validation for regular expressions on matching models #605

src/documents/serialisers.py

@@ -1,11 +1,13 @@
+import re
+
 import magic
 from django.utils.text import slugify
 from rest_framework import serializers
 from rest_framework.fields import SerializerMethodField
 
 from . import bulk_edit
-from .models import Correspondent, Tag, Document, Log, DocumentType, \
+from .models import Correspondent, Tag, Document, DocumentType, \
-    SavedView, SavedViewFilterRule
+    SavedView, SavedViewFilterRule, MatchingModel
 from .parsers import is_mime_type_supported
 
 from django.utils.translation import gettext as _
@@ -33,16 +35,27 @@ class DynamicFieldsModelSerializer(serializers.ModelSerializer):
                 self.fields.pop(field_name)
 
 
-class CorrespondentSerializer(serializers.ModelSerializer):
+class MatchingModelSerializer(serializers.ModelSerializer):
 
     document_count = serializers.IntegerField(read_only=True)
 
-    last_correspondence = serializers.DateTimeField(read_only=True)
-
     def get_slug(self, obj):
         return slugify(obj.name)
     slug = SerializerMethodField()
 
+    def validate_match(self, match):
+        if 'matching_algorithm' in self.initial_data and self.initial_data['matching_algorithm'] == MatchingModel.MATCH_REGEX:  # NOQA: E501
+            try:
+                re.compile(match)
+            except Exception as e:
+                raise serializers.ValidationError(_("Invalid regular expresssion: ") + str(e))
+        return match
+
+
+class CorrespondentSerializer(MatchingModelSerializer):
+
+    last_correspondence = serializers.DateTimeField(read_only=True)
+
     class Meta:
         model = Correspondent
         fields = (
@@ -57,13 +70,7 @@ class CorrespondentSerializer(serializers.ModelSerializer):
         )
 
 
-class DocumentTypeSerializer(serializers.ModelSerializer):
+class DocumentTypeSerializer(MatchingModelSerializer):
-
-    document_count = serializers.IntegerField(read_only=True)
-
-    def get_slug(self, obj):
-        return slugify(obj.name)
-    slug = SerializerMethodField()
 
     class Meta:
         model = DocumentType
@@ -78,13 +85,7 @@ class DocumentTypeSerializer(serializers.ModelSerializer):
         )
 
 
-class TagSerializer(serializers.ModelSerializer):
+class TagSerializer(MatchingModelSerializer):
-
-    document_count = serializers.IntegerField(read_only=True)
-
-    def get_slug(self, obj):
-        return slugify(obj.name)
-    slug = SerializerMethodField()
 
     class Meta:
         model = Tag

src/documents/tests/test_api.py

@@ -14,7 +14,7 @@ from rest_framework.test import APITestCase
 from whoosh.writing import AsyncWriter
 
 from documents import index, bulk_edit
-from documents.models import Document, Correspondent, DocumentType, Tag, SavedView
+from documents.models import Document, Correspondent, DocumentType, Tag, SavedView, MatchingModel
 from documents.tests.utils import DirectoriesMixin
 
 
@@ -772,6 +772,41 @@ class TestDocumentApi(DirectoriesMixin, APITestCase):
         self.assertEqual(response.status_code, 200)
         self.assertListEqual(response.data, ["test", "test2"])
 
+    def test_invalid_regex_other_algorithm(self):
+        for endpoint in ['correspondents', 'tags', 'document_types']:
+            response = self.client.post(f"/api/{endpoint}/", {
+                "name": "test",
+                "matching_algorithm": MatchingModel.MATCH_ANY,
+                "match": "["
+            }, format='json')
+            self.assertEqual(response.status_code, 201, endpoint)
+
+    def test_invalid_regex(self):
+        for endpoint in ['correspondents', 'tags', 'document_types']:
+            response = self.client.post(f"/api/{endpoint}/", {
+                "name": "test",
+                "matching_algorithm": MatchingModel.MATCH_REGEX,
+                "match": "["
+            }, format='json')
+            self.assertEqual(response.status_code, 400, endpoint)
+
+    def test_valid_regex(self):
+        for endpoint in ['correspondents', 'tags', 'document_types']:
+            response = self.client.post(f"/api/{endpoint}/", {
+                "name": "test",
+                "matching_algorithm": MatchingModel.MATCH_REGEX,
+                "match": "[0-9]"
+            }, format='json')
+            self.assertEqual(response.status_code, 201, endpoint)
+
+    def test_regex_no_algorithm(self):
+        for endpoint in ['correspondents', 'tags', 'document_types']:
+            response = self.client.post(f"/api/{endpoint}/", {
+                "name": "test",
+                "match": "[0-9]"
+            }, format='json')
+            self.assertEqual(response.status_code, 201, endpoint)
+
 
 class TestBulkEdit(DirectoriesMixin, APITestCase):
 

src/locale/en_US/LC_MESSAGES/django.po

@@ -8,7 +8,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: PACKAGE VERSION\n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2021-02-16 14:52+0100\n"
+"POT-Creation-Date: 2021-02-23 12:30+0100\n"
 "PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
 "Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
 "Language-Team: LANGUAGE <LL@li.org>\n"
@@ -346,7 +346,11 @@ msgstr ""
 msgid "filter rules"
 msgstr ""
 
-#: documents/serialisers.py:370
+#: documents/serialisers.py:52
+msgid "Invalid regular expresssion: "
+msgstr ""
+
+#: documents/serialisers.py:376
 #, python-format
 msgid "File type %(type)s not supported"
 msgstr ""
@@ -411,7 +415,7 @@ msgstr ""
 msgid "French"
 msgstr ""
 
-#: paperless/urls.py:114
+#: paperless/urls.py:118
 msgid "Paperless-ng administration"
 msgstr ""