Document index accent folding

docs/administration.md

@@ -333,7 +333,7 @@ must be provided to import. If this value is lost, the export cannot be imported
 The document importer takes the export produced by the [Document
 exporter](#exporter) and imports it into paperless.
 
-The importer works just like the exporter. You point it at a directory,
+The importer works just like the exporter. You point it at a directory or the generated .zip file,
 and the script does the rest of the work:
 
 ```shell
@@ -351,9 +351,6 @@ When you use the provided docker compose script, put the export inside
 the `export` folder in your paperless source directory. Specify
 `../export` as the `source`.
 
-Note that .zip files (as can be generated from the exporter) are not supported. You must unzip them into
-the target directory first.
-
 !!! note
 
     Importing from a previous version of Paperless may work, but for best

docs/troubleshooting.md

@@ -130,7 +130,7 @@ command:
     - 'gotenberg'
     - '--chromium-disable-javascript=true'
     - '--chromium-allow-list=file:///tmp/.*'
-    - '--api-timeout=60'
+    - '--api-timeout=60s'
 ```
 
 ## Permission denied errors in the consumption directory

src-ui/angular.json

@@ -27,6 +27,7 @@
           "el-GR": "src/locale/messages.el_GR.xlf",
           "en-GB": "src/locale/messages.en_GB.xlf",
           "es-ES": "src/locale/messages.es_ES.xlf",
+          "fa-IR": "src/locale/messages.fa_IR.xlf",
           "fi-FI": "src/locale/messages.fi_FI.xlf",
           "fr-FR": "src/locale/messages.fr_FR.xlf",
           "hu-HU": "src/locale/messages.hu_HU.xlf",

src-ui/messages.xlf

@@ -9805,123 +9805,130 @@
           <context context-type="linenumber">171</context>
         </context-group>
       </trans-unit>
+      <trans-unit id="4977087909184008115" datatype="html">
+        <source>Persian</source>
+        <context-group purpose="location">
+          <context context-type="sourcefile">src/app/services/settings.service.ts</context>
+          <context context-type="linenumber">177</context>
+        </context-group>
+      </trans-unit>
       <trans-unit id="792060551707690640" datatype="html">
         <source>Polish</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/services/settings.service.ts</context>
-          <context context-type="linenumber">177</context>
+          <context context-type="linenumber">183</context>
         </context-group>
       </trans-unit>
       <trans-unit id="9184513005098760425" datatype="html">
         <source>Portuguese (Brazil)</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/services/settings.service.ts</context>
-          <context context-type="linenumber">183</context>
+          <context context-type="linenumber">189</context>
         </context-group>
       </trans-unit>
       <trans-unit id="153799456510623899" datatype="html">
         <source>Portuguese</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/services/settings.service.ts</context>
-          <context context-type="linenumber">189</context>
+          <context context-type="linenumber">195</context>
         </context-group>
       </trans-unit>
       <trans-unit id="8118856427047826368" datatype="html">
         <source>Romanian</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/services/settings.service.ts</context>
-          <context context-type="linenumber">195</context>
+          <context context-type="linenumber">201</context>
         </context-group>
       </trans-unit>
       <trans-unit id="7137419789978325708" datatype="html">
         <source>Russian</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/services/settings.service.ts</context>
-          <context context-type="linenumber">201</context>
+          <context context-type="linenumber">207</context>
         </context-group>
       </trans-unit>
       <trans-unit id="9102963095355753902" datatype="html">
         <source>Slovak</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/services/settings.service.ts</context>
-          <context context-type="linenumber">207</context>
+          <context context-type="linenumber">213</context>
         </context-group>
       </trans-unit>
       <trans-unit id="4287008301409320881" datatype="html">
         <source>Slovenian</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/services/settings.service.ts</context>
-          <context context-type="linenumber">213</context>
+          <context context-type="linenumber">219</context>
         </context-group>
       </trans-unit>
       <trans-unit id="8608389829607915090" datatype="html">
         <source>Serbian</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/services/settings.service.ts</context>
-          <context context-type="linenumber">219</context>
+          <context context-type="linenumber">225</context>
         </context-group>
       </trans-unit>
       <trans-unit id="499386805970351976" datatype="html">
         <source>Swedish</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/services/settings.service.ts</context>
-          <context context-type="linenumber">225</context>
+          <context context-type="linenumber">231</context>
         </context-group>
       </trans-unit>
       <trans-unit id="5682359291233237791" datatype="html">
         <source>Turkish</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/services/settings.service.ts</context>
-          <context context-type="linenumber">231</context>
+          <context context-type="linenumber">237</context>
         </context-group>
       </trans-unit>
       <trans-unit id="3578644052206125685" datatype="html">
         <source>Ukrainian</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/services/settings.service.ts</context>
-          <context context-type="linenumber">237</context>
+          <context context-type="linenumber">243</context>
         </context-group>
       </trans-unit>
       <trans-unit id="4689443708886954687" datatype="html">
         <source>Chinese Simplified</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/services/settings.service.ts</context>
-          <context context-type="linenumber">243</context>
+          <context context-type="linenumber">249</context>
         </context-group>
       </trans-unit>
       <trans-unit id="8082606363137705994" datatype="html">
         <source>Chinese Traditional</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/services/settings.service.ts</context>
-          <context context-type="linenumber">249</context>
+          <context context-type="linenumber">255</context>
         </context-group>
       </trans-unit>
       <trans-unit id="4912706592792948707" datatype="html">
         <source>ISO 8601</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/services/settings.service.ts</context>
-          <context context-type="linenumber">257</context>
+          <context context-type="linenumber">263</context>
         </context-group>
       </trans-unit>
       <trans-unit id="313643372755303297" datatype="html">
         <source>Successfully completed one-time migratration of settings to the database!</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/services/settings.service.ts</context>
-          <context context-type="linenumber">590</context>
+          <context context-type="linenumber">596</context>
         </context-group>
       </trans-unit>
       <trans-unit id="5558341108007064934" datatype="html">
         <source>Unable to migrate settings to the database, please try saving manually.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/services/settings.service.ts</context>
-          <context context-type="linenumber">591</context>
+          <context context-type="linenumber">597</context>
         </context-group>
       </trans-unit>
       <trans-unit id="1168781785897678748" datatype="html">
         <source>You can restart the tour from the settings page.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/services/settings.service.ts</context>
-          <context context-type="linenumber">664</context>
+          <context context-type="linenumber">670</context>
         </context-group>
       </trans-unit>
       <trans-unit id="3852289441366561594" datatype="html">

src-ui/setup-jest.ts

@@ -20,6 +20,7 @@ import localeDe from '@angular/common/locales/de'
 import localeEl from '@angular/common/locales/el'
 import localeEnGb from '@angular/common/locales/en-GB'
 import localeEs from '@angular/common/locales/es'
+import localeFa from '@angular/common/locales/fa'
 import localeFi from '@angular/common/locales/fi'
 import localeFr from '@angular/common/locales/fr'
 import localeHu from '@angular/common/locales/hu'
@@ -53,6 +54,7 @@ registerLocaleData(localeDe)
 registerLocaleData(localeEl)
 registerLocaleData(localeEnGb)
 registerLocaleData(localeEs)
+registerLocaleData(localeFa)
 registerLocaleData(localeFi)
 registerLocaleData(localeFr)
 registerLocaleData(localeHu)

src-ui/src/app/services/settings.service.ts

@@ -172,6 +172,12 @@ const LANGUAGE_OPTIONS = [
     englishName: 'Norwegian',
     dateInputFormat: 'dd.mm.yyyy',
   },
+  {
+    code: 'fa-ir',
+    name: $localize`Persian`,
+    englishName: 'Persian',
+    dateInputFormat: 'yyyy-mm-dd',
+  },
   {
     code: 'pl-pl',
     name: $localize`Polish`,

src-ui/src/main.ts

@@ -162,6 +162,7 @@ import localeDe from '@angular/common/locales/de'
 import localeEl from '@angular/common/locales/el'
 import localeEnGb from '@angular/common/locales/en-GB'
 import localeEs from '@angular/common/locales/es'
+import localeFa from '@angular/common/locales/fa'
 import localeFi from '@angular/common/locales/fi'
 import localeFr from '@angular/common/locales/fr'
 import localeHu from '@angular/common/locales/hu'
@@ -198,6 +199,7 @@ registerLocaleData(localeDe)
 registerLocaleData(localeEl)
 registerLocaleData(localeEnGb)
 registerLocaleData(localeEs)
+registerLocaleData(localeFa)
 registerLocaleData(localeFi)
 registerLocaleData(localeFr)
 registerLocaleData(localeHu)

src/documents/index.py

@@ -17,6 +17,8 @@ from guardian.shortcuts import get_users_with_perms
 from whoosh import classify
 from whoosh import highlight
 from whoosh import query
+from whoosh.analysis import CharsetFilter
+from whoosh.analysis import StemmingAnalyzer
 from whoosh.fields import BOOLEAN
 from whoosh.fields import DATETIME
 from whoosh.fields import KEYWORD
@@ -36,6 +38,7 @@ from whoosh.qparser.dateparse import DateParserPlugin
 from whoosh.qparser.dateparse import English
 from whoosh.qparser.plugins import FieldsPlugin
 from whoosh.scoring import TF_IDF
+from whoosh.support.charset import accent_map
 from whoosh.util.times import timespan
 from whoosh.writing import AsyncWriter
 
@@ -54,10 +57,13 @@ logger = logging.getLogger("paperless.index")
 
 
 def get_schema() -> Schema:
+    # add accent-folding filter to a stemming analyzer:
+    af_analyzer = StemmingAnalyzer() | CharsetFilter(accent_map)
+
     return Schema(
         id=NUMERIC(stored=True, unique=True),
-        title=TEXT(sortable=True),
-        content=TEXT(),
+        title=TEXT(sortable=True, analyzer=af_analyzer),
+        content=TEXT(analyzer=af_analyzer),
         asn=NUMERIC(sortable=True, signed=False),
         correspondent=TEXT(sortable=True),
         correspondent_id=NUMERIC(),

src/documents/management/commands/document_importer.py

@@ -1,9 +1,12 @@
 import json
 import logging
 import os
+import tempfile
 from collections.abc import Generator
 from contextlib import contextmanager
 from pathlib import Path
+from zipfile import ZipFile
+from zipfile import is_zipfile
 
 import tqdm
 from django.conf import settings
@@ -234,14 +237,19 @@ class Command(CryptMixin, BaseCommand):
         self.manifest_paths = []
         self.manifest = []
 
+        # Create a temporary directory for extracting a zip file into it, even if supplied source is no zip file to keep code cleaner.
+        with tempfile.TemporaryDirectory() as tmp_dir:
+            if is_zipfile(self.source):
+                with ZipFile(self.source) as zf:
+                    zf.extractall(tmp_dir)
+                self.source = Path(tmp_dir)
+            self._run_import()
+
+    def _run_import(self):
         self.pre_check()
-
         self.load_metadata()
-
         self.load_manifest_files()
-
         self.check_manifest_validity()
-
         self.decrypt_secret_fields()
 
         # see /src/documents/signals/handlers.py

src/documents/tests/test_api_search.py

@@ -557,7 +557,7 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
 
         response = self.client.get("/api/search/autocomplete/?term=app")
         self.assertEqual(response.status_code, status.HTTP_200_OK)
-        self.assertEqual(response.data, [b"apples", b"applebaum", b"appletini"])
+        self.assertEqual(response.data, [b"appl", b"applebaum", b"appletini"])
 
         d3.owner = u2
 
@@ -566,7 +566,7 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
 
         response = self.client.get("/api/search/autocomplete/?term=app")
         self.assertEqual(response.status_code, status.HTTP_200_OK)
-        self.assertEqual(response.data, [b"apples", b"applebaum"])
+        self.assertEqual(response.data, [b"appl", b"applebaum"])
 
         assign_perm("view_document", u1, d3)
 
@@ -575,7 +575,7 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
 
         response = self.client.get("/api/search/autocomplete/?term=app")
         self.assertEqual(response.status_code, status.HTTP_200_OK)
-        self.assertEqual(response.data, [b"apples", b"applebaum", b"appletini"])
+        self.assertEqual(response.data, [b"appl", b"applebaum", b"appletini"])
 
     def test_search_autocomplete_field_name_match(self):
         """

src/documents/tests/test_management_importer.py

@@ -2,6 +2,7 @@ import json
 import tempfile
 from io import StringIO
 from pathlib import Path
+from zipfile import ZipFile
 
 from django.contrib.auth.models import User
 from django.core.management import call_command
@@ -335,3 +336,42 @@ class TestCommandImport(
 
         self.assertIn("Version mismatch:", stdout_str)
         self.assertIn("importing 2.8.1", stdout_str)
+
+    def test_import_zipped_export(self):
+        """
+        GIVEN:
+            - A zip file with correct content (manifest.json and version.json inside)
+        WHEN:
+            - An import is attempted using the zip file as the source
+        THEN:
+            - The command reads from the zip without warnings or errors
+        """
+
+        stdout = StringIO()
+        zip_path = self.dirs.scratch_dir / "export.zip"
+
+        # Create manifest.json and version.json in a temp dir
+        with tempfile.TemporaryDirectory() as temp_dir:
+            temp_dir_path = Path(temp_dir)
+
+            (temp_dir_path / "manifest.json").touch()
+            (temp_dir_path / "version.json").touch()
+
+            # Create the zip file
+            with ZipFile(zip_path, "w") as zf:
+                zf.write(temp_dir_path / "manifest.json", arcname="manifest.json")
+                zf.write(temp_dir_path / "version.json", arcname="version.json")
+
+        # Try to import from the zip file
+        with self.assertRaises(json.decoder.JSONDecodeError):
+            call_command(
+                "document_importer",
+                "--no-progress-bar",
+                str(zip_path),
+                stdout=stdout,
+            )
+        stdout.seek(0)
+        stdout_str = str(stdout.read())
+
+        # There should be no error or warnings. Therefore the output should be empty.
+        self.assertEqual(stdout_str, "")

src/locale/en_US/LC_MESSAGES/django.po

@@ -2,7 +2,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: paperless-ngx\n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2025-05-24 17:14+0000\n"
+"POT-Creation-Date: 2025-06-14 19:08-0700\n"
 "PO-Revision-Date: 2022-02-17 04:17\n"
 "Last-Translator: \n"
 "Language-Team: English\n"
@@ -1694,90 +1694,94 @@ msgid "Spanish"
 msgstr ""
 
 #: paperless/settings.py:766
-msgid "Finnish"
+msgid "Persian"
 msgstr ""
 
 #: paperless/settings.py:767
-msgid "French"
+msgid "Finnish"
 msgstr ""
 
 #: paperless/settings.py:768
-msgid "Hungarian"
+msgid "French"
 msgstr ""
 
 #: paperless/settings.py:769
-msgid "Italian"
+msgid "Hungarian"
 msgstr ""
 
 #: paperless/settings.py:770
-msgid "Japanese"
+msgid "Italian"
 msgstr ""
 
 #: paperless/settings.py:771
-msgid "Korean"
+msgid "Japanese"
 msgstr ""
 
 #: paperless/settings.py:772
-msgid "Luxembourgish"
+msgid "Korean"
 msgstr ""
 
 #: paperless/settings.py:773
-msgid "Norwegian"
+msgid "Luxembourgish"
 msgstr ""
 
 #: paperless/settings.py:774
-msgid "Dutch"
+msgid "Norwegian"
 msgstr ""
 
 #: paperless/settings.py:775
-msgid "Polish"
+msgid "Dutch"
 msgstr ""
 
 #: paperless/settings.py:776
-msgid "Portuguese (Brazil)"
+msgid "Polish"
 msgstr ""
 
 #: paperless/settings.py:777
-msgid "Portuguese"
+msgid "Portuguese (Brazil)"
 msgstr ""
 
 #: paperless/settings.py:778
-msgid "Romanian"
+msgid "Portuguese"
 msgstr ""
 
 #: paperless/settings.py:779
-msgid "Russian"
+msgid "Romanian"
 msgstr ""
 
 #: paperless/settings.py:780
-msgid "Slovak"
+msgid "Russian"
 msgstr ""
 
 #: paperless/settings.py:781
-msgid "Slovenian"
+msgid "Slovak"
 msgstr ""
 
 #: paperless/settings.py:782
-msgid "Serbian"
+msgid "Slovenian"
 msgstr ""
 
 #: paperless/settings.py:783
-msgid "Swedish"
+msgid "Serbian"
 msgstr ""
 
 #: paperless/settings.py:784
-msgid "Turkish"
+msgid "Swedish"
 msgstr ""
 
 #: paperless/settings.py:785
-msgid "Ukrainian"
+msgid "Turkish"
 msgstr ""
 
 #: paperless/settings.py:786
-msgid "Chinese Simplified"
+msgid "Ukrainian"
 msgstr ""
 
 #: paperless/settings.py:787
+msgid "Chinese Simplified"
+msgstr ""
+
+#: paperless/settings.py:788
 msgid "Chinese Traditional"
 msgstr ""
 

src/paperless/settings.py

@@ -763,6 +763,7 @@ LANGUAGES = [
     ("el-gr", _("Greek")),
     ("en-gb", _("English (GB)")),
     ("es-es", _("Spanish")),
+    ("fa-ir", _("Persian")),
     ("fi-fi", _("Finnish")),
     ("fr-fr", _("French")),
     ("hu-hu", _("Hungarian")),