VictoriaMetrics/lib/logstorage/pipe_delete.go
Aliaksandr Valialkin ad6c587494
lib/logstorage: properly propagate extra filters to all the subqueries
The purpose of extra filters ( https://docs.victoriametrics.com/victorialogs/querying/#extra-filters )
is to limit the subset of logs, which can be queried. For example, it is expected that all the queries
with `extra_filters={tenant=123}` can access only logs, which contain `123` value for the `tenant` field.

Previously this wasn't the case, since the provided extra filters weren't applied to subqueries.
For example, the following query could be used to select all the logs outside `tenant=123`, for any `extra_filters` arg:

    * | union({tenant!=123})

This commit fixes this by propagating extra filters to all the subqueries.

While at it, this commit also properly propagates [start, end] time range filter from HTTP querying APIs
into all the subqueries, since this is what most users expect. This behaviour can be overriden on per-subquery
basis with the `options(ignore_global_time_filter=true)` option - see https://docs.victoriametrics.com/victorialogs/logsql/#query-options

Also properly apply apply optimizations across all the subqueries. Previously the optimizations at Query.optimize()
function were applied only to the top-level query.
2025-01-24 18:49:25 +01:00

100 lines
2.1 KiB
Go

package logstorage
import (
"fmt"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
)
// pipeDelete implements '| delete ...' pipe.
//
// See https://docs.victoriametrics.com/victorialogs/logsql/#delete-pipe
type pipeDelete struct {
// fields contains a list of fields to delete
fields []string
}
func (pd *pipeDelete) String() string {
if len(pd.fields) == 0 {
logger.Panicf("BUG: pipeDelete must contain at least a single field")
}
return "delete " + fieldNamesString(pd.fields)
}
func (pd *pipeDelete) canLiveTail() bool {
return true
}
func (pd *pipeDelete) updateNeededFields(neededFields, unneededFields fieldsSet) {
if neededFields.contains("*") {
unneededFields.addFields(pd.fields)
} else {
neededFields.removeFields(pd.fields)
}
}
func (pd *pipeDelete) hasFilterInWithQuery() bool {
return false
}
func (pd *pipeDelete) initFilterInValues(_ *inValuesCache, _ getFieldValuesFunc) (pipe, error) {
return pd, nil
}
func (pd *pipeDelete) visitSubqueries(_ func(q *Query)) {
// nothing to do
}
func (pd *pipeDelete) newPipeProcessor(_ int, _ <-chan struct{}, _ func(), ppNext pipeProcessor) pipeProcessor {
return &pipeDeleteProcessor{
pd: pd,
ppNext: ppNext,
}
}
type pipeDeleteProcessor struct {
pd *pipeDelete
ppNext pipeProcessor
}
func (pdp *pipeDeleteProcessor) writeBlock(workerID uint, br *blockResult) {
if br.rowsLen == 0 {
return
}
br.deleteColumns(pdp.pd.fields)
pdp.ppNext.writeBlock(workerID, br)
}
func (pdp *pipeDeleteProcessor) flush() error {
return nil
}
func parsePipeDelete(lex *lexer) (pipe, error) {
if !lex.isKeyword("delete", "del", "rm", "drop") {
return nil, fmt.Errorf("expecting 'delete', 'del', 'rm' or 'drop'; got %q", lex.token)
}
var fields []string
for {
lex.nextToken()
field, err := parseFieldName(lex)
if err != nil {
return nil, fmt.Errorf("cannot parse field name: %w", err)
}
fields = append(fields, field)
switch {
case lex.isKeyword("|", ")", ""):
pd := &pipeDelete{
fields: fields,
}
return pd, nil
case lex.isKeyword(","):
default:
return nil, fmt.Errorf("unexpected token: %q; expecting ',', '|' or ')'", lex.token)
}
}
}