update phonemis library

Author: IgorSwat

packages/react-native-executorch/third-party/android/libs/phonemis/arm64-v8a/libphonemis.a

@@ -36,6 +36,184 @@ inline const std::unordered_map<std::int64_t, std::string> kLargeCardinals = {
     {1000000000000LL, "trillion"}};
 } // namespace num2words::constants
 
+// ----------------------------
+// unicode processing constants
+// ----------------------------
+namespace unicode::constants {
+// Foreign character to latin-only conversion
+inline const std::unordered_map<char32_t, std::string> kForeignToLatin = {
+    // Polish
+    {U'Ą', "A"},
+    {U'ą', "a"},
+    {U'Ć', "C"},
+    {U'ć', "c"},
+    {U'Ę', "E"},
+    {U'ę', "e"},
+    {U'Ł', "L"},
+    {U'ł', "l"},
+    {U'Ń', "N"},
+    {U'ń', "n"},
+    {U'Ó', "O"},
+    {U'ó', "o"},
+    {U'Ś', "S"},
+    {U'ś', "s"},
+    {U'Ź', "Z"},
+    {U'ź', "z"},
+    {U'Ż', "Z"},
+    {U'ż', "z"},
+
+    // German
+    {U'Ä', "A"},
+    {U'ä', "a"},
+    {U'Ö', "O"},
+    {U'ö', "o"},
+    {U'Ü', "U"},
+    {U'ü', "u"},
+    {U'ß', "ss"},
+
+    // French
+    {U'À', "A"},
+    {U'à', "a"},
+    {U'Â', "A"},
+    {U'â', "a"},
+    {U'Æ', "AE"},
+    {U'æ', "ae"},
+    {U'Ç', "C"},
+    {U'ç', "c"},
+    {U'É', "E"},
+    {U'é', "e"},
+    {U'È', "E"},
+    {U'è', "e"},
+    {U'Ê', "E"},
+    {U'ê', "e"},
+    {U'Ë', "E"},
+    {U'ë', "e"},
+    {U'Î', "I"},
+    {U'î', "i"},
+    {U'Ï', "I"},
+    {U'ï', "i"},
+    {U'Ô', "O"},
+    {U'ô', "o"},
+    {U'Œ', "OE"},
+    {U'œ', "oe"},
+    {U'Ù', "U"},
+    {U'ù', "u"},
+    {U'Û', "U"},
+    {U'û', "u"},
+    {U'Ü', "U"},
+    {U'ü', "u"},
+
+    // Spanish
+    {U'Á', "A"},
+    {U'á', "a"},
+    {U'É', "E"},
+    {U'é', "e"},
+    {U'Í', "I"},
+    {U'í', "i"},
+    {U'Ó', "O"},
+    {U'ó', "o"},
+    {U'Ú', "U"},
+    {U'ú', "u"},
+    {U'Ü', "U"},
+    {U'ü', "u"},
+    {U'Ñ', "N"},
+    {U'ñ', "n"},
+
+    // Italian
+    {U'À', "A"},
+    {U'à', "a"},
+    {U'È', "E"},
+    {U'è', "e"},
+    {U'É', "E"},
+    {U'é', "e"},
+    {U'Ì', "I"},
+    {U'ì', "i"},
+    {U'Í', "I"},
+    {U'í', "i"},
+    {U'Î', "I"},
+    {U'î', "i"},
+    {U'Ò', "O"},
+    {U'ò', "o"},
+    {U'Ó', "O"},
+    {U'ó', "o"},
+    {U'Ù', "U"},
+    {U'ù', "u"},
+    {U'Ú', "U"},
+    {U'ú', "u"},
+
+    // Scandinavian
+    {U'Å', "A"},
+    {U'å', "a"},
+    {U'Æ', "AE"},
+    {U'æ', "ae"},
+    {U'Ø', "O"},
+    {U'ø', "o"},
+
+    // Hungarian
+    {U'Á', "A"},
+    {U'á', "a"},
+    {U'É', "E"},
+    {U'é', "e"},
+    {U'Í', "I"},
+    {U'í', "i"},
+    {U'Ó', "O"},
+    {U'ó', "o"},
+    {U'Ö', "O"},
+    {U'ö', "o"},
+    {U'Ő', "O"},
+    {U'ő', "o"},
+    {U'Ú', "U"},
+    {U'ú', "u"},
+    {U'Ü', "U"},
+    {U'ü', "u"},
+    {U'Ű', "U"},
+    {U'ű', "u"},
+
+    // Czech/Slovak
+    {U'Á', "A"},
+    {U'á', "a"},
+    {U'Č', "C"},
+    {U'č', "c"},
+    {U'Ď', "D"},
+    {U'ď', "d"},
+    {U'É', "E"},
+    {U'é', "e"},
+    {U'Ě', "E"},
+    {U'ě', "e"},
+    {U'Í', "I"},
+    {U'í', "i"},
+    {U'Ň', "N"},
+    {U'ň', "n"},
+    {U'Ó', "O"},
+    {U'ó', "o"},
+    {U'Ř', "R"},
+    {U'ř', "r"},
+    {U'Š', "S"},
+    {U'š', "s"},
+    {U'Ť', "T"},
+    {U'ť', "t"},
+    {U'Ú', "U"},
+    {U'ú', "u"},
+    {U'Ů', "U"},
+    {U'ů', "u"},
+    {U'Ý', "Y"},
+    {U'ý', "y"},
+    {U'Ž', "Z"},
+    {U'ž', "z"},
+
+    // Romanian
+    {U'Ă', "A"},
+    {U'ă', "a"},
+    {U'Â', "A"},
+    {U'â', "a"},
+    {U'Î', "I"},
+    {U'î', "i"},
+    {U'Ș', "S"},
+    {U'ș', "s"},
+    {U'Ț', "T"},
+    {U'ț', "t"}};
+} // namespace unicode::constants
+
 // ---------------
 // other constants
 // ---------------

packages/react-native-executorch/third-party/android/libs/phonemis/x86_64/libphonemis.a

@@ -5,6 +5,10 @@
 
 namespace phonemis::preprocessor {
 
+// Normalizes the text by replacing all foreign characters
+// to latin-only phrases.
+std::string normalize_unicode(const std::string &text);
+
 // Divides a monolit text into multiple sentences.
 // A sentence always ends with a end of sentence character (defined in
 // constants.h).