wordformat 1.0.0__tar.gz

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.
Files changed (59) hide show
  1. wordformat-1.0.0/LICENSE +201 -0
  2. wordformat-1.0.0/PKG-INFO +166 -0
  3. wordformat-1.0.0/README.md +115 -0
  4. wordformat-1.0.0/pyproject.toml +139 -0
  5. wordformat-1.0.0/setup.cfg +4 -0
  6. wordformat-1.0.0/src/wordformat/__init__.py +11 -0
  7. wordformat-1.0.0/src/wordformat/agent/__init__.py +4 -0
  8. wordformat-1.0.0/src/wordformat/agent/message.py +79 -0
  9. wordformat-1.0.0/src/wordformat/agent/onnx_infer.py +261 -0
  10. wordformat-1.0.0/src/wordformat/api/__init__.py +269 -0
  11. wordformat-1.0.0/src/wordformat/base.py +85 -0
  12. wordformat-1.0.0/src/wordformat/cli.py +184 -0
  13. wordformat-1.0.0/src/wordformat/config/__init__.py +4 -0
  14. wordformat-1.0.0/src/wordformat/config/config.py +112 -0
  15. wordformat-1.0.0/src/wordformat/config/datamodel.py +288 -0
  16. wordformat-1.0.0/src/wordformat/data/model/id2label.json +17 -0
  17. wordformat-1.0.0/src/wordformat/data/model/label2id.json +17 -0
  18. wordformat-1.0.0/src/wordformat/data/model/tokenizer.json +21283 -0
  19. wordformat-1.0.0/src/wordformat/data/system_prompt.txt +41 -0
  20. wordformat-1.0.0/src/wordformat/log_config.py +83 -0
  21. wordformat-1.0.0/src/wordformat/rules/__init__.py +42 -0
  22. wordformat-1.0.0/src/wordformat/rules/abstract.py +288 -0
  23. wordformat-1.0.0/src/wordformat/rules/acknowledgement.py +114 -0
  24. wordformat-1.0.0/src/wordformat/rules/body.py +59 -0
  25. wordformat-1.0.0/src/wordformat/rules/caption.py +100 -0
  26. wordformat-1.0.0/src/wordformat/rules/heading.py +154 -0
  27. wordformat-1.0.0/src/wordformat/rules/keywords.py +266 -0
  28. wordformat-1.0.0/src/wordformat/rules/node.py +181 -0
  29. wordformat-1.0.0/src/wordformat/rules/references.py +100 -0
  30. wordformat-1.0.0/src/wordformat/set_style.py +177 -0
  31. wordformat-1.0.0/src/wordformat/set_tag.py +22 -0
  32. wordformat-1.0.0/src/wordformat/settings.py +33 -0
  33. wordformat-1.0.0/src/wordformat/style/__init__.py +4 -0
  34. wordformat-1.0.0/src/wordformat/style/check_format.py +530 -0
  35. wordformat-1.0.0/src/wordformat/style/get_some.py +443 -0
  36. wordformat-1.0.0/src/wordformat/style/set_some.py +527 -0
  37. wordformat-1.0.0/src/wordformat/style/style_enum.py +603 -0
  38. wordformat-1.0.0/src/wordformat/style/utils.py +140 -0
  39. wordformat-1.0.0/src/wordformat/tree.py +178 -0
  40. wordformat-1.0.0/src/wordformat/utils.py +128 -0
  41. wordformat-1.0.0/src/wordformat/word_structure/__init__.py +4 -0
  42. wordformat-1.0.0/src/wordformat/word_structure/document_builder.py +38 -0
  43. wordformat-1.0.0/src/wordformat/word_structure/node_factory.py +30 -0
  44. wordformat-1.0.0/src/wordformat/word_structure/settings.py +56 -0
  45. wordformat-1.0.0/src/wordformat/word_structure/tree_builder.py +77 -0
  46. wordformat-1.0.0/src/wordformat/word_structure/utils.py +62 -0
  47. wordformat-1.0.0/src/wordformat.egg-info/PKG-INFO +166 -0
  48. wordformat-1.0.0/src/wordformat.egg-info/SOURCES.txt +57 -0
  49. wordformat-1.0.0/src/wordformat.egg-info/dependency_links.txt +1 -0
  50. wordformat-1.0.0/src/wordformat.egg-info/entry_points.txt +3 -0
  51. wordformat-1.0.0/src/wordformat.egg-info/requires.txt +27 -0
  52. wordformat-1.0.0/src/wordformat.egg-info/top_level.txt +1 -0
  53. wordformat-1.0.0/tests/test_base.py +162 -0
  54. wordformat-1.0.0/tests/test_cli.py +230 -0
  55. wordformat-1.0.0/tests/test_node.py +226 -0
  56. wordformat-1.0.0/tests/test_set_style.py +332 -0
  57. wordformat-1.0.0/tests/test_set_tag.py +33 -0
  58. wordformat-1.0.0/tests/test_tree.py +162 -0
  59. wordformat-1.0.0/tests/test_utils.py +113 -0
@@ -0,0 +1,201 @@
1
+ Apache License
2
+ Version 2.0, January 2004
3
+ http://www.apache.org/licenses/
4
+
5
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6
+
7
+ 1. Definitions.
8
+
9
+ "License" shall mean the terms and conditions for use, reproduction,
10
+ and distribution as defined by Sections 1 through 9 of this document.
11
+
12
+ "Licensor" shall mean the copyright owner or entity authorized by
13
+ the copyright owner that is granting the License.
14
+
15
+ "Legal Entity" shall mean the union of the acting entity and all
16
+ other entities that control, are controlled by, or are under common
17
+ control with that entity. For the purposes of this definition,
18
+ "control" means (i) the power, direct or indirect, to cause the
19
+ direction or management of such entity, whether by contract or
20
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
21
+ outstanding shares, or (iii) beneficial ownership of such entity.
22
+
23
+ "You" (or "Your") shall mean an individual or Legal Entity
24
+ exercising permissions granted by this License.
25
+
26
+ "Source" form shall mean the preferred form for making modifications,
27
+ including but not limited to software source code, documentation
28
+ source, and configuration files.
29
+
30
+ "Object" form shall mean any form resulting from mechanical
31
+ transformation or translation of a Source form, including but
32
+ not limited to compiled object code, generated documentation,
33
+ and conversions to other media types.
34
+
35
+ "Work" shall mean the work of authorship, whether in Source or
36
+ Object form, made available under the License, as indicated by a
37
+ copyright notice that is included in or attached to the work
38
+ (an example is provided in the Appendix below).
39
+
40
+ "Derivative Works" shall mean any work, whether in Source or Object
41
+ form, that is based on (or derived from) the Work and for which the
42
+ editorial revisions, annotations, elaborations, or other modifications
43
+ represent, as a whole, an original work of authorship. For the purposes
44
+ of this License, Derivative Works shall not include works that remain
45
+ separable from, or merely link (or bind by name) to the interfaces of,
46
+ the Work and Derivative Works thereof.
47
+
48
+ "Contribution" shall mean any work of authorship, including
49
+ the original version of the Work and any modifications or additions
50
+ to that Work or Derivative Works thereof, that is intentionally
51
+ submitted to Licensor for inclusion in the Work by the copyright owner
52
+ or by an individual or Legal Entity authorized to submit on behalf of
53
+ the copyright owner. For the purposes of this definition, "submitted"
54
+ means any form of electronic, verbal, or written communication sent
55
+ to the Licensor or its representatives, including but not limited to
56
+ communication on electronic mailing lists, source code control systems,
57
+ and issue tracking systems that are managed by, or on behalf of, the
58
+ Licensor for the purpose of discussing and improving the Work, but
59
+ excluding communication that is conspicuously marked or otherwise
60
+ designated in writing by the copyright owner as "Not a Contribution."
61
+
62
+ "Contributor" shall mean Licensor and any individual or Legal Entity
63
+ on behalf of whom a Contribution has been received by Licensor and
64
+ subsequently incorporated within the Work.
65
+
66
+ 2. Grant of Copyright License. Subject to the terms and conditions of
67
+ this License, each Contributor hereby grants to You a perpetual,
68
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69
+ copyright license to reproduce, prepare Derivative Works of,
70
+ publicly display, publicly perform, sublicense, and distribute the
71
+ Work and such Derivative Works in Source or Object form.
72
+
73
+ 3. Grant of Patent License. Subject to the terms and conditions of
74
+ this License, each Contributor hereby grants to You a perpetual,
75
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76
+ (except as stated in this section) patent license to make, have made,
77
+ use, offer to sell, sell, import, and otherwise transfer the Work,
78
+ where such license applies only to those patent claims licensable
79
+ by such Contributor that are necessarily infringed by their
80
+ Contribution(s) alone or by combination of their Contribution(s)
81
+ with the Work to which such Contribution(s) was submitted. If You
82
+ institute patent litigation against any entity (including a
83
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
84
+ or a Contribution incorporated within the Work constitutes direct
85
+ or contributory patent infringement, then any patent licenses
86
+ granted to You under this License for that Work shall terminate
87
+ as of the date such litigation is filed.
88
+
89
+ 4. Redistribution. You may reproduce and distribute copies of the
90
+ Work or Derivative Works thereof in any medium, with or without
91
+ modifications, and in Source or Object form, provided that You
92
+ meet the following conditions:
93
+
94
+ (a) You must give any other recipients of the Work or
95
+ Derivative Works a copy of this License; and
96
+
97
+ (b) You must cause any modified files to carry prominent notices
98
+ stating that You changed the files; and
99
+
100
+ (c) You must retain, in the Source form of any Derivative Works
101
+ that You distribute, all copyright, patent, trademark, and
102
+ attribution notices from the Source form of the Work,
103
+ excluding those notices that do not pertain to any part of
104
+ the Derivative Works; and
105
+
106
+ (d) If the Work includes a "NOTICE" text file as part of its
107
+ distribution, then any Derivative Works that You distribute must
108
+ include a readable copy of the attribution notices contained
109
+ within such NOTICE file, excluding those notices that do not
110
+ pertain to any part of the Derivative Works, in at least one
111
+ of the following places: within a NOTICE text file distributed
112
+ as part of the Derivative Works; within the Source form or
113
+ documentation, if provided along with the Derivative Works; or,
114
+ within a display generated by the Derivative Works, if and
115
+ wherever such third-party notices normally appear. The contents
116
+ of the NOTICE file are for informational purposes only and
117
+ do not modify the License. You may add Your own attribution
118
+ notices within Derivative Works that You distribute, alongside
119
+ or as an addendum to the NOTICE text from the Work, provided
120
+ that such additional attribution notices cannot be construed
121
+ as modifying the License.
122
+
123
+ You may add Your own copyright statement to Your modifications and
124
+ may provide additional or different license terms and conditions
125
+ for use, reproduction, or distribution of Your modifications, or
126
+ for any such Derivative Works as a whole, provided Your use,
127
+ reproduction, and distribution of the Work otherwise complies with
128
+ the conditions stated in this License.
129
+
130
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
131
+ any Contribution intentionally submitted for inclusion in the Work
132
+ by You to the Licensor shall be under the terms and conditions of
133
+ this License, without any additional terms or conditions.
134
+ Notwithstanding the above, nothing herein shall supersede or modify
135
+ the terms of any separate license agreement you may have executed
136
+ with Licensor regarding such Contributions.
137
+
138
+ 6. Trademarks. This License does not grant permission to use the trade
139
+ names, trademarks, service marks, or product names of the Licensor,
140
+ except as required for reasonable and customary use in describing the
141
+ origin of the Work and reproducing the content of the NOTICE file.
142
+
143
+ 7. Disclaimer of Warranty. Unless required by applicable law or
144
+ agreed to in writing, Licensor provides the Work (and each
145
+ Contributor provides its Contributions) on an "AS IS" BASIS,
146
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147
+ implied, including, without limitation, any warranties or conditions
148
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149
+ PARTICULAR PURPOSE. You are solely responsible for determining the
150
+ appropriateness of using or redistributing the Work and assume any
151
+ risks associated with Your exercise of permissions under this License.
152
+
153
+ 8. Limitation of Liability. In no event and under no legal theory,
154
+ whether in tort (including negligence), contract, or otherwise,
155
+ unless required by applicable law (such as deliberate and grossly
156
+ negligent acts) or agreed to in writing, shall any Contributor be
157
+ liable to You for damages, including any direct, indirect, special,
158
+ incidental, or consequential damages of any character arising as a
159
+ result of this License or out of the use or inability to use the
160
+ Work (including but not limited to damages for loss of goodwill,
161
+ work stoppage, computer failure or malfunction, or any and all
162
+ other commercial damages or losses), even if such Contributor
163
+ has been advised of the possibility of such damages.
164
+
165
+ 9. Accepting Warranty or Additional Liability. While redistributing
166
+ the Work or Derivative Works thereof, You may choose to offer,
167
+ and charge a fee for, acceptance of support, warranty, indemnity,
168
+ or other liability obligations and/or rights consistent with this
169
+ License. However, in accepting such obligations, You may act only
170
+ on Your own behalf and on Your sole responsibility, not on behalf
171
+ of any other Contributor, and only if You agree to indemnify,
172
+ defend, and hold each Contributor harmless for any liability
173
+ incurred by, or claims asserted against, such Contributor by reason
174
+ of your accepting any such warranty or additional liability.
175
+
176
+ END OF TERMS AND CONDITIONS
177
+
178
+ APPENDIX: How to apply the Apache License to your work.
179
+
180
+ To apply the Apache License to your work, attach the following
181
+ boilerplate notice, with the fields enclosed by brackets "[]"
182
+ replaced with your own identifying information. (Don't include
183
+ the brackets!) The text should be enclosed in the appropriate
184
+ comment syntax for the file format. We also recommend that a
185
+ file or class name and description of purpose be included on the
186
+ same "printed page" as the copyright notice for easier
187
+ identification within third-party archives.
188
+
189
+ Copyright 2025 afish
190
+
191
+ Licensed under the Apache License, Version 2.0 (the "License");
192
+ you may not use this file except in compliance with the License.
193
+ You may obtain a copy of the License at
194
+
195
+ http://www.apache.org/licenses/LICENSE-2.0
196
+
197
+ Unless required by applicable law or agreed to in writing, software
198
+ distributed under the License is distributed on an "AS IS" BASIS,
199
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
200
+ See the License for the specific language governing permissions and
201
+ limitations under the License.
@@ -0,0 +1,166 @@
1
+ Metadata-Version: 2.4
2
+ Name: wordformat
3
+ Version: 1.0.0
4
+ Summary: 论文格式自动化处理工具
5
+ Author-email: afish <1593699665@qq.com>
6
+ License-Expression: Apache-2.0
7
+ Project-URL: Homepage, https://github.com/AfishInLake/WordFormat
8
+ Project-URL: Repository, https://github.com/AfishInLake/WordFormat
9
+ Project-URL: Bug Tracker, https://github.com/AfishInLake/WordFormat/issues
10
+ Keywords: word,docx,thesis,format,论文,格式,校验,自动化
11
+ Classifier: Development Status :: 3 - Alpha
12
+ Classifier: Intended Audience :: Developers
13
+ Classifier: Intended Audience :: Education
14
+ Classifier: Intended Audience :: Science/Research
15
+ Classifier: Programming Language :: Python :: 3
16
+ Classifier: Programming Language :: Python :: 3.10
17
+ Classifier: Programming Language :: Python :: 3.11
18
+ Classifier: Programming Language :: Python :: 3.12
19
+ Classifier: Programming Language :: Python :: 3.13
20
+ Classifier: Topic :: Scientific/Engineering
21
+ Classifier: Topic :: Text Processing
22
+ Classifier: Operating System :: OS Independent
23
+ Requires-Python: >=3.10
24
+ Description-Content-Type: text/markdown
25
+ License-File: LICENSE
26
+ Requires-Dist: loguru>=0.7.3
27
+ Requires-Dist: numpy>=1.24.0
28
+ Requires-Dist: onnxruntime>=1.17.0
29
+ Requires-Dist: pydantic>=2.12.5
30
+ Requires-Dist: python-docx>=1.2.0
31
+ Requires-Dist: python-dotenv>=1.2.1
32
+ Requires-Dist: pyyaml>=6.0.3
33
+ Requires-Dist: requests>=2.32.5
34
+ Requires-Dist: tenacity>=9.1.2
35
+ Requires-Dist: tokenizers>=0.22.2
36
+ Requires-Dist: webcolors>=25.10.0
37
+ Provides-Extra: api
38
+ Requires-Dist: fastapi>=0.128.1; extra == "api"
39
+ Requires-Dist: uvicorn>=0.40.0; extra == "api"
40
+ Requires-Dist: python-multipart>=0.0.22; extra == "api"
41
+ Provides-Extra: test
42
+ Requires-Dist: pytest>=9.0.2; extra == "test"
43
+ Requires-Dist: pytest-asyncio>=1.3.0; extra == "test"
44
+ Requires-Dist: pytest-cov>=7.0.0; extra == "test"
45
+ Provides-Extra: dev
46
+ Requires-Dist: wordformat[api,test]; extra == "dev"
47
+ Requires-Dist: pre-commit>=4.5.1; extra == "dev"
48
+ Requires-Dist: ruff>=0.14.14; extra == "dev"
49
+ Requires-Dist: pyinstaller>=6.18.0; extra == "dev"
50
+ Dynamic: license-file
51
+
52
+ # WordFormat
53
+
54
+ > 论文格式自动化处理工具
55
+
56
+ ![License](https://img.shields.io/github/license/AfishInLake/WordFormat?color=blue)
57
+ ![Python](https://img.shields.io/badge/python-3.10%2B-blue)
58
+ ![PyPI](https://img.shields.io/pypi/v/wordformat?color=blue)
59
+ ![Platform](https://img.shields.io/badge/platform-Windows%20%7C%20macOS%20%7C%20Linux-lightgrey)
60
+
61
+ ## 项目简介
62
+
63
+ **WordFormat** 是一个基于 Python 开发的 Word 文档自动化格式检查与修正工具,专为学术论文(本科/硕士/博士毕业论文、期刊论文等)的格式合规性审查设计。该工具能够智能解析 Word 文档结构,识别标题、摘要、正文、参考文献等不同段落类型,并依据自定义的格式规范自动校验文档格式,支持在违规位置添加批注或直接修正格式问题,大幅提升论文格式审核效率。
64
+
65
+ 点击 **[WordFormatUI](https://github.com/AfishInLake/WordFormatUI)** 查看带有GUI界面的项目
66
+ ## 功能特性
67
+
68
+ ### 核心能力
69
+ - **智能文档结构解析**:基于 ONNX 模型自动识别文档中的标题、摘要、正文、关键词、参考文献等段落类型,生成结构化 JSON 配置文件
70
+ - **精细化格式校验**:支持段落格式(对齐、行距、缩进、段间距)和字符格式(字体、字号、颜色、加粗/斜体/下划线)的全维度检查
71
+ - **多级别标题管理**:精准识别一级/二级/三级标题,支持自定义标题格式规范校验
72
+ - **多语言适配**:区分中英文字体/格式规则,完美支持中英文混合文档的格式检查
73
+ - **灵活的交互方式**:支持「生成结构文件→手动调整→执行校验」的分步流程,兼顾自动化与灵活性
74
+
75
+ ### 实用功能
76
+ - **自动批注生成**:在格式违规位置自动添加 Word 批注,标注问题类型和修正建议
77
+ - **格式一键修正**:支持根据规范自动修正部分常见格式问题(如标题字号、正文行距)
78
+ - **自定义配置**:通过 YAML 配置文件灵活定义格式规范,适配不同学校/期刊的格式要求
79
+ - **跨平台兼容**:支持 Windows/macOS/Linux 系统,基于 python-docx 实现跨平台 Word 文档处理
80
+
81
+ ## 视频教程
82
+ [点击直达B站视频](https://www.bilibili.com/video/BV1aiDjB8Edg/?spm_id_from=333.1007.top_right_bar_window_history.content.click&vd_source=490c514f59611dc0b600c1da58948e14)
83
+
84
+ ## 普通用户请看这里
85
+ + 如果你是普通用户,请点击[WordFormatUI](https://github.com/AfishInLake/WordFormatUI/releases)下载带有GUI界面的安装包直接使用,并参考[安装指南](https://github.com/AfishInLake/WordFormatUI/blob/master/README.md)进行安装。
86
+ + 如果你是开发人员,请按照以下步骤进行安装和运行
87
+
88
+ ## 快速开始
89
+
90
+ ### 环境要求
91
+ - Python 3.10+(推荐 3.11 及以上版本)
92
+ - 依赖管理工具:uv(推荐)或 pip
93
+
94
+ ### 安装步骤
95
+
96
+ 1. **克隆项目**
97
+ ```bash
98
+ git clone https://github.com/AfishInLake/WordFormat.git
99
+ cd WordFormat
100
+ ```
101
+
102
+ 2. **安装依赖**
103
+ ```bash
104
+ make install
105
+ # 或使用 pip
106
+ pip install -e .
107
+ ```
108
+
109
+ 3. **配置环境变量**
110
+ 创建 `.env` 文件,配置 HOST、PORT 等必要参数:
111
+ ```env
112
+ HOST="127.0.0.1"
113
+ # 配置服务端口
114
+ PORT="8000"
115
+ ```
116
+
117
+ 4. **启动API服务**
118
+ ```bash
119
+ # 在虚拟环境下运行
120
+ make server
121
+ ```
122
+
123
+ 5. **构建.exe程序**
124
+ ```bash
125
+ # 在虚拟环境下运行
126
+ make build
127
+ ```
128
+
129
+ ## 核心使用方法
130
+
131
+ ### 命令行使用(推荐)
132
+
133
+ WordFormat 提供三种核心执行模式:
134
+
135
+ 1. **生成文档结构 JSON**
136
+
137
+ 2. **执行格式校验**
138
+
139
+ 3. **执行格式格式化**
140
+
141
+ 具体请看
142
+ - [使用指南](docs/usage.md)
143
+
144
+ ## 详细文档
145
+
146
+ 更多详细文档请查看 `docs/` 目录:
147
+
148
+ - [安装指南](docs/installation.md) - 环境要求和安装步骤
149
+ - [使用指南](docs/usage.md) - 命令行、Python编程和API调用的详细使用方法
150
+ - [配置文件说明](docs/configuration.md) - 格式规范配置项和自定义配置方法
151
+ - [常见问题](docs/faq.md) - 常见问题及解决方案
152
+ - [贡献指南](docs/contributing.md) - 如何为项目贡献代码和文档
153
+ - [技术架构](docs/architecture.md) - 项目的技术架构和实现原理
154
+
155
+ ## 许可证
156
+
157
+ [Apache License 2.0](LICENSE) - 允许自由使用、修改和分发,需保留原作者声明。
158
+
159
+ ## 联系方式
160
+
161
+ - 反馈渠道:GitHub Issues(优先推荐,方便问题跟踪和交流)
162
+ - 联系邮箱:1593699665@qq.com
163
+
164
+ ## 项目贡献者
165
+
166
+ 待补充,欢迎各位开发者提交PR贡献代码,一起完善这个工具!
@@ -0,0 +1,115 @@
1
+ # WordFormat
2
+
3
+ > 论文格式自动化处理工具
4
+
5
+ ![License](https://img.shields.io/github/license/AfishInLake/WordFormat?color=blue)
6
+ ![Python](https://img.shields.io/badge/python-3.10%2B-blue)
7
+ ![PyPI](https://img.shields.io/pypi/v/wordformat?color=blue)
8
+ ![Platform](https://img.shields.io/badge/platform-Windows%20%7C%20macOS%20%7C%20Linux-lightgrey)
9
+
10
+ ## 项目简介
11
+
12
+ **WordFormat** 是一个基于 Python 开发的 Word 文档自动化格式检查与修正工具,专为学术论文(本科/硕士/博士毕业论文、期刊论文等)的格式合规性审查设计。该工具能够智能解析 Word 文档结构,识别标题、摘要、正文、参考文献等不同段落类型,并依据自定义的格式规范自动校验文档格式,支持在违规位置添加批注或直接修正格式问题,大幅提升论文格式审核效率。
13
+
14
+ 点击 **[WordFormatUI](https://github.com/AfishInLake/WordFormatUI)** 查看带有GUI界面的项目
15
+ ## 功能特性
16
+
17
+ ### 核心能力
18
+ - **智能文档结构解析**:基于 ONNX 模型自动识别文档中的标题、摘要、正文、关键词、参考文献等段落类型,生成结构化 JSON 配置文件
19
+ - **精细化格式校验**:支持段落格式(对齐、行距、缩进、段间距)和字符格式(字体、字号、颜色、加粗/斜体/下划线)的全维度检查
20
+ - **多级别标题管理**:精准识别一级/二级/三级标题,支持自定义标题格式规范校验
21
+ - **多语言适配**:区分中英文字体/格式规则,完美支持中英文混合文档的格式检查
22
+ - **灵活的交互方式**:支持「生成结构文件→手动调整→执行校验」的分步流程,兼顾自动化与灵活性
23
+
24
+ ### 实用功能
25
+ - **自动批注生成**:在格式违规位置自动添加 Word 批注,标注问题类型和修正建议
26
+ - **格式一键修正**:支持根据规范自动修正部分常见格式问题(如标题字号、正文行距)
27
+ - **自定义配置**:通过 YAML 配置文件灵活定义格式规范,适配不同学校/期刊的格式要求
28
+ - **跨平台兼容**:支持 Windows/macOS/Linux 系统,基于 python-docx 实现跨平台 Word 文档处理
29
+
30
+ ## 视频教程
31
+ [点击直达B站视频](https://www.bilibili.com/video/BV1aiDjB8Edg/?spm_id_from=333.1007.top_right_bar_window_history.content.click&vd_source=490c514f59611dc0b600c1da58948e14)
32
+
33
+ ## 普通用户请看这里
34
+ + 如果你是普通用户,请点击[WordFormatUI](https://github.com/AfishInLake/WordFormatUI/releases)下载带有GUI界面的安装包直接使用,并参考[安装指南](https://github.com/AfishInLake/WordFormatUI/blob/master/README.md)进行安装。
35
+ + 如果你是开发人员,请按照以下步骤进行安装和运行
36
+
37
+ ## 快速开始
38
+
39
+ ### 环境要求
40
+ - Python 3.10+(推荐 3.11 及以上版本)
41
+ - 依赖管理工具:uv(推荐)或 pip
42
+
43
+ ### 安装步骤
44
+
45
+ 1. **克隆项目**
46
+ ```bash
47
+ git clone https://github.com/AfishInLake/WordFormat.git
48
+ cd WordFormat
49
+ ```
50
+
51
+ 2. **安装依赖**
52
+ ```bash
53
+ make install
54
+ # 或使用 pip
55
+ pip install -e .
56
+ ```
57
+
58
+ 3. **配置环境变量**
59
+ 创建 `.env` 文件,配置 HOST、PORT 等必要参数:
60
+ ```env
61
+ HOST="127.0.0.1"
62
+ # 配置服务端口
63
+ PORT="8000"
64
+ ```
65
+
66
+ 4. **启动API服务**
67
+ ```bash
68
+ # 在虚拟环境下运行
69
+ make server
70
+ ```
71
+
72
+ 5. **构建.exe程序**
73
+ ```bash
74
+ # 在虚拟环境下运行
75
+ make build
76
+ ```
77
+
78
+ ## 核心使用方法
79
+
80
+ ### 命令行使用(推荐)
81
+
82
+ WordFormat 提供三种核心执行模式:
83
+
84
+ 1. **生成文档结构 JSON**
85
+
86
+ 2. **执行格式校验**
87
+
88
+ 3. **执行格式格式化**
89
+
90
+ 具体请看
91
+ - [使用指南](docs/usage.md)
92
+
93
+ ## 详细文档
94
+
95
+ 更多详细文档请查看 `docs/` 目录:
96
+
97
+ - [安装指南](docs/installation.md) - 环境要求和安装步骤
98
+ - [使用指南](docs/usage.md) - 命令行、Python编程和API调用的详细使用方法
99
+ - [配置文件说明](docs/configuration.md) - 格式规范配置项和自定义配置方法
100
+ - [常见问题](docs/faq.md) - 常见问题及解决方案
101
+ - [贡献指南](docs/contributing.md) - 如何为项目贡献代码和文档
102
+ - [技术架构](docs/architecture.md) - 项目的技术架构和实现原理
103
+
104
+ ## 许可证
105
+
106
+ [Apache License 2.0](LICENSE) - 允许自由使用、修改和分发,需保留原作者声明。
107
+
108
+ ## 联系方式
109
+
110
+ - 反馈渠道:GitHub Issues(优先推荐,方便问题跟踪和交流)
111
+ - 联系邮箱:1593699665@qq.com
112
+
113
+ ## 项目贡献者
114
+
115
+ 待补充,欢迎各位开发者提交PR贡献代码,一起完善这个工具!
@@ -0,0 +1,139 @@
1
+ [project]
2
+ name = "wordformat"
3
+ version = "1.0.0"
4
+ description = "论文格式自动化处理工具"
5
+ readme = "README.md"
6
+ license = "Apache-2.0"
7
+ requires-python = ">=3.10"
8
+ authors = [
9
+ {name = "afish", email = "1593699665@qq.com"},
10
+ ]
11
+ keywords = ["word", "docx", "thesis", "format", "论文", "格式", "校验", "自动化"]
12
+ classifiers = [
13
+ "Development Status :: 3 - Alpha",
14
+ "Intended Audience :: Developers",
15
+ "Intended Audience :: Education",
16
+ "Intended Audience :: Science/Research",
17
+ "Programming Language :: Python :: 3",
18
+ "Programming Language :: Python :: 3.10",
19
+ "Programming Language :: Python :: 3.11",
20
+ "Programming Language :: Python :: 3.12",
21
+ "Programming Language :: Python :: 3.13",
22
+ "Topic :: Scientific/Engineering",
23
+ "Topic :: Text Processing",
24
+ "Operating System :: OS Independent",
25
+ ]
26
+ dependencies = [
27
+ "loguru>=0.7.3",
28
+ "numpy>=1.24.0",
29
+ "onnxruntime>=1.17.0",
30
+ "pydantic>=2.12.5",
31
+ "python-docx>=1.2.0",
32
+ "python-dotenv>=1.2.1",
33
+ "pyyaml>=6.0.3",
34
+ "requests>=2.32.5",
35
+ "tenacity>=9.1.2",
36
+ "tokenizers>=0.22.2",
37
+ "webcolors>=25.10.0",
38
+ ]
39
+
40
+ [project.urls]
41
+ Homepage = "https://github.com/AfishInLake/WordFormat"
42
+ Repository = "https://github.com/AfishInLake/WordFormat"
43
+ "Bug Tracker" = "https://github.com/AfishInLake/WordFormat/issues"
44
+
45
+ [tool.ruff.lint]
46
+ select = [
47
+ "E", # pycodestyle errors
48
+ "W", # pycodestyle warnings
49
+ "F", # pyflakes
50
+ "I", # isort
51
+ "C", # flake8-comprehensions
52
+ "B", # flake8-bugbear
53
+ "T20", # flake8-print
54
+ "TC", # flake8-type-checking
55
+ "ASYNC", # flake8-asyncio
56
+ ]
57
+ ignore = [
58
+ "ASYNC210",
59
+ "ASYNC251",
60
+ "ASYNC230",
61
+ "TC003",
62
+ "TC002"
63
+ ]
64
+ fixable = ["A", "B", "C", "D", "E", "F", "G", "I", "N", "Q", "S", "T", "W", "ANN", "ARG", "BLE", "COM", "DJ", "DTZ", "EM", "ERA", "EXE", "FBT", "ICN", "INP", "ISC", "NPY", "PD", "PGH", "PIE", "PL", "PT", "PTH", "PYI", "RET", "RSE", "RUF", "SIM", "SLF", "TCH", "TID", "TRY", "UP", "YTT"]
65
+ unfixable = []
66
+ exclude = [
67
+ ".bzr",
68
+ ".direnv",
69
+ ".eggs",
70
+ ".git",
71
+ ".hg",
72
+ ".mypy_cache",
73
+ ".nox",
74
+ ".pants.d",
75
+ ".pytype",
76
+ ".ruff_cache",
77
+ ".svn",
78
+ ".tox",
79
+ ".venv",
80
+ "__pypackages__",
81
+ "_build",
82
+ "buck-out",
83
+ "build",
84
+ "dist",
85
+ "node_modules",
86
+ "venv",
87
+ ]
88
+ dummy-variable-rgx = "^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$"
89
+
90
+ [tool.ruff.lint.mccabe]
91
+ max-complexity = 10
92
+
93
+ [tool.ruff.lint.per-file-ignores]
94
+ "__init__.py" = ["F401", "F403", "E501"]
95
+
96
+ [tool.ruff.format]
97
+ quote-style = "double"
98
+ indent-style = "space"
99
+ skip-magic-trailing-comma = false
100
+ line-ending = "auto"
101
+
102
+ [tool.ruff.lint.pycodestyle]
103
+ max-line-length = 108
104
+ max-doc-length = 200
105
+ ignore-overlong-task-comments = true
106
+
107
+ [build-system]
108
+ requires = ["setuptools>=61.0", "wheel"]
109
+ build-backend = "setuptools.build_meta"
110
+
111
+ # 显式声明使用 src 布局(推荐)
112
+ [tool.setuptools.packages.find]
113
+ where = ["src"]
114
+
115
+ [tool.setuptools.package-data]
116
+ wordformat = ["data/**/*"]
117
+
118
+ [project.scripts]
119
+ wordformat = "wordformat.cli:main"
120
+ wf = "wordformat.cli:main"
121
+
122
+
123
+ [project.optional-dependencies]
124
+ api = [
125
+ "fastapi>=0.128.1",
126
+ "uvicorn>=0.40.0",
127
+ "python-multipart>=0.0.22",
128
+ ]
129
+ test = [
130
+ "pytest>=9.0.2",
131
+ "pytest-asyncio>=1.3.0",
132
+ "pytest-cov>=7.0.0",
133
+ ]
134
+ dev = [
135
+ "wordformat[test,api]",
136
+ "pre-commit>=4.5.1",
137
+ "ruff>=0.14.14",
138
+ "pyinstaller>=6.18.0",
139
+ ]
@@ -0,0 +1,4 @@
1
+ [egg_info]
2
+ tag_build =
3
+ tag_date = 0
4
+
@@ -0,0 +1,11 @@
1
+ #! /usr/bin/env python
2
+ # @Time : 2025/12/22 21:47
3
+ # @Author : afish
4
+ # @File : __init__.py.py
5
+ from wordformat.set_style import auto_format_thesis_document
6
+ from wordformat.set_tag import set_tag_main
7
+
8
+ __all__ = [
9
+ "auto_format_thesis_document",
10
+ "set_tag_main"
11
+ ]
@@ -0,0 +1,4 @@
1
+ #! /usr/bin/env python
2
+ # @Time : 2026/1/11 17:38
3
+ # @Author : afish
4
+ # @File : __init__.py.py