Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat(document content): support external id and instance id #2046

Open
wants to merge 8 commits into
base: master
Choose a base branch
from
Open

feat(document content): support external id and instance id #2046

Changes from 5 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
2c55744
feat(documents content): use new POST variant
andersfylling Nov 24, 2024
1c41faa
feat(document content): support external id and instance id
andersfylling Nov 24, 2024
f003000
feat(document status): support external id and instance id for streaming
andersfylling Nov 24, 2024
b21c8c6
bump version
andersfylling Nov 24, 2024
f231915
Revert "bump version"
andersfylling Nov 24, 2024
25380d1
Reapply "bump version"
andersfylling Nov 24, 2024
bb38f03
Update _version.py
andersfylling Nov 24, 2024
905eb28
Merge refs/heads/master into anders/documents-status
cognite-bulldozer[bot] Nov 27, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
33 changes: 27 additions & 6 deletions cognite/client/_api/documents.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,7 @@
from cognite.client._constants import DEFAULT_LIMIT_READ
from cognite.client.data_classes import filters
from cognite.client.data_classes.aggregations import AggregationFilter, UniqueResultList
from cognite.client.data_classes.data_modeling.ids import NodeId
from cognite.client.data_classes.documents import (
Document,
DocumentHighlightList,
Expand All @@ -19,6 +20,7 @@
TemporaryLink,
)
from cognite.client.data_classes.filters import _BASIC_FILTERS, Filter, _validate_filter
from cognite.client.utils._identifier import IdentifierSequence

if TYPE_CHECKING:
from cognite.client import ClientConfig, CogniteClient
Expand Down Expand Up @@ -475,7 +477,12 @@ def aggregate_unique_properties(
limit=limit,
)

def retrieve_content(self, id: int) -> bytes:
def retrieve_content(
self,
id: int | None = None,
external_id: str | None = None,
instance_id: NodeId | None = None,
) -> bytes:
"""`Retrieve document content <https://developer.cognite.com/api#tag/Documents/operation/documentsContent>`_

Returns extracted textual information for the given document.
Expand All @@ -487,7 +494,9 @@ def retrieve_content(self, id: int) -> bytes:


Args:
id (int): The server-generated ID for the document you want to retrieve the content of.
id (int | None): The server-generated ID for the document you want to retrieve the content of.
external_id (str | None): External ID
instance_id (NodeId | None): Instance ID

Returns:
bytes: The content of the document.
Expand All @@ -500,10 +509,18 @@ def retrieve_content(self, id: int) -> bytes:
>>> client = CogniteClient()
>>> content = client.documents.retrieve_content(id=123)
"""
response = self._do_request("GET", f"{self._RESOURCE_PATH}/{id}/content", accept="text/plain")
identifiers = IdentifierSequence.load(ids=id, external_ids=external_id, instance_ids=instance_id).as_singleton()
identifier = identifiers.as_dicts()[0]
response = self._do_request("POST", f"{self._RESOURCE_PATH}/content", accept="text/plain", json=identifier)
return response.content

def retrieve_content_buffer(self, id: int, buffer: BinaryIO) -> None:
def retrieve_content_buffer(
self,
buffer: BinaryIO,
id: int | None = None,
external_id: str | None = None,
instance_id: NodeId | None = None,
) -> None:
"""`Retrieve document content into buffer <https://developer.cognite.com/api#tag/Documents/operation/documentsContent>`_

Returns extracted textual information for the given document.
Expand All @@ -515,8 +532,10 @@ def retrieve_content_buffer(self, id: int, buffer: BinaryIO) -> None:


Args:
id (int): The server-generated ID for the document you want to retrieve the content of.
buffer (BinaryIO): The document content is streamed directly into the buffer. This is useful for retrieving large documents.
id (int | None): The server-generated ID for the document you want to retrieve the content of.
external_id (str | None): External ID
instance_id (NodeId | None): Instance ID

Examples:

Expand All @@ -528,8 +547,10 @@ def retrieve_content_buffer(self, id: int, buffer: BinaryIO) -> None:
>>> with Path("my_file.txt").open("wb") as buffer:
... client.documents.retrieve_content_buffer(id=123, buffer=buffer)
"""
identifiers = IdentifierSequence.load(ids=id, external_ids=external_id, instance_ids=instance_id).as_singleton()
identifier = identifiers.as_dicts()[0]
with self._do_request(
"GET", f"{self._RESOURCE_PATH}/{id}/content", stream=True, accept="text/plain"
"POST", f"{self._RESOURCE_PATH}/content", stream=True, accept="text/plain", json=identifier
) as response:
for chunk in response.iter_content(chunk_size=2**21):
if chunk: # filter out keep-alive new chunks
Expand Down