Remove accents in Emoji names (#20)

Co-authored-by: Eduardo Soares <[email protected]>

CHANGELOG.md

@@ -13,7 +13,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### Changed
 - Switch from `setuptools` to `poetry` ([#11])
 - Switch from Travis CI to Github Actions ([#13])
-- Rename `Emoji.emoji` property to `Emoji.metadata` (#16)
+- Rename `Emoji.emoji` property to `Emoji.metadata` ([#16])
+
+### Fixed
+- Remove accents in Emoji names instead of replacing characters by underscores ([#20])
 
 ### Removed
 - Drop support for Python 3.5 ([#10])
@@ -36,6 +39,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 [0.2.0]: https://github.com/maxbrunet/mmemoji/compare/v0.1.0...v0.2.0
 [0.1.0]: https://github.com/maxbrunet/mmemoji/releases/tag/v0.1.0
 
+[#20]: https://github.com/maxbrunet/mmemoji/issues/20
 [#16]: https://github.com/maxbrunet/mmemoji/issues/16
 [#13]: https://github.com/maxbrunet/mmemoji/issues/13
 [#12]: https://github.com/maxbrunet/mmemoji/issues/12

pyproject.toml

@@ -74,6 +74,7 @@ mattermostdriver = ">=6.1.2"
 requests = ""
 tablib = ""
 tabulate = ""
+Unidecode = ""
 
 [tool.poetry.dev-dependencies]
 black = "==21.9b0"

src/mmemoji/emoji.py

@@ -11,6 +11,7 @@
 from typing import IO, Any, Dict, List, cast
 
 from mattermostdriver.exceptions import ResourceNotFound
+from unidecode import unidecode
 
 from mmemoji.exceptions import EmojiAlreadyExists, EmojiNotFound
 
@@ -49,6 +50,8 @@ def sanitize_name(filepath: str) -> str:
         """
         # Extract filename without extension
         name = basename(filepath).split(".")[0]
+        # Transliterate Unicode to ASCII (remove accents)
+        name = unidecode(name)
         # Remove parentheses
         name = re.sub(r"[()[\]{}]", "", name)
         # Replace forbidden characters by underscores

tests/test_emoji.py

@@ -0,0 +1,21 @@
+from mmemoji import Emoji
+
+
+def test_emoji_sanitize_simple_name() -> None:
+    name = Emoji.sanitize_name("emoji_1")
+    assert name == "emoji_1"
+
+
+def test_emoji_sanitize_name_with_parentheses() -> None:
+    name = Emoji.sanitize_name("{[(parentheses)]}")
+    assert name == "parentheses"
+
+
+def test_emoji_sanitize_name_with_spaces() -> None:
+    name = Emoji.sanitize_name("spa a ace")
+    assert name == "spa_a_ace"
+
+
+def test_emoji_sanitize_name_with_accents() -> None:
+    name = Emoji.sanitize_name("àéêöhelloĐıł")
+    assert name == "aeeohelloDil"

tests/utils.py

@@ -23,6 +23,10 @@
         "path": "tests/emojis/parentheses (spaced).png",
         "sha256": "195645113194074832ac56af71de520f1e2e87e52e4c8268b675832b91bab003",  # noqa: E501
     },
+    "accentue": {
+        "path": "tests/emojis/accentué.png",
+        "sha256": "508c3f7dd47fdc0e879748cb0286e9de82d8945aab3a580c58a4a6682df6ab8f",  # noqa: E501
+    },
 }
 USERS = {
     "sysadmin": {