Move get_emoji_unicode_dict(),get_aliases_unicode_dict() to testu…

…tils.py

emoji/unicode_codes/__init__.py

@@ -1,57 +1,33 @@
-from typing import Any, Dict, Optional
+from typing import Optional
 from functools import lru_cache
-from emoji.unicode_codes.data_dict import *
+from emoji.unicode_codes.data_dict import EMOJI_DATA, STATUS, LANGUAGES
 
 __all__ = [
-    'get_emoji_by_name', 'get_emoji_unicode_dict', 'get_aliases_unicode_dict',
+    'get_emoji_by_name',
     'EMOJI_DATA', 'STATUS', 'LANGUAGES'
 ]
 
 
-_EMOJI_UNICODE: Dict[str, Any] = {lang: None for lang in LANGUAGES}  # Cache for the language dicts
-
-_ALIASES_UNICODE: Dict[str, str] = {}  # Cache for the aliases dict
-
-
 @lru_cache(maxsize=4000)
-def get_emoji_by_name(name: str, lang: str) -> Optional[str]:
-    """Find emoji in a specific language or return None if not found"""
+def get_emoji_by_name(name: str, language: str) -> Optional[str]:
+    """
+    Find emoji by short-name in a specific language.
+    Returns None if not found
+
+    :param name: emoji short code e.g. ":banana:"
+    :param language: language-code e.g. 'es', 'de', etc. or 'alias'
+    """
 
     fully_qualified = STATUS['fully_qualified']
 
-    if lang == 'alias':
+    if language == 'alias':
         for emj, data in EMOJI_DATA.items():
             if name in data.get('alias', []) and data['status'] <= fully_qualified:
                 return emj
-        lang = 'en'
+        language = 'en'
 
     for emj, data in EMOJI_DATA.items():
-        if data.get(lang) == name and data['status'] <= fully_qualified:
+        if data.get(language) == name and data['status'] <= fully_qualified:
             return emj
 
     return None
-
-
-def get_emoji_unicode_dict(lang: str) -> Dict[str, Any]:
-    """Generate dict containing all fully-qualified and component emoji name for a language
-    The dict is only generated once per language and then cached in _EMOJI_UNICODE[lang]"""
-
-    if _EMOJI_UNICODE[lang] is None:
-        _EMOJI_UNICODE[lang] = {data[lang]: emj for emj, data in EMOJI_DATA.items()
-                                if lang in data and data['status'] <= STATUS['fully_qualified']}
-
-    return _EMOJI_UNICODE[lang]
-
-
-def get_aliases_unicode_dict() -> Dict[str, str]:
-    """Generate dict containing all fully-qualified and component aliases
-    The dict is only generated once and then cached in _ALIASES_UNICODE"""
-
-    if not _ALIASES_UNICODE:
-        _ALIASES_UNICODE.update(get_emoji_unicode_dict('en'))
-        for emj, data in EMOJI_DATA.items():
-            if 'alias' in data and data['status'] <= STATUS['fully_qualified']:
-                for alias in data['alias']:
-                    _ALIASES_UNICODE[alias] = emj
-
-    return _ALIASES_UNICODE

tests/test_core.py

@@ -6,7 +6,7 @@
 from typing_extensions import Literal
 import pytest
 import emoji.unicode_codes
-from testutils import ascii, normalize, all_language_packs, all_language_and_alias_packs
+from testutils import ascii, normalize, all_language_packs, all_language_and_alias_packs, get_emoji_unicode_dict
 
 
 def test_emojize_name_only():
@@ -108,7 +108,7 @@ def test_emojize_variant():
     def remove_variant(s: str) -> str:
         return re.sub('[\ufe0e\ufe0f]$', '', s)
 
-    english_pack = emoji.unicode_codes.get_emoji_unicode_dict('en')
+    english_pack = get_emoji_unicode_dict('en')
 
     assert emoji.emojize(
         ':Taurus:', variant=None) == english_pack[':Taurus:']

tests/test_unicode_codes.py

@@ -2,7 +2,7 @@
 
 from typing import Set
 import emoji.unicode_codes
-from testutils import get_language_packs
+from testutils import get_language_packs, get_aliases_unicode_dict, get_emoji_unicode_dict
 
 
 def test_emoji_english_names():
@@ -17,8 +17,8 @@ def test_compare_normal_and_aliases():
     # There should always be more aliases than normal codes
     # since the aliases contain the normal codes
 
-    english_pack = emoji.unicode_codes.get_emoji_unicode_dict('en')
-    alias_pack = emoji.unicode_codes.get_aliases_unicode_dict()
+    english_pack = get_emoji_unicode_dict('en')
+    alias_pack = get_aliases_unicode_dict()
 
     assert len(english_pack) < len(alias_pack)
 
@@ -32,3 +32,16 @@ def test_no_alias_duplicates():
             for alias in data['alias']:
                 assert alias not in all_aliases
                 all_aliases.add(alias)
+
+
+def test_get_emoji_by_alias():
+    # Compare get_emoji_by_name() to get_aliases_unicode_dict()
+    for alias, emj in get_aliases_unicode_dict().items():
+        assert emoji.unicode_codes.get_emoji_by_name(alias, 'alias') == emj
+
+
+def test_get_emoji_by_name():
+    # Compare get_emoji_by_name() to get_emoji_unicode_dict()
+    for lang in emoji.LANGUAGES:
+        for name, emj in get_emoji_unicode_dict(lang).items():
+            assert emoji.unicode_codes.get_emoji_by_name(name, lang) == emj

utils/testutils.py

@@ -23,14 +23,42 @@ def is_normalized(form: _NormalizationForm, s: str) -> bool:
         return normalize(form, s) == s
 
 
+_EMOJI_UNICODE: Dict[str, Any] = {lang: None for lang in emoji.LANGUAGES}  # Cache for the language dicts
+_ALIASES_UNICODE: Dict[str, str] = {}  # Cache for the aliases dict
+
+def get_emoji_unicode_dict(lang: str) -> Dict[str, Any]:
+    """Generate dict containing all fully-qualified and component emoji name for a language
+    The dict is only generated once per language and then cached in _EMOJI_UNICODE[lang]"""
+
+    if _EMOJI_UNICODE[lang] is None:
+        _EMOJI_UNICODE[lang] = {data[lang]: emj for emj, data in emoji.EMOJI_DATA.items()
+                                if lang in data and data['status'] <= emoji.STATUS['fully_qualified']}
+
+    return _EMOJI_UNICODE[lang]
+
+
+def get_aliases_unicode_dict() -> Dict[str, str]:
+    """Generate dict containing all fully-qualified and component aliases
+    The dict is only generated once and then cached in _ALIASES_UNICODE"""
+
+    if not _ALIASES_UNICODE:
+        _ALIASES_UNICODE.update(get_emoji_unicode_dict('en'))
+        for emj, data in emoji.EMOJI_DATA.items():
+            if 'alias' in data and data['status'] <= emoji.STATUS['fully_qualified']:
+                for alias in data['alias']:
+                    _ALIASES_UNICODE[alias] = emj
+
+    return _ALIASES_UNICODE
+
+
 def all_language_packs() -> Generator[Tuple[str, Dict[str, Any]], None, None]:
     for lang_code in emoji.LANGUAGES:
-        yield (lang_code, emoji.unicode_codes.get_emoji_unicode_dict(lang_code))
+        yield (lang_code, get_emoji_unicode_dict(lang_code))
 
 
 def all_language_and_alias_packs(
 ) -> Generator[Tuple[str, Dict[str, Any]], None, None]:
-    yield ('alias', emoji.unicode_codes.get_aliases_unicode_dict())
+    yield ('alias', get_aliases_unicode_dict())
     yield from all_language_packs()