Merge branch 'dev' into feature-localization

src/documents/management/commands/document_thumbnails.py

@@ -0,0 +1,68 @@
+import logging
+import multiprocessing
+import shutil
+
+import tqdm
+from django import db
+from django.core.management.base import BaseCommand
+
+from documents.models import Document
+from ...mixins import Renderable
+from ...parsers import get_parser_class_for_mime_type
+
+
+def _process_document(doc_in):
+    document = Document.objects.get(id=doc_in)
+    parser = get_parser_class_for_mime_type(document.mime_type)(
+        logging_group=None)
+    try:
+        thumb = parser.get_optimised_thumbnail(
+            document.source_path, document.mime_type)
+
+        shutil.move(thumb, document.thumbnail_path)
+    finally:
+        parser.cleanup()
+
+
+class Command(Renderable, BaseCommand):
+
+    help = """
+        This will regenerate the thumbnails for all documents.
+    """.replace("    ", "")
+
+    def __init__(self, *args, **kwargs):
+        self.verbosity = 0
+        BaseCommand.__init__(self, *args, **kwargs)
+
+    def add_arguments(self, parser):
+        parser.add_argument(
+            "-d", "--document",
+            default=None,
+            type=int,
+            required=False,
+            help="Specify the ID of a document, and this command will only "
+                 "run on this specific document."
+        )
+
+    def handle(self, *args, **options):
+
+        self.verbosity = options["verbosity"]
+
+        logging.getLogger().handlers[0].level = logging.ERROR
+
+        if options['document']:
+            documents = Document.objects.filter(pk=options['document'])
+        else:
+            documents = Document.objects.all()
+
+        ids = [doc.id for doc in documents]
+
+        # Note to future self: this prevents django from reusing database
+        # conncetions between processes, which is bad and does not work
+        # with postgres.
+        db.connections.close_all()
+
+        with multiprocessing.Pool() as pool:
+            list(tqdm.tqdm(
+                pool.imap_unordered(_process_document, ids), total=len(ids)
+            ))

src/documents/parsers.py

@@ -117,6 +117,7 @@ def run_convert(input_file,
                 trim=False,
                 type=None,
                 depth=None,
+                auto_orient=False,
                 extra=None,
                 logging_group=None):
 
@@ -134,6 +135,7 @@ def run_convert(input_file,
     args += ['-trim'] if trim else []
     args += ['-type', str(type)] if type else []
     args += ['-depth', str(depth)] if depth else []
+    args += ['-auto-orient'] if auto_orient else []
     args += [input_file, output_file]
 
     logger.debug("Execute: " + " ".join(args), extra={'group': logging_group})

src/documents/signals/handlers.py

@@ -276,13 +276,6 @@ def update_filename_and_move_files(sender, instance, **kwargs):
             Document.objects.filter(pk=instance.pk).update(
                 filename=new_filename)
 
-            logging.getLogger(__name__).debug(
-                f"Moved file {old_source_path} to {new_source_path}.")
-
-            if instance.archive_checksum:
-                logging.getLogger(__name__).debug(
-                    f"Moved file {old_archive_path} to {new_archive_path}.")
-
         except OSError as e:
             instance.filename = old_filename
             # this happens when we can't move a file. If that's the case for

src/documents/tasks.py

@@ -94,7 +94,10 @@ def bulk_update_documents(document_ids):
     documents = Document.objects.filter(id__in=document_ids)
 
     ix = index.open_index()
+
+    for doc in documents:
+        post_save.send(Document, instance=doc, created=False)
+
     with AsyncWriter(ix) as writer:
         for doc in documents:
             index.update_document(writer, doc)
-            post_save.send(Document, instance=doc, created=False)

src/paperless_tesseract/parsers.py

@@ -60,6 +60,7 @@ class RasterisedDocumentParser(DocumentParser):
                         alpha="remove",
                         strip=True,
                         trim=False,
+                        auto_orient=True,
                         input_file="{}[0]".format(document_path),
                         output_file=out_path,
                         logging_group=self.logging_group)
@@ -84,6 +85,7 @@ class RasterisedDocumentParser(DocumentParser):
                         alpha="remove",
                         strip=True,
                         trim=False,
+                        auto_orient=True,
                         input_file=gs_out_path,
                         output_file=out_path,
                         logging_group=self.logging_group)