Compare commits

...

1 Commits

Author SHA1 Message Date
Nikhil Soni
55d90c687a fix(traces-qb): address JSON attribute keys as atomic %2E paths
Span attributes are ingested into the ClickHouse JSON columns with
json_type_escape_dots_in_keys, so a dotted OTel key (e.g. `db.function`) is stored as one
atomic path with its dots escaped to %2E, not split into nested paths. Reads must address the
same escaped path: `attributes.`db.function`` is interpreted by ClickHouse as the nested path
db -> function and returns nothing.

Encode dots to %2E when building JSON sub-column paths for the attribute, resource and scope
contexts (attributes, attributes_promoted, resource, scope), and set
json_type_escape_dots_in_keys on the read connection so a full JSON column serialized to a
document comes back with dotted keys instead of %2E.

Assisted-by: Claude Opus 4.8
2026-09-16 23:26:41 +05:30
14 changed files with 121 additions and 87 deletions

View File

@@ -16,6 +16,15 @@ func Identifier(value string) string {
return quote(value, '`')
}
// JSONKeyIdentifier renders one key of a ClickHouse native JSON path. A dot is the path
// separator there, so a literal dot in an OTel key (e.g. the whole key "db.function") is
// percent-encoded to %2E to keep the key a single atomic path, matching how it is stored under
// json_type_escape_dots_in_keys. Use it only for a key addressed as a JSON sub-column, never for
// a map key or a column name.
func JSONKeyIdentifier(value string) string {
return Identifier(strings.ReplaceAll(value, ".", "%2E"))
}
// LikePattern escapes value so LIKE matches it verbatim; the caller adds the wildcards.
func LikePattern(value string) string {
return likePatternEscaper.Replace(value)

View File

@@ -55,6 +55,27 @@ func TestIdentifier(t *testing.T) {
}
}
func TestJSONKeyIdentifier(t *testing.T) {
testCases := []struct {
name string
input string
expected string
}{
{name: "NoDot", input: "http_status_code", expected: "`http_status_code`"},
{name: "SingleDot", input: "db.function", expected: "`db%2Efunction`"},
{name: "MultipleDots", input: "db.function.arg_count", expected: "`db%2Efunction%2Earg_count`"},
{name: "ResourceKey", input: "service.name", expected: "`service%2Ename`"},
{name: "Backtick", input: "a.`b", expected: "`a%2E\\`b`"},
{name: "Empty", input: "", expected: "``"},
}
for _, testCase := range testCases {
t.Run(testCase.name, func(t *testing.T) {
assert.Equal(t, testCase.expected, JSONKeyIdentifier(testCase.input))
})
}
}
func TestLikePattern(t *testing.T) {
testCases := []struct {
name string

View File

@@ -21,7 +21,7 @@ func buildFieldExpr(fieldKey telemetrytypes.TelemetryFieldKey) (string, error) {
switch fieldKey.FieldContext {
case telemetrytypes.FieldContextResource:
// String cast required — Variant/Dynamic is rejected by GROUP BY.
return sqlbuilder.Escape(fmt.Sprintf("resource.%s::String", clickhousesql.Identifier(fieldKey.Name))), nil
return sqlbuilder.Escape(fmt.Sprintf("resource.%s::String", clickhousesql.JSONKeyIdentifier(fieldKey.Name))), nil
}
return "", errors.NewInvalidInputf(errors.CodeInvalidInput, "unsupported field context: %v", fieldKey.FieldContext)
}

View File

@@ -67,7 +67,7 @@ func TestGetMinimalSpans(t *testing.T) {
}
func TestGetSpanCountByField(t *testing.T) {
expectedSQL := "SELECT resource.`service.name`::String AS field_value, count(DISTINCT span_id) AS count FROM signoz_traces.distributed_signoz_index_v3 WHERE trace_id = ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND notEmpty(resource.`service.name`::String) GROUP BY field_value"
expectedSQL := "SELECT resource.`service%2Ename`::String AS field_value, count(DISTINCT span_id) AS count FROM signoz_traces.distributed_signoz_index_v3 WHERE trace_id = ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND notEmpty(resource.`service%2Ename`::String) GROUP BY field_value"
tests := []struct {
name string
@@ -117,7 +117,7 @@ func TestGetFlamegraphSpans(t *testing.T) {
func TestGetSpanDurationByField(t *testing.T) {
expectedSQL := "WITH all_spans AS (SELECT DISTINCT ON (span_id) resource.`service.name`::String AS field_value, toUnixTimestamp64Nano(timestamp) AS start_ns, start_ns + duration_nano AS end_ns FROM signoz_traces.distributed_signoz_index_v3 WHERE trace_id = ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND notEmpty(field_value) ORDER BY timestamp ASC, name ASC), effective_start AS (SELECT field_value, end_ns, greatest(start_ns, ifNull(max(end_ns) OVER (PARTITION BY field_value ORDER BY start_ns ROWS BETWEEN UNBOUNDED PRECEDING AND 1 PRECEDING), toUInt64(0))) AS effective_start_ns FROM all_spans) SELECT field_value, sum(toUInt64(greatest(end_ns - effective_start_ns, 0))) AS total_ns FROM effective_start GROUP BY field_value"
expectedSQL := "WITH all_spans AS (SELECT DISTINCT ON (span_id) resource.`service%2Ename`::String AS field_value, toUnixTimestamp64Nano(timestamp) AS start_ns, start_ns + duration_nano AS end_ns FROM signoz_traces.distributed_signoz_index_v3 WHERE trace_id = ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND notEmpty(field_value) ORDER BY timestamp ASC, name ASC), effective_start AS (SELECT field_value, end_ns, greatest(start_ns, ifNull(max(end_ns) OVER (PARTITION BY field_value ORDER BY start_ns ROWS BETWEEN UNBOUNDED PRECEDING AND 1 PRECEDING), toUInt64(0))) AS effective_start_ns FROM all_spans) SELECT field_value, sum(toUInt64(greatest(end_ns - effective_start_ns, 0))) AS total_ns FROM effective_start GROUP BY field_value"
tests := []struct {
name string

View File

@@ -101,20 +101,20 @@ func TestGroupByAttributeHomeAcrossRollout(t *testing.T) {
startMs: uint64(rel - 2*day),
endMs: uint64(rel - day),
wantContains: []string{"mapContains(attributes_string, 'http.route')", "attributes_string['http.route']"},
wantNotContains: []string{"attributes.`http.route`"},
wantNotContains: []string{"attributes.`http%2Eroute`"},
},
{
name: "StraddlingRollout_JSONThenLegacyFallback",
startMs: uint64(rel - day),
endMs: uint64(rel + day),
wantContains: []string{"attributes.`http.route` IS NOT NULL", "attributes.`http.route`::String", "attributes_string['http.route']"},
wantContains: []string{"attributes.`http%2Eroute` IS NOT NULL", "attributes.`http%2Eroute`::String", "attributes_string['http.route']"},
wantNotContains: nil,
},
{
name: "AfterRollout_ReadsJSONOnly",
startMs: uint64(rel + day),
endMs: uint64(rel + 2*day),
wantContains: []string{"attributes.`http.route`::String"},
wantContains: []string{"attributes.`http%2Eroute`::String"},
wantNotContains: []string{"attributes_string"},
},
}

View File

@@ -71,7 +71,7 @@ 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 ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), __limit_cte AS (SELECT toString(multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `__GROUP_BY_KEY_0_service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? GROUP BY `__GROUP_BY_KEY_0_service.name` ORDER BY __result_0 DESC LIMIT ?) SELECT toStartOfInterval(timestamp, INTERVAL 30 SECOND) AS ts, toString(multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `__GROUP_BY_KEY_0_service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND (`__GROUP_BY_KEY_0_service.name`) GLOBAL IN (SELECT `__GROUP_BY_KEY_0_service.name` FROM __limit_cte) GROUP BY ts, `__GROUP_BY_KEY_0_service.name`",
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 ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), __limit_cte AS (SELECT toString(multiIf(resource.`service%2Ename` IS NOT NULL, resource.`service%2Ename`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `__GROUP_BY_KEY_0_service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? GROUP BY `__GROUP_BY_KEY_0_service.name` ORDER BY __result_0 DESC LIMIT ?) SELECT toStartOfInterval(timestamp, INTERVAL 30 SECOND) AS ts, toString(multiIf(resource.`service%2Ename` IS NOT NULL, resource.`service%2Ename`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `__GROUP_BY_KEY_0_service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND (`__GROUP_BY_KEY_0_service.name`) GLOBAL IN (SELECT `__GROUP_BY_KEY_0_service.name` FROM __limit_cte) GROUP BY ts, `__GROUP_BY_KEY_0_service.name`",
Args: []any{"redis-manual", "%service.name%", "%service.name\":\"redis-manual%", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10, "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448)},
},
expectedErr: nil,
@@ -100,7 +100,7 @@ func TestStatementBuilder(t *testing.T) {
},
},
expected: qbtypes.Statement{
Query: "WITH __limit_cte AS (SELECT toString(multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `__GROUP_BY_KEY_0_service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE (multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], 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 `__GROUP_BY_KEY_0_service.name` ORDER BY __result_0 DESC LIMIT ?) SELECT toStartOfInterval(timestamp, INTERVAL 30 SECOND) AS ts, toString(multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `__GROUP_BY_KEY_0_service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE (multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], 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 (`__GROUP_BY_KEY_0_service.name`) GLOBAL IN (SELECT `__GROUP_BY_KEY_0_service.name` FROM __limit_cte) GROUP BY ts, `__GROUP_BY_KEY_0_service.name`",
Query: "WITH __limit_cte AS (SELECT toString(multiIf(resource.`service%2Ename` IS NOT NULL, resource.`service%2Ename`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `__GROUP_BY_KEY_0_service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE (multiIf(resource.`service%2Ename` IS NOT NULL, resource.`service%2Ename`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], 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 `__GROUP_BY_KEY_0_service.name` ORDER BY __result_0 DESC LIMIT ?) SELECT toStartOfInterval(timestamp, INTERVAL 30 SECOND) AS ts, toString(multiIf(resource.`service%2Ename` IS NOT NULL, resource.`service%2Ename`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `__GROUP_BY_KEY_0_service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE (multiIf(resource.`service%2Ename` IS NOT NULL, resource.`service%2Ename`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], 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 (`__GROUP_BY_KEY_0_service.name`) GLOBAL IN (SELECT `__GROUP_BY_KEY_0_service.name` FROM __limit_cte) GROUP BY ts, `__GROUP_BY_KEY_0_service.name`",
Args: []any{"redis-manual", "GET", "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10, "redis-manual", "GET", "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448)},
},
expectedErr: nil,
@@ -129,7 +129,7 @@ func TestStatementBuilder(t *testing.T) {
},
},
expected: qbtypes.Statement{
Query: "WITH __limit_cte AS (SELECT toString(multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `__GROUP_BY_KEY_0_service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE ((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 timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? GROUP BY `__GROUP_BY_KEY_0_service.name` ORDER BY __result_0 DESC LIMIT ?) SELECT toStartOfInterval(timestamp, INTERVAL 30 SECOND) AS ts, toString(multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `__GROUP_BY_KEY_0_service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE ((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 timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND (`__GROUP_BY_KEY_0_service.name`) GLOBAL IN (SELECT `__GROUP_BY_KEY_0_service.name` FROM __limit_cte) GROUP BY ts, `__GROUP_BY_KEY_0_service.name`",
Query: "WITH __limit_cte AS (SELECT toString(multiIf(resource.`service%2Ename` IS NOT NULL, resource.`service%2Ename`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `__GROUP_BY_KEY_0_service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE ((match(`attribute_string_materialized$$key$$name`, ?) AND `attribute_string_materialized$$key$$name_exists`) OR multiIf(resource.`service%2Ename` IS NOT NULL, resource.`service%2Ename`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) = ?) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? GROUP BY `__GROUP_BY_KEY_0_service.name` ORDER BY __result_0 DESC LIMIT ?) SELECT toStartOfInterval(timestamp, INTERVAL 30 SECOND) AS ts, toString(multiIf(resource.`service%2Ename` IS NOT NULL, resource.`service%2Ename`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `__GROUP_BY_KEY_0_service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE ((match(`attribute_string_materialized$$key$$name`, ?) AND `attribute_string_materialized$$key$$name_exists`) OR multiIf(resource.`service%2Ename` IS NOT NULL, resource.`service%2Ename`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) = ?) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND (`__GROUP_BY_KEY_0_service.name`) GLOBAL IN (SELECT `__GROUP_BY_KEY_0_service.name` FROM __limit_cte) GROUP BY ts, `__GROUP_BY_KEY_0_service.name`",
Args: []any{"redis-manual", "redis-manual", "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10, "redis-manual", "redis-manual", "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448)},
},
expectedErr: nil,
@@ -239,7 +239,7 @@ 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 ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), __limit_cte AS (SELECT toString(multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `__GROUP_BY_KEY_0_service.name`, sum(multiIf(mapContains(attributes_number, 'metric.max_count'), toFloat64(attributes_number['metric.max_count']), NULL)) AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? GROUP BY `__GROUP_BY_KEY_0_service.name` ORDER BY __result_0 desc LIMIT ?) SELECT toStartOfInterval(timestamp, INTERVAL 30 SECOND) AS ts, toString(multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `__GROUP_BY_KEY_0_service.name`, sum(multiIf(mapContains(attributes_number, 'metric.max_count'), toFloat64(attributes_number['metric.max_count']), NULL)) AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND (`__GROUP_BY_KEY_0_service.name`) GLOBAL IN (SELECT `__GROUP_BY_KEY_0_service.name` FROM __limit_cte) GROUP BY ts, `__GROUP_BY_KEY_0_service.name` ORDER BY ts desc",
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 ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), __limit_cte AS (SELECT toString(multiIf(resource.`service%2Ename` IS NOT NULL, resource.`service%2Ename`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `__GROUP_BY_KEY_0_service.name`, sum(multiIf(mapContains(attributes_number, 'metric.max_count'), toFloat64(attributes_number['metric.max_count']), NULL)) AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? GROUP BY `__GROUP_BY_KEY_0_service.name` ORDER BY __result_0 desc LIMIT ?) SELECT toStartOfInterval(timestamp, INTERVAL 30 SECOND) AS ts, toString(multiIf(resource.`service%2Ename` IS NOT NULL, resource.`service%2Ename`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `__GROUP_BY_KEY_0_service.name`, sum(multiIf(mapContains(attributes_number, 'metric.max_count'), toFloat64(attributes_number['metric.max_count']), NULL)) AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND (`__GROUP_BY_KEY_0_service.name`) GLOBAL IN (SELECT `__GROUP_BY_KEY_0_service.name` FROM __limit_cte) GROUP BY ts, `__GROUP_BY_KEY_0_service.name` ORDER BY ts desc",
Args: []any{"redis-manual", "%service.name%", "%service.name\":\"redis-manual%", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10, "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448)},
},
expectedErr: nil,
@@ -268,7 +268,7 @@ 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 ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), __limit_cte AS (SELECT toString(multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `__GROUP_BY_KEY_0_service.name`, sum(multiIf(`attribute_number_cart$$items_count_exists`, toFloat64(`attribute_number_cart$$items_count`), NULL)) AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? GROUP BY `__GROUP_BY_KEY_0_service.name` ORDER BY __result_0 DESC LIMIT ?) SELECT toStartOfInterval(timestamp, INTERVAL 30 SECOND) AS ts, toString(multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `__GROUP_BY_KEY_0_service.name`, sum(multiIf(`attribute_number_cart$$items_count_exists`, toFloat64(`attribute_number_cart$$items_count`), NULL)) AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND (`__GROUP_BY_KEY_0_service.name`) GLOBAL IN (SELECT `__GROUP_BY_KEY_0_service.name` FROM __limit_cte) GROUP BY ts, `__GROUP_BY_KEY_0_service.name`",
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 ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), __limit_cte AS (SELECT toString(multiIf(resource.`service%2Ename` IS NOT NULL, resource.`service%2Ename`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `__GROUP_BY_KEY_0_service.name`, sum(multiIf(`attribute_number_cart$$items_count_exists`, toFloat64(`attribute_number_cart$$items_count`), NULL)) AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? GROUP BY `__GROUP_BY_KEY_0_service.name` ORDER BY __result_0 DESC LIMIT ?) SELECT toStartOfInterval(timestamp, INTERVAL 30 SECOND) AS ts, toString(multiIf(resource.`service%2Ename` IS NOT NULL, resource.`service%2Ename`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `__GROUP_BY_KEY_0_service.name`, sum(multiIf(`attribute_number_cart$$items_count_exists`, toFloat64(`attribute_number_cart$$items_count`), NULL)) AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND (`__GROUP_BY_KEY_0_service.name`) GLOBAL IN (SELECT `__GROUP_BY_KEY_0_service.name` FROM __limit_cte) GROUP BY ts, `__GROUP_BY_KEY_0_service.name`",
Args: []any{"redis-manual", "%service.name%", "%service.name\":\"redis-manual%", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10, "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448)},
},
expectedErr: nil,
@@ -307,7 +307,7 @@ 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 ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), __limit_cte AS (SELECT toString(multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `__GROUP_BY_KEY_0_service.name`, sum(multiIf(`attribute_number_cart$$items_count_exists`, toFloat64(`attribute_number_cart$$items_count`), NULL)) AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? GROUP BY `__GROUP_BY_KEY_0_service.name` ORDER BY `__GROUP_BY_KEY_0_service.name` desc LIMIT ?) SELECT toStartOfInterval(timestamp, INTERVAL 30 SECOND) AS ts, toString(multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `__GROUP_BY_KEY_0_service.name`, sum(multiIf(`attribute_number_cart$$items_count_exists`, toFloat64(`attribute_number_cart$$items_count`), NULL)) AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND (`__GROUP_BY_KEY_0_service.name`) GLOBAL IN (SELECT `__GROUP_BY_KEY_0_service.name` FROM __limit_cte) GROUP BY ts, `__GROUP_BY_KEY_0_service.name` ORDER BY `__GROUP_BY_KEY_0_service.name` desc, ts desc",
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 ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), __limit_cte AS (SELECT toString(multiIf(resource.`service%2Ename` IS NOT NULL, resource.`service%2Ename`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `__GROUP_BY_KEY_0_service.name`, sum(multiIf(`attribute_number_cart$$items_count_exists`, toFloat64(`attribute_number_cart$$items_count`), NULL)) AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? GROUP BY `__GROUP_BY_KEY_0_service.name` ORDER BY `__GROUP_BY_KEY_0_service.name` desc LIMIT ?) SELECT toStartOfInterval(timestamp, INTERVAL 30 SECOND) AS ts, toString(multiIf(resource.`service%2Ename` IS NOT NULL, resource.`service%2Ename`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `__GROUP_BY_KEY_0_service.name`, sum(multiIf(`attribute_number_cart$$items_count_exists`, toFloat64(`attribute_number_cart$$items_count`), NULL)) AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND (`__GROUP_BY_KEY_0_service.name`) GLOBAL IN (SELECT `__GROUP_BY_KEY_0_service.name` FROM __limit_cte) GROUP BY ts, `__GROUP_BY_KEY_0_service.name` ORDER BY `__GROUP_BY_KEY_0_service.name` desc, ts desc",
Args: []any{"redis-manual", "%service.name%", "%service.name\":\"redis-manual%", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10, "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448)},
},
expectedErr: nil,
@@ -458,7 +458,7 @@ func TestStatementBuilder(t *testing.T) {
},
},
expected: qbtypes.Statement{
Query: "WITH __limit_cte AS (SELECT toString(multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `__GROUP_BY_KEY_0_service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE (scope.version::String = ? AND scope.version::String <> '') AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? GROUP BY `__GROUP_BY_KEY_0_service.name` ORDER BY __result_0 DESC LIMIT ?) SELECT toStartOfInterval(timestamp, INTERVAL 30 SECOND) AS ts, toString(multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `__GROUP_BY_KEY_0_service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE (scope.version::String = ? AND scope.version::String <> '') AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND (`__GROUP_BY_KEY_0_service.name`) GLOBAL IN (SELECT `__GROUP_BY_KEY_0_service.name` FROM __limit_cte) GROUP BY ts, `__GROUP_BY_KEY_0_service.name`",
Query: "WITH __limit_cte AS (SELECT toString(multiIf(resource.`service%2Ename` IS NOT NULL, resource.`service%2Ename`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `__GROUP_BY_KEY_0_service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE (scope.version::String = ? AND scope.version::String <> '') AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? GROUP BY `__GROUP_BY_KEY_0_service.name` ORDER BY __result_0 DESC LIMIT ?) SELECT toStartOfInterval(timestamp, INTERVAL 30 SECOND) AS ts, toString(multiIf(resource.`service%2Ename` IS NOT NULL, resource.`service%2Ename`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `__GROUP_BY_KEY_0_service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE (scope.version::String = ? AND scope.version::String <> '') AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND (`__GROUP_BY_KEY_0_service.name`) GLOBAL IN (SELECT `__GROUP_BY_KEY_0_service.name` FROM __limit_cte) GROUP BY ts, `__GROUP_BY_KEY_0_service.name`",
Args: []any{"1.0.0", "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10, "1.0.0", "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448)},
},
},
@@ -552,7 +552,7 @@ func TestStatementBuilderListQuery(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 ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint) SELECT timestamp AS `__SELECT_KEY_0_timestamp`, trace_id AS `__SELECT_KEY_1_trace_id`, span_id AS `__SELECT_KEY_2_span_id`, name AS `__SELECT_KEY_3_name`, multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) AS `__SELECT_KEY_4_service.name`, duration_nano AS `__SELECT_KEY_5_duration_nano`, multiIf(`attribute_number_cart$$items_count_exists`, `attribute_number_cart$$items_count`, NULL) AS `__SELECT_KEY_6_cart.items_count` FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? LIMIT ?",
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 ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint) SELECT timestamp AS `__SELECT_KEY_0_timestamp`, trace_id AS `__SELECT_KEY_1_trace_id`, span_id AS `__SELECT_KEY_2_span_id`, name AS `__SELECT_KEY_3_name`, multiIf(resource.`service%2Ename` IS NOT NULL, resource.`service%2Ename`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) AS `__SELECT_KEY_4_service.name`, duration_nano AS `__SELECT_KEY_5_duration_nano`, multiIf(`attribute_number_cart$$items_count_exists`, `attribute_number_cart$$items_count`, NULL) AS `__SELECT_KEY_6_cart.items_count` FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? LIMIT ?",
Args: []any{"redis-manual", "%service.name%", "%service.name\":\"redis-manual%", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10},
},
expectedErr: nil,
@@ -669,7 +669,7 @@ func TestStatementBuilderListQuery(t *testing.T) {
Limit: 10,
},
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 ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint) SELECT timestamp AS `__SELECT_KEY_0_timestamp`, trace_id AS `__SELECT_KEY_1_trace_id`, span_id AS `__SELECT_KEY_2_span_id`, name AS `__SELECT_KEY_3_name`, resource_string_service$$name AS `__SELECT_KEY_4_serviceName`, duration_nano AS `__SELECT_KEY_5_durationNano`, http_method AS `__SELECT_KEY_6_httpMethod`, multiIf(`attribute_string_mixed$$materialization$$key_exists`, `attribute_string_mixed$$materialization$$key`, multiIf(resource.`mixed.materialization.key` IS NOT NULL, resource.`mixed.materialization.key`::String, mapContains(resources_string, 'mixed.materialization.key'), resources_string['mixed.materialization.key'], NULL) IS NOT NULL, multiIf(resource.`mixed.materialization.key` IS NOT NULL, resource.`mixed.materialization.key`::String, mapContains(resources_string, 'mixed.materialization.key'), resources_string['mixed.materialization.key'], NULL), NULL) AS `__SELECT_KEY_7_mixed.materialization.key` FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? LIMIT ?",
Query: "WITH __resource_filter AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint) SELECT timestamp AS `__SELECT_KEY_0_timestamp`, trace_id AS `__SELECT_KEY_1_trace_id`, span_id AS `__SELECT_KEY_2_span_id`, name AS `__SELECT_KEY_3_name`, resource_string_service$$name AS `__SELECT_KEY_4_serviceName`, duration_nano AS `__SELECT_KEY_5_durationNano`, http_method AS `__SELECT_KEY_6_httpMethod`, multiIf(`attribute_string_mixed$$materialization$$key_exists`, `attribute_string_mixed$$materialization$$key`, multiIf(resource.`mixed%2Ematerialization%2Ekey` IS NOT NULL, resource.`mixed%2Ematerialization%2Ekey`::String, mapContains(resources_string, 'mixed.materialization.key'), resources_string['mixed.materialization.key'], NULL) IS NOT NULL, multiIf(resource.`mixed%2Ematerialization%2Ekey` IS NOT NULL, resource.`mixed%2Ematerialization%2Ekey`::String, mapContains(resources_string, 'mixed.materialization.key'), resources_string['mixed.materialization.key'], NULL), NULL) AS `__SELECT_KEY_7_mixed.materialization.key` FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? LIMIT ?",
Args: []any{"redis-manual", "%service.name%", "%service.name\":\"redis-manual%", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10},
},
expectedErr: nil,
@@ -958,7 +958,7 @@ func TestStatementBuilderListQueryWithCorruptData(t *testing.T) {
Limit: 10,
},
expected: qbtypes.Statement{
Query: "SELECT timestamp AS `__SELECT_KEY_0_timestamp`, trace_id AS `__SELECT_KEY_1_trace_id`, span_id AS `__SELECT_KEY_2_span_id`, multiIf(scope.attributes.`scope.prefixed` IS NOT NULL, scope.attributes.`scope.prefixed`::String, NULL) AS `__SELECT_KEY_3_scope.prefixed` FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? LIMIT ?",
Query: "SELECT timestamp AS `__SELECT_KEY_0_timestamp`, trace_id AS `__SELECT_KEY_1_trace_id`, span_id AS `__SELECT_KEY_2_span_id`, multiIf(scope.attributes.`scope%2Eprefixed` IS NOT NULL, scope.attributes.`scope%2Eprefixed`::String, NULL) AS `__SELECT_KEY_3_scope.prefixed` FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? LIMIT ?",
Args: []any{"1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10},
},
},
@@ -1074,7 +1074,7 @@ func TestStatementBuilderGroupByResourceEvolution(t *testing.T) {
startMs: 1747947419000, // 2025-05-22 21:56:59 UTC, ~3m before release
endMs: 1747983448000, // 2025-05-23 07:57:28 UTC, ~10h after release
expected: qbtypes.Statement{
Query: "WITH __limit_cte AS (SELECT toString(multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `__GROUP_BY_KEY_0_service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? GROUP BY `__GROUP_BY_KEY_0_service.name` ORDER BY __result_0 DESC LIMIT ?) SELECT toStartOfInterval(timestamp, INTERVAL 30 SECOND) AS ts, toString(multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `__GROUP_BY_KEY_0_service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND (`__GROUP_BY_KEY_0_service.name`) GLOBAL IN (SELECT `__GROUP_BY_KEY_0_service.name` FROM __limit_cte) GROUP BY ts, `__GROUP_BY_KEY_0_service.name`",
Query: "WITH __limit_cte AS (SELECT toString(multiIf(resource.`service%2Ename` IS NOT NULL, resource.`service%2Ename`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `__GROUP_BY_KEY_0_service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? GROUP BY `__GROUP_BY_KEY_0_service.name` ORDER BY __result_0 DESC LIMIT ?) SELECT toStartOfInterval(timestamp, INTERVAL 30 SECOND) AS ts, toString(multiIf(resource.`service%2Ename` IS NOT NULL, resource.`service%2Ename`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `__GROUP_BY_KEY_0_service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND (`__GROUP_BY_KEY_0_service.name`) GLOBAL IN (SELECT `__GROUP_BY_KEY_0_service.name` FROM __limit_cte) GROUP BY ts, `__GROUP_BY_KEY_0_service.name`",
Args: []any{"1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10, "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448)},
},
},
@@ -1083,7 +1083,7 @@ func TestStatementBuilderGroupByResourceEvolution(t *testing.T) {
startMs: 1747960000000, // 2025-05-23 00:26:40 UTC, ~2.5h after release
endMs: 1747983448000, // 2025-05-23 07:57:28 UTC
expected: qbtypes.Statement{
Query: "WITH __limit_cte AS (SELECT toString(multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, NULL)) AS `__GROUP_BY_KEY_0_service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? GROUP BY `__GROUP_BY_KEY_0_service.name` ORDER BY __result_0 DESC LIMIT ?) SELECT toStartOfInterval(timestamp, INTERVAL 30 SECOND) AS ts, toString(multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, NULL)) AS `__GROUP_BY_KEY_0_service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND (`__GROUP_BY_KEY_0_service.name`) GLOBAL IN (SELECT `__GROUP_BY_KEY_0_service.name` FROM __limit_cte) GROUP BY ts, `__GROUP_BY_KEY_0_service.name`",
Query: "WITH __limit_cte AS (SELECT toString(multiIf(resource.`service%2Ename` IS NOT NULL, resource.`service%2Ename`::String, NULL)) AS `__GROUP_BY_KEY_0_service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? GROUP BY `__GROUP_BY_KEY_0_service.name` ORDER BY __result_0 DESC LIMIT ?) SELECT toStartOfInterval(timestamp, INTERVAL 30 SECOND) AS ts, toString(multiIf(resource.`service%2Ename` IS NOT NULL, resource.`service%2Ename`::String, NULL)) AS `__GROUP_BY_KEY_0_service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND (`__GROUP_BY_KEY_0_service.name`) GLOBAL IN (SELECT `__GROUP_BY_KEY_0_service.name` FROM __limit_cte) GROUP BY ts, `__GROUP_BY_KEY_0_service.name`",
Args: []any{"1747960000000000000", "1747983448000000000", uint64(1747958200), uint64(1747983448), 10, "1747960000000000000", "1747983448000000000", uint64(1747958200), uint64(1747983448)},
},
},
@@ -1194,7 +1194,7 @@ func TestStatementBuilderTraceQuery(t *testing.T) {
Limit: 10,
},
expected: qbtypes.Statement{
Query: "WITH __toe AS (SELECT trace_id FROM signoz_traces.distributed_signoz_index_v3 WHERE ((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 timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __toe_duration_sorted AS (SELECT trace_id, duration_nano, resource_string_service$$name as `service.name`, name FROM signoz_traces.distributed_signoz_index_v3 WHERE parent_span_id = '' AND trace_id GLOBAL IN __toe AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? ORDER BY duration_nano DESC LIMIT 1 BY trace_id) SELECT __toe_duration_sorted.`service.name` AS `service.name`, __toe_duration_sorted.name AS `name`, count() AS span_count, __toe_duration_sorted.duration_nano AS `duration_nano`, __toe_duration_sorted.trace_id AS `trace_id` FROM __toe INNER JOIN __toe_duration_sorted ON __toe.trace_id = __toe_duration_sorted.trace_id GROUP BY trace_id, duration_nano, name, `service.name` ORDER BY duration_nano DESC LIMIT 1 BY trace_id LIMIT ? SETTINGS distributed_product_mode='allow', max_memory_usage=10000000000",
Query: "WITH __toe AS (SELECT trace_id FROM signoz_traces.distributed_signoz_index_v3 WHERE ((match(`attribute_string_materialized$$key$$name`, ?) AND `attribute_string_materialized$$key$$name_exists`) OR multiIf(resource.`service%2Ename` IS NOT NULL, resource.`service%2Ename`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) = ?) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __toe_duration_sorted AS (SELECT trace_id, duration_nano, resource_string_service$$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", "redis-manual", "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10},
},
expectedErr: nil,
@@ -1884,7 +1884,7 @@ func TestSkipResourceFingerprint(t *testing.T) {
require.NotContains(t, stmt.Query, "__resource_filter AS")
require.NotContains(t, stmt.Query, "resource_fingerprint")
// resource conditions are pushed onto the main table via the
// resource.`service.name` / resources_string lookup
// resource.`service%2Ename` / resources_string lookup
require.Contains(t, stmt.Query, "service.name")
require.NoError(t, mock.ExpectationsWereMet())

View File

@@ -87,7 +87,7 @@ func TestTraceOperatorStatementBuilder(t *testing.T) {
},
},
expected: qbtypes.Statement{
Query: "WITH toDateTime64(1747947419000000000, 9) AS t_from, toDateTime64(1747983448000000000, 9) AS t_to, 1747945619 AS bucket_from, 1747983448 AS bucket_to, all_spans AS (SELECT *, resource_string_service$$name AS `service.name` FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_A AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), A AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_A) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_B AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), B AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_B) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), A_DIR_DESC_B AS (SELECT p.* FROM A AS p INNER JOIN B AS c ON p.trace_id = c.trace_id AND p.span_id = c.parent_span_id) SELECT timestamp, trace_id, span_id, name, duration_nano, parent_span_id, multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) AS `__SELECT_KEY_0_service.name` FROM A_DIR_DESC_B ORDER BY timestamp DESC LIMIT ? SETTINGS distributed_product_mode='allow', max_memory_usage=10000000000",
Query: "WITH toDateTime64(1747947419000000000, 9) AS t_from, toDateTime64(1747983448000000000, 9) AS t_to, 1747945619 AS bucket_from, 1747983448 AS bucket_to, all_spans AS (SELECT *, resource_string_service$$name AS `service.name` FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_A AS (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 <= ? GROUP BY fingerprint), A AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_A) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_B AS (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 <= ? GROUP BY fingerprint), B AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_B) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), A_DIR_DESC_B AS (SELECT p.* FROM A AS p INNER JOIN B AS c ON p.trace_id = c.trace_id AND p.span_id = c.parent_span_id) SELECT timestamp, trace_id, span_id, name, duration_nano, parent_span_id, multiIf(resource.`service%2Ename` IS NOT NULL, resource.`service%2Ename`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) AS `__SELECT_KEY_0_service.name` FROM A_DIR_DESC_B ORDER BY timestamp DESC LIMIT ? SETTINGS distributed_product_mode='allow', max_memory_usage=10000000000",
Args: []any{"1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), "frontend", "%service.name%", "%service.name\":\"frontend%", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), "backend", "%service.name%", "%service.name\":\"backend%", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10},
},
expectedErr: nil,
@@ -284,7 +284,7 @@ func TestTraceOperatorStatementBuilder(t *testing.T) {
},
},
expected: qbtypes.Statement{
Query: "WITH toDateTime64(1747947419000000000, 9) AS t_from, toDateTime64(1747983448000000000, 9) AS t_to, 1747945619 AS bucket_from, 1747983448 AS bucket_to, all_spans AS (SELECT *, resource_string_service$$name AS `service.name` FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_A AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), A AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_A) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_B AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), B AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_B) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), A_DIR_DESC_B AS (SELECT p.* FROM A AS p INNER JOIN B AS c ON p.trace_id = c.trace_id AND p.span_id = c.parent_span_id) SELECT toStartOfInterval(timestamp, INTERVAL 60 SECOND) AS ts, toString(multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `service.name`, count() AS __result_0 FROM A_DIR_DESC_B GROUP BY ts, `service.name` ORDER BY ts desc SETTINGS distributed_product_mode='allow', max_memory_usage=10000000000",
Query: "WITH toDateTime64(1747947419000000000, 9) AS t_from, toDateTime64(1747983448000000000, 9) AS t_to, 1747945619 AS bucket_from, 1747983448 AS bucket_to, all_spans AS (SELECT *, resource_string_service$$name AS `service.name` FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_A AS (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 <= ? GROUP BY fingerprint), A AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_A) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_B AS (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 <= ? GROUP BY fingerprint), B AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_B) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), A_DIR_DESC_B AS (SELECT p.* FROM A AS p INNER JOIN B AS c ON p.trace_id = c.trace_id AND p.span_id = c.parent_span_id) SELECT toStartOfInterval(timestamp, INTERVAL 60 SECOND) AS ts, toString(multiIf(resource.`service%2Ename` IS NOT NULL, resource.`service%2Ename`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `service.name`, count() AS __result_0 FROM A_DIR_DESC_B GROUP BY ts, `service.name` ORDER BY ts desc SETTINGS distributed_product_mode='allow', max_memory_usage=10000000000",
Args: []any{"1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), "frontend", "%service.name%", "%service.name\":\"frontend%", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), "backend", "%service.name%", "%service.name\":\"backend%", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448)},
},
expectedErr: nil,
@@ -343,7 +343,7 @@ func TestTraceOperatorStatementBuilder(t *testing.T) {
},
},
expected: qbtypes.Statement{
Query: "WITH toDateTime64(1747947419000000000, 9) AS t_from, toDateTime64(1747983448000000000, 9) AS t_to, 1747945619 AS bucket_from, 1747983448 AS bucket_to, all_spans AS (SELECT *, resource_string_service$$name AS `service.name` FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_A AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), A AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_A) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), B AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND toFloat64(response_status_code) < ?), A_AND_B AS (SELECT l.* FROM A AS l INNER JOIN B AS r ON l.trace_id = r.trace_id) SELECT toString(multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `service.name`, avg(toFloat64(duration_nano)) AS __result_0 FROM A_AND_B GROUP BY `service.name` ORDER BY __result_0 desc SETTINGS distributed_product_mode='allow', max_memory_usage=10000000000",
Query: "WITH toDateTime64(1747947419000000000, 9) AS t_from, toDateTime64(1747983448000000000, 9) AS t_to, 1747945619 AS bucket_from, 1747983448 AS bucket_to, all_spans AS (SELECT *, resource_string_service$$name AS `service.name` FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_A AS (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 <= ? GROUP BY fingerprint), A AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_A) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), B AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND toFloat64(response_status_code) < ?), A_AND_B AS (SELECT l.* FROM A AS l INNER JOIN B AS r ON l.trace_id = r.trace_id) SELECT toString(multiIf(resource.`service%2Ename` IS NOT NULL, resource.`service%2Ename`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)) AS `service.name`, avg(toFloat64(duration_nano)) AS __result_0 FROM A_AND_B GROUP BY `service.name` ORDER BY __result_0 desc SETTINGS distributed_product_mode='allow', max_memory_usage=10000000000",
Args: []any{"1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), "frontend", "%service.name%", "%service.name\":\"frontend%", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), float64(400)},
},
expectedErr: nil,

View File

@@ -220,7 +220,7 @@ func TestConditionFor(t *testing.T) {
},
operator: qbtypes.FilterOperatorExists,
value: nil,
expectedSQL: "WHERE multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) IS NOT NULL",
expectedSQL: "WHERE multiIf(resource.`service%2Ename` IS NOT NULL, resource.`service%2Ename`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) IS NOT NULL",
expectedError: nil,
},
{
@@ -233,7 +233,7 @@ func TestConditionFor(t *testing.T) {
},
operator: qbtypes.FilterOperatorNotExists,
value: nil,
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",
expectedSQL: "WHERE multiIf(resource.`service%2Ename` IS NOT NULL, resource.`service%2Ename`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) IS NULL",
expectedError: nil,
},
{
@@ -331,7 +331,7 @@ func TestConditionForResourceWithEvolution(t *testing.T) {
operator: qbtypes.FilterOperatorExists,
tsStart: uint64(time.Date(2025, 6, 1, 0, 0, 0, 0, time.UTC).UnixNano()),
tsEnd: uint64(time.Date(2025, 7, 1, 0, 0, 0, 0, time.UTC).UnixNano()),
expectedSQL: "WHERE resource.`service.name` IS NOT NULL",
expectedSQL: "WHERE resource.`service%2Ename` IS NOT NULL",
},
{
name: "NotExists - window after release - JSON only",
@@ -344,7 +344,7 @@ func TestConditionForResourceWithEvolution(t *testing.T) {
operator: qbtypes.FilterOperatorNotExists,
tsStart: uint64(time.Date(2025, 6, 1, 0, 0, 0, 0, time.UTC).UnixNano()),
tsEnd: uint64(time.Date(2025, 7, 1, 0, 0, 0, 0, time.UTC).UnixNano()),
expectedSQL: "WHERE resource.`service.name` IS NULL",
expectedSQL: "WHERE resource.`service%2Ename` IS NULL",
},
{
name: "Exists - window before release - map only",
@@ -370,7 +370,7 @@ func TestConditionForResourceWithEvolution(t *testing.T) {
operator: qbtypes.FilterOperatorExists,
tsStart: uint64(time.Date(2024, 6, 1, 0, 0, 0, 0, time.UTC).UnixNano()),
tsEnd: uint64(time.Date(2025, 6, 1, 0, 0, 0, 0, time.UTC).UnixNano()),
expectedSQL: "WHERE multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) IS NOT NULL",
expectedSQL: "WHERE multiIf(resource.`service%2Ename` IS NOT NULL, resource.`service%2Ename`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) IS NOT NULL",
},
}
@@ -507,10 +507,10 @@ func TestConditionForSynthesizedKeys(t *testing.T) {
assert.NotEmpty(t, warnings)
sb.Where(conds...)
sql, _ := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
assert.Contains(t, sql, "scope.attributes.`custom.attr`")
assert.Contains(t, sql, "scope.attributes.`custom%2Eattr`")
// `scope.` can be part of the attribute's own name, so the literal spelling is a
// candidate too — the caller ORs the two.
assert.Contains(t, sql, "scope.attributes.`scope.custom.attr`")
assert.Contains(t, sql, "scope.attributes.`scope%2Ecustom%2Eattr`")
})
t.Run("bare key with number operand -> attribute number", func(t *testing.T) {

View File

@@ -63,7 +63,7 @@ func TestConditionForFamilyMergesMembersCurrentFirst(t *testing.T) {
sb.Where(conds...)
sql, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
require.Equal(t, "WHERE (COALESCE(NULLIF(multiIf(resource.`deployment.environment.name` IS NOT NULL, resource.`deployment.environment.name`::String, mapContains(resources_string, 'deployment.environment.name'), resources_string['deployment.environment.name'], NULL), ''), NULLIF(multiIf(resource.`deployment.environment` IS NOT NULL, resource.`deployment.environment`::String, mapContains(resources_string, 'deployment.environment'), resources_string['deployment.environment'], NULL), ''), '') = ? AND (multiIf(resource.`deployment.environment.name` IS NOT NULL, resource.`deployment.environment.name`::String, mapContains(resources_string, 'deployment.environment.name'), resources_string['deployment.environment.name'], NULL) IS NOT NULL OR multiIf(resource.`deployment.environment` IS NOT NULL, resource.`deployment.environment`::String, mapContains(resources_string, 'deployment.environment'), resources_string['deployment.environment'], NULL) IS NOT NULL))", sql)
require.Equal(t, "WHERE (COALESCE(NULLIF(multiIf(resource.`deployment%2Eenvironment%2Ename` IS NOT NULL, resource.`deployment%2Eenvironment%2Ename`::String, mapContains(resources_string, 'deployment.environment.name'), resources_string['deployment.environment.name'], NULL), ''), NULLIF(multiIf(resource.`deployment%2Eenvironment` IS NOT NULL, resource.`deployment%2Eenvironment`::String, mapContains(resources_string, 'deployment.environment'), resources_string['deployment.environment'], NULL), ''), '') = ? AND (multiIf(resource.`deployment%2Eenvironment%2Ename` IS NOT NULL, resource.`deployment%2Eenvironment%2Ename`::String, mapContains(resources_string, 'deployment.environment.name'), resources_string['deployment.environment.name'], NULL) IS NOT NULL OR multiIf(resource.`deployment%2Eenvironment` IS NOT NULL, resource.`deployment%2Eenvironment`::String, mapContains(resources_string, 'deployment.environment'), resources_string['deployment.environment'], NULL) IS NOT NULL))", sql)
require.Equal(t, []any{"production"}, args)
}
@@ -98,7 +98,7 @@ func TestConditionForFamilyNegativeKeepsKeylessRows(t *testing.T) {
// semantics), so `!=` keeps including them; no exists filter is added.
sb.Where(conds...)
sql, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
require.Equal(t, "WHERE COALESCE(NULLIF(multiIf(resource.`deployment.environment.name` IS NOT NULL, resource.`deployment.environment.name`::String, mapContains(resources_string, 'deployment.environment.name'), resources_string['deployment.environment.name'], NULL), ''), NULLIF(multiIf(resource.`deployment.environment` IS NOT NULL, resource.`deployment.environment`::String, mapContains(resources_string, 'deployment.environment'), resources_string['deployment.environment'], NULL), ''), '') <> ?", sql)
require.Equal(t, "WHERE COALESCE(NULLIF(multiIf(resource.`deployment%2Eenvironment%2Ename` IS NOT NULL, resource.`deployment%2Eenvironment%2Ename`::String, mapContains(resources_string, 'deployment.environment.name'), resources_string['deployment.environment.name'], NULL), ''), NULLIF(multiIf(resource.`deployment%2Eenvironment` IS NOT NULL, resource.`deployment%2Eenvironment`::String, mapContains(resources_string, 'deployment.environment'), resources_string['deployment.environment'], NULL), ''), '') <> ?", sql)
require.Equal(t, []any{"production"}, args)
}
@@ -131,7 +131,7 @@ func TestConditionForFamilyExists(t *testing.T) {
sb.Where(conds...)
sql, _ := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
require.Equal(t, "WHERE NOT (multiIf(resource.`deployment.environment.name` IS NOT NULL, resource.`deployment.environment.name`::String, mapContains(resources_string, 'deployment.environment.name'), resources_string['deployment.environment.name'], NULL) IS NOT NULL OR multiIf(resource.`deployment.environment` IS NOT NULL, resource.`deployment.environment`::String, mapContains(resources_string, 'deployment.environment'), resources_string['deployment.environment'], NULL) IS NOT NULL)", sql)
require.Equal(t, "WHERE NOT (multiIf(resource.`deployment%2Eenvironment%2Ename` IS NOT NULL, resource.`deployment%2Eenvironment%2Ename`::String, mapContains(resources_string, 'deployment.environment.name'), resources_string['deployment.environment.name'], NULL) IS NOT NULL OR multiIf(resource.`deployment%2Eenvironment` IS NOT NULL, resource.`deployment%2Eenvironment`::String, mapContains(resources_string, 'deployment.environment'), resources_string['deployment.environment'], NULL) IS NOT NULL)", sql)
}
// With the flag off, both spellings can be in the metadata map and the
@@ -166,7 +166,7 @@ func TestConditionForFamilyOffByDefault(t *testing.T) {
sb.Where(conds...)
sql, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
require.Equal(t, "WHERE multiIf(resource.`deployment.environment.name` IS NOT NULL, resource.`deployment.environment.name`::String, mapContains(resources_string, 'deployment.environment.name'), resources_string['deployment.environment.name'], NULL) = ?", sql)
require.Equal(t, "WHERE multiIf(resource.`deployment%2Eenvironment%2Ename` IS NOT NULL, resource.`deployment%2Eenvironment%2Ename`::String, mapContains(resources_string, 'deployment.environment.name'), resources_string['deployment.environment.name'], NULL) = ?", sql)
require.Equal(t, []any{"production"}, args)
}
@@ -202,7 +202,7 @@ func TestConditionForSingleMemberIsUnchanged(t *testing.T) {
sb.Where(conds...)
sql, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
require.Equal(t, "WHERE multiIf(resource.`deployment.environment.name` IS NOT NULL, resource.`deployment.environment.name`::String, mapContains(resources_string, 'deployment.environment.name'), resources_string['deployment.environment.name'], NULL) = ?", sql)
require.Equal(t, "WHERE multiIf(resource.`deployment%2Eenvironment%2Ename` IS NOT NULL, resource.`deployment%2Eenvironment%2Ename`::String, mapContains(resources_string, 'deployment.environment.name'), resources_string['deployment.environment.name'], NULL) = ?", sql)
require.Equal(t, []any{"production"}, args)
}
@@ -230,5 +230,5 @@ func TestColumnExpressionForFamilyGroupBy(t *testing.T) {
expr, err := querybuilder.ResolveColumn(context.Background(), querybuilder.NewQueryInfo(context.Background(), valuer.UUID{}, fl, telemetrytypes.SignalTraces, nil, startNs, endNs), storage, &telemetrytypes.TelemetryFieldKey{Name: "deployment.environment.name"}, telemetrytypes.FieldDataTypeString, fieldKeys)
require.NoError(t, err)
require.Equal(t, "multiIf((multiIf(resource.`deployment.environment.name` IS NOT NULL, resource.`deployment.environment.name`::String, mapContains(resources_string, 'deployment.environment.name'), resources_string['deployment.environment.name'], NULL) IS NOT NULL OR multiIf(resource.`deployment.environment` IS NOT NULL, resource.`deployment.environment`::String, mapContains(resources_string, 'deployment.environment'), resources_string['deployment.environment'], NULL) IS NOT NULL), COALESCE(NULLIF(multiIf(resource.`deployment.environment.name` IS NOT NULL, resource.`deployment.environment.name`::String, mapContains(resources_string, 'deployment.environment.name'), resources_string['deployment.environment.name'], NULL), ''), NULLIF(multiIf(resource.`deployment.environment` IS NOT NULL, resource.`deployment.environment`::String, mapContains(resources_string, 'deployment.environment'), resources_string['deployment.environment'], NULL), ''), ''), NULL)", expr)
require.Equal(t, "multiIf((multiIf(resource.`deployment%2Eenvironment%2Ename` IS NOT NULL, resource.`deployment%2Eenvironment%2Ename`::String, mapContains(resources_string, 'deployment.environment.name'), resources_string['deployment.environment.name'], NULL) IS NOT NULL OR multiIf(resource.`deployment%2Eenvironment` IS NOT NULL, resource.`deployment%2Eenvironment`::String, mapContains(resources_string, 'deployment.environment'), resources_string['deployment.environment'], NULL) IS NOT NULL), COALESCE(NULLIF(multiIf(resource.`deployment%2Eenvironment%2Ename` IS NOT NULL, resource.`deployment%2Eenvironment%2Ename`::String, mapContains(resources_string, 'deployment.environment.name'), resources_string['deployment.environment.name'], NULL), ''), NULLIF(multiIf(resource.`deployment%2Eenvironment` IS NOT NULL, resource.`deployment%2Eenvironment`::String, mapContains(resources_string, 'deployment.environment'), resources_string['deployment.environment'], NULL), ''), ''), NULL)", expr)
}

View File

@@ -259,8 +259,8 @@ func (m *storage) resolveColumnExprs(
// once clickHouse dependency is updated, we need to check if we can remove it.
switch key.FieldContext {
case telemetrytypes.FieldContextResource:
exprs = append(exprs, fmt.Sprintf("%s.%s::String", columnName, clickhousesql.Identifier(key.Name)))
existExprs = append(existExprs, fmt.Sprintf("%s.%s IS NOT NULL", columnName, clickhousesql.Identifier(key.Name)))
exprs = append(exprs, fmt.Sprintf("%s.%s::String", columnName, clickhousesql.JSONKeyIdentifier(key.Name)))
existExprs = append(existExprs, fmt.Sprintf("%s.%s IS NOT NULL", columnName, clickhousesql.JSONKeyIdentifier(key.Name)))
case telemetrytypes.FieldContextScope:
if f, ok := IntrinsicFields[key.Name]; ok && f.FieldContext == telemetrytypes.FieldContextScope {
// declared String paths on the scope column read '' for the missing case
@@ -268,11 +268,11 @@ func (m *storage) resolveColumnExprs(
existExprs = append(existExprs, fmt.Sprintf("%s <> ''", key.Name))
} else {
attributeName := strings.TrimPrefix(key.Name, "attribute.") // literal "attribute" prefix in attribute keys needs double prefix
exprs = append(exprs, fmt.Sprintf("%s.attributes.%s::String", columnName, clickhousesql.Identifier(attributeName)))
existExprs = append(existExprs, fmt.Sprintf("%s.attributes.%s IS NOT NULL", columnName, clickhousesql.Identifier(attributeName)))
exprs = append(exprs, fmt.Sprintf("%s.attributes.%s::String", columnName, clickhousesql.JSONKeyIdentifier(attributeName)))
existExprs = append(existExprs, fmt.Sprintf("%s.attributes.%s IS NOT NULL", columnName, clickhousesql.JSONKeyIdentifier(attributeName)))
}
case telemetrytypes.FieldContextAttribute:
path := fmt.Sprintf("%s.%s", columnName, clickhousesql.Identifier(key.Name))
path := fmt.Sprintf("%s.%s", columnName, clickhousesql.JSONKeyIdentifier(key.Name))
expr, existExpr := attributeJSONValueExpr(path, key.FieldDataType)
exprs = append(exprs, expr)
existExprs = append(existExprs, existExpr)

View File

@@ -54,15 +54,15 @@ func TestFieldForAttributeJSONEvolution(t *testing.T) {
expected string
}{
{"string before -> map", telemetrytypes.FieldDataTypeString, attrWindowBefore, "attributes_string['user.id']"},
{"string after -> json", telemetrytypes.FieldDataTypeString, attrWindowAfter, "attributes.`user.id`::String"},
{"string straddle -> dual", telemetrytypes.FieldDataTypeString, attrWindowStraddle, "multiIf(attributes.`user.id` IS NOT NULL, attributes.`user.id`::String, mapContains(attributes_string, 'user.id'), attributes_string['user.id'], NULL)"},
{"string after -> json", telemetrytypes.FieldDataTypeString, attrWindowAfter, "attributes.`user%2Eid`::String"},
{"string straddle -> dual", telemetrytypes.FieldDataTypeString, attrWindowStraddle, "multiIf(attributes.`user%2Eid` IS NOT NULL, attributes.`user%2Eid`::String, mapContains(attributes_string, 'user.id'), attributes_string['user.id'], NULL)"},
{"number before -> map", telemetrytypes.FieldDataTypeNumber, attrWindowBefore, "attributes_number['user.id']"},
{"number after -> json", telemetrytypes.FieldDataTypeNumber, attrWindowAfter, "if(dynamicType(attributes.`user.id`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`user.id`, 'Float64'), NULL)"},
{"number straddle -> dual", telemetrytypes.FieldDataTypeNumber, attrWindowStraddle, "multiIf(if(dynamicType(attributes.`user.id`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`user.id`, 'Float64'), NULL) IS NOT NULL, if(dynamicType(attributes.`user.id`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`user.id`, 'Float64'), NULL), mapContains(attributes_number, 'user.id'), attributes_number['user.id'], NULL)"},
{"int64 after -> json", telemetrytypes.FieldDataTypeInt64, attrWindowAfter, "if(dynamicType(attributes.`user.id`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`user.id`, 'Float64'), NULL)"},
{"number after -> json", telemetrytypes.FieldDataTypeNumber, attrWindowAfter, "if(dynamicType(attributes.`user%2Eid`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`user%2Eid`, 'Float64'), NULL)"},
{"number straddle -> dual", telemetrytypes.FieldDataTypeNumber, attrWindowStraddle, "multiIf(if(dynamicType(attributes.`user%2Eid`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`user%2Eid`, 'Float64'), NULL) IS NOT NULL, if(dynamicType(attributes.`user%2Eid`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`user%2Eid`, 'Float64'), NULL), mapContains(attributes_number, 'user.id'), attributes_number['user.id'], NULL)"},
{"int64 after -> json", telemetrytypes.FieldDataTypeInt64, attrWindowAfter, "if(dynamicType(attributes.`user%2Eid`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`user%2Eid`, 'Float64'), NULL)"},
{"bool before -> map", telemetrytypes.FieldDataTypeBool, attrWindowBefore, "attributes_bool['user.id']"},
{"bool after -> json", telemetrytypes.FieldDataTypeBool, attrWindowAfter, "if(dynamicType(attributes.`user.id`) = 'Bool', accurateCastOrNull(attributes.`user.id`, 'Bool'), NULL)"},
{"bool straddle -> dual", telemetrytypes.FieldDataTypeBool, attrWindowStraddle, "multiIf(if(dynamicType(attributes.`user.id`) = 'Bool', accurateCastOrNull(attributes.`user.id`, 'Bool'), NULL) IS NOT NULL, if(dynamicType(attributes.`user.id`) = 'Bool', accurateCastOrNull(attributes.`user.id`, 'Bool'), NULL), mapContains(attributes_bool, 'user.id'), attributes_bool['user.id'], NULL)"},
{"bool after -> json", telemetrytypes.FieldDataTypeBool, attrWindowAfter, "if(dynamicType(attributes.`user%2Eid`) = 'Bool', accurateCastOrNull(attributes.`user%2Eid`, 'Bool'), NULL)"},
{"bool straddle -> dual", telemetrytypes.FieldDataTypeBool, attrWindowStraddle, "multiIf(if(dynamicType(attributes.`user%2Eid`) = 'Bool', accurateCastOrNull(attributes.`user%2Eid`, 'Bool'), NULL) IS NOT NULL, if(dynamicType(attributes.`user%2Eid`) = 'Bool', accurateCastOrNull(attributes.`user%2Eid`, 'Bool'), NULL), mapContains(attributes_bool, 'user.id'), attributes_bool['user.id'], NULL)"},
}
for _, tc := range testCases {
@@ -115,49 +115,49 @@ func TestConditionForAttributeJSON(t *testing.T) {
name: "equal string",
key: attrKey("user.id", telemetrytypes.FieldDataTypeString, evo),
operator: qbtypes.FilterOperatorEqual, value: "admin",
expected: "(attributes.`user.id`::String = ? AND attributes.`user.id` IS NOT NULL)",
expected: "(attributes.`user%2Eid`::String = ? AND attributes.`user%2Eid` IS NOT NULL)",
},
{
name: "not equal string has no exists guard",
key: attrKey("user.id", telemetrytypes.FieldDataTypeString, evo),
operator: qbtypes.FilterOperatorNotEqual, value: "admin",
expected: "attributes.`user.id`::String <> ?",
expected: "attributes.`user%2Eid`::String <> ?",
},
{
name: "greater than number",
key: attrKey("http.status_code", telemetrytypes.FieldDataTypeInt64, evo),
operator: qbtypes.FilterOperatorGreaterThan, value: float64(200),
expected: "toFloat64(if(dynamicType(attributes.`http.status_code`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`http.status_code`, 'Float64'), NULL)) > ?",
expected: "toFloat64(if(dynamicType(attributes.`http%2Estatus_code`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`http%2Estatus_code`, 'Float64'), NULL)) > ?",
},
{
name: "ilike string",
key: attrKey("user.id", telemetrytypes.FieldDataTypeString, evo),
operator: qbtypes.FilterOperatorILike, value: "%adm%",
expected: "LOWER(attributes.`user.id`::String) LIKE LOWER(?)",
expected: "LOWER(attributes.`user%2Eid`::String) LIKE LOWER(?)",
},
{
name: "exists uses raw path",
key: attrKey("user.id", telemetrytypes.FieldDataTypeString, evo),
operator: qbtypes.FilterOperatorExists, value: nil,
expected: "attributes.`user.id` IS NOT NULL",
expected: "attributes.`user%2Eid` IS NOT NULL",
},
{
name: "not exists uses raw path",
key: attrKey("user.id", telemetrytypes.FieldDataTypeString, evo),
operator: qbtypes.FilterOperatorNotExists, value: nil,
expected: "attributes.`user.id` IS NULL",
expected: "attributes.`user%2Eid` IS NULL",
},
{
name: "in string",
key: attrKey("user.id", telemetrytypes.FieldDataTypeString, evo),
operator: qbtypes.FilterOperatorIn, value: []any{"a", "b"},
expected: "((attributes.`user.id`::String = ? OR attributes.`user.id`::String = ?) AND attributes.`user.id` IS NOT NULL)",
expected: "((attributes.`user%2Eid`::String = ? OR attributes.`user%2Eid`::String = ?) AND attributes.`user%2Eid` IS NOT NULL)",
},
{
name: "not in string has no exists guard",
key: attrKey("user.id", telemetrytypes.FieldDataTypeString, evo),
operator: qbtypes.FilterOperatorNotIn, value: []any{"a", "b"},
expected: "(attributes.`user.id`::String <> ? AND attributes.`user.id`::String <> ?)",
expected: "(attributes.`user%2Eid`::String <> ? AND attributes.`user%2Eid`::String <> ?)",
},
{
name: "between number",
@@ -195,7 +195,7 @@ func TestConditionForAttributeJSONNotExistsDualRead(t *testing.T) {
sql, _ := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
// the value multiIf resolves the row's home; NOT EXISTS negates the whole thing to IS NULL
assert.Contains(t, sql, "IS NULL")
assert.Contains(t, sql, "attributes.`user.id` IS NOT NULL")
assert.Contains(t, sql, "attributes.`user%2Eid` IS NOT NULL")
assert.Contains(t, sql, "mapContains(attributes_string, 'user.id')")
}
@@ -211,7 +211,7 @@ func TestColumnExpressionForAttributeJSON(t *testing.T) {
key := attrKey("user.id", telemetrytypes.FieldDataTypeString, evo)
got, err := querybuilder.ResolveColumn(ctx, qbtypes.QueryInfo{StartNs: attrWindowAfter[0], EndNs: attrWindowAfter[1]}, storage, &key, telemetrytypes.FieldDataTypeString, nil)
require.NoError(t, err)
assert.Equal(t, "multiIf(attributes.`user.id` IS NOT NULL, attributes.`user.id`::String, mapContains(attributes_string, 'attribute.user.id'), attributes_string['attribute.user.id'], NULL)", got)
assert.Equal(t, "multiIf(attributes.`user%2Eid` IS NOT NULL, attributes.`user%2Eid`::String, mapContains(attributes_string, 'attribute.user.id'), attributes_string['attribute.user.id'], NULL)", got)
})
t.Run("aggregation numeric", func(t *testing.T) {
@@ -260,9 +260,9 @@ func TestConditionForAttributeJSONTypeCollision(t *testing.T) {
sb.Where(sb.Or(conds...))
sql, _ := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
assert.Contains(t, sql, "toFloat64OrNull(attributes.`http.status_code`::String) = ?")
assert.Contains(t, sql, "toFloat64(if(dynamicType(attributes.`http.status_code`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`http.status_code`, 'Float64'), NULL)) = ?")
assert.Contains(t, sql, "attributes.`http.status_code` IS NOT NULL")
assert.Contains(t, sql, "toFloat64OrNull(attributes.`http%2Estatus_code`::String) = ?")
assert.Contains(t, sql, "toFloat64(if(dynamicType(attributes.`http%2Estatus_code`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`http%2Estatus_code`, 'Float64'), NULL)) = ?")
assert.Contains(t, sql, "attributes.`http%2Estatus_code` IS NOT NULL")
assert.NotEmpty(t, warnings, "a colliding name must surface the ambiguity warning")
}
@@ -286,7 +286,7 @@ func TestColumnExpressionForAttributeJSONTypeCollision(t *testing.T) {
got, err := querybuilder.ResolveColumn(ctx, qbtypes.QueryInfo{StartNs: attrWindowAfter[0], EndNs: attrWindowAfter[1]}, storage, &ref, telemetrytypes.FieldDataTypeString, fieldKeys)
require.NoError(t, err)
assert.Equal(t,
"multiIf(attributes.`http.status_code` IS NOT NULL, attributes.`http.status_code`::String, if(dynamicType(attributes.`http.status_code`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`http.status_code`, 'Float64'), NULL) IS NOT NULL, toString(if(dynamicType(attributes.`http.status_code`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`http.status_code`, 'Float64'), NULL)), NULL)",
"multiIf(attributes.`http%2Estatus_code` IS NOT NULL, attributes.`http%2Estatus_code`::String, if(dynamicType(attributes.`http%2Estatus_code`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`http%2Estatus_code`, 'Float64'), NULL) IS NOT NULL, toString(if(dynamicType(attributes.`http%2Estatus_code`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`http%2Estatus_code`, 'Float64'), NULL)), NULL)",
got)
}
@@ -310,7 +310,7 @@ func TestColumnExpressionForAttributeJSONTypeCollisionNumericAgg(t *testing.T) {
got, err := querybuilder.ResolveColumn(ctx, qbtypes.QueryInfo{StartNs: attrWindowAfter[0], EndNs: attrWindowAfter[1]}, storage, &ref, telemetrytypes.FieldDataTypeFloat64, fieldKeys)
require.NoError(t, err)
assert.Equal(t,
"multiIf(if(dynamicType(attributes.`http.status_code`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`http.status_code`, 'Float64'), NULL) IS NOT NULL, toFloat64(if(dynamicType(attributes.`http.status_code`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`http.status_code`, 'Float64'), NULL)), attributes.`http.status_code` IS NOT NULL, toFloat64OrNull(attributes.`http.status_code`::String), NULL)",
"multiIf(if(dynamicType(attributes.`http%2Estatus_code`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`http%2Estatus_code`, 'Float64'), NULL) IS NOT NULL, toFloat64(if(dynamicType(attributes.`http%2Estatus_code`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`http%2Estatus_code`, 'Float64'), NULL)), attributes.`http%2Estatus_code` IS NOT NULL, toFloat64OrNull(attributes.`http%2Estatus_code`::String), NULL)",
got)
}
@@ -379,13 +379,13 @@ func TestConditionForAttributeJSONNegativeOperatorParity(t *testing.T) {
t.Run("not equal number after -> NULL folded to 0", func(t *testing.T) {
key := attrKey("http.status_code", telemetrytypes.FieldDataTypeInt64, evo)
sql := build(t, key, attrWindowAfter, qbtypes.FilterOperatorNotEqual, float64(200))
assert.Contains(t, sql, "toFloat64(ifNull(if(dynamicType(attributes.`http.status_code`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`http.status_code`, 'Float64'), NULL), 0)) <> ?")
assert.Contains(t, sql, "toFloat64(ifNull(if(dynamicType(attributes.`http%2Estatus_code`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`http%2Estatus_code`, 'Float64'), NULL), 0)) <> ?")
})
t.Run("not equal bool after -> NULL folded to false", func(t *testing.T) {
key := attrKey("http.cache.hit", telemetrytypes.FieldDataTypeBool, evo)
sql := build(t, key, attrWindowAfter, qbtypes.FilterOperatorNotEqual, true)
assert.Contains(t, sql, "ifNull(if(dynamicType(attributes.`http.cache.hit`) = 'Bool', accurateCastOrNull(attributes.`http.cache.hit`, 'Bool'), NULL), false) <> ?")
assert.Contains(t, sql, "ifNull(if(dynamicType(attributes.`http%2Ecache%2Ehit`) = 'Bool', accurateCastOrNull(attributes.`http%2Ecache%2Ehit`, 'Bool'), NULL), false) <> ?")
})
// A numeric key compared to a non-numeric string is string-cast; the fold runs on the raw
@@ -394,27 +394,27 @@ func TestConditionForAttributeJSONNegativeOperatorParity(t *testing.T) {
t.Run("not equal number after, string value -> string cast over folded read, no type mismatch", func(t *testing.T) {
key := attrKey("http.status_code", telemetrytypes.FieldDataTypeInt64, evo)
sql := build(t, key, attrWindowAfter, qbtypes.FilterOperatorNotEqual, "teapot")
assert.Contains(t, sql, "toString(ifNull(if(dynamicType(attributes.`http.status_code`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`http.status_code`, 'Float64'), NULL), 0)) <> ?")
assert.Contains(t, sql, "toString(ifNull(if(dynamicType(attributes.`http%2Estatus_code`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`http%2Estatus_code`, 'Float64'), NULL), 0)) <> ?")
assert.NotContains(t, sql, "ifNull(toString(")
})
t.Run("equal number after -> not folded, exists guard excludes absent", func(t *testing.T) {
key := attrKey("http.status_code", telemetrytypes.FieldDataTypeInt64, evo)
sql := build(t, key, attrWindowAfter, qbtypes.FilterOperatorEqual, float64(0))
assert.Contains(t, sql, "toFloat64(if(dynamicType(attributes.`http.status_code`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`http.status_code`, 'Float64'), NULL)) = ?")
assert.Contains(t, sql, "toFloat64(if(dynamicType(attributes.`http%2Estatus_code`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`http%2Estatus_code`, 'Float64'), NULL)) = ?")
assert.NotContains(t, sql, "ifNull")
})
t.Run("not in number after -> each operand folded to 0", func(t *testing.T) {
key := attrKey("http.status_code", telemetrytypes.FieldDataTypeInt64, evo)
sql := build(t, key, attrWindowAfter, qbtypes.FilterOperatorNotIn, []any{float64(200), float64(404)})
assert.Contains(t, sql, "(toFloat64(ifNull(if(dynamicType(attributes.`http.status_code`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`http.status_code`, 'Float64'), NULL), 0)) <> ? AND toFloat64(ifNull(if(dynamicType(attributes.`http.status_code`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`http.status_code`, 'Float64'), NULL), 0)) <> ?)")
assert.Contains(t, sql, "(toFloat64(ifNull(if(dynamicType(attributes.`http%2Estatus_code`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`http%2Estatus_code`, 'Float64'), NULL), 0)) <> ? AND toFloat64(ifNull(if(dynamicType(attributes.`http%2Estatus_code`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`http%2Estatus_code`, 'Float64'), NULL), 0)) <> ?)")
})
t.Run("not equal number straddle -> whole multiIf folded", func(t *testing.T) {
key := attrKey("http.status_code", telemetrytypes.FieldDataTypeInt64, evo)
sql := build(t, key, attrWindowStraddle, qbtypes.FilterOperatorNotEqual, float64(200))
assert.Contains(t, sql, "toFloat64(ifNull(multiIf(if(dynamicType(attributes.`http.status_code`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`http.status_code`, 'Float64'), NULL) IS NOT NULL, if(dynamicType(attributes.`http.status_code`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`http.status_code`, 'Float64'), NULL), mapContains(attributes_number, 'http.status_code'), attributes_number['http.status_code'], NULL), 0)) <> ?")
assert.Contains(t, sql, "toFloat64(ifNull(multiIf(if(dynamicType(attributes.`http%2Estatus_code`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`http%2Estatus_code`, 'Float64'), NULL) IS NOT NULL, if(dynamicType(attributes.`http%2Estatus_code`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`http%2Estatus_code`, 'Float64'), NULL), mapContains(attributes_number, 'http.status_code'), attributes_number['http.status_code'], NULL), 0)) <> ?")
})
t.Run("not equal number before -> harmless fold over the map read", func(t *testing.T) {
@@ -433,7 +433,7 @@ func TestConditionForAttributeJSONNegativeOperatorParity(t *testing.T) {
t.Run("not equal string after -> '' default, never folded", func(t *testing.T) {
key := attrKey("user.id", telemetrytypes.FieldDataTypeString, evo)
sql := build(t, key, attrWindowAfter, qbtypes.FilterOperatorNotEqual, "admin")
assert.Contains(t, sql, "attributes.`user.id`::String <> ?")
assert.Contains(t, sql, "attributes.`user%2Eid`::String <> ?")
assert.NotContains(t, sql, "ifNull")
})
}
@@ -456,7 +456,7 @@ func TestConditionForAttributeJSONStraddleAbsentKeyExclusion(t *testing.T) {
return sql
}
guard := "multiIf(if(dynamicType(attributes.`http.status_code`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`http.status_code`, 'Float64'), NULL) IS NOT NULL, if(dynamicType(attributes.`http.status_code`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`http.status_code`, 'Float64'), NULL), mapContains(attributes_number, 'http.status_code'), attributes_number['http.status_code'], NULL) IS NOT NULL"
guard := "multiIf(if(dynamicType(attributes.`http%2Estatus_code`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`http%2Estatus_code`, 'Float64'), NULL) IS NOT NULL, if(dynamicType(attributes.`http%2Estatus_code`) IN ('Int64', 'UInt64', 'Float64'), accurateCastOrNull(attributes.`http%2Estatus_code`, 'Float64'), NULL), mapContains(attributes_number, 'http.status_code'), attributes_number['http.status_code'], NULL) IS NOT NULL"
t.Run("equal zero takes no guard: the absent read is NULL", func(t *testing.T) {
key := attrKey("http.status_code", telemetrytypes.FieldDataTypeInt64, evo)

View File

@@ -39,10 +39,10 @@ func TestFieldForAttributePromotedEvolution(t *testing.T) {
expected string
}{
{"before json rollout -> map", win("2024-01-01", "2024-06-01"), "attributes_string['span.operation']"},
{"between json and promotion -> attributes", win("2025-02-01", "2025-04-01"), "attributes.`span.operation`::String"},
{"after promotion -> promoted only", win("2025-07-01", "2025-08-01"), "attributes_promoted.`span.operation`::String"},
{"straddle promotion -> attributes_promoted + attributes", win("2025-04-01", "2025-08-01"), "multiIf(attributes_promoted.`span.operation` IS NOT NULL, attributes_promoted.`span.operation`::String, attributes.`span.operation` IS NOT NULL, attributes.`span.operation`::String, NULL)"},
{"straddle json rollout -> attributes + map", win("2024-06-01", "2025-03-01"), "multiIf(attributes.`span.operation` IS NOT NULL, attributes.`span.operation`::String, mapContains(attributes_string, 'span.operation'), attributes_string['span.operation'], NULL)"},
{"between json and promotion -> attributes", win("2025-02-01", "2025-04-01"), "attributes.`span%2Eoperation`::String"},
{"after promotion -> promoted only", win("2025-07-01", "2025-08-01"), "attributes_promoted.`span%2Eoperation`::String"},
{"straddle promotion -> attributes_promoted + attributes", win("2025-04-01", "2025-08-01"), "multiIf(attributes_promoted.`span%2Eoperation` IS NOT NULL, attributes_promoted.`span%2Eoperation`::String, attributes.`span%2Eoperation` IS NOT NULL, attributes.`span%2Eoperation`::String, NULL)"},
{"straddle json rollout -> attributes + map", win("2024-06-01", "2025-03-01"), "multiIf(attributes.`span%2Eoperation` IS NOT NULL, attributes.`span%2Eoperation`::String, mapContains(attributes_string, 'span.operation'), attributes_string['span.operation'], NULL)"},
}
for _, tc := range testCases {
@@ -85,8 +85,8 @@ func TestConditionForAttributePromoted(t *testing.T) {
require.NoError(t, err)
sb.Where(conds...)
sql, _ := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
assert.Contains(t, sql, "(attributes_promoted.`span.operation`::String = ? AND attributes_promoted.`span.operation` IS NOT NULL)")
assert.NotContains(t, sql, "attributes.`span.operation`")
assert.Contains(t, sql, "(attributes_promoted.`span%2Eoperation`::String = ? AND attributes_promoted.`span%2Eoperation` IS NOT NULL)")
assert.NotContains(t, sql, "attributes.`span%2Eoperation`")
})
t.Run("exists uses promoted raw path", func(t *testing.T) {
@@ -95,6 +95,6 @@ func TestConditionForAttributePromoted(t *testing.T) {
require.NoError(t, err)
sb.Where(conds...)
sql, _ := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
assert.Contains(t, sql, "attributes_promoted.`span.operation` IS NOT NULL")
assert.Contains(t, sql, "attributes_promoted.`span%2Eoperation` IS NOT NULL")
})
}

View File

@@ -68,7 +68,7 @@ func TestGetFieldKeyName(t *testing.T) {
FieldContext: telemetrytypes.FieldContextResource,
Evolutions: mockEvolution,
},
expectedResult: "multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)",
expectedResult: "multiIf(resource.`service%2Ename` IS NOT NULL, resource.`service%2Ename`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)",
expectedError: nil,
},
{
@@ -80,7 +80,7 @@ func TestGetFieldKeyName(t *testing.T) {
Materialized: true,
Evolutions: mockEvolution,
},
expectedResult: "multiIf(resource.`deployment.environment` IS NOT NULL, resource.`deployment.environment`::String, `resource_string_deployment$$environment_exists`, `resource_string_deployment$$environment`, NULL)",
expectedResult: "multiIf(resource.`deployment%2Eenvironment` IS NOT NULL, resource.`deployment%2Eenvironment`::String, `resource_string_deployment$$environment_exists`, `resource_string_deployment$$environment`, NULL)",
expectedError: nil,
},
{
@@ -107,7 +107,7 @@ func TestGetFieldKeyName(t *testing.T) {
Name: "custom.attr",
FieldContext: telemetrytypes.FieldContextScope,
},
expectedResult: "scope.attributes.`custom.attr`::String",
expectedResult: "scope.attributes.`custom%2Eattr`::String",
expectedError: nil,
},
{
@@ -180,7 +180,7 @@ func TestFieldForResourceWithEvolution(t *testing.T) {
},
tsStart: uint64(time.Date(2024, 6, 1, 0, 0, 0, 0, time.UTC).UnixNano()),
tsEnd: uint64(time.Date(2025, 6, 1, 0, 0, 0, 0, time.UTC).UnixNano()),
expectedResult: "multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)",
expectedResult: "multiIf(resource.`service%2Ename` IS NOT NULL, resource.`service%2Ename`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL)",
},
{
name: "Window fully after release - JSON column only",
@@ -191,7 +191,7 @@ func TestFieldForResourceWithEvolution(t *testing.T) {
},
tsStart: uint64(time.Date(2025, 6, 1, 0, 0, 0, 0, time.UTC).UnixNano()),
tsEnd: uint64(time.Date(2025, 7, 1, 0, 0, 0, 0, time.UTC).UnixNano()),
expectedResult: "resource.`service.name`::String",
expectedResult: "resource.`service%2Ename`::String",
},
{
name: "Window fully before release - map column only",
@@ -215,7 +215,7 @@ func TestFieldForResourceWithEvolution(t *testing.T) {
},
tsStart: uint64(time.Date(2025, 6, 1, 0, 0, 0, 0, time.UTC).UnixNano()),
tsEnd: uint64(time.Date(2025, 7, 1, 0, 0, 0, 0, time.UTC).UnixNano()),
expectedResult: "resource.`deployment.environment`::String",
expectedResult: "resource.`deployment%2Eenvironment`::String",
},
{
name: "Window straddles release - materialized resource",
@@ -228,7 +228,7 @@ func TestFieldForResourceWithEvolution(t *testing.T) {
},
tsStart: uint64(time.Date(2024, 6, 1, 0, 0, 0, 0, time.UTC).UnixNano()),
tsEnd: uint64(time.Date(2025, 6, 1, 0, 0, 0, 0, time.UTC).UnixNano()),
expectedResult: "multiIf(resource.`deployment.environment` IS NOT NULL, resource.`deployment.environment`::String, `resource_string_deployment$$environment_exists`, `resource_string_deployment$$environment`, NULL)",
expectedResult: "multiIf(resource.`deployment%2Eenvironment` IS NOT NULL, resource.`deployment%2Eenvironment`::String, `resource_string_deployment$$environment_exists`, `resource_string_deployment$$environment`, NULL)",
},
}
@@ -402,7 +402,7 @@ func TestColumnExpressionForScopeDeclaredPath(t *testing.T) {
name: "attribute prefix reaches the named scope attribute",
key: telemetrytypes.TelemetryFieldKey{Name: "attribute.name", FieldContext: telemetrytypes.FieldContextScope},
keys: withAttr,
expectedResult: "multiIf(scope.attributes.`name` IS NOT NULL, scope.attributes.`name`::String, scope.attributes.`scope.attribute.name` IS NOT NULL, scope.attributes.`scope.attribute.name`::String, NULL)",
expectedResult: "multiIf(scope.attributes.`name` IS NOT NULL, scope.attributes.`name`::String, scope.attributes.`scope%2Eattribute%2Ename` IS NOT NULL, scope.attributes.`scope%2Eattribute%2Ename`::String, NULL)",
},
{
// the caller supplied the context, so `scope.` is part of the name rather than a
@@ -411,7 +411,7 @@ func TestColumnExpressionForScopeDeclaredPath(t *testing.T) {
name: "explicit context keeps a scope-prefixed name intact",
key: telemetrytypes.TelemetryFieldKey{Name: "scope.testing.env", FieldContext: telemetrytypes.FieldContextScope},
keys: declaredOnly,
expectedResult: "multiIf(scope.attributes.`scope.testing.env` IS NOT NULL, scope.attributes.`scope.testing.env`::String, scope.attributes.`scope.scope.testing.env` IS NOT NULL, scope.attributes.`scope.scope.testing.env`::String, NULL)",
expectedResult: "multiIf(scope.attributes.`scope%2Etesting%2Eenv` IS NOT NULL, scope.attributes.`scope%2Etesting%2Eenv`::String, scope.attributes.`scope%2Escope%2Etesting%2Eenv` IS NOT NULL, scope.attributes.`scope%2Escope%2Etesting%2Eenv`::String, NULL)",
},
{
// metadata knows both homes under this name, so the short spelling coalesces

View File

@@ -99,6 +99,10 @@ func New(ctx context.Context, providerSettings factory.ProviderSettings, config
options.DialTimeout = config.Connection.DialTimeout
// This is to avoid the driver decoding issues with JSON columns
options.Settings["output_format_native_write_json_as_string"] = 1
// Attribute keys are ingested with dots escaped to %2E so a dotted key (e.g. "db.function")
// stays one JSON path instead of splitting into nested paths; unescape them back to dotted
// keys when a JSON column is serialized to a document on read.
options.Settings["json_type_escape_dots_in_keys"] = 1
chConn, err := clickhouse.Open(options)
if err != nil {