app/vmselect: add -search.treatDotsAsIsInRegexps command-line flag for automatic escaping of dots in regexp label filters

app/vmselect/promql/exec.go

@@ -5,6 +5,7 @@ import (
 	"fmt"
 	"math"
 	"sort"
+	"strings"
 	"sync"
 	"sync/atomic"
 	"time"
@@ -15,7 +16,13 @@ import (
 	"github.com/VictoriaMetrics/metricsql"
 )
 
-var logSlowQueryDuration = flag.Duration("search.logSlowQueryDuration", 5*time.Second, "Log queries with execution time exceeding this value. Zero disables slow query logging")
+var (
+	logSlowQueryDuration   = flag.Duration("search.logSlowQueryDuration", 5*time.Second, "Log queries with execution time exceeding this value. Zero disables slow query logging")
+	treatDotsAsIsInRegexps = flag.Bool("search.treatDotsAsIsInRegexps", false, "Whether to treat dots as is in regexp label filters used in queries. "+
+		`For example, foo{bar=~"a.b.c"} will be automatically converted to foo{bar=~"a\\.b\\.c"}, i.e. all the dots in regexp filters will be automatically escaped `+
+		`in order to match only dot char instead of matching any char. Dots in ".+", ".*" and ".{n}" regexps aren't escaped. `+
+		`Such escaping can be useful when querying Graphite data`)
+)
 
 var slowQueries = metrics.NewCounter(`vm_slow_queries_total`)
 
@@ -177,6 +184,9 @@ func parsePromQLWithCache(q string) (metricsql.Expr, error) {
 		if err == nil {
 			e = metricsql.Optimize(e)
 			e = adjustCmpOps(e)
+			if *treatDotsAsIsInRegexps {
+				e = escapeDotsInRegexpLabelFilters(e)
+			}
 		}
 		pcv = &parseCacheValue{
 			e:   e,
@@ -190,6 +200,41 @@ func parsePromQLWithCache(q string) (metricsql.Expr, error) {
 	return pcv.e, nil
 }
 
+func escapeDotsInRegexpLabelFilters(e metricsql.Expr) metricsql.Expr {
+	metricsql.VisitAll(e, func(expr metricsql.Expr) {
+		me, ok := expr.(*metricsql.MetricExpr)
+		if !ok {
+			return
+		}
+		for i := range me.LabelFilters {
+			f := &me.LabelFilters[i]
+			if f.IsRegexp {
+				f.Value = escapeDots(f.Value)
+			}
+		}
+	})
+	return e
+}
+
+func escapeDots(s string) string {
+	dotsCount := strings.Count(s, ".")
+	if dotsCount <= 0 {
+		return s
+	}
+	result := make([]byte, 0, len(s)+2*dotsCount)
+	for i := 0; i < len(s); i++ {
+		if s[i] == '.' && (i == 0 || s[i-1] != '\\') && (i+1 == len(s) || i+1 < len(s) && s[i+1] != '*' && s[i+1] != '+' && s[i+1] != '{') {
+			// Escape a dot if the following conditions are met:
+			// - if it isn't escaped already, i.e. if there is no `\` char before the dot.
+			// - if there is no regexp modifiers such as '+', '*' or '{' after the dot.
+			result = append(result, '\\', '.')
+		} else {
+			result = append(result, s[i])
+		}
+	}
+	return string(result)
+}
+
 var parseCacheV = func() *parseCache {
 	pc := &parseCache{
 		m: make(map[string]*parseCacheValue),

app/vmselect/promql/exec_test.go

@@ -8,8 +8,46 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmselect/searchutils"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/storage"
+	"github.com/VictoriaMetrics/metricsql"
 )
 
+func TestEscapeDots(t *testing.T) {
+	f := func(s, resultExpected string) {
+		t.Helper()
+		result := escapeDots(s)
+		if result != resultExpected {
+			t.Fatalf("unexpected result for escapeDots(%q); got\n%s\nwant\n%s", s, result, resultExpected)
+		}
+	}
+	f("", "")
+	f("a", "a")
+	f("foobar", "foobar")
+	f(".", `\.`)
+	f(".*", `.*`)
+	f(".+", `.+`)
+	f("..", `\.\.`)
+	f("foo.b.{2}ar..+baz.*", `foo\.b.{2}ar\..+baz.*`)
+}
+
+func TestEscapeDotsInRegexpLabelFilters(t *testing.T) {
+	f := func(s, resultExpected string) {
+		t.Helper()
+		e, err := metricsql.Parse(s)
+		if err != nil {
+			t.Fatalf("unexpected error in metricsql.Parse(%q): %s", s, err)
+		}
+		e = escapeDotsInRegexpLabelFilters(e)
+		result := e.AppendString(nil)
+		if string(result) != resultExpected {
+			t.Fatalf("unexpected result for escapeDotsInRegexpLabelFilters(%q);\ngot\n%s\nwant\n%s", s, result, resultExpected)
+		}
+	}
+	f("2", "2")
+	f(`foo.bar + 123`, `foo.bar + 123`)
+	f(`foo{bar=~"baz.xx.yyy"}`, `foo{bar=~"baz\\.xx\\.yyy"}`)
+	f(`foo(a.b{c="d.e",x=~"a.b.+[.a]",y!~"aaa.bb|cc.dd"}) + x.y(1,sum({x=~"aa.bb"}))`, `foo(a.b{c="d.e", x=~"a\\.b.+[\\.a]", y!~"aaa\\.bb|cc\\.dd"}) + x.y(1, sum({x=~"aa\\.bb"}))`)
+}
+
 func TestExecSuccess(t *testing.T) {
 	accountID := uint32(123)
 	projectID := uint32(567)

docs/CHANGELOG.md

@@ -7,6 +7,9 @@
 * FEATURE: vmagent: add `-promscrape.dropOriginalLabels` command-line option, which can be used for reducing memory usage when scraping big number of targets.
   See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/825#issuecomment-724308361 for details.
 * FEATURE: vmalert: explicitly set extra labels to alert entities. See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/870
+* FEATURE: add `-search.treatDotsAsIsInRegexps` command-line flag, which can be used for automatic escaping of dots in regexp label filters used in queries.
+  For example, if `-search.treatDotsAsIsInRegexps` is set, then the query `foo{bar=~"aaa.bb.cc|dd.eee"}` is automatically converted to `foo{bar=~"aaa\\.bb\\.cc|dd\\.eee"}`.
+  This may be useful for querying Graphite data.
 
 * BUGFIX: do not return data points in the end of the selected time range for time series ending in the middle of the selected time range.
   See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/887 and https://github.com/VictoriaMetrics/VictoriaMetrics/issues/845