test: update langmap tests for expanded dict shape with regions

tests/test_langmap.py

@@ -6,7 +6,7 @@ def test_langid_mapping_is_nonempty():
 
 
 def test_langid_mapping_count():
-    assert len(langid_to_language) == 22, f"Expected 22 Tier 1 languages, got {len(langid_to_language)}"
+    assert len(langid_to_language) >= 400, f"Expected ~419 languages, got {len(langid_to_language)}"
 
 
 def test_keys_are_bcp47_tokens():
@@ -15,53 +15,42 @@ def test_keys_are_bcp47_tokens():
         assert key.endswith(">"), f"Key {key} does not end with '>'"
 
 
-def test_values_are_nonempty_strings():
+def test_values_are_dicts_with_name_and_region():
     for key, value in langid_to_language.items():
-        assert isinstance(value, str) and value.strip(), f"Empty language name for {key}"
+        assert isinstance(value, dict), f"Value for {key} is not a dict"
+        assert "name" in value, f"Value for {key} missing 'name' key"
+        assert "region" in value, f"Value for {key} missing 'region' key"
+
+
+def test_names_are_nonempty_strings():
+    for key, value in langid_to_language.items():
+        assert isinstance(value["name"], str) and value["name"].strip(), f"Empty name for {key}"
+
+
+def test_regions_are_nonempty_strings():
+    for key, value in langid_to_language.items():
+        assert isinstance(value["region"], str) and value["region"].strip(), f"Empty region for {key}"
 
 
 def test_no_leading_or_trailing_whitespace():
     for key, value in langid_to_language.items():
-        assert value == value.strip(), f"Language name for {key} has leading/trailing whitespace: {value!r}"
+        assert value["name"] == value["name"].strip(), f"Name for {key} has whitespace: {value['name']!r}"
+        assert value["region"] == value["region"].strip(), f"Region for {key} has whitespace: {value['region']!r}"
 
 
 def test_no_duplicate_language_names():
-    names = list(langid_to_language.values())
+    names = [v["name"] for v in langid_to_language.values()]
     assert len(names) == len(set(names)), "Duplicate language names found"
 
 
-def test_all_tier1_languages_present():
-    """Verify all 22 Tier 1 languages are present."""
-    expected = {
-        "Afrikaans",
-        "Bulgarian",
-        "Bosnian",
-        "Catalan",
-        "Czech",
-        "Danish",
-        "German",
-        "Spanish",
-        "Filipino",
-        "French",
-        "Croatian",
-        "Indonesian",
-        "Italian",
-        "Macedonian",
-        "Malay",
-        "Maltese",
-        "Norwegian Nynorsk",
-        "Norwegian",
-        "Portuguese",
-        "Romanian",
-        "Slovak",
-        "Swedish",
-    }
-    values = set(langid_to_language.values())
-    assert values == expected, f"Mismatch: missing={expected - values}, extra={values - expected}"
-
-
-def test_removed_languages_absent():
-    """Languages outside Tier 1 must not be in the mapping."""
-    values = set(langid_to_language.values())
-    for lang in ["Japanese", "Hindi", "Swahili", "Arabic", "Russian", "Polish", "Dutch"]:
-        assert lang not in values, f"{lang} should have been removed (not Tier 1)"
+def test_key_languages_present():
+    """Spot-check key language codes across regions."""
+    key_codes = ["<2en>", "<2fr>", "<2de>", "<2es>", "<2ja>", "<2zh>", "<2ar>", "<2hi>", "<2pt>", "<2ru>"]
+    for code in key_codes:
+        assert code in langid_to_language, f"Missing language code: {code}"
+
+
+def test_no_other_region():
+    """No language should have 'Other' as its region."""
+    for key, value in langid_to_language.items():
+        assert value["region"] != "Other", f"{key} ({value['name']}) has region 'Other'"