glitchlings 0.2.3__cp310-cp310-manylinux_2_28_x86_64.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- glitchlings/__init__.py +42 -0
- glitchlings/__main__.py +9 -0
- glitchlings/_zoo_rust.cpython-310-x86_64-linux-gnu.so +0 -0
- glitchlings/dlc/__init__.py +5 -0
- glitchlings/dlc/huggingface.py +96 -0
- glitchlings/dlc/prime.py +274 -0
- glitchlings/main.py +218 -0
- glitchlings/util/__init__.py +181 -0
- glitchlings/zoo/__init__.py +134 -0
- glitchlings/zoo/_ocr_confusions.py +34 -0
- glitchlings/zoo/_rate.py +21 -0
- glitchlings/zoo/core.py +405 -0
- glitchlings/zoo/jargoyle.py +336 -0
- glitchlings/zoo/mim1c.py +108 -0
- glitchlings/zoo/ocr_confusions.tsv +30 -0
- glitchlings/zoo/redactyl.py +165 -0
- glitchlings/zoo/reduple.py +128 -0
- glitchlings/zoo/rushmore.py +136 -0
- glitchlings/zoo/scannequin.py +171 -0
- glitchlings/zoo/typogre.py +212 -0
- glitchlings-0.2.3.dist-info/METADATA +478 -0
- glitchlings-0.2.3.dist-info/RECORD +26 -0
- glitchlings-0.2.3.dist-info/WHEEL +5 -0
- glitchlings-0.2.3.dist-info/entry_points.txt +2 -0
- glitchlings-0.2.3.dist-info/licenses/LICENSE +201 -0
- glitchlings-0.2.3.dist-info/top_level.txt +1 -0
@@ -0,0 +1,478 @@
|
|
1
|
+
Metadata-Version: 2.4
|
2
|
+
Name: glitchlings
|
3
|
+
Version: 0.2.3
|
4
|
+
Summary: Monsters for your language games.
|
5
|
+
Author: osoleve
|
6
|
+
License: Apache License
|
7
|
+
Version 2.0, January 2004
|
8
|
+
http://www.apache.org/licenses/
|
9
|
+
|
10
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
11
|
+
|
12
|
+
1. Definitions.
|
13
|
+
|
14
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
15
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
16
|
+
|
17
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
18
|
+
the copyright owner that is granting the License.
|
19
|
+
|
20
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
21
|
+
other entities that control, are controlled by, or are under common
|
22
|
+
control with that entity. For the purposes of this definition,
|
23
|
+
"control" means (i) the power, direct or indirect, to cause the
|
24
|
+
direction or management of such entity, whether by contract or
|
25
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
26
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
27
|
+
|
28
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
29
|
+
exercising permissions granted by this License.
|
30
|
+
|
31
|
+
"Source" form shall mean the preferred form for making modifications,
|
32
|
+
including but not limited to software source code, documentation
|
33
|
+
source, and configuration files.
|
34
|
+
|
35
|
+
"Object" form shall mean any form resulting from mechanical
|
36
|
+
transformation or translation of a Source form, including but
|
37
|
+
not limited to compiled object code, generated documentation,
|
38
|
+
and conversions to other media types.
|
39
|
+
|
40
|
+
"Work" shall mean the work of authorship, whether in Source or
|
41
|
+
Object form, made available under the License, as indicated by a
|
42
|
+
copyright notice that is included in or attached to the work
|
43
|
+
(an example is provided in the Appendix below).
|
44
|
+
|
45
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
46
|
+
form, that is based on (or derived from) the Work and for which the
|
47
|
+
editorial revisions, annotations, elaborations, or other modifications
|
48
|
+
represent, as a whole, an original work of authorship. For the purposes
|
49
|
+
of this License, Derivative Works shall not include works that remain
|
50
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
51
|
+
the Work and Derivative Works thereof.
|
52
|
+
|
53
|
+
"Contribution" shall mean any work of authorship, including
|
54
|
+
the original version of the Work and any modifications or additions
|
55
|
+
to that Work or Derivative Works thereof, that is intentionally
|
56
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
57
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
58
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
59
|
+
means any form of electronic, verbal, or written communication sent
|
60
|
+
to the Licensor or its representatives, including but not limited to
|
61
|
+
communication on electronic mailing lists, source code control systems,
|
62
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
63
|
+
Licensor for the purpose of discussing and improving the Work, but
|
64
|
+
excluding communication that is conspicuously marked or otherwise
|
65
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
66
|
+
|
67
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
68
|
+
on behalf of whom a Contribution has been received by Licensor and
|
69
|
+
subsequently incorporated within the Work.
|
70
|
+
|
71
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
72
|
+
this License, each Contributor hereby grants to You a perpetual,
|
73
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
74
|
+
copyright license to reproduce, prepare Derivative Works of,
|
75
|
+
publicly display, publicly perform, sublicense, and distribute the
|
76
|
+
Work and such Derivative Works in Source or Object form.
|
77
|
+
|
78
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
79
|
+
this License, each Contributor hereby grants to You a perpetual,
|
80
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
81
|
+
(except as stated in this section) patent license to make, have made,
|
82
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
83
|
+
where such license applies only to those patent claims licensable
|
84
|
+
by such Contributor that are necessarily infringed by their
|
85
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
86
|
+
with the Work to which such Contribution(s) was submitted. If You
|
87
|
+
institute patent litigation against any entity (including a
|
88
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
89
|
+
or a Contribution incorporated within the Work constitutes direct
|
90
|
+
or contributory patent infringement, then any patent licenses
|
91
|
+
granted to You under this License for that Work shall terminate
|
92
|
+
as of the date such litigation is filed.
|
93
|
+
|
94
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
95
|
+
Work or Derivative Works thereof in any medium, with or without
|
96
|
+
modifications, and in Source or Object form, provided that You
|
97
|
+
meet the following conditions:
|
98
|
+
|
99
|
+
(a) You must give any other recipients of the Work or
|
100
|
+
Derivative Works a copy of this License; and
|
101
|
+
|
102
|
+
(b) You must cause any modified files to carry prominent notices
|
103
|
+
stating that You changed the files; and
|
104
|
+
|
105
|
+
(c) You must retain, in the Source form of any Derivative Works
|
106
|
+
that You distribute, all copyright, patent, trademark, and
|
107
|
+
attribution notices from the Source form of the Work,
|
108
|
+
excluding those notices that do not pertain to any part of
|
109
|
+
the Derivative Works; and
|
110
|
+
|
111
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
112
|
+
distribution, then any Derivative Works that You distribute must
|
113
|
+
include a readable copy of the attribution notices contained
|
114
|
+
within such NOTICE file, excluding those notices that do not
|
115
|
+
pertain to any part of the Derivative Works, in at least one
|
116
|
+
of the following places: within a NOTICE text file distributed
|
117
|
+
as part of the Derivative Works; within the Source form or
|
118
|
+
documentation, if provided along with the Derivative Works; or,
|
119
|
+
within a display generated by the Derivative Works, if and
|
120
|
+
wherever such third-party notices normally appear. The contents
|
121
|
+
of the NOTICE file are for informational purposes only and
|
122
|
+
do not modify the License. You may add Your own attribution
|
123
|
+
notices within Derivative Works that You distribute, alongside
|
124
|
+
or as an addendum to the NOTICE text from the Work, provided
|
125
|
+
that such additional attribution notices cannot be construed
|
126
|
+
as modifying the License.
|
127
|
+
|
128
|
+
You may add Your own copyright statement to Your modifications and
|
129
|
+
may provide additional or different license terms and conditions
|
130
|
+
for use, reproduction, or distribution of Your modifications, or
|
131
|
+
for any such Derivative Works as a whole, provided Your use,
|
132
|
+
reproduction, and distribution of the Work otherwise complies with
|
133
|
+
the conditions stated in this License.
|
134
|
+
|
135
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
136
|
+
any Contribution intentionally submitted for inclusion in the Work
|
137
|
+
by You to the Licensor shall be under the terms and conditions of
|
138
|
+
this License, without any additional terms or conditions.
|
139
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
140
|
+
the terms of any separate license agreement you may have executed
|
141
|
+
with Licensor regarding such Contributions.
|
142
|
+
|
143
|
+
6. Trademarks. This License does not grant permission to use the trade
|
144
|
+
names, trademarks, service marks, or product names of the Licensor,
|
145
|
+
except as required for reasonable and customary use in describing the
|
146
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
147
|
+
|
148
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
149
|
+
agreed to in writing, Licensor provides the Work (and each
|
150
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
151
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
152
|
+
implied, including, without limitation, any warranties or conditions
|
153
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
154
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
155
|
+
appropriateness of using or redistributing the Work and assume any
|
156
|
+
risks associated with Your exercise of permissions under this License.
|
157
|
+
|
158
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
159
|
+
whether in tort (including negligence), contract, or otherwise,
|
160
|
+
unless required by applicable law (such as deliberate and grossly
|
161
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
162
|
+
liable to You for damages, including any direct, indirect, special,
|
163
|
+
incidental, or consequential damages of any character arising as a
|
164
|
+
result of this License or out of the use or inability to use the
|
165
|
+
Work (including but not limited to damages for loss of goodwill,
|
166
|
+
work stoppage, computer failure or malfunction, or any and all
|
167
|
+
other commercial damages or losses), even if such Contributor
|
168
|
+
has been advised of the possibility of such damages.
|
169
|
+
|
170
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
171
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
172
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
173
|
+
or other liability obligations and/or rights consistent with this
|
174
|
+
License. However, in accepting such obligations, You may act only
|
175
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
176
|
+
of any other Contributor, and only if You agree to indemnify,
|
177
|
+
defend, and hold each Contributor harmless for any liability
|
178
|
+
incurred by, or claims asserted against, such Contributor by reason
|
179
|
+
of your accepting any such warranty or additional liability.
|
180
|
+
|
181
|
+
END OF TERMS AND CONDITIONS
|
182
|
+
|
183
|
+
APPENDIX: How to apply the Apache License to your work.
|
184
|
+
|
185
|
+
To apply the Apache License to your work, attach the following
|
186
|
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
187
|
+
replaced with your own identifying information. (Don't include
|
188
|
+
the brackets!) The text should be enclosed in the appropriate
|
189
|
+
comment syntax for the file format. We also recommend that a
|
190
|
+
file or class name and description of purpose be included on the
|
191
|
+
same "printed page" as the copyright notice for easier
|
192
|
+
identification within third-party archives.
|
193
|
+
|
194
|
+
Copyright 2025 osoleve
|
195
|
+
|
196
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
197
|
+
you may not use this file except in compliance with the License.
|
198
|
+
You may obtain a copy of the License at
|
199
|
+
|
200
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
201
|
+
|
202
|
+
Unless required by applicable law or agreed to in writing, software
|
203
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
204
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
205
|
+
See the License for the specific language governing permissions and
|
206
|
+
limitations under the License.
|
207
|
+
|
208
|
+
Project-URL: Homepage, https://github.com/osoleve/glitchlings
|
209
|
+
Project-URL: Repository, https://github.com/osoleve/glitchlings.git
|
210
|
+
Project-URL: Issues, https://github.com/osoleve/glitchlings/issues
|
211
|
+
Project-URL: Changelog, https://github.com/osoleve/glitchlings/releases
|
212
|
+
Keywords: nlp,text,adversarial augmentation,text augmentation,large language models,llms,data augmentation,confusables,typo,
|
213
|
+
Classifier: Development Status :: 3 - Alpha
|
214
|
+
Classifier: Intended Audience :: Developers
|
215
|
+
Classifier: Programming Language :: Python
|
216
|
+
Classifier: Programming Language :: Python :: 3
|
217
|
+
Classifier: Programming Language :: Python :: 3.10
|
218
|
+
Classifier: Programming Language :: Python :: 3.11
|
219
|
+
Classifier: Programming Language :: Python :: 3.12
|
220
|
+
Classifier: Programming Language :: Rust
|
221
|
+
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
|
222
|
+
Classifier: Topic :: Software Development :: Testing
|
223
|
+
Requires-Python: >=3.10
|
224
|
+
Description-Content-Type: text/markdown
|
225
|
+
License-File: LICENSE
|
226
|
+
Requires-Dist: confusable-homoglyphs>=3.3.1
|
227
|
+
Provides-Extra: hf
|
228
|
+
Requires-Dist: datasets>=4.0.0; extra == "hf"
|
229
|
+
Provides-Extra: wordnet
|
230
|
+
Requires-Dist: nltk>=3.9.1; extra == "wordnet"
|
231
|
+
Requires-Dist: numpy<=2.0,>=1.24; extra == "wordnet"
|
232
|
+
Provides-Extra: prime
|
233
|
+
Requires-Dist: verifiers>=0.1.3.post0; extra == "prime"
|
234
|
+
Requires-Dist: jellyfish>=1.2.0; extra == "prime"
|
235
|
+
Provides-Extra: dev
|
236
|
+
Requires-Dist: pytest>=8.0.0; extra == "dev"
|
237
|
+
Requires-Dist: hypothesis>=6.140.0; extra == "dev"
|
238
|
+
Requires-Dist: nltk>=3.9.1; extra == "dev"
|
239
|
+
Requires-Dist: numpy<=2.0,>=1.24; extra == "dev"
|
240
|
+
Dynamic: license-file
|
241
|
+
|
242
|
+
#
|
243
|
+
|
244
|
+
```plaintext
|
245
|
+
.─') _ .─') _
|
246
|
+
( OO) ) ( OO ) )
|
247
|
+
░██████ ░██ ░██ ░██ ░██ ░██ ░██
|
248
|
+
░██ ░██ ░██ ░██ ░██ ░██
|
249
|
+
░██ ░██ ░██░████████ ░███████ ░████████ ░██ ░██░████████ ░████████ ░███████
|
250
|
+
░██ █████ ░██ ░██ ░██ ░██('─.░██ ░██ ░██ ░██ ░██░██ ░██ ░██.─')░██ ░██
|
251
|
+
░██ ██ ░██ ░██ ░██ ░██( OO ) ╱░██ ░██ ░██ ░██░██ ░██ ░██(OO)░██ ░███████
|
252
|
+
░██ ░███ ░██ ░██ ░██ ░██ ░██ ░██ ░██ ░██ ░██░██ ░██ ░██ o░███ ░██
|
253
|
+
░█████░█ ░██ ░██ ░████ ░███████ ░██ ░██ ░██ ░██░██ ░██ ░█████░██ ░███████
|
254
|
+
░██
|
255
|
+
░███████
|
256
|
+
|
257
|
+
Every language game breeds monsters.
|
258
|
+
```
|
259
|
+
|
260
|
+
`Glitchlings` are **utilities for corrupting the text inputs to your language models in deterministic, _linguistically principled_** ways.
|
261
|
+
Each embodies a different way that documents can be compromised in the wild.
|
262
|
+
|
263
|
+
If reinforcement learning environments are games, then `Glitchling`s are enemies to breathe new life into old challenges.
|
264
|
+
|
265
|
+
They do this by breaking surface patterns in the input while keeping the target output intact.
|
266
|
+
|
267
|
+
Some `Glitchling`s are petty nuisances. Some `Glitchling`s are eldritch horrors.
|
268
|
+
Together, they create truly nightmarish scenarios for your language models.
|
269
|
+
|
270
|
+
After all, what good is general intelligence if it can't handle a little chaos?
|
271
|
+
|
272
|
+
-_The Curator_
|
273
|
+
|
274
|
+
## Quickstart
|
275
|
+
|
276
|
+
```python
|
277
|
+
pip install -U glitchlings
|
278
|
+
```
|
279
|
+
|
280
|
+
> Glitchlings requires Python 3.10 or newer.
|
281
|
+
|
282
|
+
```python
|
283
|
+
from glitchlings import Gaggle, SAMPLE_TEXT, Typogre, Mim1c, Reduple, Rushmore
|
284
|
+
|
285
|
+
gaggle = Gaggle([
|
286
|
+
Typogre(rate=0.03),
|
287
|
+
Mim1c(rate=0.02),
|
288
|
+
Reduple(seed=404),
|
289
|
+
Rushmore(rate=0.02),
|
290
|
+
])
|
291
|
+
|
292
|
+
print(gaggle(SAMPLE_TEXT))
|
293
|
+
```
|
294
|
+
|
295
|
+
> Onҽ mھrning, wһen Gregor Samƽa woke from trouble𝐝 𝑑reams, he found himself transformed in his bed into a horrible vermin٠ He l lay on his armour-like back, and if he lifted his head a little he could see his brown belly, slightlh domed and divided by arches ino stiff sections. The bedding was adly able to cover it and and seemed ready to slide off any moment. His many legxs, pitifully thin compared with the size of the the rest of him, waved about helplessly ashe looked looked.
|
296
|
+
|
297
|
+
Consult the [Glitchlings Usage Guide](docs/index.md)
|
298
|
+
for end-to-end instructions spanning the Python API, CLI, HuggingFace and Prime Intellect
|
299
|
+
integrations, and the feature-flagged Rust pipeline.
|
300
|
+
|
301
|
+
## Motivation
|
302
|
+
|
303
|
+
If your model performs well on a particular task, but not when `Glitchling`s are present, it's a sign that it hasn't actually generalized to the problem.
|
304
|
+
|
305
|
+
Conversely, training a model to perform well in the presence of the types of perturbations introduced by `Glitchling`s should help it generalize better.
|
306
|
+
|
307
|
+
## Your First Battle
|
308
|
+
|
309
|
+
Summon your chosen `Glitchling` (_or a few, if ya nasty_) and call it on your text or slot it into `Dataset.map(...)`, supplying a seed if desired.
|
310
|
+
Glitchlings are standard Python classes, so you can instantiate them with whatever parameters fit your scenario:
|
311
|
+
|
312
|
+
```python
|
313
|
+
from glitchlings import Gaggle, Typogre, Mim1c
|
314
|
+
|
315
|
+
custom_typogre = Typogre(rate=0.1)
|
316
|
+
selective_mimic = Mim1c(rate=0.05, classes=["LATIN", "GREEK"])
|
317
|
+
|
318
|
+
gaggle = Gaggle([custom_typogre, selective_mimic], seed=99)
|
319
|
+
print(gaggle("Summoned heroes do not fear the glitch."))
|
320
|
+
```
|
321
|
+
|
322
|
+
Calling a `Glitchling` on a `str` transparently calls `.corrupt(str, ...) -> str`.
|
323
|
+
This means that as long as your glitchlings get along logically, they play nicely with one another.
|
324
|
+
|
325
|
+
When summoned as or gathered into a `Gaggle`, the `Glitchling`s will automatically order themselves into attack waves, based on the scope of the change they make:
|
326
|
+
|
327
|
+
1. Document
|
328
|
+
2. Paragraph
|
329
|
+
3. Sentence
|
330
|
+
4. Word
|
331
|
+
5. Character
|
332
|
+
|
333
|
+
They're horrible little gremlins, but they're not _unreasonable_.
|
334
|
+
|
335
|
+
## Command-Line Interface (CLI)
|
336
|
+
|
337
|
+
Keyboard warriors can challenge them directly via the `glitchlings` command:
|
338
|
+
|
339
|
+
```bash
|
340
|
+
# Discover which glitchlings are currently on the loose.
|
341
|
+
glitchlings --list
|
342
|
+
|
343
|
+
# Run Typogre against the contents of a file and inspect the diff.
|
344
|
+
glitchlings -g typogre --file documents/report.txt --diff
|
345
|
+
|
346
|
+
# Configure glitchlings inline by passing keyword arguments.
|
347
|
+
glitchlings -g "Typogre(rate=0.05)" "Ghouls just wanna have fun"
|
348
|
+
|
349
|
+
# Pipe text straight into the CLI for an on-the-fly corruption.
|
350
|
+
echo "Beware LLM-written flavor-text" | glitchlings -g mim1c
|
351
|
+
```
|
352
|
+
|
353
|
+
Use `--help` for a complete breakdown of available options, including support for parameterised glitchlings via `-g "Name(arg=value, ...)"` to mirror the Python API.
|
354
|
+
|
355
|
+
## Development
|
356
|
+
|
357
|
+
Follow the [development setup guide](docs/development.md) for editable installs, automated tests, and tips on enabling the Rust pipeline while you hack on new glitchlings.
|
358
|
+
|
359
|
+
## Starter 'lings
|
360
|
+
|
361
|
+
For maintainability reasons, all `Glitchling` have consented to be given nicknames once they're in your care. See the [Monster Manual](MONSTER_MANUAL.md) for a complete bestiary.
|
362
|
+
|
363
|
+
### Typogre
|
364
|
+
|
365
|
+
_What a nice word, would be a shame if something happened to it._
|
366
|
+
|
367
|
+
> _**Fatfinger.**_ Typogre introduces character-level errors (duplicating, dropping, adding, or swapping) based on the layout of a keyboard (QWERTY by default, with Dvorak and Colemak variants built-in).
|
368
|
+
>
|
369
|
+
> Args
|
370
|
+
>
|
371
|
+
> - `rate (float)`: The maximum number of edits to make as a percentage of the length (default: 0.02, 2%).
|
372
|
+
> - `keyboard (str)`: Keyboard layout key-neighbor map to use (default: "CURATOR_QWERTY"; also accepts "QWERTY", "DVORAK", "COLEMAK", and "AZERTY").
|
373
|
+
> - `seed (int)`: The random seed for reproducibility (default: 151).
|
374
|
+
|
375
|
+
### Mim1c
|
376
|
+
|
377
|
+
_Wait, was that...?_
|
378
|
+
|
379
|
+
> _**Confusion.**_ Mim1c replaces non-space characters with Unicode Confusables, characters that are distinct but would not usually confuse a human reader.
|
380
|
+
>
|
381
|
+
> Args
|
382
|
+
>
|
383
|
+
> - `rate (float)`: The maximum proportion of characters to replace (default: 0.02, 2%).
|
384
|
+
> - `classes (list[str] | "all")`: Restrict replacements to these Unicode script classes (default: ["LATIN", "GREEK", "CYRILLIC"]).
|
385
|
+
> - `banned_characters (Collection[str])`: Characters that must never appear as replacements (default: none).
|
386
|
+
> - `seed (int)`: The random seed for reproducibility (default: 151).
|
387
|
+
|
388
|
+
### Scannequin
|
389
|
+
|
390
|
+
_How can a computer need reading glasses?_
|
391
|
+
|
392
|
+
> _**OCR Artifacts.**_ Scannequin mimics optical character recognition errors by swapping visually similar character sequences (like rn↔m, cl↔d, O↔0, l/I/1).
|
393
|
+
>
|
394
|
+
> Args
|
395
|
+
>
|
396
|
+
> - `rate (float)`: The maximum proportion of eligible confusion spans to replace (default: 0.02, 2%).
|
397
|
+
> - `seed (int)`: The random seed for reproducibility (default: 151).
|
398
|
+
|
399
|
+
### Jargoyle
|
400
|
+
|
401
|
+
_Uh oh. The worst person you know just bought a thesaurus._
|
402
|
+
|
403
|
+
> _**Sesquipedalianism.**_ Jargoyle, the insufferable `Glitchling`, replaces words from selected parts of speech with synonyms at random, without regard for connotational or denotational differences.
|
404
|
+
>
|
405
|
+
> Args
|
406
|
+
>
|
407
|
+
> - `rate (float)`: The maximum proportion of words to replace (default: 0.1, 10%).
|
408
|
+
> - `part_of_speech`: The WordNet part(s) of speech to target (default: nouns). Accepts `wn.NOUN`, `wn.VERB`, `wn.ADJ`, `wn.ADV`, any iterable of those tags, or the string `"any"` to include them all.
|
409
|
+
> - `seed (int)`: The random seed for reproducibility (default: 151).
|
410
|
+
|
411
|
+
### Reduple
|
412
|
+
|
413
|
+
_Did you say that or did I?_
|
414
|
+
|
415
|
+
> _**Broken Record.**_ Reduple stutters through text by randomly reduplicating words. Like a nervous speaker, it creates natural repetitions that test a model's ability to handle redundancy without losing the thread.
|
416
|
+
>
|
417
|
+
> Args
|
418
|
+
>
|
419
|
+
> - `rate (float)`: The maximum proportion of words to reduplicate (default: 0.05, 5%).
|
420
|
+
> - `seed (int)`: The random seed for reproducibility (default: 151).
|
421
|
+
|
422
|
+
### Rushmore
|
423
|
+
|
424
|
+
_I accidentally an entire word._
|
425
|
+
|
426
|
+
> _**Hasty Omission.**_ The evil (?) twin of `reduple`, Rushmore moves with such frantic speed that it causes words to simply vanish from existence as it passes.
|
427
|
+
>
|
428
|
+
> Args
|
429
|
+
>
|
430
|
+
> - `rate (float)`: The maximum proportion of words to delete (default: 0.01, 1%).
|
431
|
+
> - `seed (int)`: The random seed for reproducibility (default: 151).
|
432
|
+
|
433
|
+
### Redactyl
|
434
|
+
|
435
|
+
_Oops, that was my black highlighter._
|
436
|
+
|
437
|
+
> _**FOIA Reply.**_ Redactyl obscures random words in your document like an NSA analyst with a bad sense of humor.
|
438
|
+
>
|
439
|
+
> ### Args
|
440
|
+
>
|
441
|
+
> - `replacement_char (str)`: The character to use for redaction (default: █).
|
442
|
+
> - `rate (float)`: The maximum proportion of words to redact (default: 0.05, 5%).
|
443
|
+
> - `merge_adjacent (bool)`: Whether to redact the space between adjacent redacted words (default: False).
|
444
|
+
> - `seed (int)`: The random seed for reproducibility (default: 151).
|
445
|
+
|
446
|
+
## Field Report: Uncontained Specimens
|
447
|
+
|
448
|
+
### _Containment procedures pending_
|
449
|
+
|
450
|
+
- `ekkokin` substitutes words with homophones (phonetic equivalents).
|
451
|
+
- `nylingual` backtranslates portions of text.
|
452
|
+
- `glothopper` introduces code-switching effects, blending languages or dialects.
|
453
|
+
- `palimpsest` rewrites, but leaves accidental traces of the past.
|
454
|
+
- `vesuvius` is an apocryphal `Glitchling` with ties to _[Nosy, aren't we? -The Curator]_
|
455
|
+
|
456
|
+
## Apocrypha
|
457
|
+
|
458
|
+
Cave paintings and oral tradition contain many depictions of strange, otherworldly `Glitchling`s.
|
459
|
+
These _Apocryphal `Glitchling`_ are said to possess unique abilities or behaviors.
|
460
|
+
If you encounter one of these elusive beings, please document your findings and share them with _The Curator_.
|
461
|
+
|
462
|
+
### Ensuring Reproducible Corruption
|
463
|
+
|
464
|
+
Every `Glitchling` should own its own independent `random.Random` instance. That means:
|
465
|
+
|
466
|
+
- No `random.seed(...)` calls touch Python's global RNG.
|
467
|
+
- Supplying a `seed` when you construct a `Glitchling` (or when you `summon(...)`) makes its behavior reproducible.
|
468
|
+
- Re-running a `Gaggle` with the same master seed and the same input text (_and same external data!_) yields identical corruption output.
|
469
|
+
- Corruption functions are written to accept an `rng` parameter internally so that all randomness is centralized and testable.
|
470
|
+
|
471
|
+
#### At Wits' End?
|
472
|
+
|
473
|
+
If you're trying to add a new glitchling and can't seem to make it deterministic, here are some places to look for determinism-breaking code:
|
474
|
+
|
475
|
+
1. Search for any direct calls to `random.choice`, `random.shuffle`, or `set(...)` ordering without going through the provided `rng`.
|
476
|
+
2. Ensure you sort collections before shuffling or sampling.
|
477
|
+
3. Make sure indices are chosen from a stable reference (e.g., original text) when applying length‑changing edits.
|
478
|
+
4. Make sure there are enough sort keys to maintain stability.
|
@@ -0,0 +1,26 @@
|
|
1
|
+
glitchlings/__init__.py,sha256=yD0BaldUpcc_QlHVca1z1iwpOp8ne1H9YVQHc85d1So,580
|
2
|
+
glitchlings/__main__.py,sha256=EOiBgay0x6B9VlSDzSQvMuoq6bHJdSvFSgcAVGGKkd4,121
|
3
|
+
glitchlings/_zoo_rust.cpython-310-x86_64-linux-gnu.so,sha256=0DLVlG_hNesx7S3hunRmJeQ2Sc6QUg5dvv2RqX1bcRw,3125632
|
4
|
+
glitchlings/main.py,sha256=u6969Vl0n47e3S-ZlYZBj3HWVsjs-hvW6RpF9RYuXnc,5931
|
5
|
+
glitchlings/dlc/__init__.py,sha256=eTLEEWrVWPqniXHqee4W23H1rjElI1PQ_jcqWFe9D3g,141
|
6
|
+
glitchlings/dlc/huggingface.py,sha256=I1QWanWVxO02awgSpHDtgQEVF-9AQRLtsta2RCitWhE,2933
|
7
|
+
glitchlings/dlc/prime.py,sha256=v6wzkVxIsjTOAumn9cPfsmjuGf3RitCfUtk9eZzthyg,8698
|
8
|
+
glitchlings/util/__init__.py,sha256=7KiZ0gKMjocfd34cajneZhTqYb7Hkwi_PpjltPqvkNI,4498
|
9
|
+
glitchlings/zoo/__init__.py,sha256=bpQyCs-gEyv8RyQmBqssw-ozYLKz5yBIGODhiTGv-1U,4178
|
10
|
+
glitchlings/zoo/_ocr_confusions.py,sha256=MkCbwk9T24SO2pD3JNPajYCfpMMlm2vQ5_sJty5GoXE,1218
|
11
|
+
glitchlings/zoo/_rate.py,sha256=TMyfVFV7pLxSGVswPlOAtBvk25Bjtx5xXTtpb_utgik,527
|
12
|
+
glitchlings/zoo/core.py,sha256=Fdxx4uoRH1WOL5rH_FeTUuQSwmnagP8mGXALq6IrtGY,14007
|
13
|
+
glitchlings/zoo/jargoyle.py,sha256=T6vPWBxceIPE6gOQ7BaihaqALOJwzXuhfiZzvKa4S50,10666
|
14
|
+
glitchlings/zoo/mim1c.py,sha256=yAt1ngR3j2KXLbzc8LhrQlIWRO_KT5dFK1EE8QivMAQ,3429
|
15
|
+
glitchlings/zoo/ocr_confusions.tsv,sha256=KhtR7vJDTITpfTSGa-I7RHr6CK7LkGi2KjdhEWipI6o,183
|
16
|
+
glitchlings/zoo/redactyl.py,sha256=IvyT9d-KPRTJoblSRTSagdFDhN8Y_ITBw9aSlFfE-Yo,4669
|
17
|
+
glitchlings/zoo/reduple.py,sha256=5mNqdArs4raSEVH9tMLfhMl1s_uBDGxJ8h2DxM82vYw,3513
|
18
|
+
glitchlings/zoo/rushmore.py,sha256=ooFmTKfq32NMjyehs5-luBPD0g9sFVZ5GTLk5dpGOp4,3544
|
19
|
+
glitchlings/zoo/scannequin.py,sha256=Ps8nxysKjkJV408zaL1kjVjy4jliATDBpYcNHLWbNFg,4859
|
20
|
+
glitchlings/zoo/typogre.py,sha256=xD02ldcMIA07XsdSts2bUniOc-k_DqTf0PBMaXGjLZE,6009
|
21
|
+
glitchlings-0.2.3.dist-info/METADATA,sha256=kMHv-9UDIEQBwV2skbIDLyN40zVobChr2mZnWY_rSeU,26035
|
22
|
+
glitchlings-0.2.3.dist-info/WHEEL,sha256=yzF9ixp0XVYLhnovZSdud9vspTPdVe52BzwI7Tv3jTM,113
|
23
|
+
glitchlings-0.2.3.dist-info/entry_points.txt,sha256=kGOwuAsjFDLtztLisaXtOouq9wFVMOJg5FzaAkg-Hto,54
|
24
|
+
glitchlings-0.2.3.dist-info/top_level.txt,sha256=VHFNBrLjtDwPCYXbGKi6o17Eueedi81eNbR3hBOoST0,12
|
25
|
+
glitchlings-0.2.3.dist-info/RECORD,,
|
26
|
+
glitchlings-0.2.3.dist-info/licenses/LICENSE,sha256=YCvGip-LoaRyu6h0nPo71q6eHEkzUpsE11psDJOIRkw,11337
|