code-towel 1.0.0__py3-none-any.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.
- code_towel-1.0.0.dist-info/METADATA +722 -0
- code_towel-1.0.0.dist-info/RECORD +27 -0
- code_towel-1.0.0.dist-info/WHEEL +5 -0
- code_towel-1.0.0.dist-info/entry_points.txt +4 -0
- code_towel-1.0.0.dist-info/licenses/LICENSE +201 -0
- code_towel-1.0.0.dist-info/top_level.txt +1 -0
- towel/__init__.py +20 -0
- towel/cli.py +813 -0
- towel/unification/__init__.py +24 -0
- towel/unification/assignment_analyzer.py +403 -0
- towel/unification/ast_normalizer.py +223 -0
- towel/unification/ast_pretty_printer.py +133 -0
- towel/unification/binding_detector.py +381 -0
- towel/unification/block_signature.py +123 -0
- towel/unification/builtins.py +209 -0
- towel/unification/exceptions.py +113 -0
- towel/unification/extractor.py +884 -0
- towel/unification/models.py +190 -0
- towel/unification/nominal_unifier.py +375 -0
- towel/unification/orphan_detector.py +187 -0
- towel/unification/pipeline.py +524 -0
- towel/unification/project_layout.py +201 -0
- towel/unification/refactor_engine.py +3381 -0
- towel/unification/scope_analyzer.py +597 -0
- towel/unification/unifier.py +2128 -0
- towel/unification/visitor_utils.py +83 -0
- towel/unification/visitors.py +377 -0
|
@@ -0,0 +1,722 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: code-towel
|
|
3
|
+
Version: 1.0.0
|
|
4
|
+
Summary: A Python tool that DRYs your code - finds and refactors repeated code using unification-based analysis
|
|
5
|
+
Author: Eric Allen
|
|
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 [yyyy] [name of copyright owner]
|
|
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
|
+
Classifier: Development Status :: 5 - Production/Stable
|
|
209
|
+
Classifier: Intended Audience :: Developers
|
|
210
|
+
Classifier: License :: OSI Approved :: Apache Software License
|
|
211
|
+
Classifier: Programming Language :: Python :: 3
|
|
212
|
+
Classifier: Programming Language :: Python :: 3.9
|
|
213
|
+
Classifier: Programming Language :: Python :: 3.10
|
|
214
|
+
Classifier: Programming Language :: Python :: 3.11
|
|
215
|
+
Classifier: Programming Language :: Python :: 3.12
|
|
216
|
+
Classifier: Programming Language :: Python :: 3.13
|
|
217
|
+
Classifier: Topic :: Software Development :: Quality Assurance
|
|
218
|
+
Classifier: Topic :: Software Development :: Libraries :: Python Modules
|
|
219
|
+
Requires-Python: >=3.9
|
|
220
|
+
Description-Content-Type: text/markdown
|
|
221
|
+
License-File: LICENSE
|
|
222
|
+
Provides-Extra: dev
|
|
223
|
+
Requires-Dist: coverage>=7.0.0; extra == "dev"
|
|
224
|
+
Requires-Dist: black>=23.0.0; extra == "dev"
|
|
225
|
+
Requires-Dist: flake8>=6.0.0; extra == "dev"
|
|
226
|
+
Requires-Dist: mypy>=1.0.0; extra == "dev"
|
|
227
|
+
Requires-Dist: pre-commit>=3.0.0; extra == "dev"
|
|
228
|
+
Requires-Dist: pydocstyle>=6.0.0; extra == "dev"
|
|
229
|
+
Requires-Dist: tqdm>=4.66.0; extra == "dev"
|
|
230
|
+
Dynamic: license-file
|
|
231
|
+
|
|
232
|
+
# Towel
|
|
233
|
+
|
|
234
|
+
[](https://github.com/ericeallen/towel/actions/workflows/ci.yml)
|
|
235
|
+
[](https://codecov.io/gh/ericeallen/towel)
|
|
236
|
+
[](https://pypi.org/project/code-towel/)
|
|
237
|
+
|
|
238
|
+
**A Python tool that DRYs your code.**
|
|
239
|
+
|
|
240
|
+
Towel automatically detects and refactors violations of the DRY (Don't Repeat Yourself) principle in Python codebases using unification algorithms from automated theorem proving.
|
|
241
|
+
|
|
242
|
+
## Testing Status
|
|
243
|
+
|
|
244
|
+
- **Unit Tests**: 125/125 passing (100%)
|
|
245
|
+
- **Observational Equivalence**: 175/175 refactoring proposals pass automated behavioral equivalence testing
|
|
246
|
+
- **Test Coverage**: 18 example files with comprehensive edge cases
|
|
247
|
+
|
|
248
|
+
All refactorings are verified to behave identically to the original code through automated observational equivalence testing.
|
|
249
|
+
|
|
250
|
+
## Quick Start
|
|
251
|
+
|
|
252
|
+
The tool uses only Python stdlib with zero external dependencies.
|
|
253
|
+
|
|
254
|
+
### Using Just (Recommended)
|
|
255
|
+
|
|
256
|
+
The easiest way to use the tool is with [just](https://github.com/casey/just):
|
|
257
|
+
|
|
258
|
+
```bash
|
|
259
|
+
# Install just: brew install just (macOS) or cargo install just
|
|
260
|
+
|
|
261
|
+
# Preview refactoring opportunities (read-only)
|
|
262
|
+
just preview test_examples/
|
|
263
|
+
|
|
264
|
+
# Apply refactorings to a new directory
|
|
265
|
+
just dry test_examples/ cleaned_examples/
|
|
266
|
+
|
|
267
|
+
# Apply refactorings in-place (overwrites original)
|
|
268
|
+
just dry my_code/ my_code/
|
|
269
|
+
|
|
270
|
+
# Run tests
|
|
271
|
+
just test
|
|
272
|
+
|
|
273
|
+
# Check test coverage
|
|
274
|
+
just coverage-unification
|
|
275
|
+
|
|
276
|
+
# See all commands
|
|
277
|
+
just --list
|
|
278
|
+
```
|
|
279
|
+
|
|
280
|
+
### CLI Commands
|
|
281
|
+
|
|
282
|
+
After installation, Towel provides three main commands:
|
|
283
|
+
|
|
284
|
+
```bash
|
|
285
|
+
# Preview duplicates (read-only)
|
|
286
|
+
code-towel preview <file_or_directory>
|
|
287
|
+
|
|
288
|
+
# Apply refactorings
|
|
289
|
+
code-towel dry <input> <output>
|
|
290
|
+
|
|
291
|
+
# Rename extracted functions with LLM assistance
|
|
292
|
+
code-towel rename-helpers <directory>
|
|
293
|
+
```
|
|
294
|
+
|
|
295
|
+
### Direct Script Usage
|
|
296
|
+
|
|
297
|
+
You can also run the scripts directly without installation:
|
|
298
|
+
|
|
299
|
+
```bash
|
|
300
|
+
# Preview duplicates (read-only)
|
|
301
|
+
python3 scripts/preview <file_or_directory>
|
|
302
|
+
|
|
303
|
+
# Refactor code (writes to output location)
|
|
304
|
+
python3 scripts/dry <input> <output>
|
|
305
|
+
```
|
|
306
|
+
|
|
307
|
+
## Features
|
|
308
|
+
|
|
309
|
+
- **Zero External Dependencies**: Uses only Python standard library
|
|
310
|
+
- **Unification-Based Analysis**: Advanced algorithm from automated theorem proving
|
|
311
|
+
- **Hygienic Code Generation**: Generates functions with hygienically renamed parameters to avoid name conflicts. The generated parameter names like `__param_0` are intentionally generic and can be renamed to more meaningful names using an LLM coding assistant for better readability.
|
|
312
|
+
- **Referential Transparency**: Preserves referential transparency and maintains program semantics through careful scope analysis
|
|
313
|
+
- **Safe Refactoring**:
|
|
314
|
+
- Alpha-renaming for loop variables (treats `i` and `j` as equivalent)
|
|
315
|
+
- Return value propagation (detects returns anywhere in block)
|
|
316
|
+
- Orphan variable detection (prevents unsafe extractions)
|
|
317
|
+
- Builtin filtering (never parameterizes `len`, `print`, etc.)
|
|
318
|
+
- F-string handling (correct AST manipulation)
|
|
319
|
+
- **Smart Parameterization**:
|
|
320
|
+
- Constant parameterization (different numbers/strings become parameters)
|
|
321
|
+
- Structural comparison (only extracts truly similar code)
|
|
322
|
+
- Max parameter limits (prevents over-parameterization)
|
|
323
|
+
- **Class-Aware Method Extraction**:
|
|
324
|
+
- Promotes duplicate methods into the nearest shared base class when possible
|
|
325
|
+
- Preserves decorators (`@classmethod`, `@staticmethod`) and implicit binders (`self`/`cls`)
|
|
326
|
+
- Rewrites call sites across files to dispatch through the new helper correctly
|
|
327
|
+
- Falls back gracefully when no safe shared ancestor exists
|
|
328
|
+
- **Cross-File Support**: Automatically handles duplicates spanning multiple files
|
|
329
|
+
- **Comprehensive Testing**:
|
|
330
|
+
- 175/175 refactoring proposals pass observational equivalence testing
|
|
331
|
+
- 125 unit tests passing (100%)
|
|
332
|
+
- Automatic observational equivalence testing verifies refactored code behaves identically to original
|
|
333
|
+
- Tests 175 refactoring proposals across 18 example files automatically
|
|
334
|
+
- Intelligent test input generation based on AST analysis
|
|
335
|
+
- Recursive testing of returned functions (closures)
|
|
336
|
+
- See `tests/OBSERVATIONAL_EQUIVALENCE.md` for details
|
|
337
|
+
|
|
338
|
+
## Installation
|
|
339
|
+
|
|
340
|
+
### For Users
|
|
341
|
+
|
|
342
|
+
```bash
|
|
343
|
+
# Install from PyPI (zero external dependencies)
|
|
344
|
+
pip install code-towel
|
|
345
|
+
|
|
346
|
+
# Or install from source
|
|
347
|
+
git clone https://github.com/ericeallen/towel.git
|
|
348
|
+
cd towel
|
|
349
|
+
pip install -e .
|
|
350
|
+
```
|
|
351
|
+
|
|
352
|
+
### For Developers
|
|
353
|
+
|
|
354
|
+
```bash
|
|
355
|
+
# Create virtual environment
|
|
356
|
+
python3 -m venv venv
|
|
357
|
+
source venv/bin/activate
|
|
358
|
+
|
|
359
|
+
# Install with dev dependencies
|
|
360
|
+
pip install -e ".[dev]"
|
|
361
|
+
|
|
362
|
+
# Alternatively, install the specific tools you need
|
|
363
|
+
pip install black flake8 mypy coverage
|
|
364
|
+
```
|
|
365
|
+
|
|
366
|
+
## Usage
|
|
367
|
+
|
|
368
|
+
### Preview Mode (Read-Only)
|
|
369
|
+
|
|
370
|
+
Preview refactoring opportunities without modifying files:
|
|
371
|
+
|
|
372
|
+
```bash
|
|
373
|
+
# Preview a single file
|
|
374
|
+
python3 preview.py my_code.py
|
|
375
|
+
|
|
376
|
+
# Preview a directory
|
|
377
|
+
python3 preview.py src/
|
|
378
|
+
```
|
|
379
|
+
|
|
380
|
+
### Refactoring Mode
|
|
381
|
+
|
|
382
|
+
Apply refactorings to code:
|
|
383
|
+
|
|
384
|
+
```bash
|
|
385
|
+
# Refactor to a new location (safe - doesn't overwrite)
|
|
386
|
+
python3 dry.py src/ src_refactored/
|
|
387
|
+
|
|
388
|
+
# Refactor a single file
|
|
389
|
+
python3 dry.py my_code.py my_code_clean.py
|
|
390
|
+
|
|
391
|
+
# Refactor in-place (overwrites original)
|
|
392
|
+
python3 dry.py src/ src/
|
|
393
|
+
python3 dry.py src/ src/ --progress detail --max-iterations 0 # verbose unlimited
|
|
394
|
+
python3 dry.py src/ src/ --progress none --max-iterations 100 # quiet capped
|
|
395
|
+
```
|
|
396
|
+
|
|
397
|
+
### Examples
|
|
398
|
+
|
|
399
|
+
Preview duplicates in test examples:
|
|
400
|
+
|
|
401
|
+
```bash
|
|
402
|
+
just preview test_examples/
|
|
403
|
+
```
|
|
404
|
+
|
|
405
|
+
Refactor a project to a new location:
|
|
406
|
+
|
|
407
|
+
```bash
|
|
408
|
+
just dry my_project/ my_project_refactored/
|
|
409
|
+
```
|
|
410
|
+
|
|
411
|
+
Test the tool with coverage:
|
|
412
|
+
|
|
413
|
+
```bash
|
|
414
|
+
just coverage-unification
|
|
415
|
+
```
|
|
416
|
+
|
|
417
|
+
### Renaming Extracted Helpers with LLM Assistance
|
|
418
|
+
|
|
419
|
+
After running the DRY tool, extracted functions are named `__extracted_func_*` with generic parameter names like `__param_0`. Towel includes an interactive tool that uses LLM assistance to rename these into meaningful, human-readable names:
|
|
420
|
+
|
|
421
|
+
```bash
|
|
422
|
+
# Interactive mode: Generate LLM prompt and apply suggestions
|
|
423
|
+
code-towel rename-helpers src/
|
|
424
|
+
|
|
425
|
+
# List all extracted helpers
|
|
426
|
+
code-towel rename-helpers src/ --list
|
|
427
|
+
|
|
428
|
+
# Apply renamings from a JSON file
|
|
429
|
+
code-towel rename-helpers src/ --rename-file renames.json
|
|
430
|
+
|
|
431
|
+
# Dry run (preview only)
|
|
432
|
+
code-towel rename-helpers src/ --dry-run
|
|
433
|
+
|
|
434
|
+
# Limit to specific files or functions
|
|
435
|
+
code-towel rename-helpers src/ --file mymodule.py
|
|
436
|
+
code-towel rename-helpers src/ --function __extracted_func_7
|
|
437
|
+
```
|
|
438
|
+
|
|
439
|
+
#### How It Works
|
|
440
|
+
|
|
441
|
+
The `rename-helpers` command works in two modes:
|
|
442
|
+
|
|
443
|
+
**1. Interactive Mode (default):**
|
|
444
|
+
- Analyzes all `__extracted_func_*` functions in your code
|
|
445
|
+
- Generates a prompt showing each function's code
|
|
446
|
+
- You paste this prompt into Claude Code, ChatGPT, or any LLM
|
|
447
|
+
- The LLM suggests meaningful names based on what each function does
|
|
448
|
+
- You paste the LLM's JSON response back
|
|
449
|
+
- Towel automatically renames all references throughout your codebase
|
|
450
|
+
|
|
451
|
+
**2. File Mode (`--rename-file`):**
|
|
452
|
+
- Provide a JSON file mapping old names to new names
|
|
453
|
+
- Towel applies these renamings across your entire codebase
|
|
454
|
+
|
|
455
|
+
Example workflow:
|
|
456
|
+
```bash
|
|
457
|
+
# Run the refactoring tool
|
|
458
|
+
code-towel dry src/ src_cleaned/
|
|
459
|
+
|
|
460
|
+
# Use LLM to rename extracted functions
|
|
461
|
+
code-towel rename-helpers src_cleaned/
|
|
462
|
+
# (Follow the interactive prompts to get LLM suggestions)
|
|
463
|
+
```
|
|
464
|
+
|
|
465
|
+
The tool uses smart regex-based renaming to update all function definitions and calls throughout your project.
|
|
466
|
+
|
|
467
|
+
## How It Works
|
|
468
|
+
|
|
469
|
+
The tool uses **unification** from automated theorem proving to detect and parameterize duplicates:
|
|
470
|
+
|
|
471
|
+
1. **Parsing**: Parses Python files into ASTs using the `ast` module
|
|
472
|
+
2. **Block Extraction**: Extracts all contiguous code blocks from functions
|
|
473
|
+
3. **Unification**: Uses a nominal unification algorithm to find blocks that can be unified:
|
|
474
|
+
- Matches AST structure recursively
|
|
475
|
+
- Allows alpha-renaming of loop variables (`i` ≈ `j`)
|
|
476
|
+
- Parameterizes differing constants and expressions
|
|
477
|
+
- Respects Python builtin names and scoping rules
|
|
478
|
+
4. **Orphan Detection**: Validates that extraction won't create undefined variable references
|
|
479
|
+
5. **Function Extraction**: Generates hygienically-renamed extracted functions
|
|
480
|
+
6. **Replacement Generation**: Creates function calls with correct parameter order
|
|
481
|
+
7. **Cross-File Support**: Handles duplicates across multiple files with import generation
|
|
482
|
+
|
|
483
|
+
## Safety Guarantees
|
|
484
|
+
|
|
485
|
+
The tool ensures safe refactorings by:
|
|
486
|
+
|
|
487
|
+
- **Orphan Variable Detection**: Never extracts code that binds variables used later
|
|
488
|
+
- **Return Value Propagation**: Detects return statements anywhere in block
|
|
489
|
+
- **Alpha-Renaming**: Treats loop variables `i`, `j`, `k` as equivalent binding constructs
|
|
490
|
+
- **Builtin Filtering**: Never parameterizes Python builtins (`len`, `print`, `range`, etc.)
|
|
491
|
+
- **F-String Handling**: Correct AST manipulation for f-strings (never parameterizes literal parts)
|
|
492
|
+
- **Comprehension Scoping**: Respects that comprehension variables are local to the comprehension
|
|
493
|
+
- **Structural Similarity**: Only unifies blocks with >60% structural similarity
|
|
494
|
+
|
|
495
|
+
## Advanced Features
|
|
496
|
+
|
|
497
|
+
**Class-Aware Helper Promotion** – Duplicate instance, class, or static methods are automatically lifted into their nearest shared base class, even across different files:
|
|
498
|
+
|
|
499
|
+
- Builds an inheritance table while scanning the project
|
|
500
|
+
- Chooses the most specific shared ancestor for the extracted helper
|
|
501
|
+
- Preserves method semantics (decorators, implicit parameters, and call dispatch)
|
|
502
|
+
- Emits the helper in the ancestor class and rewrites original methods to dispatch through it, inserting imports only when needed
|
|
503
|
+
|
|
504
|
+
**Orphan Variable Detection** – Prevents unsafe extractions that would create undefined variables:
|
|
505
|
+
```python
|
|
506
|
+
# Rejects this unsafe extraction:
|
|
507
|
+
def compute():
|
|
508
|
+
x = 10
|
|
509
|
+
y = 20
|
|
510
|
+
total = x + y
|
|
511
|
+
return total # Would leave 'total' undefined if lines 1-3 extracted alone
|
|
512
|
+
```
|
|
513
|
+
|
|
514
|
+
**Return Value Propagation** – Detects returns anywhere in code blocks:
|
|
515
|
+
```python
|
|
516
|
+
# Correctly generates: return extracted_func()
|
|
517
|
+
if x > 100:
|
|
518
|
+
return y * 2 # Nested return automatically detected
|
|
519
|
+
```
|
|
520
|
+
|
|
521
|
+
**Alpha-Renaming for Loop Variables** - Treats `i`, `j`, `k` as equivalent binding variables:
|
|
522
|
+
```python
|
|
523
|
+
for i in range(10): # Unifies with
|
|
524
|
+
for j in range(10): # this block
|
|
525
|
+
```
|
|
526
|
+
|
|
527
|
+
### Progress & Iteration Feedback
|
|
528
|
+
|
|
529
|
+
The directory fixed-point refactoring loop supports progress modes via `--progress`:
|
|
530
|
+
|
|
531
|
+
| Mode | Description |
|
|
532
|
+
|---------|-------------|
|
|
533
|
+
| `tqdm` | Rich progress bar (applied count + queued proposals). |
|
|
534
|
+
| `auto` | Attempts `tqdm`; falls back to single-line textual bar. |
|
|
535
|
+
| `none` | Suppresses progress output (quiet / CI). |
|
|
536
|
+
| `detail`| Verbose: lists discovered proposals (first 25) and localized follow-ups. |
|
|
537
|
+
|
|
538
|
+
`refactor_directory_to_fixed_point` returns `(results_dict, termination_reason)` where `termination_reason` is `fixed_point` (no proposals remain) or `iteration_cap` (stopped due to `--max-iterations N`). Use `--max-iterations 0` (default) for unlimited iterations until a fixed point.
|
|
539
|
+
|
|
540
|
+
Example (detail mode):
|
|
541
|
+
|
|
542
|
+
```text
|
|
543
|
+
[towel] Analyzing 26 file(s)...
|
|
544
|
+
[towel] Discovered 128 proposal(s)
|
|
545
|
+
1. Extract common code from state_machine_pattern_v1 and state_machine_pattern_v2
|
|
546
|
+
2. Extract common code from deeply_nested_computation_v1 and deeply_nested_computation_v2
|
|
547
|
+
...
|
|
548
|
+
```
|
|
549
|
+
|
|
550
|
+
Localized follow-ups: after each applied proposal the engine re-analyzes only changed files and prepends new opportunities to the queue for faster chained extraction.
|
|
551
|
+
|
|
552
|
+
## Testing
|
|
553
|
+
|
|
554
|
+
### Observational Equivalence Testing
|
|
555
|
+
|
|
556
|
+
Towel includes **automatic observational equivalence testing** that verifies refactored code behaves identically to the original:
|
|
557
|
+
|
|
558
|
+
```bash
|
|
559
|
+
# Run observational equivalence tests
|
|
560
|
+
just test-observational
|
|
561
|
+
|
|
562
|
+
# Run comprehensive automatic tests on all 18 example files
|
|
563
|
+
python -m unittest tests.test_observational_equivalence.TestAutomaticObservationalEquivalence -v
|
|
564
|
+
```
|
|
565
|
+
|
|
566
|
+
**Features:**
|
|
567
|
+
- **175/175 proposals pass (100%)** across **18 example files**
|
|
568
|
+
- No manual test configuration needed - extracts function names from proposals
|
|
569
|
+
- Intelligent test input generation using AST analysis:
|
|
570
|
+
- Detects tuple unpacking: `for a, b in pairs:` → generates `[('a', 1), ('b', 2)]`
|
|
571
|
+
- Detects dictionary access: `data['key']` → generates `{'key': 'value'}`
|
|
572
|
+
- Uses type annotations and parameter name heuristics
|
|
573
|
+
- Recursive testing: When functions return functions (closures), tests the returned functions for behavioral equivalence
|
|
574
|
+
- **100% success rate** - all refactorings preserve program behavior
|
|
575
|
+
|
|
576
|
+
See `tests/OBSERVATIONAL_EQUIVALENCE.md` for complete documentation.
|
|
577
|
+
|
|
578
|
+
### Unit Tests
|
|
579
|
+
|
|
580
|
+
Run the comprehensive unit test suite:
|
|
581
|
+
|
|
582
|
+
```bash
|
|
583
|
+
# Run all 125 unit tests (100% passing)
|
|
584
|
+
just test
|
|
585
|
+
|
|
586
|
+
# Run with coverage
|
|
587
|
+
just coverage-unification
|
|
588
|
+
|
|
589
|
+
# Generate HTML coverage report
|
|
590
|
+
just coverage-html
|
|
591
|
+
|
|
592
|
+
# Test specific aspects
|
|
593
|
+
just test-bindings # Binding constructs (for loops, comprehensions)
|
|
594
|
+
just test-returns # Return value propagation
|
|
595
|
+
just test-fstrings # F-string handling
|
|
596
|
+
just test-orphans # Orphan variable detection
|
|
597
|
+
just test-engine # End-to-end refactoring
|
|
598
|
+
|
|
599
|
+
### Fast Smoke Suite
|
|
600
|
+
|
|
601
|
+
During inner-loop development you can run a curated fast subset (proposal generation, stability, and observational equivalence on representative examples) instead of the full suite:
|
|
602
|
+
|
|
603
|
+
```bash
|
|
604
|
+
just test-smoke
|
|
605
|
+
```
|
|
606
|
+
|
|
607
|
+
Use this for quick validation (< a few minutes). Run the full suite (`just test` or `just test-all`) before pushing or releasing.
|
|
608
|
+
```
|
|
609
|
+
|
|
610
|
+
## Project Structure
|
|
611
|
+
|
|
612
|
+
```
|
|
613
|
+
src/towel/ # Core package (towel for compatibility)
|
|
614
|
+
└── unification/ # Unification-based refactoring system
|
|
615
|
+
├── refactor_engine.py # Main refactoring engine
|
|
616
|
+
├── unifier.py # Nominal unification algorithm
|
|
617
|
+
├── extractor.py # Hygienic function extraction
|
|
618
|
+
├── scope_analyzer.py # Variable scope analysis
|
|
619
|
+
├── orphan_detector.py # Orphan variable detection
|
|
620
|
+
└── builtins.py # Python builtin filtering
|
|
621
|
+
|
|
622
|
+
scripts/
|
|
623
|
+
├── dry # Main refactoring tool
|
|
624
|
+
├── preview # Read-only preview tool
|
|
625
|
+
└── verify-examples # Verification tool
|
|
626
|
+
|
|
627
|
+
tests/ # 125 comprehensive unit tests
|
|
628
|
+
test_examples/ # 18 example files with duplicates
|
|
629
|
+
docs/ # Documentation
|
|
630
|
+
```
|
|
631
|
+
|
|
632
|
+
## Examples
|
|
633
|
+
|
|
634
|
+
The `test_examples/` directory contains examples with DRY violations:
|
|
635
|
+
|
|
636
|
+
- `example1_simple.py`: Simple repeated validation logic
|
|
637
|
+
- `example4_complex.py`: Complex data processing loops
|
|
638
|
+
- `bindings_for_loops.py`: Loop variable edge cases
|
|
639
|
+
- `bindings_comprehensions.py`: List/dict/set comprehensions
|
|
640
|
+
- `return_values.py`: Return value propagation scenarios
|
|
641
|
+
- `fstrings_constants.py`: F-string and constant handling
|
|
642
|
+
|
|
643
|
+
## Justfile Commands
|
|
644
|
+
|
|
645
|
+
Run `just --list` to see all commands, or `just help` for detailed help.
|
|
646
|
+
|
|
647
|
+
### Common Commands
|
|
648
|
+
|
|
649
|
+
```bash
|
|
650
|
+
# For users
|
|
651
|
+
just dry <input> <output> # Refactor code (writes to output)
|
|
652
|
+
just preview <target> # Preview duplicates (read-only)
|
|
653
|
+
just help # Show detailed help
|
|
654
|
+
|
|
655
|
+
# For developers
|
|
656
|
+
just test # Run all 97 unit tests
|
|
657
|
+
just coverage-unification # Check coverage (91%)
|
|
658
|
+
just coverage-html # Generate HTML coverage report
|
|
659
|
+
just check # Run all code quality checks (format, lint, typecheck)
|
|
660
|
+
just clean # Clean generated files
|
|
661
|
+
just reset-examples # Reset example files to original state
|
|
662
|
+
|
|
663
|
+
# Documentation
|
|
664
|
+
just docs # Show usage guide
|
|
665
|
+
just docs-cross-file # Show cross-file refactoring docs
|
|
666
|
+
just docs-directory # Show directory usage docs
|
|
667
|
+
```
|
|
668
|
+
|
|
669
|
+
### Examples
|
|
670
|
+
|
|
671
|
+
```bash
|
|
672
|
+
# Analyze test examples
|
|
673
|
+
just analyze test_examples
|
|
674
|
+
|
|
675
|
+
# Preview what would change in src/
|
|
676
|
+
just preview src/
|
|
677
|
+
|
|
678
|
+
# Run all tests
|
|
679
|
+
just test-all
|
|
680
|
+
|
|
681
|
+
# Apply refactoring to example3
|
|
682
|
+
just refactor-example3
|
|
683
|
+
```
|
|
684
|
+
|
|
685
|
+
## Python API - Unification-Based Approach
|
|
686
|
+
|
|
687
|
+
The tool uses a unification-based approach for principled refactoring:
|
|
688
|
+
|
|
689
|
+
```python
|
|
690
|
+
from towel.unification.refactor_engine import UnificationRefactorEngine
|
|
691
|
+
|
|
692
|
+
# Create engine
|
|
693
|
+
engine = UnificationRefactorEngine(
|
|
694
|
+
max_parameters=5, # Max parameters for extracted functions
|
|
695
|
+
min_lines=4 # Minimum lines for code blocks
|
|
696
|
+
)
|
|
697
|
+
|
|
698
|
+
# Analyze entire directory (finds cross-file duplicates)
|
|
699
|
+
proposals = engine.analyze_directory("src/")
|
|
700
|
+
|
|
701
|
+
# Apply refactorings
|
|
702
|
+
for proposal in proposals:
|
|
703
|
+
modified_files = engine.apply_refactoring_multi_file(proposal)
|
|
704
|
+
for file_path, content in modified_files.items():
|
|
705
|
+
with open(file_path, 'w') as f:
|
|
706
|
+
f.write(content)
|
|
707
|
+
```
|
|
708
|
+
|
|
709
|
+
See [docs/USAGE_GUIDE.md](docs/USAGE_GUIDE.md) for complete API documentation.
|
|
710
|
+
|
|
711
|
+
## Documentation
|
|
712
|
+
|
|
713
|
+
- **[docs/USAGE_GUIDE.md](docs/USAGE_GUIDE.md)** - Complete usage guide
|
|
714
|
+
- **[docs/CROSS_FILE_REFACTORING.md](docs/CROSS_FILE_REFACTORING.md)** - Cross-file refactoring details
|
|
715
|
+
- **[docs/README_DIRECTORY_USAGE.md](docs/README_DIRECTORY_USAGE.md)** - Directory analysis guide
|
|
716
|
+
- **[docs/UNIFICATION_IMPLEMENTATION.md](docs/UNIFICATION_IMPLEMENTATION.md)** - Implementation details
|
|
717
|
+
- **[docs/TROUBLESHOOTING.md](docs/TROUBLESHOOTING.md)** - Common issues and solutions
|
|
718
|
+
- **[docs/JUSTFILE_REFERENCE.md](docs/JUSTFILE_REFERENCE.md)** - Complete justfile command reference
|
|
719
|
+
|
|
720
|
+
## License
|
|
721
|
+
|
|
722
|
+
Apache 2.0
|