perf(common): compile LLM-JSON code-fence regexp once

ParseLLMJsonResponse recompiled its ```json fence-extraction regexp on
every call that fell through the direct-unmarshal fast path — i.e. every
fenced LLM response on the graph-extraction path. Hoist it to a
package-level var.

Adds a test (none existed) covering direct, fenced, no-lang and
prose-wrapped inputs, plus a benchmark.

Benchmark, fenced payload (-benchmem):
  before: 3205 ns/op, 5712 B/op, 54 allocs/op
  after:  1315 ns/op,  693 B/op, 15 allocs/op

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
adawang
2026-06-16 17:46:01 +08:00
committed by lyingbug
parent 8f4b3333f2
commit ec66a3dac7
2 changed files with 52 additions and 2 deletions
+5 -2
View File
@@ -96,6 +96,10 @@ func DeduplicateWithScore[T ScoreComparable, K comparable](keyFunc func(T) K, it
// {"key": "value"}
// ```
// or regular JSON responses directly.
// jsonCodeFenceRE extracts a JSON payload wrapped in a Markdown code fence.
// Compiled once: ParseLLMJsonResponse runs on the graph-extraction path.
var jsonCodeFenceRE = regexp.MustCompile("```(?:json)?\\s*([\\s\\S]*?)```")
func ParseLLMJsonResponse(content string, target interface{}) error {
// First, try to parse directly as JSON
err := json.Unmarshal([]byte(content), target)
@@ -104,8 +108,7 @@ func ParseLLMJsonResponse(content string, target interface{}) error {
}
// If direct parsing fails, try to extract JSON from code blocks
re := regexp.MustCompile("```(?:json)?\\s*([\\s\\S]*?)```")
matches := re.FindStringSubmatch(content)
matches := jsonCodeFenceRE.FindStringSubmatch(content)
if len(matches) >= 2 {
// Extract the JSON content within the code block
jsonContent := strings.TrimSpace(matches[1])
+47
View File
@@ -0,0 +1,47 @@
package common
import "testing"
func TestParseLLMJsonResponse(t *testing.T) {
type payload struct {
Key string `json:"key"`
}
tests := []struct {
name string
content string
want string
wantErr bool
}{
{"direct json", `{"key":"value"}`, "value", false},
{"fenced json", "```json\n{\"key\":\"fenced\"}\n```", "fenced", false},
{"fenced no lang", "```\n{\"key\":\"plain\"}\n```", "plain", false},
{"prose around fence", "Here you go:\n```json\n{\"key\":\"wrapped\"}\n```\nThanks", "wrapped", false},
{"not json", "just some text", "", true},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
var got payload
err := ParseLLMJsonResponse(tt.content, &got)
if (err != nil) != tt.wantErr {
t.Fatalf("err = %v, wantErr %v", err, tt.wantErr)
}
if !tt.wantErr && got.Key != tt.want {
t.Errorf("Key = %q, want %q", got.Key, tt.want)
}
})
}
}
func BenchmarkParseLLMJsonResponse_Fenced(b *testing.B) {
const content = "```json\n{\"name\":\"Acme\",\"slug\":\"entity/acme\",\"aliases\":[\"A\",\"B\"]}\n```"
type payload struct {
Name string `json:"name"`
}
b.ReportAllocs()
for i := 0; i < b.N; i++ {
var p payload
_ = ParseLLMJsonResponse(content, &p)
}
}