From fbac30429bebc79973bcaab34870da1fddc64edd Mon Sep 17 00:00:00 2001
From: Keerthan Vasist <kvasist@amazon.com>
Date: Thu, 21 Jul 2022 09:14:26 -0700
Subject: [PATCH] fix: Two letter language code must be supported

---
 src/sagemaker/clarify.py | 67 ++++++++++++++++++++++++++++++++++++++--
 1 file changed, 65 insertions(+), 2 deletions(-)

diff --git a/src/sagemaker/clarify.py b/src/sagemaker/clarify.py
index 873a87ca57..6590d30514 100644
--- a/src/sagemaker/clarify.py
+++ b/src/sagemaker/clarify.py
@@ -512,68 +512,131 @@ class TextConfig:
     _SUPPORTED_GRANULARITIES = ["token", "sentence", "paragraph"]
     _SUPPORTED_LANGUAGES = [
         "chinese",
+        "zh",
         "danish",
+        "da",
         "dutch",
+        "nl",
         "english",
+        "en",
         "french",
+        "fr",
         "german",
+        "de",
         "greek",
+        "el",
         "italian",
+        "it",
         "japanese",
+        "ja",
         "lithuanian",
+        "lt",
         "multi-language",
+        "xx",
         "norwegian bokmål",
+        "nb",
         "polish",
+        "pl",
         "portuguese",
+        "pt",
         "romanian",
+        "ro",
         "russian",
+        "ru",
         "spanish",
+        "es",
         "afrikaans",
+        "af",
         "albanian",
+        "sq",
         "arabic",
+        "ar",
         "armenian",
+        "hy",
         "basque",
+        "eu",
         "bengali",
+        "bn",
         "bulgarian",
+        "bg",
         "catalan",
+        "ca",
         "croatian",
+        "hr",
         "czech",
+        "cs",
         "estonian",
+        "et",
         "finnish",
+        "fi",
         "gujarati",
+        "gu",
         "hebrew",
+        "he",
         "hindi",
+        "hi",
         "hungarian",
+        "hu",
         "icelandic",
+        "is",
         "indonesian",
+        "id",
         "irish",
+        "ga",
         "kannada",
+        "kn",
         "kyrgyz",
+        "ky",
         "latvian",
+        "lv",
         "ligurian",
+        "lij",
         "luxembourgish",
+        "lb",
         "macedonian",
+        "mk",
         "malayalam",
+        "ml",
         "marathi",
+        "mr",
         "nepali",
+        "ne",
         "persian",
+        "fa",
         "sanskrit",
+        "sa",
         "serbian",
+        "sr",
         "setswana",
+        "tn",
         "sinhala",
+        "si",
         "slovak",
+        "sk",
         "slovenian",
+        "sl",
         "swedish",
+        "sv",
         "tagalog",
+        "tl",
         "tamil",
+        "ta",
         "tatar",
+        "tt",
         "telugu",
+        "te",
         "thai",
+        "th",
         "turkish",
+        "tr",
         "ukrainian",
+        "uk",
         "urdu",
+        "ur",
         "vietnamese",
+        "vi",
         "yoruba",
+        "yo",
     ]
 
     def __init__(
@@ -602,8 +665,8 @@ def __init__(
                 ``"persian"``, ``"sanskrit"``, ``"serbian"``, ``"setswana"``, ``"sinhala"``,
                 ``"slovak"``, ``"slovenian"``, ``"swedish"``, ``"tagalog"``, ``"tamil"``,
                 ``"tatar"``, ``"telugu"``, ``"thai"``, ``"turkish"``, ``"ukrainian"``, ``"urdu"``,
-                ``"vietnamese"``, ``"yoruba"``.
-                Use ``"multi-language"`` for a mix of multiple languages.
+                ``"vietnamese"``, ``"yoruba"``. Use "multi-language" for a mix of multiple
+                languages. The corresponding two-letter ISO codes are also accepted.
 
         Raises:
             ValueError: when ``granularity`` is not in list of supported values