Merge pull request #571 from adamdecaf/misc-updates-2024-10-22

cmd/server: pool x/text/transform.Transformer instances
moov-io · Oct 22, 2024 · 1eca0f6 · 1eca0f6
2 parents 2dba69f + 5210a9d
commit 1eca0f6
Show file tree

Hide file tree

Showing 7 changed files with 61 additions and 19 deletions.
diff --git a/cmd/server/main.go b/cmd/server/main.go
@@ -129,9 +129,9 @@ func main() {
 
 	var pipeline *pipeliner
 	if debug, err := strconv.ParseBool(os.Getenv("DEBUG_NAME_PIPELINE")); debug && err == nil {
-		pipeline = newPipeliner(logger)
+		pipeline = newPipeliner(logger, true)
 	} else {
-		pipeline = newPipeliner(log.NewNopLogger())
+		pipeline = newPipeliner(log.NewNopLogger(), false)
 	}
 
 	searchWorkers := readInt(os.Getenv("SEARCH_MAX_WORKERS"), *flagWorkers)

diff --git a/cmd/server/pipeline.go b/cmd/server/pipeline.go
@@ -210,15 +210,21 @@ func (ds *debugStep) apply(in *Name) error {
 	return nil
 }
 
-func newPipeliner(logger log.Logger) *pipeliner {
+func newPipeliner(logger log.Logger, debug bool) *pipeliner {
+	steps := []step{
+		&reorderSDNStep{},
+		&companyNameCleanupStep{},
+		&stopwordsStep{},
+		&normalizeStep{},
+	}
+	if debug {
+		for i := range steps {
+			steps[i] = &debugStep{logger: logger, step: steps[i]}
+		}
+	}
 	return &pipeliner{
 		logger: logger,
-		steps: []step{
-			&debugStep{logger: logger, step: &reorderSDNStep{}},
-			&debugStep{logger: logger, step: &companyNameCleanupStep{}},
-			&debugStep{logger: logger, step: &stopwordsStep{}},
-			&debugStep{logger: logger, step: &normalizeStep{}},
-		},
+		steps:  steps,
 	}
 }
 

diff --git a/cmd/server/pipeline_normalize.go b/cmd/server/pipeline_normalize.go
@@ -6,6 +6,7 @@ package main
 
 import (
 	"strings"
+	"sync"
 	"unicode"
 
 	"golang.org/x/text/runes"
@@ -34,7 +35,35 @@ func precompute(s string) string {
 	trimmed := strings.TrimSpace(strings.ToLower(punctuationReplacer.Replace(s)))
 
 	// UTF-8 normalization
-	t := transform.Chain(norm.NFD, runes.Remove(runes.In(unicode.Mn)), norm.NFC) // Mn: nonspacing marks
-	result, _, _ := transform.String(t, trimmed)
+	chain := getTransformChain()
+	defer saveBuffer(chain)
+
+	result, _, _ := transform.String(chain, trimmed)
 	return result
 }
+
+var (
+	transformChainPool = sync.Pool{
+		New: func() any {
+			return newTransformChain()
+		},
+	}
+)
+
+func newTransformChain() transform.Transformer {
+	nonspacingMarksRemover := runes.Remove(runes.In(unicode.Mn)) // Mn: nonspacing marks
+	return transform.Chain(norm.NFD, nonspacingMarksRemover, norm.NFC)
+}
+
+func getTransformChain() transform.Transformer {
+	t, ok := transformChainPool.Get().(transform.Transformer)
+	if !ok {
+		return newTransformChain()
+	}
+	return t
+}
+
+func saveBuffer(t transform.Transformer) {
+	t.Reset()
+	transformChainPool.Put(t)
+}
diff --git a/cmd/server/pipeline_test.go b/cmd/server/pipeline_test.go
@@ -17,7 +17,7 @@ var (
 		steps:  []step{},
 	}
 
-	noLogPipeliner = newPipeliner(log.NewNopLogger())
+	noLogPipeliner = newPipeliner(log.NewNopLogger(), false)
 )
 
 func TestPipelineNoop(t *testing.T) {
@@ -75,6 +75,7 @@ func TestFullPipeline(t *testing.T) {
 		// Normalize ("-" -> " ")
 		{company("ANGLO-CARIBBEAN CO., LTD."), "anglo caribbean"},
 	}
+
 	for i := range cases {
 		if err := noLogPipeliner.Do(cases[i].in); err != nil {
 			t.Error(err)

diff --git a/cmd/server/search_benchmark_test.go b/cmd/server/search_benchmark_test.go
@@ -19,8 +19,14 @@ func BenchmarkSearch__All(b *testing.B) {
 	searcher := createBenchmarkSearcher(b)
 	b.ResetTimer()
 
+	var filters filterRequest
+
 	for i := 0; i < b.N; i++ {
-		buildFullSearchResponse(searcher, filterRequest{}, 10, 0.0, fake.Person().Name())
+		b.StopTimer()
+		name := fake.Person().Name()
+		b.StartTimer()
+
+		buildFullSearchResponse(searcher, filters, 10, 0.0, name)
 	}
 }
 

diff --git a/go.mod b/go.mod
@@ -17,8 +17,8 @@ require (
 	github.com/xrash/smetrics v0.0.0-20201216005158-039620a65673
 	go4.org v0.0.0-20230225012048-214862532bf5
 	golang.org/x/oauth2 v0.14.0
-	golang.org/x/sync v0.6.0
-	golang.org/x/text v0.14.0
+	golang.org/x/sync v0.8.0
+	golang.org/x/text v0.19.0
 )
 
 require (

diff --git a/go.sum b/go.sum
@@ -192,8 +192,8 @@ golang.org/x/sync v0.0.0-20190227155943-e225da77a7e6/go.mod h1:RxMgew5VJxzue5/jJ
 golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20190911185100-cd5d95a43a6e/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
-golang.org/x/sync v0.6.0 h1:5BMeUDZ7vkXGfEr1x9B4bRcTH4lpkTkpdh0T/J+qjbQ=
-golang.org/x/sync v0.6.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
+golang.org/x/sync v0.8.0 h1:3NFvSEYkUoMifnESzZl15y791HH1qU2xm6eCJU5ZPXQ=
+golang.org/x/sync v0.8.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
 golang.org/x/sys v0.0.0-20180830151530-49385e6e1522/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20190312061237-fead79001313/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
@@ -224,8 +224,8 @@ golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
 golang.org/x/text v0.3.8/go.mod h1:E6s5w1FMmriuDzIBO73fBruAKo1PCIq6d2Q6DHfQ8WQ=
 golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
-golang.org/x/text v0.14.0 h1:ScX5w1eTa3QqT8oi6+ziP7dTV1S2+ALU0bI+0zXKWiQ=
-golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
+golang.org/x/text v0.19.0 h1:kTxAhCbGbxhK0IwgSKiMO5awPoDQ0RpfiVYBfK860YM=
+golang.org/x/text v0.19.0/go.mod h1:BuEKDfySbSR4drPmRPG/7iBdf8hvFMuRexcpahXilzY=
 golang.org/x/time v0.0.0-20181108054448-85acf8d2951c/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/time v0.0.0-20190308202827-9d24e82272b4/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=