add the languages support

bump to 0.0.6

pygoruut/pygoruut.py

@@ -5,6 +5,7 @@
 from dataclasses import dataclass
 from typing import List
 from pygoruut.executable import MyPlatformExecutable
+from pygoruut.pygoruut_languages import PygoruutLanguages
 from pygoruut.config import Config
 import tempfile
 
@@ -61,6 +62,8 @@ def __del__(self):
             self.process.wait()
 
     def phonemize(self, language="Greek", sentence="Σήμερα...") -> PhonemeResponse:
+        # handle ISO here
+        language = PygoruutLanguages()[language]
         url = self.config.url("tts/phonemize/sentence")
         payload = {"Language": language, "Sentence": sentence}
 

pygoruut/pygoruut_languages.py

@@ -0,0 +1,72 @@
+class PygoruutLanguages:
+    def __init__(self):
+        # ISO 639 language codes and their corresponding languages
+        self.languagesISO639 = {
+		"ar": "Arabic",
+		"bn": "Bengali",
+		"zh": "ChineseMandarin",
+		"cs": "Czech",
+		"nl": "Dutch",
+		"en": "English",
+		"eo": "Esperanto",
+		"fa": "Farsi",
+		"fi": "Finnish",
+		"fr": "French",
+		"de": "German",
+		"el": "Greek",
+		"gu": "Gujarati",
+		"hi": "Hindi",
+		"hu": "Hungarian",
+		"is": "Icelandic",
+		"it": "Italian",
+		"jam": "Jamaican",
+		"ja": "Japanese",
+		"lb": "Luxembourgish",
+		"ms": "MalayLatin",
+		"mr": "Marathi",
+		"no": "Norwegian",
+		"pl": "Polish",
+		"pt": "Portuguese",
+		"pa": "Punjabi",
+		"ro": "Romanian",
+		"ru": "Russian",
+		"sk": "Slovak",
+		"es": "Spanish",
+		"sw": "Swahili",
+		"sv": "Swedish",
+		"ta": "Tamil",
+		"te": "Telugu",
+		"tr": "Turkish",
+		"uk": "Ukrainian",
+		"ur": "Urdu",
+		"vi": "VietnameseNorthern"
+        }
+
+        # Non-ISO 639 language or dialect names
+        self.languagesNonISO639 = [
+		"BengaliDhaka",
+		"BengaliRahr",
+		"Isan",
+		"MalayArab",
+		"VietnameseCentral",
+		"VietnameseSouthern"
+        ]
+
+    def get_supported_languages(self):
+        # Concatenate the keys of languagesISO639 with the values of languagesNonISO639
+        return list(self.languagesISO639.keys()) + self.languagesNonISO639
+
+    def get_all_supported_languages(self):
+        # Concatenate the keys and values of languagesISO639 with the values of languagesNonISO639
+        return list(self.languagesISO639.keys()) + list(self.languagesISO639.values()) + self.languagesNonISO639
+
+    def __getitem__(self, value):
+        if len(value) == 2 or len(value) == 3:
+            value = self.languagesISO639[value] or value
+        return value
+
+# Example usage:
+if __name__ == '__main__':
+    pygoruut = PygoruutLanguages()
+    print(pygoruut.get_supported_languages())
+    print(pygoruut["vi"])

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "pygoruut"
-version = "0.0.5"
+version = "0.0.6"
 description = "A Python wrapper for the goruut phonemization tool"
 readme = "README.md"
 authors = [{ name = "Neurlang Project", email = "[email protected]" }]

setup.py

@@ -2,7 +2,7 @@
 
 setup(
     name="pygoruut",
-    version="0.0.5",
+    version="0.0.6",
     packages=find_packages(),
     install_requires=[
         "requests",

tests/test_pygoruut_sanity.py

@@ -11,7 +11,7 @@ def tearDown(self):
 
     def test_languages_and_word_pairs(self):
         test_cases = [
-            ("Greek", [
+            ("el", [
                 ("Σήμερα", "sime̞ɾɐ"),
                 ("καλημέρα", "kalime̞ɾa"),
                 ("ευχαριστώ", "e̞fxaɾisto")
@@ -26,7 +26,7 @@ def test_languages_and_word_pairs(self):
                 ("mundo", "mundo"),
                 ("gracias", "gɾakias")
             ]),
-            ("French", [
+            ("fr", [
                 ("bonjour", "bonʒuʁ"),
                 ("monde", "mod"),
                 ("merci", "mɛʁki")