go: Performance: Don't compile regex on matcher create

go/gherkin_test.go

@@ -0,0 +1,31 @@
+package gherkin_test
+
+import (
+	"bytes"
+	"io"
+	"testing"
+
+	gherkin "github.com/cucumber/gherkin/go/v26"
+	"github.com/gofrs/uuid"
+)
+
+func Benchmark_ParseGherkinDocumentForLanguage(b *testing.B) {
+	eatGodogContents := `
+Feature: eat godogs
+  In order to be happy
+  As a hungry gopher
+  I need to be able to eat godogs
+  Scenario: Eat 5 out of 12
+    Given there are 12 godogs
+    When I eat 5
+    Then there should be 7 remaining`
+
+	r := bytes.NewReader([]byte(eatGodogContents))
+	buf := new(bytes.Buffer)
+	newIDFunc := func() string {
+		return uuid.Must(uuid.NewV4()).String()
+	}
+	for i := 0; i < b.N; i++ {
+		gherkin.ParseGherkinDocumentForLanguage(io.TeeReader(r, buf), gherkin.DefaultDialect, newIDFunc)
+	}
+}

go/go.mod

@@ -2,13 +2,12 @@ module github.com/cucumber/gherkin/go/v26
 
 require (
 	github.com/cucumber/messages/go/v21 v21.0.1
-	github.com/cucumber/messages/go/v22 v22.0.0
+	github.com/gofrs/uuid v4.3.1+incompatible
 	github.com/stretchr/testify v1.8.2
 )
 
 require (
 	github.com/davecgh/go-spew v1.1.1 // indirect
-	github.com/gofrs/uuid v4.3.1+incompatible // indirect
 	github.com/pmezard/go-difflib v1.0.0 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
 )

go/go.sum

@@ -1,11 +1,8 @@
 github.com/cucumber/messages/go/v21 v21.0.1 h1:wzA0LxwjlWQYZd32VTlAVDTkW6inOFmSM+RuOwHZiMI=
 github.com/cucumber/messages/go/v21 v21.0.1/go.mod h1:zheH/2HS9JLVFukdrsPWoPdmUtmYQAQPLk7w5vWsk5s=
-github.com/cucumber/messages/go/v22 v22.0.0/go.mod h1:aZipXTKc0JnjCsXrJnuZpWhtay93k7Rn3Dee7iyPJjs=
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
-github.com/gofrs/uuid v4.2.0+incompatible h1:yyYWMnhkhrKwwr8gAOcOCYxOOscHgDS9yZgBrnJfGa0=
-github.com/gofrs/uuid v4.2.0+incompatible/go.mod h1:b2aQJv3Z4Fp6yNu3cdSllBxTCLRxnplIgP/c0N/04lM=
 github.com/gofrs/uuid v4.3.1+incompatible h1:0/KbAdpx3UXAx1kEOWHJeOkpbgRFGHVgv+CFIY7dBJI=
 github.com/gofrs/uuid v4.3.1+incompatible/go.mod h1:b2aQJv3Z4Fp6yNu3cdSllBxTCLRxnplIgP/c0N/04lM=
 github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
@@ -15,8 +12,6 @@ github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSS
 github.com/stretchr/objx v0.5.0/go.mod h1:Yh+to48EsGEfYuaHDzXPcE3xhTkx73EhmCGUpEOglKo=
 github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
 github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
-github.com/stretchr/testify v1.8.1 h1:w7B6lhMri9wdJUVmEZPGGhZzrYTPvgJArz7wNPgYKsk=
-github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
 github.com/stretchr/testify v1.8.2 h1:+h33VjcLVPDHtOdpUCuF+7gSuG3yGIftsP1YvFihtJ8=
 github.com/stretchr/testify v1.8.2/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM=

go/matcher.go

@@ -19,6 +19,11 @@ const (
 	DocstringAlternativeSeparator = "```"
 )
 
+var (
+	defaultLanguagePattern  = regexp.MustCompile("^\\s*#\\s*language\\s*:\\s*([a-zA-Z\\-_]+)\\s*$")
+	commentDelimiterPattern = regexp.MustCompile(`\s+` + CommentPrefix)
+)
+
 type matcher struct {
 	gdp                      DialectProvider
 	defaultLang              string
@@ -35,7 +40,7 @@ func NewMatcher(gdp DialectProvider) Matcher {
 		defaultLang:     DefaultDialect,
 		lang:            DefaultDialect,
 		dialect:         gdp.GetDialect(DefaultDialect),
-		languagePattern: regexp.MustCompile("^\\s*#\\s*language\\s*:\\s*([a-zA-Z\\-_]+)\\s*$"),
+		languagePattern: defaultLanguagePattern,
 	}
 }
 
@@ -45,7 +50,7 @@ func NewLanguageMatcher(gdp DialectProvider, language string) Matcher {
 		defaultLang:     language,
 		lang:            language,
 		dialect:         gdp.GetDialect(language),
-		languagePattern: regexp.MustCompile("^\\s*#\\s*language\\s*:\\s*([a-zA-Z\\-_]+)\\s*$"),
+		languagePattern: defaultLanguagePattern,
 	}
 }
 
@@ -95,8 +100,7 @@ func (m *matcher) MatchTagLine(line *Line) (ok bool, token *Token, err error) {
 	if !line.StartsWith(TagPrefix) {
 		return
 	}
-	commentDelimiter := regexp.MustCompile(`\s+` + CommentPrefix)
-	uncommentedLine := commentDelimiter.Split(line.TrimmedLineText, 2)[0]
+	uncommentedLine := commentDelimiterPattern.Split(line.TrimmedLineText, 2)[0]
 	var tags []*LineSpan
 	var column = line.Indent() + 1
 
@@ -108,7 +112,7 @@ func (m *matcher) MatchTagLine(line *Line) (ok bool, token *Token, err error) {
 		if len(txt) == 0 {
 			continue
 		}
-		if !regexp.MustCompile(`^\S+$`).MatchString(txt) {
+		if strings.ContainsAny(txt, "\t\n\f\r ") {
 			location := &Location{line.LineNumber, column}
 			msg := "A tag may not contain whitespace"
 			err = &parseError{msg, location}

go/matcher_test.go

@@ -0,0 +1,35 @@
+package gherkin_test
+
+import (
+	"testing"
+
+	gherkin "github.com/cucumber/gherkin/go/v26"
+	"github.com/gofrs/uuid"
+)
+
+func BenchmarkMatcher_MatchTagLine(b *testing.B) {
+	builder := gherkin.NewAstBuilder(func() string {
+		return uuid.Must(uuid.NewV4()).String()
+	})
+	parser := gherkin.NewParser(builder)
+	parser.StopAtFirstError(false)
+	matcher := gherkin.NewLanguageMatcher(gherkin.DialectsBuiltin(), gherkin.DefaultDialect)
+
+	lines := []gherkin.Line{{
+		LineText:        "    @hello # there",
+		AtEof:           false,
+		LineNumber:      0,
+		TrimmedLineText: "@hello # there",
+	}, {
+		LineText:        "    @yes # there",
+		AtEof:           false,
+		LineNumber:      0,
+		TrimmedLineText: "@yes # there",
+	}}
+
+	for i := 0; i < b.N; i++ {
+		for _, line := range lines {
+			matcher.MatchTagLine(&line)
+		}
+	}
+}