Enhancement: add --id-range for document_retagger (#4080)

---------

Co-authored-by: Trenton H <797416+stumpylog@users.noreply.github.com>

diff --git a/docs/administration.md b/docs/administration.md
index 627aa413666f768e35bcb21adf3137e0803d003b..2003edec9a7390ba1542311f88c45cdb1e6bf0e0 100644 (file)
--- a/docs/administration.md
+++ b/docs/administration.md
@@ -351,7 +351,7 @@ currently-imported docs. This problem is common enough that there are
 tools for it.
 
 ```
-document_retagger [-h] [-c] [-T] [-t] [-i] [--use-first] [-f]
+document_retagger [-h] [-c] [-T] [-t] [-i] [--id-range] [--use-first] [-f]
 
 optional arguments:
 -c, --correspondent
@@ -359,6 +359,7 @@ optional arguments:
 -t, --document_type
 -s, --storage_path
 -i, --inbox-only
+--id-range
 --use-first
 -f, --overwrite
 ```
@@ -375,6 +376,11 @@ Specify `-i` to have the document retagger work on documents tagged with
 inbox tags only. This is useful when you don't want to mess with your
 already processed documents.
 
+Specify `--id-range 1 100` to have the document retagger work only on a
+specific range of document id´s. This can be useful if you have a lot of
+documents and want to test the matching rules only on a subset of
+documents.
+
 When multiple document types or correspondents match a single document,
 the retagger won't assign these to the document. Specify `--use-first`
 to override this behavior and just use the first correspondent or type

diff --git a/src/documents/management/commands/document_retagger.py b/src/documents/management/commands/document_retagger.py
index e67d6aed00d5efb261cea5425fdfc81e67bc58c3..385cbf6081bf086f5b634e154757c5d1ace1993f 100644 (file)
--- a/src/documents/management/commands/document_retagger.py
+++ b/src/documents/management/commands/document_retagger.py
@@ -63,6 +63,12 @@ class Command(BaseCommand):
             "--base-url",
             help="The base URL to use to build the link to the documents.",
         )
+        parser.add_argument(
+            "--id-range",
+            help="A range of document ids on which the retagging should be applied.",
+            nargs=2,
+            type=int,
+        )
 
     def handle(self, *args, **options):
         # Detect if we support color
@@ -72,6 +78,12 @@ class Command(BaseCommand):
             queryset = Document.objects.filter(tags__is_inbox_tag=True)
         else:
             queryset = Document.objects.all()
+
+        if options["id_range"]:
+            queryset = queryset.filter(
+                id__range=(options["id_range"][0], options["id_range"][1]),
+            )
+
         documents = queryset.distinct()
 
         classifier = load_classifier()

diff --git a/src/documents/tests/test_management_retagger.py b/src/documents/tests/test_management_retagger.py
index 75e5f7dee777401469df58c1e6952c9b4c1e403d..eb65afb4212c07da0e7c1465fe3b5356fb6a0917 100644 (file)
--- a/src/documents/tests/test_management_retagger.py
+++ b/src/documents/tests/test_management_retagger.py
@@ -1,4 +1,5 @@
 from django.core.management import call_command
+from django.core.management.base import CommandError
 from django.test import TestCase
 
 from documents.models import Correspondent
@@ -258,3 +259,38 @@ class TestRetagger(DirectoriesMixin, TestCase):
         self.assertEqual(d_auto.storage_path, self.sp1)
         self.assertIsNone(d_second.storage_path)
         self.assertEqual(d_unrelated.storage_path, self.sp2)
+
+    def test_id_range_parameter(self):
+        commandOutput = ""
+        Document.objects.create(
+            checksum="E",
+            title="E",
+            content="NOT the first document",
+        )
+        call_command("document_retagger", "--tags", "--id-range", "1", "2")
+        # The retagger shouldn`t apply the 'first' tag to our new document
+        self.assertEqual(Document.objects.filter(tags__id=self.tag_first.id).count(), 1)
+
+        try:
+            commandOutput = call_command("document_retagger", "--tags", "--id-range")
+        except CommandError:
+            # Just ignore the error
+            None
+        self.assertIn(commandOutput, "Error: argument --id-range: expected 2 arguments")
+
+        try:
+            commandOutput = call_command(
+                "document_retagger",
+                "--tags",
+                "--id-range",
+                "a",
+                "b",
+            )
+        except CommandError:
+            # Just ignore the error
+            None
+        self.assertIn(commandOutput, "error: argument --id-range: invalid int value:")
+
+        call_command("document_retagger", "--tags", "--id-range", "1", "9999")
+        # Now we should have 2 documents
+        self.assertEqual(Document.objects.filter(tags__id=self.tag_first.id).count(), 2)