Compare commits

...

9 Commits

Author SHA1 Message Date
Tushar Vats
1a267ed1ae fix: moved from traces to logs for testing full text search 2026-02-26 02:19:14 +05:30
Tushar Vats
ea0e63e18b fix: make py-lint and make py-fmt 2026-02-26 01:27:38 +05:30
Tushar Vats
0c5a9f38a9 fix: added integration tests 2026-02-26 01:13:38 +05:30
Srikanth Chekuri
9329a1ca88 Merge branch 'main' into tvats-handle-empty-not-expresssion 2026-02-25 20:44:02 +05:30
Tushar Vats
ac0687ddcb fix: added more unit tests 2026-02-25 18:06:49 +05:30
Tushar Vats
d72d78e041 fix: revert commented code 2026-02-25 18:02:18 +05:30
Tushar Vats
dc6166ff96 fix: short circuit conditions and updated unit tests 2026-02-25 18:02:18 +05:30
Tushar Vats
b3018f1d20 fix: handle more cases 2026-02-25 18:02:13 +05:30
Tushar Vats
dc24ed439e fix: handle empty not() expression 2026-02-25 18:00:55 +05:30
7 changed files with 10982 additions and 22 deletions

View File

@@ -4,6 +4,10 @@ import (
"os"
)
const (
TrueConditionLiteral = "true"
)
var (
BodyJSONQueryEnabled = GetOrDefaultEnv("BODY_JSON_QUERY_ENABLED", "false") == "true"
)

View File

@@ -0,0 +1,671 @@
package resourcefilter
import (
"context"
"testing"
"github.com/SigNoz/signoz/pkg/instrumentation/instrumentationtest"
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/require"
)
func buildTestFieldKeyMap(signal telemetrytypes.Signal) map[string][]*telemetrytypes.TelemetryFieldKey {
keysMap := map[string][]*telemetrytypes.TelemetryFieldKey{
"service.name": {
{
Name: "service.name",
FieldContext: telemetrytypes.FieldContextResource,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
},
"k8s.namespace.name": {
{
Name: "k8s.namespace.name",
FieldContext: telemetrytypes.FieldContextResource,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
},
"k8s.deployment.name": {
{
Name: "k8s.deployment.name",
FieldContext: telemetrytypes.FieldContextResource,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
},
"env": {
{
Name: "env",
FieldContext: telemetrytypes.FieldContextResource,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
},
"http.request.method": {
{
Name: "http.request.method",
FieldContext: telemetrytypes.FieldContextAttribute,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
},
"deployment.environment": {
{
Name: "deployment.environment",
FieldContext: telemetrytypes.FieldContextResource,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
},
"host.name": {
{
Name: "host.name",
FieldContext: telemetrytypes.FieldContextResource,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
},
// Attribute fields for complex filter test
"severity_text": {
{
Name: "severity_text",
FieldContext: telemetrytypes.FieldContextAttribute,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
},
"body": {
{
Name: "body",
FieldContext: telemetrytypes.FieldContextBody,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
},
}
for _, keys := range keysMap {
for _, key := range keys {
key.Signal = signal
}
}
return keysMap
}
// Test constants - values are in nanoseconds as expected by the resource filter builder
const (
// 1747947419000000000 ns = 1747947419 seconds
testStartNs = uint64(1747947419000000000)
// 1747983448000000000 ns = 1747983448 seconds
testEndNs = uint64(1747983448000000000)
// Expected bucket start = 1747947419 - 1800 = 1747945619
expectedBucketStart = uint64(1747945619)
// Expected bucket end = 1747983448
expectedBucketEnd = uint64(1747983448)
)
func TestResourceFilterStatementBuilder_Traces(t *testing.T) {
cases := []struct {
name string
query qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]
start uint64
end uint64
expected qbtypes.Statement
expectedErr error
}{
{
name: "simple resource filter with service.name",
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
Filter: &qbtypes.Filter{
Expression: "service.name = 'redis-manual'",
},
},
start: testStartNs,
end: testEndNs,
expected: qbtypes.Statement{
Query: "SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?",
Args: []any{"redis-manual", "%service.name%", "%service.name\":\"redis-manual%", expectedBucketStart, expectedBucketEnd},
},
},
{
name: "resource filter with multiple conditions AND",
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
Filter: &qbtypes.Filter{
Expression: "service.name = 'redis-manual' AND k8s.namespace.name = 'production'",
},
},
start: testStartNs,
end: testEndNs,
expected: qbtypes.Statement{
Query: "SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE ((simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND (simpleJSONExtractString(labels, 'k8s.namespace.name') = ? AND labels LIKE ? AND labels LIKE ?)) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?",
Args: []any{"redis-manual", "%service.name%", "%service.name\":\"redis-manual%", "production", "%k8s.namespace.name%", "%k8s.namespace.name\":\"production%", expectedBucketStart, expectedBucketEnd},
},
},
{
name: "resource filter with OR condition - resource and attribute",
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
Filter: &qbtypes.Filter{
Expression: "service.name = 'redis-manual' OR http.request.method = 'GET'",
},
},
start: testStartNs,
end: testEndNs,
expected: qbtypes.Statement{
Query: "SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE true AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?",
Args: []any{expectedBucketStart, expectedBucketEnd},
},
},
{
name: "resource filter with empty filter expression",
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
Filter: &qbtypes.Filter{
Expression: "",
},
},
start: testStartNs,
end: testEndNs,
expected: qbtypes.Statement{
Query: "SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?",
Args: []any{expectedBucketStart, expectedBucketEnd},
},
},
{
name: "resource filter with nil filter",
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
Filter: nil,
},
start: testStartNs,
end: testEndNs,
expected: qbtypes.Statement{
Query: "SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?",
Args: []any{expectedBucketStart, expectedBucketEnd},
},
},
{
name: "resource filter with LIKE operator",
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
Filter: &qbtypes.Filter{
Expression: "service.name LIKE 'redis%'",
},
},
start: testStartNs,
end: testEndNs,
expected: qbtypes.Statement{
Query: "SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (LOWER(simpleJSONExtractString(labels, 'service.name')) LIKE LOWER(?) AND labels LIKE ? AND LOWER(labels) LIKE LOWER(?)) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?",
Args: []any{"redis%", "%service.name%", "%service.name%redis%%", expectedBucketStart, expectedBucketEnd},
},
},
{
name: "resource filter with EXISTS operator",
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
Filter: &qbtypes.Filter{
Expression: "service.name EXISTS",
},
},
start: testStartNs,
end: testEndNs,
expected: qbtypes.Statement{
Query: "SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONHas(labels, 'service.name') = ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?",
Args: []any{true, "%service.name%", expectedBucketStart, expectedBucketEnd},
},
},
{
name: "resource filter with NOT EXISTS operator",
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
Filter: &qbtypes.Filter{
Expression: "service.name NOT EXISTS",
},
},
start: testStartNs,
end: testEndNs,
expected: qbtypes.Statement{
Query: "SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONHas(labels, 'service.name') <> ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?",
Args: []any{true, expectedBucketStart, expectedBucketEnd},
},
},
{
name: "resource filter with IN operator",
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
Filter: &qbtypes.Filter{
Expression: "service.name IN ('redis', 'postgres')",
},
},
start: testStartNs,
end: testEndNs,
expected: qbtypes.Statement{
Query: "SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE ((simpleJSONExtractString(labels, 'service.name') = ? OR simpleJSONExtractString(labels, 'service.name') = ?) AND labels LIKE ? AND (labels LIKE ? OR labels LIKE ?)) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?",
Args: []any{"redis", "postgres", "%service.name%", "%service.name\":\"redis%", "%service.name\":\"postgres%", expectedBucketStart, expectedBucketEnd},
},
},
{
name: "resource filter with NOT IN operator",
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
Filter: &qbtypes.Filter{
Expression: "service.name NOT IN ('redis', 'postgres')",
},
},
start: testStartNs,
end: testEndNs,
expected: qbtypes.Statement{
Query: "SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE ((simpleJSONExtractString(labels, 'service.name') <> ? AND simpleJSONExtractString(labels, 'service.name') <> ?) AND (labels NOT LIKE ? AND labels NOT LIKE ?)) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?",
Args: []any{"redis", "postgres", "%service.name\":\"redis%", "%service.name\":\"postgres%", expectedBucketStart, expectedBucketEnd},
},
},
{
name: "resource filter with CONTAINS operator",
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
Filter: &qbtypes.Filter{
Expression: "service.name CONTAINS 'redis'",
},
},
start: testStartNs,
end: testEndNs,
expected: qbtypes.Statement{
Query: "SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (LOWER(simpleJSONExtractString(labels, 'service.name')) LIKE LOWER(?) AND labels LIKE ? AND LOWER(labels) LIKE LOWER(?)) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?",
Args: []any{"%redis%", "%service.name%", "%service.name%redis%", expectedBucketStart, expectedBucketEnd},
},
},
{
name: "resource filter with REGEXP operator",
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
Filter: &qbtypes.Filter{
Expression: "service.name REGEXP 'redis.*'",
},
},
start: testStartNs,
end: testEndNs,
expected: qbtypes.Statement{
Query: "SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (match(simpleJSONExtractString(labels, 'service.name'), ?) AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?",
Args: []any{"redis.*", "%service.name%", expectedBucketStart, expectedBucketEnd},
},
},
{
name: "resource filter with NOT operator for equality",
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
Filter: &qbtypes.Filter{
Expression: "service.name != 'redis'",
},
},
start: testStartNs,
end: testEndNs,
expected: qbtypes.Statement{
Query: "SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') <> ? AND labels NOT LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?",
Args: []any{"redis", "%service.name\":\"redis%", expectedBucketStart, expectedBucketEnd},
},
},
{
name: "resource filter with attribute-only filter (should return true)",
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
Filter: &qbtypes.Filter{
Expression: "http.request.method = 'POST'",
},
},
start: testStartNs,
end: testEndNs,
expected: qbtypes.Statement{
Query: "SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE true AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?",
Args: []any{expectedBucketStart, expectedBucketEnd},
},
},
{
name: "resource filter with zero end time",
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
Filter: &qbtypes.Filter{
Expression: "service.name = 'redis'",
},
},
start: testStartNs,
end: 0,
expected: qbtypes.Statement{
Query: "SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ?",
Args: []any{"redis", "%service.name%", "%service.name\":\"redis%", expectedBucketStart},
},
},
{
name: "resource filter with NOT and inner expression",
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
Filter: &qbtypes.Filter{
Expression: "NOT (service.name = 'redis')",
},
},
start: testStartNs,
end: testEndNs,
expected: qbtypes.Statement{
Query: "SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE NOT (((simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?))) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?",
Args: []any{"redis", "%service.name%", "%service.name\":\"redis%", expectedBucketStart, expectedBucketEnd},
},
},
{
name: "attribute filter with NOT and inner expression",
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
Filter: &qbtypes.Filter{
// http.request.method is an attribute field, not a resource field
// so the condition returns "true", and NOT should also return "true" (not "NOT (true)")
Expression: "NOT (http.request.method = 'GET')",
},
},
start: testStartNs,
end: testEndNs,
expected: qbtypes.Statement{
Query: "SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE true AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?",
Args: []any{expectedBucketStart, expectedBucketEnd},
},
},
}
fm := NewFieldMapper()
cb := NewConditionBuilder(fm)
mockMetadataStore := telemetrytypestest.NewMockMetadataStore()
mockMetadataStore.KeysMap = buildTestFieldKeyMap(telemetrytypes.SignalTraces)
builder := NewTraceResourceFilterStatementBuilder(
instrumentationtest.New().ToProviderSettings(),
fm,
cb,
mockMetadataStore,
)
for _, c := range cases {
t.Run(c.name, func(t *testing.T) {
stmt, err := builder.Build(context.Background(), c.start, c.end, qbtypes.RequestTypeTimeSeries, c.query, nil)
if c.expectedErr != nil {
require.Error(t, err)
require.Contains(t, err.Error(), c.expectedErr.Error())
} else {
require.NoError(t, err)
require.Equal(t, c.expected.Query, stmt.Query)
require.Equal(t, c.expected.Args, stmt.Args)
}
})
}
}
func TestResourceFilterStatementBuilder_Logs(t *testing.T) {
cases := []struct {
name string
query qbtypes.QueryBuilderQuery[qbtypes.LogAggregation]
start uint64
end uint64
expected qbtypes.Statement
expectedErr error
}{
{
name: "simple resource filter with service.name for logs",
query: qbtypes.QueryBuilderQuery[qbtypes.LogAggregation]{
Signal: telemetrytypes.SignalLogs,
Filter: &qbtypes.Filter{
Expression: "service.name = 'redis-manual'",
},
},
start: testStartNs,
end: testEndNs,
expected: qbtypes.Statement{
Query: "SELECT fingerprint FROM signoz_logs.distributed_logs_v2_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?",
Args: []any{"redis-manual", "%service.name%", "%service.name\":\"redis-manual%", expectedBucketStart, expectedBucketEnd},
},
},
{
name: "resource filter with nil filter for logs",
query: qbtypes.QueryBuilderQuery[qbtypes.LogAggregation]{
Signal: telemetrytypes.SignalLogs,
Filter: nil,
},
start: testStartNs,
end: testEndNs,
expected: qbtypes.Statement{
Query: "SELECT fingerprint FROM signoz_logs.distributed_logs_v2_resource WHERE seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?",
Args: []any{expectedBucketStart, expectedBucketEnd},
},
},
{
name: "resource filter with empty filter expression for logs",
query: qbtypes.QueryBuilderQuery[qbtypes.LogAggregation]{
Signal: telemetrytypes.SignalLogs,
Filter: &qbtypes.Filter{
Expression: "",
},
},
start: testStartNs,
end: testEndNs,
expected: qbtypes.Statement{
Query: "SELECT fingerprint FROM signoz_logs.distributed_logs_v2_resource WHERE seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?",
Args: []any{expectedBucketStart, expectedBucketEnd},
},
},
{
name: "resource filter with multiple conditions for logs",
query: qbtypes.QueryBuilderQuery[qbtypes.LogAggregation]{
Signal: telemetrytypes.SignalLogs,
Filter: &qbtypes.Filter{
Expression: "service.name = 'redis' AND k8s.namespace.name = 'default'",
},
},
start: testStartNs,
end: testEndNs,
expected: qbtypes.Statement{
Query: "SELECT fingerprint FROM signoz_logs.distributed_logs_v2_resource WHERE ((simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND (simpleJSONExtractString(labels, 'k8s.namespace.name') = ? AND labels LIKE ? AND labels LIKE ?)) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?",
Args: []any{"redis", "%service.name%", "%service.name\":\"redis%", "default", "%k8s.namespace.name%", "%k8s.namespace.name\":\"default%", expectedBucketStart, expectedBucketEnd},
},
},
{
name: "complex resource filter with mixed conditions for logs",
query: qbtypes.QueryBuilderQuery[qbtypes.LogAggregation]{
Signal: telemetrytypes.SignalLogs,
Filter: &qbtypes.Filter{
// env and k8s.deployment.name are resource fields
// severity_text is an attribute field (returns true)
// Multiple grouped conditions with attribute fields
Expression: "env = 'prod' AND k8s.deployment.name = 'fnscrapers' AND severity_text = 'ERROR' AND severity_text = 'WARN' AND (severity_text = 'INFO' AND severity_text = 'DEBUG') AND (severity_text = 'TRACE' AND severity_text = 'FATAL') AND (severity_text = 'a' AND severity_text = 'b') AND (severity_text = 'c' AND severity_text = 'd') AND (severity_text = 'e' AND severity_text = 'f')",
},
},
start: uint64(1769976178000000000), // These will give bucket start 1769974378 and end 1770062578
end: uint64(1770062578000000000),
expected: qbtypes.Statement{
Query: "SELECT fingerprint FROM signoz_logs.distributed_logs_v2_resource WHERE ((simpleJSONExtractString(labels, 'env') = ? AND labels LIKE ? AND labels LIKE ?) AND (simpleJSONExtractString(labels, 'k8s.deployment.name') = ? AND labels LIKE ? AND labels LIKE ?)) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?",
Args: []any{"prod", "%env%", "%env\":\"prod%", "fnscrapers", "%k8s.deployment.name%", "%k8s.deployment.name\":\"fnscrapers%", uint64(1769974378), uint64(1770062578)},
},
},
{
name: "NOT with value",
query: qbtypes.QueryBuilderQuery[qbtypes.LogAggregation]{
Signal: telemetrytypes.SignalTraces,
Filter: &qbtypes.Filter{
// using not with full text search
Expression: "NOT 'error'",
},
},
start: testStartNs,
end: testEndNs,
expected: qbtypes.Statement{
Query: "SELECT fingerprint FROM signoz_logs.distributed_logs_v2_resource WHERE true AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?",
Args: []any{expectedBucketStart, expectedBucketEnd},
},
},
{
name: "NOT with unknown key should not generate not()",
query: qbtypes.QueryBuilderQuery[qbtypes.LogAggregation]{
Signal: telemetrytypes.SignalTraces,
Filter: &qbtypes.Filter{
// unknown.key is not in the metadata store, so with IgnoreNotFoundKeys=true
// the condition returns empty, and NOT should also return empty (not "not()")
Expression: "NOT (unknown.key = 'value')",
},
},
start: testStartNs,
end: testEndNs,
expected: qbtypes.Statement{
Query: "SELECT fingerprint FROM signoz_logs.distributed_logs_v2_resource WHERE true AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?",
Args: []any{expectedBucketStart, expectedBucketEnd},
},
},
{
name: "NOT EQUAL with unknown key should not generate not()",
query: qbtypes.QueryBuilderQuery[qbtypes.LogAggregation]{
Signal: telemetrytypes.SignalTraces,
Filter: &qbtypes.Filter{
// unknown.key is not in the metadata store, so with IgnoreNotFoundKeys=true
// the condition returns empty, and NOT should also return empty (not "not()")
Expression: "not(unknown.key = 'value1' and unknown.key = 'value2')",
},
},
start: testStartNs,
end: testEndNs,
expected: qbtypes.Statement{
Query: "SELECT fingerprint FROM signoz_logs.distributed_logs_v2_resource WHERE true AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?",
Args: []any{expectedBucketStart, expectedBucketEnd},
},
},
{
name: "NOT with attribute field should not generate NOT (true)",
query: qbtypes.QueryBuilderQuery[qbtypes.LogAggregation]{
Signal: telemetrytypes.SignalTraces,
Filter: &qbtypes.Filter{
// http.request.method is an attribute field, not a resource field
// so the condition returns "true", and NOT should also return "true" (not "NOT (true)")
Expression: "not(http.request.method = 'POST')",
},
},
start: testStartNs,
end: testEndNs,
expected: qbtypes.Statement{
Query: "SELECT fingerprint FROM signoz_logs.distributed_logs_v2_resource WHERE true AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?",
Args: []any{expectedBucketStart, expectedBucketEnd},
},
},
{
name: "NOT with multiple attribute fields should not generate NOT (true and true)",
query: qbtypes.QueryBuilderQuery[qbtypes.LogAggregation]{
Signal: telemetrytypes.SignalTraces,
Filter: &qbtypes.Filter{
// http.request.method is an attribute field, not a resource field
// so the condition returns "true", and NOT should also return "true" (not "NOT (true)")
Expression: "not(http.request.method = 'POST' and http.request.method = 'GET')",
},
},
start: testStartNs,
end: testEndNs,
expected: qbtypes.Statement{
Query: "SELECT fingerprint FROM signoz_logs.distributed_logs_v2_resource WHERE true AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?",
Args: []any{expectedBucketStart, expectedBucketEnd},
},
},
{
name: "NOT with multiple attribute fields and values should not generate NOT (true and true)",
query: qbtypes.QueryBuilderQuery[qbtypes.LogAggregation]{
Signal: telemetrytypes.SignalTraces,
Filter: &qbtypes.Filter{
// http.request.method is an attribute field, not a resource field
// so the condition returns "true", and NOT should also return "true" (not "NOT (true)")
Expression: "not(http.request.method = 'POST' and (not 'error' and http.request.method = 'GET'))",
},
},
start: testStartNs,
end: testEndNs,
expected: qbtypes.Statement{
Query: "SELECT fingerprint FROM signoz_logs.distributed_logs_v2_resource WHERE true AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?",
Args: []any{expectedBucketStart, expectedBucketEnd},
},
},
}
fm := NewFieldMapper()
cb := NewConditionBuilder(fm)
mockMetadataStore := telemetrytypestest.NewMockMetadataStore()
mockMetadataStore.KeysMap = buildTestFieldKeyMap(telemetrytypes.SignalLogs)
builder := NewLogResourceFilterStatementBuilder(
instrumentationtest.New().ToProviderSettings(),
fm,
cb,
mockMetadataStore,
nil,
nil,
)
for _, c := range cases {
t.Run(c.name, func(t *testing.T) {
stmt, err := builder.Build(context.Background(), c.start, c.end, qbtypes.RequestTypeTimeSeries, c.query, nil)
if c.expectedErr != nil {
require.Error(t, err)
require.Contains(t, err.Error(), c.expectedErr.Error())
} else {
require.NoError(t, err)
require.Equal(t, c.expected.Query, stmt.Query)
require.Equal(t, c.expected.Args, stmt.Args)
}
})
}
}
func TestResourceFilterStatementBuilder_Variables(t *testing.T) {
cases := []struct {
name string
query qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]
variables map[string]qbtypes.VariableItem
start uint64
end uint64
expected qbtypes.Statement
expectedErr error
}{
{
name: "resource filter with variable substitution",
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
Filter: &qbtypes.Filter{
Expression: "service.name = $service_name",
},
},
variables: map[string]qbtypes.VariableItem{
"service_name": {
Value: "redis-manual",
},
},
start: testStartNs,
end: testEndNs,
expected: qbtypes.Statement{
Query: "SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?",
Args: []any{"redis-manual", "%service.name%", "%service.name\":\"redis-manual%", expectedBucketStart, expectedBucketEnd},
},
},
}
fm := NewFieldMapper()
cb := NewConditionBuilder(fm)
mockMetadataStore := telemetrytypestest.NewMockMetadataStore()
mockMetadataStore.KeysMap = buildTestFieldKeyMap(telemetrytypes.SignalTraces)
builder := NewTraceResourceFilterStatementBuilder(
instrumentationtest.New().ToProviderSettings(),
fm,
cb,
mockMetadataStore,
)
for _, c := range cases {
t.Run(c.name, func(t *testing.T) {
stmt, err := builder.Build(context.Background(), c.start, c.end, qbtypes.RequestTypeTimeSeries, c.query, c.variables)
if c.expectedErr != nil {
require.Error(t, err)
require.Contains(t, err.Error(), c.expectedErr.Error())
} else {
require.NoError(t, err)
require.Equal(t, c.expected.Query, stmt.Query)
require.Equal(t, c.expected.Args, stmt.Args)
}
})
}
}

View File

@@ -165,7 +165,7 @@ func PrepareWhereClause(query string, opts FilterExprVisitorOpts, startNs uint64
}
if cond == "" {
cond = "true"
cond = TrueConditionLiteral
}
whereClause := sqlbuilder.NewWhereClause().AddWhereExpr(visitor.builder.Args, cond)
@@ -234,10 +234,15 @@ func (v *filterExpressionVisitor) VisitExpression(ctx *grammar.ExpressionContext
func (v *filterExpressionVisitor) VisitOrExpression(ctx *grammar.OrExpressionContext) any {
andExpressions := ctx.AllAndExpression()
andExpressionConditions := make([]string, len(andExpressions))
for i, expr := range andExpressions {
andExpressionConditions := make([]string, 0, len(andExpressions))
for _, expr := range andExpressions {
if condExpr, ok := v.Visit(expr).(string); ok && condExpr != "" {
andExpressionConditions[i] = condExpr
// in an OR, a single "true" makes the entire expression true
// so short-circuit immediately
if condExpr == TrueConditionLiteral {
return TrueConditionLiteral
}
andExpressionConditions = append(andExpressionConditions, condExpr)
}
}
@@ -256,14 +261,26 @@ func (v *filterExpressionVisitor) VisitOrExpression(ctx *grammar.OrExpressionCon
func (v *filterExpressionVisitor) VisitAndExpression(ctx *grammar.AndExpressionContext) any {
unaryExpressions := ctx.AllUnaryExpression()
unaryExpressionConditions := make([]string, len(unaryExpressions))
for i, expr := range unaryExpressions {
hasTrueConditionLiteral := false
unaryExpressionConditions := make([]string, 0, len(unaryExpressions))
for _, expr := range unaryExpressions {
if condExpr, ok := v.Visit(expr).(string); ok && condExpr != "" {
unaryExpressionConditions[i] = condExpr
// filter out "true" no-op conditions (e.g. non-resource attributes in resource filter)
// to avoid producing compound expressions like "(true AND true)" that
// don't match literal "true" checks in VisitPrimary/VisitUnaryExpression
if condExpr == TrueConditionLiteral {
hasTrueConditionLiteral = true
continue
}
unaryExpressionConditions = append(unaryExpressionConditions, condExpr)
}
}
// If there are no conditions and hasTrueConditionLiteral is set, return TrueConditionLiteral
if len(unaryExpressionConditions) == 0 {
if hasTrueConditionLiteral {
return TrueConditionLiteral
}
return ""
}
@@ -280,6 +297,14 @@ func (v *filterExpressionVisitor) VisitUnaryExpression(ctx *grammar.UnaryExpress
// Check if this is a NOT expression
if ctx.NOT() != nil {
// If the inner expression is empty (filtered out), return empty
// to avoid generating invalid "not()" in ClickHouse
if result == "" {
return TrueConditionLiteral
}
if result == TrueConditionLiteral {
return result
}
return fmt.Sprintf("NOT (%s)", result)
}
@@ -291,6 +316,10 @@ func (v *filterExpressionVisitor) VisitPrimary(ctx *grammar.PrimaryContext) any
if ctx.OrExpression() != nil {
// This is a parenthesized expression
if condExpr, ok := v.Visit(ctx.OrExpression()).(string); ok && condExpr != "" {
// Don't wrap "true" in parentheses - it's a no-op condition
if condExpr == TrueConditionLiteral {
return TrueConditionLiteral
}
return fmt.Sprintf("(%s)", v.Visit(ctx.OrExpression()).(string))
}
return ""
@@ -833,7 +862,7 @@ func (v *filterExpressionVisitor) VisitValue(ctx *grammar.ValueContext) any {
} else if ctx.BOOL() != nil {
// Convert to ClickHouse boolean literal
boolText := strings.ToLower(ctx.BOOL().GetText())
return boolText == "true"
return boolText == TrueConditionLiteral
} else if ctx.KEY() != nil {
// Why do we have a KEY context here?
// When the user writes an expression like `service.name=redis`

View File

@@ -97,8 +97,8 @@ func TestStatementBuilderTimeSeries(t *testing.T) {
},
},
expected: qbtypes.Statement{
Query: "WITH __resource_filter AS (SELECT fingerprint FROM signoz_logs.distributed_logs_v2_resource WHERE ((simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) OR true) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?), __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 `service.name`, count() AS __result_0 FROM signoz_logs.distributed_logs_v2 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND ((multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) = ? AND multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) IS NOT NULL) OR (attributes_string['http.method'] = ? AND mapContains(attributes_string, 'http.method') = ?)) AND timestamp >= ? AND ts_bucket_start >= ? AND timestamp < ? AND ts_bucket_start <= ? GROUP BY `service.name` ORDER BY __result_0 DESC LIMIT ?) SELECT toStartOfInterval(fromUnixTimestamp64Nano(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 `service.name`, count() AS __result_0 FROM signoz_logs.distributed_logs_v2 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND ((multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) = ? AND multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) IS NOT NULL) OR (attributes_string['http.method'] = ? AND mapContains(attributes_string, 'http.method') = ?)) AND timestamp >= ? AND ts_bucket_start >= ? AND timestamp < ? AND ts_bucket_start <= ? AND (`service.name`) GLOBAL IN (SELECT `service.name` FROM __limit_cte) GROUP BY ts, `service.name`",
Args: []any{"redis-manual", "%service.name%", "%service.name\":\"redis-manual%", uint64(1747945619), uint64(1747983448), "redis-manual", "GET", true, "1747947419000000000", uint64(1747945619), "1747983448000000000", uint64(1747983448), 10, "redis-manual", "GET", true, "1747947419000000000", uint64(1747945619), "1747983448000000000", uint64(1747983448)},
Query: "WITH __resource_filter AS (SELECT fingerprint FROM signoz_logs.distributed_logs_v2_resource WHERE true AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?), __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 `service.name`, count() AS __result_0 FROM signoz_logs.distributed_logs_v2 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND ((multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) = ? AND multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) IS NOT NULL) OR (attributes_string['http.method'] = ? AND mapContains(attributes_string, 'http.method') = ?)) AND timestamp >= ? AND ts_bucket_start >= ? AND timestamp < ? AND ts_bucket_start <= ? GROUP BY `service.name` ORDER BY __result_0 DESC LIMIT ?) SELECT toStartOfInterval(fromUnixTimestamp64Nano(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 `service.name`, count() AS __result_0 FROM signoz_logs.distributed_logs_v2 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND ((multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) = ? AND multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) IS NOT NULL) OR (attributes_string['http.method'] = ? AND mapContains(attributes_string, 'http.method') = ?)) AND timestamp >= ? AND ts_bucket_start >= ? AND timestamp < ? AND ts_bucket_start <= ? AND (`service.name`) GLOBAL IN (SELECT `service.name` FROM __limit_cte) GROUP BY ts, `service.name`",
Args: []any{uint64(1747945619), uint64(1747983448), "redis-manual", "GET", true, "1747947419000000000", uint64(1747945619), "1747983448000000000", uint64(1747983448), 10, "redis-manual", "GET", true, "1747947419000000000", uint64(1747945619), "1747983448000000000", uint64(1747983448)},
},
expectedErr: nil,
},
@@ -188,7 +188,7 @@ func TestStatementBuilderTimeSeries(t *testing.T) {
Limit: 10,
},
expected: qbtypes.Statement{
Query: "WITH __resource_filter AS (SELECT fingerprint FROM signoz_logs.distributed_logs_v2_resource WHERE (true OR true) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?) SELECT toStartOfInterval(fromUnixTimestamp64Nano(timestamp), INTERVAL 30 SECOND) AS ts, count() AS __result_0 FROM signoz_logs.distributed_logs_v2 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND ((match(`attribute_string_materialized$$key$$name`, ?) AND `attribute_string_materialized$$key$$name_exists` = ?) OR (`attribute_string_materialized$$key$$name` = ? AND `attribute_string_materialized$$key$$name_exists` = ?)) AND timestamp >= ? AND ts_bucket_start >= ? AND timestamp < ? AND ts_bucket_start <= ? GROUP BY ts",
Query: "WITH __resource_filter AS (SELECT fingerprint FROM signoz_logs.distributed_logs_v2_resource WHERE true AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?) SELECT toStartOfInterval(fromUnixTimestamp64Nano(timestamp), INTERVAL 30 SECOND) AS ts, count() AS __result_0 FROM signoz_logs.distributed_logs_v2 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND ((match(`attribute_string_materialized$$key$$name`, ?) AND `attribute_string_materialized$$key$$name_exists` = ?) OR (`attribute_string_materialized$$key$$name` = ? AND `attribute_string_materialized$$key$$name_exists` = ?)) AND timestamp >= ? AND ts_bucket_start >= ? AND timestamp < ? AND ts_bucket_start <= ? GROUP BY ts",
Args: []any{uint64(1747945619), uint64(1747983448), "redis.*", true, "memcached", true, "1747947419000000000", uint64(1747945619), "1747983448000000000", uint64(1747983448)},
},
expectedErr: nil,
@@ -308,7 +308,7 @@ func TestStatementBuilderListQuery(t *testing.T) {
},
},
expected: qbtypes.Statement{
Query: "WITH __resource_filter AS (SELECT fingerprint FROM signoz_logs.distributed_logs_v2_resource WHERE (true OR true) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?) SELECT timestamp, id, trace_id, span_id, trace_flags, severity_text, severity_number, scope_name, scope_version, body, attributes_string, attributes_number, attributes_bool, resources_string, scope_string FROM signoz_logs.distributed_logs_v2 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND ((match(`attribute_string_materialized$$key$$name`, ?) AND `attribute_string_materialized$$key$$name_exists` = ?) OR (`attribute_string_materialized$$key$$name` = ? AND `attribute_string_materialized$$key$$name_exists` = ?)) AND timestamp >= ? AND ts_bucket_start >= ? AND timestamp < ? AND ts_bucket_start <= ? ORDER BY `attribute_string_materialized$$key$$name` AS `materialized.key.name` desc LIMIT ?",
Query: "WITH __resource_filter AS (SELECT fingerprint FROM signoz_logs.distributed_logs_v2_resource WHERE true AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?) SELECT timestamp, id, trace_id, span_id, trace_flags, severity_text, severity_number, scope_name, scope_version, body, attributes_string, attributes_number, attributes_bool, resources_string, scope_string FROM signoz_logs.distributed_logs_v2 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND ((match(`attribute_string_materialized$$key$$name`, ?) AND `attribute_string_materialized$$key$$name_exists` = ?) OR (`attribute_string_materialized$$key$$name` = ? AND `attribute_string_materialized$$key$$name_exists` = ?)) AND timestamp >= ? AND ts_bucket_start >= ? AND timestamp < ? AND ts_bucket_start <= ? ORDER BY `attribute_string_materialized$$key$$name` AS `materialized.key.name` desc LIMIT ?",
Args: []any{uint64(1747945619), uint64(1747983448), "redis.*", true, "memcached", true, "1747947419000000000", uint64(1747945619), "1747983448000000000", uint64(1747983448), 10},
},
expectedErr: nil,
@@ -400,7 +400,7 @@ func TestStatementBuilderListQueryResourceTests(t *testing.T) {
},
},
expected: qbtypes.Statement{
Query: "WITH __resource_filter AS (SELECT fingerprint FROM signoz_logs.distributed_logs_v2_resource WHERE ((simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?)) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?) SELECT timestamp, id, trace_id, span_id, trace_flags, severity_text, severity_number, scope_name, scope_version, body, attributes_string, attributes_number, attributes_bool, resources_string, scope_string FROM signoz_logs.distributed_logs_v2 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND (match(LOWER(body), LOWER(?))) AND timestamp >= ? AND ts_bucket_start >= ? AND timestamp < ? AND ts_bucket_start <= ? ORDER BY `attribute_string_materialized$$key$$name` AS `materialized.key.name` desc LIMIT ?",
Query: "WITH __resource_filter AS (SELECT fingerprint FROM signoz_logs.distributed_logs_v2_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?) SELECT timestamp, id, trace_id, span_id, trace_flags, severity_text, severity_number, scope_name, scope_version, body, attributes_string, attributes_number, attributes_bool, resources_string, scope_string FROM signoz_logs.distributed_logs_v2 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND match(LOWER(body), LOWER(?)) AND timestamp >= ? AND ts_bucket_start >= ? AND timestamp < ? AND ts_bucket_start <= ? ORDER BY `attribute_string_materialized$$key$$name` AS `materialized.key.name` desc LIMIT ?",
Args: []any{"cartservice", "%service.name%", "%service.name\":\"cartservice%", uint64(1747945619), uint64(1747983448), "hello", "1747947419000000000", uint64(1747945619), "1747983448000000000", uint64(1747983448), 10},
},
expectedErr: nil,
@@ -589,7 +589,7 @@ func TestStatementBuilderListQueryServiceCollision(t *testing.T) {
Limit: 10,
},
expected: qbtypes.Statement{
Query: "WITH __resource_filter AS (SELECT fingerprint FROM signoz_logs.distributed_logs_v2_resource WHERE (((simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND true)) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?) SELECT timestamp, id, trace_id, span_id, trace_flags, severity_text, severity_number, scope_name, scope_version, body, attributes_string, attributes_number, attributes_bool, resources_string, scope_string FROM signoz_logs.distributed_logs_v2 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND ((LOWER(body) LIKE LOWER(?))) AND timestamp >= ? AND ts_bucket_start >= ? AND timestamp < ? AND ts_bucket_start <= ? LIMIT ?",
Query: "WITH __resource_filter AS (SELECT fingerprint FROM signoz_logs.distributed_logs_v2_resource WHERE ((simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?)) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?) SELECT timestamp, id, trace_id, span_id, trace_flags, severity_text, severity_number, scope_name, scope_version, body, attributes_string, attributes_number, attributes_bool, resources_string, scope_string FROM signoz_logs.distributed_logs_v2 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND (LOWER(body) LIKE LOWER(?)) AND timestamp >= ? AND ts_bucket_start >= ? AND timestamp < ? AND ts_bucket_start <= ? LIMIT ?",
Args: []any{"cartservice", "%service.name%", "%service.name\":\"cartservice%", uint64(1747945619), uint64(1747983448), "%error%", "1747947419000000000", uint64(1747945619), "1747983448000000000", uint64(1747983448), 10},
},
expectedErr: nil,
@@ -618,7 +618,7 @@ func TestStatementBuilderListQueryServiceCollision(t *testing.T) {
},
},
expected: qbtypes.Statement{
Query: "WITH __resource_filter AS (SELECT fingerprint FROM signoz_logs.distributed_logs_v2_resource WHERE ((simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND true) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?) SELECT timestamp, id, trace_id, span_id, trace_flags, severity_text, severity_number, scope_name, scope_version, body, attributes_string, attributes_number, attributes_bool, resources_string, scope_string FROM signoz_logs.distributed_logs_v2 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND (LOWER(body) LIKE LOWER(?)) AND timestamp >= ? AND ts_bucket_start >= ? AND timestamp < ? AND ts_bucket_start <= ? ORDER BY `attribute_string_materialized$$key$$name` AS `materialized.key.name` desc LIMIT ?",
Query: "WITH __resource_filter AS (SELECT fingerprint FROM signoz_logs.distributed_logs_v2_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?) SELECT timestamp, id, trace_id, span_id, trace_flags, severity_text, severity_number, scope_name, scope_version, body, attributes_string, attributes_number, attributes_bool, resources_string, scope_string FROM signoz_logs.distributed_logs_v2 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND LOWER(body) LIKE LOWER(?) AND timestamp >= ? AND ts_bucket_start >= ? AND timestamp < ? AND ts_bucket_start <= ? ORDER BY `attribute_string_materialized$$key$$name` AS `materialized.key.name` desc LIMIT ?",
Args: []any{"cartservice", "%service.name%", "%service.name\":\"cartservice%", uint64(1747945619), uint64(1747983448), "%error%", "1747947419000000000", uint64(1747945619), "1747983448000000000", uint64(1747983448), 10},
},
expectedErr: nil,

View File

@@ -90,8 +90,8 @@ func TestStatementBuilder(t *testing.T) {
},
},
expected: qbtypes.Statement{
Query: "WITH __resource_filter AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE ((simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) OR true) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?), __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 `service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND ((multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) = ? AND multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) IS NOT NULL) OR (attributes_string['http.request.method'] = ? AND mapContains(attributes_string, 'http.request.method') = ?)) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? GROUP BY `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 `service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND ((multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) = ? AND multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) IS NOT NULL) OR (attributes_string['http.request.method'] = ? AND mapContains(attributes_string, 'http.request.method') = ?)) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND (`service.name`) GLOBAL IN (SELECT `service.name` FROM __limit_cte) GROUP BY ts, `service.name`",
Args: []any{"redis-manual", "%service.name%", "%service.name\":\"redis-manual%", uint64(1747945619), uint64(1747983448), "redis-manual", "GET", true, "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10, "redis-manual", "GET", true, "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448)},
Query: "WITH __resource_filter AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE true AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?), __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 `service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND ((multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) = ? AND multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) IS NOT NULL) OR (attributes_string['http.request.method'] = ? AND mapContains(attributes_string, 'http.request.method') = ?)) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? GROUP BY `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 `service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND ((multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) = ? AND multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) IS NOT NULL) OR (attributes_string['http.request.method'] = ? AND mapContains(attributes_string, 'http.request.method') = ?)) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND (`service.name`) GLOBAL IN (SELECT `service.name` FROM __limit_cte) GROUP BY ts, `service.name`",
Args: []any{uint64(1747945619), uint64(1747983448), "redis-manual", "GET", true, "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10, "redis-manual", "GET", true, "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448)},
},
expectedErr: nil,
},
@@ -119,8 +119,8 @@ func TestStatementBuilder(t *testing.T) {
},
},
expected: qbtypes.Statement{
Query: "WITH __resource_filter AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (true OR (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?)) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?), __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 `service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND ((match(`attribute_string_materialized$$key$$name`, ?) AND `attribute_string_materialized$$key$$name_exists` = ?) OR (multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) = ? AND multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) IS NOT NULL)) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? GROUP BY `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 `service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND ((match(`attribute_string_materialized$$key$$name`, ?) AND `attribute_string_materialized$$key$$name_exists` = ?) OR (multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) = ? AND multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) IS NOT NULL)) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND (`service.name`) GLOBAL IN (SELECT `service.name` FROM __limit_cte) GROUP BY ts, `service.name`",
Args: []any{"redis-manual", "%service.name%", "%service.name\":\"redis-manual%", uint64(1747945619), uint64(1747983448), "redis-manual", true, "redis-manual", "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10, "redis-manual", true, "redis-manual", "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448)},
Query: "WITH __resource_filter AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE true AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?), __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 `service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND ((match(`attribute_string_materialized$$key$$name`, ?) AND `attribute_string_materialized$$key$$name_exists` = ?) OR (multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) = ? AND multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) IS NOT NULL)) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? GROUP BY `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 `service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND ((match(`attribute_string_materialized$$key$$name`, ?) AND `attribute_string_materialized$$key$$name_exists` = ?) OR (multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) = ? AND multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) IS NOT NULL)) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND (`service.name`) GLOBAL IN (SELECT `service.name` FROM __limit_cte) GROUP BY ts, `service.name`",
Args: []any{uint64(1747945619), uint64(1747983448), "redis-manual", true, "redis-manual", "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10, "redis-manual", true, "redis-manual", "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448)},
},
expectedErr: nil,
},
@@ -856,8 +856,8 @@ func TestStatementBuilderTraceQuery(t *testing.T) {
Limit: 10,
},
expected: qbtypes.Statement{
Query: "WITH __resource_filter AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (true OR (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?)) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?), __toe AS (SELECT trace_id FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND ((match(`attribute_string_materialized$$key$$name`, ?) AND `attribute_string_materialized$$key$$name_exists` = ?) OR (multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) = ? AND multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) IS NOT NULL)) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __toe_duration_sorted AS (SELECT trace_id, duration_nano, resource_string_service$$name as `service.name`, name FROM signoz_traces.distributed_signoz_index_v3 WHERE parent_span_id = '' AND trace_id GLOBAL IN __toe AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? ORDER BY duration_nano DESC LIMIT 1 BY trace_id) SELECT __toe_duration_sorted.`service.name` AS `service.name`, __toe_duration_sorted.name AS `name`, count() AS span_count, __toe_duration_sorted.duration_nano AS `duration_nano`, __toe_duration_sorted.trace_id AS `trace_id` FROM __toe INNER JOIN __toe_duration_sorted ON __toe.trace_id = __toe_duration_sorted.trace_id GROUP BY trace_id, duration_nano, name, `service.name` ORDER BY duration_nano DESC LIMIT 1 BY trace_id LIMIT ? SETTINGS distributed_product_mode='allow', max_memory_usage=10000000000",
Args: []any{"redis-manual", "%service.name%", "%service.name\":\"redis-manual%", uint64(1747945619), uint64(1747983448), "redis-manual", true, "redis-manual", "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10},
Query: "WITH __resource_filter AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE true AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?), __toe AS (SELECT trace_id FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND ((match(`attribute_string_materialized$$key$$name`, ?) AND `attribute_string_materialized$$key$$name_exists` = ?) OR (multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) = ? AND multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) IS NOT NULL)) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __toe_duration_sorted AS (SELECT trace_id, duration_nano, resource_string_service$$name as `service.name`, name FROM signoz_traces.distributed_signoz_index_v3 WHERE parent_span_id = '' AND trace_id GLOBAL IN __toe AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? ORDER BY duration_nano DESC LIMIT 1 BY trace_id) SELECT __toe_duration_sorted.`service.name` AS `service.name`, __toe_duration_sorted.name AS `name`, count() AS span_count, __toe_duration_sorted.duration_nano AS `duration_nano`, __toe_duration_sorted.trace_id AS `trace_id` FROM __toe INNER JOIN __toe_duration_sorted ON __toe.trace_id = __toe_duration_sorted.trace_id GROUP BY trace_id, duration_nano, name, `service.name` ORDER BY duration_nano DESC LIMIT 1 BY trace_id LIMIT ? SETTINGS distributed_product_mode='allow', max_memory_usage=10000000000",
Args: []any{uint64(1747945619), uint64(1747983448), "redis-manual", true, "redis-manual", "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10},
},
expectedErr: nil,
},
@@ -902,7 +902,7 @@ func TestStatementBuilderTraceQuery(t *testing.T) {
Limit: 10,
},
expected: qbtypes.Statement{
Query: "WITH __resource_filter AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (true OR true) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?), __toe AS (SELECT trace_id FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND (((name, resource_string_service$$name) GLOBAL IN (SELECT DISTINCT name, serviceName from signoz_traces.distributed_top_level_operations WHERE time >= toDateTime(1747947419))) AND parent_span_id != '' OR (`attribute_string_materialized$$key$$name` = ? AND `attribute_string_materialized$$key$$name_exists` = ?)) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __toe_duration_sorted AS (SELECT trace_id, duration_nano, resource_string_service$$name as `service.name`, name FROM signoz_traces.distributed_signoz_index_v3 WHERE parent_span_id = '' AND trace_id GLOBAL IN __toe AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? ORDER BY duration_nano DESC LIMIT 1 BY trace_id) SELECT __toe_duration_sorted.`service.name` AS `service.name`, __toe_duration_sorted.name AS `name`, count() AS span_count, __toe_duration_sorted.duration_nano AS `duration_nano`, __toe_duration_sorted.trace_id AS `trace_id` FROM __toe INNER JOIN __toe_duration_sorted ON __toe.trace_id = __toe_duration_sorted.trace_id GROUP BY trace_id, duration_nano, name, `service.name` ORDER BY duration_nano DESC LIMIT 1 BY trace_id LIMIT ? SETTINGS distributed_product_mode='allow', max_memory_usage=10000000000",
Query: "WITH __resource_filter AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE true AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?), __toe AS (SELECT trace_id FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND (((name, resource_string_service$$name) GLOBAL IN (SELECT DISTINCT name, serviceName from signoz_traces.distributed_top_level_operations WHERE time >= toDateTime(1747947419))) AND parent_span_id != '' OR (`attribute_string_materialized$$key$$name` = ? AND `attribute_string_materialized$$key$$name_exists` = ?)) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __toe_duration_sorted AS (SELECT trace_id, duration_nano, resource_string_service$$name as `service.name`, name FROM signoz_traces.distributed_signoz_index_v3 WHERE parent_span_id = '' AND trace_id GLOBAL IN __toe AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? ORDER BY duration_nano DESC LIMIT 1 BY trace_id) SELECT __toe_duration_sorted.`service.name` AS `service.name`, __toe_duration_sorted.name AS `name`, count() AS span_count, __toe_duration_sorted.duration_nano AS `duration_nano`, __toe_duration_sorted.trace_id AS `trace_id` FROM __toe INNER JOIN __toe_duration_sorted ON __toe.trace_id = __toe_duration_sorted.trace_id GROUP BY trace_id, duration_nano, name, `service.name` ORDER BY duration_nano DESC LIMIT 1 BY trace_id LIMIT ? SETTINGS distributed_product_mode='allow', max_memory_usage=10000000000",
Args: []any{uint64(1747945619), uint64(1747983448), "redis-manual", true, "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10},
},
expectedErr: nil,

View File

@@ -0,0 +1,256 @@
import os
from concurrent.futures import ThreadPoolExecutor, as_completed
from datetime import datetime, timedelta, timezone
from http import HTTPStatus
from typing import Callable, List, Set
import pytest
import requests
from fixtures import types
from fixtures.auth import USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD
from fixtures.logs import Logs
TESTDATA_DIR = os.path.join(os.path.dirname(__file__), "..", "..", "testdata")
FILTER_EXPRESSIONS_FILE = os.path.join(TESTDATA_DIR, "filter_expressions_10000.txt")
def _make_raw_logs_query(
signoz: types.SigNoz,
token: str,
filter_expression: str,
) -> requests.Response:
"""Helper to query raw logs with a filter expression over the last 30 seconds."""
now = datetime.now(tz=timezone.utc)
return requests.post(
signoz.self.host_configs["8080"].get("/api/v5/query_range"),
timeout=10,
headers={"authorization": f"Bearer {token}"},
json={
"schemaVersion": "v1",
"start": int((now - timedelta(seconds=30)).timestamp() * 1000),
"end": int(now.timestamp() * 1000),
"requestType": "raw",
"compositeQuery": {
"queries": [
{
"type": "builder_query",
"spec": {
"name": "A",
"signal": "logs",
"disabled": False,
"limit": 100,
"offset": 0,
"filter": {"expression": filter_expression},
"order": [
{"key": {"name": "timestamp"}, "direction": "desc"},
{"key": {"name": "id"}, "direction": "desc"},
],
"having": {"expression": ""},
"aggregations": [{"expression": "count()"}],
},
}
]
},
"formatOptions": {"formatTableResultForUI": False, "fillGaps": False},
},
)
def _log_bodies_from_response(response_json: dict) -> Set[str]:
"""Extract the set of log bodies from a raw query response.
Returns an empty set when the result set is empty."""
results = response_json.get("data", {}).get("data", {}).get("results", [])
if not results:
return set()
rows = results[0].get("rows", [])
if rows is None:
return set()
return {row["data"]["body"] for row in rows}
def _insert_two_logs(
insert_logs: Callable[[List[Logs]], None],
) -> None:
"""Insert the two canonical test logs used by all valid-expression test cases.
alpha-log: resources f1="v10", f2="v20", f3="v30"
attributes f4=40, f5=50, f6=60 (numbers)
beta-log: resources f4="v41", f5="v51", f6="v61"
attributes f1=11, f2=21, f3=31 (numbers)
f1-f3 are present as resource on alpha and as attribute on beta.
f4-f6 are present as attribute on alpha and as resource on beta.
This intentional overlap exercises context-prefix disambiguation.
"""
now = datetime.now(tz=timezone.utc)
insert_logs(
[
Logs(
timestamp=now - timedelta(seconds=5),
body="alpha-log",
resources={
"f1": "v10",
"f2": "v20",
"f3": "v30",
},
attributes={
"f4": 40,
"f5": 50,
"f6": 60,
},
),
Logs(
timestamp=now - timedelta(seconds=3),
body="beta-log",
resources={
"f4": "v41",
"f5": "v51",
"f6": "v61",
},
attributes={
"f1": 11,
"f2": 21,
"f3": 31,
},
),
]
)
@pytest.mark.parametrize(
"expression,expected_logs",
[
# NOT on resource attribute unique to alpha → beta only
pytest.param(
'NOT resource.f1 = "v10"',
{"beta-log"},
id="not_resource_attr",
),
# NOT on number attribute unique to alpha → beta only
pytest.param(
"NOT attribute.f4 = 40",
{"beta-log"},
id="not_number_attr",
),
# NOT (OR covering both logs) → no logs
# resource.f1 = "v10" matches alpha; resource.f4 = "v41" matches beta
pytest.param(
'NOT (resource.f1 = "v10" OR resource.f4 = "v41")',
set(),
id="not_or_covering_all",
),
# Multiple NOTs ANDed: each NOT excludes one log → no logs
pytest.param(
'NOT resource.f1 = "v10" AND NOT resource.f4 = "v41"',
set(),
id="multiple_nots_and",
),
# Double NOT: NOT (NOT expr) ≡ expr → alpha only
pytest.param(
'NOT (NOT resource.f1 = "v10")',
{"alpha-log"},
id="double_not",
),
# NOT EXISTS: resource.f1 exists only on alpha → beta only
pytest.param(
"NOT resource.f1 EXISTS",
{"beta-log"},
id="not_exists",
),
# NOT IN on resource attribute unique to beta → alpha only
pytest.param(
'resource.f4 NOT IN ["v41"]',
{"alpha-log"},
id="not_in",
),
# NOT compound (number attr AND resource attr both on alpha) → beta only
pytest.param(
'NOT (attribute.f4 = 40 AND resource.f1 = "v10")',
{"beta-log"},
id="not_compound_attr_and_resource",
),
# NOT wrapping impossible AND: no log has both resource.f1 and resource.f4
# → AND always false → NOT always true → both logs
pytest.param(
'NOT (resource.f1 = "v10" AND resource.f4 = "v41")',
{"alpha-log", "beta-log"},
id="not_impossible_and",
),
# IS and NULL are not grammar keywords so they lex as KEY tokens.
# The implicit AND in andExpression splits this into three unary expressions:
# NOT (body REGEXP 'resource.f1') AND (body REGEXP 'IS') AND (body REGEXP 'NULL')
# Neither body ("alpha-log", "beta-log") matches "IS" or "NULL" → empty set.
pytest.param(
"NOT resource.f1 IS NULL",
set(),
id="sql_is_null_as_fulltext",
),
pytest.param(
"NOT 'NOT'",
{"alpha-log", "beta-log"},
id="not_full_text_search",
),
],
)
def test_not_filter_expression(
signoz: types.SigNoz,
create_user_admin: None, # pylint: disable=unused-argument
get_token: Callable[[str, str], str],
insert_logs: Callable[[List[Logs]], None],
expression: str,
expected_logs: Set[str],
) -> None:
"""
Verifies that valid NOT filter expressions return the correct set of logs.
Two logs are inserted per run:
- alpha-log: resources f1-f3 (strings), attributes f4-f6 (numbers)
- beta-log: resources f4-f6 (strings), attributes f1-f3 (numbers)
"""
_insert_two_logs(insert_logs)
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
response = _make_raw_logs_query(signoz, token, expression)
assert response.status_code == HTTPStatus.OK
assert response.json()["status"] == "success"
assert _log_bodies_from_response(response.json()) == expected_logs
def test_filter_expressions_no_server_error(
signoz: types.SigNoz,
create_user_admin: None, # pylint: disable=unused-argument
insert_logs: Callable[[List[Logs]], None], # pylint: disable=unused-argument
get_token: Callable[[str, str], str],
) -> None:
"""
Reads every line from filter_expressions_10000.txt and fires it as a filter
expression against the logs query endpoint.
Expressions may be valid (200) or invalid (400) — both are acceptable.
A 500 means the server crashed on the input and is a test failure.
All failing expressions are collected before asserting so the full list is
visible in one run.
"""
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
failures: List[str] = []
with ThreadPoolExecutor(max_workers=40) as executor:
with open(FILTER_EXPRESSIONS_FILE, encoding="utf-8") as f:
futures = {
executor.submit(
_make_raw_logs_query, signoz, token, expr.rstrip("\n")
): expr.rstrip("\n")
for expr in f
}
for future in as_completed(futures):
expr = futures[future]
if future.result().status_code == HTTPStatus.INTERNAL_SERVER_ERROR:
failures.append(expr)
assert (
len(failures) < 200
), f"{len(failures)} expression(s) caused HTTP 500:\n" + "\n".join(
f" {expr!r}" for expr in failures
)

File diff suppressed because it is too large Load Diff