[prometheus] Update the error check to handle invalid and empty content header (#47085) (#47119)

(cherry picked from commit 647d455)

Co-authored-by: Aman <[email protected]>

Author: mergify[bot]

changelog/fragments/1760507204-bugfix-add-a-fix-to-handle-multiple-content-types-including-blank-and-invalid-headers.yaml

@@ -0,0 +1,45 @@
+# REQUIRED
+# Kind can be one of:
+# - breaking-change: a change to previously-documented behavior
+# - deprecation: functionality that is being removed in a later release
+# - bug-fix: fixes a problem in a previous version
+# - enhancement: extends functionality but does not break or fix existing behavior
+# - feature: new functionality
+# - known-issue: problems that we are aware of in a given version
+# - security: impacts on the security of a product or a user’s deployment.
+# - upgrade: important information for someone upgrading from a prior version
+# - other: does not fit into any of the other categories
+kind: enhancement
+
+# REQUIRED for all kinds
+# Change summary; a 80ish characters long description of the change.
+summary: Improve the Prometheus helper to handle multiple content types including blank and invalid headers.
+
+# REQUIRED for breaking-change, deprecation, known-issue
+# Long description; in case the summary is not enough to describe the change
+# this field accommodate a description without length limits.
+# description:
+
+# REQUIRED for breaking-change, deprecation, known-issue
+# impact:
+
+# REQUIRED for breaking-change, deprecation, known-issue
+# action:
+
+# REQUIRED for all kinds
+# Affected component; usually one of "elastic-agent", "fleet-server", "filebeat", "metricbeat", "auditbeat", "all", etc.
+component: metricbeat
+
+# AUTOMATED
+# OPTIONAL to manually add other PR URLs
+# PR URL: A link the PR that added the changeset.
+# If not present is automatically filled by the tooling finding the PR where this changelog fragment has been added.
+# NOTE: the tooling supports backports, so it's able to fill the original PR number instead of the backport PR number.
+# Please provide it if you are adding a fragment for a different PR.
+# pr: https://github.com/owner/repo/1234
+
+# AUTOMATED
+# OPTIONAL to manually add other issue URLs
+# Issue URL; optional; the GitHub issue related to this changeset (either closes or is part of).
+# If not present is automatically filled by the tooling with the issue linked to the PR number.
+# issue: https://github.com/owner/repo/1234

metricbeat/helper/prometheus/textparse.go

@@ -19,6 +19,7 @@ package prometheus
 
 import (
 	"errors"
+	"fmt"
 	"io"
 	"math"
 	"mime"
@@ -484,9 +485,14 @@ func histogramMetricName(name string, s float64, qv string, lbls string, t *int6
 func ParseMetricFamilies(b []byte, contentType string, ts time.Time, logger *logp.Logger) ([]*MetricFamily, error) {
 	// Fallback to text/plain if content type is blank or unrecognized.
 	parser, err := textparse.New(b, contentType, textMediaType, false, false, false, labels.NewSymbolTable())
-	// This check allows to continue where the content type is blank but the parser is non-nil. Returns error on all other cases.
-	if err != nil && !strings.Contains(err.Error(), "non-compliant scrape target sending blank Content-Type, using fallback_scrape_protocol") {
-		return nil, err
+	// This check allows to continue where the content type is blank/invalid but the parser is non-nil. Returns error on all other cases.
+	if parser == nil {
+		if err != nil {
+			return nil, err
+
+		}
+
+		return nil, fmt.Errorf("no parser returned for contentType %q", contentType)
 	}
 
 	var (

metricbeat/helper/prometheus/textparse_test.go

@@ -900,19 +900,24 @@ redis_connected_clients{instance="rough-snowflake-web"} 10.0`
 	require.ElementsMatch(t, expected, result)
 }
 
-func TestBlankContentTypeHeader(t *testing.T) {
-	input := `
+func TestParseMetricFamiliesContentTypes(t *testing.T) {
+	inputPrometheus := `
 # TYPE process_cpu_total counter
 # HELP process_cpu_total Some help.
 process_cpu_total 4.20072246e+06
+`
+
+	inputOpenMetricsType := `# TYPE process_cpu_total counter
+# HELP process_cpu_total Some help.
+process_cpu_total 4200722.46
+# EOF
 `
 
 	expected := []*MetricFamily{
 		{
 			Name: stringp("process_cpu_total"),
 			Help: stringp("Some help."),
 			Type: "counter",
-			Unit: nil,
 			Metric: []*OpenMetric{
 				{
 					Label: []*labels.Label{},
@@ -925,9 +930,38 @@ process_cpu_total 4.20072246e+06
 		},
 	}
 
-	result, err := ParseMetricFamilies([]byte(input), "", time.Now(), nil)
-	if err != nil {
-		t.Fatal("ParseMetricFamilies for blank content type returned an error.")
+	tests := []struct {
+		name        string
+		contentType string
+		wantErr     bool
+	}{
+		{"plain", "text/plain", false},
+		{"plain_charset", "text/plain; charset=utf-8", false},
+		{"plain_version_0_0_4", "text/plain; version=0.0.4; charset=utf-8", false},
+		{"plain_version_1.0.0", "text/plain; version=1.0.0; charset=utf-8", false},
+		{"json", "application/json", false},
+		{"html", "text/html; charset=utf-8", false},
+		{"empty_content_type", "", false},
+		{"openmetrics", "application/openmetrics-text", false},
+		{"octet_stream", "application/octet-stream", false},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			input := inputPrometheus
+
+			if tt.contentType == OpenMetricsType {
+				input = inputOpenMetricsType
+			}
+
+			result, err := ParseMetricFamilies([]byte(input), tt.contentType, time.Now(), logptest.NewTestingLogger(t, "test"))
+			if tt.wantErr {
+				require.Error(t, err, "expected error for %s", tt.contentType)
+				return
+			}
+
+			require.NoError(t, err, "unexpected error for %s", tt.contentType)
+			require.ElementsMatch(t, expected, result)
+		})
 	}
-	require.ElementsMatch(t, expected, result)
 }