tiennm99/DocsGPT
1
0 Fork 0
mirror of https://github.com/tiennm99/DocsGPT.git synced 2026-10-14 20:16:48 +00:00
Code Issues Packages Projects Releases Wiki Activity

Pg 4 (#2390)

Browse Source 
* feat: postgres tests

* feat: mongo cutoff

* feat: mongo cutoff

* feat: adjust docs and compose files

* fix: mini code mongo removals

* fix: tests and k8s mongo stuff

* feat: test fixes

* fix: ruff

* fix: vale

* Potential fix for pull request finding 'CodeQL / Clear-text logging of sensitive information'

Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>

* fix: mini suggestions

* vale lint fix 2

* fix: codeql columns thing

* fix: test mongo

* fix: tests coverage

* feat: better tests 4

* feat: more tests

* feat: decent coverage

* fix: ruff fixes

* fix: remove mongo mock

* feat: enhance workflow engine and API routes; add document retrieval and source handling

* feat: e2e tests

* fix: mcp, mongo and more

* fix: mini codeql warning

* fix: agent chunk view

* fix: mini issues

* fix: more pg fixes

* feat: postgres prep on start

* feat: qa tests

* fix: mini improvements

* fix: tests

---------

Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
Co-authored-by: Siddhant Rai <siddhant.rai.5686@gmail.com>
This commit is contained in:
AlexCopilot Autofix powered by AISiddhant Rai
 authored and GitHub committed 2026-04-18 13:13:57 +01:00
1 parent 7f6360b4ff
commit 81b6ee5daa
312 files changed
+763725 -25159
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

tests/parser/remote/test_s3_loader.py
+84 -16
View File
@@ -126,13 +126,17 @@ class TestInitClient:
def test_init_client_with_custom_endpoint(self, s3_loader, mock_boto3):
"""Should configure path-style addressing for custom endpoints."""
s3_loader._init_client(
aws_access_key_id="test-key",
aws_secret_access_key="test-secret",
region_name="us-east-1",
endpoint_url="https://nyc3.digitaloceanspaces.com",
bucket="my-bucket",
)
with patch(
"application.parser.remote.s3_loader.validate_url",
side_effect=lambda u: u,
):
s3_loader._init_client(
aws_access_key_id="test-key",
aws_secret_access_key="test-secret",
region_name="us-east-1",
endpoint_url="https://nyc3.digitaloceanspaces.com",
bucket="my-bucket",
)
call_kwargs = mock_boto3.client.call_args[1]
assert call_kwargs["endpoint_url"] == "https://nyc3.digitaloceanspaces.com"
@@ -140,13 +144,17 @@ class TestInitClient:
def test_init_client_normalizes_do_endpoint(self, s3_loader, mock_boto3):
"""Should normalize DigitalOcean Spaces bucket-prefixed URLs."""
corrected_bucket = s3_loader._init_client(
aws_access_key_id="test-key",
aws_secret_access_key="test-secret",
region_name="us-east-1",
endpoint_url="https://mybucket.nyc3.digitaloceanspaces.com",
bucket="",
)
with patch(
"application.parser.remote.s3_loader.validate_url",
side_effect=lambda u: u,
):
corrected_bucket = s3_loader._init_client(
aws_access_key_id="test-key",
aws_secret_access_key="test-secret",
region_name="us-east-1",
endpoint_url="https://mybucket.nyc3.digitaloceanspaces.com",
bucket="",
)
assert corrected_bucket == "mybucket"
call_kwargs = mock_boto3.client.call_args[1]
@@ -555,7 +563,11 @@ class TestLoadData:
"endpoint_url": "https://nyc3.digitaloceanspaces.com",
}
s3_loader.load_data(input_data)
with patch(
"application.parser.remote.s3_loader.validate_url",
side_effect=lambda u: u,
):
s3_loader.load_data(input_data)
call_kwargs = mock_boto3.client.call_args[1]
assert call_kwargs["endpoint_url"] == "https://nyc3.digitaloceanspaces.com"
@@ -631,7 +643,11 @@ class TestLoadData:
"endpoint_url": "https://mybucket.nyc3.digitaloceanspaces.com",
}
docs = s3_loader.load_data(input_data)
with patch(
"application.parser.remote.s3_loader.validate_url",
side_effect=lambda u: u,
):
docs = s3_loader.load_data(input_data)
# Verify bucket name was corrected
paginator.paginate.assert_called_once_with(Bucket="mybucket", Prefix="")
@@ -835,3 +851,55 @@ class TestProcessDocumentAdditional:
)
assert result is None
class TestSSRFValidation:
"""Ensure user-supplied endpoint_url values cannot target internal networks."""
def test_init_client_rejects_loopback_endpoint(self, s3_loader, mock_boto3):
"""Should refuse to initialize boto3 when endpoint points at localhost."""
with pytest.raises(ValueError, match="Invalid S3 endpoint_url"):
s3_loader._init_client(
aws_access_key_id="k",
aws_secret_access_key="s",
region_name="us-east-1",
endpoint_url="http://127.0.0.1:9000",
bucket="b",
)
mock_boto3.client.assert_not_called()
def test_init_client_rejects_metadata_ip(self, s3_loader, mock_boto3):
"""Should refuse to initialize boto3 when endpoint targets cloud metadata."""
with pytest.raises(ValueError, match="Invalid S3 endpoint_url"):
s3_loader._init_client(
aws_access_key_id="k",
aws_secret_access_key="s",
region_name="us-east-1",
endpoint_url="http://169.254.169.254/",
bucket="b",
)
mock_boto3.client.assert_not_called()
def test_init_client_rejects_private_ip(self, s3_loader, mock_boto3):
"""Should refuse to initialize boto3 when endpoint targets an RFC1918 host."""
with pytest.raises(ValueError, match="Invalid S3 endpoint_url"):
s3_loader._init_client(
aws_access_key_id="k",
aws_secret_access_key="s",
region_name="us-east-1",
endpoint_url="http://10.0.0.5:9000",
bucket="b",
)
mock_boto3.client.assert_not_called()
def test_load_data_rejects_ssrf_endpoint(self, s3_loader, mock_boto3):
"""load_data should surface a ValueError without hitting boto3 for blocked endpoints."""
input_data = {
"aws_access_key_id": "k",
"aws_secret_access_key": "s",
"bucket": "b",
"endpoint_url": "http://localhost:9000",
}
with pytest.raises(ValueError, match="Invalid S3 endpoint_url"):
s3_loader.load_data(input_data)
mock_boto3.client.assert_not_called()