-
-
Notifications
You must be signed in to change notification settings - Fork 188
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Pull the emoji list from unicode.org (#612)
- Removing unused information (names and descriptions) from the Emoji class - Creating a Gradle task that generates a more efficient res/raw/emojis.txt file from the most recent Unicode standard - Saving recently used emoji preferences as emoji values rather than names - Migrating old user preferences to the new system
- Loading branch information
Showing
6 changed files
with
4,621 additions
and
3,860 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,38 @@ | ||
import urllib.request | ||
import os.path | ||
|
||
EMOJIS_PATH = 'res/raw/emojis.txt' | ||
EMOJI_TEST_PATH = 'emoji-test.txt' | ||
EMOJI_TEST_URL = 'https://unicode.org/Public/emoji/latest/emoji-test.txt' | ||
|
||
def rawEmojiFromCodes(codes): | ||
return ''.join([chr(int(c, 16)) for c in codes]) | ||
|
||
def getEmojiTestContents(): | ||
if os.path.exists(EMOJI_TEST_PATH): | ||
print(f'Using existing {EMOJI_TEST_PATH}') | ||
else: | ||
print(f'Downloading {EMOJI_TEST_URL}') | ||
urllib.request.urlretrieve(EMOJI_TEST_URL, EMOJI_TEST_PATH) | ||
return open(EMOJI_TEST_PATH, mode='r', encoding='UTF-8').read() | ||
|
||
|
||
emoji_list = [] | ||
group_indices = [] | ||
for line in getEmojiTestContents().splitlines(): | ||
if line.startswith('# group:'): | ||
if len(group_indices) == 0 or len(emoji_list) > group_indices[-1]: | ||
group_indices.append(len(emoji_list)) | ||
elif not line.startswith('#') and 'fully-qualified' in line: | ||
codes = line.split(';')[0].split() | ||
emoji_list.append(rawEmojiFromCodes(codes)) | ||
|
||
with open(EMOJIS_PATH, 'w', encoding='UTF-8') as emojis: | ||
for e in emoji_list: | ||
emojis.write(f'{e}\n') | ||
emojis.write('\n') | ||
|
||
emojis.write(' '.join([str(g) for g in group_indices])) | ||
emojis.write('\n') | ||
|
||
print(f'Parsed {len(emoji_list)} emojis in {len(group_indices)}') |
Oops, something went wrong.