tokenizers 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/CHANGELOG.md +3 -0
- data/Cargo.lock +1891 -0
- data/Cargo.toml +14 -0
- data/LICENSE.txt +202 -0
- data/README.md +67 -0
- data/ext/tokenizers/extconf.rb +7 -0
- data/lib/tokenizers/char_bpe_tokenizer.rb +19 -0
- data/lib/tokenizers/version.rb +3 -0
- data/lib/tokenizers.rb +14 -0
- data/src/lib.rs +290 -0
- metadata +53 -0
data/Cargo.toml
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
[package]
|
2
|
+
name = "tokenizers-ruby"
|
3
|
+
version = "0.1.0"
|
4
|
+
authors = ["Andrew Kane <andrew@ankane.org>"]
|
5
|
+
edition = "2018"
|
6
|
+
|
7
|
+
[lib]
|
8
|
+
name = "tokenizers"
|
9
|
+
crate-type = ["cdylib"]
|
10
|
+
|
11
|
+
[dependencies]
|
12
|
+
lazy_static = "1"
|
13
|
+
rutie = "0.8.3"
|
14
|
+
tokenizers = "0.11"
|
data/LICENSE.txt
ADDED
@@ -0,0 +1,202 @@
|
|
1
|
+
|
2
|
+
Apache License
|
3
|
+
Version 2.0, January 2004
|
4
|
+
http://www.apache.org/licenses/
|
5
|
+
|
6
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
7
|
+
|
8
|
+
1. Definitions.
|
9
|
+
|
10
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
11
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
12
|
+
|
13
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
14
|
+
the copyright owner that is granting the License.
|
15
|
+
|
16
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
17
|
+
other entities that control, are controlled by, or are under common
|
18
|
+
control with that entity. For the purposes of this definition,
|
19
|
+
"control" means (i) the power, direct or indirect, to cause the
|
20
|
+
direction or management of such entity, whether by contract or
|
21
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
22
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
23
|
+
|
24
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
25
|
+
exercising permissions granted by this License.
|
26
|
+
|
27
|
+
"Source" form shall mean the preferred form for making modifications,
|
28
|
+
including but not limited to software source code, documentation
|
29
|
+
source, and configuration files.
|
30
|
+
|
31
|
+
"Object" form shall mean any form resulting from mechanical
|
32
|
+
transformation or translation of a Source form, including but
|
33
|
+
not limited to compiled object code, generated documentation,
|
34
|
+
and conversions to other media types.
|
35
|
+
|
36
|
+
"Work" shall mean the work of authorship, whether in Source or
|
37
|
+
Object form, made available under the License, as indicated by a
|
38
|
+
copyright notice that is included in or attached to the work
|
39
|
+
(an example is provided in the Appendix below).
|
40
|
+
|
41
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
42
|
+
form, that is based on (or derived from) the Work and for which the
|
43
|
+
editorial revisions, annotations, elaborations, or other modifications
|
44
|
+
represent, as a whole, an original work of authorship. For the purposes
|
45
|
+
of this License, Derivative Works shall not include works that remain
|
46
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
47
|
+
the Work and Derivative Works thereof.
|
48
|
+
|
49
|
+
"Contribution" shall mean any work of authorship, including
|
50
|
+
the original version of the Work and any modifications or additions
|
51
|
+
to that Work or Derivative Works thereof, that is intentionally
|
52
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
53
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
54
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
55
|
+
means any form of electronic, verbal, or written communication sent
|
56
|
+
to the Licensor or its representatives, including but not limited to
|
57
|
+
communication on electronic mailing lists, source code control systems,
|
58
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
59
|
+
Licensor for the purpose of discussing and improving the Work, but
|
60
|
+
excluding communication that is conspicuously marked or otherwise
|
61
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
62
|
+
|
63
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
64
|
+
on behalf of whom a Contribution has been received by Licensor and
|
65
|
+
subsequently incorporated within the Work.
|
66
|
+
|
67
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
68
|
+
this License, each Contributor hereby grants to You a perpetual,
|
69
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
70
|
+
copyright license to reproduce, prepare Derivative Works of,
|
71
|
+
publicly display, publicly perform, sublicense, and distribute the
|
72
|
+
Work and such Derivative Works in Source or Object form.
|
73
|
+
|
74
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
75
|
+
this License, each Contributor hereby grants to You a perpetual,
|
76
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
77
|
+
(except as stated in this section) patent license to make, have made,
|
78
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
79
|
+
where such license applies only to those patent claims licensable
|
80
|
+
by such Contributor that are necessarily infringed by their
|
81
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
82
|
+
with the Work to which such Contribution(s) was submitted. If You
|
83
|
+
institute patent litigation against any entity (including a
|
84
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
85
|
+
or a Contribution incorporated within the Work constitutes direct
|
86
|
+
or contributory patent infringement, then any patent licenses
|
87
|
+
granted to You under this License for that Work shall terminate
|
88
|
+
as of the date such litigation is filed.
|
89
|
+
|
90
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
91
|
+
Work or Derivative Works thereof in any medium, with or without
|
92
|
+
modifications, and in Source or Object form, provided that You
|
93
|
+
meet the following conditions:
|
94
|
+
|
95
|
+
(a) You must give any other recipients of the Work or
|
96
|
+
Derivative Works a copy of this License; and
|
97
|
+
|
98
|
+
(b) You must cause any modified files to carry prominent notices
|
99
|
+
stating that You changed the files; and
|
100
|
+
|
101
|
+
(c) You must retain, in the Source form of any Derivative Works
|
102
|
+
that You distribute, all copyright, patent, trademark, and
|
103
|
+
attribution notices from the Source form of the Work,
|
104
|
+
excluding those notices that do not pertain to any part of
|
105
|
+
the Derivative Works; and
|
106
|
+
|
107
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
108
|
+
distribution, then any Derivative Works that You distribute must
|
109
|
+
include a readable copy of the attribution notices contained
|
110
|
+
within such NOTICE file, excluding those notices that do not
|
111
|
+
pertain to any part of the Derivative Works, in at least one
|
112
|
+
of the following places: within a NOTICE text file distributed
|
113
|
+
as part of the Derivative Works; within the Source form or
|
114
|
+
documentation, if provided along with the Derivative Works; or,
|
115
|
+
within a display generated by the Derivative Works, if and
|
116
|
+
wherever such third-party notices normally appear. The contents
|
117
|
+
of the NOTICE file are for informational purposes only and
|
118
|
+
do not modify the License. You may add Your own attribution
|
119
|
+
notices within Derivative Works that You distribute, alongside
|
120
|
+
or as an addendum to the NOTICE text from the Work, provided
|
121
|
+
that such additional attribution notices cannot be construed
|
122
|
+
as modifying the License.
|
123
|
+
|
124
|
+
You may add Your own copyright statement to Your modifications and
|
125
|
+
may provide additional or different license terms and conditions
|
126
|
+
for use, reproduction, or distribution of Your modifications, or
|
127
|
+
for any such Derivative Works as a whole, provided Your use,
|
128
|
+
reproduction, and distribution of the Work otherwise complies with
|
129
|
+
the conditions stated in this License.
|
130
|
+
|
131
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
132
|
+
any Contribution intentionally submitted for inclusion in the Work
|
133
|
+
by You to the Licensor shall be under the terms and conditions of
|
134
|
+
this License, without any additional terms or conditions.
|
135
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
136
|
+
the terms of any separate license agreement you may have executed
|
137
|
+
with Licensor regarding such Contributions.
|
138
|
+
|
139
|
+
6. Trademarks. This License does not grant permission to use the trade
|
140
|
+
names, trademarks, service marks, or product names of the Licensor,
|
141
|
+
except as required for reasonable and customary use in describing the
|
142
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
143
|
+
|
144
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
145
|
+
agreed to in writing, Licensor provides the Work (and each
|
146
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
147
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
148
|
+
implied, including, without limitation, any warranties or conditions
|
149
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
150
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
151
|
+
appropriateness of using or redistributing the Work and assume any
|
152
|
+
risks associated with Your exercise of permissions under this License.
|
153
|
+
|
154
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
155
|
+
whether in tort (including negligence), contract, or otherwise,
|
156
|
+
unless required by applicable law (such as deliberate and grossly
|
157
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
158
|
+
liable to You for damages, including any direct, indirect, special,
|
159
|
+
incidental, or consequential damages of any character arising as a
|
160
|
+
result of this License or out of the use or inability to use the
|
161
|
+
Work (including but not limited to damages for loss of goodwill,
|
162
|
+
work stoppage, computer failure or malfunction, or any and all
|
163
|
+
other commercial damages or losses), even if such Contributor
|
164
|
+
has been advised of the possibility of such damages.
|
165
|
+
|
166
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
167
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
168
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
169
|
+
or other liability obligations and/or rights consistent with this
|
170
|
+
License. However, in accepting such obligations, You may act only
|
171
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
172
|
+
of any other Contributor, and only if You agree to indemnify,
|
173
|
+
defend, and hold each Contributor harmless for any liability
|
174
|
+
incurred by, or claims asserted against, such Contributor by reason
|
175
|
+
of your accepting any such warranty or additional liability.
|
176
|
+
|
177
|
+
END OF TERMS AND CONDITIONS
|
178
|
+
|
179
|
+
APPENDIX: How to apply the Apache License to your work.
|
180
|
+
|
181
|
+
To apply the Apache License to your work, attach the following
|
182
|
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
183
|
+
replaced with your own identifying information. (Don't include
|
184
|
+
the brackets!) The text should be enclosed in the appropriate
|
185
|
+
comment syntax for the file format. We also recommend that a
|
186
|
+
file or class name and description of purpose be included on the
|
187
|
+
same "printed page" as the copyright notice for easier
|
188
|
+
identification within third-party archives.
|
189
|
+
|
190
|
+
Copyright [yyyy] [name of copyright owner]
|
191
|
+
|
192
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
193
|
+
you may not use this file except in compliance with the License.
|
194
|
+
You may obtain a copy of the License at
|
195
|
+
|
196
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
197
|
+
|
198
|
+
Unless required by applicable law or agreed to in writing, software
|
199
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
200
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
201
|
+
See the License for the specific language governing permissions and
|
202
|
+
limitations under the License.
|
data/README.md
ADDED
@@ -0,0 +1,67 @@
|
|
1
|
+
# Tokenizers
|
2
|
+
|
3
|
+
:slightly_smiling_face: Fast state-of-the-art [tokenizers](https://github.com/huggingface/tokenizers) for Ruby
|
4
|
+
|
5
|
+
[![Build Status](https://github.com/ankane/tokenizers-ruby/workflows/build/badge.svg?branch=master)](https://github.com/ankane/tokenizers-ruby/actions)
|
6
|
+
|
7
|
+
## Installation
|
8
|
+
|
9
|
+
Add this line to your application’s Gemfile:
|
10
|
+
|
11
|
+
```ruby
|
12
|
+
gem "tokenizers"
|
13
|
+
```
|
14
|
+
|
15
|
+
Note: Rust is currently required for installation.
|
16
|
+
|
17
|
+
## Getting Started
|
18
|
+
|
19
|
+
Load a pretrained tokenizer
|
20
|
+
|
21
|
+
```ruby
|
22
|
+
tokenizer = Tokenizers.from_pretrained("bert-base-cased")
|
23
|
+
```
|
24
|
+
|
25
|
+
Encode
|
26
|
+
|
27
|
+
```ruby
|
28
|
+
encoded = tokenizer.encode("I can feel the magic, can you?")
|
29
|
+
encoded.ids
|
30
|
+
encoded.tokens
|
31
|
+
```
|
32
|
+
|
33
|
+
Decode
|
34
|
+
|
35
|
+
```ruby
|
36
|
+
tokenizer.decode(ids)
|
37
|
+
```
|
38
|
+
|
39
|
+
Load a tokenizer from files
|
40
|
+
|
41
|
+
```ruby
|
42
|
+
tokenizer = Tokenizers::CharBPETokenizer.new("vocab.json", "merges.txt")
|
43
|
+
```
|
44
|
+
|
45
|
+
## History
|
46
|
+
|
47
|
+
View the [changelog](https://github.com/ankane/tokenizers-ruby/blob/master/CHANGELOG.md)
|
48
|
+
|
49
|
+
## Contributing
|
50
|
+
|
51
|
+
Everyone is encouraged to help improve this project. Here are a few ways you can help:
|
52
|
+
|
53
|
+
- [Report bugs](https://github.com/ankane/tokenizers-ruby/issues)
|
54
|
+
- Fix bugs and [submit pull requests](https://github.com/ankane/tokenizers-ruby/pulls)
|
55
|
+
- Write, clarify, or fix documentation
|
56
|
+
- Suggest or add new features
|
57
|
+
|
58
|
+
To get started with development:
|
59
|
+
|
60
|
+
```sh
|
61
|
+
git clone https://github.com/ankane/tokenizers-ruby.git
|
62
|
+
cd tokenizers-ruby
|
63
|
+
bundle install
|
64
|
+
bundle exec ruby ext/tokenizers/extconf.rb && make
|
65
|
+
bundle exec rake download:files
|
66
|
+
bundle exec rake test
|
67
|
+
```
|
@@ -0,0 +1,19 @@
|
|
1
|
+
module Tokenizers
|
2
|
+
class CharBPETokenizer
|
3
|
+
def initialize(vocab, merges)
|
4
|
+
@tokenizer = Tokenizer.new(BPE.new(vocab, merges))
|
5
|
+
@tokenizer.add_special_tokens(["<unk>"])
|
6
|
+
@tokenizer.normalizer = BertNormalizer.new
|
7
|
+
@tokenizer.pre_tokenizer = BertPreTokenizer.new
|
8
|
+
@tokenizer.decoder = BPEDecoder.new
|
9
|
+
end
|
10
|
+
|
11
|
+
def encode(text)
|
12
|
+
@tokenizer.encode(text)
|
13
|
+
end
|
14
|
+
|
15
|
+
def decode(ids)
|
16
|
+
@tokenizer.decode(ids)
|
17
|
+
end
|
18
|
+
end
|
19
|
+
end
|
data/lib/tokenizers.rb
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
# extlib
|
2
|
+
require "tokenizers/ext"
|
3
|
+
|
4
|
+
# modules
|
5
|
+
require "tokenizers/char_bpe_tokenizer"
|
6
|
+
require "tokenizers/version"
|
7
|
+
|
8
|
+
module Tokenizers
|
9
|
+
class Error < StandardError; end
|
10
|
+
|
11
|
+
def self.from_pretrained(identifier, revision: "main", auth_token: nil)
|
12
|
+
_from_pretrained(identifier, revision, auth_token)
|
13
|
+
end
|
14
|
+
end
|
data/src/lib.rs
ADDED
@@ -0,0 +1,290 @@
|
|
1
|
+
#[macro_use]
|
2
|
+
extern crate rutie;
|
3
|
+
|
4
|
+
use rutie::{AnyException, AnyObject, Array, Integer, Module, Object, RString, VerifiedObject, VM};
|
5
|
+
use tokenizers::decoders::bpe::BPEDecoder;
|
6
|
+
use tokenizers::models::bpe::BPE;
|
7
|
+
use tokenizers::normalizers::BertNormalizer;
|
8
|
+
use tokenizers::pre_tokenizers::bert::BertPreTokenizer;
|
9
|
+
use tokenizers::tokenizer::Tokenizer;
|
10
|
+
use tokenizers::{decoders, AddedToken, Encoding};
|
11
|
+
|
12
|
+
pub const VERSION: &str = env!("CARGO_PKG_VERSION");
|
13
|
+
|
14
|
+
wrappable_struct!(Tokenizer, TokenizerWrapper, TOKENIZER_WRAPPER);
|
15
|
+
wrappable_struct!(BPE, BPEWrapper, BPE_WRAPPER);
|
16
|
+
wrappable_struct!(Encoding, EncodingWrapper, ENCODING_WRAPPER);
|
17
|
+
wrappable_struct!(BPEDecoder, BPEDecoderWrapper, BPE_DECODER_WRAPPER);
|
18
|
+
wrappable_struct!(BertPreTokenizer, BertPreTokenizerWrapper, BERT_PRE_TOKENIZER_WRAPPER);
|
19
|
+
wrappable_struct!(BertNormalizer, BertNormalizerWrapper, BERT_NORMALIZER_WRAPPER);
|
20
|
+
|
21
|
+
module!(rbTokenizers);
|
22
|
+
|
23
|
+
class!(rbBPE);
|
24
|
+
class!(rbTokenizer);
|
25
|
+
class!(rbEncoding);
|
26
|
+
class!(rbBPEDecoder);
|
27
|
+
class!(rbBertPreTokenizer);
|
28
|
+
class!(rbBertNormalizer);
|
29
|
+
|
30
|
+
fn unwrap_object<T>(res: Result<T, AnyException>) -> T {
|
31
|
+
res.map_err(VM::raise_ex).unwrap()
|
32
|
+
}
|
33
|
+
|
34
|
+
fn unwrap_optional<T>(res: Result<AnyObject, AnyException>) -> Option<T>
|
35
|
+
where
|
36
|
+
T: VerifiedObject,
|
37
|
+
{
|
38
|
+
let x = unwrap_object(res);
|
39
|
+
if x.is_nil() {
|
40
|
+
None
|
41
|
+
} else {
|
42
|
+
Some(unwrap_object(x.try_convert_to::<T>()))
|
43
|
+
}
|
44
|
+
}
|
45
|
+
|
46
|
+
fn handle_error<T>(res: Result<T, Box<dyn std::error::Error + Send + Sync>>) -> T {
|
47
|
+
match res {
|
48
|
+
Ok(x) => x,
|
49
|
+
Err(e) => {
|
50
|
+
VM::raise(
|
51
|
+
Module::from_existing("Tokenizers").get_nested_class("Error"),
|
52
|
+
&e.to_string(),
|
53
|
+
);
|
54
|
+
unreachable!()
|
55
|
+
}
|
56
|
+
}
|
57
|
+
}
|
58
|
+
|
59
|
+
methods!(
|
60
|
+
rbTokenizers,
|
61
|
+
_rtself,
|
62
|
+
|
63
|
+
fn tokenizers_from_pretrained(identifier: RString, revision: RString, auth_token: AnyObject) -> AnyObject {
|
64
|
+
let identifier = unwrap_object(identifier);
|
65
|
+
let revision = unwrap_object(revision);
|
66
|
+
let auth_token: Option<RString> = unwrap_optional(auth_token);
|
67
|
+
|
68
|
+
let params = tokenizers::FromPretrainedParameters {
|
69
|
+
revision: revision.to_string(),
|
70
|
+
auth_token: auth_token.map(|x| x.to_string()),
|
71
|
+
user_agent: [("bindings", "Ruby"), ("version", VERSION)]
|
72
|
+
.iter()
|
73
|
+
.map(|(k, v)| (k.to_string(), v.to_string()))
|
74
|
+
.collect(),
|
75
|
+
};
|
76
|
+
|
77
|
+
let tokenizer = handle_error(Tokenizer::from_pretrained(identifier.to_string(), Some(params)));
|
78
|
+
Module::from_existing("Tokenizers")
|
79
|
+
.get_nested_class("Tokenizer")
|
80
|
+
.wrap_data(tokenizer, &*TOKENIZER_WRAPPER)
|
81
|
+
}
|
82
|
+
);
|
83
|
+
|
84
|
+
methods!(
|
85
|
+
rbBPE,
|
86
|
+
_rtself,
|
87
|
+
|
88
|
+
fn bpe_new(vocab: RString, merges: RString) -> AnyObject {
|
89
|
+
let vocab = unwrap_object(vocab);
|
90
|
+
let merges = unwrap_object(merges);
|
91
|
+
|
92
|
+
let bpe = handle_error(BPE::from_file(&vocab.to_string(), &merges.to_string())
|
93
|
+
.unk_token("<unk>".into())
|
94
|
+
.end_of_word_suffix("</w>".into())
|
95
|
+
.build());
|
96
|
+
|
97
|
+
Module::from_existing("Tokenizers")
|
98
|
+
.get_nested_class("BPE")
|
99
|
+
.wrap_data(bpe, &*BPE_WRAPPER)
|
100
|
+
}
|
101
|
+
);
|
102
|
+
|
103
|
+
methods!(
|
104
|
+
rbTokenizer,
|
105
|
+
_rtself,
|
106
|
+
|
107
|
+
fn tokenizer_new(model: AnyObject) -> AnyObject {
|
108
|
+
let model = unwrap_object(model);
|
109
|
+
|
110
|
+
// TODO support any model
|
111
|
+
let model = model.get_data(&*BPE_WRAPPER).clone();
|
112
|
+
|
113
|
+
let mut tokenizer = Tokenizer::new(model);
|
114
|
+
|
115
|
+
Module::from_existing("Tokenizers")
|
116
|
+
.get_nested_class("Tokenizer")
|
117
|
+
.wrap_data(tokenizer, &*TOKENIZER_WRAPPER)
|
118
|
+
}
|
119
|
+
);
|
120
|
+
|
121
|
+
methods!(
|
122
|
+
rbTokenizer,
|
123
|
+
rtself,
|
124
|
+
|
125
|
+
fn tokenizer_add_special_tokens(tokens: Array) -> rbTokenizer {
|
126
|
+
let tokenizer = rtself.get_data_mut(&*TOKENIZER_WRAPPER);
|
127
|
+
let tokens = unwrap_object(tokens);
|
128
|
+
|
129
|
+
let mut vec = Vec::new();
|
130
|
+
for token in tokens.into_iter() {
|
131
|
+
vec.push(AddedToken::from(unwrap_object(token.try_convert_to::<RString>()).to_string(), true));
|
132
|
+
}
|
133
|
+
tokenizer.add_special_tokens(&vec);
|
134
|
+
rtself
|
135
|
+
}
|
136
|
+
|
137
|
+
fn tokenizer_encode(text: RString) -> AnyObject {
|
138
|
+
let tokenizer = rtself.get_data(&*TOKENIZER_WRAPPER);
|
139
|
+
let text = unwrap_object(text);
|
140
|
+
|
141
|
+
let encoding = handle_error(tokenizer.encode(text.to_string(), false));
|
142
|
+
Module::from_existing("Tokenizers")
|
143
|
+
.get_nested_class("Encoding")
|
144
|
+
.wrap_data(encoding, &*ENCODING_WRAPPER)
|
145
|
+
}
|
146
|
+
|
147
|
+
fn tokenizer_decode(ids: Array) -> RString {
|
148
|
+
let tokenizer = rtself.get_data(&*TOKENIZER_WRAPPER);
|
149
|
+
let ids = unwrap_object(ids);
|
150
|
+
|
151
|
+
let mut vec = Vec::new();
|
152
|
+
for item in ids.into_iter() {
|
153
|
+
vec.push(unwrap_object(item.try_convert_to::<Integer>()).into());
|
154
|
+
}
|
155
|
+
let s = handle_error(tokenizer.decode(vec, true));
|
156
|
+
RString::new_utf8(&s)
|
157
|
+
}
|
158
|
+
|
159
|
+
fn tokenizer_decoder_set(decoder: AnyObject) -> AnyObject {
|
160
|
+
let tokenizer = rtself.get_data_mut(&*TOKENIZER_WRAPPER);
|
161
|
+
let decoder = unwrap_object(decoder);
|
162
|
+
|
163
|
+
tokenizer.with_decoder(decoder.get_data(&*BPE_DECODER_WRAPPER).clone());
|
164
|
+
decoder
|
165
|
+
}
|
166
|
+
|
167
|
+
fn tokenizer_pre_tokenizer_set(pre_tokenizer: AnyObject) -> AnyObject {
|
168
|
+
let tokenizer = rtself.get_data_mut(&*TOKENIZER_WRAPPER);
|
169
|
+
let pre_tokenizer = unwrap_object(pre_tokenizer);
|
170
|
+
|
171
|
+
tokenizer.with_pre_tokenizer(*pre_tokenizer.get_data(&*BERT_PRE_TOKENIZER_WRAPPER));
|
172
|
+
pre_tokenizer
|
173
|
+
}
|
174
|
+
|
175
|
+
fn tokenizer_normalizer_set(normalizer: AnyObject) -> AnyObject {
|
176
|
+
let tokenizer = rtself.get_data_mut(&*TOKENIZER_WRAPPER);
|
177
|
+
let normalizer = unwrap_object(normalizer);
|
178
|
+
|
179
|
+
tokenizer.with_normalizer(*normalizer.get_data(&*BERT_NORMALIZER_WRAPPER));
|
180
|
+
normalizer
|
181
|
+
}
|
182
|
+
);
|
183
|
+
|
184
|
+
methods!(
|
185
|
+
rbEncoding,
|
186
|
+
rtself,
|
187
|
+
|
188
|
+
fn encoding_ids() -> Array {
|
189
|
+
let encoding = rtself.get_data(&*ENCODING_WRAPPER);
|
190
|
+
|
191
|
+
let mut array = Array::new();
|
192
|
+
for x in encoding.get_ids() {
|
193
|
+
array.push(Integer::from(*x));
|
194
|
+
}
|
195
|
+
array
|
196
|
+
}
|
197
|
+
|
198
|
+
fn encoding_tokens() -> Array {
|
199
|
+
let encoding = rtself.get_data(&*ENCODING_WRAPPER);
|
200
|
+
|
201
|
+
let mut array = Array::new();
|
202
|
+
for x in encoding.get_tokens() {
|
203
|
+
array.push(RString::new_utf8(x));
|
204
|
+
}
|
205
|
+
array
|
206
|
+
}
|
207
|
+
);
|
208
|
+
|
209
|
+
methods!(
|
210
|
+
rbBPEDecoder,
|
211
|
+
_rtself,
|
212
|
+
|
213
|
+
fn bpe_decoder_new() -> AnyObject {
|
214
|
+
let decoder = decoders::bpe::BPEDecoder::default();
|
215
|
+
Module::from_existing("Tokenizers")
|
216
|
+
.get_nested_class("BPEDecoder")
|
217
|
+
.wrap_data(decoder, &*BPE_DECODER_WRAPPER)
|
218
|
+
}
|
219
|
+
);
|
220
|
+
|
221
|
+
methods!(
|
222
|
+
rbBertPreTokenizer,
|
223
|
+
_rtself,
|
224
|
+
|
225
|
+
fn bert_pre_tokenizer_new() -> AnyObject {
|
226
|
+
let pre_tokenizer = BertPreTokenizer;
|
227
|
+
Module::from_existing("Tokenizers")
|
228
|
+
.get_nested_class("BertPreTokenizer")
|
229
|
+
.wrap_data(pre_tokenizer, &*BERT_PRE_TOKENIZER_WRAPPER)
|
230
|
+
}
|
231
|
+
);
|
232
|
+
|
233
|
+
methods!(
|
234
|
+
rbBertNormalizer,
|
235
|
+
_rtself,
|
236
|
+
|
237
|
+
fn bert_normalizer_new() -> AnyObject {
|
238
|
+
let normalizer = BertNormalizer::default();
|
239
|
+
Module::from_existing("Tokenizers")
|
240
|
+
.get_nested_class("BertNormalizer")
|
241
|
+
.wrap_data(normalizer, &*BERT_NORMALIZER_WRAPPER)
|
242
|
+
}
|
243
|
+
);
|
244
|
+
|
245
|
+
#[allow(non_snake_case)]
|
246
|
+
#[no_mangle]
|
247
|
+
pub extern "C" fn Init_ext() {
|
248
|
+
let mut m = Module::new("Tokenizers");
|
249
|
+
|
250
|
+
m.define(|klass| {
|
251
|
+
klass.def_self("_from_pretrained", tokenizers_from_pretrained);
|
252
|
+
klass.define_nested_class("BPE", None);
|
253
|
+
klass.define_nested_class("Tokenizer", None);
|
254
|
+
klass.define_nested_class("Encoding", None);
|
255
|
+
klass.define_nested_class("BPEDecoder", None);
|
256
|
+
klass.define_nested_class("BertPreTokenizer", None);
|
257
|
+
klass.define_nested_class("BertNormalizer", None);
|
258
|
+
});
|
259
|
+
|
260
|
+
m.get_nested_class("BPE").define(|klass| {
|
261
|
+
klass.def_self("new", bpe_new);
|
262
|
+
});
|
263
|
+
|
264
|
+
m.get_nested_class("Tokenizer").define(|klass| {
|
265
|
+
klass.def_self("new", tokenizer_new);
|
266
|
+
klass.def("add_special_tokens", tokenizer_add_special_tokens);
|
267
|
+
klass.def("encode", tokenizer_encode);
|
268
|
+
klass.def("decode", tokenizer_decode);
|
269
|
+
klass.def("decoder=", tokenizer_decoder_set);
|
270
|
+
klass.def("pre_tokenizer=", tokenizer_pre_tokenizer_set);
|
271
|
+
klass.def("normalizer=", tokenizer_normalizer_set);
|
272
|
+
});
|
273
|
+
|
274
|
+
m.get_nested_class("Encoding").define(|klass| {
|
275
|
+
klass.def("ids", encoding_ids);
|
276
|
+
klass.def("tokens", encoding_tokens);
|
277
|
+
});
|
278
|
+
|
279
|
+
m.get_nested_class("BPEDecoder").define(|klass| {
|
280
|
+
klass.def_self("new", bpe_decoder_new);
|
281
|
+
});
|
282
|
+
|
283
|
+
m.get_nested_class("BertPreTokenizer").define(|klass| {
|
284
|
+
klass.def_self("new", bert_pre_tokenizer_new);
|
285
|
+
});
|
286
|
+
|
287
|
+
m.get_nested_class("BertNormalizer").define(|klass| {
|
288
|
+
klass.def_self("new", bert_normalizer_new);
|
289
|
+
});
|
290
|
+
}
|
metadata
ADDED
@@ -0,0 +1,53 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: tokenizers
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Andrew Kane
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2022-03-19 00:00:00.000000000 Z
|
12
|
+
dependencies: []
|
13
|
+
description:
|
14
|
+
email: andrew@ankane.org
|
15
|
+
executables: []
|
16
|
+
extensions:
|
17
|
+
- ext/tokenizers/extconf.rb
|
18
|
+
extra_rdoc_files: []
|
19
|
+
files:
|
20
|
+
- CHANGELOG.md
|
21
|
+
- Cargo.lock
|
22
|
+
- Cargo.toml
|
23
|
+
- LICENSE.txt
|
24
|
+
- README.md
|
25
|
+
- ext/tokenizers/extconf.rb
|
26
|
+
- lib/tokenizers.rb
|
27
|
+
- lib/tokenizers/char_bpe_tokenizer.rb
|
28
|
+
- lib/tokenizers/version.rb
|
29
|
+
- src/lib.rs
|
30
|
+
homepage: https://github.com/ankane/tokenizers-ruby
|
31
|
+
licenses:
|
32
|
+
- Apache-2.0
|
33
|
+
metadata: {}
|
34
|
+
post_install_message:
|
35
|
+
rdoc_options: []
|
36
|
+
require_paths:
|
37
|
+
- lib
|
38
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
39
|
+
requirements:
|
40
|
+
- - ">="
|
41
|
+
- !ruby/object:Gem::Version
|
42
|
+
version: '2.7'
|
43
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ">="
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
requirements: []
|
49
|
+
rubygems_version: 3.3.7
|
50
|
+
signing_key:
|
51
|
+
specification_version: 4
|
52
|
+
summary: Fast state-of-the-art tokenizers for Ruby
|
53
|
+
test_files: []
|