Created
January 1, 2024 15:05
-
-
Save dejurin/27da1526ab9ea5fe291084997483622f to your computer and use it in GitHub Desktop.
Parse emoji from https://unicode.org/Public/emoji/latest/emoji-test.txt
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
import os | |
import requests | |
import json | |
import re | |
from slugify import slugify | |
EMOJI_VERSION = '15.1' | |
def main(): | |
text = get_test_file(EMOJI_VERSION) | |
print("Format text to json...") | |
collected = parse_emoji_text(text) | |
print(f"Processed emojis: {len(collected['full'])}") | |
print("Write files: emoji.json, emoji-compact.json\n") | |
write_files(collected) | |
print(collected['comments']) | |
def get_test_file(ver): | |
url = f"https://unicode.org/Public/emoji/{ver}/emoji-test.txt" | |
print(f"Fetch emoji-test.txt (v{EMOJI_VERSION})", end="", flush=True) | |
response = requests.get(url) | |
response.raise_for_status() | |
text = response.text | |
print() | |
return text | |
def parse_emoji_text(text): | |
lines = text.strip().split('\n') | |
collected = {'comments': '', 'full': [], 'compact': []} | |
group = subgroup = None | |
for line in lines: | |
line = line.strip() | |
if line.startswith('# group: '): | |
print(f" Processing {line[9:]}...") | |
group = line[9:] | |
elif line.startswith('# subgroup: '): | |
subgroup = line[12:] | |
elif line.startswith('#'): | |
collected['comments'] += line + '\n' | |
else: | |
meta = parse_line(line) | |
if meta: | |
meta['category'] = f"{group} ({subgroup})" | |
meta['group'] = group | |
meta['subgroup'] = subgroup | |
collected['full'].append(meta) | |
else: | |
collected['comments'] = collected['comments'].strip() + '\n\n' | |
return collected | |
def parse_line(line): | |
data = line.strip().split(None, 2) | |
if len(data) != 3: | |
return None | |
codes, status, char_and_name = data | |
match = re.match(r'^(.*?)\s+(E\d+\.\d+)\s+(.*?)$', char_and_name) | |
if match: | |
char = match.group(1) | |
name = match.group(3) | |
slug = slugify(name) | |
else: | |
return None | |
return {'codes': codes, 'name': name, 'slug': slug} | |
def write_files(data): | |
with open(rel('../src/data/emoji.json'), 'w', encoding='utf8') as full_file: | |
json.dump(data['full'], full_file, ensure_ascii=False, indent=2) | |
def rel(*args): | |
return os.path.abspath(os.path.join(os.path.dirname(__file__), *args)) | |
if __name__ == "__main__": | |
main() | |
""" | |
[ | |
{ | |
"codes": "1F432", | |
"name": "dragon face", | |
"slug": "dragon-face", | |
"category": "Animals & Nature (animal-reptile)", | |
"group": "Animals & Nature", | |
"subgroup": "animal-reptile" | |
}, | |
... | |
] | |
""" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment