From dad8b76a0e9031aa0e4bf4570e4e469ab9b485bf Mon Sep 17 00:00:00 2001
From: Aliaksandr Valialkin <valyala@gmail.com>
Date: Tue, 24 Nov 2020 12:26:17 +0200
Subject: [PATCH] lib/protoparser/prometheus: properly parse metrics with
 exemplars

Examplars have been introduced in OpenMetrics - see https://github.com/OpenObservability/OpenMetrics/blob/master/OpenMetrics.md#exemplars-1
Previously VictoriaMetrics couldn't parse the following metric

    foo{bar="baz"} 123 # exemplar here

This commit fixes this. Note that VictoriaMetrics ignores the exemplar as for now.
---
 docs/CHANGELOG.md                         |  2 ++
 lib/protoparser/prometheus/parser.go      | 15 ++++++++++-
 lib/protoparser/prometheus/parser_test.go | 31 +++++++++++++++++++++++
 3 files changed, 47 insertions(+), 1 deletion(-)

diff --git a/docs/CHANGELOG.md b/docs/CHANGELOG.md
index 66d91bd554..fd8ea4f262 100644
--- a/docs/CHANGELOG.md
+++ b/docs/CHANGELOG.md
@@ -19,6 +19,8 @@ See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/851
 * FEATURE: add remoteAddr to slow query log in order to simplify identifying the client that sends slow queries to VictoriaMetrics.
   Slow query logging is controlled with `-search.logSlowQueryDuration` command-line flag.
 
+* BUGFIX: properly parse Prometheus metrics with [exemplars](https://github.com/OpenObservability/OpenMetrics/blob/master/OpenMetrics.md#exemplars-1) such as `foo 123 # {bar="baz"} 1`.
+
 
 # [v1.47.0](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.47.0)
 
diff --git a/lib/protoparser/prometheus/parser.go b/lib/protoparser/prometheus/parser.go
index 4972c7bd6e..c7381f2bcc 100644
--- a/lib/protoparser/prometheus/parser.go
+++ b/lib/protoparser/prometheus/parser.go
@@ -70,6 +70,14 @@ func (r *Row) reset() {
 	r.Timestamp = 0
 }
 
+func skipTrailingComment(s string) string {
+	n := strings.IndexByte(s, '#')
+	if n < 0 {
+		return s
+	}
+	return s[:n]
+}
+
 func skipLeadingWhitespace(s string) string {
 	// Prometheus treats ' ' and '\t' as whitespace
 	// according to https://github.com/prometheus/docs/blob/master/content/docs/instrumenting/exposition_formats.md#text-format-details
@@ -133,6 +141,7 @@ func (r *Row) unmarshal(s string, tagsPool []Tag, noEscapes bool) ([]Tag, error)
 		return tagsPool, fmt.Errorf("metric cannot be empty")
 	}
 	s = skipLeadingWhitespace(s)
+	s = skipTrailingComment(s)
 	if len(s) == 0 {
 		return tagsPool, fmt.Errorf("value cannot be empty")
 	}
@@ -151,12 +160,16 @@ func (r *Row) unmarshal(s string, tagsPool []Tag, noEscapes bool) ([]Tag, error)
 	if err != nil {
 		return tagsPool, fmt.Errorf("cannot parse value %q: %w", s[:n], err)
 	}
+	r.Value = v
 	s = skipLeadingWhitespace(s[n+1:])
+	if len(s) == 0 {
+		// There is no timestamp - just a whitespace after the value.
+		return tagsPool, nil
+	}
 	ts, err := fastfloat.ParseInt64(s)
 	if err != nil {
 		return tagsPool, fmt.Errorf("cannot parse timestamp %q: %w", s, err)
 	}
-	r.Value = v
 	r.Timestamp = ts
 	return tagsPool, nil
 }
diff --git a/lib/protoparser/prometheus/parser_test.go b/lib/protoparser/prometheus/parser_test.go
index dafa3f447a..f864dd9a11 100644
--- a/lib/protoparser/prometheus/parser_test.go
+++ b/lib/protoparser/prometheus/parser_test.go
@@ -202,6 +202,37 @@ cassandra_token_ownership_ratio 78.9`, &Rows{
 		}},
 	})
 
+	// Exemplars - see https://github.com/OpenObservability/OpenMetrics/blob/master/OpenMetrics.md#exemplars-1
+	f(`foo_bucket{le="10",a="#b"} 17 # {trace_id="oHg5SJ#YRHA0"} 9.8 1520879607.789
+	   abc 123 456#foobar
+	   foo   344#bar`, &Rows{
+		Rows: []Row{
+			{
+				Metric: "foo_bucket",
+				Tags: []Tag{
+					{
+						Key:   "le",
+						Value: "10",
+					},
+					{
+						Key:   "a",
+						Value: "#b",
+					},
+				},
+				Value: 17,
+			},
+			{
+				Metric:    "abc",
+				Value:     123,
+				Timestamp: 456,
+			},
+			{
+				Metric: "foo",
+				Value:  344,
+			},
+		},
+	})
+
 	// Timestamp bigger than 1<<31
 	f("aaa 1123 429496729600", &Rows{
 		Rows: []Row{{