Skip to content

[SC-23705] fix(sematext): deduplicate corrupted measurement name prefixes #17

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
boratanrikulu wants to merge 1 commit into from
+71 −0
Closed

[SC-23705] fix(sematext): deduplicate corrupted measurement name prefixes #17

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 28 additions & 0 deletions plugins/outputs/sematext/processors/rename.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -210,6 +210,10 @@ func NewRename() BatchProcessor { return &Rename{} }
func (r *Rename) Process(points []telegraf.Metric) []telegraf.Metric {
for _, point := range points {
originalName := point.Name()

// Fix corrupted measurement names (e.g., "apache.apache.apache" → "apache")
originalName = deduplicatePrefix(originalName)

replace, ok := measurementReplaces[originalName]
if !ok {
replace = ChangeNames(originalName)
Expand Down Expand Up @@ -275,3 +279,27 @@ func ChangeNames(name string) string {
}

func (Rename) Close() {}

// deduplicatePrefix fixes recursive prefix corruption.
// Example: "apache.apache.apache" → "apache"
func deduplicatePrefix(name string) string {
parts := strings.Split(name, ".")
if len(parts) < 2 {
return name
}

prefix := parts[0]
count := 0
for count < len(parts) && parts[count] == prefix {
count++
}

if count > 1 {
remaining := parts[count:]
if len(remaining) > 0 {
return prefix + "." + strings.Join(remaining, ".")
}
return prefix
}
return name
}
43 changes: 43 additions & 0 deletions plugins/outputs/sematext/processors/rename_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,6 +34,49 @@ func TestRename(t *testing.T) {
assert.Equal(t, "mongodb_shard_stats.in_use", results[8].FieldList()[0].Key)
}

func TestDeduplicatePrefix(t *testing.T) {
tests := []struct {
input string
expected string
}{
{"apache", "apache"},
{"apache.apache", "apache"},
{"apache.apache.apache", "apache"},
{"apache.apache.apache.apache", "apache"},
{"nginx", "nginx"},
{"nginx.nginx", "nginx"},
{"nginx.nginx.nginx", "nginx"},
{"mongodb", "mongodb"},
{"mongodb.mongodb.mongodb", "mongodb"},
// Edge cases
{"", ""},
{"a", "a"},
{"a.b", "a.b"},
{"a.a.b", "a.b"},
{"foo.foo.bar.baz", "foo.bar.baz"},
}

for _, tt := range tests {
t.Run(tt.input, func(t *testing.T) {
result := deduplicatePrefix(tt.input)
assert.Equal(t, tt.expected, result)
})
}
}

func TestRenameWithCorruptedMeasurementName(t *testing.T) {
r := Rename{}

// Simulate corrupted measurement name with 64+ repeated prefixes
corruptedName := "apache.apache.apache.apache.apache"
m := newMetric(corruptedName, nil, map[string]interface{}{"BusyWorkers": 10})

results := r.Process([]telegraf.Metric{m})

assert.Equal(t, "apache", results[0].Name())
assert.Equal(t, "workers.busy", results[0].FieldList()[0].Key)
}

func newMetric(name string, tags map[string]string, fields map[string]interface{}) telegraf.Metric {
if tags == nil {
tags = map[string]string{}
Expand Down