refactor(qb): quote field names with the ClickHouse quoting helpers

Every plain field-name literal and identifier in the statement-builder
layer now goes through querybuilder.ClickHouseStringLiteral and
querybuilder.ClickHouseIdentifier: map reads, mapContains, JSON
subcolumn paths, JSONExtractString and JSONExtractKeys on labels,
simpleJSONExtractString and simpleJSONHas on the fingerprint labels,
and the column aliases.

The helpers escape backslashes, quotes, and backticks, so a field name
that contains a quote or a backtick can no longer break out of its
literal or identifier. For every other name the output is byte
identical, and the full test suite passes unchanged.

Out of scope, on purpose: LIKE index-hint fragments and body JSON path
builders (they have pattern and path semantics, not plain literals),
and the materialized-column name builders in telemetrytypes (importing
querybuilder there is an import cycle).

Assisted-by: Claude Fable 5

pkg/modules/rulestatehistory/implrulestatehistory/field_mapper.go

@@ -88,5 +88,5 @@ func (m *fieldMapper) ColumnExpressionFor(ctx context.Context, orgID valuer.UUID
 	if err != nil {
 		return "", err
 	}
-	return fmt.Sprintf("%s AS `%s`", sqlbuilder.Escape(colName), field.Name), nil
+	return fmt.Sprintf("%s AS %s", sqlbuilder.Escape(colName), querybuilder.ClickHouseIdentifier(field.Name)), nil
 }

pkg/querybuilder/exists_expr.go

@@ -43,7 +43,7 @@ func ExistsExpression(columns []*schema.Column, key *telemetrytypes.TelemetryFie
 		if len(evolutionsEntries) > 0 && evolutionsEntries[0] != nil {
 			columnName = evolutionsEntries[0].ColumnName
 		}
-		rawPath := fmt.Sprintf("%s.`%s`", columnName, key.Name)
+		rawPath := fmt.Sprintf("%s.%s", columnName, ClickHouseIdentifier(key.Name))
 		if exists {
 			return rawPath + " IS NOT NULL", nil
 		}
@@ -88,7 +88,7 @@ func ExistsExpression(columns []*schema.Column, key *telemetrytypes.TelemetryFie
 
 		switch valueType := column.Type.(schema.MapColumnType).ValueType; valueType.GetType() {
 		case schema.ColumnTypeEnumString, schema.ColumnTypeEnumBool, schema.ColumnTypeEnumFloat64:
-			leftOperand := fmt.Sprintf("mapContains(%s, '%s')", column.Name, key.Name)
+			leftOperand := fmt.Sprintf("mapContains(%s, %s)", column.Name, ClickHouseStringLiteral(key.Name))
 			if key.Materialized {
 				leftOperand = telemetrytypes.FieldKeyToMaterializedColumnNameForExists(key)
 			}

pkg/statementbuilder/resourcefilter/condition_builder.go

@@ -96,7 +96,7 @@ func valueIndexCondition(
 func memberPresenceCondition(sb *sqlbuilder.SelectBuilder, column string, members []*telemetrytypes.TelemetryFieldKey, exists bool) string {
 	conditions := make([]string, 0, len(members))
 	for _, member := range members {
-		field := fmt.Sprintf("simpleJSONHas(%s, '%s')", column, member.Name)
+		field := fmt.Sprintf("simpleJSONHas(%s, %s)", column, querybuilder.ClickHouseStringLiteral(member.Name))
 		if exists {
 			conditions = append(conditions, sb.E(field, true))
 		} else {

pkg/statementbuilder/resourcefilter/field_mapper.go

@@ -5,6 +5,7 @@ import (
 	"fmt"
 
 	schema "github.com/SigNoz/signoz-otel-collector/cmd/signozschemamigrator/schema_migrator"
+	"github.com/SigNoz/signoz/pkg/querybuilder"
 	qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
 	"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
 	"github.com/SigNoz/signoz/pkg/valuer"
@@ -66,7 +67,7 @@ func (m *defaultFieldMapper) FieldFor(
 		return "", err
 	}
 	if key.FieldContext == telemetrytypes.FieldContextResource {
-		return fmt.Sprintf("simpleJSONExtractString(%s, '%s')", columns[0].Name, key.Name), nil
+		return fmt.Sprintf("simpleJSONExtractString(%s, %s)", columns[0].Name, querybuilder.ClickHouseStringLiteral(key.Name)), nil
 	}
 	return columns[0].Name, nil
 }
@@ -91,7 +92,7 @@ func (m *defaultFieldMapper) ExistsFor(
 		}
 		return "false", nil
 	}
-	pred := fmt.Sprintf("simpleJSONHas(%s, '%s')", columns[0].Name, key.Name)
+	pred := fmt.Sprintf("simpleJSONHas(%s, %s)", columns[0].Name, querybuilder.ClickHouseStringLiteral(key.Name))
 	if exists {
 		return pred, nil
 	}
@@ -110,5 +111,5 @@ func (m *defaultFieldMapper) ColumnExpressionFor(
 	if err != nil {
 		return "", err
 	}
-	return fmt.Sprintf("%s AS `%s`", fieldExpression, key.Name), nil
+	return fmt.Sprintf("%s AS %s", fieldExpression, querybuilder.ClickHouseIdentifier(key.Name)), nil
 }

pkg/telemetrymetadata/condition_builder.go

@@ -168,7 +168,7 @@ func (c *conditionBuilder) conditionForKey(
 			KeyType:   schema.LowCardinalityColumnType{ElementType: schema.ColumnTypeString},
 			ValueType: schema.ColumnTypeString,
 		}:
-			leftOperand := fmt.Sprintf("mapContains(%s, '%s')", columns[0].Name, key.Name)
+			leftOperand := fmt.Sprintf("mapContains(%s, %s)", columns[0].Name, querybuilder.ClickHouseStringLiteral(key.Name))
 			if operator == qbtypes.FilterOperatorExists {
 				cond = sb.E(leftOperand, true)
 			} else {

pkg/telemetrymetadata/field_mapper.go

@@ -7,6 +7,7 @@ import (
 
 	schema "github.com/SigNoz/signoz-otel-collector/cmd/signozschemamigrator/schema_migrator"
 	"github.com/SigNoz/signoz/pkg/errors"
+	"github.com/SigNoz/signoz/pkg/querybuilder"
 	qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
 	"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
 	"github.com/SigNoz/signoz/pkg/valuer"
@@ -64,7 +65,7 @@ func (m *fieldMapper) ExistsFor(ctx context.Context, _ valuer.UUID, tsStart, tsE
 	if err != nil {
 		return "", err
 	}
-	pred := fmt.Sprintf("mapContains(%s, '%s')", columns[0].Name, key.Name)
+	pred := fmt.Sprintf("mapContains(%s, %s)", columns[0].Name, querybuilder.ClickHouseStringLiteral(key.Name))
 	if exists {
 		return pred, nil
 	}
@@ -82,7 +83,7 @@ func (m *fieldMapper) FieldFor(ctx context.Context, _ valuer.UUID, startNs, endN
 		KeyType:   schema.LowCardinalityColumnType{ElementType: schema.ColumnTypeString},
 		ValueType: schema.ColumnTypeString,
 	}:
-		return fmt.Sprintf("%s['%s']", columns[0].Name, key.Name), nil
+		return fmt.Sprintf("%s[%s]", columns[0].Name, querybuilder.ClickHouseStringLiteral(key.Name)), nil
 	}
 	return columns[0].Name, nil
 }
@@ -130,5 +131,5 @@ func (m *fieldMapper) ColumnExpressionFor(
 		}
 	}
 
-	return fmt.Sprintf("%s AS `%s`", sqlbuilder.Escape(fieldExpression), field.Name), nil
+	return fmt.Sprintf("%s AS %s", sqlbuilder.Escape(fieldExpression), querybuilder.ClickHouseIdentifier(field.Name)), nil
 }

pkg/telemetryschema/audittelemetryschema/field_mapper.go

@@ -68,7 +68,7 @@ func (m *fieldMapper) FieldFor(ctx context.Context, _ valuer.UUID, _, _ uint64,
 		if key.FieldContext != telemetrytypes.FieldContextResource {
 			return "", errors.NewInvalidInputf(errors.CodeInvalidInput, "only resource context fields are supported for json columns in audit, got %s", key.FieldContext.String)
 		}
-		return fmt.Sprintf("%s.`%s`::String", column.Name, key.Name), nil
+		return fmt.Sprintf("%s.%s::String", column.Name, querybuilder.ClickHouseIdentifier(key.Name)), nil
 	case schema.ColumnTypeEnumLowCardinality:
 		return column.Name, nil
 	case schema.ColumnTypeEnumString, schema.ColumnTypeEnumUInt64, schema.ColumnTypeEnumUInt32, schema.ColumnTypeEnumUInt8:
@@ -84,7 +84,7 @@ func (m *fieldMapper) FieldFor(ctx context.Context, _ valuer.UUID, _, _ uint64,
 			if key.Materialized {
 				return telemetrytypes.FieldKeyToMaterializedColumnName(key), nil
 			}
-			return fmt.Sprintf("%s['%s']", column.Name, key.Name), nil
+			return fmt.Sprintf("%s[%s]", column.Name, querybuilder.ClickHouseStringLiteral(key.Name)), nil
 		default:
 			return "", errors.NewInvalidInputf(errors.CodeInvalidInput, "unsupported map value type %s", valueType)
 		}
@@ -156,7 +156,7 @@ func (m *fieldMapper) ColumnExpressionFor(
 		return fmt.Sprintf("multiIf(%s, %s, NULL)", guard, coerced), nil
 	}
 
-	return fmt.Sprintf("%s AS `%s`", sqlbuilder.Escape(fieldExpression), field.Name), nil
+	return fmt.Sprintf("%s AS %s", sqlbuilder.Escape(fieldExpression), querybuilder.ClickHouseIdentifier(field.Name)), nil
 }
 
 // CandidateKeys returns nil: audit has no synthesize-on-unknown-key fallback, so an

pkg/telemetryschema/logstelemetryschema/field_mapper.go

@@ -141,8 +141,8 @@ func (m *fieldMapper) FieldFor(ctx context.Context, orgID valuer.UUID, tsStart,
 		case schema.ColumnTypeEnumJSON:
 			switch key.FieldContext {
 			case telemetrytypes.FieldContextResource:
-				exprs = append(exprs, fmt.Sprintf("%s.`%s`::String", columnName, key.Name))
-				existExpr = append(existExpr, fmt.Sprintf("%s.`%s` IS NOT NULL", columnName, key.Name))
+				exprs = append(exprs, fmt.Sprintf("%s.%s::String", columnName, querybuilder.ClickHouseIdentifier(key.Name)))
+				existExpr = append(existExpr, fmt.Sprintf("%s.%s IS NOT NULL", columnName, querybuilder.ClickHouseIdentifier(key.Name)))
 			case telemetrytypes.FieldContextBody:
 				if key.Name == messageSubField {
 					exprs = append(exprs, messageSubColumn)
@@ -186,8 +186,8 @@ func (m *fieldMapper) FieldFor(ctx context.Context, orgID valuer.UUID, tsStart,
 					exprs = append(exprs, telemetrytypes.FieldKeyToMaterializedColumnName(key))
 					existExpr = append(existExpr, telemetrytypes.FieldKeyToMaterializedColumnNameForExists(key))
 				} else {
-					exprs = append(exprs, fmt.Sprintf("%s['%s']", columnName, key.Name))
-					existExpr = append(existExpr, fmt.Sprintf("mapContains(%s, '%s')", columnName, key.Name))
+					exprs = append(exprs, fmt.Sprintf("%s[%s]", columnName, querybuilder.ClickHouseStringLiteral(key.Name)))
+					existExpr = append(existExpr, fmt.Sprintf("mapContains(%s, %s)", columnName, querybuilder.ClickHouseStringLiteral(key.Name)))
 				}
 			default:
 				return "", errors.NewInvalidInputf(errors.CodeInvalidInput, "exists operator is not supported for map column type %s", valueType)
@@ -415,7 +415,7 @@ func (m *fieldMapper) buildFieldForJSON(key *telemetrytypes.TelemetryFieldKey) (
 			elemType = telemetrytypes.String
 		}
 
-		fieldPath := fmt.Sprintf("%s.`%s`", LogsV2BodyV2Column, key.Name)
+		fieldPath := fmt.Sprintf("%s.%s", LogsV2BodyV2Column, querybuilder.ClickHouseIdentifier(key.Name))
 		return fmt.Sprintf("dynamicElement(%s, '%s')", fieldPath, elemType.StringValue()), nil
 	}
 

pkg/telemetryschema/logstelemetryschema/json_condition_builder.go

@@ -41,7 +41,7 @@ func (c *jsonConditionBuilder) buildJSONCondition(operator qbtypes.FilterOperato
 
 	// path index
 	if operator.AddDefaultExistsFilter() {
-		pathIndex := fmt.Sprintf(`has(%s, '%s')`, schemamigrator.JSONPathsIndexExpr(LogsV2BodyV2Column), c.key.ArrayParentPaths()[0])
+		pathIndex := fmt.Sprintf(`has(%s, %s)`, schemamigrator.JSONPathsIndexExpr(LogsV2BodyV2Column), querybuilder.ClickHouseStringLiteral(c.key.ArrayParentPaths()[0]))
 		return sb.And(baseCond, pathIndex), nil
 	}
 

pkg/telemetryschema/metricstelemetryschema/condition_builder.go

@@ -136,9 +136,9 @@ func (c *conditionBuilder) conditionFor(
 		}
 
 		if operator == qbtypes.FilterOperatorExists {
-			return fmt.Sprintf("has(JSONExtractKeys(labels), '%s')", key.Name), nil
+			return fmt.Sprintf("has(JSONExtractKeys(labels), %s)", querybuilder.ClickHouseStringLiteral(key.Name)), nil
 		}
-		return fmt.Sprintf("not has(JSONExtractKeys(labels), '%s')", key.Name), nil
+		return fmt.Sprintf("not has(JSONExtractKeys(labels), %s)", querybuilder.ClickHouseStringLiteral(key.Name)), nil
 	}
 	return "", errors.NewInvalidInputf(errors.CodeInvalidInput, "unsupported operator: %v", operator)
 }

pkg/telemetryschema/metricstelemetryschema/field_mapper.go

@@ -6,6 +6,7 @@ import (
 	"slices"
 
 	schema "github.com/SigNoz/signoz-otel-collector/cmd/signozschemamigrator/schema_migrator"
+	"github.com/SigNoz/signoz/pkg/querybuilder"
 	qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
 	"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
 	"github.com/SigNoz/signoz/pkg/valuer"
@@ -79,14 +80,14 @@ func (m *fieldMapper) FieldFor(ctx context.Context, _ valuer.UUID, startNs, endN
 
 	switch key.FieldContext {
 	case telemetrytypes.FieldContextResource, telemetrytypes.FieldContextScope, telemetrytypes.FieldContextAttribute:
-		return fmt.Sprintf("JSONExtractString(%s, '%s')", columns[0].Name, key.Name), nil
+		return fmt.Sprintf("JSONExtractString(%s, %s)", columns[0].Name, querybuilder.ClickHouseStringLiteral(key.Name)), nil
 	case telemetrytypes.FieldContextMetric:
 		return columns[0].Name, nil
 	case telemetrytypes.FieldContextUnspecified:
 		if slices.Contains(IntrinsicFields, key.Name) {
 			return columns[0].Name, nil
 		}
-		return fmt.Sprintf("JSONExtractString(%s, '%s')", columns[0].Name, key.Name), nil
+		return fmt.Sprintf("JSONExtractString(%s, %s)", columns[0].Name, querybuilder.ClickHouseStringLiteral(key.Name)), nil
 	}
 
 	return columns[0].Name, nil
@@ -103,9 +104,9 @@ func (m *fieldMapper) ExistsFor(_ context.Context, _ valuer.UUID, _, _ uint64, k
 		return "true", nil
 	}
 	if exists {
-		return fmt.Sprintf("has(JSONExtractKeys(labels), '%s')", key.Name), nil
+		return fmt.Sprintf("has(JSONExtractKeys(labels), %s)", querybuilder.ClickHouseStringLiteral(key.Name)), nil
 	}
-	return fmt.Sprintf("not has(JSONExtractKeys(labels), '%s')", key.Name), nil
+	return fmt.Sprintf("not has(JSONExtractKeys(labels), %s)", querybuilder.ClickHouseStringLiteral(key.Name)), nil
 }
 
 func (m *fieldMapper) ColumnExpressionFor(

pkg/telemetryschema/tracestelemetryschema/field_mapper.go

@@ -298,8 +298,8 @@ func (m *fieldMapper) resolveColumnExprs(
 			}
 			// have to add ::string as clickHouse throws an error :- data types Variant/Dynamic are not allowed in GROUP BY
 			// once clickHouse dependency is updated, we need to check if we can remove it.
-			exprs = append(exprs, fmt.Sprintf("%s.`%s`::String", columnName, key.Name))
-			existExprs = append(existExprs, fmt.Sprintf("%s.`%s` IS NOT NULL", columnName, key.Name))
+			exprs = append(exprs, fmt.Sprintf("%s.%s::String", columnName, querybuilder.ClickHouseIdentifier(key.Name)))
+			existExprs = append(existExprs, fmt.Sprintf("%s.%s IS NOT NULL", columnName, querybuilder.ClickHouseIdentifier(key.Name)))
 		case schema.ColumnTypeEnumString,
 			schema.ColumnTypeEnumUInt64,
 			schema.ColumnTypeEnumUInt32,
@@ -329,8 +329,8 @@ func (m *fieldMapper) resolveColumnExprs(
 					exprs = append(exprs, telemetrytypes.FieldKeyToMaterializedColumnName(key))
 					existExprs = append(existExprs, telemetrytypes.FieldKeyToMaterializedColumnNameForExists(key))
 				} else {
-					exprs = append(exprs, fmt.Sprintf("%s['%s']", columnName, key.Name))
-					existExprs = append(existExprs, fmt.Sprintf("mapContains(%s, '%s')", columnName, key.Name))
+					exprs = append(exprs, fmt.Sprintf("%s[%s]", columnName, querybuilder.ClickHouseStringLiteral(key.Name)))
+					existExprs = append(existExprs, fmt.Sprintf("mapContains(%s, %s)", columnName, querybuilder.ClickHouseStringLiteral(key.Name)))
 				}
 			default:
 				return nil, nil, nil, errors.NewInvalidInputf(errors.CodeInvalidInput, "value type %s is not supported for map column type %s", valueType, column.Type)

tests/conftest.py

@@ -19,7 +19,6 @@ pytest_plugins = [
     "fixtures.traces",
     "fixtures.metrics",
     "fixtures.queriercommon",
-    "fixtures.semconvfamilies",
     "fixtures.metadata",
     "fixtures.meter",
     "fixtures.browser",

tests/fixtures/semconvfamilies.py

@@ -1,75 +0,0 @@
-"""Seed data for the semconv family matrix tests.
-
-Four identities cover every fleet state of the deployment.environment(.name)
-family. The tests assert which identities a filter returns, so BOTH (a row
-that carries the two spellings with different values) and NEITHER (a keyless
-row) are the point of most cases.
-
-Each row carries its family pairs in the resource attributes and in the span
-attributes, so one fleet serves the resource-context and attribute-context
-matrices. The same rows exist as logs for the logs literalness guard.
-"""
-
-from collections.abc import Callable, Generator
-from datetime import UTC, datetime, timedelta
-
-import pytest
-
-from fixtures.logs import Logs
-from fixtures.traces import TraceIdGenerator, Traces, TracesKind, TracesStatusCode
-
-PREFIX = "semconv-fam"
-CURRENT_KEY = "deployment.environment.name"
-OLD_KEY = "deployment.environment"
-
-# Row identities. The span name, the log body, and service.name are the identity.
-OLD = f"{PREFIX}-old"  # only the old spelling, value "production"
-NEW = f"{PREFIX}-new"  # only the current spelling, value "production"
-BOTH = f"{PREFIX}-both"  # current "staging" and old "production" - the conflict row
-NEITHER = f"{PREFIX}-neither"  # no member at all
-
-_ROWS = [
-    (OLD, {OLD_KEY: "production"}, timedelta(seconds=4)),
-    (NEW, {CURRENT_KEY: "production"}, timedelta(seconds=3)),
-    (BOTH, {CURRENT_KEY: "staging", OLD_KEY: "production"}, timedelta(seconds=2)),
-    (NEITHER, {}, timedelta(seconds=1)),
-]
-
-
-@pytest.fixture(name="family_fleet", scope="function")
-def family_fleet(
-    insert_logs: Callable[[list[Logs]], None],
-    insert_traces: Callable[[list[Traces]], None],
-) -> Generator[datetime]:
-    """Inserts one span and one log per identity and yields the base
-    timestamp."""
-    now = datetime.now(tz=UTC).replace(microsecond=0) - timedelta(minutes=1)
-
-    insert_traces(
-        [
-            Traces(
-                timestamp=now - offset,
-                duration=timedelta(milliseconds=10),
-                trace_id=TraceIdGenerator.trace_id(),
-                span_id=TraceIdGenerator.span_id(),
-                name=identity,
-                kind=TracesKind.SPAN_KIND_SERVER,
-                status_code=TracesStatusCode.STATUS_CODE_OK,
-                resources={"service.name": identity, **family},
-                attributes=dict(family),
-            )
-            for identity, family, offset in _ROWS
-        ]
-    )
-    insert_logs(
-        [
-            Logs(
-                timestamp=now - offset,
-                body=identity,
-                resources={"service.name": identity, **family},
-                attributes=dict(family),
-            )
-            for identity, family, offset in _ROWS
-        ]
-    )
-    yield now

tests/integration/tests/semconvfamilies/01_family_matrix.py

@@ -1,220 +0,0 @@
-"""The phase-1 matrix for semantic-convention family resolution.
-
-The package runs SigNoz with resolve_semconv_families on. The fleet in
-fixtures/semconvfamilies.py has one identity per state: OLD (old spelling
-only), NEW (current only), BOTH (current "staging" and old "production"),
-NEITHER (keyless). Each case asserts which identities a filter returns, with
-either spelling as the requested name and for both contexts.
-
-The pinned facts:
-  - Both spellings resolve to the same merged field; the result sets do not
-    depend on the requested spelling.
-  - The current spelling wins on a row that carries both (BOTH reads
-    "staging", never "production").
-  - Negative operators keep keyless rows (NEITHER), exactly like a single
-    key; presence stays an explicit EXISTS opt-in.
-  - Logs stay literal: only traces have family support today.
-  - With the flag off, everything stays literal.
-"""
-
-from collections.abc import Callable
-from datetime import datetime, timedelta
-from http import HTTPStatus
-
-import pytest
-
-from fixtures import types
-from fixtures.auth import USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD
-from fixtures.querier import (
-    RequestType,
-    build_aggregation,
-    build_group_by_field,
-    build_order_by,
-    build_raw_query,
-    build_traces_scalar_query,
-    get_column_data_from_response,
-    make_query_request,
-)
-from fixtures.semconvfamilies import (
-    BOTH,
-    CURRENT_KEY,
-    NEITHER,
-    NEW,
-    OLD,
-    OLD_KEY,
-    PREFIX,
-)
-
-FILTER_MATRIX = [
-    pytest.param("{key} = 'production'", {OLD, NEW}, id="eq_matches_either_spelling"),
-    pytest.param("{key} = 'staging'", {BOTH}, id="eq_current_wins_on_conflict"),
-    pytest.param("{key} != 'production'", {BOTH, NEITHER}, id="neq_keeps_keyless_and_conflict"),
-    pytest.param("{key} IN ['production', 'staging']", {OLD, NEW, BOTH}, id="in_matches_merged_value"),
-    pytest.param("{key} NOT IN ['production']", {BOTH, NEITHER}, id="not_in_keeps_keyless"),
-    pytest.param("{key} LIKE '%prod%'", {OLD, NEW}, id="like_matches_merged_value"),
-    pytest.param("{key} EXISTS", {OLD, NEW, BOTH}, id="exists_is_any_member"),
-    pytest.param("{key} NOT EXISTS", {NEITHER}, id="not_exists_is_no_member"),
-    pytest.param("{key} != 'production' AND {key} EXISTS", {BOTH}, id="neq_composed_with_exists"),
-]
-
-LITERAL_MATRIX = [
-    pytest.param("{key} = 'production'", {NEW}, id="literal_eq_reads_one_spelling"),
-    pytest.param("{key} != 'production'", {OLD, BOTH, NEITHER}, id="literal_neq_reads_one_spelling"),
-]
-
-
-def _trace_identities(
-    signoz: types.SigNoz,
-    token: str,
-    base: datetime,
-    expression: str,
-    signal: str = "traces",
-) -> set[str]:
-    identity_field = "span.name" if signal == "traces" else "body"
-    identity_column = "name" if signal == "traces" else "body"
-    response = make_query_request(
-        signoz,
-        token,
-        start_ms=int((base - timedelta(minutes=2)).timestamp() * 1000),
-        end_ms=int((base + timedelta(minutes=1)).timestamp() * 1000),
-        request_type=RequestType.RAW,
-        queries=[
-            build_raw_query(
-                "A",
-                signal,
-                limit=100,
-                filter_expression=expression,
-                order=[build_order_by("timestamp", "asc")],
-                select_fields=[{"name": identity_field}],
-            )
-        ],
-    )
-    assert response.status_code == HTTPStatus.OK, response.text
-    # Sets keep the assertion stable when the shared stack is reused and older
-    # rows with the same identities remain.
-    return {name for name in get_column_data_from_response(response.json(), identity_column) if name.startswith(PREFIX)}
-
-
-@pytest.mark.parametrize("expression_template,expected", FILTER_MATRIX)
-@pytest.mark.parametrize("requested_key", [CURRENT_KEY, OLD_KEY], ids=["current", "old"])
-@pytest.mark.parametrize("context", ["resource", "attribute"])
-def test_family_filters(
-    signoz: types.SigNoz,
-    create_user_admin: None,  # pylint: disable=unused-argument
-    get_token: Callable[[str, str], str],
-    family_fleet: datetime,
-    context: str,
-    requested_key: str,
-    expression_template: str,
-    expected: set[str],
-) -> None:
-    """One matrix cell: a filter on one spelling, in one context. The result
-    set is a property of the family, not of the requested spelling."""
-    token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
-    expression = expression_template.format(key=f"{context}.{requested_key}")
-    assert _trace_identities(signoz, token, family_fleet, expression) == expected, expression
-
-
-@pytest.mark.parametrize("expression_template,expected", LITERAL_MATRIX)
-def test_flag_off_stays_literal(
-    signoz_families_off: types.SigNoz,
-    create_user_admin: None,  # pylint: disable=unused-argument
-    get_token: Callable[[str, str], str],
-    family_fleet: datetime,
-    expression_template: str,
-    expected: set[str],
-) -> None:
-    """The same fleet through an instance with the flag at its default: the
-    current spelling reads only rows that carry the current spelling."""
-    token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
-    expression = expression_template.format(key=f"resource.{CURRENT_KEY}")
-    assert _trace_identities(signoz_families_off, token, family_fleet, expression) == expected, expression
-
-
-@pytest.mark.parametrize("expression_template,expected", LITERAL_MATRIX)
-def test_logs_stay_literal_with_flag_on(
-    signoz: types.SigNoz,
-    create_user_admin: None,  # pylint: disable=unused-argument
-    get_token: Callable[[str, str], str],
-    family_fleet: datetime,
-    expression_template: str,
-    expected: set[str],
-) -> None:
-    """Only traces have family support. The same filters on the logs copy of
-    the fleet behave literally even with the flag on."""
-    token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
-    expression = expression_template.format(key=f"resource.{CURRENT_KEY}")
-    assert _trace_identities(signoz, token, family_fleet, expression, signal="logs") == expected, expression
-
-
-def test_group_by_merges_and_echoes_requested_spelling(
-    signoz: types.SigNoz,
-    create_user_admin: None,  # pylint: disable=unused-argument
-    get_token: Callable[[str, str], str],
-    family_fleet: datetime,
-) -> None:
-    """Group by the current spelling over the fleet: OLD and NEW land in one
-    "production" group, BOTH lands in "staging", and the group column carries
-    the requested spelling."""
-    token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
-    response = make_query_request(
-        signoz,
-        token,
-        start_ms=int((family_fleet - timedelta(minutes=2)).timestamp() * 1000),
-        end_ms=int((family_fleet + timedelta(minutes=1)).timestamp() * 1000),
-        request_type=RequestType.SCALAR,
-        queries=[
-            build_traces_scalar_query(
-                [build_aggregation("count()")],
-                filter_expression=f"service.name LIKE '{PREFIX}%'",
-                group_by=[build_group_by_field(CURRENT_KEY, "string", "resource")],
-            )
-        ],
-    )
-    assert response.status_code == HTTPStatus.OK, response.text
-
-    result = response.json()["data"]["data"]["results"][0]
-    group_column = result["columns"][0]
-    assert group_column["name"] == CURRENT_KEY, group_column
-    assert group_column["columnType"] == "group", group_column
-
-    groups = {row[0] for row in result["data"]}
-    assert {"production", "staging"}.issubset(groups), groups
-    assert None in groups, groups
-
-
-def test_bare_name_prefers_resource_and_warns(
-    signoz: types.SigNoz,
-    create_user_admin: None,  # pylint: disable=unused-argument
-    get_token: Callable[[str, str], str],
-    family_fleet: datetime,
-) -> None:
-    """The fleet stores the family under the resource and the attribute
-    contexts, so a bare name is ambiguous. Resolution warns and keeps the
-    resource side; the family survives the collision as one unit."""
-    token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
-    response = make_query_request(
-        signoz,
-        token,
-        start_ms=int((family_fleet - timedelta(minutes=2)).timestamp() * 1000),
-        end_ms=int((family_fleet + timedelta(minutes=1)).timestamp() * 1000),
-        request_type=RequestType.RAW,
-        queries=[
-            build_raw_query(
-                "A",
-                "traces",
-                limit=100,
-                filter_expression=f"{CURRENT_KEY} = 'production'",
-                order=[build_order_by("timestamp", "asc")],
-                select_fields=[{"name": "span.name"}],
-            )
-        ],
-    )
-    assert response.status_code == HTTPStatus.OK, response.text
-
-    matched = {name for name in get_column_data_from_response(response.json(), "name") if name.startswith(PREFIX)}
-    assert matched == {OLD, NEW}
-
-    warning = response.json()["data"].get("warning") or {}
-    messages = " ".join(entry.get("message", "") for entry in warning.get("warnings", []))
-    assert "ambiguous" in messages.lower(), messages

tests/integration/tests/semconvfamilies/conftest.py

@@ -1,56 +0,0 @@
-import pytest
-from testcontainers.core.container import Network
-
-from fixtures import types
-from fixtures.signoz import create_signoz
-
-
-@pytest.fixture(name="signoz", scope="package")
-def signoz_semconv_families(
-    network: Network,
-    zeus: types.TestContainerDocker,
-    gateway: types.TestContainerDocker,
-    sqlstore: types.TestContainerSQL,
-    clickhouse: types.TestContainerClickhouse,
-    request: pytest.FixtureRequest,
-    pytestconfig: pytest.Config,
-) -> types.SigNoz:
-    """Package-scoped SigNoz with resolve_semconv_families on."""
-    return create_signoz(
-        network=network,
-        zeus=zeus,
-        gateway=gateway,
-        sqlstore=sqlstore,
-        clickhouse=clickhouse,
-        request=request,
-        pytestconfig=pytestconfig,
-        cache_key="signoz-semconv-families",
-        env_overrides={
-            "SIGNOZ_FLAGGER_CONFIG_BOOLEAN_RESOLVE__SEMCONV__FAMILIES": True,
-        },
-    )
-
-
-@pytest.fixture(name="signoz_families_off", scope="package")
-def signoz_families_off(
-    network: Network,
-    zeus: types.TestContainerDocker,
-    gateway: types.TestContainerDocker,
-    sqlstore: types.TestContainerSQL,
-    clickhouse: types.TestContainerClickhouse,
-    request: pytest.FixtureRequest,
-    pytestconfig: pytest.Config,
-) -> types.SigNoz:
-    """A second instance with the flag at its default (off). It shares the
-    sqlstore and clickhouse, so the same admin token and seeded rows work."""
-    return create_signoz(
-        network=network,
-        zeus=zeus,
-        gateway=gateway,
-        sqlstore=sqlstore,
-        clickhouse=clickhouse,
-        request=request,
-        pytestconfig=pytestconfig,
-        cache_key="signoz-semconv-families-off",
-        env_overrides={},
-    )