Compare commits

..

1 Commits

Author SHA1 Message Date
srikanthccv
ce43780c78 fix(querybuilder): read an unknown body path in a column as a string path
A body. key that metadata does not report kept no data type in the logs
fallback, so a select, group by, order by, or aggregation on it failed with
404 "field not found" instead of the not-found warning. The fallback now types
it as bodyPath does for a bare key. Filters keep their SQL.

Assisted-by: Claude Opus 5.5
2026-11-05 03:46:58 +05:30
3 changed files with 128 additions and 7 deletions

View File

@@ -0,0 +1,86 @@
package querybuilder_test
import (
"context"
"testing"
"time"
"github.com/SigNoz/signoz/pkg/errors"
"github.com/SigNoz/signoz/pkg/querybuilder"
"github.com/SigNoz/signoz/pkg/telemetryschema/audittelemetryschema"
"github.com/SigNoz/signoz/pkg/telemetryschema/logstelemetryschema"
"github.com/SigNoz/signoz/pkg/telemetryschema/metricstelemetryschema"
"github.com/SigNoz/signoz/pkg/telemetryschema/tracestelemetryschema"
qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
"github.com/SigNoz/signoz/pkg/types/telemetrytypes/telemetrytypestest"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/mock"
"github.com/stretchr/testify/require"
)
// A key metadata does not report warns and the query runs, so in a select
// field, group by, order by, or aggregation every storage's fallback must read.
// The only failure allowed is invalid input for a context the signal does not
// serve.
func TestResolveColumn_UnknownKey(t *testing.T) {
releaseTime := time.Date(2024, 1, 15, 10, 0, 0, 0, time.UTC)
start := uint64(releaseTime.Add(24 * time.Hour).UnixNano())
end := start + uint64(time.Hour.Nanoseconds())
schemaMetadataStore := telemetrytypestest.NewMockSchemaMetadataStore(t)
schemaMetadataStore.EXPECT().GetBaseColumnEvolutions(mock.Anything, telemetrytypes.SignalTraces, telemetrytypes.FieldContextAttribute).Return(tracestelemetryschema.MockAttributeEvolutionData(releaseTime), nil).Maybe()
testCases := []struct {
name string
storage qbtypes.Storage
query qbtypes.QueryInfo
}{
{
name: "Logs",
storage: logstelemetryschema.NewStorage(),
query: qbtypes.QueryInfo{Signal: telemetrytypes.SignalLogs, StartNs: start, EndNs: end},
},
{
name: "Logs_JSONBody",
storage: logstelemetryschema.NewStorage(),
query: qbtypes.QueryInfo{Signal: telemetrytypes.SignalLogs, StartNs: start, EndNs: end, BodyJSONOn: true},
},
{
name: "Traces",
storage: tracestelemetryschema.NewStorage(schemaMetadataStore),
query: qbtypes.QueryInfo{Signal: telemetrytypes.SignalTraces, StartNs: start, EndNs: end},
},
{
name: "Traces_JSONAttributes",
storage: tracestelemetryschema.NewStorage(schemaMetadataStore),
query: qbtypes.QueryInfo{Signal: telemetrytypes.SignalTraces, StartNs: start, EndNs: end, TraceAttrsJSONOn: true},
},
{
name: "Metrics",
storage: metricstelemetryschema.NewStorage(),
query: qbtypes.QueryInfo{Signal: telemetrytypes.SignalMetrics, StartNs: start, EndNs: end},
},
{
name: "Audit",
storage: audittelemetryschema.NewStorage(),
query: qbtypes.QueryInfo{Signal: telemetrytypes.SignalLogs, StartNs: start, EndNs: end},
},
}
for _, testCase := range testCases {
for _, value := range (telemetrytypes.FieldContext{}).Enum() {
fieldContext, ok := value.(telemetrytypes.FieldContext)
require.True(t, ok)
t.Run(testCase.name+"_"+fieldContext.StringValue(), func(t *testing.T) {
key := telemetrytypes.TelemetryFieldKey{Name: "unknown.key", FieldContext: fieldContext, Signal: testCase.query.Signal}
_, err := querybuilder.ResolveColumn(context.Background(), testCase.query, testCase.storage, &key, telemetrytypes.FieldDataTypeUnspecified, map[string][]*telemetrytypes.TelemetryFieldKey{})
if err != nil {
assert.True(t, errors.Ast(err, errors.TypeInvalidInput), "%v", err)
}
})
}
}
}

View File

@@ -505,7 +505,7 @@ func (m *storage) Fallback(_ context.Context, _ qbtypes.QueryInfo, key *telemetr
var keys []*telemetrytypes.TelemetryFieldKey
switch key.FieldContext {
case telemetrytypes.FieldContextBody:
keys = []*telemetrytypes.TelemetryFieldKey{telemetrytypes.NewTelemetryFieldKey(key.Name, key.FieldContext, key.FieldDataType)}
keys = []*telemetrytypes.TelemetryFieldKey{bodyPath(key.Name, key.FieldDataType, value)}
case telemetrytypes.FieldContextUnspecified:
if column, ok := logsV2Columns[key.Name]; ok {
keys = []*telemetrytypes.TelemetryFieldKey{{Name: key.Name, FieldContext: telemetrytypes.FieldContextLog, FieldDataType: querybuilder.ColumnDataType(column)}}

View File

@@ -240,12 +240,14 @@ def test_json_body_unknown_key_aggregation_over_body(
assert tuple(data[0]) == (6, 4), data[0]
@pytest.mark.parametrize("prefix", ["", "body."], ids=["bare", "body_prefix"])
def test_json_body_unknown_key_body_path_parity(
signoz: types.SigNoz,
create_user_admin: None, # pylint: disable=unused-argument
get_token: Callable[[str, str], str],
insert_logs: Callable[[list[Logs]], None],
export_json_types: Callable[[list[JSONPathType]], None],
prefix: str,
) -> None:
"""
Setup:
@@ -254,10 +256,11 @@ def test_json_body_unknown_key_body_path_parity(
(distributed_field_keys); unknown_field is left unregistered.
Tests:
Grouping/filtering by the registered body path (known_field, metadata-driven) and
by the unregistered one (unknown_field, synthesized body branch) return identical
results — the synthesize fallback reproduces exported-metadata resolution for body
paths, the body counterpart of the attribute parity in 13_unknown_key_collisions.py.
Grouping, counting distinct values, and selecting by the registered body path
(known_field, metadata-driven) and by the unregistered one (unknown_field,
fallback body path) return identical results, for the bare key and the
body.-prefixed key — the body counterpart of the attribute parity in
13_unknown_key_collisions.py.
"""
now = datetime.now(tz=UTC).replace(second=0, microsecond=0)
logs = []
@@ -279,7 +282,10 @@ def test_json_body_unknown_key_body_path_parity(
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
counts: dict[str, dict[str, int]] = {}
distinct: dict[str, int] = {}
selected: dict[str, list[str]] = {}
for key in ("known_field", "unknown_field"):
field = f"{prefix}{key}"
response = make_scalar_query_request(
signoz,
token,
@@ -289,13 +295,42 @@ def test_json_body_unknown_key_body_path_parity(
"A",
"logs",
[build_aggregation("count()")],
group_by=[build_group_by_field(key, field_data_type="", field_context="")],
group_by=[build_group_by_field(field, field_data_type="", field_context="")],
filter_expression=f'service.name = "{SERVICE}"',
)
],
)
assert response.status_code == HTTPStatus.OK, f"{key}: {response.text}"
assert response.status_code == HTTPStatus.OK, f"{field}: {response.text}"
counts[key] = {row[0]: row[-1] for row in get_scalar_table_data(response.json())}
response = make_scalar_query_request(
signoz,
token,
now,
[
build_scalar_query(
"A",
"logs",
[build_aggregation(f"count_distinct({field})")],
filter_expression=f'service.name = "{SERVICE}"',
)
],
)
assert response.status_code == HTTPStatus.OK, f"{field}: {response.text}"
distinct[key] = get_scalar_table_data(response.json())[0][-1]
response = make_query_request(
signoz,
token,
start_ms=int((now - timedelta(minutes=5)).timestamp() * 1000),
end_ms=int(now.timestamp() * 1000),
request_type=RequestType.RAW,
queries=[build_raw_query("A", "logs", limit=100, filter_expression=f'service.name = "{SERVICE}"', select_fields=[{"name": field}])],
)
assert response.status_code == HTTPStatus.OK, f"{field}: {response.text}"
selected[key] = sorted(row["data"][key] for row in get_rows(response))
assert counts["known_field"] == counts["unknown_field"], f"registered {counts['known_field']} != synthesized {counts['unknown_field']}"
assert counts["known_field"] == {"alpha": 2, "beta": 1}, counts["known_field"]
assert distinct == {"known_field": 2, "unknown_field": 2}, distinct
assert selected == {"known_field": ["alpha", "alpha", "beta"], "unknown_field": ["alpha", "alpha", "beta"]}, selected