fix: escape $ signs in materialised columns (#9667)

This commit is contained in:
Tushar Vats
2025-11-30 02:16:52 +05:30
committed by GitHub
parent 5288022ffd
commit 5d9dc17645
9 changed files with 389 additions and 24 deletions

View File

@@ -66,9 +66,13 @@ func (c *conditionBuilder) conditionFor(
case qbtypes.FilterOperatorNotLike:
return sb.NotILike(tblFieldName, value), nil
case qbtypes.FilterOperatorRegexp:
return fmt.Sprintf(`match(LOWER(%s), LOWER(%s))`, tblFieldName, sb.Var(value)), nil
// Note: Escape $$ to $$$$ to avoid sqlbuilder interpreting materialized $ signs
// Only needed because we are using sprintf instead of sb.Match (not implemented in sqlbuilder)
return fmt.Sprintf(`match(LOWER(%s), LOWER(%s))`, sqlbuilder.Escape(tblFieldName), sb.Var(value)), nil
case qbtypes.FilterOperatorNotRegexp:
return fmt.Sprintf(`NOT match(LOWER(%s), LOWER(%s))`, tblFieldName, sb.Var(value)), nil
// Note: Escape $$ to $$$$ to avoid sqlbuilder interpreting materialized $ signs
// Only needed because we are using sprintf instead of sb.Match (not implemented in sqlbuilder)
return fmt.Sprintf(`NOT match(LOWER(%s), LOWER(%s))`, sqlbuilder.Escape(tblFieldName), sb.Var(value)), nil
}
}
@@ -104,9 +108,13 @@ func (c *conditionBuilder) conditionFor(
return sb.NotILike(tblFieldName, fmt.Sprintf("%%%s%%", value)), nil
case qbtypes.FilterOperatorRegexp:
return fmt.Sprintf(`match(%s, %s)`, tblFieldName, sb.Var(value)), nil
// Note: Escape $$ to $$$$ to avoid sqlbuilder interpreting materialized $ signs
// Only needed because we are using sprintf instead of sb.Match (not implemented in sqlbuilder)
return fmt.Sprintf(`match(%s, %s)`, sqlbuilder.Escape(tblFieldName), sb.Var(value)), nil
case qbtypes.FilterOperatorNotRegexp:
return fmt.Sprintf(`NOT match(%s, %s)`, tblFieldName, sb.Var(value)), nil
// Note: Escape $$ to $$$$ to avoid sqlbuilder interpreting materialized $ signs
// Only needed because we are using sprintf instead of sb.Match (not implemented in sqlbuilder)
return fmt.Sprintf(`NOT match(%s, %s)`, sqlbuilder.Escape(tblFieldName), sb.Var(value)), nil
// between and not between
case qbtypes.FilterOperatorBetween:
values, ok := value.([]any)
@@ -218,8 +226,8 @@ func (c *conditionBuilder) ConditionFor(
operator qbtypes.FilterOperator,
value any,
sb *sqlbuilder.SelectBuilder,
_ uint64,
_ uint64,
_ uint64,
_ uint64,
) (string, error) {
condition, err := c.conditionFor(ctx, key, operator, value, sb)
if err != nil {

View File

@@ -257,6 +257,108 @@ func TestConditionFor(t *testing.T) {
expectedSQL: "WHERE multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) IS NULL",
expectedError: nil,
},
{
name: "Regexp operator - body field",
key: telemetrytypes.TelemetryFieldKey{
Name: "body",
FieldContext: telemetrytypes.FieldContextLog,
},
operator: qbtypes.FilterOperatorRegexp,
value: "error.*failed",
expectedSQL: "match(LOWER(body), LOWER(?))",
expectedArgs: []any{"error.*failed"},
expectedError: nil,
},
{
name: "Not Regexp operator - body field",
key: telemetrytypes.TelemetryFieldKey{
Name: "body",
FieldContext: telemetrytypes.FieldContextLog,
},
operator: qbtypes.FilterOperatorNotRegexp,
value: "debug|trace",
expectedSQL: "NOT match(LOWER(body), LOWER(?))",
expectedArgs: []any{"debug|trace"},
expectedError: nil,
},
{
name: "Regexp operator - string attribute",
key: telemetrytypes.TelemetryFieldKey{
Name: "http.url",
FieldContext: telemetrytypes.FieldContextAttribute,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
operator: qbtypes.FilterOperatorRegexp,
value: "^https://.*\\.example\\.com.*$",
expectedSQL: "(match(attributes_string['http.url'], ?) AND mapContains(attributes_string, 'http.url') = ?)",
expectedArgs: []any{"^https://.*\\.example\\.com.*$", true},
expectedError: nil,
},
{
name: "Not Regexp operator - string attribute",
key: telemetrytypes.TelemetryFieldKey{
Name: "http.url",
FieldContext: telemetrytypes.FieldContextAttribute,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
operator: qbtypes.FilterOperatorNotRegexp,
value: "^http://localhost.*",
expectedSQL: "WHERE NOT match(attributes_string['http.url'], ?)",
expectedArgs: []any{"^http://localhost.*"},
expectedError: nil,
},
{
name: "Regexp operator - resource attribute",
key: telemetrytypes.TelemetryFieldKey{
Name: "service.name",
FieldContext: telemetrytypes.FieldContextResource,
FieldDataType: telemetrytypes.FieldDataTypeString,
Materialized: true,
},
operator: qbtypes.FilterOperatorRegexp,
value: "frontend-.*",
expectedSQL: "(match(multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, `resource_string_service$$name_exists`==true, `resource_string_service$$name`, NULL), ?) AND multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, `resource_string_service$$name_exists`==true, `resource_string_service$$name`, NULL) IS NOT NULL)",
expectedArgs: []any{"frontend-.*"},
expectedError: nil,
},
{
name: "Not Regexp operator - resource attribute",
key: telemetrytypes.TelemetryFieldKey{
Name: "service.name",
FieldContext: telemetrytypes.FieldContextResource,
FieldDataType: telemetrytypes.FieldDataTypeString,
Materialized: true,
},
operator: qbtypes.FilterOperatorNotRegexp,
value: "test-.*",
expectedSQL: "WHERE NOT match(multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, `resource_string_service$$name_exists`==true, `resource_string_service$$name`, NULL), ?)",
expectedArgs: []any{"test-.*"},
expectedError: nil,
},
{
name: "Regexp operator - severity_text",
key: telemetrytypes.TelemetryFieldKey{
Name: "severity_text",
FieldContext: telemetrytypes.FieldContextLog,
},
operator: qbtypes.FilterOperatorRegexp,
value: "ERROR|FATAL|CRITICAL",
expectedSQL: "match(severity_text, ?)",
expectedArgs: []any{"ERROR|FATAL|CRITICAL"},
expectedError: nil,
},
{
name: "Not Regexp operator - severity_text",
key: telemetrytypes.TelemetryFieldKey{
Name: "severity_text",
FieldContext: telemetrytypes.FieldContextLog,
},
operator: qbtypes.FilterOperatorNotRegexp,
value: "DEBUG|TRACE",
expectedSQL: "NOT match(severity_text, ?)",
expectedArgs: []any{"DEBUG|TRACE"},
expectedError: nil,
},
{
name: "Non-existent column",
key: telemetrytypes.TelemetryFieldKey{
@@ -276,7 +378,7 @@ func TestConditionFor(t *testing.T) {
for _, tc := range testCases {
sb := sqlbuilder.NewSelectBuilder()
t.Run(tc.name, func(t *testing.T) {
cond, err := conditionBuilder.ConditionFor(ctx, &tc.key, tc.operator, tc.value, sb, 0, 0)
cond, err := conditionBuilder.ConditionFor(ctx, &tc.key, tc.operator, tc.value, sb, 0, 0)
sb.Where(cond)
if tc.expectedError != nil {
@@ -331,7 +433,7 @@ func TestConditionForMultipleKeys(t *testing.T) {
t.Run(tc.name, func(t *testing.T) {
var err error
for _, key := range tc.keys {
cond, err := conditionBuilder.ConditionFor(ctx, &key, tc.operator, tc.value, sb, 0, 0)
cond, err := conditionBuilder.ConditionFor(ctx, &key, tc.operator, tc.value, sb, 0, 0)
sb.Where(cond)
if err != nil {
t.Fatalf("Error getting condition for key %s: %v", key.Name, err)
@@ -520,6 +622,46 @@ func TestConditionForJSONBodySearch(t *testing.T) {
expectedSQL: `(JSONExtract(JSON_VALUE(body, '$."http"."status_code"'), 'Int64') = ? OR JSONExtract(JSON_VALUE(body, '$."http"."status_code"'), 'Int64') = ? OR JSONExtract(JSON_VALUE(body, '$."http"."status_code"'), 'Int64') = ?)`,
expectedError: nil,
},
{
name: "Regexp operator - json body string",
key: telemetrytypes.TelemetryFieldKey{
Name: "body.http.method",
},
operator: qbtypes.FilterOperatorRegexp,
value: "GET|POST|PUT",
expectedSQL: `match(JSON_VALUE(body, '$."http"."method"'), ?)`,
expectedError: nil,
},
{
name: "Not Regexp operator - json body string",
key: telemetrytypes.TelemetryFieldKey{
Name: "body.http.method",
},
operator: qbtypes.FilterOperatorNotRegexp,
value: "DELETE|PATCH",
expectedSQL: `NOT match(JSON_VALUE(body, '$."http"."method"'), ?)`,
expectedError: nil,
},
{
name: "Regexp operator - json body with dots in path",
key: telemetrytypes.TelemetryFieldKey{
Name: "body.user.email",
},
operator: qbtypes.FilterOperatorRegexp,
value: "^.*@example\\.com$",
expectedSQL: `match(JSON_VALUE(body, '$."user"."email"'), ?)`,
expectedError: nil,
},
{
name: "Not Regexp operator - json body nested path",
key: telemetrytypes.TelemetryFieldKey{
Name: "body.response.headers.content-type",
},
operator: qbtypes.FilterOperatorNotRegexp,
value: "^text/.*",
expectedSQL: `NOT match(JSON_VALUE(body, '$."response"."headers"."content-type"'), ?)`,
expectedError: nil,
},
}
fm := NewFieldMapper()
@@ -528,7 +670,7 @@ func TestConditionForJSONBodySearch(t *testing.T) {
for _, tc := range testCases {
sb := sqlbuilder.NewSelectBuilder()
t.Run(tc.name, func(t *testing.T) {
cond, err := conditionBuilder.ConditionFor(ctx, &tc.key, tc.operator, tc.value, sb, 0, 0)
cond, err := conditionBuilder.ConditionFor(ctx, &tc.key, tc.operator, tc.value, sb, 0, 0)
sb.Where(cond)
if tc.expectedError != nil {

View File

@@ -172,6 +172,28 @@ func TestStatementBuilderTimeSeries(t *testing.T) {
Args: []any{"cartservice", "%service.name%", "%service.name\":\"cartservice%", uint64(1747945619), uint64(1747983448), true, "1747947419000000000", uint64(1747945619), "1747983448000000000", uint64(1747983448), 10, true, "1747947419000000000", uint64(1747945619), "1747983448000000000", uint64(1747983448)},
},
},
{
name: "Time series with materialised column using or with regex operator",
requestType: qbtypes.RequestTypeTimeSeries,
query: qbtypes.QueryBuilderQuery[qbtypes.LogAggregation]{
Signal: telemetrytypes.SignalLogs,
StepInterval: qbtypes.Step{Duration: 30 * time.Second},
Aggregations: []qbtypes.LogAggregation{
{
Expression: "count()",
},
},
Filter: &qbtypes.Filter{
Expression: "materialized.key.name REGEXP 'redis.*' OR materialized.key.name = 'memcached'",
},
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",
Args: []any{uint64(1747945619), uint64(1747983448), "redis.*", true, "memcached", true, "1747947419000000000", uint64(1747945619), "1747983448000000000", uint64(1747983448)},
},
expectedErr: nil,
},
}
fm := NewFieldMapper()
@@ -265,6 +287,34 @@ func TestStatementBuilderListQuery(t *testing.T) {
},
expectedErr: nil,
},
{
name: "list query with mat col using or and regex operator",
requestType: qbtypes.RequestTypeRaw,
query: qbtypes.QueryBuilderQuery[qbtypes.LogAggregation]{
Signal: telemetrytypes.SignalLogs,
Filter: &qbtypes.Filter{
Expression: "materialized.key.name REGEXP 'redis.*' OR materialized.key.name = 'memcached'",
},
Limit: 10,
Order: []qbtypes.OrderBy{
{
Key: qbtypes.OrderByKey{
TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
Name: "materialized.key.name",
FieldContext: telemetrytypes.FieldContextAttribute,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
},
Direction: qbtypes.OrderDirectionDesc,
},
},
},
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 ?",
Args: []any{uint64(1747945619), uint64(1747983448), "redis.*", true, "memcached", true, "1747947419000000000", uint64(1747945619), "1747983448000000000", uint64(1747983448), 10},
},
expectedErr: nil,
},
}
fm := NewFieldMapper()

View File

@@ -74,10 +74,13 @@ func (c *conditionBuilder) conditionFor(
return sb.NotILike(tblFieldName, fmt.Sprintf("%%%s%%", value)), nil
case qbtypes.FilterOperatorRegexp:
return fmt.Sprintf(`match(%s, %s)`, tblFieldName, sb.Var(value)), nil
// Note: Escape $$ to $$$$ to avoid sqlbuilder interpreting materialized $ signs
// Only needed because we are using sprintf instead of sb.Match (not implemented in sqlbuilder)
return fmt.Sprintf(`match(%s, %s)`, sqlbuilder.Escape(tblFieldName), sb.Var(value)), nil
case qbtypes.FilterOperatorNotRegexp:
return fmt.Sprintf(`NOT match(%s, %s)`, tblFieldName, sb.Var(value)), nil
// Note: Escape $$ to $$$$ to avoid sqlbuilder interpreting materialized $ signs
// Only needed because we are using sprintf instead of sb.Match (not implemented in sqlbuilder)
return fmt.Sprintf(`NOT match(%s, %s)`, sqlbuilder.Escape(tblFieldName), sb.Var(value)), nil
// between and not between
case qbtypes.FilterOperatorBetween:
values, ok := value.([]any)
@@ -136,8 +139,8 @@ func (c *conditionBuilder) ConditionFor(
operator qbtypes.FilterOperator,
value any,
sb *sqlbuilder.SelectBuilder,
_ uint64,
_ uint64,
_ uint64,
_ uint64,
) (string, error) {
condition, err := c.conditionFor(ctx, key, operator, value, sb)
if err != nil {

View File

@@ -54,6 +54,39 @@ func TestStatementBuilder(t *testing.T) {
},
expectedErr: nil,
},
{
name: "test_cumulative_rate_sum_with_mat_column",
requestType: qbtypes.RequestTypeTimeSeries,
query: qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation]{
Signal: telemetrytypes.SignalMetrics,
StepInterval: qbtypes.Step{Duration: 30 * time.Second},
Aggregations: []qbtypes.MetricAggregation{
{
MetricName: "signoz_calls_total",
Type: metrictypes.SumType,
Temporality: metrictypes.Cumulative,
TimeAggregation: metrictypes.TimeAggregationRate,
SpaceAggregation: metrictypes.SpaceAggregationSum,
},
},
Filter: &qbtypes.Filter{
Expression: "materialized.key.name REGEXP 'cartservice' OR service.name = 'cartservice'",
},
Limit: 10,
GroupBy: []qbtypes.GroupByKey{
{
TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
Name: "service.name",
},
},
},
},
expected: qbtypes.Statement{
Query: "WITH __temporal_aggregation_cte AS (SELECT ts, `service.name`, If((per_series_value - lagInFrame(per_series_value, 1, 0) OVER rate_window) < 0, per_series_value / (ts - lagInFrame(ts, 1, toDateTime(fromUnixTimestamp64Milli(1747947360000))) OVER rate_window), (per_series_value - lagInFrame(per_series_value, 1, 0) OVER rate_window) / (ts - lagInFrame(ts, 1, toDateTime(fromUnixTimestamp64Milli(1747947360000))) OVER rate_window)) AS per_series_value FROM (SELECT fingerprint, toStartOfInterval(toDateTime(intDiv(unix_milli, 1000)), toIntervalSecond(30)) AS ts, `service.name`, max(value) AS per_series_value FROM signoz_metrics.distributed_samples_v4 AS points INNER JOIN (SELECT fingerprint, JSONExtractString(labels, 'service.name') AS `service.name` FROM signoz_metrics.time_series_v4_6hrs WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli <= ? AND LOWER(temporality) LIKE LOWER(?) AND __normalized = ? AND (match(JSONExtractString(labels, 'materialized.key.name'), ?) OR JSONExtractString(labels, 'service.name') = ?) GROUP BY fingerprint, `service.name`) AS filtered_time_series ON points.fingerprint = filtered_time_series.fingerprint WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli < ? GROUP BY fingerprint, ts, `service.name` ORDER BY fingerprint, ts) WINDOW rate_window AS (PARTITION BY fingerprint ORDER BY fingerprint, ts)), __spatial_aggregation_cte AS (SELECT ts, `service.name`, sum(per_series_value) AS value FROM __temporal_aggregation_cte WHERE isNaN(per_series_value) = ? GROUP BY ts, `service.name`) SELECT * FROM __spatial_aggregation_cte",
Args: []any{"signoz_calls_total", uint64(1747936800000), uint64(1747983420000), "cumulative", false, "cartservice", "cartservice", "signoz_calls_total", uint64(1747947360000), uint64(1747983420000), 0},
},
expectedErr: nil,
},
{
name: "test_delta_rate_sum",
requestType: qbtypes.RequestTypeTimeSeries,
@@ -191,6 +224,13 @@ func TestStatementBuilder(t *testing.T) {
t.Fatalf("failed to load field keys: %v", err)
}
mockMetadataStore.KeysMap = keys
// NOTE: LoadFieldKeysFromJSON doesn't set Materialized field
// for keys, so we have to set it manually here for testing
if _, ok := mockMetadataStore.KeysMap["materialized.key.name"]; ok {
if len(mockMetadataStore.KeysMap["materialized.key.name"]) > 0 {
mockMetadataStore.KeysMap["materialized.key.name"][0].Materialized = true
}
}
statementBuilder := NewMetricQueryStatementBuilder(
instrumentationtest.New().ToProviderSettings(),

View File

@@ -30,5 +30,14 @@
"fieldDataType": "string",
"signal": "metrics"
}
],
"materialized.key.name": [
{
"name": "materialized.key.name",
"fieldContext": "attribute",
"fieldDataType": "string",
"materialized": true,
"signal": "metrics"
}
]
}

View File

@@ -108,10 +108,13 @@ func (c *conditionBuilder) conditionFor(
return sb.NotILike(tblFieldName, fmt.Sprintf("%%%s%%", value)), nil
case qbtypes.FilterOperatorRegexp:
return fmt.Sprintf(`match(%s, %s)`, tblFieldName, sb.Var(value)), nil
// Note: Escape $$ to $$$$ to avoid sqlbuilder interpreting materialized $ signs
// Only needed because we are using sprintf instead of sb.Match (not implemented in sqlbuilder)
return fmt.Sprintf(`match(%s, %s)`, sqlbuilder.Escape(tblFieldName), sb.Var(value)), nil
case qbtypes.FilterOperatorNotRegexp:
return fmt.Sprintf(`NOT match(%s, %s)`, tblFieldName, sb.Var(value)), nil
// Note: Escape $$ to $$$$ to avoid sqlbuilder interpreting materialized $ signs
// Only needed because we are using sprintf instead of sb.Match (not implemented in sqlbuilder)
return fmt.Sprintf(`NOT match(%s, %s)`, sqlbuilder.Escape(tblFieldName), sb.Var(value)), nil
// between and not between
case qbtypes.FilterOperatorBetween:
values, ok := value.([]any)
@@ -223,8 +226,8 @@ func (c *conditionBuilder) ConditionFor(
operator qbtypes.FilterOperator,
value any,
sb *sqlbuilder.SelectBuilder,
startNs uint64,
_ uint64,
startNs uint64,
_ uint64,
) (string, error) {
if c.isSpanScopeField(key.Name) {
return c.buildSpanScopeCondition(key, operator, value, startNs)
@@ -285,11 +288,13 @@ func (c *conditionBuilder) buildSpanScopeCondition(key *telemetrytypes.Telemetry
case SpanSearchScopeEntryPoint:
if startNs > 0 { // only add time filter if it is a valid time, else do not add
startS := int64(startNs / 1_000_000_000)
return fmt.Sprintf("((name, resource_string_service$$$name) GLOBAL IN (SELECT DISTINCT name, serviceName from %s.%s WHERE time >= toDateTime(%d))) AND parent_span_id != ''",
DBName, TopLevelOperationsTableName, startS), nil
// Note: Escape $$ to $$$$ to avoid sqlbuilder interpreting materialized $ signs
return sqlbuilder.Escape(fmt.Sprintf("((name, resource_string_service$$name) GLOBAL IN (SELECT DISTINCT name, serviceName from %s.%s WHERE time >= toDateTime(%d))) AND parent_span_id != ''",
DBName, TopLevelOperationsTableName, startS)), nil
}
return fmt.Sprintf("((name, resource_string_service$$$name) GLOBAL IN (SELECT DISTINCT name, serviceName from %s.%s)) AND parent_span_id != ''",
DBName, TopLevelOperationsTableName), nil
// Note: Escape $$ to $$$$ to avoid sqlbuilder interpreting materialized $ signs
return sqlbuilder.Escape(fmt.Sprintf("((name, resource_string_service$$name) GLOBAL IN (SELECT DISTINCT name, serviceName from %s.%s)) AND parent_span_id != ''",
DBName, TopLevelOperationsTableName)), nil
default:
return "", errors.NewInvalidInputf(errors.CodeInvalidInput, "invalid span search scope: %s", key.Name)
}

View File

@@ -94,6 +94,35 @@ func TestStatementBuilder(t *testing.T) {
},
expectedErr: nil,
},
{
name: "OR with regexp",
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: "materialized.key.name REGEXP 'redis-manual' OR service.name = 'redis-manual'",
},
Limit: 10,
GroupBy: []qbtypes.GroupByKey{
{
TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
Name: "service.name",
},
},
},
},
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)},
},
expectedErr: nil,
},
{
name: "legacy httpRoute in group by",
requestType: qbtypes.RequestTypeTimeSeries,
@@ -537,7 +566,7 @@ func TestStatementBuilderTraceQuery(t *testing.T) {
expectedErr error
}{
{
name: "List query with mat selected fields",
name: "List query with non-mat selected fields",
requestType: qbtypes.RequestTypeTrace,
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
@@ -552,6 +581,38 @@ func TestStatementBuilderTraceQuery(t *testing.T) {
},
expectedErr: nil,
},
{
name: "List query with mat selected fields",
requestType: qbtypes.RequestTypeTrace,
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
Filter: &qbtypes.Filter{
Expression: "materialized.key.name = 'redis-manual'",
},
Limit: 10,
},
expected: qbtypes.Statement{
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 (`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$$name as `service.name`, name FROM signoz_traces.distributed_signoz_index_v3 WHERE parent_span_id = '' AND trace_id GLOBAL IN __toe AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? ORDER BY duration_nano DESC LIMIT 1 BY trace_id) SELECT __toe_duration_sorted.`service.name` AS `service.name`, __toe_duration_sorted.name AS `name`, count() AS span_count, __toe_duration_sorted.duration_nano AS `duration_nano`, __toe_duration_sorted.trace_id AS `trace_id` FROM __toe INNER JOIN __toe_duration_sorted ON __toe.trace_id = __toe_duration_sorted.trace_id GROUP BY trace_id, duration_nano, name, `service.name` ORDER BY duration_nano DESC LIMIT 1 BY trace_id LIMIT ? SETTINGS distributed_product_mode='allow', max_memory_usage=10000000000",
Args: []any{uint64(1747945619), uint64(1747983448), "redis-manual", true, "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10},
},
expectedErr: nil,
},
{
name: "List query with mat selected fields using or and regexp",
requestType: qbtypes.RequestTypeTrace,
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
Filter: &qbtypes.Filter{
Expression: "materialized.key.name REGEXP 'redis-manual' OR service.name = 'redis-manual'",
},
Limit: 10,
},
expected: qbtypes.Statement{
Query: "WITH __resource_filter AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (true OR (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?)) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?), __toe AS (SELECT trace_id FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND ((match(`attribute_string_materialized$$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},
},
expectedErr: nil,
},
{
name: "List query without any filter",
requestType: qbtypes.RequestTypeTrace,
@@ -566,6 +627,38 @@ func TestStatementBuilderTraceQuery(t *testing.T) {
},
expectedErr: nil,
},
{
name: "list query with span scope filter",
requestType: qbtypes.RequestTypeTrace,
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
Filter: &qbtypes.Filter{
Expression: "isentrypoint = true",
},
Limit: 10,
},
expected: qbtypes.Statement{
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$$name) GLOBAL IN (SELECT DISTINCT name, serviceName from signoz_traces.distributed_top_level_operations WHERE time >= toDateTime(1747947419))) AND parent_span_id != '' AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __toe_duration_sorted AS (SELECT trace_id, duration_nano, resource_string_service$$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), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10},
},
expectedErr: nil,
},
{
name: "list query with span scope filter Or mat field",
requestType: qbtypes.RequestTypeTrace,
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
Filter: &qbtypes.Filter{
Expression: "isentrypoint = true or materialized.key.name = 'redis-manual'",
},
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",
Args: []any{uint64(1747945619), uint64(1747983448), "redis-manual", true, "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10},
},
expectedErr: nil,
},
}
fm := NewFieldMapper()

View File

@@ -77,6 +77,21 @@ func buildCompleteFieldKeyMap() map[string][]*telemetrytypes.TelemetryFieldKey {
FieldDataType: telemetrytypes.FieldDataTypeInt64,
},
},
"materialized.key.name": {
{
Name: "materialized.key.name",
FieldContext: telemetrytypes.FieldContextAttribute,
FieldDataType: telemetrytypes.FieldDataTypeString,
Materialized: true,
},
},
"isentrypoint": {
{
Name: "isentrypoint",
FieldContext: telemetrytypes.FieldContextSpan,
FieldDataType: telemetrytypes.FieldDataTypeBool,
},
},
}
for _, keys := range keysMap {
for _, key := range keys {