Compare commits

..

1 Commits

Author SHA1 Message Date
Tushar Vats
34b68e4eb1 fix(querier): decode JSON columns for every reader
`POST /api/v5/query_range` returned HTTP 500 for any scalar or time-series
query whose result carried a JSON column, since only the raw reader knew to
read one. The scan type the driver reports for a JSON column is unusable — it
comes from the zero-row header block, which carries no serialization prefix,
so the column claims object mode while the data arrives as a string.

Report JSONValue as the scan type of every JSON column at the rows boundary
instead, next to the connection setting that causes the mismatch. The querier
drops its own scan-target and decode helpers, and the v3/v4 readers stop
failing on a JSON column without changes of their own. Dynamic columns are
unwrapped from their chcol.Variant envelope so consumers get the value itself.

A JSON column can also be a group-by key — ClickHouse allows that on the
column, only refusing it on a Dynamic path — so the time-series reader labels
each series with its document rather than dropping the column and merging
every group into one line.
2026-08-19 04:08:03 +05:30
30 changed files with 313 additions and 943 deletions

View File

@@ -8807,7 +8807,6 @@ components:
- span
- trace
- resource
- scope
- attribute
- body
- ""

View File

@@ -3492,7 +3492,6 @@ export enum TelemetrytypesFieldContextDTO {
span = 'span',
trace = 'trace',
resource = 'resource',
scope = 'scope',
attribute = 'attribute',
body = 'body',
'' = '',

View File

@@ -18,9 +18,10 @@ jest.mock('periscope/components/DataViewer', () => ({
DataViewer: (): JSX.Element => <div data-testid="overview-data-viewer" />,
}));
// Force v2 for these tests regardless of route.
jest.mock('../useIsLogDetailsV2', () => ({
useIsLogDetailsV2: (): boolean => true,
// The flag to be removed later
jest.mock('../constants', () => ({
...jest.requireActual('../constants'),
isLogDetailsV2: true,
}));
const mockLog: ILog = {

View File

@@ -1,3 +1,6 @@
// temporary flag to be removed with old log details code.
export const isLogDetailsV2 = true;
export const VIEW_TYPES = {
OVERVIEW: 'OVERVIEW',
JSON: 'JSON',

View File

@@ -51,12 +51,11 @@ import { ILogBody } from 'types/api/logs/log';
import { Query, TagFilter } from 'types/api/queryBuilder/queryBuilderData';
import { DataSource, StringOperators } from 'types/common/queryBuilder';
import { RESOURCE_KEYS, VIEW_TYPES, VIEWS } from './constants';
import { isLogDetailsV2, RESOURCE_KEYS, VIEW_TYPES, VIEWS } from './constants';
import { LogDetailInnerProps, LogDetailProps } from './LogDetail.interfaces';
import LogDetailsHeader from './LogDetailsHeader/LogDetailsHeader';
import { useLogNavigation } from './LogDetailsHeader/useLogNavigation';
import LogHighlights from './LogHighlights/LogHighlights';
import { useIsLogDetailsV2 } from './useIsLogDetailsV2';
import './LogDetails.styles.scss';
@@ -93,8 +92,6 @@ function LogDetailInner({
const [isEdit, setIsEdit] = useState<boolean>(false);
const { stagedQuery } = useQueryBuilder();
const isLogDetailsV2 = useIsLogDetailsV2();
// Handle clicks outside to close drawer, except on explicitly ignored regions
useEffect(() => {
const handleClickOutside = (e: MouseEvent): void => {

View File

@@ -1,9 +0,0 @@
import ROUTES from 'constants/routes';
import { useLocation } from 'react-router-dom';
// v2 is rolled out only on the logs explorer route for now; every other surface
// (dashboards, infra monitoring, etc.) keeps the v1 log details view.
export function useIsLogDetailsV2(): boolean {
const { pathname } = useLocation();
return pathname === ROUTES.LOGS_EXPLORER;
}

View File

@@ -10,7 +10,6 @@ const fieldContextToSuggestionMap: Record<
[TelemetrytypesFieldContextDTO.attribute]: 'attribute',
// no maps for the following values on suggestion context
[TelemetrytypesFieldContextDTO.trace]: undefined,
[TelemetrytypesFieldContextDTO.scope]: undefined,
[TelemetrytypesFieldContextDTO.body]: undefined,
[TelemetrytypesFieldContextDTO.metric]: undefined,
[TelemetrytypesFieldContextDTO.log]: undefined,

View File

@@ -13,7 +13,7 @@ import { ChangeViewFunctionType } from 'container/ExplorerOptions/types';
import { OptionsQuery } from 'container/OptionsMenu/types';
import { useIsDarkMode } from 'hooks/useDarkMode';
import { ChevronDown, ChevronRight, Search } from '@signozhq/icons';
import { useIsLogDetailsV2 } from 'components/LogDetail/useIsLogDetailsV2';
import { isLogDetailsV2 } from 'components/LogDetail/constants';
import { DataViewer } from 'periscope/components/DataViewer';
import { IField } from 'types/api/logs/fields';
import { ILog } from 'types/api/logs/log';
@@ -69,8 +69,6 @@ function Overview({
isListViewPanel,
});
const isLogDetailsV2 = useIsLogDetailsV2();
if (isLogDetailsV2) {
const raw = aggregateAttributesResourcesToObject(logData);
const prettyData = buildPrettyViewData(raw);

View File

@@ -1,6 +1,7 @@
package querier
import (
"encoding/json"
"fmt"
"math"
"reflect"
@@ -11,12 +12,12 @@ import (
"strings"
"time"
"github.com/ClickHouse/clickhouse-go/v2/lib/chcol"
"github.com/ClickHouse/clickhouse-go/v2/lib/driver"
"github.com/SigNoz/signoz/pkg/errors"
qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
"github.com/SigNoz/signoz/pkg/types/spantypes"
"github.com/SigNoz/signoz/pkg/types/telemetrystoretypes"
"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
"github.com/bytedance/sonic"
)
var (
@@ -30,8 +31,6 @@ var (
// written clickhouse query. The column alias indcate which value is
// to be considered as final result (or target).
legacyReservedColumnTargetAliases = []string{"__result", "__value", "result", "res", "value"}
CodeFailUnmarshalJSONColumn = errors.MustNewCode("fail_unmarshal_json_column")
)
// stripKeyAlias removes the __SELECT_KEY_<n>_ / __GROUP_BY_KEY_<n>_ prefix from a result
@@ -40,6 +39,32 @@ func stripKeyAlias(name string) string {
return keyAliasRe.ReplaceAllString(name, "")
}
// unwrapVariant returns the concrete value inside the chcol.Variant envelope the driver scans a
// Dynamic column — a JSON path such as body_v2.level — into.
func unwrapVariant(val any) any {
if v, ok := val.(chcol.Variant); ok {
return v.Any()
}
return val
}
// labelValue renders a group-by value the payload cannot carry as a scalar — a JSON column, or a
// Dynamic one — as a stable string, so that rows differing only in that value land in different
// series. JSON goes through encoding/json for its sorted map keys: ClickHouse groups documents by
// structure, so two rows it considers equal have to produce the same label.
func labelValue(val any) string {
val = unwrapVariant(val)
if val == nil {
return ""
}
if v, ok := val.(telemetrystoretypes.JSONValue); ok {
if raw, err := json.Marshal(v); err == nil {
return string(raw)
}
}
return fmt.Sprint(val)
}
// consume reads every row and shapes it into the payload expected for the
// given request type.
//
@@ -205,6 +230,14 @@ func readAsTimeSeries(rows driver.Rows, queryWindow *qbtypes.TimeRange, step qbt
Value: *val,
})
case *telemetrystoretypes.JSONValue, *chcol.Variant:
val := labelValue(derefValue(ptr))
lblVals = append(lblVals, val)
lblObjs = append(lblObjs, &qbtypes.Label{
Key: telemetrytypes.TelemetryFieldKey{Name: name},
Value: val,
})
default:
continue
}
@@ -345,7 +378,7 @@ func readAsScalar(rows driver.Rows, queryName string) (*qbtypes.ScalarData, erro
// 2. deref each slot into the output row
row := make([]any, len(scan))
for i, cell := range scan {
row[i] = derefValue(cell)
row[i] = unwrapVariant(derefValue(cell))
}
data = append(data, row)
}
@@ -382,31 +415,13 @@ func readAsRaw(rows driver.Rows, queryName string) (*qbtypes.RawData, error) {
colTypes := rows.ColumnTypes()
colCnt := len(colNames)
// Helper that decides scan target per column based on DB type
makeScanTarget := func(i int) any {
dbt := strings.ToUpper(colTypes[i].DatabaseTypeName())
if strings.HasPrefix(dbt, "JSON") {
// Since the driver fails to decode JSON/Dynamic into native Go values, we read it as raw bytes
// TODO: check in future if fixed in the driver
var v []byte
return &v
}
return reflect.New(colTypes[i].ScanType()).Interface()
}
// Build a template slice of correctly-typed pointers once
scanTpl := make([]any, colCnt)
for i := range colTypes {
scanTpl[i] = makeScanTarget(i)
}
var outRows []*qbtypes.RawRow
for rows.Next() {
// fresh copy of the scan slice (otherwise the driver reuses pointers)
scan := make([]any, colCnt)
for i := range scanTpl {
scan[i] = makeScanTarget(i)
for i := range colTypes {
scan[i] = reflect.New(colTypes[i].ScanType()).Interface()
}
if err := rows.Scan(scan...); err != nil {
@@ -421,21 +436,7 @@ func readAsRaw(rows driver.Rows, queryName string) (*qbtypes.RawData, error) {
name := stripKeyAlias(colNames[i])
// de-reference the typed pointer to any
val := reflect.ValueOf(cellPtr).Elem().Interface()
// Post-process JSON columns: unmarshal bytes into map[string]any
if strings.HasPrefix(strings.ToUpper(colTypes[i].DatabaseTypeName()), "JSON") {
switch x := val.(type) {
case []byte:
var m map[string]any
err := sonic.Unmarshal(x, &m)
if err != nil {
return nil, errors.WrapInternalf(err, CodeFailUnmarshalJSONColumn, "failed to unmarshal JSON column %s", name)
}
val = m
default:
// already a structured type (map[string]any, []any, etc.)
}
}
val := unwrapVariant(reflect.ValueOf(cellPtr).Elem().Interface())
// special-case: timestamp column
if name == "timestamp" || name == "timestamp_datetime" {

View File

@@ -3,8 +3,16 @@ package querier
import (
"reflect"
"testing"
"time"
"github.com/ClickHouse/clickhouse-go/v2/lib/chcol"
cmock "github.com/SigNoz/clickhouse-go-mock"
"github.com/SigNoz/signoz/pkg/telemetrystore"
qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
"github.com/SigNoz/signoz/pkg/types/spantypes"
"github.com/SigNoz/signoz/pkg/types/telemetrystoretypes"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
func TestMergeSpanAttributeColumns_ParsesEventsAndLinks(t *testing.T) {
@@ -75,6 +83,103 @@ func TestMergeSpanAttributeColumns_ParsesEventsAndLinks(t *testing.T) {
}
}
// A ClickHouse query can put a JSON column in the result of any request type — e.g.
// `select * from signoz_logs.logs_v2` on a body_v2 stack, where `*` covers body_v2.
func TestConsume_JSONColumn(t *testing.T) {
ts := time.Date(2026, 8, 14, 10, 0, 0, 0, time.UTC)
body := `{"level":"error","attrs":{"code":500}}`
wantBody := telemetrystoretypes.JSONValue{
"level": "error",
"attrs": map[string]any{"code": float64(500)},
}
// the scalar reader reuses its scan slots across rows, so each row must still carry its own body
t.Run("scalar", func(t *testing.T) {
rows := telemetrystore.WrapRows(cmock.NewRows([]cmock.ColumnType{
{Name: "body_v2", Type: "JSON"},
{Name: "__result_0", Type: "UInt64"},
}, [][]any{{body, uint64(3)}, {`{"level":"warn"}`, uint64(1)}}))
payload, err := consume(rows, qbtypes.RequestTypeScalar, nil, qbtypes.Step{}, "A")
require.NoError(t, err)
data := payload.(*qbtypes.ScalarData)
require.Len(t, data.Data, 2)
assert.Equal(t, wantBody, data.Data[0][0])
assert.Equal(t, uint64(3), data.Data[0][1])
assert.Equal(t, telemetrystoretypes.JSONValue{"level": "warn"}, data.Data[1][0])
assert.Equal(t, uint64(1), data.Data[1][1])
})
t.Run("time series", func(t *testing.T) {
rows := telemetrystore.WrapRows(cmock.NewRows([]cmock.ColumnType{
{Name: "ts", Type: "DateTime"},
{Name: "body_v2", Type: "JSON"},
{Name: "__result_0", Type: "UInt64"},
}, [][]any{{ts, body, uint64(3)}}))
payload, err := consume(rows, qbtypes.RequestTypeTimeSeries, nil, qbtypes.Step{}, "A")
require.NoError(t, err)
data := payload.(*qbtypes.TimeSeriesData)
require.Len(t, data.Aggregations, 1)
require.Len(t, data.Aggregations[0].Series, 1)
require.Len(t, data.Aggregations[0].Series[0].Values, 1)
assert.Equal(t, float64(3), data.Aggregations[0].Series[0].Values[0].Value)
})
// grouping by a JSON column is legal in ClickHouse, so each document has to label its own
// series rather than being dropped, which would merge every group into one
t.Run("time series grouped by the JSON column", func(t *testing.T) {
rows := telemetrystore.WrapRows(cmock.NewRows([]cmock.ColumnType{
{Name: "ts", Type: "DateTime"},
{Name: "body_v2", Type: "JSON"},
{Name: "__result_0", Type: "UInt64"},
}, [][]any{
{ts, `{"level":"error"}`, uint64(7)},
{ts, `{"level":"warn"}`, uint64(2)},
}))
payload, err := consume(rows, qbtypes.RequestTypeTimeSeries, nil, qbtypes.Step{}, "A")
require.NoError(t, err)
data := payload.(*qbtypes.TimeSeriesData)
require.Len(t, data.Aggregations, 1)
require.Len(t, data.Aggregations[0].Series, 2)
got := map[string]float64{}
for _, series := range data.Aggregations[0].Series {
require.Len(t, series.Labels, 1)
require.Len(t, series.Values, 1)
got[series.Labels[0].Value.(string)] = series.Values[0].Value
}
assert.Equal(t, map[string]float64{`{"level":"error"}`: 7, `{"level":"warn"}`: 2}, got)
})
t.Run("raw", func(t *testing.T) {
rows := telemetrystore.WrapRows(cmock.NewRows([]cmock.ColumnType{
{Name: "timestamp", Type: "DateTime"},
{Name: "body_v2", Type: "JSON"},
}, [][]any{{ts, body}}))
payload, err := consume(rows, qbtypes.RequestTypeRaw, nil, qbtypes.Step{}, "A")
require.NoError(t, err)
data := payload.(*qbtypes.RawData)
require.Len(t, data.Rows, 1)
assert.Equal(t, ts, data.Rows[0].Timestamp.UTC())
assert.Equal(t, wantBody, data.Rows[0].Data["body_v2"])
})
}
// A JSON path (e.g. `body_v2.level`) comes back as a Dynamic column, which the driver scans
// into a chcol.Variant envelope rather than the value itself.
func TestUnwrapVariant(t *testing.T) {
assert.Equal(t, "error", unwrapVariant(chcol.NewDynamicWithType("error", "String")))
assert.Nil(t, unwrapVariant(chcol.Dynamic{}))
assert.Equal(t, uint64(3), unwrapVariant(uint64(3)))
}
func TestMergeSpanAttributeColumns_EmptyEventsAndLinks(t *testing.T) {
data := map[string]any{
"events": []string{},

View File

@@ -16,6 +16,7 @@ import (
"github.com/SigNoz/signoz/pkg/types/featuretypes"
"github.com/SigNoz/signoz/pkg/querybuilder"
qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
"github.com/SigNoz/signoz/pkg/types/telemetrystoretypes"
"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
"github.com/SigNoz/signoz/pkg/valuer"
)
@@ -1065,7 +1066,7 @@ func (q *querier) postProcessLogBody(ctx context.Context, orgID valuer.UUID, res
return result
}
for _, row := range rawData.Rows {
bodyMap, ok := row.Data["body"].(map[string]any)
bodyMap, ok := row.Data["body"].(telemetrystoretypes.JSONValue)
if !ok {
continue
}

View File

@@ -56,17 +56,6 @@ func QueryStringToKeysSelectors(query string) []*telemetrytypes.FieldKeySelector
FieldDataType: key.FieldDataType,
})
}
// todo(tushar): consider reverting changes done to this method in below PR to avoid scope specific checks
// https://github.com/SigNoz/signoz/issues/11374
if key.FieldContext == telemetrytypes.FieldContextScope {
keys = append(keys, &telemetrytypes.FieldKeySelector{
Name: key.FieldContext.StringValue() + "." + key.Name,
Signal: key.Signal,
FieldContext: telemetrytypes.FieldContextUnspecified, // this allows 'scope.' prefix for keys with other context as well
FieldDataType: key.FieldDataType,
})
}
}
}

View File

@@ -72,44 +72,6 @@ func TestQueryToKeys(t *testing.T) {
},
},
},
{
query: `scope.version = '1.0.0'`,
expectedKeys: []telemetrytypes.FieldKeySelector{
{
Name: "version",
Signal: telemetrytypes.SignalUnspecified,
FieldContext: telemetrytypes.FieldContextScope,
FieldDataType: telemetrytypes.FieldDataTypeUnspecified,
},
{
Name: "scope.version",
Signal: telemetrytypes.SignalUnspecified,
FieldContext: telemetrytypes.FieldContextUnspecified,
FieldDataType: telemetrytypes.FieldDataTypeUnspecified,
},
},
},
{
// A scope attribute whose own name carries a `scope.` prefix. `scope.prefixed`
// normalizes to {prefixed, scope}; the second selector re-adds the prefix so the
// metadata fetch can target the attribute's exact key `scope.prefixed` rather than
// relying on the broad `%prefixed%` match.
query: `scope.prefixed = 'x'`,
expectedKeys: []telemetrytypes.FieldKeySelector{
{
Name: "prefixed",
Signal: telemetrytypes.SignalUnspecified,
FieldContext: telemetrytypes.FieldContextScope,
FieldDataType: telemetrytypes.FieldDataTypeUnspecified,
},
{
Name: "scope.prefixed",
Signal: telemetrytypes.SignalUnspecified,
FieldContext: telemetrytypes.FieldContextUnspecified,
FieldDataType: telemetrytypes.FieldDataTypeUnspecified,
},
},
},
}
for _, testCase := range testCases {

View File

@@ -163,15 +163,31 @@ func getKeySelectors(query qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation])
}
for idx := range query.GroupBy {
keySelectors = append(keySelectors, keySelectorsForField(query.GroupBy[idx].TelemetryFieldKey)...)
groupBy := query.GroupBy[idx]
keySelectors = append(keySelectors, &telemetrytypes.FieldKeySelector{
Name: groupBy.Name,
Signal: telemetrytypes.SignalTraces,
FieldContext: groupBy.FieldContext,
FieldDataType: groupBy.FieldDataType,
})
}
for idx := range query.SelectFields {
keySelectors = append(keySelectors, keySelectorsForField(query.SelectFields[idx])...)
keySelectors = append(keySelectors, &telemetrytypes.FieldKeySelector{
Name: query.SelectFields[idx].Name,
Signal: telemetrytypes.SignalTraces,
FieldContext: query.SelectFields[idx].FieldContext,
FieldDataType: query.SelectFields[idx].FieldDataType,
})
}
for idx := range query.Order {
keySelectors = append(keySelectors, keySelectorsForField(query.Order[idx].Key.TelemetryFieldKey)...)
keySelectors = append(keySelectors, &telemetrytypes.FieldKeySelector{
Name: query.Order[idx].Key.Name,
Signal: telemetrytypes.SignalTraces,
FieldContext: query.Order[idx].Key.FieldContext,
FieldDataType: query.Order[idx].Key.FieldDataType,
})
}
for idx := range keySelectors {
@@ -182,26 +198,6 @@ func getKeySelectors(query qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation])
return keySelectors
}
func keySelectorsForField(key telemetrytypes.TelemetryFieldKey) []*telemetrytypes.FieldKeySelector {
selectors := []*telemetrytypes.FieldKeySelector{
{
Name: key.Name,
Signal: telemetrytypes.SignalTraces,
FieldContext: key.FieldContext,
FieldDataType: key.FieldDataType,
},
}
if key.FieldContext != telemetrytypes.FieldContextUnspecified {
selectors = append(selectors, &telemetrytypes.FieldKeySelector{
Name: key.FieldContext.StringValue() + "." + key.Name,
Signal: telemetrytypes.SignalTraces,
FieldContext: telemetrytypes.FieldContextUnspecified,
FieldDataType: key.FieldDataType,
})
}
return selectors
}
// mergeDeprecatedTraceKeys prepends deprecated intrinsic/calculated trace field
// definitions to the keys map. We do this during statement building, not at
// metadata fetch time, because:
@@ -273,14 +269,20 @@ func adjustTraceKey(key *telemetrytypes.TelemetryFieldKey, keys map[string][]*te
For example: trace_id (intrinsic), response_status_code (calculated).
*/
// Resolve against the context-qualified name first, then the bare name since that can be instrinsic field e.g. scope.name.
var isIntrinsicOrCalculatedField bool
var intrinsicOrCalculatedField telemetrytypes.TelemetryFieldKey
if key.FieldContext != telemetrytypes.FieldContextUnspecified {
intrinsicOrCalculatedField, isIntrinsicOrCalculatedField = lookupIntrinsicOrCalculatedField(key.FieldContext.StringValue() + "." + key.Name)
}
if !isIntrinsicOrCalculatedField {
intrinsicOrCalculatedField, isIntrinsicOrCalculatedField = lookupIntrinsicOrCalculatedField(key.Name)
if _, ok := tracestelemetryschema.IntrinsicFields[key.Name]; ok {
isIntrinsicOrCalculatedField = true
intrinsicOrCalculatedField = tracestelemetryschema.IntrinsicFields[key.Name]
} else if _, ok := tracestelemetryschema.CalculatedFields[key.Name]; ok {
isIntrinsicOrCalculatedField = true
intrinsicOrCalculatedField = tracestelemetryschema.CalculatedFields[key.Name]
} else if _, ok := tracestelemetryschema.IntrinsicFieldsDeprecated[key.Name]; ok {
isIntrinsicOrCalculatedField = true
intrinsicOrCalculatedField = tracestelemetryschema.IntrinsicFieldsDeprecated[key.Name]
} else if _, ok := tracestelemetryschema.CalculatedFieldsDeprecated[key.Name]; ok {
isIntrinsicOrCalculatedField = true
intrinsicOrCalculatedField = tracestelemetryschema.CalculatedFieldsDeprecated[key.Name]
}
if isIntrinsicOrCalculatedField {
@@ -292,24 +294,6 @@ func adjustTraceKey(key *telemetrytypes.TelemetryFieldKey, keys map[string][]*te
return actions
}
// lookupIntrinsicOrCalculatedField returns the intrinsic or calculated field registered under
// name, across the current and deprecated tables.
func lookupIntrinsicOrCalculatedField(name string) (telemetrytypes.TelemetryFieldKey, bool) {
if f, ok := tracestelemetryschema.IntrinsicFields[name]; ok {
return f, true
}
if f, ok := tracestelemetryschema.CalculatedFields[name]; ok {
return f, true
}
if f, ok := tracestelemetryschema.IntrinsicFieldsDeprecated[name]; ok {
return f, true
}
if f, ok := tracestelemetryschema.CalculatedFieldsDeprecated[name]; ok {
return f, true
}
return telemetrytypes.TelemetryFieldKey{}, false
}
// buildListQuery builds a query for list panel type.
func (b *traceQueryStatementBuilder) buildListQuery(
ctx context.Context,

View File

@@ -374,94 +374,6 @@ func TestStatementBuilder(t *testing.T) {
},
expectedErr: nil,
},
{
name: "scope.name filter and group by",
requestType: qbtypes.RequestTypeTimeSeries,
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
StepInterval: qbtypes.Step{Duration: 30 * time.Second},
Aggregations: []qbtypes.TraceAggregation{
{
Expression: "count()",
},
},
Filter: &qbtypes.Filter{
Expression: "scope.name = 'opentelemetry-io'",
},
Limit: 10,
GroupBy: []qbtypes.GroupByKey{
{
TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
Name: "scope.name",
FieldContext: telemetrytypes.FieldContextScope,
},
},
},
},
expected: qbtypes.Statement{
Query: "WITH __limit_cte AS (SELECT toString(multiIf(scope.name::String <> '', scope.name::String, NULL)) AS `__GROUP_BY_KEY_0_scope.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE (scope.name::String = ? AND scope.name::String <> '') AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? GROUP BY `__GROUP_BY_KEY_0_scope.name` ORDER BY __result_0 DESC LIMIT ?) SELECT toStartOfInterval(timestamp, INTERVAL 30 SECOND) AS ts, toString(multiIf(scope.name::String <> '', scope.name::String, NULL)) AS `__GROUP_BY_KEY_0_scope.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE (scope.name::String = ? AND scope.name::String <> '') AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND (`__GROUP_BY_KEY_0_scope.name`) GLOBAL IN (SELECT `__GROUP_BY_KEY_0_scope.name` FROM __limit_cte) GROUP BY ts, `__GROUP_BY_KEY_0_scope.name`",
Args: []any{"opentelemetry-io", "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10, "opentelemetry-io", "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448)},
},
expectedErr: nil,
},
{
name: "scope.version filter with scope.name group by",
requestType: qbtypes.RequestTypeTimeSeries,
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
StepInterval: qbtypes.Step{Duration: 30 * time.Second},
Aggregations: []qbtypes.TraceAggregation{
{
Expression: "count()",
},
},
Filter: &qbtypes.Filter{
Expression: "scope.version = '1.0.0'",
},
Limit: 10,
GroupBy: []qbtypes.GroupByKey{
{
TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
Name: "scope.name",
FieldContext: telemetrytypes.FieldContextScope,
},
},
},
},
expected: qbtypes.Statement{
Query: "WITH __limit_cte AS (SELECT toString(multiIf(scope.name::String <> '', scope.name::String, NULL)) AS `__GROUP_BY_KEY_0_scope.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE (scope.version::String = ? AND scope.version::String <> '') AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? GROUP BY `__GROUP_BY_KEY_0_scope.name` ORDER BY __result_0 DESC LIMIT ?) SELECT toStartOfInterval(timestamp, INTERVAL 30 SECOND) AS ts, toString(multiIf(scope.name::String <> '', scope.name::String, NULL)) AS `__GROUP_BY_KEY_0_scope.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE (scope.version::String = ? AND scope.version::String <> '') AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND (`__GROUP_BY_KEY_0_scope.name`) GLOBAL IN (SELECT `__GROUP_BY_KEY_0_scope.name` FROM __limit_cte) GROUP BY ts, `__GROUP_BY_KEY_0_scope.name`",
Args: []any{"1.0.0", "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10, "1.0.0", "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448)},
},
expectedErr: nil,
},
{
name: "scope.version filter only (no scope field in group by)",
requestType: qbtypes.RequestTypeTimeSeries,
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
StepInterval: qbtypes.Step{Duration: 30 * time.Second},
Aggregations: []qbtypes.TraceAggregation{
{
Expression: "count()",
},
},
Filter: &qbtypes.Filter{
Expression: "scope.version = '1.0.0'",
},
Limit: 10,
GroupBy: []qbtypes.GroupByKey{
{
TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
Name: "service.name",
},
},
},
},
expected: qbtypes.Statement{
Query: "WITH __limit_cte AS (SELECT toString(multiIf(multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) IS NOT NULL, multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL), NULL)) AS `__GROUP_BY_KEY_0_service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE (scope.version::String = ? AND scope.version::String <> '') AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? GROUP BY `__GROUP_BY_KEY_0_service.name` ORDER BY __result_0 DESC LIMIT ?) SELECT toStartOfInterval(timestamp, INTERVAL 30 SECOND) AS ts, toString(multiIf(multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) IS NOT NULL, multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL), NULL)) AS `__GROUP_BY_KEY_0_service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE (scope.version::String = ? AND scope.version::String <> '') AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND (`__GROUP_BY_KEY_0_service.name`) GLOBAL IN (SELECT `__GROUP_BY_KEY_0_service.name` FROM __limit_cte) GROUP BY ts, `__GROUP_BY_KEY_0_service.name`",
Args: []any{"1.0.0", "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10, "1.0.0", "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448)},
},
},
}
fl := flaggertest.New(t)
@@ -888,143 +800,6 @@ func TestStatementBuilderListQueryWithCorruptData(t *testing.T) {
},
expectedErr: nil,
},
{
name: "List query with scope filter only (no scope in select or group by)",
requestType: qbtypes.RequestTypeRaw,
keysMap: map[string][]*telemetrytypes.TelemetryFieldKey{
"scope.version": {
{
Name: "scope.version",
Signal: telemetrytypes.SignalTraces,
FieldContext: telemetrytypes.FieldContextScope,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
},
},
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
StepInterval: qbtypes.Step{Duration: 30 * time.Second},
Filter: &qbtypes.Filter{
Expression: "scope.version = '1.0.0'",
},
Limit: 10,
},
expected: qbtypes.Statement{
Query: "SELECT timestamp AS `__SELECT_KEY_0_timestamp`, trace_id AS `__SELECT_KEY_1_trace_id`, span_id AS `__SELECT_KEY_2_span_id`, trace_state AS `__SELECT_KEY_3_trace_state`, parent_span_id AS `__SELECT_KEY_4_parent_span_id`, flags AS `__SELECT_KEY_5_flags`, name AS `__SELECT_KEY_6_name`, kind AS `__SELECT_KEY_7_kind`, kind_string AS `__SELECT_KEY_8_kind_string`, duration_nano AS `__SELECT_KEY_9_duration_nano`, status_code AS `__SELECT_KEY_10_status_code`, status_message AS `__SELECT_KEY_11_status_message`, status_code_string AS `__SELECT_KEY_12_status_code_string`, events AS `__SELECT_KEY_13_events`, links AS `__SELECT_KEY_14_links`, response_status_code AS `__SELECT_KEY_15_response_status_code`, external_http_url AS `__SELECT_KEY_16_external_http_url`, http_url AS `__SELECT_KEY_17_http_url`, external_http_method AS `__SELECT_KEY_18_external_http_method`, http_method AS `__SELECT_KEY_19_http_method`, http_host AS `__SELECT_KEY_20_http_host`, db_name AS `__SELECT_KEY_21_db_name`, db_operation AS `__SELECT_KEY_22_db_operation`, has_error AS `__SELECT_KEY_23_has_error`, is_remote AS `__SELECT_KEY_24_is_remote`, attributes_string, attributes_number, attributes_bool, resources_string FROM signoz_traces.distributed_signoz_index_v3 WHERE (scope.version::String = ? AND scope.version::String <> '') AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? LIMIT ?",
Args: []any{"1.0.0", "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10},
},
},
{
// Regression test: scope.version in selectFields with no metadata (isColumn=true filters it out)
// must still produce scope.version::String, not scope.attributes.version::String
name: "scope.version in selectFields only, no metadata (intrinsic field fallback)",
requestType: qbtypes.RequestTypeRaw,
keysMap: map[string][]*telemetrytypes.TelemetryFieldKey{},
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
StepInterval: qbtypes.Step{Duration: 30 * time.Second},
Filter: &qbtypes.Filter{},
SelectFields: []telemetrytypes.TelemetryFieldKey{
{Name: "scope.version", FieldContext: telemetrytypes.FieldContextUnspecified},
},
Limit: 10,
},
expected: qbtypes.Statement{
Query: "SELECT timestamp AS `__SELECT_KEY_0_timestamp`, trace_id AS `__SELECT_KEY_1_trace_id`, span_id AS `__SELECT_KEY_2_span_id`, multiIf(scope.version::String <> '', scope.version::String, NULL) AS `__SELECT_KEY_3_scope.version` FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? LIMIT ?",
Args: []any{"1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10},
},
},
{
// A scope attribute whose own name literally carries a `scope.` prefix (`scope.prefixed`,
// normalized to {prefixed, scope}) resolves to that attribute in a SELECT even without a
// filter: getKeySelectors emits the reconstructed `scope.prefixed` selector so the metadata
// fetch surfaces it and AdjustKey recovers the full name. Without it the `scope.` prefix is
// lost and it wrongly reads `scope.attributes.prefixed`.
name: "scope-prefixed attribute in selectFields resolves without a filter",
requestType: qbtypes.RequestTypeRaw,
keysMap: map[string][]*telemetrytypes.TelemetryFieldKey{
"scope.prefixed": {
{
Name: "scope.prefixed",
Signal: telemetrytypes.SignalTraces,
FieldContext: telemetrytypes.FieldContextScope,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
},
},
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
StepInterval: qbtypes.Step{Duration: 30 * time.Second},
Filter: &qbtypes.Filter{},
SelectFields: []telemetrytypes.TelemetryFieldKey{
{Name: "prefixed", FieldContext: telemetrytypes.FieldContextScope},
},
Limit: 10,
},
expected: qbtypes.Statement{
Query: "SELECT timestamp AS `__SELECT_KEY_0_timestamp`, trace_id AS `__SELECT_KEY_1_trace_id`, span_id AS `__SELECT_KEY_2_span_id`, multiIf(scope.attributes.`scope.prefixed` IS NOT NULL, scope.attributes.`scope.prefixed`::String, NULL) AS `__SELECT_KEY_3_scope.prefixed` FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? LIMIT ?",
Args: []any{"1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10},
},
},
{
// A scope-context key whose name matches a declared scope path resolves to that
// declared path (scope.name), not the span `name` column and not an undeclared
// scope attribute. getTracesKeys surfaces the declared path as an intrinsic key
// (metadata.go), which shadows the same-named span intrinsic.
name: "scope-context name resolves to the declared scope path",
requestType: qbtypes.RequestTypeRaw,
keysMap: map[string][]*telemetrytypes.TelemetryFieldKey{
"scope.name": {
{
Name: "scope.name",
Signal: telemetrytypes.SignalTraces,
FieldContext: telemetrytypes.FieldContextScope,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
},
"name": {
{
Name: "name",
Signal: telemetrytypes.SignalTraces,
FieldContext: telemetrytypes.FieldContextSpan,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
},
},
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
StepInterval: qbtypes.Step{Duration: 30 * time.Second},
Filter: &qbtypes.Filter{},
SelectFields: []telemetrytypes.TelemetryFieldKey{
{Name: "name", FieldContext: telemetrytypes.FieldContextScope},
},
Limit: 10,
},
expected: qbtypes.Statement{
Query: "SELECT timestamp AS `__SELECT_KEY_0_timestamp`, trace_id AS `__SELECT_KEY_1_trace_id`, span_id AS `__SELECT_KEY_2_span_id`, multiIf(scope.name::String <> '', scope.name::String, NULL) AS `__SELECT_KEY_3_name` FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? LIMIT ?",
Args: []any{"1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10},
},
},
{
// span.scope.name (span context, name "scope.name") resolves to the declared
// scope path scope.name, not a span attribute literally named scope.name.
name: "span-context scope.name in selectFields resolves to the declared scope path",
requestType: qbtypes.RequestTypeRaw,
keysMap: map[string][]*telemetrytypes.TelemetryFieldKey{},
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
StepInterval: qbtypes.Step{Duration: 30 * time.Second},
Filter: &qbtypes.Filter{},
SelectFields: []telemetrytypes.TelemetryFieldKey{
{Name: "scope.name", FieldContext: telemetrytypes.FieldContextSpan},
},
Limit: 10,
},
expected: qbtypes.Statement{
Query: "SELECT timestamp AS `__SELECT_KEY_0_timestamp`, trace_id AS `__SELECT_KEY_1_trace_id`, span_id AS `__SELECT_KEY_2_span_id`, multiIf(scope.name::String <> '', scope.name::String, NULL) AS `__SELECT_KEY_3_scope.name` FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? LIMIT ?",
Args: []any{"1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10},
},
},
}
for _, c := range cases {

View File

@@ -180,7 +180,7 @@ func (t *telemetryMetaStore) getTracesKeys(ctx context.Context, fieldKeySelector
`CASE
// WHEN tagType = 'spanfield' THEN 1
WHEN tagType = 'resource' THEN 2
WHEN tagType = 'scope' THEN 3
// WHEN tagType = 'scope' THEN 3
WHEN tagType = 'tag' THEN 4
ELSE 5
END as priority`,

View File

@@ -391,96 +391,6 @@ func TestConditionForResourceWithEvolution(t *testing.T) {
}
}
// TestConditionForScopeIntrinsicFields covers the scope.name/scope.version intrinsic
// fields against the "scope" JSON column. These are *declared* String paths on that
// column, so a row without a scope reads as ” and never NULL: presence must be an
// empty-string check, since "IS NOT NULL" would hold for every row. That also rules
// out treating them as nested attribute keys under scope.attributes, which are
// undeclared (Dynamic) paths and genuinely NULL when absent.
func TestConditionForScopeIntrinsicFields(t *testing.T) {
ctx := context.Background()
fm := NewFieldMapper(flaggertest.New(t))
conditionBuilder := NewConditionBuilder(fm, flaggertest.New(t))
testCases := []struct {
name string
key telemetrytypes.TelemetryFieldKey
operator qbtypes.FilterOperator
value any
expectedSQL string
}{
{
name: "Equal - scope.name",
key: telemetrytypes.TelemetryFieldKey{
Name: "scope.name",
FieldContext: telemetrytypes.FieldContextScope,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
operator: qbtypes.FilterOperatorEqual,
value: "io.signoz.payment",
expectedSQL: "(scope.name::String = ? AND scope.name::String <> '')",
},
{
name: "Equal - scope.version",
key: telemetrytypes.TelemetryFieldKey{
Name: "scope.version",
FieldContext: telemetrytypes.FieldContextScope,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
operator: qbtypes.FilterOperatorEqual,
value: "2.3.1",
expectedSQL: "(scope.version::String = ? AND scope.version::String <> '')",
},
{
name: "Exists - scope.name",
key: telemetrytypes.TelemetryFieldKey{
Name: "scope.name",
FieldContext: telemetrytypes.FieldContextScope,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
operator: qbtypes.FilterOperatorExists,
value: nil,
expectedSQL: "scope.name::String <> ''",
},
{
name: "NotExists - scope.version",
key: telemetrytypes.TelemetryFieldKey{
Name: "scope.version",
FieldContext: telemetrytypes.FieldContextScope,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
operator: qbtypes.FilterOperatorNotExists,
value: nil,
expectedSQL: "scope.version::String = ''",
},
{
// `scope.attribute.name` (normalized to {attribute.name, scope}) addresses the scope
// attribute named `name` — the declared `scope.name` path is never reached this way.
name: "Equal - scope.attribute.name reaches the named scope attribute",
key: telemetrytypes.TelemetryFieldKey{
Name: "attribute.name",
FieldContext: telemetrytypes.FieldContextScope,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
operator: qbtypes.FilterOperatorEqual,
value: "io.signoz.checkout",
expectedSQL: "(scope.attributes.`name`::String = ? AND scope.attributes.`name` IS NOT NULL)",
},
}
for _, tc := range testCases {
sb := sqlbuilder.NewSelectBuilder()
t.Run(tc.name, func(t *testing.T) {
conds, _, err := conditionBuilder.ConditionFor(ctx, valuer.UUID{}, 0, 0, &tc.key, map[string][]*telemetrytypes.TelemetryFieldKey{tc.key.Name: {&tc.key}}, qbtypes.ConditionBuilderOptions{}, tc.operator, tc.value, sb)
require.NoError(t, err)
sb.Where(conds...)
sql, _ := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
assert.Contains(t, sql, tc.expectedSQL)
assert.NotContains(t, sql, "scope.`scope.", "must not double-prefix the scope JSON path")
})
}
}
// TestConditionForSynthesizedKeys covers the KeyNotFound fallback: when a
// referenced attribute key has no metadata match, the builder synthesizes key(s) from
// user input and queries anyway, emitting a warning instead of failing.
@@ -504,17 +414,6 @@ func TestConditionForSynthesizedKeys(t *testing.T) {
assert.Contains(t, args, "timeout")
})
t.Run("scope context with no metadata -> scope attribute", func(t *testing.T) {
sb := sqlbuilder.NewSelectBuilder()
key := telemetrytypes.TelemetryFieldKey{Name: "custom.attr", FieldContext: telemetrytypes.FieldContextScope}
conds, warnings, err := cb.ConditionFor(ctx, valuer.UUID{}, 0, 0, &key, noMatches, qbtypes.ConditionBuilderOptions{}, qbtypes.FilterOperatorEqual, "v", sb)
assert.NoError(t, err, "an undeclared scope attribute must still be filterable")
assert.NotEmpty(t, warnings)
sb.Where(conds...)
sql, _ := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
assert.Contains(t, sql, "scope.attributes.`custom.attr`")
})
t.Run("bare key with number operand -> attribute number", func(t *testing.T) {
sb := sqlbuilder.NewSelectBuilder()
key := telemetrytypes.TelemetryFieldKey{Name: "http.status"}

View File

@@ -121,20 +121,6 @@ var (
FieldContext: telemetrytypes.FieldContextSpan,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
"scope.name": {
Name: "scope.name",
Description: "Instrumentation scope name",
Signal: telemetrytypes.SignalTraces,
FieldContext: telemetrytypes.FieldContextScope,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
"scope.version": {
Name: "scope.version",
Description: "Instrumentation scope version",
Signal: telemetrytypes.SignalTraces,
FieldContext: telemetrytypes.FieldContextScope,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
}
IntrinsicFieldsDeprecated = map[string]telemetrytypes.TelemetryFieldKey{
"traceID": {

View File

@@ -53,7 +53,6 @@ var (
ValueType: schema.ColumnTypeString,
}},
"resource": {Name: "resource", Type: schema.JSONColumnType{}},
"scope": {Name: "scope", Type: schema.JSONColumnType{}},
"events": {Name: "events", Type: schema.ArrayColumnType{
ElementType: schema.ColumnTypeString,
@@ -182,7 +181,7 @@ func (m *fieldMapper) getColumn(
case telemetrytypes.FieldContextResource:
return []*schema.Column{indexV3Columns["resource"], indexV3Columns["resources_string"]}, nil
case telemetrytypes.FieldContextScope:
return []*schema.Column{indexV3Columns["scope"]}, nil
return []*schema.Column{}, qbtypes.ErrColumnNotFound
case telemetrytypes.FieldContextAttribute:
switch key.FieldDataType {
case telemetrytypes.FieldDataTypeString:
@@ -293,25 +292,14 @@ func (m *fieldMapper) resolveColumnExprs(
switch column.Type.GetType() {
case schema.ColumnTypeEnumJSON:
// json is only supported for resource context as of now
if key.FieldContext != telemetrytypes.FieldContextResource {
return nil, nil, nil, errors.Newf(errors.TypeInvalidInput, errors.CodeInvalidInput, "only resource context fields are supported for json columns, got %s", key.FieldContext.String)
}
// have to add ::string as clickHouse throws an error :- data types Variant/Dynamic are not allowed in GROUP BY
// once clickHouse dependency is updated, we need to check if we can remove it.
switch key.FieldContext {
case telemetrytypes.FieldContextResource:
exprs = append(exprs, fmt.Sprintf("%s.`%s`::String", columnName, key.Name))
existExprs = append(existExprs, fmt.Sprintf("%s.`%s` IS NOT NULL", columnName, key.Name))
case telemetrytypes.FieldContextScope:
if f, ok := IntrinsicFields[key.Name]; ok && f.FieldContext == telemetrytypes.FieldContextScope {
// declared String paths on the scope column read '' for the missing case
exprs = append(exprs, fmt.Sprintf("%s::String", key.Name))
existExprs = append(existExprs, fmt.Sprintf("%s <> ''", key.Name))
} else {
attributeName := strings.TrimPrefix(key.Name, "attribute.") // literal "attribute" prefix in attribute keys needs double prefix
exprs = append(exprs, fmt.Sprintf("%s.attributes.%s::String", columnName, querybuilder.ClickHouseIdentifier(attributeName)))
existExprs = append(existExprs, fmt.Sprintf("%s.attributes.%s IS NOT NULL", columnName, querybuilder.ClickHouseIdentifier(attributeName)))
}
default:
return nil, nil, nil, errors.NewInternalf(errors.CodeInternal, "only resource and scope context fields are supported for json columns, got %s", key.FieldContext.String)
}
exprs = append(exprs, fmt.Sprintf("%s.`%s`::String", columnName, key.Name))
existExprs = append(existExprs, fmt.Sprintf("%s.`%s` IS NOT NULL", columnName, key.Name))
case schema.ColumnTypeEnumString,
schema.ColumnTypeEnumUInt64,
schema.ColumnTypeEnumUInt32,
@@ -353,6 +341,20 @@ func (m *fieldMapper) resolveColumnExprs(
return exprs, existExprs, columns, nil
}
// logicalForResolvedColumn upgrades a directly-resolvable key (the FieldFor
// probe succeeded) to its family when the metadata map proves membership;
// otherwise the key stays a single-member logical field.
func (m *fieldMapper) logicalForResolvedColumn(ctx context.Context, orgID valuer.UUID, field *telemetrytypes.TelemetryFieldKey, keys map[string][]*telemetrytypes.TelemetryFieldKey) *telemetrytypes.LogicalField {
for _, logical := range querybuilder.MatchingLogicalFields(ctx, orgID, m.fl, field, keys) {
if logical.IsFamily() &&
logical.FieldContext == field.FieldContext &&
(field.FieldDataType == telemetrytypes.FieldDataTypeUnspecified || logical.FieldDataType == field.FieldDataType) {
return logical
}
}
return telemetrytypes.SingleLogicalField(field.Name, field)
}
// upgradeToFamilies swaps single-member candidates for their family when the
// metadata map proves membership. Candidate order and every non-family
// candidate stay exactly as the legacy flow produced them; sibling candidates
@@ -417,12 +419,14 @@ func (m *fieldMapper) ColumnExpressionFor(
var candidates []*telemetrytypes.LogicalField
switch _, err := m.FieldFor(ctx, orgID, startNs, endNs, field); {
case err == nil:
// Every match from metadata is kept, similar to the filter path.
candidates = querybuilder.MatchingLogicalFields(ctx, orgID, m.fl, field, keys)
if len(candidates) == 0 {
candidates = []*telemetrytypes.LogicalField{telemetrytypes.SingleLogicalField(field.Name, field)}
}
// A directly-resolvable key upgrades to its family when the metadata
// map proves membership; otherwise it stays single-member.
candidates = []*telemetrytypes.LogicalField{m.logicalForResolvedColumn(ctx, orgID, field, keys)}
case errors.Is(err, qbtypes.ErrColumnNotFound):
// The legacy candidate flow, unchanged: column (when the bare name is
// one) plus metadata matches, else synthesized type-variant keys. The
// family step below only swaps candidates for their family; it never
// changes candidate order or non-family behavior.
raw := m.CandidateKeys(ctx, orgID, field, nil, keys)
if len(raw) == 0 {
return "", errors.Wrapf(err, errors.TypeInvalidInput, errors.CodeInvalidInput, "field `%s` not found", field.Name).WithSuggestions(errors.NewSuggestionsOnLevenshteinDistance(field.Name, errors.NounKeys, maps.Keys(keys))...)
@@ -595,37 +599,11 @@ func (m *fieldMapper) CandidateKeys(ctx context.Context, _ valuer.UUID, field *t
// strict context honored as-is: stripped interpretation first, literal spelling second
literal := telemetrytypes.NewTelemetryFieldKey(field.FieldContext.StringValue()+"."+field.Name, field.FieldContext, field.FieldDataType)
return append(querybuilder.SynthesizeKeys(field, value), querybuilder.SynthesizeKeys(literal, value)...)
case telemetrytypes.FieldContextScope:
// Declared scope paths (scope.name / scope.version) arrive via metadata as intrinsics;
// anything reaching synth is an undeclared scope attribute.
return []*telemetrytypes.TelemetryFieldKey{telemetrytypes.NewTelemetryFieldKey(field.Name, telemetrytypes.FieldContextScope, telemetrytypes.FieldDataTypeString)}
}
// contexts that don't exist on spans (log, body, …) have nothing to synthesize
// contexts that don't exist on spans (log, body, scope, …) have nothing to synthesize
return nil
}
// scopeJSONExistsExpression renders the existence predicate for the scope JSON column, the one
// signal-specific case the generic querybuilder.ExistsExpression must not carry.
func scopeJSONExistsExpression(key *telemetrytypes.TelemetryFieldKey, fieldExpression string, exists bool) (string, bool) {
if key.FieldContext != telemetrytypes.FieldContextScope {
return "", false
}
// Declared String paths are non-Nullable (absent reads '' not NULL).
if f, ok := IntrinsicFields[key.Name]; ok && f.FieldContext == telemetrytypes.FieldContextScope {
if exists {
return fieldExpression + " <> ''", true
}
return fieldExpression + " = ''", true
}
// Scope attribute: the value expression casts the JSON path to String, which folds a missing
// key's NULL to '', so presence must test the raw path — drop the ::String cast.
path := strings.TrimSuffix(fieldExpression, "::String")
if exists {
return path + " IS NOT NULL", true
}
return path + " IS NULL", true
}
// ExistsFor implements the per-key existence primitive of qbtypes.FieldMapper.
func (m *fieldMapper) ExistsFor(
ctx context.Context,
@@ -642,8 +620,5 @@ func (m *fieldMapper) ExistsFor(
if err != nil {
return "", err
}
if expr, ok := scopeJSONExistsExpression(key, fieldExpression, exists); ok {
return expr, nil
}
return querybuilder.ExistsExpression(columns, key, tsStart, tsEnd, fieldExpression, exists)
}

View File

@@ -84,45 +84,6 @@ func TestGetFieldKeyName(t *testing.T) {
expectedResult: "multiIf(resource.`deployment.environment` IS NOT NULL, resource.`deployment.environment`::String, `resource_string_deployment$$environment_exists`, `resource_string_deployment$$environment`, NULL)",
expectedError: nil,
},
{
name: "Scope field - scope.name",
key: telemetrytypes.TelemetryFieldKey{
Name: "scope.name",
FieldContext: telemetrytypes.FieldContextScope,
},
expectedResult: "scope.name::String",
expectedError: nil,
},
{
name: "Scope field - scope.version",
key: telemetrytypes.TelemetryFieldKey{
Name: "scope.version",
FieldContext: telemetrytypes.FieldContextScope,
},
expectedResult: "scope.version::String",
expectedError: nil,
},
{
name: "Scope field - custom attribute",
key: telemetrytypes.TelemetryFieldKey{
Name: "custom.attr",
FieldContext: telemetrytypes.FieldContextScope,
},
expectedResult: "scope.attributes.`custom.attr`::String",
expectedError: nil,
},
{
// `scope.attribute.name` normalizes to {attribute.name, scope}; the literal
// `attribute.` prefix is dropped so it addresses the scope attribute named `name`
// (which the declared `scope.name` path deliberately does not).
name: "Scope field - attribute prefix addresses the named scope attribute",
key: telemetrytypes.TelemetryFieldKey{
Name: "attribute.name",
FieldContext: telemetrytypes.FieldContextScope,
},
expectedResult: "scope.attributes.`name`::String",
expectedError: nil,
},
{
// Query like `attribute.attribute_string:string` should resolve to `attributes_string['attribute_string']`.
name: "Attribute key whose name collides with contextual map column resolves as a map lookup",
@@ -343,99 +304,3 @@ func TestColumnExpressionForTimestampAttributeCollision(t *testing.T) {
assert.Contains(t, result, "attributes_number['timestamp']")
})
}
// TestColumnExpressionForScopeDeclaredPath covers select-side resolution of scope names that
// collide with a declared scope path. A short name under scope context (or the bare
// `scope.<x>` spelling that normalizes to it) names both homes and coalesces them when
// metadata knows a same-named scope attribute, and binds to the declared path alone when it
// does not. The full `scope.<x>` name under explicit scope context addresses the declared
// path alone; the explicit `scope.attribute.` prefix addresses the attribute alone.
func TestColumnExpressionForScopeDeclaredPath(t *testing.T) {
ctx := context.Background()
scopeKey := func(name string) *telemetrytypes.TelemetryFieldKey {
return &telemetrytypes.TelemetryFieldKey{
Name: name,
Signal: telemetrytypes.SignalTraces,
FieldContext: telemetrytypes.FieldContextScope,
FieldDataType: telemetrytypes.FieldDataTypeString,
}
}
declaredOnly := map[string][]*telemetrytypes.TelemetryFieldKey{
"scope.name": {scopeKey("scope.name")},
"scope.version": {scopeKey("scope.version")},
}
withAttr := map[string][]*telemetrytypes.TelemetryFieldKey{
"scope.name": {scopeKey("scope.name")},
"scope.version": {scopeKey("scope.version")},
"name": {scopeKey("name")},
"version": {scopeKey("version")},
}
testCases := []struct {
name string
key telemetrytypes.TelemetryFieldKey
keys map[string][]*telemetrytypes.TelemetryFieldKey
expectedResult string
}{
{
name: "short name under scope context binds to the declared path",
key: telemetrytypes.TelemetryFieldKey{Name: "version", FieldContext: telemetrytypes.FieldContextScope},
keys: declaredOnly,
expectedResult: "multiIf(scope.version::String <> '', scope.version::String, NULL)",
},
{
name: "full scope.version name under scope context addresses the declared path alone",
key: telemetrytypes.TelemetryFieldKey{Name: "scope.version", FieldContext: telemetrytypes.FieldContextScope},
keys: withAttr,
expectedResult: "multiIf(scope.version::String <> '', scope.version::String, NULL)",
},
{
name: "full scope.name name under scope context addresses the declared path alone",
key: telemetrytypes.TelemetryFieldKey{Name: "scope.name", FieldContext: telemetrytypes.FieldContextScope},
keys: withAttr,
expectedResult: "multiIf(scope.name::String <> '', scope.name::String, NULL)",
},
{
// `scope.attribute.name` normalizes to {attribute.name, scope}; the `attribute.`
// prefix is dropped so it addresses the scope attribute named `name` — the only
// way to reach it, since `scope.name` is reserved for the declared path.
name: "attribute prefix reaches the named scope attribute",
key: telemetrytypes.TelemetryFieldKey{Name: "attribute.name", FieldContext: telemetrytypes.FieldContextScope},
keys: withAttr,
expectedResult: "multiIf(scope.attributes.`name` IS NOT NULL, scope.attributes.`name`::String, NULL)",
},
{
// the caller supplied the context, so `scope.` is part of the name rather than a
// prefix to strip: this addresses a scope attribute literally named
// `scope.testing.env`, not the attribute `testing.env`
name: "explicit context keeps a scope-prefixed name intact",
key: telemetrytypes.TelemetryFieldKey{Name: "scope.testing.env", FieldContext: telemetrytypes.FieldContextScope},
keys: declaredOnly,
expectedResult: "multiIf(scope.attributes.`scope.testing.env` IS NOT NULL, scope.attributes.`scope.testing.env`::String, NULL)",
},
{
// metadata knows both homes under this name, so the short spelling coalesces
// them instead of being rejected as ambiguous
name: "short name coalesces a known scope attribute with the declared path",
key: telemetrytypes.TelemetryFieldKey{Name: "name", FieldContext: telemetrytypes.FieldContextScope},
keys: withAttr,
expectedResult: "multiIf(scope.attributes.`name` IS NOT NULL, toString(scope.attributes.`name`::String), scope.name::String <> '', toString(scope.name::String), NULL)",
},
{
name: "short version coalesces a known scope attribute with the declared path",
key: telemetrytypes.TelemetryFieldKey{Name: "version", FieldContext: telemetrytypes.FieldContextScope},
keys: withAttr,
expectedResult: "multiIf(scope.attributes.`version` IS NOT NULL, toString(scope.attributes.`version`::String), scope.version::String <> '', toString(scope.version::String), NULL)",
},
}
for _, tc := range testCases {
t.Run(tc.name, func(t *testing.T) {
fm := NewFieldMapper(flaggertest.New(t))
result, err := fm.ColumnExpressionFor(ctx, valuer.UUID{}, 0, 0, &tc.key, telemetrytypes.FieldDataTypeUnspecified, tc.keys)
require.NoError(t, err)
assert.Equal(t, tc.expectedResult, result)
})
}
}

View File

@@ -113,20 +113,6 @@ func BuildCompleteFieldKeyMap(releaseTime time.Time) map[string][]*telemetrytype
FieldDataType: telemetrytypes.FieldDataTypeBool,
},
},
"scope.name": {
{
Name: "scope.name",
FieldContext: telemetrytypes.FieldContextScope,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
},
"scope.version": {
{
Name: "scope.version",
FieldContext: telemetrytypes.FieldContextScope,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
},
// both spellings of an enabled semantic-convention family
"deployment.environment.name": {
{

View File

@@ -184,7 +184,7 @@ func (p *provider) Query(ctx context.Context, query string, args ...interface{})
}
return &rowsWithHooks{
Rows: rows,
Rows: telemetrystore.WrapRows(rows),
ctx: ctx,
event: event,
onClose: func() { telemetrystore.WrapAfterQuery(p.hooks, ctx, event) },

View File

@@ -0,0 +1,39 @@
package telemetrystore
import (
"reflect"
"strings"
"github.com/ClickHouse/clickhouse-go/v2/lib/driver"
"github.com/SigNoz/signoz/pkg/types/telemetrystoretypes"
)
// WrapRows reports JSONValue as the scan type of every JSON column. Nested JSON — Array(JSON),
// Map(String, JSON) — is not covered.
func WrapRows(rows driver.Rows) driver.Rows {
return &rowsWithJSONScanType{Rows: rows}
}
type rowsWithJSONScanType struct {
driver.Rows
}
func (r *rowsWithJSONScanType) ColumnTypes() []driver.ColumnType {
colTypes := r.Rows.ColumnTypes()
wrapped := make([]driver.ColumnType, len(colTypes))
for i, colType := range colTypes {
wrapped[i] = colType
if strings.HasPrefix(strings.ToUpper(colType.DatabaseTypeName()), "JSON") {
wrapped[i] = jsonColumnType{ColumnType: colType}
}
}
return wrapped
}
type jsonColumnType struct {
driver.ColumnType
}
func (jsonColumnType) ScanType() reflect.Type {
return reflect.TypeFor[telemetrystoretypes.JSONValue]()
}

View File

@@ -4,6 +4,7 @@ import (
"context"
"github.com/ClickHouse/clickhouse-go/v2"
"github.com/ClickHouse/clickhouse-go/v2/lib/driver"
"github.com/DATA-DOG/go-sqlmock"
cmock "github.com/SigNoz/clickhouse-go-mock"
"github.com/SigNoz/signoz/pkg/telemetrystore"
@@ -32,7 +33,21 @@ func New(_ telemetrystore.Config, matcher sqlmock.QueryMatcher) *Provider {
// ClickhouseDB returns the mock Clickhouse connection.
func (p *Provider) ClickhouseDB() clickhouse.Conn {
return p.clickhouseDB.(clickhouse.Conn)
return conn{Conn: p.clickhouseDB.(clickhouse.Conn)}
}
// conn wraps rows the way the clickhouse provider does, so mocked JSON columns report the scan
// type they do in production.
type conn struct {
clickhouse.Conn
}
func (c conn) Query(ctx context.Context, query string, args ...any) (driver.Rows, error) {
rows, err := c.Conn.Query(ctx, query, args...)
if err != nil {
return nil, err
}
return telemetrystore.WrapRows(rows), nil
}
// Cluster returns the cluster name.

View File

@@ -0,0 +1,37 @@
package telemetrystoretypes
import (
"github.com/SigNoz/signoz/pkg/errors"
"github.com/bytedance/sonic"
)
var ErrCodeUnmarshalJSONColumn = errors.MustNewCode("fail_unmarshal_json_column")
// JSONValue is the scan target for a ClickHouse JSON column: the connection sets
// output_format_native_write_json_as_string, so the column arrives as a raw document rather than
// the chcol.JSON the driver reports as its scan type.
type JSONValue map[string]any
// Scan decodes into a fresh map every time: a scan target is reused across rows, and unmarshalling
// into the map already there would both keep its keys and hand every row the same map.
func (v *JSONValue) Scan(src any) error {
var raw []byte
switch value := src.(type) {
case nil:
*v = nil
return nil
case string:
raw = []byte(value)
case []byte:
raw = value
default:
return errors.NewInternalf(ErrCodeUnmarshalJSONColumn, "cannot decode %T as a JSON column", src)
}
decoded := JSONValue{}
if err := sonic.Unmarshal(raw, &decoded); err != nil {
return errors.WrapInternalf(err, ErrCodeUnmarshalJSONColumn, "failed to unmarshal JSON column")
}
*v = decoded
return nil
}

View File

@@ -18,7 +18,7 @@ import (
// - Use `scope.` prefix to explicitly indicate and enforce scope context. Example
// - `scope.name`
// - `scope.version`
// - `scope.my.custom.attribute` resolves to the `my.custom.attribute` scope attribute
// - `scope.my.custom.attribute` and `scope.attribute.my.custom.attribute` resolve to same attribute
//
// - Use `attribute.` to explicitly indicate and enforce attribute context. Example
// - `attribute.http.method`
@@ -190,7 +190,7 @@ func (FieldContext) Enum() []any {
FieldContextSpan,
FieldContextTrace,
FieldContextResource,
FieldContextScope,
// FieldContextScope,
FieldContextAttribute,
// FieldContextEvent,
FieldContextBody,

View File

@@ -294,17 +294,6 @@ func TestNormalize(t *testing.T) {
FieldDataType: FieldDataTypeString,
},
},
{
name: "Normalize keeps a prefix that does not match the set context",
input: TelemetryFieldKey{
Name: "scope.name",
FieldContext: FieldContextAttribute,
},
expected: TelemetryFieldKey{
Name: "scope.name",
FieldContext: FieldContextAttribute,
},
},
{
name: "Normalize body field",
input: TelemetryFieldKey{

View File

@@ -999,8 +999,6 @@ def generate_traces_with_corrupt_metadata() -> list[Traces]:
"cloud.provider": "integration",
"cloud.account.id": "000",
"trace_id": "corrupt_data",
"scope_name": "corrupt_data",
"scope.scope.name": "corrupt_data",
},
attributes={
"net.transport": "IP.TCP",
@@ -1009,10 +1007,7 @@ def generate_traces_with_corrupt_metadata() -> list[Traces]:
"http.request.method": "POST",
"http.response.status_code": "200",
"timestamp": "corrupt_data",
"version": "1.0.0",
"scope.scope.version": "1.0.0",
},
scope={"name": "io.signoz.http.server", "version": "2.0.0"},
),
Traces(
timestamp=now - timedelta(seconds=3.5),
@@ -1032,24 +1027,12 @@ def generate_traces_with_corrupt_metadata() -> list[Traces]:
"cloud.provider": "integration",
"cloud.account.id": "000",
"timestamp": "corrupt_data",
"scope.attributes.name": "corrupt_data",
},
attributes={
"db.name": "integration",
"db.operation": "SELECT",
"db.statement": "SELECT * FROM integration",
"trace_d": "corrupt_data",
"scope.attributes.version": "corrupt_data",
},
scope={
"name": "io.opentelemetry.contrib.http",
"version": "1.0.0",
"attributes": {
"telemetry.sdk.language": "cpp",
"name": "not-the-real-name",
"version": "not-the-real-version",
"attributes": "literally-a-key-named-attributes",
},
},
),
Traces(
@@ -1070,15 +1053,12 @@ def generate_traces_with_corrupt_metadata() -> list[Traces]:
"cloud.provider": "integration",
"cloud.account.id": "000",
"duration_nano": "corrupt_data",
"scope.scope.attributes.version": "corrupt_data",
},
attributes={
"http.request.method": "PATCH",
"http.status_code": "404",
"id": "1",
"scope.scope.version": "corrupt_data",
},
scope={"name": "io.signoz.http.client", "version": "2.0.0"},
),
Traces(
timestamp=now - timedelta(seconds=1),
@@ -1097,7 +1077,6 @@ def generate_traces_with_corrupt_metadata() -> list[Traces]:
"host.name": "linux-001",
"cloud.provider": "integration",
"cloud.account.id": "001",
"scope.scope.version": "corrupt_data",
},
attributes={
"message.type": "SENT",
@@ -1105,10 +1084,7 @@ def generate_traces_with_corrupt_metadata() -> list[Traces]:
"messaging.message.id": "001",
"duration_nano": "corrupt_data",
"id": 1,
"scope": "corrupt_data",
"scope.attributes.name": "corrupt_data",
},
scope={"name": "io.signoz.messaging", "version": "3.0.0"},
),
]

View File

@@ -302,7 +302,6 @@ class Traces(ABC):
db_operation: str
has_error: bool
is_remote: str
scope_json: dict[str, Any]
resource: list[TracesResource]
tag_attributes: list[TracesTagAttributes]
@@ -328,7 +327,6 @@ class Traces(ABC):
links: list[TracesLink] = [],
trace_state: str = "",
flags: np.uint32 = 0,
scope: dict[str, Any] = {},
resource_write_mode: Literal["legacy_only", "dual_write"] = "dual_write",
) -> None:
if timestamp is None:
@@ -410,33 +408,6 @@ class Traces(ABC):
# Calculate resource fingerprint
self.resource_fingerprint = LogsOrTracesFingerprint(self.resources_string).calculate()
# Process scope mirroring the InstrumentationScope on the OTLP span.
scope_name = scope.get("name", "")
scope_version = scope.get("version", "")
scope_string = {k: str(v) for k, v in scope.get("attributes", {}).items()}
self.scope_json = {
"name": scope_name,
"version": scope_version,
"attributes": scope_string,
}
scope_keys = {"scope.name": scope_name, "scope.version": scope_version}
scope_keys.update(scope_string)
for k, v in scope_keys.items():
if v == "":
continue
self.tag_attributes.append(
TracesTagAttributes(
timestamp=timestamp,
tag_key=k,
tag_type="scope",
tag_data_type="string",
string_value=v,
number_value=None,
)
)
self.attribute_keys.append(TracesResourceOrAttributeKeys(name=k, datatype="string", tag_type="scope"))
# Process attributes by type and populate custom fields
self.attribute_string = {}
self.attributes_number = {}
@@ -688,7 +659,6 @@ class Traces(ABC):
self.has_error,
self.is_remote,
self.resource_json,
self.scope_json,
],
dtype=object,
)
@@ -719,7 +689,6 @@ class Traces(ABC):
attributes=data.get("attributes", {}),
trace_state=data.get("trace_state", ""),
flags=data.get("flags", 0),
scope=data.get("scope", {}),
)
@classmethod
@@ -859,7 +828,6 @@ def insert_traces_to_clickhouse(conn, traces: list[Traces]) -> None:
"has_error",
"is_remote",
"resource",
"scope",
],
data=[trace.np_arr() for trace in traces],
)

View File

@@ -1240,13 +1240,6 @@ def test_traces_list_span_scope(
lambda x: {"duration_nano": int(x[1].duration_nano), "span_id": x[1].span_id, "timestamp": format_timestamp(x[1].timestamp), "trace_id": x[1].trace_id},
id="select_attribute_duration_order_intrinsic",
),
# Case 9: filter on the intrinsic scope.version. Only x[1] should match.
pytest.param(
BuilderQuery(signal="traces", name="A", select_fields=[TelemetryFieldKey("timestamp")], filter_expression="scope.version = '1.0.0'", limit=1),
HTTPStatus.OK,
lambda x: {"span_id": x[1].span_id, "timestamp": format_timestamp(x[1].timestamp), "trace_id": x[1].trace_id},
id="filter_scope_version",
),
],
)
def test_traces_list_with_corrupt_data(
@@ -1290,168 +1283,6 @@ def test_traces_list_with_corrupt_data(
assert get_rows(response)[0]["data"] == expected(traces)
@pytest.mark.parametrize(
"filter_expression,expected_indices",
[
# Intrinsic scope.name / scope.version resolve to the JSON sub-columns.
pytest.param("scope.name = 'io.signoz.payment'", [1], id="intrinsic_scope_name"),
pytest.param("scope.version = '2.3.1'", [0], id="intrinsic_scope_version"),
# A scope attribute resolves against the scope JSON column's attributes.
pytest.param("scope.telemetry.sdk.language = 'python'", [1], id="scope_attribute"),
# A scope attribute whose own name carries a `scope.` prefix. `scope.prefixed`
# normalizes to {prefixed, scope} and must still resolve to the attribute.
pytest.param("scope.prefixed = 'prefixed-val'", [0], id="scope_prefixed_attribute"),
# `env.tier` is a span attribute on span 0 and a scope attribute on
# span 1. Unprefixed -> no explicit context, so it is checked in every
# applicable context (attribute OR scope) and both spans match.
pytest.param("env.tier = 'gold'", [0, 1], id="bare_cross_context"),
# The explicit `scope.` prefix forces scope context only, so span 0's
# span attribute is ignored — only span 1 matches.
pytest.param("scope.env.tier = 'gold'", [1], id="scope_prefixed_cross_context"),
# `scope.name` names both homes it can resolve to: the declared scope.name field
# (span 0) and a same-named `name` scope attribute (span 1), the same way any
# other name colliding across contexts unions. `scope.attribute.name` addresses
# the attribute alone.
pytest.param("scope.name = 'io.signoz.checkout'", [0, 1], id="scope_name_unions_attribute"),
# The `scope.name` spelling is also a real stored key: span 2 carries a span
# attribute literally named `scope.name`, so it matches too.
pytest.param("scope.name = 'attr-scope-name'", [2], id="scope_name_matches_stored_spelling"),
# The explicit `scope.attribute.` prefix addresses the scope attribute alone, without
# the declared path. Span 1 has a `name` scope attribute = 'io.signoz.checkout'.
pytest.param("scope.attribute.name = 'io.signoz.checkout'", [1], id="scope_attribute_name"),
# `version` as a scope attribute: no span carries one (span 1's 4.5.6 is the declared
# scope.version, not a scope attribute), so this matches nothing.
pytest.param("scope.attribute.version = '4.5.6'", [], id="scope_attribute_version_none"),
# An unprefixed `name` is checked in every applicable context: the span `name`
# column (span 2) and a `name` scope attribute (span 1). It does not reach the
# declared scope.name field (span 0), which only the `scope.` prefix addresses.
pytest.param("name = 'io.signoz.checkout'", [1, 2], id="bare_name_unions_scope_attribute"),
# A value that no resolvable key holds (scope.name/scope.version field,
# a `name`/`version` scope attribute, or a same-named attribute/resource)
# returns nothing.
pytest.param("scope.version = 'corrupt_data'", [], id="scope_version_no_match"),
pytest.param("scope.name = 'corrupt_data'", [], id="scope_name_no_match"),
],
)
def test_traces_list_with_scope_filter(
signoz: types.SigNoz,
create_user_admin: None, # pylint: disable=unused-argument
get_token: Callable[[str, str], str],
insert_traces: Callable[[list[Traces]], None],
filter_expression: str,
expected_indices: list[int],
) -> None:
"""
Setup three spans with different scope key resolution:
- x[0]: scope.name/version 'io.signoz.checkout'/'2.3.1'; span attribute
env.tier='gold'.
- x[1]: scope.name/version 'io.signoz.payment'/'4.5.6'; scope attributes
telemetry.sdk.language='python', env.tier='gold', and a `name` scope
attribute colliding with x[0]'s scope.name value.
- x[2]: span name 'io.signoz.checkout' (colliding with x[0]'s scope.name
value) and a span attribute literally named `scope.name`.
Tests:
- Filtering on scope.name / scope.version / a scope attribute.
- An unprefixed key is resolved across contexts (scope checked alongside
attribute / intrinsic), while a `scope.`-prefixed key is scope-only.
- `scope.name`/`scope.version` name every home they resolve to: the declared JSON
sub-column and a same-named `name`/`version` scope attribute. The explicit
`scope.attribute.` prefix addresses the attribute alone.
- a bare `name` reaches the span `name` column and a `name` scope attribute, but
never the declared scope.name field.
"""
now = datetime.now(tz=UTC).replace(microsecond=0)
trace_id = TraceIdGenerator.trace_id()
span_ids = [TraceIdGenerator.span_id() for _ in range(3)]
traces = [
Traces(
timestamp=now - timedelta(seconds=4),
duration=timedelta(seconds=2),
trace_id=trace_id,
span_id=span_ids[0],
parent_span_id="",
name="GET /checkout",
kind=TracesKind.SPAN_KIND_SERVER,
status_code=TracesStatusCode.STATUS_CODE_OK,
resources={"service.name": "checkout"},
attributes={"http.request.method": "GET", "env.tier": "gold"},
scope={
"name": "io.signoz.checkout",
"version": "2.3.1",
# a scope attribute whose own name carries a `scope.` prefix
"attributes": {"telemetry.sdk.language": "go", "scope.prefixed": "prefixed-val"},
},
),
Traces(
timestamp=now - timedelta(seconds=2),
duration=timedelta(seconds=1),
trace_id=trace_id,
span_id=span_ids[1],
parent_span_id="",
name="POST /pay",
kind=TracesKind.SPAN_KIND_SERVER,
status_code=TracesStatusCode.STATUS_CODE_OK,
resources={"service.name": "payment"},
attributes={"http.request.method": "POST"},
# env.tier is a scope attribute here (cross-context with span 0);
# `name` is a scope attribute colliding with span 0's scope.name.
scope={
"name": "io.signoz.payment",
"version": "4.5.6",
"attributes": {
"telemetry.sdk.language": "python",
"env.tier": "gold",
"name": "io.signoz.checkout",
},
},
),
Traces(
timestamp=now - timedelta(seconds=1),
duration=timedelta(seconds=1),
trace_id=trace_id,
span_id=span_ids[2],
parent_span_id="",
# span name collides with span 0's scope.name value
name="io.signoz.checkout",
kind=TracesKind.SPAN_KIND_SERVER,
status_code=TracesStatusCode.STATUS_CODE_OK,
resources={"service.name": "probe"},
# a span attribute named `scope.name`
attributes={"scope.name": "attr-scope-name"},
scope={"name": "span-gamma", "version": "9.9.9"},
),
]
insert_traces(traces)
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
start_ms = int((now - timedelta(minutes=1)).timestamp() * 1000)
end_ms = int((now + timedelta(seconds=1)).timestamp() * 1000)
response = make_query_request(
signoz,
token,
start_ms=start_ms,
end_ms=end_ms,
request_type=RequestType.RAW,
queries=[
BuilderQuery(
signal="traces",
name="A",
select_fields=[TelemetryFieldKey("timestamp")],
filter_expression=filter_expression,
limit=10,
).to_dict()
],
)
assert response.status_code == HTTPStatus.OK, response.text
got_span_ids = {row["data"]["span_id"] for row in get_rows(response)}
expected_span_ids = {traces[i].span_id for i in expected_indices}
assert got_span_ids == expected_span_ids
@pytest.mark.parametrize("surface", ["filter", "select", "order"])
def test_traces_list_unknown_span_context_synthesizes(
signoz: types.SigNoz,