Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix #5 Encoding text that contains certain some emojis. #6

Merged
merged 2 commits into from
Jan 28, 2023
Merged

Fix #5 Encoding text that contains certain some emojis. #6

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e912482
this PR will fix the issue with encoding text that certain some emojis.
Gioni06 Jan 28, 2023
30cf136
fix typo
Gioni06 Jan 28, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion composer.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@
"source": "https://github.com/Gioni06/GPT3Tokenizer"
},
"scripts": {
"test": "vendor/bin/phpunit tests"
"test": "vendor/bin/phpunit -d memory_limit=-1 tests"
},
"authors": [
{
Expand Down
290 changes: 264 additions & 26 deletions src/Gpt3Tokenizer.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,7 @@ public function __construct(Gpt3TokenizerConfig $config)
private function cacheSet($key, $val): void
{
if ($this->apcuAvailable) {
/** @noinspection PhpComposerExtensionStubsInspection */
apcu_store($key, $val);
} else {
$this->cache[$key] = $val;
Expand All @@ -46,6 +47,7 @@ private function cacheSet($key, $val): void
private function cacheGet($key): mixed
{
if ($this->apcuAvailable) {
/** @noinspection PhpComposerExtensionStubsInspection */
return apcu_fetch($key);
} else {
return $this->cache[$key] ?? null;
Expand All @@ -55,6 +57,7 @@ private function cacheGet($key): mixed
private function cacheExists($key): array|bool
{
if ($this->apcuAvailable) {
/** @noinspection PhpComposerExtensionStubsInspection */
return apcu_exists($key);
} else {
return isset($this->cache[$key]);
Expand All @@ -63,32 +66,267 @@ private function cacheExists($key): array|bool

public static function bytes_to_unicode(): array
{
$bs = array_merge(range(mb_ord('!'), mb_ord('~') + 1), range(mb_ord('¡'), mb_ord('¬') + 1), range(mb_ord('®'), mb_ord('ÿ') + 1));

$cs = $bs;
$n = 0;
foreach (range(0, 2 ** 8 - 1) as $b) {
if (!in_array($b, $bs)) {
$bs[] = $b;
$cs[] = 2 ** 8 + $n;
$n = $n + 1;
}
}

$cs = array_map(function($x) {
return mb_chr($x);
}, $cs);

$result = array();
array_map(function($_, $i) use(&$result, $bs, $cs) {
$result[$bs[$i]] = $cs[$i];
}, $bs, array_keys($cs));

if (array_key_exists(256, $result)) {
unset($result[256]);
}
ksort($result);
return $result;
// Bytes-to-Unicode is a list of utf-8 byte and a corresponding unicode string.
// Using this static list is much faster than decoding the utf-8 everytime a character is encountered.
// Also, it produces the exact output as tokenizer from OpenAI uses. https://beta.openai.com/tokenizer
return [
0 => 'Ā',
1 => 'ā',
2 => 'Ă',
3 => 'ă',
4 => 'Ą',
5 => 'ą',
6 => 'Ć',
7 => 'ć',
8 => 'Ĉ',
9 => 'ĉ',
10 => 'Ċ',
11 => 'ċ',
12 => 'Č',
13 => 'č',
14 => 'Ď',
15 => 'ď',
16 => 'Đ',
17 => 'đ',
18 => 'Ē',
19 => 'ē',
20 => 'Ĕ',
21 => 'ĕ',
22 => 'Ė',
23 => 'ė',
24 => 'Ę',
25 => 'ę',
26 => 'Ě',
27 => 'ě',
28 => 'Ĝ',
29 => 'ĝ',
30 => 'Ğ',
31 => 'ğ',
32 => 'Ġ',
33 => '!',
34 => '"',
35 => '#',
36 => '$',
37 => '%',
38 => '&',
39 => '\'',
40 => '(',
41 => ')',
42 => '*',
43 => '+',
44 => ',',
45 => '-',
46 => '.',
47 => '/',
48 => '0',
49 => '1',
50 => '2',
51 => '3',
52 => '4',
53 => '5',
54 => '6',
55 => '7',
56 => '8',
57 => '9',
58 => ':',
59 => ';',
60 => '<',
61 => '=',
62 => '>',
63 => '?',
64 => '@',
65 => 'A',
66 => 'B',
67 => 'C',
68 => 'D',
69 => 'E',
70 => 'F',
71 => 'G',
72 => 'H',
73 => 'I',
74 => 'J',
75 => 'K',
76 => 'L',
77 => 'M',
78 => 'N',
79 => 'O',
80 => 'P',
81 => 'Q',
82 => 'R',
83 => 'S',
84 => 'T',
85 => 'U',
86 => 'V',
87 => 'W',
88 => 'X',
89 => 'Y',
90 => 'Z',
91 => '[',
92 => '\\',
93 => ']',
94 => '^',
95 => '_',
96 => '`',
97 => 'a',
98 => 'b',
99 => 'c',
100 => 'd',
101 => 'e',
102 => 'f',
103 => 'g',
104 => 'h',
105 => 'i',
106 => 'j',
107 => 'k',
108 => 'l',
109 => 'm',
110 => 'n',
111 => 'o',
112 => 'p',
113 => 'q',
114 => 'r',
115 => 's',
116 => 't',
117 => 'u',
118 => 'v',
119 => 'w',
120 => 'x',
121 => 'y',
122 => 'z',
123 => '{',
124 => '|',
125 => '}',
126 => '~',
127 => 'ġ',
128 => 'Ģ',
129 => 'ģ',
130 => 'Ĥ',
131 => 'ĥ',
132 => 'Ħ',
133 => 'ħ',
134 => 'Ĩ',
135 => 'ĩ',
136 => 'Ī',
137 => 'ī',
138 => 'Ĭ',
139 => 'ĭ',
140 => 'Į',
141 => 'į',
142 => 'İ',
143 => 'ı',
144 => 'IJ',
145 => 'ij',
146 => 'Ĵ',
147 => 'ĵ',
148 => 'Ķ',
149 => 'ķ',
150 => 'ĸ',
151 => 'Ĺ',
152 => 'ĺ',
153 => 'Ļ',
154 => 'ļ',
155 => 'Ľ',
156 => 'ľ',
157 => 'Ŀ',
158 => 'ŀ',
159 => 'Ł',
160 => 'ł',
161 => '¡',
162 => '¢',
163 => '£',
164 => '¤',
165 => '¥',
166 => '¦',
167 => '§',
168 => '¨',
169 => '©',
170 => 'ª',
171 => '«',
172 => '¬',
173 => 'Ń',
174 => '®',
175 => '¯',
176 => '°',
177 => '±',
178 => '²',
179 => '³',
180 => '´',
181 => 'µ',
182 => '¶',
183 => '·',
184 => '¸',
185 => '¹',
186 => 'º',
187 => '»',
188 => '¼',
189 => '½',
190 => '¾',
191 => '¿',
192 => 'À',
193 => 'Á',
194 => 'Â',
195 => 'Ã',
196 => 'Ä',
197 => 'Å',
198 => 'Æ',
199 => 'Ç',
200 => 'È',
201 => 'É',
202 => 'Ê',
203 => 'Ë',
204 => 'Ì',
205 => 'Í',
206 => 'Î',
207 => 'Ï',
208 => 'Ð',
209 => 'Ñ',
210 => 'Ò',
211 => 'Ó',
212 => 'Ô',
213 => 'Õ',
214 => 'Ö',
215 => '×',
216 => 'Ø',
217 => 'Ù',
218 => 'Ú',
219 => 'Û',
220 => 'Ü',
221 => 'Ý',
222 => 'Þ',
223 => 'ß',
224 => 'à',
225 => 'á',
226 => 'â',
227 => 'ã',
228 => 'ä',
229 => 'å',
230 => 'æ',
231 => 'ç',
232 => 'è',
233 => 'é',
234 => 'ê',
235 => 'ë',
236 => 'ì',
237 => 'í',
238 => 'î',
239 => 'ï',
240 => 'ð',
241 => 'ñ',
242 => 'ò',
243 => 'ó',
244 => 'ô',
245 => 'õ',
246 => 'ö',
247 => '÷',
248 => 'ø',
249 => 'ù',
250 => 'ú',
251 => 'û',
252 => 'ü',
253 => 'ý',
254 => 'þ',
255 => 'ÿ',
];
}

public static function encodeStr(string $str): array {
Expand Down
14 changes: 13 additions & 1 deletion tests/Gpt3TokenizerTest.php
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,5 @@
<?php
<?php /** @noinspection SpellCheckingInspection */

namespace Gioni06\Gpt3Tokenizer\Tests;

use Gioni06\Gpt3Tokenizer\Gpt3Tokenizer;
Expand All @@ -19,13 +20,15 @@ public function test_encodeStr_function(): void
{
$this->assertEquals([ '32', '119', '111', '114', '108', '100' ], Gpt3Tokenizer::encodeStr(" world"));
$this->assertEquals([ '32', '240', '159', '140', '141' ], Gpt3Tokenizer::encodeStr(" 🌍"));
$this->assertEquals([ '240', '159', '148', '173' ], Gpt3Tokenizer::encodeStr("🔭"));
}


public function test_decodeStr_function(): void
{
$this->assertEquals(" world", Gpt3Tokenizer::decodeStr([ '32', '119', '111', '114', '108', '100' ]));
$this->assertEquals(" 🌍", Gpt3Tokenizer::decodeStr([ '32', '240', '159', '140', '141' ]));
$this->assertEquals("🔭", Gpt3Tokenizer::decodeStr([ '240', '159', '148', '173' ]));
}

public function test_get_pairs_function()
Expand Down Expand Up @@ -58,6 +61,7 @@ public function test_bytes_to_unicode_function()
$this->assertEquals("d", Gpt3Tokenizer::bytes_to_unicode()[100]);
$this->assertEquals("È", Gpt3Tokenizer::bytes_to_unicode()[200]);
$this->assertEquals("ÿ", Gpt3Tokenizer::bytes_to_unicode()[255]);
$this->assertCount(256, Gpt3Tokenizer::bytes_to_unicode());
}

/*
Expand Down Expand Up @@ -138,4 +142,12 @@ public function test_config()
$this->assertStringEndsWith('vocab.json', $config->getConfig()['vocabPath']);
$this->assertFalse($config->getConfig()['useCache']);
}

public function test_regression_issue_5()
{
$config = new Gpt3TokenizerConfig();
$tokenizer = new Gpt3Tokenizer($config);
$tokens = $tokenizer->encode("🔭");
$this->assertEquals([8582, 242, 255], $tokens);
}
}