Merge pull request #933 from sbrunner/suggest

Add suggest

src/documents/management/commands/document_retagger.py

@@ -63,8 +63,20 @@ class Command(BaseCommand):
             action="store_true",
             help="If set, the progress bar will not be shown"
         )
+        parser.add_argument(
+            "--suggest",
+            default=False,
+            action="store_true",
+            help="Return the suggestion, don't change anything."
+        )
+        parser.add_argument(
+            "--base-url",
+            help="The base URL to use to build the link to the documents."
+        )
 
     def handle(self, *args, **options):
+        # Detect if we support color
+        color = self.style.ERROR("test") != "test"
 
         if options["inbox_only"]:
             queryset = Document.objects.filter(tags__is_inbox_tag=True)
@@ -85,18 +97,27 @@ class Command(BaseCommand):
                     document=document,
                     classifier=classifier,
                     replace=options['overwrite'],
-                    use_first=options['use_first'])
+                    use_first=options['use_first'],
+                    suggest=options['suggest'],
+                    base_url=options['base_url'],
+                    color=color)
 
             if options['document_type']:
                 set_document_type(sender=None,
                                   document=document,
                                   classifier=classifier,
                                   replace=options['overwrite'],
-                                  use_first=options['use_first'])
+                                  use_first=options['use_first'],
+                                  suggest=options['suggest'],
+                                  base_url=options['base_url'],
+                                  color=color)
 
             if options['tags']:
                 set_tags(
                     sender=None,
                     document=document,
                     classifier=classifier,
-                    replace=options['overwrite'])
+                    replace=options['overwrite'],
+                    suggest=options['suggest'],
+                    base_url=options['base_url'],
+                    color=color)

src/documents/signals/handlers.py

@@ -1,6 +1,7 @@
 import logging
 import os
 
+from django.utils import termcolors
 from django.conf import settings
 from django.contrib.admin.models import ADDITION, LogEntry
 from django.contrib.auth.models import User
@@ -8,14 +9,14 @@ from django.contrib.contenttypes.models import ContentType
 from django.db import models, DatabaseError
 from django.db.models import Q
 from django.dispatch import receiver
-from django.utils import timezone
+from django.utils import termcolors, timezone
 from filelock import FileLock
 
 from .. import matching
 from ..file_handling import delete_empty_directories, \
     create_source_path_directory, \
     generate_unique_filename
-from ..models import Document, Tag
+from ..models import Document, Tag, MatchingModel
 
 
 logger = logging.getLogger("paperless.handlers")
@@ -32,6 +33,9 @@ def set_correspondent(sender,
                       classifier=None,
                       replace=False,
                       use_first=True,
+                      suggest=False,
+                      base_url=None,
+                      color=False,
                       **kwargs):
     if document.correspondent and not replace:
         return
@@ -60,6 +64,24 @@ def set_correspondent(sender,
             return
 
     if selected or replace:
+        if suggest:
+            if base_url:
+                print(
+                    termcolors.colorize(str(document), fg='green')
+                    if color
+                    else str(document)
+                )
+                print(f"{base_url}/documents/{document.pk}")
+            else:
+                print(
+                    (
+                        termcolors.colorize(str(document), fg='green')
+                        if color
+                        else str(document)
+                    ) + f" [{document.pk}]"
+                )
+            print(f"Suggest correspondent {selected}")
+        else:
             logger.info(
                 f"Assigning correspondent {selected} to {document}",
                 extra={'group': logging_group}
@@ -75,6 +97,9 @@ def set_document_type(sender,
                       classifier=None,
                       replace=False,
                       use_first=True,
+                      suggest=False,
+                      base_url=None,
+                      color=False,
                       **kwargs):
     if document.document_type and not replace:
         return
@@ -104,6 +129,24 @@ def set_document_type(sender,
             return
 
     if selected or replace:
+        if suggest:
+            if base_url:
+                print(
+                    termcolors.colorize(str(document), fg='green')
+                    if color
+                    else str(document)
+                )
+                print(f"{base_url}/documents/{document.pk}")
+            else:
+                print(
+                    (
+                        termcolors.colorize(str(document), fg='green')
+                        if color
+                        else str(document)
+                    ) + f" [{document.pk}]"
+                )
+            print(f"Sugest document type {selected}")
+        else:
             logger.info(
                 f"Assigning document type {selected} to {document}",
                 extra={'group': logging_group}
@@ -118,6 +161,9 @@ def set_tags(sender,
              logging_group=None,
              classifier=None,
              replace=False,
+             suggest=False,
+             base_url=None,
+             color=False,
              **kwargs):
 
     if replace:
@@ -132,12 +178,44 @@ def set_tags(sender,
 
     relevant_tags = set(matched_tags) - current_tags
 
+    if suggest:
+        extra_tags = current_tags - set(matched_tags)
+        extra_tags = [
+            t for t in extra_tags
+            if t.matching_algorithm == MatchingModel.MATCH_AUTO
+        ]
+        if not relevant_tags and not extra_tags:
+            return
+        if base_url:
+            print(
+                termcolors.colorize(str(document), fg='green')
+                if color
+                else str(document)
+            )
+            print(f"{base_url}/documents/{document.pk}")
+        else:
+            print(
+                (
+                    termcolors.colorize(str(document), fg='green')
+                    if color
+                    else str(document)
+                ) + f" [{document.pk}]"
+            )
+        if relevant_tags:
+            print(
+                "Suggest tags: " + ", ".join([t.name for t in relevant_tags])
+            )
+        if extra_tags:
+            print("Extra tags: " + ", ".join([t.name for t in extra_tags]))
+    else:
         if not relevant_tags:
             return
 
         message = 'Tagging "{}" with "{}"'
         logger.info(
-        message.format(document, ", ".join([t.name for t in relevant_tags])),
+            message.format(
+                document, ", ".join([t.name for t in relevant_tags])
+            ),
             extra={'group': logging_group}
         )
 

src/documents/tests/test_management_retagger.py

@@ -11,14 +11,17 @@ class TestRetagger(DirectoriesMixin, TestCase):
         self.d1 = Document.objects.create(checksum="A", title="A", content="first document")
         self.d2 = Document.objects.create(checksum="B", title="B", content="second document")
         self.d3 = Document.objects.create(checksum="C", title="C", content="unrelated document")
+        self.d4 = Document.objects.create(checksum="D", title="D", content="auto document")
 
         self.tag_first = Tag.objects.create(name="tag1", match="first", matching_algorithm=Tag.MATCH_ANY)
         self.tag_second = Tag.objects.create(name="tag2", match="second", matching_algorithm=Tag.MATCH_ANY)
         self.tag_inbox = Tag.objects.create(name="test", is_inbox_tag=True)
         self.tag_no_match = Tag.objects.create(name="test2")
+        self.tag_auto = Tag.objects.create(name="tagauto", matching_algorithm=Tag.MATCH_AUTO)
 
         self.d3.tags.add(self.tag_inbox)
         self.d3.tags.add(self.tag_no_match)
+        self.d4.tags.add(self.tag_auto)
 
 
         self.correspondent_first = Correspondent.objects.create(
@@ -32,7 +35,8 @@ class TestRetagger(DirectoriesMixin, TestCase):
             name="dt2", match="second", matching_algorithm=DocumentType.MATCH_ANY)
 
     def get_updated_docs(self):
-        return Document.objects.get(title="A"), Document.objects.get(title="B"), Document.objects.get(title="C")
+        return Document.objects.get(title="A"), Document.objects.get(title="B"), \
+            Document.objects.get(title="C"), Document.objects.get(title="D")
 
     def setUp(self) -> None:
         super(TestRetagger, self).setUp()
@@ -40,25 +44,26 @@ class TestRetagger(DirectoriesMixin, TestCase):
 
     def test_add_tags(self):
         call_command('document_retagger', '--tags')
-        d_first, d_second, d_unrelated = self.get_updated_docs()
+        d_first, d_second, d_unrelated, d_auto = self.get_updated_docs()
 
         self.assertEqual(d_first.tags.count(), 1)
         self.assertEqual(d_second.tags.count(), 1)
         self.assertEqual(d_unrelated.tags.count(), 2)
+        self.assertEqual(d_auto.tags.count(), 1)
 
         self.assertEqual(d_first.tags.first(), self.tag_first)
         self.assertEqual(d_second.tags.first(), self.tag_second)
 
     def test_add_type(self):
         call_command('document_retagger', '--document_type')
-        d_first, d_second, d_unrelated = self.get_updated_docs()
+        d_first, d_second, d_unrelated, d_auto = self.get_updated_docs()
 
         self.assertEqual(d_first.document_type, self.doctype_first)
         self.assertEqual(d_second.document_type, self.doctype_second)
 
     def test_add_correspondent(self):
         call_command('document_retagger', '--correspondent')
-        d_first, d_second, d_unrelated = self.get_updated_docs()
+        d_first, d_second, d_unrelated, d_auto = self.get_updated_docs()
 
         self.assertEqual(d_first.correspondent, self.correspondent_first)
         self.assertEqual(d_second.correspondent, self.correspondent_second)
@@ -68,11 +73,55 @@ class TestRetagger(DirectoriesMixin, TestCase):
 
         call_command('document_retagger', '--tags', '--overwrite')
 
-        d_first, d_second, d_unrelated = self.get_updated_docs()
+        d_first, d_second, d_unrelated, d_auto = self.get_updated_docs()
 
         self.assertIsNotNone(Tag.objects.get(id=self.tag_second.id))
 
         self.assertCountEqual([tag.id for tag in d_first.tags.all()], [self.tag_first.id])
         self.assertCountEqual([tag.id for tag in d_second.tags.all()], [self.tag_second.id])
         self.assertCountEqual([tag.id for tag in d_unrelated.tags.all()], [self.tag_inbox.id, self.tag_no_match.id])
+        self.assertEqual(d_auto.tags.count(), 0)
 
+    def test_add_tags_suggest(self):
+        call_command('document_retagger', '--tags', '--suggest')
+        d_first, d_second, d_unrelated, d_auto = self.get_updated_docs()
+
+        self.assertEqual(d_first.tags.count(), 0)
+        self.assertEqual(d_second.tags.count(), 0)
+        self.assertEqual(d_auto.tags.count(), 1)
+
+    def test_add_type_suggest(self):
+        call_command('document_retagger', '--document_type', '--suggest')
+        d_first, d_second, d_unrelated, d_auto = self.get_updated_docs()
+
+        self.assertEqual(d_first.document_type, None)
+        self.assertEqual(d_second.document_type, None)
+
+    def test_add_correspondent_suggest(self):
+        call_command('document_retagger', '--correspondent', '--suggest')
+        d_first, d_second, d_unrelated, d_auto = self.get_updated_docs()
+
+        self.assertEqual(d_first.correspondent, None)
+        self.assertEqual(d_second.correspondent, None)
+
+    def test_add_tags_suggest_url(self):
+        call_command('document_retagger', '--tags', '--suggest', '--base-url=http://localhost')
+        d_first, d_second, d_unrelated, d_auto = self.get_updated_docs()
+
+        self.assertEqual(d_first.tags.count(), 0)
+        self.assertEqual(d_second.tags.count(), 0)
+        self.assertEqual(d_auto.tags.count(), 1)
+
+    def test_add_type_suggest_url(self):
+        call_command('document_retagger', '--document_type', '--suggest', '--base-url=http://localhost')
+        d_first, d_second, d_unrelated, d_auto = self.get_updated_docs()
+
+        self.assertEqual(d_first.document_type, None)
+        self.assertEqual(d_second.document_type, None)
+
+    def test_add_correspondent_suggest_url(self):
+        call_command('document_retagger', '--correspondent', '--suggest', '--base-url=http://localhost')
+        d_first, d_second, d_unrelated, d_auto = self.get_updated_docs()
+
+        self.assertEqual(d_first.correspondent, None)
+        self.assertEqual(d_second.correspondent, None)