Skip to content

feat(stdlib): Support data_collection filtering for URL query params #7291

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

Merged
ericapisani merged 4 commits into from
Aug 31, 2026
Merged

feat(stdlib): Support data_collection filtering for URL query params #7291

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
f94d868
feat(stdlib): Support data_collection filtering for URL query params
ericapisani Aug 28, 2026
2d25d86
test(requests): Drop stale empty url.query/url.fragment expectations
ericapisani Aug 28, 2026
5bbdd48
ref(tracing): Deduplicate per-integration `_get_url_attributes` helper
ericapisani Aug 31, 2026
8cc46e2
fix circular import issue related to building the docs
ericapisani Aug 31, 2026
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
45 changes: 2 additions & 43 deletions sentry_sdk/integrations/boto3.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,22 +3,18 @@

import sentry_sdk
from sentry_sdk.consts import OP, SPANDATA
from sentry_sdk.data_collection import (
_apply_data_collection_filtering_to_query_string,
)
from sentry_sdk.integrations import DidNotEnable, Integration, _check_minimum_version
from sentry_sdk.scope import should_send_default_pii
from sentry_sdk.traces import StreamedSpan
from sentry_sdk.tracing import BAGGAGE_HEADER_NAME, Span
from sentry_sdk.tracing_utils import (
add_http_breadcrumb,
add_sentry_baggage_to_headers,
get_url_attributes,
has_span_streaming_enabled,
should_propagate_trace,
)
from sentry_sdk.utils import (
capture_internal_exceptions,
has_data_collection_enabled,
parse_url,
parse_version,
)
Expand All @@ -28,9 +24,6 @@

from botocore.model import ServiceId

from sentry_sdk._types import Attributes
from sentry_sdk.client import BaseClient as SentryClient
from sentry_sdk.utils import ParsedUrl

try:
from botocore import __version__ as BOTOCORE_VERSION
Expand Down Expand Up @@ -70,40 +63,6 @@ def sentry_patched_init(
BaseClient.__init__ = sentry_patched_init # type: ignore


def _get_url_attributes(
client: "SentryClient", parsed_url: "Optional[ParsedUrl]"
) -> "Attributes":
attributes: "Attributes" = {}
if parsed_url is None:
return attributes

query: "Optional[str]"
if has_data_collection_enabled(client.options):
query = None
if parsed_url.query:
query = _apply_data_collection_filtering_to_query_string(
query_string=parsed_url.query,
behaviour=client.options["data_collection"]["url_query_params"],
)
elif should_send_default_pii():
query = parsed_url.query
else:
return attributes

url_full = parsed_url.url
if query:
attributes[SPANDATA.URL_QUERY] = query
url_full += "?" + query

if parsed_url.fragment:
attributes[SPANDATA.URL_FRAGMENT] = parsed_url.fragment
url_full += "#" + parsed_url.fragment

attributes[SPANDATA.URL_FULL] = url_full

return attributes


def _sentry_request_created(
service_id: "ServiceId", request: "AWSRequest", operation_name: str, **kwargs: "Any"
) -> None:
Expand All @@ -123,7 +82,7 @@ def _sentry_request_created(
is_span_streaming_enabled = has_span_streaming_enabled(client.options)
span: "Union[Span, StreamedSpan, None]" = None
if is_span_streaming_enabled:
url_attributes = _get_url_attributes(client, parsed_url)
url_attributes = get_url_attributes(client, parsed_url)
breadcrumb.update(url_attributes)

if request.method is not None:
Expand Down
53 changes: 4 additions & 49 deletions sentry_sdk/integrations/httpx.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,31 +2,25 @@

import sentry_sdk
from sentry_sdk.consts import OP, SPANDATA
from sentry_sdk.data_collection import (
_apply_data_collection_filtering_to_query_string,
)
from sentry_sdk.integrations import DidNotEnable, Integration
from sentry_sdk.scope import should_send_default_pii
from sentry_sdk.tracing_utils import (
add_http_breadcrumb,
add_http_request_source,
get_url_attributes,
has_span_streaming_enabled,
propagate_trace_headers,
)
from sentry_sdk.utils import (
SENSITIVE_DATA_SUBSTITUTE,
capture_internal_exceptions,
ensure_integration_enabled,
has_data_collection_enabled,
parse_url,
)

if TYPE_CHECKING:
from typing import Any, Optional
from typing import Any

from sentry_sdk._types import Attributes
from sentry_sdk.client import BaseClient
from sentry_sdk.utils import ParsedUrl


try:
Expand All @@ -51,45 +45,6 @@ def setup_once() -> None:
_install_httpx_async_client()


def _get_url_attributes(
client: "BaseClient", parsed_url: "Optional[ParsedUrl]"
) -> "Attributes":
attributes: "Attributes" = {}
if parsed_url is None:
return attributes

url_full = parsed_url.url

if has_data_collection_enabled(client.options):
if parsed_url.query:
filtered_query = _apply_data_collection_filtering_to_query_string(
query_string=parsed_url.query,
behaviour=client.options["data_collection"]["url_query_params"],
)
if filtered_query:
attributes["url.query"] = filtered_query
url_full += "?" + filtered_query

if parsed_url.fragment:
attributes["url.fragment"] = parsed_url.fragment
url_full += "#" + parsed_url.fragment

attributes["url.full"] = url_full

elif should_send_default_pii():
if parsed_url.query:
attributes["url.query"] = parsed_url.query
url_full += "?" + parsed_url.query

if parsed_url.fragment:
attributes["url.fragment"] = parsed_url.fragment
url_full += "#" + parsed_url.fragment

attributes["url.full"] = url_full

return attributes


def _install_httpx_client() -> None:
real_send = Client.send

Expand All @@ -109,7 +64,7 @@ def send(self: "Client", request: "Request", **kwargs: "Any") -> "Response":
propagate_trace_headers(client, request)
return real_send(self, request, **kwargs)

url_attributes = _get_url_attributes(client, parsed_url)
url_attributes = get_url_attributes(client, parsed_url)

with sentry_sdk.traces.start_span(
name="%s %s"
Expand Down Expand Up @@ -218,7 +173,7 @@ async def send(
propagate_trace_headers(client, request)
return await real_send(self, request, **kwargs)

url_attributes = _get_url_attributes(client, parsed_url)
url_attributes = get_url_attributes(client, parsed_url)

with sentry_sdk.traces.start_span(
name="%s %s"
Expand Down
53 changes: 4 additions & 49 deletions sentry_sdk/integrations/httpx2.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,31 +2,25 @@

import sentry_sdk
from sentry_sdk.consts import OP, SPANDATA
from sentry_sdk.data_collection import (
_apply_data_collection_filtering_to_query_string,
)
from sentry_sdk.integrations import DidNotEnable, Integration
from sentry_sdk.scope import should_send_default_pii
from sentry_sdk.tracing_utils import (
add_http_breadcrumb,
add_http_request_source,
get_url_attributes,
has_span_streaming_enabled,
propagate_trace_headers,
)
from sentry_sdk.utils import (
SENSITIVE_DATA_SUBSTITUTE,
capture_internal_exceptions,
ensure_integration_enabled,
has_data_collection_enabled,
parse_url,
)

if TYPE_CHECKING:
from typing import Any, Optional
from typing import Any

from sentry_sdk._types import Attributes
from sentry_sdk.client import BaseClient
from sentry_sdk.utils import ParsedUrl


try:
Expand All @@ -51,45 +45,6 @@ def setup_once() -> None:
_install_httpx2_async_client()


def _get_url_attributes(
client: "BaseClient", parsed_url: "Optional[ParsedUrl]"
) -> "Attributes":
attributes: "Attributes" = {}
if parsed_url is None:
return attributes

url_full = parsed_url.url

if has_data_collection_enabled(client.options):
if parsed_url.query:
filtered_query = _apply_data_collection_filtering_to_query_string(
query_string=parsed_url.query,
behaviour=client.options["data_collection"]["url_query_params"],
)
if filtered_query:
attributes["url.query"] = filtered_query
url_full += "?" + filtered_query

if parsed_url.fragment:
attributes["url.fragment"] = parsed_url.fragment
url_full += "#" + parsed_url.fragment

attributes["url.full"] = url_full

elif should_send_default_pii():
if parsed_url.query:
attributes["url.query"] = parsed_url.query
url_full += "?" + parsed_url.query

if parsed_url.fragment:
attributes["url.fragment"] = parsed_url.fragment
url_full += "#" + parsed_url.fragment

attributes["url.full"] = url_full

return attributes


def _install_httpx2_client() -> None:
real_send = Client.send

Expand All @@ -109,7 +64,7 @@ def send(self: "Client", request: "Request", **kwargs: "Any") -> "Response":
propagate_trace_headers(client, request)
return real_send(self, request, **kwargs)

url_attributes = _get_url_attributes(client, parsed_url)
url_attributes = get_url_attributes(client, parsed_url)

with sentry_sdk.traces.start_span(
name="%s %s"
Expand Down Expand Up @@ -218,7 +173,7 @@ async def send(
propagate_trace_headers(client, request)
return await real_send(self, request, **kwargs)

url_attributes = _get_url_attributes(client, parsed_url)
url_attributes = get_url_attributes(client, parsed_url)

with sentry_sdk.traces.start_span(
name="%s %s"
Expand Down
45 changes: 3 additions & 42 deletions sentry_sdk/integrations/pyreqwest.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,25 +4,21 @@
import sentry_sdk
from sentry_sdk import start_span
from sentry_sdk.consts import OP, SPANDATA
from sentry_sdk.data_collection import (
_apply_data_collection_filtering_to_query_string,
)
from sentry_sdk.integrations import DidNotEnable, Integration
from sentry_sdk.scope import should_send_default_pii
from sentry_sdk.traces import StreamedSpan
from sentry_sdk.tracing import BAGGAGE_HEADER_NAME
from sentry_sdk.tracing_utils import (
add_http_breadcrumb,
add_http_request_source,
add_sentry_baggage_to_headers,
get_url_attributes,
has_span_streaming_enabled,
propagate_trace_headers,
should_propagate_trace,
)
from sentry_sdk.utils import (
SENSITIVE_DATA_SUBSTITUTE,
capture_internal_exceptions,
has_data_collection_enabled,
logger,
parse_url,
)
Expand All @@ -31,7 +27,6 @@
from typing import Optional

from sentry_sdk._types import Attributes
from sentry_sdk.client import BaseClient
from sentry_sdk.utils import ParsedUrl

try:
Expand Down Expand Up @@ -97,40 +92,6 @@ def sentry_patched_method(self: "Any", *args: "Any", **kwargs: "Any") -> "Any":
setattr(cls, method_name, sentry_patched_method)


def _get_url_attributes(
client: "BaseClient", parsed_url: "Optional[ParsedUrl]"
) -> "Attributes":
attributes: "Attributes" = {}
if parsed_url is None:
return attributes

query: "Optional[str]"
if has_data_collection_enabled(client.options):
query = None
if parsed_url.query:
query = _apply_data_collection_filtering_to_query_string(
query_string=parsed_url.query,
behaviour=client.options["data_collection"]["url_query_params"],
)
elif should_send_default_pii():
query = parsed_url.query
else:
return attributes

url_full = parsed_url.url
if query:
attributes[SPANDATA.URL_QUERY] = query
url_full += "?" + query

if parsed_url.fragment:
attributes[SPANDATA.URL_FRAGMENT] = parsed_url.fragment
url_full += "#" + parsed_url.fragment

attributes[SPANDATA.URL_FULL] = url_full

return attributes


def _get_breadcrumb_url_data(
parsed_url: "Optional[ParsedUrl]", url_attributes: "Attributes"
) -> "dict[str, Any]":
Expand Down Expand Up @@ -233,7 +194,7 @@ async def sentry_async_middleware(
# after the request has been sent
parsed_url = parse_url(str(request.url), sanitize=False)

url_attributes = _get_url_attributes(sentry_sdk.get_client(), parsed_url)
url_attributes = get_url_attributes(sentry_sdk.get_client(), parsed_url)

response = None
with _sentry_pyreqwest_span(request, url_attributes) as span:
Expand Down Expand Up @@ -273,7 +234,7 @@ def sentry_sync_middleware(
# after the request has been sent
parsed_url = parse_url(str(request.url), sanitize=False)

url_attributes = _get_url_attributes(sentry_sdk.get_client(), parsed_url)
url_attributes = get_url_attributes(sentry_sdk.get_client(), parsed_url)

response = None
with _sentry_pyreqwest_span(request, url_attributes) as span:
Expand Down
Loading
Loading