add croatian, serbian

dicts/croatian/language.go

@@ -0,0 +1,6 @@
+package croatian
+
+import "embed"
+
+//go:embed *.tsv language.json weights1.json.lzw
+var Language embed.FS

dicts/croatian/language.json

@@ -0,0 +1,33 @@
+{"Map":{"a":["a","ǎ","aː","ǎː","â","âː"],
+"b":["b"],
+"c":["ts"],
+"d":["d","t"],
+"e":["e","ě","ê","eː","ěː","êː"],
+"f":["f"],
+"g":["ɡ"],
+"h":["x"],
+"i":["i","iː","ǐ","ǐː","î","îː"],
+"j":["j","ʒ"],
+"k":["k"],
+"l":["l"],
+"lj":["ʎ"],
+"m":["m"],
+"n":["n"],
+"nj":["ɲ","nj"],
+"o":["o","ǒ","oː","ô","ǒː","ôː"],
+"p":["p"],
+"r":["r","ř","r̂","řː","r̩","r̂ː","rː"],
+"s":["s"],
+"t":["t"],
+"u":["u","ǔ","û","ǔː","uː","ûː"],
+"v":["ʋ","v"],
+"z":["z"],
+"ć":["tɕ"],
+"č":["tʃ"],
+"đ":["dʑ"],
+"š":["ʃ"],
+"ź":["ʑ"],
+"ž":["ʒ"]}
+,"SrcMulti":null,"DstMulti":null,"SrcMultiSuffix":null,"DstMultiSuffix":["ː"],
+"DstMultiPrefix":["ˈ","'","ˌ"],
+"DropLast":null,"SplitBefore":null,"SplitAfter":null,"PrePhonWordSteps":[{"Trim":".,"},{"ToLower":true}]}

dicts/dicts.go

@@ -71,6 +71,8 @@ import "github.com/neurlang/goruut/dicts/thai"
 import "github.com/neurlang/goruut/dicts/zulu"
 import "github.com/neurlang/goruut/dicts/catalan"
 import "github.com/neurlang/goruut/dicts/armenian"
+import "github.com/neurlang/goruut/dicts/croatian"
+import "github.com/neurlang/goruut/dicts/serbian"
 import "errors"
 
 var ErrUnsupportedLanguage = errors.New("unsupportedLang")
@@ -241,6 +243,10 @@ func GetDict(lang, filename string) ([]byte, error) {
 		return catalan.Language.ReadFile(filename)
 	case "Armenian":
 		return armenian.Language.ReadFile(filename)
+	case "Croatian":
+		return croatian.Language.ReadFile(filename)
+	case "Serbian":
+		return serbian.Language.ReadFile(filename)
 	default:
 		return nil, ErrUnsupportedLanguage
 	}

dicts/serbian/language.go

@@ -0,0 +1,6 @@
+package serbian
+
+import "embed"
+
+//go:embed *.tsv language.json weights1.json.lzw
+var Language embed.FS

dicts/serbian/language.json

@@ -0,0 +1,35 @@
+{"Map":{"а":["a","ǎ","aː","ǎː","â","âː"],
+"б":["b"],
+"в":["ʋ","v"],
+"г":["ɡ"],
+"д":["d"],
+"е":["e","ě","ê","eː","ěː","êː"],
+"ж":["ʒ"],
+"з":["z"],
+"з́":["ʑ"],
+"и":["i","iː","ǐ","ǐː","î","îː"],
+"к":["k"],
+"л":["l"],
+"м":["m"],
+"н":["n"],
+"о":["o","ǒ","oː","ô","ǒː","ôː"],
+"п":["p"],
+"р":["r","ř","r̂","řː","r̩","r̂ː","rː"],
+"с":["s"],
+"с́":["ɕ"],
+"т":["t"],
+"у":["u","ǔ","û","ǔː","uː","ûː"],
+"ф":["f"],
+"х":["x","k"],
+"ц":["ts"],
+"ч":["tʃ"],
+"ш":["ʃ"],
+"ђ":["dʑ"],
+"ј":["j","ʒ"],
+"љ":["ʎ"],
+"њ":["ɲ"],
+"ћ":["tɕ"],
+"џ":["dʒ"]}
+,"SrcMulti":null,"DstMulti":null,"SrcMultiSuffix":null,"DstMultiSuffix":["ː"],
+"DstMultiPrefix":["ˈ","'","ˌ"],
+"DropLast":null,"SplitBefore":null,"SplitAfter":null,"PrePhonWordSteps":[{"Trim":".,"},{"ToLower":true}]}