Merge branch 'dev' into feature-ocrmypdf

src/documents/tests/test_api.py

@@ -325,6 +325,22 @@ class DocumentApiTest(DirectoriesMixin, APITestCase):
         self.assertEqual(response.status_code, 200)
         self.assertEqual(len(response.data), 10)
 
+    def test_search_spelling_correction(self):
+        with AsyncWriter(index.open_index()) as writer:
+            for i in range(55):
+                doc = Document.objects.create(checksum=str(i), pk=i+1, title=f"Document {i+1}", content=f"Things document {i+1}")
+                index.update_document(writer, doc)
+
+        response = self.client.get("/api/search/?query=thing")
+        correction = response.data['corrected_query']
+
+        self.assertEqual(correction, "things")
+
+        response = self.client.get("/api/search/?query=things")
+        correction = response.data['corrected_query']
+
+        self.assertEqual(correction, None)
+
     def test_statistics(self):
 
         doc1 = Document.objects.create(title="none1", checksum="A")

src/documents/tests/test_consumer.py

@@ -425,7 +425,7 @@ class TestConsumer(DirectoriesMixin, TestCase):
         m = patcher.start()
         m.return_value = [(None, {
             "parser": self.make_dummy_parser,
-            "mime_types": ["application/pdf"],
+            "mime_types": {"application/pdf": ".pdf"},
             "weight": 0
         })]
 
@@ -551,7 +551,7 @@ class TestConsumer(DirectoriesMixin, TestCase):
         try:
             self.consumer.try_consume_file(self.get_test_file())
         except ConsumerError as e:
-            self.assertTrue(str(e).startswith("No parsers abvailable"))
+            self.assertTrue("File extension .pdf does not map to any" in str(e))
             return
 
         self.fail("Should throw exception")
@@ -560,7 +560,7 @@ class TestConsumer(DirectoriesMixin, TestCase):
     def testFaultyParser(self, m):
         m.return_value = [(None, {
             "parser": self.make_faulty_parser,
-            "mime_types": ["application/pdf"],
+            "mime_types": {"application/pdf": ".pdf"},
             "weight": 0
         })]
 

src/documents/tests/test_parsers.py

@@ -6,7 +6,10 @@ from unittest import mock
 
 from django.test import TestCase, override_settings
 
-from documents.parsers import get_parser_class, DocumentParser
+from documents.parsers import get_parser_class, get_supported_file_extensions, get_default_file_extension, \
+    get_parser_class_for_mime_type, DocumentParser
+from paperless_tesseract.parsers import RasterisedDocumentParser
+from paperless_text.parsers import TextDocumentParser
 
 
 def fake_magic_from_file(file, mime=False):
@@ -29,7 +32,7 @@ class TestParserDiscovery(TestCase):
             pass
 
         m.return_value = (
-            (None, {"weight": 0, "parser": DummyParser, "mime_types": ["application/pdf"]}),
+            (None, {"weight": 0, "parser": DummyParser, "mime_types": {"application/pdf": ".pdf"}}),
         )
 
         self.assertEqual(
@@ -47,8 +50,8 @@ class TestParserDiscovery(TestCase):
             pass
 
         m.return_value = (
-            (None, {"weight": 0, "parser": DummyParser1, "mime_types": ["application/pdf"]}),
-            (None, {"weight": 1, "parser": DummyParser2, "mime_types": ["application/pdf"]}),
+            (None, {"weight": 0, "parser": DummyParser1, "mime_types": {"application/pdf": ".pdf"}}),
+            (None, {"weight": 1, "parser": DummyParser2, "mime_types": {"application/pdf": ".pdf"}}),
         )
 
         self.assertEqual(
@@ -96,3 +99,20 @@ class TestBaseParser(TestCase):
         path = parser.get_optimised_thumbnail("any", "not important")
         self.assertEqual(path, fake_get_thumbnail(None, None, None))
 
+
+class TestParserAvailability(TestCase):
+
+    def test_file_extensions(self):
+
+        for ext in [".pdf", ".jpe", ".jpg", ".jpeg", ".txt", ".csv"]:
+            self.assertIn(ext, get_supported_file_extensions())
+        self.assertEqual(get_default_file_extension('application/pdf'), ".pdf")
+        self.assertEqual(get_default_file_extension('image/png'), ".png")
+        self.assertEqual(get_default_file_extension('image/jpeg'), ".jpg")
+        self.assertEqual(get_default_file_extension('text/plain'), ".txt")
+        self.assertEqual(get_default_file_extension('text/csv'), ".csv")
+        self.assertEqual(get_default_file_extension('aasdasd/dgfgf'), None)
+
+        self.assertEqual(get_parser_class_for_mime_type('application/pdf'), RasterisedDocumentParser)
+        self.assertEqual(get_parser_class_for_mime_type('text/plain'), TextDocumentParser)
+        self.assertEqual(get_parser_class_for_mime_type('text/sdgsdf'), None)