merge file handling

src/documents/file_handling.py

@@ -1,150 +0,0 @@
-import os
-
-from django.conf import settings
-
-from documents.templating.filepath import validate_filepath_template_and_render
-from documents.templating.utils import convert_format_str_to_template_format
-from paperless.models import Document
-
-
-def create_source_path_directory(source_path):
-    os.makedirs(os.path.dirname(source_path), exist_ok=True)
-
-
-def delete_empty_directories(directory, root):
-    if not os.path.isdir(directory):
-        return
-
-    # Go up in the directory hierarchy and try to delete all directories
-    directory = os.path.normpath(directory)
-    root = os.path.normpath(root)
-
-    if not directory.startswith(root + os.path.sep):
-        # don't do anything outside our originals folder.
-
-        # append os.path.set so that we avoid these cases:
-        #   directory = /home/originals2/test
-        #   root = /home/originals ("/" gets appended and startswith fails)
-        return
-
-    while directory != root:
-        if not os.listdir(directory):
-            # it's empty
-            try:
-                os.rmdir(directory)
-            except OSError:
-                # whatever. empty directories aren't that bad anyway.
-                return
-        else:
-            # it's not empty.
-            return
-
-        # go one level up
-        directory = os.path.normpath(os.path.dirname(directory))
-
-
-def generate_unique_filename(doc, *, archive_filename=False):
-    """
-    Generates a unique filename for doc in settings.ORIGINALS_DIR.
-
-    The returned filename is guaranteed to be either the current filename
-    of the document if unchanged, or a new filename that does not correspondent
-    to any existing files. The function will append _01, _02, etc to the
-    filename before the extension to avoid conflicts.
-
-    If archive_filename is True, return a unique archive filename instead.
-
-    """
-    if archive_filename:
-        old_filename = doc.archive_filename
-        root = settings.ARCHIVE_DIR
-    else:
-        old_filename = doc.filename
-        root = settings.ORIGINALS_DIR
-
-    # If generating archive filenames, try to make a name that is similar to
-    # the original filename first.
-
-    if archive_filename and doc.filename:
-        new_filename = os.path.splitext(doc.filename)[0] + ".pdf"
-        if new_filename == old_filename or not os.path.exists(
-            os.path.join(root, new_filename),
-        ):
-            return new_filename
-
-    counter = 0
-
-    while True:
-        new_filename = generate_filename(
-            doc,
-            counter=counter,
-            archive_filename=archive_filename,
-        )
-        if new_filename == old_filename:
-            # still the same as before.
-            return new_filename
-
-        if os.path.exists(os.path.join(root, new_filename)):
-            counter += 1
-        else:
-            return new_filename
-
-
-def generate_filename(
-    doc: Document,
-    *,
-    counter=0,
-    append_gpg=True,
-    archive_filename=False,
-):
-    path = ""
-
-    def format_filename(document: Document, template_str: str) -> str | None:
-        rendered_filename = validate_filepath_template_and_render(
-            template_str,
-            document,
-        )
-        if rendered_filename is None:
-            return None
-
-        # Apply this setting.  It could become a filter in the future (or users could use |default)
-        if settings.FILENAME_FORMAT_REMOVE_NONE:
-            rendered_filename = rendered_filename.replace("/-none-/", "/")
-            rendered_filename = rendered_filename.replace(" -none-", "")
-            rendered_filename = rendered_filename.replace("-none-", "")
-            rendered_filename = rendered_filename.strip(os.sep)
-
-        rendered_filename = rendered_filename.replace(
-            "-none-",
-            "none",
-        )  # backward compatibility
-
-        return rendered_filename
-
-    # Determine the source of the format string
-    if doc.storage_path is not None:
-        filename_format = doc.storage_path.path
-    elif settings.FILENAME_FORMAT is not None:
-        # Maybe convert old to new style
-        filename_format = convert_format_str_to_template_format(
-            settings.FILENAME_FORMAT,
-        )
-    else:
-        filename_format = None
-
-    # If we have one, render it
-    if filename_format is not None:
-        path = format_filename(doc, filename_format)
-
-    counter_str = f"_{counter:02}" if counter else ""
-    filetype_str = ".pdf" if archive_filename else doc.file_type
-
-    if path:
-        filename = f"{path}{counter_str}{filetype_str}"
-    else:
-        filename = f"{doc.pk:07}{counter_str}{filetype_str}"
-
-    if append_gpg and doc.storage_type == doc.STORAGE_TYPE_GPG:
-        filename += ".gpg"
-
-    return filename

src/documents/management/commands/document_exporter.py

@@ -32,14 +32,14 @@ if TYPE_CHECKING:
 if settings.AUDIT_LOG_ENABLED:
     from auditlog.models import LogEntry
 
-from documents.file_handling import delete_empty_directories
-from documents.file_handling import generate_filename
 from documents.management.commands.mixins import CryptMixin
 from documents.settings import EXPORTER_ARCHIVE_NAME
 from documents.settings import EXPORTER_FILE_NAME
 from documents.settings import EXPORTER_THUMBNAIL_NAME
 from paperless import version
 from paperless.db import GnuPG
+from paperless.file_handling import delete_empty_directories
+from paperless.file_handling import generate_filename
 from paperless.models import ApplicationConfiguration
 from paperless.models import Correspondent
 from paperless.models import CustomField

src/documents/management/commands/document_importer.py

@@ -21,7 +21,6 @@ from django.db.models.signals import m2m_changed
 from django.db.models.signals import post_save
 from filelock import FileLock
 
-from documents.file_handling import create_source_path_directory
 from documents.management.commands.mixins import CryptMixin
 from documents.parsers import run_convert
 from documents.settings import EXPORTER_ARCHIVE_NAME
@@ -31,6 +30,7 @@ from documents.settings import EXPORTER_THUMBNAIL_NAME
 from documents.signals.handlers import check_paths_and_prune_custom_fields
 from documents.signals.handlers import update_filename_and_move_files
 from paperless import version
+from paperless.file_handling import create_source_path_directory
 from paperless.models import Correspondent
 from paperless.models import CustomField
 from paperless.models import CustomFieldInstance

src/documents/signals/handlers.py

@@ -24,12 +24,12 @@ from filelock import FileLock
 from guardian.shortcuts import remove_perm
 
 from documents.caching import clear_document_caches
-from documents.file_handling import create_source_path_directory
-from documents.file_handling import delete_empty_directories
-from documents.file_handling import generate_unique_filename
 from documents.mail import send_email
 from documents.templating.workflows import parse_w_workflow_placeholders
 from paperless import matching
+from paperless.file_handling import create_source_path_directory
+from paperless.file_handling import delete_empty_directories
+from paperless.file_handling import generate_unique_filename
 from paperless.models import Correspondent
 from paperless.models import CustomField
 from paperless.models import CustomFieldInstance

src/documents/tasks.py

@@ -21,8 +21,6 @@ from whoosh.writing import AsyncWriter
 
 from documents import sanity_checker
 from documents.caching import clear_document_caches
-from documents.file_handling import create_source_path_directory
-from documents.file_handling import generate_unique_filename
 from documents.parsers import DocumentParser
 from documents.parsers import get_parser_class_for_mime_type
 from documents.plugins.base import ConsumeTaskPlugin
@@ -42,6 +40,8 @@ from paperless.consumer import WorkflowTriggerPlugin
 from paperless.data_models import ConsumableDocument
 from paperless.data_models import DocumentMetadataOverrides
 from paperless.double_sided import CollatePlugin
+from paperless.file_handling import create_source_path_directory
+from paperless.file_handling import generate_unique_filename
 from paperless.models import Correspondent
 from paperless.models import CustomFieldInstance
 from paperless.models import Document

src/documents/tests/test_file_handling.py

@@ -13,12 +13,12 @@ from django.test import TestCase
 from django.test import override_settings
 from django.utils import timezone
 
-from documents.file_handling import create_source_path_directory
-from documents.file_handling import delete_empty_directories
-from documents.file_handling import generate_filename
 from documents.tasks import empty_trash
 from documents.tests.utils import DirectoriesMixin
 from documents.tests.utils import FileSystemAssertsMixin
+from paperless.file_handling import create_source_path_directory
+from paperless.file_handling import delete_empty_directories
+from paperless.file_handling import generate_filename
 from paperless.models import Correspondent
 from paperless.models import CustomField
 from paperless.models import CustomFieldInstance

src/documents/tests/test_management.py

@@ -13,10 +13,10 @@ from django.core.management import call_command
 from django.test import TestCase
 from django.test import override_settings
 
-from documents.file_handling import generate_filename
 from documents.tasks import update_document_content_maybe_archive_file
 from documents.tests.utils import DirectoriesMixin
 from documents.tests.utils import FileSystemAssertsMixin
+from paperless.file_handling import generate_filename
 from paperless.models import Document
 
 sample_file = os.path.join(os.path.dirname(__file__), "samples", "simple.pdf")