├── .gitignore ├── LICENSE ├── README.md ├── extra-config ├── t2hkp.json └── t2twp.json └── opencc_to_hanlp.py /.gitignore: -------------------------------------------------------------------------------- 1 | # Created by .ignore support plugin (hsz.mobi) 2 | ### JetBrains template 3 | # Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio and WebStorm 4 | # Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839 5 | 6 | # User-specific stuff 7 | .idea/**/workspace.xml 8 | .idea/**/tasks.xml 9 | .idea/**/usage.statistics.xml 10 | .idea/**/dictionaries 11 | .idea/**/shelf 12 | 13 | # Sensitive or high-churn files 14 | .idea/**/dataSources/ 15 | .idea/**/dataSources.ids 16 | .idea/**/dataSources.local.xml 17 | .idea/**/sqlDataSources.xml 18 | .idea/**/dynamic.xml 19 | .idea/**/uiDesigner.xml 20 | .idea/**/dbnavigator.xml 21 | 22 | # Gradle 23 | .idea/**/gradle.xml 24 | .idea/**/libraries 25 | 26 | # Gradle and Maven with auto-import 27 | # When using Gradle or Maven with auto-import, you should exclude module files, 28 | # since they will be recreated, and may cause churn. Uncomment if using 29 | # auto-import. 30 | # .idea/modules.xml 31 | # .idea/*.iml 32 | # .idea/modules 33 | 34 | # CMake 35 | cmake-build-*/ 36 | 37 | # Mongo Explorer plugin 38 | .idea/**/mongoSettings.xml 39 | 40 | # File-based project format 41 | *.iws 42 | 43 | # IntelliJ 44 | out/ 45 | 46 | # mpeltonen/sbt-idea plugin 47 | .idea_modules/ 48 | 49 | # JIRA plugin 50 | atlassian-ide-plugin.xml 51 | 52 | # Cursive Clojure plugin 53 | .idea/replstate.xml 54 | 55 | # Crashlytics plugin (for Android Studio and IntelliJ) 56 | com_crashlytics_export_strings.xml 57 | crashlytics.properties 58 | crashlytics-build.properties 59 | fabric.properties 60 | 61 | # Editor-based Rest Client 62 | .idea/httpRequests 63 | ### Python template 64 | # Byte-compiled / optimized / DLL files 65 | __pycache__/ 66 | *.py[cod] 67 | *$py.class 68 | 69 | # C extensions 70 | *.so 71 | 72 | # Distribution / packaging 73 | .Python 74 | build/ 75 | develop-eggs/ 76 | dist/ 77 | downloads/ 78 | eggs/ 79 | .eggs/ 80 | lib/ 81 | lib64/ 82 | parts/ 83 | sdist/ 84 | var/ 85 | wheels/ 86 | *.egg-info/ 87 | .installed.cfg 88 | *.egg 89 | MANIFEST 90 | 91 | # PyInstaller 92 | # Usually these files are written by a python script from a template 93 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 94 | *.manifest 95 | *.spec 96 | 97 | # Installer logs 98 | pip-log.txt 99 | pip-delete-this-directory.txt 100 | 101 | # Unit test / coverage reports 102 | htmlcov/ 103 | .tox/ 104 | .coverage 105 | .coverage.* 106 | .cache 107 | nosetests.xml 108 | coverage.xml 109 | *.cover 110 | .hypothesis/ 111 | .pytest_cache/ 112 | 113 | # Translations 114 | *.mo 115 | *.pot 116 | 117 | # Django stuff: 118 | *.log 119 | local_settings.py 120 | db.sqlite3 121 | 122 | # Flask stuff: 123 | instance/ 124 | .webassets-cache 125 | 126 | # Scrapy stuff: 127 | .scrapy 128 | 129 | # Sphinx documentation 130 | docs/_build/ 131 | 132 | # PyBuilder 133 | target/ 134 | 135 | # Jupyter Notebook 136 | .ipynb_checkpoints 137 | 138 | # pyenv 139 | .python-version 140 | 141 | # celery beat schedule file 142 | celerybeat-schedule 143 | 144 | # SageMath parsed files 145 | *.sage.py 146 | 147 | # Environments 148 | .env 149 | .venv 150 | env/ 151 | venv/ 152 | ENV/ 153 | env.bak/ 154 | venv.bak/ 155 | 156 | # Spyder project settings 157 | .spyderproject 158 | .spyproject 159 | 160 | # Rope project settings 161 | .ropeproject 162 | 163 | # mkdocs documentation 164 | /site 165 | 166 | # mypy 167 | .mypy_cache/ 168 | .idea/ -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 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 [yyyy] [name of copyright owner] 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. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # OpenCC-to-HanLP 2 | 转换[OpenCC](https://github.com/BYVoid/OpenCC/tree/master/data)词典为[HanLP](https://github.com/hankcs/HanLP)格式。 3 | 4 | ## 用法 5 | 6 | ```bash 7 | $ python3 opencc_to_hanlp.py 8 | usage: opencc_to_hanlp.py [-h] --opencc_path OPENCC_PATH --output_dir 9 | OUTPUT_DIR 10 | 11 | Tool for converting dictionaries from OpenCC to HanLP 12 | 13 | optional arguments: 14 | -h, --help show this help message and exit 15 | --opencc_path OPENCC_PATH 16 | root path to OpenCC 17 | --output_dir OUTPUT_DIR 18 | the folder to store converted dictionaries in HanLP 19 | format 20 | ``` 21 | 22 | - `opencc_path`指向OpenCC的根目录，即`git clone https://github.com/BYVoid/OpenCC.git`后获取到的`OpenCC`目录。 23 | - `output_dir`指向输出目录。 24 | 25 | 典型用法如下： 26 | 27 | ```bash 28 | git clone https://github.com/hankcs/OpenCC-to-HanLP.git 29 | git clone https://github.com/BYVoid/OpenCC.git 30 | cp OpenCC-to-HanLP/extra-config/* OpenCC/data/config/ 31 | python3 --opencc_path ./OpenCC --output_dir ./hanlp-tc 32 | tree hanlp-tc 33 | hanlp-tc 34 | ├── hk2s.txt 35 | ├── s2hk.txt 36 | ├── s2t.txt 37 | ├── s2tw.txt 38 | ├── s2twp.txt 39 | ├── t2hk.txt 40 | ├── t2hkp.txt 41 | ├── t2s.txt 42 | ├── t2tw.txt 43 | ├── t2twp.txt 44 | ├── tw2s.txt 45 | └── tw2sp.txt 46 | 47 | 0 directories, 12 files 48 | ``` 49 | 50 | 这些`txt`词典即为转换后的HanLP格式，用户只需用`s2t.txt`、`t2s.txt`、`t2hk.txt`和`t2tw.txt`替换HanLP项目的`data/dictionary/tc`中相应的`4`个文件，并删除所有`.bin`缓存文件即可。 51 | 52 | `t2hkp.txt`和`t2twp.txt`是合并了短语的“短语版”词典，比“精简版”`t2hk.txt`和`t2tw.txt`提供更多分歧词。OpenCC官方不提供相应的配置文件，默认不会生成这两个文件。通过拷贝本项目提供的[extra-config](https://github.com/hankcs/OpenCC-to-HanLP/tree/master/extra-config)到OpenCC的[config](https://github.com/BYVoid/OpenCC/tree/master/data/config)目录，才能生成这两个新文件。导入HanLP时，将这两个文件名中的`p`去掉重复上面的操作即可。 53 | 54 | 用户可根据自己的需求自由选择，HanLP默认采用了“短语版”词典。 55 | 56 | ## 转换后的词库下载 57 | 58 | 方便起见，特提供转换后的词库下载：https://github.com/hankcs/OpenCC-to-HanLP/releases -------------------------------------------------------------------------------- /extra-config/t2hkp.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Traditional Chinese to Traditional Chinese (Hong Kong standard)", 3 | "segmentation": { 4 | "type": "mmseg", 5 | "dict": { 6 | "type": "ocd", 7 | "file": "HKVariants.ocd" 8 | } 9 | }, 10 | "conversion_chain": [{ 11 | "dict": { 12 | "type": "group", 13 | "dicts": [{ 14 | "type": "ocd", 15 | "file": "HKVariantsPhrases.ocd" 16 | }, { 17 | "type": "ocd", 18 | "file": "HKVariants.ocd" 19 | }] 20 | } 21 | }] 22 | } 23 | -------------------------------------------------------------------------------- /extra-config/t2twp.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Traditional Chinese to Traditional Chinese (Taiwan standard)", 3 | "segmentation": { 4 | "type": "mmseg", 5 | "dict": { 6 | "type": "ocd", 7 | "file": "TWVariants.ocd" 8 | } 9 | }, 10 | "conversion_chain": [{ 11 | "dict": { 12 | "type": "ocd", 13 | "file": "TWPhrases.ocd" 14 | } 15 | }, { 16 | "dict": { 17 | "type": "ocd", 18 | "file": "TWVariants.ocd" 19 | } 20 | }] 21 | } 22 | -------------------------------------------------------------------------------- /opencc_to_hanlp.py: -------------------------------------------------------------------------------- 1 | # -*- coding:utf-8 -*- 2 | # Author: hankcs 3 | # Date: 2019-06-27 20:37 4 | import argparse 5 | import glob 6 | import json 7 | import os 8 | import sys 9 | 10 | 11 | def convert_single(json_path, output_path): 12 | print('转换 {} 为 {} 通过合并'.format(json_path, output_path), end=' ') 13 | opencc_data = os.path.dirname(os.path.dirname(json_path)) 14 | with open(json_path) as json_fp, open(output_path, 'w') as out: 15 | dic = dict() 16 | config = json.load(json_fp) 17 | for chain in config['conversion_chain']: 18 | dicts = chain['dict'].get('dicts', None) 19 | if not dicts: 20 | dicts = [chain['dict']] 21 | for dic_item in dicts: 22 | dic_txt = dic_item['file'].replace('.ocd', '.txt') 23 | rev = False 24 | if not os.path.isfile(os.path.join(opencc_data, 'dictionary', dic_txt)) and 'Rev' in dic_txt: 25 | rev = True # 有些Rev文件不存在，需要动态逆转 26 | dic_txt = dic_txt.replace('Rev', '') 27 | print(dic_txt, end=' ') 28 | dic_txt = os.path.join(opencc_data, 'dictionary', dic_txt) 29 | if os.path.isfile(dic_txt): 30 | load_dic(dic, dic_txt, rev) 31 | else: # 有些文件需要动态合并 32 | for file in glob.glob(dic_txt.replace('.txt', '*.txt')): 33 | load_dic(dic, file, rev) 34 | for first, second in sorted(dic.items()): 35 | out.write('{}={}\n'.format(first, second)) 36 | print() 37 | 38 | 39 | def load_dic(dic, dic_txt, rev): 40 | with open(dic_txt) as src: 41 | for line in src: 42 | cells = line.strip().split() 43 | if not cells: 44 | continue 45 | first, second = cells[0], cells[1] 46 | if rev: 47 | first, second = second, first 48 | dic[first] = second 49 | 50 | 51 | def convert_all(opencc_path, output_dir): 52 | os.makedirs(output_dir, exist_ok=True) 53 | for json_file in glob.glob(os.path.join(opencc_path, 'data', 'config', '*.json')): 54 | convert_single(json_file, os.path.join(output_dir, os.path.basename(json_file).replace('.json', '.txt'))) 55 | print('转换完毕，词典保存在目录 {}'.format(output_dir)) 56 | 57 | 58 | def main(): 59 | arg_parser = argparse.ArgumentParser(description='Tool for converting dictionaries from OpenCC to HanLP') 60 | arg_parser.add_argument('--opencc_path', required=True, help='root path to OpenCC') 61 | arg_parser.add_argument('--output_dir', required=True, 62 | help='the folder to store converted dictionaries in HanLP format') 63 | if len(sys.argv) == 1: 64 | sys.argv.append('--help') 65 | args = arg_parser.parse_args() 66 | convert_all(args.opencc_path, args.output_dir) 67 | 68 | 69 | if __name__ == '__main__': 70 | main() 71 | --------------------------------------------------------------------------------