From 774f7ca1c1c6b57c99adfc17765f1657d0617677 Mon Sep 17 00:00:00 2001
From: nicbaz <nicolas@linux.com>
Date: Tue, 23 Jun 2020 22:50:33 +0200
Subject: [PATCH] vmselect: fix label_replace when mismatch (#579)

As per documentation on `label_replace` function: "If the regular
expression doesn't match then the timeseries is returned unchanged".

Currently this behavior is not enforced, if a regexp on an existing
tag doesn't match then the tag value is copied as-is in the destination
tag. This fix first checks that the regular expression matches the
source tag before applying anything.

Given the current implementation, this fix also changes the behavior
of the **MetricsQL** `label_transform` function which does not
document this behavior at the moment.
---
 app/vmselect/promql/exec_test.go | 17 ++++++++++++++++-
 app/vmselect/promql/transform.go |  3 +++
 2 files changed, 19 insertions(+), 1 deletion(-)

diff --git a/app/vmselect/promql/exec_test.go b/app/vmselect/promql/exec_test.go
index f6f8dfb01d..a7c015d9b0 100644
--- a/app/vmselect/promql/exec_test.go
+++ b/app/vmselect/promql/exec_test.go
@@ -1480,7 +1480,7 @@ func TestExecSuccess(t *testing.T) {
 		resultExpected := []netstorage.Result{r}
 		f(q, resultExpected)
 	})
-	t.Run(`label_replace(mismatch)`, func(t *testing.T) {
+	t.Run(`label_replace(nonexisting_src)`, func(t *testing.T) {
 		t.Parallel()
 		q := `label_replace(time(), "__name__", "x${1}y", "foo", ".+")`
 		r := netstorage.Result{
@@ -1491,6 +1491,21 @@ func TestExecSuccess(t *testing.T) {
 		resultExpected := []netstorage.Result{r}
 		f(q, resultExpected)
 	})
+	t.Run(`label_replace(mismatch)`, func(t *testing.T) {
+		t.Parallel()
+		q := `label_replace(label_set(time(), "foo", "foobar"), "__name__", "x${1}y", "foo", "bar(.+)")`
+		r := netstorage.Result{
+			MetricName: metricNameExpected,
+			Values:     []float64{1000, 1200, 1400, 1600, 1800, 2000},
+			Timestamps: timestampsExpected,
+		}
+		r.MetricName.Tags = []storage.Tag{{
+			Key:   []byte("foo"),
+			Value: []byte("foobar"),
+		}}
+		resultExpected := []netstorage.Result{r}
+		f(q, resultExpected)
+	})
 	t.Run(`label_replace(match)`, func(t *testing.T) {
 		t.Parallel()
 		q := `label_replace(time(), "__name__", "x${1}y", "foo", ".*")`
diff --git a/app/vmselect/promql/transform.go b/app/vmselect/promql/transform.go
index b08f9e8a42..1f0f858127 100644
--- a/app/vmselect/promql/transform.go
+++ b/app/vmselect/promql/transform.go
@@ -1219,6 +1219,9 @@ func labelReplace(tss []*timeseries, srcLabel string, r *regexp.Regexp, dstLabel
 		mn := &ts.MetricName
 		dstValue := getDstValue(mn, dstLabel)
 		srcValue := mn.GetTagValue(srcLabel)
+		if !r.Match(srcValue) {
+			continue
+		}
 		b := r.ReplaceAll(srcValue, replacementBytes)
 		*dstValue = append((*dstValue)[:0], b...)
 		if len(b) == 0 {