lgcosta/paperless-ngx
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Refactor pages_count --> page_count

Browse Source
This commit is contained in:
shamoon
2024-09-25 00:35:14 -07:00
parent 9b13c607db
commit 693ce6553d
21 changed files with 64 additions and 64 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/documents/bulk_edit.py
View File

@@ -387,8 +387,8 @@ def delete_pages(doc_ids: list[int], pages: list[int]):
pdf.remove_unreferenced_resources()
pdf.save()
doc.checksum = hashlib.md5(doc.source_path.read_bytes()).hexdigest()
if doc.pages_count is not None:
doc.pages_count = doc.pages_count - len(pages)
if doc.page_count is not None:
doc.page_count = doc.page_count - len(pages)
doc.save()
update_document_archive_file.delay(document_id=doc.id)
logger.info(f"Deleted pages {pages} from document {doc.id}")

10
src/documents/consumer.py
View File

@@ -586,7 +586,7 @@ class ConsumerPlugin(
date = None
thumbnail = None
archive_path = None
pages_count = None
page_count = None
try:
self._send_progress(
@@ -622,7 +622,7 @@ class ConsumerPlugin(
)
date = parse_date(self.filename, text)
archive_path = document_parser.get_archive_path()
pages_count = document_parser.get_pages_count(self.working_copy, mime_type)
page_count = document_parser.get_page_count(self.working_copy, mime_type)
except ParseError as e:
document_parser.cleanup()
@@ -667,7 +667,7 @@ class ConsumerPlugin(
document = self._store(
text=text,
date=date,
pages_count=pages_count,
page_count=page_count,
mime_type=mime_type,
)
@@ -797,7 +797,7 @@ class ConsumerPlugin(
self,
text: str,
date: Optional[datetime.datetime],
pages_count: Optional[int],
page_count: Optional[int],
mime_type: str,
) -> Document:
# If someone gave us the original filename, use it instead of doc.
@@ -843,7 +843,7 @@ class ConsumerPlugin(
created=create_date,
modified=create_date,
storage_type=storage_type,
pages_count=pages_count,
page_count=page_count,
original_filename=self.filename,
)

6
src/documents/index.py
View File

@@ -80,7 +80,7 @@ def get_schema():
has_owner=BOOLEAN(),
viewer_id=KEYWORD(commas=True),
checksum=TEXT(),
pages_count=NUMERIC(sortable=True),
page_count=NUMERIC(sortable=True),
original_filename=TEXT(sortable=True),
is_shared=BOOLEAN(),
)
@@ -182,7 +182,7 @@ def update_document(writer: AsyncWriter, doc: Document):
has_owner=doc.owner is not None,
viewer_id=viewer_ids if viewer_ids else None,
checksum=doc.checksum,
pages_count=doc.pages_count,
page_count=doc.page_count,
original_filename=doc.original_filename,
is_shared=len(viewer_ids) > 0,
)
@@ -249,7 +249,7 @@ class DelayedQuery:
"archive_serial_number": "asn",
"num_notes": "num_notes",
"owner": "owner",
"pages_count": "pages_count",
"page_count": "page_count",
}
if field.startswith("-"):

8
src/documents/migrations/1053_document_pages_count.py → src/documents/migrations/1053_document_page_count.py
View File

@@ -15,7 +15,7 @@ def source_path(self):
return Path(settings.ORIGINALS_DIR / fname).resolve()
def add_number_of_pages_to_pages_count(apps, schema_editor):
def add_number_of_pages_to_page_count(apps, schema_editor):
Document = apps.get_model("documents", "Document")
if not Document.objects.all().exists():
@@ -33,7 +33,7 @@ def add_number_of_pages_to_pages_count(apps, schema_editor):
try:
with pikepdf.Pdf.open(source_path(doc)) as pdf:
if pdf.pages is not None:
doc.pages_count = len(pdf.pages)
doc.page_count = len(pdf.pages)
doc.save()
except Exception as e: # pragma: no cover
print(f"Error retrieving number of pages for {doc.filename}: {e}")
@@ -47,7 +47,7 @@ class Migration(migrations.Migration):
operations = [
migrations.AddField(
model_name="document",
name="pages_count",
name="page_count",
field=models.PositiveIntegerField(
blank=False,
null=True,
@@ -56,7 +56,7 @@ class Migration(migrations.Migration):
),
),
migrations.RunPython(
add_number_of_pages_to_pages_count,
add_number_of_pages_to_page_count,
migrations.RunPython.noop,
),
]

6
src/documents/models.py
View File

@@ -205,8 +205,8 @@ class Document(SoftDeleteModel, ModelWithOwner):
help_text=_("The checksum of the archived document."),
)
pages_count = models.PositiveIntegerField(
_("pages count"),
page_count = models.PositiveIntegerField(
_("page count"),
blank=False,
null=True,
unique=False,
@@ -426,7 +426,7 @@ class SavedView(ModelWithOwner):
OWNER = ("owner", _("Owner"))
SHARED = ("shared", _("Shared"))
ASN = ("asn", _("ASN"))
PAGES_COUNT = ("pagescount", _("Pages"))
PAGE_COUNT = ("pagecount", _("Pages"))
CUSTOM_FIELD = ("custom_field_%d", ("Custom Field"))
name = models.CharField(_("name"), max_length=128)

2
src/documents/parsers.py
View File

@@ -367,7 +367,7 @@ class DocumentParser(LoggingMixin):
def extract_metadata(self, document_path, mime_type):
return []
def get_pages_count(self, document_path, mime_type):
def get_page_count(self, document_path, mime_type):
return None
def parse(self, document_path, mime_type, file_name=None):

8
src/documents/serialisers.py
View File

@@ -750,7 +750,7 @@ class DocumentSerializer(
original_file_name = SerializerMethodField()
archived_file_name = SerializerMethodField()
created_date = serializers.DateField(required=False)
pages_count = SerializerMethodField()
page_count = SerializerMethodField()
custom_fields = CustomFieldInstanceSerializer(
many=True,
@@ -771,8 +771,8 @@ class DocumentSerializer(
required=False,
)
def get_pages_count(self, obj):
return obj.pages_count
def get_page_count(self, obj):
return obj.page_count
def get_original_file_name(self, obj):
return obj.original_filename
@@ -889,7 +889,7 @@ class DocumentSerializer(
"notes",
"custom_fields",
"remove_inbox_tags",
"pages_count",
"page_count",
)
list_serializer_class = OwnedObjectListSerializer

10
src/documents/tests/test_bulk_edit.py
View File

@@ -389,7 +389,7 @@ class TestPDFActions(DirectoriesMixin, TestCase):
title="B",
filename=sample2,
mime_type="application/pdf",
pages_count=8,
page_count=8,
)
self.doc2.archive_filename = sample2_archive
self.doc2.save()
@@ -682,19 +682,19 @@ class TestPDFActions(DirectoriesMixin, TestCase):
THEN:
- Save should be called once
- Archive file should be updated once
- The document's pages_count should be reduced by the number of deleted pages
- The document's page_count should be reduced by the number of deleted pages
"""
doc_ids = [self.doc2.id]
initial_pages_count = self.doc2.pages_count
initial_page_count = self.doc2.page_count
pages = [1, 3]
result = bulk_edit.delete_pages(doc_ids, pages)
mock_pdf_save.assert_called_once()
mock_update_archive_file.assert_called_once()
self.assertEqual(result, "OK")
expected_pages_count = initial_pages_count - len(pages)
expected_page_count = initial_page_count - len(pages)
self.doc2.refresh_from_db()
self.assertEqual(self.doc2.pages_count, expected_pages_count)
self.assertEqual(self.doc2.page_count, expected_page_count)
@mock.patch("documents.tasks.update_document_archive_file.delay")
@mock.patch("pikepdf.Pdf.save")

18
src/documents/tests/test_migration_document_pages_count.py
View File

@@ -14,9 +14,9 @@ def source_path_before(self):
return os.path.join(settings.ORIGINALS_DIR, fname)
class TestMigrateDocumentPagesCount(TestMigrations):
class TestMigrateDocumentPageCount(TestMigrations):
migrate_from = "1052_document_transaction_id"
migrate_to = "1053_document_pages_count"
migrate_to = "1053_document_page_count"
def setUpBeforeMigration(self, apps):
Document = apps.get_model("documents", "Document")
@@ -31,15 +31,15 @@ class TestMigrateDocumentPagesCount(TestMigrations):
source_path_before(doc),
)
def testDocumentPagesCountMigrated(self):
def testDocumentPageCountMigrated(self):
Document = self.apps.get_model("documents", "Document")
doc = Document.objects.get(id=self.doc_id)
self.assertEqual(doc.pages_count, 1)
self.assertEqual(doc.page_count, 1)
class TestMigrateDocumentPagesCountBackwards(TestMigrations):
migrate_from = "1053_document_pages_count"
class TestMigrateDocumentPageCountBackwards(TestMigrations):
migrate_from = "1053_document_page_count"
migrate_to = "1052_document_transaction_id"
def setUpBeforeMigration(self, apps):
@@ -48,12 +48,12 @@ class TestMigrateDocumentPagesCountBackwards(TestMigrations):
title="test1",
mime_type="application/pdf",
filename="file1.pdf",
pages_count=8,
page_count=8,
)
self.doc_id = doc.id
def test_remove_number_of_pages_to_pages_count(self):
def test_remove_number_of_pages_to_page_count(self):
Document = self.apps.get_model("documents", "Document")
self.assertFalse(
"pages_count" in [field.name for field in Document._meta.get_fields()],
"page_count" in [field.name for field in Document._meta.get_fields()],
)

2
src/documents/views.py
View File

@@ -361,7 +361,7 @@ class DocumentViewSet(
"archive_serial_number",
"num_notes",
"owner",
"pages_count",
"page_count",
)
def get_queryset(self):

8
src/paperless_tesseract/parsers.py
View File

@@ -41,14 +41,14 @@ class RasterisedDocumentParser(DocumentParser):
"""
return OcrConfig()
def get_pages_count(self, document_path, mime_type):
pages_count = None
def get_page_count(self, document_path, mime_type):
page_count = None
if mime_type == "application/pdf":
import pikepdf
with pikepdf.Pdf.open(document_path) as pdf:
pages_count = len(pdf.pages)
return pages_count
page_count = len(pdf.pages)
return page_count
def extract_metadata(self, document_path, mime_type):
result = []

10
src/paperless_tesseract/tests/test_parser.py
View File

@@ -57,7 +57,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
self.assertContainsStrings(text.strip(), ["This is a test document."])
def test_get_pages_count(self):
def test_get_page_count(self):
"""
GIVEN:
- PDF file with a single page
@@ -69,17 +69,17 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
- The method returns the correct number of pages (6)
"""
parser = RasterisedDocumentParser(uuid.uuid4())
pages_count = parser.get_pages_count(
page_count = parser.get_page_count(
os.path.join(self.SAMPLE_FILES, "simple-digital.pdf"),
"application/pdf",
)
self.assertEqual(pages_count, 1)
self.assertEqual(page_count, 1)
pages_count = parser.get_pages_count(
page_count = parser.get_page_count(
os.path.join(self.SAMPLE_FILES, "multi-page-mixed.pdf"),
"application/pdf",
)
self.assertEqual(pages_count, 6)
self.assertEqual(page_count, 6)
def test_thumbnail(self):
parser = RasterisedDocumentParser(uuid.uuid4())