1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
|
#!/usr/bin/env python3
import sys
import re
from unidecode import unidecode
from jinja2 import Template
class Emoji(object):
def __init__(self, code, shortname, unicodename):
self.code = ''.join(['\\U'+c.rjust(8, '0') for c in code.strip().split(' ')])
self.shortname = shortname
self.unicodename = unicodename
def generate_qml_list(**kwargs):
tmpl = Template('''
const QVector<Emoji> emoji::Provider::emoji = {
{%- for c in kwargs.items() %}
// {{ c[0].capitalize() }}
{%- for e in c[1] %}
Emoji{QStringLiteral(u"{{ e.code }}"), QStringLiteral(u"{{ e.shortname }}"), QStringLiteral(u"{{ e.unicodename }}"), emoji::Emoji::Category::{{ c[0].capitalize() }}},
{%- endfor %}
{%- endfor %}
};
''')
d = dict(kwargs=kwargs)
print(tmpl.render(d))
# FIXME: Stop this madness
def humanize_keypad(num):
match num:
case "0":
return "zero"
case "1":
return "one"
case "2":
return "two"
case "3":
return "three"
case "4":
return "four"
case "5":
return "five"
case "6":
return "six"
case "7":
return "seven"
case "8":
return "eight"
case "9":
return "nine"
case "10":
return "ten"
case "*":
return "asterisk"
case "#":
return "hash"
case _:
return None
if __name__ == '__main__':
if len(sys.argv) < 3:
print('usage: emoji_codegen.py /path/to/emoji-test.txt /path/to/shortcodes.txt')
sys.exit(1)
filename = sys.argv[1]
shortcodefilename = sys.argv[2]
people = []
nature = []
food = []
activity = []
travel = []
objects = []
symbols = []
flags = []
categories = {
'Smileys & Emotion': people,
'People & Body': people,
'Animals & Nature': nature,
'Food & Drink': food,
'Travel & Places': travel,
'Activities': activity,
'Objects': objects,
'Symbols': symbols,
'Flags': flags,
'Component': symbols
}
shortcodeDict = {}
# for my sanity - this strips newlines
for line in open(shortcodefilename, 'r', encoding="utf8"):
longname, shortname = line.strip().split(':')
shortcodeDict[longname] = shortname
current_category = ''
for line in open(filename, 'r', encoding="utf8"):
if line.startswith('# group:'):
current_category = line.split(':', 1)[1].strip()
if not line or line.startswith('#'):
continue
segments = re.split(r'\s+[#;] ', line.strip())
if len(segments) != 3:
continue
code, qualification, charAndName = segments
# skip unqualified versions of same unicode
if qualification != 'fully-qualified' and qualification != 'component' :
continue
char, name = re.match(r'^(\S+) E\d+\.\d+ (.*)$', charAndName).groups()
shortname = name
# discard skin tone variants for sanity
# __contains__ is so stupid i hate prototype languages
if name.__contains__("skin tone") and qualification != 'component':
continue
if qualification == 'component' and not name.__contains__("skin tone"):
continue
#TODO: Handle skintone modifiers in a sane way
if shortname in shortcodeDict:
shortname = shortcodeDict[shortname]
else:
shortname = shortname.lower()
if shortname.endswith(' (blood type)'):
shortname = shortname[:-13]
if shortname.endswith(': red hair'):
shortname = "red_haired_" + shortname[:-10]
if shortname.endswith(': curly hair'):
shortname = "curly_haired_" + shortname[:-12]
if shortname.endswith(': white hair'):
shortname = "white_haried_" + shortname[:-12]
if shortname.endswith(': bald'):
shortname = "bald_" + shortname[:-6]
if shortname.endswith(': beard'):
shortname = "bearded_" + shortname[:-7]
if shortname.endswith(' face'):
shortname = shortname[:-5]
if shortname.endswith(' button'):
shortname = shortname[:-7]
if shortname.endswith(' banknote'):
shortname = shortname[:-9]
keycapmtch = re.match(r'^keycap: (.+)$', shortname)
if keycapmtch:
keycapthing, = keycapmtch.groups()
type(keycapthing)
num_name = humanize_keypad(keycapthing)
if num_name:
shortname = num_name
else:
raise Exception("incomplete keycap " + keycapthing + ", fix ur code")
# FIXME: Is there a better way to do this?
matchobj = re.match(r'^flag: (.*)$', shortname)
if matchobj:
country, = matchobj.groups()
shortname = country + " flag"
shortname = shortname.replace("u.s.", "us")
shortname = shortname.replace("&", "and")
shortname = shortname.replace("-", "_")
shortname, = re.match(r'^_*(.+)_*$', shortname).groups()
shortname = re.sub(r'\W', '_', shortname)
shortname = re.sub(r'_{2,}', '_', shortname)
shortname = unidecode(shortname)
categories[current_category].append(Emoji(code, shortname, name))
# Use xclip to pipe the output to clipboard.
# e.g ./codegen.py emoji.json | xclip -sel clip
# alternatively - delete the var from src/emoji/Provider.cpp, and do ./codegen.py emojis shortcodes >> src/emoji/Provider.cpp
generate_qml_list(people=people, nature=nature, food=food, activity=activity, travel=travel, objects=objects, symbols=symbols, flags=flags)
|
