Merge branch 'dev' into feature-unified-search

src/documents/consumer.py

@@ -64,9 +64,9 @@ class Consumer(LoggingMixin):
                                                      {'type': 'status_update',
                                                       'data': payload})
 
-    def _fail(self, message, log_message=None):
+    def _fail(self, message, log_message=None, exc_info=None):
         self._send_progress(100, 100, 'FAILED', message)
-        self.log("error", log_message or message)
+        self.log("error", log_message or message, exc_info=exc_info)
         raise ConsumerError(f"{self.filename}: {log_message or message}")
 
     def __init__(self):
@@ -120,7 +120,8 @@ class Consumer(LoggingMixin):
         except Exception as e:
             self._fail(
                 MESSAGE_PRE_CONSUME_SCRIPT_ERROR,
-                f"Error while executing pre-consume script: {e}"
+                f"Error while executing pre-consume script: {e}",
+                exc_info=True
             )
 
     def run_post_consume_script(self, document):
@@ -150,7 +151,8 @@ class Consumer(LoggingMixin):
         except Exception as e:
             self._fail(
                 MESSAGE_POST_CONSUME_SCRIPT_ERROR,
-                f"Error while executing post-consume script: {e}"
+                f"Error while executing post-consume script: {e}",
+                exc_info=True
             )
 
     def try_consume_file(self,
@@ -255,7 +257,8 @@ class Consumer(LoggingMixin):
             document_parser.cleanup()
             self._fail(
                 str(e),
-                f"Error while consuming document {self.filename}: {e}"
+                f"Error while consuming document {self.filename}: {e}",
+                exc_info=True
             )
 
         # Prepare the document classifier.
@@ -326,7 +329,8 @@ class Consumer(LoggingMixin):
             self._fail(
                 str(e),
                 f"The following error occured while consuming "
-                f"{self.filename}: {e}"
+                f"{self.filename}: {e}",
+                exc_info=True
             )
         finally:
             document_parser.cleanup()

src/documents/management/commands/document_exporter.py

@@ -6,15 +6,18 @@ import time
 
 import tqdm
 from django.conf import settings
+from django.contrib.auth.models import User
 from django.core import serializers
 from django.core.management.base import BaseCommand, CommandError
 from django.db import transaction
 from filelock import FileLock
 
-from documents.models import Document, Correspondent, Tag, DocumentType
+from documents.models import Document, Correspondent, Tag, DocumentType, \
+    SavedView, SavedViewFilterRule
 from documents.settings import EXPORTER_FILE_NAME, EXPORTER_THUMBNAIL_NAME, \
     EXPORTER_ARCHIVE_NAME
 from paperless.db import GnuPG
+from paperless_mail.models import MailAccount, MailRule
 from ...file_handling import generate_filename, delete_empty_directories
 
 
@@ -105,6 +108,21 @@ class Command(BaseCommand):
                 serializers.serialize("json", documents))
             manifest += document_manifest
 
+            manifest += json.loads(serializers.serialize(
+                "json", MailAccount.objects.all()))
+
+            manifest += json.loads(serializers.serialize(
+                "json", MailRule.objects.all()))
+
+            manifest += json.loads(serializers.serialize(
+                "json", SavedView.objects.all()))
+
+            manifest += json.loads(serializers.serialize(
+                "json", SavedViewFilterRule.objects.all()))
+
+            manifest += json.loads(serializers.serialize(
+                "json", User.objects.all()))
+
         # 3. Export files from each document
         for index, document_dict in tqdm.tqdm(enumerate(document_manifest),
                                               total=len(document_manifest)):

src/documents/matching.py

@@ -90,7 +90,7 @@ def matches(matching_model, document):
 
     elif matching_model.matching_algorithm == MatchingModel.MATCH_LITERAL:
         result = bool(re.search(
-            rf"\b{matching_model.match}\b",
+            rf"\b{re.escape(matching_model.match)}\b",
             document_content,
             **search_kwargs
         ))
@@ -161,6 +161,9 @@ def _split_match(matching_model):
     findterms = re.compile(r'"([^"]+)"|(\S+)').findall
     normspace = re.compile(r"\s+").sub
     return [
-        normspace(" ", (t[0] or t[1]).strip()).replace(" ", r"\s+")
+        # normspace(" ", (t[0] or t[1]).strip()).replace(" ", r"\s+")
+        re.escape(
+            normspace(" ", (t[0] or t[1]).strip())
+        ).replace(r"\ ", r"\s+")
         for t in findterms(matching_model.match)
     ]

src/documents/tests/test_management_exporter.py

@@ -69,7 +69,7 @@ class TestExportImport(DirectoriesMixin, TestCase):
 
         manifest = self._do_export(use_filename_format=use_filename_format)
 
-        self.assertEqual(len(manifest), 7)
+        self.assertEqual(len(manifest), 8)
         self.assertEqual(len(list(filter(lambda e: e['model'] == 'documents.document', manifest))), 4)
 
         self.assertTrue(os.path.exists(os.path.join(self.target, "manifest.json")))