Compare commits

...

2 Commits

Author SHA1 Message Date
srikanthccv
28bb4939c1 test(querier): pin explicit context resolution under ambiguous names
The same name can exist as an intrinsic column and as an attribute (`name`
on spans, `severity_text` on logs), in two data types under one context,
or as a resource attribute and as a span or log attribute (`service.name`).
These cases pin what the query builder does today for a filter, EXISTS, a
group by, an order by, an aggregation argument, and a raw select on each
shape, so a change to name resolution shows as a failure here, not as a
surprise in a dashboard.

- An explicit context is honored as written. The ambiguity warning fires
  for a bare name with several readings and for an explicit attribute
  context whose attribute exists in two data types.
- A bare name that is both a column and an attribute reads both in a
  filter, orders and groups by the column alone, and counts the column's
  values alone. A string operand reaches a number attribute through a
  text cast.
- A bare name that is both a resource and an attribute reads the resource
  in a filter and in a raw select, with a warning in the filter.
- Under an explicit attribute context, traces order by the attribute and
  logs still order by the column.
- A key under the signal's own context that exists only as an attribute
  corrects to the attribute; on logs the correction also reads the body
  JSON path. A `scope.` key on logs resolves through metadata alone and
  answers "key not found" otherwise, also for the declared `scope.name`.

Assisted-by: Claude Fable 5.1
Claude-Session: https://claude.ai/code/session_01RSnZFLSfyi5S4QYQDcxHeW
2026-09-09 07:23:27 +05:30
Srikanth Chekuri
d5af6f6d6b feat(telemetrymetadata): fields keys and values for the quick filters migration (#12794)
Some checks are pending
build-staging / prepare (push) Waiting to run
build-staging / js-build (push) Blocked by required conditions
build-staging / go-build (push) Blocked by required conditions
build-staging / staging (push) Blocked by required conditions
cacheci / tests (push) Waiting to run
Release Drafter / update_release_draft (push) Waiting to run
#### Description

- `fields/values` returns `boolValues` for bool fields: static span
fields such as `has_error`, stored bool attributes (decided by a
row-existence check, so they take no limit slots), and keys the caller
declares bool. `isRoot` and `isEntryPoint` return `true` only, matching
the condition builder.
- `fields/values` honors `startUnixMilli` for logs and traces against
the tag tables. The predicate is `toDate(unix_milli / 1000) >=
toDate(start)`, the partition expression, because the tag tables
deduplicate a value per day and keep whichever hour was inserted last.
For traces this means "span started on or after the start's day", for
logs "ingested on or after the start's day". `endUnixMilli` is ignored.
- `fields/keys` honors `fieldContext` and `fieldDataType` for the static
intrinsic and calculated keys, matches them case-insensitively, types
`isRoot`/`isEntryPoint` as bool, gives meter keys a data type, filters
the traces keys table by tag type for the scope context, and no longer
returns early for the log and scope contexts (logs and audit).
- The span context keeps returning attribute keys, since queries spell
span attributes as `span.<name>`.
- Default quick filters name the span and log fields the way the fields
API serves them (`has_error` as a span bool, `name`, `duration_nano`,
`response_status_code`, `http_host`, `http_url`, `trace_id` as span
fields, `severity_text` as a log field). Migration 126 rewrites the
static fields of every stored quick filter the same way, whatever
context the legacy seeds gave them. Deprecated names such as `hasError`
are not served.
- The API-backed checkbox hook merges `boolValues` into its options; the
`has_error` title is kept.
- The fields/values handler no longer drops `boolValues` from the
response.


🤖 Generated with [Claude Code](https://claude.com/claude-code)
2026-09-08 22:11:27 +00:00
15 changed files with 1255 additions and 280 deletions

View File

@@ -34,6 +34,7 @@ export function mockFieldsValuesAPI(response: {
relatedValues?: (string | null)[];
stringValues?: (string | null)[];
numberValues?: (number | null)[];
boolValues?: (boolean | null)[];
}): void {
server.use(
rest.get('http://localhost/api/v1/fields/values', (_, res, ctx) =>
@@ -46,6 +47,7 @@ export function mockFieldsValuesAPI(response: {
relatedValues: response.relatedValues ?? [],
stringValues: response.stringValues ?? [],
numberValues: response.numberValues ?? [],
boolValues: response.boolValues ?? [],
},
},
}),

View File

@@ -92,8 +92,12 @@ export function useFieldValues({
values.numberValues
?.filter((value): value is number => value !== null && value !== undefined)
.map((value) => value.toString()) || [];
const boolValues =
values.boolValues
?.filter((value): value is boolean => value !== null && value !== undefined)
.map((value) => value.toString()) || [];
return [...stringValues, ...numberValues];
return [...stringValues, ...numberValues, ...boolValues];
}, [data]);
return { relatedValues, allValues, isLoading, isFetching };

View File

@@ -8,6 +8,7 @@ import { FiltersType, IQuickFiltersConfig, SignalType } from './types';
const FILTER_TITLE_MAP: Record<string, string> = {
duration_nano: 'Duration',
hasError: 'Has Error (Status)',
has_error: 'Has Error (Status)',
};
const FILTER_TYPE_MAP: Record<string, FiltersType> = {

View File

@@ -82,6 +82,7 @@ func (handler *handler) GetFieldsValues(rw http.ResponseWriter, req *http.Reques
values := &telemetrytypes.TelemetryFieldValues{
StringValues: allValues.StringValues,
BoolValues: allValues.BoolValues,
NumberValues: allValues.NumberValues,
RelatedValues: relatedValues,
}

View File

@@ -253,6 +253,7 @@ func NewSQLMigrationProviderFactories(
sqlmigration.NewAddQuickFilterTuplesFactory(sqlstore),
sqlmigration.NewAddIngestionTuplesFactory(sqlstore),
sqlmigration.NewAddSubscriptionTuplesFactory(sqlstore),
sqlmigration.NewNormalizeQuickFilterFieldsFactory(sqlstore),
)
}

View File

@@ -0,0 +1,161 @@
package sqlmigration
import (
"context"
"encoding/json"
"log/slog"
"github.com/uptrace/bun"
"github.com/uptrace/bun/migrate"
"github.com/SigNoz/signoz/pkg/factory"
"github.com/SigNoz/signoz/pkg/sqlstore"
)
type quickFilterSourceRow struct {
bun.BaseModel `bun:"table:quick_filter"`
ID string `bun:"id,pk"`
Source string `bun:"source"`
Filter string `bun:"filter"`
}
type quickFilterStaticField struct {
name string
fieldContext string
fieldDataType string
}
// quickFilterSpanFields are the span-level fields the fields API serves with
// the span context, keyed by every name a stored filter may carry for them.
var quickFilterSpanFields = func() map[string]quickFilterStaticField {
fields := map[string]quickFilterStaticField{}
for name, dataType := range map[string]string{
"trace_id": "string", "span_id": "string", "trace_state": "string", "parent_span_id": "string",
"flags": "number", "name": "string", "kind": "number", "kind_string": "string",
"duration_nano": "number", "status_code": "number", "status_message": "string", "status_code_string": "string",
"response_status_code": "string", "external_http_url": "string", "http_url": "string",
"external_http_method": "string", "http_method": "string", "http_host": "string",
"db_name": "string", "db_operation": "string", "has_error": "bool", "is_remote": "string",
} {
fields[name] = quickFilterStaticField{name: name, fieldContext: "span", fieldDataType: dataType}
}
for deprecated, current := range map[string]string{
"responseStatusCode": "response_status_code", "externalHttpUrl": "external_http_url", "httpUrl": "http_url",
"externalHttpMethod": "external_http_method", "httpMethod": "http_method", "httpHost": "http_host",
"dbName": "db_name", "dbOperation": "db_operation", "hasError": "has_error", "isRemote": "is_remote",
} {
fields[deprecated] = fields[current]
}
return fields
}()
// quickFilterLogFields are the log-level fields the fields API serves with
// the log context.
var quickFilterLogFields = map[string]quickFilterStaticField{
"body": {name: "body", fieldContext: "log", fieldDataType: "string"},
"severity_text": {name: "severity_text", fieldContext: "log", fieldDataType: "string"},
"severity_number": {name: "severity_number", fieldContext: "log", fieldDataType: "number"},
"trace_id": {name: "trace_id", fieldContext: "log", fieldDataType: "string"},
"span_id": {name: "span_id", fieldContext: "log", fieldDataType: "string"},
"trace_flags": {name: "trace_flags", fieldContext: "log", fieldDataType: "number"},
}
type normalizeQuickFilterFields struct {
settings factory.ProviderSettings
}
func NewNormalizeQuickFilterFieldsFactory(sqlstore sqlstore.SQLStore) factory.ProviderFactory[SQLMigration, Config] {
return factory.NewProviderFactory(factory.MustNewName("normalize_quick_filter_fields"), func(ctx context.Context, ps factory.ProviderSettings, c Config) (SQLMigration, error) {
return &normalizeQuickFilterFields{settings: ps}, nil
})
}
func (migration *normalizeQuickFilterFields) Register(migrations *migrate.Migrations) error {
return migrations.Register(migration.Up, migration.Down)
}
func (migration *normalizeQuickFilterFields) Up(ctx context.Context, db *bun.DB) error {
tx, err := db.BeginTx(ctx, nil)
if err != nil {
return err
}
defer func() { _ = tx.Rollback() }()
var rows []*quickFilterSourceRow
if err := tx.NewSelect().Model(&rows).Scan(ctx); err != nil {
return err
}
var migrated, skipped int
for _, row := range rows {
normalized, changed, ok := normalizeQuickFilterEntries(row.Source, row.Filter)
if !ok {
migration.settings.Logger.WarnContext(ctx, "quick filter could not be parsed, leaving it untouched", slog.String("quick_filter_id", row.ID), slog.String("raw_filter", row.Filter))
skipped++
continue
}
if !changed {
continue
}
migrated++
if _, err := tx.NewUpdate().Model((*quickFilterSourceRow)(nil)).Set("filter = ?", normalized).Where("id = ?", row.ID).Exec(ctx); err != nil {
return err
}
}
migration.settings.Logger.InfoContext(ctx, "normalized quick filter static fields", slog.Int("total", len(rows)), slog.Int("migrated", migrated), slog.Int("skipped", skipped))
return tx.Commit()
}
func (migration *normalizeQuickFilterFields) Down(context.Context, *bun.DB) error {
return nil
}
// normalizeQuickFilterEntries rewrites the static fields of a stored filter
// list to the name, context and data type the fields API serves them with:
// span fields for the trace-based sources, log fields for logs, whatever
// context the legacy seeds gave them. Other keys are left as they are;
// ok=false means unparseable.
func normalizeQuickFilterEntries(source string, filter string) (normalized string, changed bool, ok bool) {
var staticFields map[string]quickFilterStaticField
switch source {
case "traces", "api_monitoring", "exceptions", "ai_observability":
staticFields = quickFilterSpanFields
case "logs":
staticFields = quickFilterLogFields
default:
return "", false, true
}
var entries []telemetryFieldKeyOutput
if err := json.Unmarshal([]byte(filter), &entries); err != nil {
return "", false, false
}
for i, entry := range entries {
field, static := staticFields[entry.Name]
if !static {
continue
}
if entry.Name == field.name && entry.FieldContext == field.fieldContext && entry.FieldDataType == field.fieldDataType {
continue
}
entries[i].Name = field.name
entries[i].FieldContext = field.fieldContext
entries[i].FieldDataType = field.fieldDataType
changed = true
}
if !changed {
return "", false, true
}
normalizedJSON, err := marshalUnescaped(entries)
if err != nil {
return "", false, false
}
return string(normalizedJSON), true, true
}

View File

@@ -0,0 +1,61 @@
package telemetrymetadata
import (
"strconv"
"strings"
"github.com/SigNoz/signoz/pkg/telemetryschema/tracestelemetryschema"
"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
)
// boolFieldValues is the suggestion set for a bool field, optionally narrowed
// by the search text.
func boolFieldValues(searchText string) *telemetrytypes.TelemetryFieldValues {
values := &telemetrytypes.TelemetryFieldValues{}
needle := strings.ToLower(searchText)
for _, v := range []bool{true, false} {
if needle == "" || strings.Contains(strconv.FormatBool(v), needle) {
values.BoolValues = append(values.BoolValues, v)
}
}
return values
}
// spanSearchScopeFieldValues is the suggestion set for a search-scope selector
// (isRoot, isEntryPoint), which only filters with true. ok is false for any
// other name.
func spanSearchScopeFieldValues(name, searchText string) (*telemetrytypes.TelemetryFieldValues, bool) {
for scopeName := range tracestelemetryschema.SpanSearchScopeFields {
if !strings.EqualFold(scopeName, name) {
continue
}
values := &telemetrytypes.TelemetryFieldValues{}
if needle := strings.ToLower(searchText); needle == "" || strings.Contains("true", needle) {
values.BoolValues = []bool{true}
}
return values, true
}
return nil, false
}
// isKnownBoolField is true when the caller asked for the bool data type, or
// when the name is one of the signal's static bool fields and the requested
// context does not rule that static field out.
func isKnownBoolField(selector *telemetrytypes.FieldValueSelector, staticFields ...map[string]telemetrytypes.TelemetryFieldKey) bool {
if selector.FieldDataType == telemetrytypes.FieldDataTypeBool {
return true
}
if selector.FieldDataType != telemetrytypes.FieldDataTypeUnspecified {
return false
}
for _, fields := range staticFields {
field, ok := fields[selector.Name]
if !ok || field.FieldDataType != telemetrytypes.FieldDataTypeBool {
continue
}
if selector.FieldContext == telemetrytypes.FieldContextUnspecified || selector.FieldContext == field.FieldContext {
return true
}
}
return false
}

View File

@@ -187,8 +187,6 @@ func (t *telemetryMetaStore) getTracesKeys(ctx context.Context, fieldKeySelector
).From(t.tracesDBName + "." + t.spanAttributesKeysTblName)
var limit int
searchTexts := []string{}
conds := []string{}
for _, fieldKeySelector := range fieldKeySelectors {
@@ -208,14 +206,12 @@ func (t *telemetryMetaStore) getTracesKeys(ctx context.Context, fieldKeySelector
fieldKeyConds = append(fieldKeyConds, sb.ILike("tagKey", "%"+escapeForLike(fieldKeySelector.Name)+"%"))
}
searchTexts = append(searchTexts, fieldKeySelector.Name)
// now look at the field context
// we don't write most of intrinsic fields to keys table
// for this reason we don't want to apply tagType if the field context
// is not attribute or resource attribute
if fieldKeySelector.FieldContext != telemetrytypes.FieldContextUnspecified &&
(fieldKeySelector.FieldContext == telemetrytypes.FieldContextAttribute ||
fieldKeySelector.FieldContext == telemetrytypes.FieldContextResource) {
// is not attribute, resource attribute or scope
switch fieldKeySelector.FieldContext {
case telemetrytypes.FieldContextAttribute, telemetrytypes.FieldContextResource, telemetrytypes.FieldContextScope:
fieldKeyConds = append(fieldKeyConds, sb.E("tagType", fieldKeySelector.FieldContext.TagType()))
}
@@ -288,41 +284,20 @@ func (t *telemetryMetaStore) getTracesKeys(ctx context.Context, fieldKeySelector
// hit the limit? (only counting DB results)
complete := rowCount <= limit
staticKeys := []string{"isRoot", "isEntryPoint"}
staticKeys = append(staticKeys, maps.Keys(tracestelemetryschema.IntrinsicFields)...)
staticKeys = append(staticKeys, maps.Keys(tracestelemetryschema.CalculatedFields)...)
// Add the matching static fields: the span scope selectors, the intrinsic
// columns and the calculated columns. These don't count towards the limit
staticFields := maps.Values(tracestelemetryschema.SpanSearchScopeFields)
staticFields = append(staticFields, maps.Values(tracestelemetryschema.IntrinsicFields)...)
staticFields = append(staticFields, maps.Values(tracestelemetryschema.CalculatedFields)...)
// Add matching intrinsic and matching calculated fields
// These don't count towards the limit
for _, key := range staticKeys {
found := false
for _, v := range searchTexts {
if v == "" || strings.Contains(key, v) {
found = true
break
}
for _, field := range staticFields {
if !staticFieldMatchesAny(field, fieldKeySelectors) {
continue
}
if found {
if field, exists := tracestelemetryschema.IntrinsicFields[key]; exists {
if _, added := mapOfKeys[field.Name+";"+field.FieldContext.StringValue()+";"+field.FieldDataType.StringValue()]; !added {
keys = append(keys, &field)
}
continue
}
if field, exists := tracestelemetryschema.CalculatedFields[key]; exists {
if _, added := mapOfKeys[field.Name+";"+field.FieldContext.StringValue()+";"+field.FieldDataType.StringValue()]; !added {
keys = append(keys, &field)
}
continue
}
keys = append(keys, &telemetrytypes.TelemetryFieldKey{
Name: key,
FieldContext: telemetrytypes.FieldContextSpan,
Signal: telemetrytypes.SignalTraces,
})
if _, added := mapOfKeys[field.Name+";"+field.FieldContext.StringValue()+";"+field.FieldDataType.StringValue()]; added {
continue
}
keys = append(keys, &field)
}
if err = t.updateColumnEvolutionMetadataForKeys(ctx, keys); err != nil {
@@ -542,12 +517,6 @@ func (t *telemetryMetaStore) getLogsKeys(ctx context.Context, orgID valuer.UUID,
allArgs = append(allArgs, args...)
}
if len(queries) == 0 {
// No matching contexts, return empty result
return []*telemetrytypes.TelemetryFieldKey{}, true, nil
}
// Combine queries with UNION ALL
var limit int
for _, fieldKeySelector := range fieldKeySelectors {
limit += fieldKeySelector.Limit
@@ -556,7 +525,15 @@ func (t *telemetryMetaStore) getLogsKeys(ctx context.Context, orgID valuer.UUID,
limit = 1000
}
mainQuery := fmt.Sprintf(`
keys := []*telemetrytypes.TelemetryFieldKey{}
parentTypes := make(map[string][]telemetrytypes.FieldDataType)
rowCount := 0
// the log and scope contexts have no keys table; they are served by the
// static fields appended below
if len(queries) > 0 {
// Combine queries with UNION ALL
mainQuery := fmt.Sprintf(`
SELECT tag_key, tag_type, tag_data_type, max(priority) as priority
FROM (
%s
@@ -566,103 +543,75 @@ func (t *telemetryMetaStore) getLogsKeys(ctx context.Context, orgID valuer.UUID,
LIMIT %d
`, strings.Join(queries, " UNION ALL "), limit+1)
rows, err := t.telemetrystore.ClickhouseDB().Query(ctx, mainQuery, allArgs...)
if err != nil {
return nil, false, errors.Wrap(err, errors.TypeInternal, errors.CodeInternal, ErrFailedToGetLogsKeys.Error())
}
defer rows.Close()
keys := []*telemetrytypes.TelemetryFieldKey{}
parentTypes := make(map[string][]telemetrytypes.FieldDataType)
rowCount := 0
searchTexts := []string{}
// Collect search texts for static field matching
for _, fieldKeySelector := range fieldKeySelectors {
searchTexts = append(searchTexts, fieldKeySelector.Name)
}
for rows.Next() {
rowCount++
// reached the limit, we know there are more results
if rowCount > limit {
break
}
var name string
var fieldContext telemetrytypes.FieldContext
var fieldDataType telemetrytypes.FieldDataType
var priority uint8
err = rows.Scan(&name, &fieldContext, &fieldDataType, &priority)
rows, err := t.telemetrystore.ClickhouseDB().Query(ctx, mainQuery, allArgs...)
if err != nil {
return nil, false, errors.Wrap(err, errors.TypeInternal, errors.CodeInternal, ErrFailedToGetLogsKeys.Error())
}
defer rows.Close()
// ArrayJSON/ArrayDynamic body rows for parent paths are needed by the JSON access plan
// builder (enrichJSONKeys). Always record them in parentTypes. Only skip adding to keys
// if the user did not also directly request this name — a field like "education" can be
// both a parent of "education[].name" and an explicitly queried field in its own right.
switch fieldDataType {
case telemetrytypes.FieldDataTypeArrayJSON, telemetrytypes.FieldDataTypeArrayDynamic:
if fieldContext == telemetrytypes.FieldContextBody && parentPaths[name] {
parentTypes[name] = append(parentTypes[name], fieldDataType)
if !mapOfRequestedSelectors[name] {
continue // skip; don't register the key.
for rows.Next() {
rowCount++
// reached the limit, we know there are more results
if rowCount > limit {
break
}
var name string
var fieldContext telemetrytypes.FieldContext
var fieldDataType telemetrytypes.FieldDataType
var priority uint8
err = rows.Scan(&name, &fieldContext, &fieldDataType, &priority)
if err != nil {
return nil, false, errors.Wrap(err, errors.TypeInternal, errors.CodeInternal, ErrFailedToGetLogsKeys.Error())
}
// ArrayJSON/ArrayDynamic body rows for parent paths are needed by the JSON access plan
// builder (enrichJSONKeys). Always record them in parentTypes. Only skip adding to keys
// if the user did not also directly request this name — a field like "education" can be
// both a parent of "education[].name" and an explicitly queried field in its own right.
switch fieldDataType {
case telemetrytypes.FieldDataTypeArrayJSON, telemetrytypes.FieldDataTypeArrayDynamic:
if fieldContext == telemetrytypes.FieldContextBody && parentPaths[name] {
parentTypes[name] = append(parentTypes[name], fieldDataType)
if !mapOfRequestedSelectors[name] {
continue // skip; don't register the key.
}
}
}
}
key, ok := mapOfKeys[name+";"+fieldContext.StringValue()+";"+fieldDataType.StringValue()]
key, ok := mapOfKeys[name+";"+fieldContext.StringValue()+";"+fieldDataType.StringValue()]
// if there is no materialised column, create a key with the field context and data type
if !ok {
key = &telemetrytypes.TelemetryFieldKey{
Name: name,
Signal: telemetrytypes.SignalLogs,
FieldContext: fieldContext,
FieldDataType: fieldDataType,
// if there is no materialised column, create a key with the field context and data type
if !ok {
key = &telemetrytypes.TelemetryFieldKey{
Name: name,
Signal: telemetrytypes.SignalLogs,
FieldContext: fieldContext,
FieldDataType: fieldDataType,
}
}
keys = append(keys, key)
mapOfKeys[name+";"+fieldContext.StringValue()+";"+fieldDataType.StringValue()] = key
}
keys = append(keys, key)
mapOfKeys[name+";"+fieldContext.StringValue()+";"+fieldDataType.StringValue()] = key
}
if rows.Err() != nil {
return nil, false, errors.Wrap(rows.Err(), errors.TypeInternal, errors.CodeInternal, ErrFailedToGetLogsKeys.Error())
if rows.Err() != nil {
return nil, false, errors.Wrap(rows.Err(), errors.TypeInternal, errors.CodeInternal, ErrFailedToGetLogsKeys.Error())
}
}
// hit the limit? (only counting DB results)
complete := rowCount <= limit
staticKeys := []string{}
staticKeys = append(staticKeys, maps.Keys(logstelemetryschema.IntrinsicFields)...)
// Add matching intrinsic and matching calculated fields
// These don't count towards the limit
for _, key := range staticKeys {
found := false
for _, v := range searchTexts {
if v == "" || strings.Contains(key, v) {
found = true
break
}
// Add the matching intrinsic columns. These don't count towards the limit
for _, field := range maps.Values(logstelemetryschema.IntrinsicFields) {
if !staticFieldMatchesAny(field, fieldKeySelectors) {
continue
}
if found {
if field, exists := logstelemetryschema.IntrinsicFields[key]; exists {
if _, added := mapOfKeys[field.Name+";"+field.FieldContext.StringValue()+";"+field.FieldDataType.StringValue()]; !added {
keys = append(keys, &field)
}
continue
}
keys = append(keys, &telemetrytypes.TelemetryFieldKey{
Name: key,
FieldContext: telemetrytypes.FieldContextLog,
Signal: telemetrytypes.SignalLogs,
})
if _, added := mapOfKeys[field.Name+";"+field.FieldContext.StringValue()+";"+field.FieldDataType.StringValue()]; added {
continue
}
keys = append(keys, &field)
}
// enrich body keys with promoted paths, indexes, and JSON access plans
@@ -806,10 +755,6 @@ func (t *telemetryMetaStore) getAuditKeys(ctx context.Context, fieldKeySelectors
allArgs = append(allArgs, args...)
}
if len(queries) == 0 {
return []*telemetrytypes.TelemetryFieldKey{}, true, nil
}
var limit int
for _, fieldKeySelector := range fieldKeySelectors {
limit += fieldKeySelector.Limit
@@ -818,7 +763,13 @@ func (t *telemetryMetaStore) getAuditKeys(ctx context.Context, fieldKeySelectors
limit = 1000
}
mainQuery := fmt.Sprintf(`
keys := []*telemetrytypes.TelemetryFieldKey{}
rowCount := 0
// the log and scope contexts have no keys table; they are served by the
// static fields appended below
if len(queries) > 0 {
mainQuery := fmt.Sprintf(`
SELECT tag_key, tag_type, tag_data_type, max(priority) as priority
FROM (
%s
@@ -828,73 +779,57 @@ func (t *telemetryMetaStore) getAuditKeys(ctx context.Context, fieldKeySelectors
LIMIT %d
`, strings.Join(queries, " UNION ALL "), limit+1)
rows, err := t.telemetrystore.ClickhouseDB().Query(ctx, mainQuery, allArgs...)
if err != nil {
return nil, false, errors.Wrap(err, errors.TypeInternal, errors.CodeInternal, ErrFailedToGetAuditKeys.Error())
}
defer rows.Close()
keys := []*telemetrytypes.TelemetryFieldKey{}
rowCount := 0
searchTexts := []string{}
for _, fieldKeySelector := range fieldKeySelectors {
searchTexts = append(searchTexts, fieldKeySelector.Name)
}
for rows.Next() {
rowCount++
if rowCount > limit {
break
}
var name string
var fieldContext telemetrytypes.FieldContext
var fieldDataType telemetrytypes.FieldDataType
var priority uint8
err = rows.Scan(&name, &fieldContext, &fieldDataType, &priority)
rows, err := t.telemetrystore.ClickhouseDB().Query(ctx, mainQuery, allArgs...)
if err != nil {
return nil, false, errors.Wrap(err, errors.TypeInternal, errors.CodeInternal, ErrFailedToGetAuditKeys.Error())
}
key, ok := mapOfKeys[name+";"+fieldContext.StringValue()+";"+fieldDataType.StringValue()]
defer rows.Close()
if !ok {
key = &telemetrytypes.TelemetryFieldKey{
Name: name,
Signal: telemetrytypes.SignalLogs,
FieldContext: fieldContext,
FieldDataType: fieldDataType,
for rows.Next() {
rowCount++
if rowCount > limit {
break
}
var name string
var fieldContext telemetrytypes.FieldContext
var fieldDataType telemetrytypes.FieldDataType
var priority uint8
err = rows.Scan(&name, &fieldContext, &fieldDataType, &priority)
if err != nil {
return nil, false, errors.Wrap(err, errors.TypeInternal, errors.CodeInternal, ErrFailedToGetAuditKeys.Error())
}
key, ok := mapOfKeys[name+";"+fieldContext.StringValue()+";"+fieldDataType.StringValue()]
if !ok {
key = &telemetrytypes.TelemetryFieldKey{
Name: name,
Signal: telemetrytypes.SignalLogs,
FieldContext: fieldContext,
FieldDataType: fieldDataType,
}
}
keys = append(keys, key)
mapOfKeys[name+";"+fieldContext.StringValue()+";"+fieldDataType.StringValue()] = key
}
keys = append(keys, key)
mapOfKeys[name+";"+fieldContext.StringValue()+";"+fieldDataType.StringValue()] = key
}
if rows.Err() != nil {
return nil, false, errors.Wrap(rows.Err(), errors.TypeInternal, errors.CodeInternal, ErrFailedToGetAuditKeys.Error())
if rows.Err() != nil {
return nil, false, errors.Wrap(rows.Err(), errors.TypeInternal, errors.CodeInternal, ErrFailedToGetAuditKeys.Error())
}
}
complete := rowCount <= limit
// Add intrinsic audit fields (same as logs intrinsics: body, severity_text, etc.)
staticKeys := maps.Keys(audittelemetryschema.IntrinsicFields)
for _, key := range staticKeys {
found := false
for _, v := range searchTexts {
if v == "" || strings.Contains(key, v) {
found = true
break
}
// Add the matching intrinsic audit fields (same as logs intrinsics: body, severity_text, etc.)
for _, field := range maps.Values(audittelemetryschema.IntrinsicFields) {
if !staticFieldMatchesAny(field, fieldKeySelectors) {
continue
}
if found {
if field, exists := audittelemetryschema.IntrinsicFields[key]; exists {
if _, added := mapOfKeys[field.Name+";"+field.FieldContext.StringValue()+";"+field.FieldDataType.StringValue()]; !added {
keys = append(keys, &field)
}
}
if _, added := mapOfKeys[field.Name+";"+field.FieldContext.StringValue()+";"+field.FieldDataType.StringValue()]; added {
continue
}
keys = append(keys, &field)
}
return keys, complete, nil
@@ -1091,9 +1026,12 @@ func (t *telemetryMetaStore) getMeterSourceMetricKeys(ctx context.Context, field
if err != nil {
return nil, false, errors.Wrap(err, errors.TypeInternal, errors.CodeInternal, ErrFailedToGetMeterKeys.Error())
}
// meter labels are stored as strings in the labels JSON and have no
// attribute context, so only the data type is known
keys = append(keys, &telemetrytypes.TelemetryFieldKey{
Name: name,
Signal: telemetrytypes.SignalMetrics,
Name: name,
Signal: telemetrytypes.SignalMetrics,
FieldDataType: telemetrytypes.FieldDataTypeString,
})
}
@@ -1506,88 +1444,13 @@ func (t *telemetryMetaStore) getSpanFieldValues(ctx context.Context, fieldValueS
instrumentationtypes.CodeNamespace: "metadata",
instrumentationtypes.CodeFunctionName: "getSpanFieldValues",
})
// build the query to get the keys from the spans that match the field selection criteria
limit := fieldValueSelector.Limit
if limit == 0 {
limit = 50
if values, ok := spanSearchScopeFieldValues(fieldValueSelector.Name, fieldValueSelector.Value); ok {
return values, true, nil
}
sb := sqlbuilder.Select("DISTINCT string_value, number_value").From(t.tracesDBName + "." + t.tracesFieldsTblName)
if fieldValueSelector.Name != "" {
sb.Where(sb.E("tag_key", fieldValueSelector.Name))
}
// now look at the field context
if fieldValueSelector.FieldContext != telemetrytypes.FieldContextUnspecified {
sb.Where(sb.E("tag_type", fieldValueSelector.FieldContext.TagType()))
}
// now look at the field data type
if fieldValueSelector.FieldDataType != telemetrytypes.FieldDataTypeUnspecified {
sb.Where(sb.E("tag_data_type", fieldValueSelector.FieldDataType.TagDataType()))
}
if fieldValueSelector.Value != "" {
switch fieldValueSelector.FieldDataType {
case telemetrytypes.FieldDataTypeString:
sb.Where(sb.ILike("string_value", "%"+escapeForLike(fieldValueSelector.Value)+"%"))
case telemetrytypes.FieldDataTypeNumber:
sb.Where(sb.IsNotNull("number_value"))
sb.Where(sb.ILike("toString(number_value)", "%"+escapeForLike(fieldValueSelector.Value)+"%"))
case telemetrytypes.FieldDataTypeUnspecified:
// or b/w string and number
sb.Where(sb.Or(
sb.ILike("string_value", "%"+escapeForLike(fieldValueSelector.Value)+"%"),
sb.ILike("toString(number_value)", "%"+escapeForLike(fieldValueSelector.Value)+"%"),
))
}
}
// query one extra to check if we hit the limit
sb.Limit(limit + 1)
query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
rows, err := t.telemetrystore.ClickhouseDB().Query(ctx, query, args...)
if err != nil {
return nil, false, errors.Wrap(err, errors.TypeInternal, errors.CodeInternal, ErrFailedToGetLogsKeys.Error())
}
defer rows.Close()
values := &telemetrytypes.TelemetryFieldValues{}
seen := make(map[string]bool)
rowCount := 0
totalCount := 0 // Track total unique values
for rows.Next() {
rowCount++
var stringValue string
var numberValue float64
if err := rows.Scan(&stringValue, &numberValue); err != nil {
return nil, false, errors.Wrap(err, errors.TypeInternal, errors.CodeInternal, ErrFailedToGetLogsKeys.Error())
}
// Only add values if we haven't hit the limit yet
if totalCount < limit {
if _, ok := seen[stringValue]; !ok && stringValue != "" {
values.StringValues = append(values.StringValues, stringValue)
seen[stringValue] = true
totalCount++
}
if _, ok := seen[fmt.Sprintf("%f", numberValue)]; !ok && numberValue != 0 && totalCount < limit {
values.NumberValues = append(values.NumberValues, numberValue)
seen[fmt.Sprintf("%f", numberValue)] = true
totalCount++
}
}
}
// hit the limit?
complete := rowCount <= limit
return values, complete, nil
knownBool := isKnownBoolField(fieldValueSelector, tracestelemetryschema.IntrinsicFields, tracestelemetryschema.CalculatedFields)
// unix_milli is the hour of the span start
return t.getTagTableValues(ctx, t.tracesDBName+"."+t.tracesFieldsTblName, fieldValueSelector, knownBool)
}
func (t *telemetryMetaStore) getLogFieldValues(ctx context.Context, fieldValueSelector *telemetrytypes.FieldValueSelector) (*telemetrytypes.TelemetryFieldValues, bool, error) {
@@ -1596,17 +1459,77 @@ func (t *telemetryMetaStore) getLogFieldValues(ctx context.Context, fieldValueSe
instrumentationtypes.CodeNamespace: "metadata",
instrumentationtypes.CodeFunctionName: "getLogFieldValues",
})
// build the query to get the keys from the spans that match the field selection criteria
knownBool := isKnownBoolField(fieldValueSelector, logstelemetryschema.IntrinsicFields)
// unix_milli is the hour the log was ingested, not the log's own timestamp
return t.getTagTableValues(ctx, t.logsDBName+"."+t.logsFieldsTblName, fieldValueSelector, knownBool)
}
// tagTableSinceDay restricts rows to the tag table's day partitions from the
// start's day on. Partitions are toDate(unix_milli / 1000) in the server's
// timezone, and a value's surviving row within a day carries whichever hour
// was inserted last, so the day is the finest safe unit.
func tagTableSinceDay(sb *sqlbuilder.SelectBuilder, startUnixMilli int64) {
if startUnixMilli != 0 {
sb.Where(fmt.Sprintf("toDate(unix_milli / 1000) >= toDate(%d)", startUnixMilli/1000))
}
}
// tagTableHasBoolRows reports whether the tag table holds a bool row for the
// key. Bool rows carry no value, so one row is enough to know the key takes
// the values true and false.
func (t *telemetryMetaStore) tagTableHasBoolRows(ctx context.Context, table string, selector *telemetrytypes.FieldValueSelector) (bool, error) {
sb := sqlbuilder.Select("1").From(table)
sb.Where(sb.E("tag_key", selector.Name))
sb.Where(sb.E("tag_data_type", telemetrytypes.FieldDataTypeBool.TagDataType()))
if selector.FieldContext != telemetrytypes.FieldContextUnspecified {
sb.Where(sb.E("tag_type", selector.FieldContext.TagType()))
}
tagTableSinceDay(sb, selector.StartUnixMilli)
sb.Limit(1)
query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
rows, err := t.telemetrystore.ClickhouseDB().Query(ctx, query, args...)
if err != nil {
return false, errors.Wrap(err, errors.TypeInternal, errors.CodeInternal, ErrFailedToGetLogsKeys.Error())
}
defer rows.Close()
return rows.Next(), rows.Err()
}
// getTagTableValues returns the string and number values of the key from a
// tag table, and true and false when the key is a known bool field or the
// table holds bool rows for it. Bool rows do not count towards the limit.
func (t *telemetryMetaStore) getTagTableValues(ctx context.Context, table string, fieldValueSelector *telemetrytypes.FieldValueSelector, knownBool bool) (*telemetrytypes.TelemetryFieldValues, bool, error) {
limit := fieldValueSelector.Limit
if limit == 0 {
limit = 50
}
sb := sqlbuilder.Select("DISTINCT string_value, number_value").From(t.logsDBName + "." + t.logsFieldsTblName)
values := &telemetrytypes.TelemetryFieldValues{}
if knownBool {
values.BoolValues = boolFieldValues(fieldValueSelector.Value).BoolValues
if fieldValueSelector.FieldDataType == telemetrytypes.FieldDataTypeBool {
return values, true, nil
}
} else if fieldValueSelector.FieldDataType == telemetrytypes.FieldDataTypeUnspecified {
hasBoolRows, err := t.tagTableHasBoolRows(ctx, table, fieldValueSelector)
if err != nil {
return nil, false, err
}
if hasBoolRows {
values.BoolValues = boolFieldValues(fieldValueSelector.Value).BoolValues
}
}
sb := sqlbuilder.Select("DISTINCT string_value, number_value").From(table)
if fieldValueSelector.Name != "" {
sb.Where(sb.E("tag_key", fieldValueSelector.Name))
}
sb.Where(sb.NE("tag_data_type", telemetrytypes.FieldDataTypeBool.TagDataType()))
tagTableSinceDay(sb, fieldValueSelector.StartUnixMilli)
if fieldValueSelector.FieldContext != telemetrytypes.FieldContextUnspecified {
sb.Where(sb.E("tag_type", fieldValueSelector.FieldContext.TagType()))
@@ -1643,7 +1566,6 @@ func (t *telemetryMetaStore) getLogFieldValues(ctx context.Context, fieldValueSe
}
defer rows.Close()
values := &telemetrytypes.TelemetryFieldValues{}
seen := make(map[string]bool)
rowCount := 0
totalCount := 0 // Track total unique values
@@ -2097,6 +2019,18 @@ func populateAllUnspecifiedValues(allUnspecifiedValues *telemetrytypes.Telemetry
}
}
for _, value := range values.BoolValues {
if totalCount >= limit {
complete = false
break
}
if _, ok := mapOfValues[value]; !ok {
mapOfValues[value] = true
allUnspecifiedValues.BoolValues = append(allUnspecifiedValues.BoolValues, value)
totalCount++
}
}
for _, value := range values.RelatedValues {
if totalCount >= limit {
complete = false
@@ -2467,6 +2401,10 @@ func (k *telemetryMetaStore) fetchEvolutionEntryFromClickHouse(ctx context.Conte
// updateColumnEvolutionMetadataForKeys updates the evolution field for keys.
func (k *telemetryMetaStore) updateColumnEvolutionMetadataForKeys(ctx context.Context, keysToUpdate []*telemetrytypes.TelemetryFieldKey) error {
// an empty selector list would run the evolution query without a filter
if len(keysToUpdate) == 0 {
return nil
}
var metadataKeySelectors []*telemetrytypes.EvolutionSelector
for _, keySelector := range keysToUpdate {

View File

@@ -0,0 +1,53 @@
package telemetrymetadata
import (
"strings"
"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
)
func staticFieldMatchesAny(field telemetrytypes.TelemetryFieldKey, selectors []*telemetrytypes.FieldKeySelector) bool {
for _, selector := range selectors {
if staticFieldMatches(field, selector) {
return true
}
}
return false
}
// staticFieldMatches mirrors the keys-table lookup for a static field: the
// requested context and data type, when given, must agree with the field's,
// and the name matches case-insensitively, as a substring for fuzzy selectors
// and as the whole name for exact ones.
func staticFieldMatches(field telemetrytypes.TelemetryFieldKey, selector *telemetrytypes.FieldKeySelector) bool {
if selector.FieldContext != telemetrytypes.FieldContextUnspecified && selector.FieldContext != field.FieldContext {
return false
}
if selector.FieldDataType != telemetrytypes.FieldDataTypeUnspecified && !sameDataTypeFamily(selector.FieldDataType, field.FieldDataType) {
return false
}
if selector.Name == "" {
return true
}
if selector.SelectorMatchType == telemetrytypes.FieldSelectorMatchTypeExact {
return strings.EqualFold(field.Name, selector.Name)
}
return strings.Contains(strings.ToLower(field.Name), strings.ToLower(selector.Name))
}
// sameDataTypeFamily treats the numeric types as one family: static fields
// declare "number" while callers may ask for int64 or float64.
func sameDataTypeFamily(requested, actual telemetrytypes.FieldDataType) bool {
if requested == actual {
return true
}
return isNumericDataType(requested) && isNumericDataType(actual)
}
func isNumericDataType(dataType telemetrytypes.FieldDataType) bool {
switch dataType {
case telemetrytypes.FieldDataTypeNumber, telemetrytypes.FieldDataTypeInt64, telemetrytypes.FieldDataTypeFloat64:
return true
}
return false
}

View File

@@ -392,6 +392,24 @@ var (
SpanSearchScopeRoot = "isroot"
SpanSearchScopeEntryPoint = "isentrypoint"
// SpanSearchScopeFields are the search-scope selectors (isRoot, isEntryPoint),
// not columns and unrelated to the instrumentation scope: they only filter
// with the value true.
SpanSearchScopeFields = map[string]telemetrytypes.TelemetryFieldKey{
"isRoot": {
Name: "isRoot",
Signal: telemetrytypes.SignalTraces,
FieldContext: telemetrytypes.FieldContextSpan,
FieldDataType: telemetrytypes.FieldDataTypeBool,
},
"isEntryPoint": {
Name: "isEntryPoint",
Signal: telemetrytypes.SignalTraces,
FieldContext: telemetrytypes.FieldContextSpan,
FieldDataType: telemetrytypes.FieldDataTypeBool,
},
}
// IntrinsicSpanFields lists the intrinsic span columns, in the order they
// should appear when a raw query expands its SelectFields.
IntrinsicSpanFields = []telemetrytypes.TelemetryFieldKey{

View File

@@ -173,18 +173,18 @@ func NewSourceFilterFromStorableQuickFilter(storableQuickFilter *StorableQuickFi
// NewDefaultQuickFilter generates default filters for all supported sources.
func NewDefaultQuickFilter(orgID valuer.UUID) ([]*StorableQuickFilter, error) {
tracesFilters := []telemetrytypes.TelemetryFieldKey{
{Name: "duration_nano", FieldContext: telemetrytypes.FieldContextAttribute, FieldDataType: telemetrytypes.FieldDataTypeNumber},
{Name: "duration_nano", FieldContext: telemetrytypes.FieldContextSpan, FieldDataType: telemetrytypes.FieldDataTypeNumber},
{Name: "deployment.environment", FieldContext: telemetrytypes.FieldContextResource, FieldDataType: telemetrytypes.FieldDataTypeString},
{Name: "hasError", FieldContext: telemetrytypes.FieldContextAttribute, FieldDataType: telemetrytypes.FieldDataTypeBool},
{Name: "has_error", FieldContext: telemetrytypes.FieldContextSpan, FieldDataType: telemetrytypes.FieldDataTypeBool},
{Name: "service.name", FieldContext: telemetrytypes.FieldContextResource, FieldDataType: telemetrytypes.FieldDataTypeString},
{Name: "name", FieldContext: telemetrytypes.FieldContextAttribute, FieldDataType: telemetrytypes.FieldDataTypeString},
{Name: "name", FieldContext: telemetrytypes.FieldContextSpan, FieldDataType: telemetrytypes.FieldDataTypeString},
{Name: "rpc.method", FieldContext: telemetrytypes.FieldContextAttribute, FieldDataType: telemetrytypes.FieldDataTypeString},
{Name: "response_status_code", FieldContext: telemetrytypes.FieldContextAttribute, FieldDataType: telemetrytypes.FieldDataTypeString},
{Name: "http_host", FieldContext: telemetrytypes.FieldContextAttribute, FieldDataType: telemetrytypes.FieldDataTypeString},
{Name: "response_status_code", FieldContext: telemetrytypes.FieldContextSpan, FieldDataType: telemetrytypes.FieldDataTypeString},
{Name: "http_host", FieldContext: telemetrytypes.FieldContextSpan, FieldDataType: telemetrytypes.FieldDataTypeString},
{Name: "http.method", FieldContext: telemetrytypes.FieldContextAttribute, FieldDataType: telemetrytypes.FieldDataTypeString},
{Name: "http.route", FieldContext: telemetrytypes.FieldContextAttribute, FieldDataType: telemetrytypes.FieldDataTypeString},
{Name: "http_url", FieldContext: telemetrytypes.FieldContextAttribute, FieldDataType: telemetrytypes.FieldDataTypeString},
{Name: "trace_id", FieldContext: telemetrytypes.FieldContextAttribute, FieldDataType: telemetrytypes.FieldDataTypeString},
{Name: "http_url", FieldContext: telemetrytypes.FieldContextSpan, FieldDataType: telemetrytypes.FieldDataTypeString},
{Name: "trace_id", FieldContext: telemetrytypes.FieldContextSpan, FieldDataType: telemetrytypes.FieldDataTypeString},
}
logsFilters := []telemetrytypes.TelemetryFieldKey{

View File

@@ -1,4 +1,4 @@
"""Seed data for the queriercommon keyless-semantics tests.
"""Seed data for the queriercommon keyless-semantics and explicit-context tests.
Three identities exist in every signal. GOLD and SILVER carry the test keys.
NONE carries no key at all. The tests assert which identities a filter
@@ -8,6 +8,7 @@ The attribute names are outside every semantic-convention family, so the
seeded data pins base behavior with any semconv overlay state.
"""
import json
from collections.abc import Callable, Generator
from datetime import UTC, datetime, timedelta
@@ -122,3 +123,98 @@ def keyless_series(insert_metrics: Callable[[list[Metrics]], None]) -> Generator
]
)
yield start, start + points * 60
EXPLICIT_PREFIX = "explicit-ctx"
# Unambiguous string attribute that names the row. Every assertion reads it back.
IDENTITY_KEY = "probe.id"
# Attribute-only key with no same-named column, for the own-context miss. On
# logs the rows that lack the attribute carry it nested in the body JSON.
ATTRIBUTE_ONLY_KEY = "route.tag"
CONTESTED_VALUE = "checkout"
# Row identities, by where the contested name carries the contested value:
# the intrinsic column (`name` on spans, `severity_text` on logs), the
# same-named string attribute, both, neither, or a same-named number
# attribute (a data type that contradicts the column).
COLUMN_ONLY = f"{EXPLICIT_PREFIX}-column"
ATTRIBUTE_ONLY = f"{EXPLICIT_PREFIX}-attribute"
BOTH = f"{EXPLICIT_PREFIX}-both"
NEITHER = f"{EXPLICIT_PREFIX}-neither"
NUMBER_ATTRIBUTE = f"{EXPLICIT_PREFIX}-number"
NUMBER_VALUE = 42
# (identity, column carries the value, attribute carries the value,
# attribute carries the number, resource service.name, attribute service.name,
# carries route.tag, insert offset in seconds)
ROWS = [
(COLUMN_ONLY, True, False, False, "svc-a", None, True, 1),
(ATTRIBUTE_ONLY, False, True, False, "svc-b", "svc-a", False, 2),
(BOTH, True, True, False, "svc-a", "svc-a", True, 3),
(NEITHER, False, False, False, "svc-b", "svc-b", False, 4),
(NUMBER_ATTRIBUTE, False, False, True, "svc-b", None, False, 5),
]
# Logs only: the declared scope path `scope.name` next to a scope attribute
# that is also named `name`, and a plain scope attribute.
SCOPE_NAME = "scope-a"
SCOPE_ATTRIBUTE_KEY = "env"
SCOPE_ATTRIBUTE_VALUE = "prod"
@pytest.fixture(name="ambiguous_rows", scope="function")
def ambiguous_rows(
insert_logs: Callable[[list[Logs]], None],
insert_traces: Callable[[list[Traces]], None],
) -> Generator[datetime]:
"""One span and one log per identity. `service.name` exists as a resource
attribute on every row and as a span or log attribute on some, with
different values, so a bare `service.name` is ambiguous. Logs that lack
the `route.tag` attribute carry it in the body JSON instead. Logs with
the column value carry the scope name; logs with the attribute value
carry the scope attributes. Yields the base timestamp."""
now = datetime.now(tz=UTC).replace(microsecond=0) - timedelta(minutes=1)
insert_traces(
[
Traces(
timestamp=now - timedelta(seconds=offset),
duration=timedelta(milliseconds=10),
trace_id=TraceIdGenerator.trace_id(),
span_id=TraceIdGenerator.span_id(),
name=CONTESTED_VALUE if column else "other",
kind=TracesKind.SPAN_KIND_SERVER,
status_code=TracesStatusCode.STATUS_CODE_OK,
resources={"service.name": resource_service},
attributes={
IDENTITY_KEY: identity,
**({"name": CONTESTED_VALUE} if attribute else {}),
**({"name": NUMBER_VALUE} if number else {}),
**({"service.name": attribute_service} if attribute_service else {}),
**({ATTRIBUTE_ONLY_KEY: CONTESTED_VALUE} if tagged else {}),
},
)
for identity, column, attribute, number, resource_service, attribute_service, tagged, offset in ROWS
]
)
insert_logs(
[
Logs(
timestamp=now - timedelta(seconds=offset),
body=json.dumps({} if tagged else {"route": {"tag": CONTESTED_VALUE}}),
severity_text="ERROR" if column else "INFO",
scope_name=SCOPE_NAME if column else "",
scope_attributes={"name": CONTESTED_VALUE, SCOPE_ATTRIBUTE_KEY: SCOPE_ATTRIBUTE_VALUE} if attribute else {},
resources={"service.name": resource_service},
attributes={
IDENTITY_KEY: identity,
**({"severity_text": "ERROR"} if attribute else {}),
**({"severity_text": NUMBER_VALUE} if number else {}),
**({"service.name": attribute_service} if attribute_service else {}),
**({ATTRIBUTE_ONLY_KEY: CONTESTED_VALUE} if tagged else {}),
},
)
for identity, column, attribute, number, resource_service, attribute_service, tagged, offset in ROWS
]
)
yield now

View File

@@ -0,0 +1,371 @@
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,
assert_scalar_value,
build_aggregation,
build_group_by_field,
build_order_by,
build_raw_query,
build_scalar_query,
get_all_warnings,
get_column_data_from_response,
get_scalar_table_data,
make_query_request,
)
from fixtures.queriercommon import (
ATTRIBUTE_ONLY,
BOTH,
COLUMN_ONLY,
EXPLICIT_PREFIX,
IDENTITY_KEY,
NEITHER,
NUMBER_ATTRIBUTE,
)
# Which rows a filter returns when the same name exists as an intrinsic
# column and as an attribute (`name` on spans, `severity_text` on logs), or
# as a resource attribute and a span or log attribute (`service.name`).
# An explicit context is honored as written. A bare name that is both a
# column and an attribute reads both, with an ambiguity warning. A bare name
# that is both a resource and an attribute reads the resource, with a
# warning. The warning also fires for an explicit attribute context when the
# attribute exists in two data types, and a string operand reaches the
# number attribute through a text cast. A key under the signal's own context
# that exists only as an attribute corrects to the attribute; on logs the
# correction also reads the body JSON path.
FILTER_MATRIX = [
pytest.param("{contested} = '{value}'", {COLUMN_ONLY, ATTRIBUTE_ONLY, BOTH}, True, id="bare_column_and_attribute"),
pytest.param("{own}.{contested} = '{value}'", {COLUMN_ONLY, BOTH}, False, id="own_context_column_only"),
pytest.param("attribute.{contested} = '{value}'", {ATTRIBUTE_ONLY, BOTH}, True, id="attribute_context_warns_about_two_types"),
pytest.param("{contested} != '{value}'", {NEITHER, NUMBER_ATTRIBUTE}, True, id="bare_negative_excludes_every_carrier"),
pytest.param("{contested} EXISTS", {COLUMN_ONLY, ATTRIBUTE_ONLY, BOTH, NEITHER, NUMBER_ATTRIBUTE}, True, id="bare_exists_is_the_column"),
pytest.param("{contested} NOT EXISTS", set(), True, id="bare_not_exists_is_never"),
pytest.param("attribute.{contested} EXISTS", {ATTRIBUTE_ONLY, BOTH, NUMBER_ATTRIBUTE}, True, id="attribute_exists_spans_both_types"),
pytest.param("attribute.{contested} NOT EXISTS", {COLUMN_ONLY, NEITHER}, True, id="attribute_not_exists"),
pytest.param("{contested} = '42'", {NUMBER_ATTRIBUTE}, True, id="bare_string_operand_reaches_the_number_attribute"),
pytest.param("attribute.{contested}:string = '{value}'", {ATTRIBUTE_ONLY, BOTH}, False, id="type_suffix_selects_the_string_attribute"),
pytest.param("attribute.{contested}:float64 = 42", {NUMBER_ATTRIBUTE}, False, id="type_suffix_selects_the_number_attribute"),
pytest.param("service.name = 'svc-a'", {COLUMN_ONLY, BOTH}, True, id="bare_resource_wins_with_warning"),
pytest.param("service.name != 'svc-a'", {ATTRIBUTE_ONLY, NEITHER, NUMBER_ATTRIBUTE}, True, id="bare_resource_negative"),
pytest.param("resource.service.name = 'svc-a'", {COLUMN_ONLY, BOTH}, False, id="resource_context_no_warning"),
pytest.param("resource.service.name != 'svc-a'", {ATTRIBUTE_ONLY, NEITHER, NUMBER_ATTRIBUTE}, False, id="resource_context_negative"),
pytest.param("attribute.service.name = 'svc-a'", {ATTRIBUTE_ONLY, BOTH}, False, id="attribute_context_no_warning"),
pytest.param(
"{own}.route.tag = 'checkout'",
{"traces": {COLUMN_ONLY, BOTH}, "logs": {COLUMN_ONLY, ATTRIBUTE_ONLY, BOTH, NEITHER, NUMBER_ATTRIBUTE}},
False,
id="own_context_miss_corrects_to_attribute_and_on_logs_to_body",
),
pytest.param("route.tag = 'checkout'", {COLUMN_ONLY, BOTH}, False, id="bare_attribute_only_key"),
]
SIGNALS = [
pytest.param("traces", "span", "name", "checkout", "other", id="traces"),
pytest.param("logs", "log", "severity_text", "ERROR", "INFO", id="logs"),
]
@pytest.mark.parametrize("expression_template,expected,expects_ambiguity_warning", FILTER_MATRIX)
@pytest.mark.parametrize("signal,own_context,contested,value,other_value", SIGNALS)
def test_filter_resolution(
signoz: types.SigNoz,
create_user_admin: None, # pylint: disable=unused-argument
get_token: Callable[[str, str], str],
ambiguous_rows: datetime,
signal: str,
own_context: str,
contested: str,
value: str,
other_value: str, # pylint: disable=unused-argument
expression_template: str,
expected: set[str] | dict[str, set[str]],
expects_ambiguity_warning: bool,
) -> None:
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
expression = expression_template.format(own=own_context, contested=contested, value=value)
response = make_query_request(
signoz,
token,
start_ms=int((ambiguous_rows - timedelta(minutes=2)).timestamp() * 1000),
end_ms=int((ambiguous_rows + 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_KEY}],
)
],
)
assert response.status_code == HTTPStatus.OK, response.text
matched = {row for row in get_column_data_from_response(response.json(), IDENTITY_KEY) if row.startswith(EXPLICIT_PREFIX)}
assert matched == (expected[signal] if isinstance(expected, dict) else expected), expression
warnings = [w["message"] for w in get_all_warnings(response.json())]
assert any("ambiguous" in w for w in warnings) == expects_ambiguity_warning, warnings
# Group by resolves the contested name in the column stage: a bare name that
# is both a column and an attribute groups by the column alone, an explicit
# context groups by that context alone.
GROUP_BY_MATRIX = [
pytest.param(None, {"{value}": 2, "{other}": 3}, id="bare_groups_by_the_column"),
pytest.param("own", {"{value}": 2, "{other}": 3}, id="own_context_groups_by_the_column"),
pytest.param("attribute", {"{value}": 2}, id="attribute_context_groups_by_the_attribute"),
]
@pytest.mark.parametrize("context,expected_template", GROUP_BY_MATRIX)
@pytest.mark.parametrize("signal,own_context,contested,value,other_value", SIGNALS)
def test_group_by_resolution(
signoz: types.SigNoz,
create_user_admin: None, # pylint: disable=unused-argument
get_token: Callable[[str, str], str],
ambiguous_rows: datetime,
signal: str,
own_context: str,
contested: str,
value: str,
other_value: str,
context: str | None,
expected_template: dict[str, int],
) -> None:
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
field_context = own_context if context == "own" else context
response = make_query_request(
signoz,
token,
start_ms=int((ambiguous_rows - timedelta(minutes=2)).timestamp() * 1000),
end_ms=int((ambiguous_rows + timedelta(minutes=1)).timestamp() * 1000),
request_type=RequestType.SCALAR,
queries=[
build_scalar_query(
"A",
signal,
[build_aggregation("count()", "rows")],
group_by=[build_group_by_field(contested, "string", field_context) if field_context else {"name": contested}],
filter_expression=f"{IDENTITY_KEY} LIKE '{EXPLICIT_PREFIX}%'",
)
],
)
assert response.status_code == HTTPStatus.OK, response.text
expected = {key.format(value=value, other=other_value): count for key, count in expected_template.items()}
groups = {row[0]: row[1] for row in get_scalar_table_data(response.json()) if row[0] in expected}
assert groups == expected, get_scalar_table_data(response.json())
# A raw select of a bare name that is both a resource and an attribute reads
# one value per row: the resource value, also on the row whose attribute
# carries a different value.
@pytest.mark.parametrize("signal", ["traces", "logs"])
def test_select_of_ambiguous_name(
signoz: types.SigNoz,
create_user_admin: None, # pylint: disable=unused-argument
get_token: Callable[[str, str], str],
ambiguous_rows: datetime,
signal: str,
) -> None:
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
response = make_query_request(
signoz,
token,
start_ms=int((ambiguous_rows - timedelta(minutes=2)).timestamp() * 1000),
end_ms=int((ambiguous_rows + timedelta(minutes=1)).timestamp() * 1000),
request_type=RequestType.RAW,
queries=[
build_raw_query(
"A",
signal,
limit=100,
filter_expression=f"{IDENTITY_KEY} LIKE '{EXPLICIT_PREFIX}%'",
order=[build_order_by("timestamp", "asc")],
select_fields=[{"name": IDENTITY_KEY}, {"name": "service.name"}],
)
],
)
assert response.status_code == HTTPStatus.OK, response.text
rows = response.json()["data"]["data"]["results"][0]["rows"] or []
by_identity = {row["data"][IDENTITY_KEY]: row["data"]["service.name"] for row in rows if row["data"].get(IDENTITY_KEY, "").startswith(EXPLICIT_PREFIX)}
assert by_identity == {
COLUMN_ONLY: "svc-a",
ATTRIBUTE_ONLY: "svc-b",
BOTH: "svc-a",
NEITHER: "svc-b",
NUMBER_ATTRIBUTE: "svc-b",
}
# Order by resolves the contested name in the column stage, descending, with
# the timestamp descending as the tie breaker. A bare or own-context name
# sorts by the column alone. An explicit attribute context sorts by the
# attribute on traces, where the number attribute reads as text and rows
# without the attribute come last; on logs it still sorts by the column.
BY_COLUMN = [ATTRIBUTE_ONLY, NEITHER, NUMBER_ATTRIBUTE, COLUMN_ONLY, BOTH]
ORDER_BY_MATRIX = [
pytest.param(None, {"traces": BY_COLUMN, "logs": BY_COLUMN}, id="bare_orders_by_the_column"),
pytest.param("own", {"traces": BY_COLUMN, "logs": BY_COLUMN}, id="own_context_orders_by_the_column"),
pytest.param(
"attribute",
{"traces": [ATTRIBUTE_ONLY, BOTH, NUMBER_ATTRIBUTE, COLUMN_ONLY, NEITHER], "logs": BY_COLUMN},
id="attribute_context_orders_by_the_attribute_on_traces_only",
),
]
@pytest.mark.parametrize("context,expected", ORDER_BY_MATRIX)
@pytest.mark.parametrize("signal,own_context,contested,value,other_value", SIGNALS)
def test_order_by_resolution(
signoz: types.SigNoz,
create_user_admin: None, # pylint: disable=unused-argument
get_token: Callable[[str, str], str],
ambiguous_rows: datetime,
signal: str,
own_context: str,
contested: str,
value: str, # pylint: disable=unused-argument
other_value: str, # pylint: disable=unused-argument
context: str | None,
expected: dict[str, list[str]],
) -> None:
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
prefix = f"{own_context}." if context == "own" else f"{context}." if context else ""
response = make_query_request(
signoz,
token,
start_ms=int((ambiguous_rows - timedelta(minutes=2)).timestamp() * 1000),
end_ms=int((ambiguous_rows + timedelta(minutes=1)).timestamp() * 1000),
request_type=RequestType.RAW,
queries=[
build_raw_query(
"A",
signal,
limit=100,
filter_expression=f"{IDENTITY_KEY} LIKE '{EXPLICIT_PREFIX}%'",
order=[build_order_by(f"{prefix}{contested}", "desc"), build_order_by("timestamp", "desc")],
select_fields=[{"name": IDENTITY_KEY}],
)
],
)
assert response.status_code == HTTPStatus.OK, response.text
ordered = [row for row in get_column_data_from_response(response.json(), IDENTITY_KEY) if row.startswith(EXPLICIT_PREFIX)]
assert ordered == expected[signal]
# An aggregation argument resolves the contested name in the column stage: a
# bare name counts the column's values alone; an attribute context counts the
# attribute in both of its data types, so the number attribute adds a
# distinct value.
AGGREGATION_MATRIX = [
pytest.param(None, 2, id="bare_counts_the_column"),
pytest.param("own", 2, id="own_context_counts_the_column"),
pytest.param("attribute", 2, id="attribute_context_counts_both_attribute_types"),
]
@pytest.mark.parametrize("context,expected", AGGREGATION_MATRIX)
@pytest.mark.parametrize("signal,own_context,contested,value,other_value", SIGNALS)
def test_aggregation_argument_resolution(
signoz: types.SigNoz,
create_user_admin: None, # pylint: disable=unused-argument
get_token: Callable[[str, str], str],
ambiguous_rows: datetime,
signal: str,
own_context: str,
contested: str,
value: str, # pylint: disable=unused-argument
other_value: str, # pylint: disable=unused-argument
context: str | None,
expected: int,
) -> None:
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
prefix = f"{own_context}." if context == "own" else f"{context}." if context else ""
response = make_query_request(
signoz,
token,
start_ms=int((ambiguous_rows - timedelta(minutes=2)).timestamp() * 1000),
end_ms=int((ambiguous_rows + timedelta(minutes=1)).timestamp() * 1000),
request_type=RequestType.SCALAR,
queries=[
build_scalar_query(
"A",
signal,
[build_aggregation(f"count_distinct({prefix}{contested})", "distinct")],
filter_expression=f"{IDENTITY_KEY} LIKE '{EXPLICIT_PREFIX}%'",
)
],
)
assert response.status_code == HTTPStatus.OK, response.text
assert_scalar_value(response, "A", expected)
# Logs only. `body.x` addresses the body JSON and never the same-named
# attribute; `log.x` reads the attribute and the body JSON path together,
# even when the attribute exists in metadata. A `scope.` key is a strict
# context resolved through metadata alone: the declared scope path
# `scope.name` and a scope attribute both answer "key not found" when
# metadata does not report them, even when the rows carry them.
LOGS_ONLY_MATRIX = [
pytest.param("body.route.tag = 'checkout'", {ATTRIBUTE_ONLY, NEITHER, NUMBER_ATTRIBUTE}, id="body_context_reads_the_body_json"),
pytest.param("log.route.tag = 'checkout'", {COLUMN_ONLY, ATTRIBUTE_ONLY, BOTH, NEITHER, NUMBER_ATTRIBUTE}, id="log_context_reads_attribute_and_body"),
pytest.param("scope.name = 'scope-a'", "key `name` not found", id="scope_name_needs_metadata"),
pytest.param("scope.env = 'prod'", "key `env` not found", id="scope_attribute_needs_metadata"),
pytest.param("scope.env EXISTS", "key `env` not found", id="scope_attribute_exists_needs_metadata"),
]
@pytest.mark.parametrize("expression,expected", LOGS_ONLY_MATRIX)
def test_logs_body_and_scope_contexts(
signoz: types.SigNoz,
create_user_admin: None, # pylint: disable=unused-argument
get_token: Callable[[str, str], str],
ambiguous_rows: datetime,
expression: str,
expected: set[str] | str,
) -> None:
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
response = make_query_request(
signoz,
token,
start_ms=int((ambiguous_rows - timedelta(minutes=2)).timestamp() * 1000),
end_ms=int((ambiguous_rows + timedelta(minutes=1)).timestamp() * 1000),
request_type=RequestType.RAW,
queries=[
build_raw_query(
"A",
"logs",
limit=100,
filter_expression=expression,
order=[build_order_by("timestamp", "asc")],
select_fields=[{"name": IDENTITY_KEY}],
)
],
)
if isinstance(expected, str):
assert response.status_code == HTTPStatus.BAD_REQUEST, response.text
assert expected in response.text, response.text
return
assert response.status_code == HTTPStatus.OK, response.text
matched = {row for row in get_column_data_from_response(response.json(), IDENTITY_KEY) if row.startswith(EXPLICIT_PREFIX)}
assert matched == expected, expression

View File

@@ -0,0 +1,235 @@
from collections.abc import Callable
from datetime import UTC, datetime, timedelta
from http import HTTPStatus
import pytest
import requests
from fixtures import types
from fixtures.auth import USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD
from fixtures.logs import Logs
from fixtures.traces import Traces
@pytest.mark.parametrize(
"signal,field_context,present,absent",
[
pytest.param("logs", "log", {"severity_text": "log", "body": "log", "trace_id": "log"}, ["code.file", "scope_name"], id="log_context_lists_log_intrinsics"),
pytest.param("logs", "scope", {"scope_name": "scope", "scope_version": "scope"}, ["severity_text", "body", "code.file"], id="scope_context_lists_scope_intrinsics_for_logs"),
pytest.param("logs", "attribute", {"code.file": "attribute"}, ["body", "scope_name"], id="attribute_context_excludes_log_intrinsics"),
pytest.param("traces", "span", {"name": "span", "has_error": "span", "isRoot": "span", "http.method": "attribute"}, ["scope.name"], id="span_context_lists_span_intrinsics_and_attributes"),
pytest.param("traces", "scope", {"scope.name": "scope", "scope.version": "scope"}, ["name", "has_error", "isRoot", "http.method", "host.name"], id="scope_context_lists_scope_intrinsics_for_traces"),
pytest.param("traces", "resource", {"host.name": "resource"}, ["name", "has_error", "isRoot", "http.method"], id="resource_context_excludes_span_intrinsics"),
pytest.param("traces", "attribute", {"http.method": "attribute"}, ["name", "has_error", "isRoot", "host.name"], id="attribute_context_excludes_span_intrinsics"),
],
)
def test_fields_keys_by_context(
signoz: types.SigNoz,
create_user_admin: None, # pylint: disable=unused-argument
get_token: Callable[[str, str], str],
insert_logs: Callable[[list[Logs]], None],
insert_traces: Callable[[list[Traces]], None],
signal: str,
field_context: str,
present: dict[str, str],
absent: list[str],
) -> None:
"""
Setup:
Insert a log with a code.file attribute and a span with an http.method attribute and a host.name resource.
Tests:
1. Keys for a context list that context's intrinsic columns and the stored keys the context maps to,
each with its context; intrinsics of other contexts are not listed. The span context also keeps
listing attributes because `span.<attribute>` resolves attributes in queries.
"""
now = datetime.now(tz=UTC)
insert_logs([Logs(timestamp=now, attributes={"code.file": "/opt/integration.go"}, body="a log line")])
insert_traces([Traces(timestamp=now, resources={"host.name": "linux-001"}, attributes={"http.method": "GET"})])
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
response = requests.get(
signoz.self.host_configs["8080"].get("/api/v1/fields/keys"),
timeout=2,
headers={"authorization": f"Bearer {token}"},
params={"signal": signal, "fieldContext": field_context},
)
assert response.status_code == HTTPStatus.OK
keys = response.json()["data"]["keys"]
listed = {name: [key["fieldContext"] for key in keys.get(name, [])] for name in present}
assert listed == {name: [context] for name, context in present.items()}, f"keys for the {field_context} context"
assert [name for name in absent if name in keys] == [], f"keys that do not belong to the {field_context} context"
@pytest.mark.parametrize(
"signal,field_context,field_data_type,present,absent",
[
pytest.param("traces", "span", "float64", ["duration_nano", "status_code"], ["name", "has_error"], id="float64_matches_number_span_intrinsics"),
pytest.param("traces", "span", "int64", ["duration_nano", "status_code"], ["name", "has_error"], id="int64_matches_number_span_intrinsics"),
pytest.param("traces", "span", "bool", ["has_error", "isRoot", "isEntryPoint"], ["name", "duration_nano"], id="bool_matches_bool_span_intrinsics"),
pytest.param("traces", "span", "string", ["name", "http_method"], ["duration_nano", "has_error"], id="string_matches_string_span_intrinsics"),
pytest.param("logs", "log", "number", ["severity_number", "trace_flags"], ["severity_text", "body"], id="number_matches_number_log_intrinsics"),
],
)
def test_fields_keys_by_data_type(
signoz: types.SigNoz,
create_user_admin: None, # pylint: disable=unused-argument
get_token: Callable[[str, str], str],
signal: str,
field_context: str,
field_data_type: str,
present: list[str],
absent: list[str],
) -> None:
"""
Tests:
1. A data type filter keeps the intrinsic columns of that type; number, int64 and float64 are one family.
"""
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
response = requests.get(
signoz.self.host_configs["8080"].get("/api/v1/fields/keys"),
timeout=2,
headers={"authorization": f"Bearer {token}"},
params={"signal": signal, "fieldContext": field_context, "fieldDataType": field_data_type},
)
assert response.status_code == HTTPStatus.OK
keys = response.json()["data"]["keys"]
assert [name for name in present if name not in keys] == [], f"intrinsics of type {field_data_type}"
assert [name for name in absent if name in keys] == [], f"intrinsics not of type {field_data_type}"
@pytest.mark.parametrize(
"signal,search_text,present",
[
pytest.param("logs", "SEVERITY", ["severity_text", "severity_number"], id="upper_case_search_logs"),
pytest.param("traces", "HTTP_", ["http_method", "http_host", "http_url"], id="upper_case_search_traces"),
pytest.param("traces", "Duration", ["duration_nano"], id="mixed_case_search_traces"),
pytest.param("traces", "span.HAS_ERR", ["has_error"], id="context_prefix_with_upper_case_search"),
],
)
def test_fields_keys_search_matches_intrinsics_case_insensitively(
signoz: types.SigNoz,
create_user_admin: None, # pylint: disable=unused-argument
get_token: Callable[[str, str], str],
signal: str,
search_text: str,
present: list[str],
) -> None:
"""
Tests:
1. The search text matches intrinsic columns case-insensitively, as it does for stored keys,
with or without a context prefix.
"""
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
response = requests.get(
signoz.self.host_configs["8080"].get("/api/v1/fields/keys"),
timeout=2,
headers={"authorization": f"Bearer {token}"},
params={"signal": signal, "searchText": search_text},
)
assert response.status_code == HTTPStatus.OK
keys = response.json()["data"]["keys"]
assert [name for name in present if name not in keys] == [], f"intrinsics matching {search_text!r}"
@pytest.mark.parametrize(
"signal,params,expected",
[
pytest.param("traces", {"name": "has_error"}, [True, False], id="calculated_bool_span_field"),
pytest.param("traces", {"name": "has_error", "fieldContext": "span"}, [True, False], id="calculated_bool_span_field_with_context"),
pytest.param("traces", {"name": "has_error", "searchText": "tr"}, [True], id="search_text_narrows_bool_values"),
pytest.param("traces", {"name": "isRoot"}, [True], id="span_scope_field_is_true_only"),
pytest.param("logs", {"name": "retry"}, [True, False], id="bool_attribute_from_tag_rows"),
pytest.param("logs", {"name": "retry", "fieldContext": "attribute"}, [True, False], id="bool_attribute_with_context"),
pytest.param("logs", {"name": "retry", "searchText": "tr"}, [True], id="search_text_narrows_stored_bool_values"),
pytest.param("logs", {"name": "never_seen", "fieldDataType": "bool"}, [True, False], id="declared_bool_type_needs_no_rows"),
],
)
def test_fields_values_bool_fields(
signoz: types.SigNoz,
create_user_admin: None, # pylint: disable=unused-argument
get_token: Callable[[str, str], str],
insert_logs: Callable[[list[Logs]], None],
signal: str,
params: dict[str, str],
expected: list[bool],
) -> None:
"""
Setup:
Insert a log with a bool attribute.
Tests:
1. Values for a bool field are true and false (narrowed by the search text): for the calculated span
field, for a stored bool attribute whose tag rows carry no value, and for a key the caller
declares bool.
2. A span scope selector (isRoot) only takes true.
"""
insert_logs([Logs(timestamp=datetime.now(tz=UTC), attributes={"retry": True}, body="retrying")])
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
response = requests.get(
signoz.self.host_configs["8080"].get("/api/v1/fields/values"),
timeout=2,
headers={"authorization": f"Bearer {token}"},
params={"signal": signal, **params},
)
assert response.status_code == HTTPStatus.OK
assert response.json()["data"]["values"]["boolValues"] == expected
assert response.json()["data"]["complete"] is True
def test_fields_values_start_excludes_span_values_not_seen_since_the_day(
signoz: types.SigNoz,
create_user_admin: None, # pylint: disable=unused-argument
get_token: Callable[[str, str], str],
insert_traces: Callable[[list[Traces]], None],
) -> None:
"""
Setup:
Insert a span three days old and a span now, with different service names.
Tests:
1. Values with startUnixMilli an hour ago contain only the service seen today: the start is
floored to the day, the tag table's deduplication unit.
2. Values without a start contain both services.
Logs are not covered: the logs collector stamps tag rows with the ingestion hour, not the
log's timestamp, and the fixture writes the log's timestamp.
"""
signal = "traces"
now = datetime.now(tz=UTC)
insert_traces(
[
Traces(timestamp=now - timedelta(days=3), resources={"service.name": "archived-service"}),
Traces(timestamp=now, resources={"service.name": "live-service"}),
]
)
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
response = requests.get(
signoz.self.host_configs["8080"].get("/api/v1/fields/values"),
timeout=2,
headers={"authorization": f"Bearer {token}"},
params={
"signal": signal,
"name": "service.name",
"startUnixMilli": int((now - timedelta(hours=1)).timestamp() * 1000),
},
)
assert response.status_code == HTTPStatus.OK
assert response.json()["data"]["values"]["stringValues"] == ["live-service"], "values last seen before the start must be dropped"
response = requests.get(
signoz.self.host_configs["8080"].get("/api/v1/fields/values"),
timeout=2,
headers={"authorization": f"Bearer {token}"},
params={"signal": signal, "name": "service.name"},
)
assert response.status_code == HTTPStatus.OK
assert set(response.json()["data"]["values"]["stringValues"]) == {"archived-service", "live-service"}

View File

@@ -71,7 +71,7 @@ def test_v1_get_serves_legacy_shape(
assert response.status_code == HTTPStatus.OK, response.text
filters = response.json()["data"]["filters"]
assert filters[0]["key"] == "duration_nano"
assert filters[0]["type"] == "tag"
assert filters[0]["type"] == "", "span fields have no v3 attribute type"
assert filters[0]["dataType"] == "float64"
assert all("name" not in legacy_filter for legacy_filter in filters)
@@ -274,3 +274,36 @@ def test_update_quick_filters_rejects_invalid_input(
timeout=2,
)
assert response.status_code == HTTPStatus.BAD_REQUEST, response.text
def test_default_traces_filters_are_served_as_the_fields_api_serves_them(
signoz: types.SigNoz,
create_user_admin: types.Operation, # pylint: disable=unused-argument
get_token: Callable[[str, str], str],
):
admin_token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
response = requests.get(
signoz.self.host_configs["8080"].get("/api/v2/quick_filters/traces"),
headers={"Authorization": f"Bearer {admin_token}"},
timeout=2,
)
assert response.status_code == HTTPStatus.OK, response.text
filters = {field_key["name"]: field_key for field_key in response.json()["data"]["filters"]}
assert "hasError" not in filters
assert (filters["has_error"]["fieldContext"], filters["has_error"]["fieldDataType"]) == ("span", "bool")
assert (filters["name"]["fieldContext"], filters["name"]["fieldDataType"]) == ("span", "string")
assert (filters["duration_nano"]["fieldContext"], filters["duration_nano"]["fieldDataType"]) == ("span", "number")
assert (filters["http.route"]["fieldContext"], filters["http.route"]["fieldDataType"]) == ("attribute", "string")
for name in ("has_error", "name"):
response = requests.get(
signoz.self.host_configs["8080"].get("/api/v1/fields/keys"),
headers={"Authorization": f"Bearer {admin_token}"},
timeout=2,
params={"signal": "traces", "searchText": name, "fieldContext": filters[name]["fieldContext"]},
)
assert response.status_code == HTTPStatus.OK, response.text
served = response.json()["data"]["keys"][name]
assert (filters[name]["fieldContext"], filters[name]["fieldDataType"]) in [(key["fieldContext"], key["fieldDataType"]) for key in served]