feat(svc/ProcessTranslationRequest): integrate detect lang logic (#19)

* chore(deps): add language-detect go sdk

* feat(pkg/translate): add detect_lang methods

* patch(svc/ProcessTranslationRequest): integrate detect lang logic

Author: sumire88

go.mod

@@ -12,6 +12,7 @@ require (
 )
 
 require (
+	github.com/detectlanguage/detectlanguage-go v1.0.1 // indirect
 	github.com/golang-jwt/jwt/v4 v4.5.2 // indirect
 	github.com/google/go-github/v72 v72.0.0 // indirect
 	github.com/google/go-querystring v1.1.0 // indirect

go.sum

@@ -7,6 +7,8 @@ github.com/cloudevents/sdk-go/v2 v2.16.1/go.mod h1:v/kVOaWjNfbvc6tkhhlkhvLapj8Aa
 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/detectlanguage/detectlanguage-go v1.0.1 h1:WjSz4LrmY6r3PpPwgIjE5A0TcqZ34zViKfi1uS2X1Eg=
+github.com/detectlanguage/detectlanguage-go v1.0.1/go.mod h1:v6CcAECwWXM7YX4/CtHJSPwHsDNY0VtIfLf/z44L8aU=
 github.com/golang-jwt/jwt/v4 v4.5.2 h1:YtQM7lnr8iZ+j5q71MGKkNw9Mn7AjHM68uc9g5fXeUI=
 github.com/golang-jwt/jwt/v4 v4.5.2/go.mod h1:m21LjoU+eqJr34lmDMbreY2eSTRJ1cv77w39/MY0Ch0=
 github.com/google/go-cmp v0.5.2/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
@@ -32,6 +34,7 @@ github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZb
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
 github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
 github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
+github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4=
 github.com/stretchr/testify v1.10.0 h1:Xv5erBjTwe/5IxqUQTdXv5kgmIvbHo3QQyRwhJsOfJA=
 github.com/stretchr/testify v1.10.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
 github.com/valyala/bytebufferpool v1.0.0 h1:GqA5TC/0021Y/b9FG4Oi9Mr3q7XYx6KllzawFIhcdPw=
@@ -49,5 +52,7 @@ golang.org/x/sync v0.15.0/go.mod h1:1dzgHSNfp02xaA81J2MS99Qcpr2w7fw1gpm99rleRqA=
 golang.org/x/time v0.12.0 h1:ScB/8o8olJvc+CQPWrK3fPZNfh7qgwCrY0zJmoEQLSE=
 golang.org/x/time v0.12.0/go.mod h1:CDIdPxbZBQxdj6cxyCIdrNogrJKMJ7pr37NYpMcMDSg=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
+gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
+gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
 gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
 gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

pkg/translate/detect_lang.go

@@ -0,0 +1,21 @@
+package translate
+
+import (
+	"errors"
+	"os"
+
+	"github.com/detectlanguage/detectlanguage-go"
+)
+
+const LANG_DECT_CONFIDENCE_THRESHOLD = 11.5
+
+func DetectLanguage(text string) ([]*detectlanguage.DetectionResult, error) {
+	client := detectlanguage.New(os.Getenv("DETECTLANGUAGE_API_KEY"))
+
+	result, err := client.Detect(text)
+	if err != nil {
+		return nil, errors.New("error detecting language: " + err.Error())
+	}
+
+	return result, nil
+}

pkg/translate/detect_lang_test.go

@@ -0,0 +1,28 @@
+package translate
+
+import (
+	"testing"
+)
+
+func TestDectLang_Detect(t *testing.T) {
+	// Construct multiple test cases
+	testCases := []struct {
+		input string
+	}{
+		{"你好，世界"},
+		{"Hello, world"},
+		{"你好嗎？I am fine"},
+	}
+
+	for _, tc := range testCases {
+		result, err := DetectLanguage(tc.input)
+		if err != nil {
+			t.Fatalf("Language detection failed for input '%s': %v", tc.input, err)
+		}
+
+		t.Logf("Detected languages for input '%v' is:", result[0].Language)
+		t.Logf("Reliable is '%v': ", result[0].Reliable)
+		t.Logf("Confidence is '%v': ", result[0].Confidence)
+
+	}
+}

service/action.go

@@ -4,6 +4,7 @@ import (
 	"errors"
 
 	"github.com/vertexbox/github-translation-bot/pkg/github"
+	"github.com/vertexbox/github-translation-bot/pkg/translate"
 )
 
 // GetRepo returns the GitHub repository associated with the AppService
@@ -45,6 +46,27 @@ func (s *AppService) ProcessTranslationRequest(issueNumber int, text string) err
 	// Log the incoming translation request
 	s.logger.Infow("Processing translation request", "issueNumber", issueNumber)
 
+	// Check if the text needs to be translated
+	langResult, err := translate.DetectLanguage(text)
+	if err != nil {
+		return errors.New("failed to detect language: " + err.Error())
+	}
+
+	// Log the detected language and confidence
+	s.logger.Infow("Detect language for incoming text",
+		"language", langResult[0].Language,
+		"confidence", langResult[0].Confidence,
+		"reliable", langResult[0].Reliable,
+	)
+
+	// If the detected language is English and the confidence is above the threshold, skip translation
+	if langResult[0].Language == "en" && langResult[0].Confidence > translate.LANG_DECT_CONFIDENCE_THRESHOLD {
+		s.logger.Infof("No translation needed for comment: %s", text)
+		return nil
+	}
+
+	// *** Proceed with translation ***
+
 	// Translate the comment body
 	result, err := s.MultilineTranslate(text)
 	if err != nil {
@@ -53,12 +75,6 @@ func (s *AppService) ProcessTranslationRequest(issueNumber int, text string) err
 	// Log the result of the translation for debugging
 	s.logger.Infof("Multiline Translated Comment: %s", result)
 
-	// If the translation result is empty, skip adding a comment
-	if result == "" {
-		s.logger.Infof("No translation needed for comment: %s", text)
-		return nil
-	}
-
 	// Add a note about the translation
 	result = "> [!NOTE]\n> The following content has been translated from its original language using an automated process powered by a proprietary API. Segments originally written in English have been preserved, while non-English portions have been machine-translated for readability. Please be aware that minor inaccuracies may exist due to the automated nature of the translation.\n\n" + result