,17 +11,17 @@
   },
   "private": true,
   "dependencies": {
-    "@angular/cdk": "^22.0.2",
-    "@angular/common": "~22.0.3",
-    "@angular/compiler": "~22.0.3",
-    "@angular/core": "~22.0.3",
-    "@angular/forms": "~22.0.3",
-    "@angular/localize": "~22.0.3",
-    "@angular/platform-browser": "~22.0.3",
+    "@angular/cdk": "^21.2.12",
+    "@angular/common": "~21.2.17",
+    "@angular/compiler": "~21.2.17",
+    "@angular/core": "~21.2.17",
+    "@angular/forms": "~21.2.14",
+    "@angular/localize": "~21.2.14",
+    "@angular/platform-browser": "~21.2.14",
     "@angular/platform-browser-dynamic": "~21.2.14",
-    "@angular/router": "~22.0.3",
-    "@ng-bootstrap/ng-bootstrap": "^21.0.0",
-    "@ng-select/ng-select": "^23.0.1",
+    "@angular/router": "~21.2.14",
+    "@ng-bootstrap/ng-bootstrap": "^20.0.0",
+    "@ng-select/ng-select": "^21.8.2",
     "@ngneat/dirty-check-forms": "^3.0.3",
     "@popperjs/core": "^2.11.8",
     "bootstrap": "^5.3.8",
@@ -29,42 +29,42 @@
     "mime-names": "^1.0.0",
     "ngx-bootstrap-icons": "^1.9.3",
     "ngx-color": "^10.1.0",
-    "ngx-cookie-service": "^22.0.0",
-    "ngx-device-detector": "^12.0.0",
+    "ngx-cookie-service": "^21.3.1",
+    "ngx-device-detector": "^11.0.0",
     "ngx-ui-tour-ng-bootstrap": "^18.0.0",
     "normalize-diacritics": "^5.0.0",
     "pdfjs-dist": "^5.7.284",
     "rxjs": "^7.8.2",
     "tslib": "^2.8.1",
     "utif": "^3.1.0",
-    "uuid": "^14.0.1",
+    "uuid": "^14.0.0",
     "zone.js": "^0.16.2"
   },
   "devDependencies": {
-    "@angular-builders/custom-webpack": "^22.0.1",
-    "@angular-builders/jest": "^22.0.1",
-    "@angular-devkit/core": "^22.0.4",
-    "@angular-devkit/schematics": "^22.0.4",
-    "@angular-eslint/builder": "22.0.0",
-    "@angular-eslint/eslint-plugin": "22.0.0",
-    "@angular-eslint/eslint-plugin-template": "22.0.0",
-    "@angular-eslint/schematics": "22.0.0",
-    "@angular-eslint/template-parser": "22.0.0",
-    "@angular/build": "^22.0.4",
-    "@angular/cli": "~22.0.4",
-    "@angular/compiler-cli": "~22.0.3",
+    "@angular-builders/custom-webpack": "^21.0.3",
+    "@angular-builders/jest": "^21.0.3",
+    "@angular-devkit/core": "^21.2.12",
+    "@angular-devkit/schematics": "^21.2.12",
+    "@angular-eslint/builder": "21.4.0",
+    "@angular-eslint/eslint-plugin": "21.4.0",
+    "@angular-eslint/eslint-plugin-template": "21.4.0",
+    "@angular-eslint/schematics": "21.4.0",
+    "@angular-eslint/template-parser": "21.4.0",
+    "@angular/build": "^21.2.12",
+    "@angular/cli": "~21.2.12",
+    "@angular/compiler-cli": "~21.2.14",
     "@codecov/webpack-plugin": "^2.0.1",
-    "@playwright/test": "^1.61.1",
+    "@playwright/test": "^1.60.0",
     "@types/jest": "^30.0.0",
-    "@types/node": "^26.0.0",
-    "@typescript-eslint/eslint-plugin": "^8.62.0",
-    "@typescript-eslint/parser": "^8.62.0",
-    "@typescript-eslint/utils": "^8.62.0",
-    "eslint": "^10.5.0",
+    "@types/node": "^25.9.1",
+    "@typescript-eslint/eslint-plugin": "^8.60.0",
+    "@typescript-eslint/parser": "^8.60.0",
+    "@typescript-eslint/utils": "^8.60.0",
+    "eslint": "^10.4.0",
     "jest": "30.4.2",
     "jest-environment-jsdom": "^30.4.1",
     "jest-junit": "^17.0.0",
-    "jest-preset-angular": "^17.0.0",
+    "jest-preset-angular": "^16.1.5",
     "jest-websocket-mock": "^2.5.0",
     "prettier-plugin-organize-imports": "^4.3.0",
     "ts-node": "~10.9.1",

src/documents/search/_tokenizer.py

@@ -48,6 +48,9 @@ _LANGUAGE_MAP: dict[str, str] = {
 }
 
 SUPPORTED_LANGUAGES: frozenset[str] = frozenset(_LANGUAGE_MAP)
+# Document.title is max_length=128, so use 129 as the limit for
+# Tantivy's remove_long filter
+_TOKEN_REMOVE_LONG_LIMIT: Final[int] = 129
 
 
 def register_tokenizers(index: tantivy.Index, language: str | None) -> None:
@@ -77,10 +80,10 @@ def register_tokenizers(index: tantivy.Index, language: str | None) -> None:
 
 
 def _paperless_text(language: str | None) -> tantivy.TextAnalyzer:
-    """Main full-text tokenizer for content, title, etc: simple -> remove_long(65) -> lowercase -> ascii_fold [-> stemmer]"""
+    """Main full-text tokenizer for content, title, etc: simple -> remove_long(129) -> lowercase -> ascii_fold [-> stemmer]"""
     builder = (
         tantivy.TextAnalyzerBuilder(tantivy.Tokenizer.simple())
-        .filter(tantivy.Filter.remove_long(65))
+        .filter(tantivy.Filter.remove_long(_TOKEN_REMOVE_LONG_LIMIT))
         .filter(tantivy.Filter.lowercase())
         .filter(tantivy.Filter.ascii_fold())
     )
@@ -119,12 +122,12 @@ def _bigram_analyzer() -> tantivy.TextAnalyzer:
 
 
 def _simple_search_analyzer() -> tantivy.TextAnalyzer:
-    """Tokenizer for simple substring search fields: non-whitespace chunks -> remove_long(65) -> lowercase -> ascii_fold."""
+    """Tokenizer for simple substring search fields: non-whitespace chunks -> remove_long(129) -> lowercase -> ascii_fold."""
     return (
         tantivy.TextAnalyzerBuilder(
             tantivy.Tokenizer.regex(r"\S+"),
         )
-        .filter(tantivy.Filter.remove_long(65))
+        .filter(tantivy.Filter.remove_long(_TOKEN_REMOVE_LONG_LIMIT))
         .filter(tantivy.Filter.lowercase())
         .filter(tantivy.Filter.ascii_fold())
         .build()

src/documents/tests/search/test_backend.py

@@ -261,6 +261,36 @@ class TestSearch:
             == 1
         )
 
+    @pytest.mark.parametrize(
+        ("search_mode", "query"),
+        [
+            pytest.param(SearchMode.TITLE, "12345", id="title_search"),
+            pytest.param(SearchMode.TEXT, "12345", id="text_search"),
+            pytest.param(SearchMode.QUERY, None, id="query_title_exact"),
+        ],
+    )
+    def test_search_modes_match_model_limit_title_tokens(
+        self,
+        backend: TantivyBackend,
+        search_mode: SearchMode,
+        query: str | None,
+    ) -> None:
+        """Search must keep filename-like title tokens up to the model limit."""
+        long_title = "1234567890" * 12 + "12345678"
+        doc = Document.objects.create(
+            title=long_title,
+            content="ordinary content",
+            checksum="TXT12",
+            pk=18,
+        )
+        backend.add_or_update(doc)
+
+        assert backend.search_ids(
+            query or f"title:{long_title}",
+            user=None,
+            search_mode=search_mode,
+        ) == [doc.pk]
+
     @pytest.mark.parametrize(
         ("mode", "title", "content", "hits", "misses"),
         [

src/documents/tests/search/test_tokenizer.py

@@ -99,6 +99,25 @@ class TestTokenizers:
         )
         assert simple_search_index.searcher().search(q, limit=5).count == 1
 
+    def test_simple_search_analyzer_supports_model_limit_token_substrings(
+        self,
+        simple_search_index: tantivy.Index,
+    ) -> None:
+        """Simple substring search keeps tokens up to Document.title's model limit."""
+        long_token = "abcdefghij" * 12 + "abcdefgh"
+        writer = simple_search_index.writer()
+        doc = tantivy.Document()
+        doc.add_text("simple_content", long_token)
+        writer.add_document(doc)
+        writer.commit()
+        simple_search_index.reload()
+        q = tantivy.Query.regex_query(
+            simple_search_index.schema,
+            "simple_content",
+            ".*cdefg.*",
+        )
+        assert simple_search_index.searcher().search(q, limit=5).count == 1
+
     def test_unsupported_language_logs_warning(self, caplog: LogCaptureFixture) -> None:
         """Unsupported language codes should log a warning and disable stemming gracefully."""
         sb = tantivy.SchemaBuilder()