From 33360494a5af96567d76a6ae6650f8718bc6001b Mon Sep 17 00:00:00 2001
From: 07pepa <“no@sharebcs.spam”>
Date: Sat, 24 Feb 2024 11:43:24 +0100
Subject: [PATCH] Add language code definitions and test

* added literal with custom exception message
* tested all possibilities exhaustively
---
 pydantic_extra_types/language_code.py | 206 +++++++++++++++++++++++++
 tests/test_language_codes.py          | 212 ++++++++++++++++++++++++++
 2 files changed, 418 insertions(+)
 create mode 100644 pydantic_extra_types/language_code.py
 create mode 100644 tests/test_language_codes.py

diff --git a/pydantic_extra_types/language_code.py b/pydantic_extra_types/language_code.py
new file mode 100644
index 00000000..0590bbf9
--- /dev/null
+++ b/pydantic_extra_types/language_code.py
@@ -0,0 +1,206 @@
+from typing import Any, Literal
+
+from pydantic import ValidationInfo, WrapValidator
+from typing_extensions import Annotated
+
+
+def _not_iso_code(v: Any, next_: Any, ctx: ValidationInfo) -> Any:
+    try:
+        return next_(v, ctx)
+    except Exception as _:
+        raise ValueError(
+            f'{v} is not a valid ISO 639-3 language code. ' f'See https://wikipedia.org/wiki/ISO_639-3.'
+        ) from None
+
+
+# language code definition as defined in ISO 639-3 https://wikipedia.org/wiki/ISO_639-3
+# basically just defines list of literals  https://docs.pydantic.dev/1.10/usage/types/#literal-type
+LanguageCode = Annotated[
+    Literal[
+        'aar',
+        'abk',
+        'afr',
+        'aka',
+        'alb',
+        'amh',
+        'ara',
+        'arg',
+        'arm',
+        'asm',
+        'ava',
+        'ave',
+        'aym',
+        'aze',
+        'bak',
+        'bam',
+        'baq',
+        'bel',
+        'ben',
+        'bih',
+        'bis',
+        'bos',
+        'bre',
+        'bul',
+        'bur',
+        'cat',
+        'cha',
+        'che',
+        'chi',
+        'chu',
+        'chv',
+        'cor',
+        'cos',
+        'cre',
+        'cze',
+        'dan',
+        'div',
+        'dut',
+        'dzo',
+        'eng',
+        'epo',
+        'est',
+        'ewe',
+        'fao',
+        'fij',
+        'fin',
+        'fre',
+        'fry',
+        'ful',
+        'geo',
+        'ger',
+        'gla',
+        'gle',
+        'glg',
+        'glv',
+        'gre',
+        'grn',
+        'guj',
+        'hat',
+        'hau',
+        'heb',
+        'her',
+        'hin',
+        'hmo',
+        'hrv',
+        'hun',
+        'ibo',
+        'ice',
+        'ido',
+        'iii',
+        'iku',
+        'ile',
+        'ina',
+        'ind',
+        'ipk',
+        'ita',
+        'jav',
+        'jpn',
+        'kal',
+        'kan',
+        'kas',
+        'kau',
+        'kaz',
+        'khm',
+        'kik',
+        'kin',
+        'kir',
+        'kom',
+        'kon',
+        'kor',
+        'kua',
+        'kur',
+        'lao',
+        'lat',
+        'lav',
+        'lim',
+        'lin',
+        'lit',
+        'ltz',
+        'lub',
+        'lug',
+        'mac',
+        'mah',
+        'mal',
+        'mao',
+        'mar',
+        'may',
+        'mlg',
+        'mlt',
+        'mon',
+        'nau',
+        'nav',
+        'nbl',
+        'nde',
+        'ndo',
+        'nep',
+        'nno',
+        'nob',
+        'nor',
+        'nya',
+        'oci',
+        'oji',
+        'ori',
+        'orm',
+        'oss',
+        'pan',
+        'per',
+        'pli',
+        'pol',
+        'por',
+        'pus',
+        'que',
+        'roh',
+        'rum',
+        'run',
+        'rus',
+        'sag',
+        'san',
+        'sin',
+        'slo',
+        'slv',
+        'sme',
+        'smo',
+        'sna',
+        'snd',
+        'som',
+        'sot',
+        'spa',
+        'srd',
+        'srp',
+        'ssw',
+        'sun',
+        'swa',
+        'swe',
+        'tah',
+        'tam',
+        'tat',
+        'tel',
+        'tgk',
+        'tgl',
+        'tha',
+        'tib',
+        'tir',
+        'ton',
+        'tsn',
+        'tso',
+        'tuk',
+        'tur',
+        'twi',
+        'uig',
+        'ukr',
+        'urd',
+        'uzb',
+        'ven',
+        'vie',
+        'vol',
+        'wel',
+        'wln',
+        'wol',
+        'xho',
+        'yid',
+        'yor',
+        'zha',
+        'zul',
+    ],
+    WrapValidator(_not_iso_code),
+]
diff --git a/tests/test_language_codes.py b/tests/test_language_codes.py
new file mode 100644
index 00000000..e7b6fbb0
--- /dev/null
+++ b/tests/test_language_codes.py
@@ -0,0 +1,212 @@
+import pytest
+from pydantic import BaseModel, ValidationError
+
+from pydantic_extra_types.language_code import LanguageCode
+
+
+class CheckingModel(BaseModel):
+    lang: LanguageCode
+
+
+@pytest.mark.parametrize(
+    'lang',
+    [
+        'aar',
+        'abk',
+        'afr',
+        'aka',
+        'alb',
+        'amh',
+        'ara',
+        'arg',
+        'arm',
+        'asm',
+        'ava',
+        'ave',
+        'aym',
+        'aze',
+        'bak',
+        'bam',
+        'baq',
+        'bel',
+        'ben',
+        'bih',
+        'bis',
+        'bos',
+        'bre',
+        'bul',
+        'bur',
+        'cat',
+        'cha',
+        'che',
+        'chi',
+        'chu',
+        'chv',
+        'cor',
+        'cos',
+        'cre',
+        'cze',
+        'dan',
+        'div',
+        'dut',
+        'dzo',
+        'eng',
+        'epo',
+        'est',
+        'ewe',
+        'fao',
+        'fij',
+        'fin',
+        'fre',
+        'fry',
+        'ful',
+        'geo',
+        'ger',
+        'gla',
+        'gle',
+        'glg',
+        'glv',
+        'gre',
+        'grn',
+        'guj',
+        'hat',
+        'hau',
+        'heb',
+        'her',
+        'hin',
+        'hmo',
+        'hrv',
+        'hun',
+        'ibo',
+        'ice',
+        'ido',
+        'iii',
+        'iku',
+        'ile',
+        'ina',
+        'ind',
+        'ipk',
+        'ita',
+        'jav',
+        'jpn',
+        'kal',
+        'kan',
+        'kas',
+        'kau',
+        'kaz',
+        'khm',
+        'kik',
+        'kin',
+        'kir',
+        'kom',
+        'kon',
+        'kor',
+        'kua',
+        'kur',
+        'lao',
+        'lat',
+        'lav',
+        'lim',
+        'lin',
+        'lit',
+        'ltz',
+        'lub',
+        'lug',
+        'mac',
+        'mah',
+        'mal',
+        'mao',
+        'mar',
+        'may',
+        'mlg',
+        'mlt',
+        'mon',
+        'nau',
+        'nav',
+        'nbl',
+        'nde',
+        'ndo',
+        'nep',
+        'nno',
+        'nob',
+        'nor',
+        'nya',
+        'oci',
+        'oji',
+        'ori',
+        'orm',
+        'oss',
+        'pan',
+        'per',
+        'pli',
+        'pol',
+        'por',
+        'pus',
+        'que',
+        'roh',
+        'rum',
+        'run',
+        'rus',
+        'sag',
+        'san',
+        'sin',
+        'slo',
+        'slv',
+        'sme',
+        'smo',
+        'sna',
+        'snd',
+        'som',
+        'sot',
+        'spa',
+        'srd',
+        'srp',
+        'ssw',
+        'sun',
+        'swa',
+        'swe',
+        'tah',
+        'tam',
+        'tat',
+        'tel',
+        'tgk',
+        'tgl',
+        'tha',
+        'tib',
+        'tir',
+        'ton',
+        'tsn',
+        'tso',
+        'tuk',
+        'tur',
+        'twi',
+        'uig',
+        'ukr',
+        'urd',
+        'uzb',
+        'ven',
+        'vie',
+        'vol',
+        'wel',
+        'wln',
+        'wol',
+        'xho',
+        'yid',
+        'yor',
+        'zha',
+        'zul',
+    ],
+)
+def test_language_code_ok(lang: str):
+    model = CheckingModel(lang=lang)
+    assert model.lang == lang
+
+
+def test_language_fail():
+    with pytest.raises(
+        ValidationError,
+        match=r'1 validation error for CheckingModel\nlang\n  Value error, en-US is '
+        'not a valid ISO 639-3 language code\\. '
+        'See https://wikipedia.org/wiki/ISO_639-3\\..*',
+    ):
+        CheckingModel(lang='en-US')