mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-10-30 08:50:48 +01:00
eecc461b39
* util: do not bind outbound dials to a loopback -ip.bind `weed server -ip.bind=127.0.0.1` keeps every listener local, but the same address became the source of outbound connections, so the filer dialled its remote mount from 127.0.0.1 and failed with "connect: invalid argument". A loopback source cannot reach off the host; leave the source to the OS, as for a wildcard bind. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * s3vectors: put, get and delete vector bucket policies The AWS S3 Vectors policy operations had no handlers; the policy document is stored on the shared table bucket, so the handlers delegate to the catalog's PutTableBucketPolicy, GetTableBucketPolicy and DeleteTableBucketPolicy and keep its guard. * s3vectors: treat ICEBERG buckets as absent in policy handlers GetVectorBucketPolicy/PutVectorBucketPolicy/DeleteVectorBucketPolicy delegated straight to the table bucket, so a bucket created for ICEBERG tables — invisible to every other vectors operation — could still have its policy read and written through the vectors API. Gate all three on lanceBucket, the same format check DeleteVectorBucket and CreateIndex already apply. * test/vectors: cover vector bucket policy put/get/delete Round-trips a policy document through the new ops and asserts a get on the deleted policy surfaces NotFoundException, so the boto3 conformance run exercises the added handlers end to end. * s3vectors: validate the bucket ARN and policy document Bucket-level operations now reject an index ARN and an ARN minted for another service, and PutVectorBucketPolicy refuses a document carrying s3vectors actions — the evaluator only honors s3tables actions, so such a rule would be a dead grant. * s3vectors: validate the bucket ARN on the remaining bucket-level operations * s3vectors: cover bucket ARN and policy document validation TestBucketARNs pins the accepted forms and the index/foreign-service rejections; TestValidatePolicyDocument covers a valid document, a malformed one, and the dead s3vectors action namespace. * s3vectors test: use an enforceable action in the bucket policy test The catalog refuses s3vectors actions in a stored policy, so the put call rejected the document before the get and delete assertions ran. --------- Co-authored-by: Ólafur Bjarki Bogason <olafur@genkiinstruments.com> Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
113 lines
3.8 KiB
Python
113 lines
3.8 KiB
Python
"""Boto3 conformance subset for the S3 Vectors API gateway.
|
|
|
|
Run via `make test` — a mini cluster, an s3 gateway serving the vectors API on its main port, and a
|
|
weed-vector are up by then.
|
|
"""
|
|
|
|
import json
|
|
|
|
import boto3
|
|
import pytest
|
|
from botocore.exceptions import ClientError
|
|
|
|
ENDPOINT = "http://127.0.0.1:8334"
|
|
BUCKET = "vectors-bucket"
|
|
INDEX = "idx"
|
|
|
|
|
|
@pytest.fixture(scope="module")
|
|
def vectors():
|
|
return boto3.client(
|
|
"s3vectors",
|
|
endpoint_url=ENDPOINT,
|
|
aws_access_key_id="test",
|
|
aws_secret_access_key="test",
|
|
region_name="us-east-1",
|
|
)
|
|
|
|
|
|
def test_vector_lifecycle(vectors):
|
|
vectors.create_vector_bucket(vectorBucketName=BUCKET)
|
|
buckets = [b["vectorBucketName"] for b in vectors.list_vector_buckets()["vectorBuckets"]]
|
|
assert BUCKET in buckets
|
|
|
|
vectors.create_index(
|
|
vectorBucketName=BUCKET,
|
|
indexName=INDEX,
|
|
dataType="float32",
|
|
dimension=4,
|
|
distanceMetric="euclidean",
|
|
)
|
|
idx = vectors.get_index(vectorBucketName=BUCKET, indexName=INDEX)["index"]
|
|
assert idx["dimension"] == 4
|
|
|
|
vectors.put_vectors(
|
|
vectorBucketName=BUCKET,
|
|
indexName=INDEX,
|
|
vectors=[
|
|
{"key": "a", "data": {"float32": [1, 0, 0, 0]}, "metadata": {"color": "red"}},
|
|
{"key": "b", "data": {"float32": [0.95, 0.05, 0, 0]}, "metadata": {"color": "blue"}},
|
|
{"key": "c", "data": {"float32": [0.9, 0.1, 0, 0]}, "metadata": {"color": "red"}},
|
|
],
|
|
)
|
|
|
|
got = vectors.get_vectors(
|
|
vectorBucketName=BUCKET, indexName=INDEX, keys=["a"], returnData=True, returnMetadata=True
|
|
)["vectors"]
|
|
assert got[0]["key"] == "a" and got[0]["metadata"]["color"] == "red"
|
|
|
|
listed = vectors.list_vectors(vectorBucketName=BUCKET, indexName=INDEX)["vectors"]
|
|
assert sorted(v["key"] for v in listed) == ["a", "b", "c"]
|
|
|
|
hits = vectors.query_vectors(
|
|
vectorBucketName=BUCKET,
|
|
indexName=INDEX,
|
|
queryVector={"float32": [1, 0, 0, 0]},
|
|
topK=2,
|
|
returnDistance=True,
|
|
returnMetadata=True,
|
|
filter={"color": {"$eq": "red"}},
|
|
)["vectors"]
|
|
# b is the second-nearest vector but blue, so an ignored filter would
|
|
# return ["a", "b"] here.
|
|
assert [h["key"] for h in hits] == ["a", "c"]
|
|
distances = {h["key"]: h["distance"] for h in hits}
|
|
assert distances["a"] == pytest.approx(0.0, abs=1e-6)
|
|
assert distances["c"] == pytest.approx(0.02, abs=1e-4)
|
|
assert all(h["metadata"]["color"] == "red" for h in hits)
|
|
|
|
vectors.delete_vectors(vectorBucketName=BUCKET, indexName=INDEX, keys=["b"])
|
|
listed = vectors.list_vectors(vectorBucketName=BUCKET, indexName=INDEX)["vectors"]
|
|
assert sorted(v["key"] for v in listed) == ["a", "c"]
|
|
|
|
vectors.delete_index(vectorBucketName=BUCKET, indexName=INDEX)
|
|
vectors.delete_vector_bucket(vectorBucketName=BUCKET)
|
|
|
|
|
|
def test_vector_bucket_policy(vectors):
|
|
vectors.create_vector_bucket(vectorBucketName=BUCKET)
|
|
try:
|
|
policy = json.dumps(
|
|
{
|
|
"Version": "2012-10-17",
|
|
"Statement": [
|
|
{
|
|
"Effect": "Allow",
|
|
"Principal": {"AWS": "*"},
|
|
"Action": "s3tables:*",
|
|
"Resource": "*",
|
|
}
|
|
],
|
|
}
|
|
)
|
|
vectors.put_vector_bucket_policy(vectorBucketName=BUCKET, policy=policy)
|
|
got = vectors.get_vector_bucket_policy(vectorBucketName=BUCKET)["policy"]
|
|
assert json.loads(got) == json.loads(policy)
|
|
|
|
vectors.delete_vector_bucket_policy(vectorBucketName=BUCKET)
|
|
with pytest.raises(ClientError) as exc:
|
|
vectors.get_vector_bucket_policy(vectorBucketName=BUCKET)
|
|
assert exc.value.response["Error"]["Code"] == "NotFoundException"
|
|
finally:
|
|
vectors.delete_vector_bucket(vectorBucketName=BUCKET)
|