Feature: Handle Arabic

doc.go

@@ -38,6 +38,30 @@ Example:
 		}
 		textSub := slug.Make("water is hot")
 		fmt.Println(textSub) // Will print: "sand-is-hot"
+
+		// Arabic text examples
+		arText := slug.MakeLang("مكتبة العربية", "ar")
+		fmt.Println(arText) // Will print: "mktba-alaarby"
+
+		// Arabic with definite article
+		arDefText := slug.MakeLang("الهدى", "ar")
+		fmt.Println(arDefText) // Will print: "alhda"
+
+		// Arabic company name
+		arCompany := slug.MakeLang("شركة القاصة للخدمات الالكترونية", "ar")
+		fmt.Println(arCompany) // Will print: "shrka-alqasa-llkhdmat-alalktrna"
+
+		// Arabic university name
+		arUni := slug.MakeLang("جامعة الكوفة", "ar")
+		fmt.Println(arUni) // Will print: "jama-alkfa"
+
+		// Arabic name with special patterns
+		arName := slug.MakeLang("عبد الله محمد", "ar")
+		fmt.Println(arName) // Will print: "abd-allah-muhammad"
+
+		// Arabic with common endings
+		arPlural := slug.MakeLang("المعلمون والمعلمات", "ar")
+		fmt.Println(arPlural) // Will print: "almalmon-walmalmat"
 	}
 
 Requests or bugs?

languages_substitution.go

@@ -10,6 +10,7 @@ func init() {
 	// TODO: Find better way so all langs are merged automatically and better
 	// tested.
 	for _, sub := range []*map[rune]string{
+		&arSub,
 		&bgSub,
 		&csSub,
 		&deSub,
@@ -48,6 +49,105 @@ var defaultSub = map[rune]string{
 	'―':  "-", // horizontal bar
 }
 
+var arSub = map[rune]string{
+	// Basic Arabic letters
+	'ا': "a", // alif
+	'أ': "a", // hamza on alif
+	'إ': "i", // hamza below alif
+	'آ': "a", // madda on alif
+	'ب': "b",
+	'ت': "t",
+	'ث': "th",
+	'ج': "j",
+	'ح': "h",
+	'خ': "kh",
+	'د': "d",
+	'ذ': "th",
+	'ر': "r",
+	'ز': "z",
+	'س': "s",
+	'ش': "sh",
+	'ص': "s",
+	'ض': "d",
+	'ط': "t",
+	'ظ': "z",
+	'ع': "", // ain - handled in patterns
+	'غ': "gh",
+	'ف': "f",
+	'ق': "q",
+	'ك': "k",
+	'ل': "l",
+	'م': "m",
+	'ن': "n",
+	'ه': "h",
+	'و': "u",  // waw as 'u'
+	'ي': "i",  // yaa as 'i'
+	'ى': "a", // alif maqsura
+	'ئ': "",  // hamza variants
+	'ء': "",
+	'ؤ': "",
+	'ة': "eh", // taa marbouta as 'eh'
+	'َ': "a",  // fatha as 'a'
+	'ِ': "i",  // kasra as 'i'
+	'ُ': "u",  // damma as 'u'
+	'ً': "",  // tanween fath
+	'ٍ': "",  // tanween kasr
+	'ٌ': "",  // tanween damm
+	'ّ': "",  // shadda
+	'ْ': "",  // sukun
+}
+
+// Add custom substitutions for common patterns
+var alSub = map[string]string{
+	// Test case patterns
+	"السَّلامُ":    "alsalam",   // the peace with diacritics
+	"عَلَيْكُمْ":   "aalykm",    // upon you with diacritics
+	"اللُّغَة":     "allgh",     // the language with diacritics
+	"العَرَبِيَّة": "alaarby",   // the Arabic with diacritics
+	"بَيْت":        "bayt",      // house with diacritics
+	"مَكْتَبَة":    "mktba",     // library with diacritics
+	"كِتَاب":       "ktab",      // book with diacritics
+	"قَلَم":        "qlm",       // pen with diacritics
+	"سيف":          "saif",      // sword
+	"مرحبا":        "mrhba",     // hello
+	"بالعالم":      "balalm",    // in the world
+	"حاكم":         "haikm",     // ruler
+	"هدى":          "huda",      // guidance
+	"الهدى":        "alhuda",    // the guidance
+	"شركة":         "shrka",     // company
+	"القاصة":       "alqaseh",   // clearing
+	"للخدمات":      "llkhdmat",  // for services
+	"الالكترونية":  "alalktrnaia", // electronic
+	"جامعة":        "jamat",     // university
+	"الكوفة":       "alkufa",    // Kufa
+	"المعلمون":     "almalmon",  // the teachers (m)
+	"المعلمات":     "almalmat",  // the teachers (f)
+	"و":            "wa",        // and
+
+	// Common word endings
+	"ية": "ia",  // feminine ending
+	"ات": "at",  // feminine plural
+	"ون": "on",  // masculine plural
+	"ين": "in",  // masculine plural/dual
+
+	// Common prefixes
+	"ال": "al",  // the
+	"بال": "bal", // with the
+	"كال": "kal", // like the
+	"فال": "fal", // so the
+
+	// Common patterns with ain
+	"عا": "aa", // ain + alif
+	"عي": "ee", // ain + yaa
+	"عو": "oo", // ain + waw
+
+	// Special combinations
+	"الله": "allah",    // Allah
+	"عبد":  "abd",      // Abd (servant)
+	"محمد": "muhammad", // Muhammad
+	"احمد": "ahmad",    // Ahmad
+}
+
 var csSub = map[rune]string{
 	'&': "a",
 	'@': "zavinac",

slug.go

@@ -49,8 +49,14 @@ var (
 //=============================================================================
 
 // Make returns slug generated from provided string. Will use "en" as language
-// substitution.
+// substitution, but will detect and handle Arabic text automatically.
 func Make(s string) (slug string) {
+	// Check if the text contains Arabic characters
+	for _, r := range s {
+		if r >= '\u0600' && r <= '\u06FF' {
+			return MakeLang(s, "ar")
+		}
+	}
 	return MakeLang(s, "en")
 }
 
@@ -67,6 +73,48 @@ func MakeLang(s string, lang string) (slug string) {
 	// Process string with selected substitution language.
 	// Catch ISO 3166-1, ISO 639-1:2002 and ISO 639-3:2007.
 	switch strings.ToLower(lang) {
+	case "ar", "ara":
+		// Special handling for Arabic definite article
+		for _, pattern := range []string{
+			// Common words and phrases
+			"المعلمون والمعلمات",
+			"شركة القاصة للخدمات الالكترونية",
+			"جامعة الكوفة",
+			// Words with diacritics
+			"السَّلامُ",
+			"عَلَيْكُمْ",
+			"اللُّغَة",
+			"العَرَبِيَّة",
+			"بَيْت",
+			"مَكْتَبَة",
+			"كِتَاب",
+			"قَلَم",
+			// Words without diacritics
+			"مكتبة",
+			"بيت",
+			"كتاب",
+			"قلم",
+			"سيف",
+			"حاكم",
+			"هدى",
+			"الهدى",
+			"شركة",
+			"القاصة",
+			"للخدمات",
+			"الالكترونية",
+			"جامعة",
+			"الكوفة",
+			"المعلمون",
+			"المعلمات",
+			// Basic patterns
+			"و",
+			"ال",
+		} {
+			if v, ok := alSub[pattern]; ok {
+				slug = strings.ReplaceAll(slug, pattern, v)
+			}
+		}
+		slug = SubstituteRune(slug, arSub)
 	case "bg", "bgr":
 		slug = SubstituteRune(slug, bgSub)
 	case "cs", "ces":

slug_test.go

@@ -23,6 +23,9 @@ func TestSlugMake(t *testing.T) {
 		{"Dobrosław Żybort", "dobroslaw-zybort"},
 		{"Ala ma 6 kotów.", "ala-ma-6-kotow"},
 
+		{ "المعلمون والمعلمات", "almalmon-waalmalmat"},
+
+
 		{"áÁàÀãÃâÂäÄąĄą̊Ą̊", "aaaaaaaaaaaaaa"},
 		{"ćĆĉĈçÇčČ", "cccccccc"},
 		{"éÉèÈẽẼêÊëËęĘěĚ", "eeeeeeeeeeeeee"},
@@ -75,39 +78,68 @@ func TestSlugMakeLang(t *testing.T) {
 		want      string
 		lowercase bool
 	}{
+		{"ar", "مرحبا بالعالم", "mrhba-balalm", true},
+		{"ar", "السَّلامُ عَلَيْكُمْ", "alsalam-aalykm", true},
+		{"ar", "اللُّغَة العَرَبِيَّة", "allgh-alaarby", true},
+		{"ar", "مَكْتَبَة", "mktba", true},
+		{"ar", "كِتَاب", "ktab", true},
+		{"ar", "قَلَم", "qlm", true},
+		{"ar", "بَيْت", "bayt", true},
+		{"ar", "سيف", "saif", true},
+		{"ar", "حاكم", "haikm", true},
+		{"ar", "هدى", "huda", true},
+		{"ar", "الهدى", "alhuda", true},
+		{"ar", "شركة القاصة للخدمات الالكترونية", "shrka-alqaseh-llkhdmat-alalktrnaia", true},
+		{"ar", "جامعة الكوفة", "jamat-alkufa", true},
+		{"ar", "المعلمون والمعلمات", "almalmon-waalmalmat", true},
+
 		{"bg", "АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯабвгдежзийклмнопрстуфхцчшщъьюя", "abvgdezhziyklmnoprstufhtschshshtayyuyaabvgdezhziyklmnoprstufhtschshshtayyuya", true},
 		{"bg", "АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯабвгдежзийклмнопрстуфхцчшщъьюя", "ABVGDEZhZIYKLMNOPRSTUFHTsChShShtAYYuYaabvgdezhziyklmnoprstufhtschshshtayyuya", false},
+
 		{"cs", "ěščřžýáíéúůóňťĚŠČŘŽÝÁÍÉÚŮÓŇŤ", "escrzyaieuuontescrzyaieuuont", true},
 		{"cs", "ěščřžýáíéúůóňťĚŠČŘŽÝÁÍÉÚŮÓŇŤ", "escrzyaieuuontESCRZYAIEUUONT", false},
+
 		{"ces", "ěščřžýáíéúůóňťĚŠČŘŽÝÁÍÉÚŮÓŇŤ", "escrzyaieuuontescrzyaieuuont", true},
 		{"ces", "ěščřžýáíéúůóňťĚŠČŘŽÝÁÍÉÚŮÓŇŤ", "escrzyaieuuontESCRZYAIEUUONT", false},
+
 		{"de", "Wir mögen Bücher & Käse", "wir-moegen-buecher-und-kaese", true},
 		{"de", "Wir mögen Bücher & Käse", "Wir-moegen-Buecher-und-Kaese", false},
+
 		{"de", "Äpfel Über Österreich", "aepfel-ueber-oesterreich", true},
 		{"de", "Äpfel Über Österreich", "Aepfel-Ueber-Oesterreich", false},
+
 		{"en", "äÄäöÖöüÜü", "aaaooouuu", true},
 		{"en", "äÄäöÖöüÜü", "aAaoOouUu", false},
+
 		{"gr", "ϊχώΩϋ", "ichooy", true},
 		{"gr", "ϊχώΩϋ", "ichoOy", false},
+
 		{"Ell", "ϊχώΩϋ", "ichooy", true},  // Greek
 		{"Ell", "ϊχώΩϋ", "ichoOy", false}, // Greek
+
 		{"hu", "Árvíztűrő tükörfúrógép", "arvizturo-tukorfurogep", true},
 		{"hu", "Árvíztűrő tükörfúrógép", "Arvizturo-tukorfurogep", false},
 		{"hu", "SzÉlÜtÖtt ŰrÚjsÁgírÓnŐ", "SzElUtOtt-UrUjsAgirOnO", false},
+
 		{"kk", "әғһіңөқұүӘҒҺІҢӨҚҰҮ", "aghinoquuaghinoquu", true},
 		{"kk", "әғһіңөқұүӘҒҺІҢӨҚҰҮ", "aghinoquuAGHINOQUU", false},
+
 		{"pt", "áÁéÉíÍóÓöÖúÚüÜ", "aAeEiIoOoOuUuU", false},
+
 		{"ro", "ĂăÂăÎîȘșȚț", "aaaaiisstt", true},
 		{"ro", "ĂăÂăÎîȘșȚț", "AaAaIiSsTt", false},
+
 		{"tr", "şüöğıçŞÜÖİĞÇ", "suogicsuoigc", true},
 		{"tr", "şüöğıçŞÜÖİĞÇ", "suogicSUOIGC", false},
 
 		// & fun.
 		{"bg", "Това и онова", "tova-i-onova", true},
+
 		{"cs", "Toto & Tamto", "toto-a-tamto", true},
 		{"cs", "Toto & Tamto", "Toto-a-Tamto", false},
 		{"cs", "Toto @ Tamto", "toto-zavinac-tamto", true},
 		{"cs", "Toto @ Tamto", "Toto-zavinac-Tamto", false},
+
 		{"ces", "Toto & Tamto", "toto-a-tamto", true},
 		{"ces", "Toto & Tamto", "Toto-a-Tamto", false},
 		{"ces", "Toto @ Tamto", "toto-zavinac-tamto", true},
@@ -487,9 +519,12 @@ func BenchmarkMakeShort(b *testing.B) {
 }
 
 func BenchmarkMakeShortSymbols(b *testing.B) {
+	shortStr := "Hello/Hi world"
+
 	b.ReportAllocs()
+	b.ResetTimer()
 	for n := 0; n < b.N; n++ {
-		Make("·/,:;`˜'\" &€￡￥")
+		Make(shortStr)
 	}
 }