Repository: ffffffff0x/name-fuzz Branch: main Commit: 5f9cbb695073 Files: 5 Total size: 39.7 KB Directory structure: gitextract_yljkvgse/ ├── .gitignore ├── LICENSE ├── README.md ├── name-fuzz.py └── suffix.txt ================================================ FILE CONTENTS ================================================ ================================================ FILE: .gitignore ================================================ .idea /assets/temp.md push.sh output*.txt ================================================ FILE: LICENSE ================================================ Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 1. Definitions. "License" shall mean the terms and conditions for use, reproduction, and distribution as defined by Sections 1 through 9 of this document. "Licensor" shall mean the copyright owner or entity authorized by the copyright owner that is granting the License. "Legal Entity" shall mean the union of the acting entity and all other entities that control, are controlled by, or are under common control with that entity. For the purposes of this definition, "control" means (i) the power, direct or indirect, to cause the direction or management of such entity, whether by contract or otherwise, or (ii) ownership of fifty percent (50%) or more of the outstanding shares, or (iii) beneficial ownership of such entity. "You" (or "Your") shall mean an individual or Legal Entity exercising permissions granted by this License. "Source" form shall mean the preferred form for making modifications, including but not limited to software source code, documentation source, and configuration files. "Object" form shall mean any form resulting from mechanical transformation or translation of a Source form, including but not limited to compiled object code, generated documentation, and conversions to other media types. "Work" shall mean the work of authorship, whether in Source or Object form, made available under the License, as indicated by a copyright notice that is included in or attached to the work (an example is provided in the Appendix below). "Derivative Works" shall mean any work, whether in Source or Object form, that is based on (or derived from) the Work and for which the editorial revisions, annotations, elaborations, or other modifications represent, as a whole, an original work of authorship. For the purposes of this License, Derivative Works shall not include works that remain separable from, or merely link (or bind by name) to the interfaces of, the Work and Derivative Works thereof. "Contribution" shall mean any work of authorship, including the original version of the Work and any modifications or additions to that Work or Derivative Works thereof, that is intentionally submitted to Licensor for inclusion in the Work by the copyright owner or by an individual or Legal Entity authorized to submit on behalf of the copyright owner. For the purposes of this definition, "submitted" means any form of electronic, verbal, or written communication sent to the Licensor or its representatives, including but not limited to communication on electronic mailing lists, source code control systems, and issue tracking systems that are managed by, or on behalf of, the Licensor for the purpose of discussing and improving the Work, but excluding communication that is conspicuously marked or otherwise designated in writing by the copyright owner as "Not a Contribution." "Contributor" shall mean Licensor and any individual or Legal Entity on behalf of whom a Contribution has been received by Licensor and subsequently incorporated within the Work. 2. Grant of Copyright License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare Derivative Works of, publicly display, publicly perform, sublicense, and distribute the Work and such Derivative Works in Source or Object form. 3. Grant of Patent License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this section) patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer the Work, where such license applies only to those patent claims licensable by such Contributor that are necessarily infringed by their Contribution(s) alone or by combination of their Contribution(s) with the Work to which such Contribution(s) was submitted. If You institute patent litigation against any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Work or a Contribution incorporated within the Work constitutes direct or contributory patent infringement, then any patent licenses granted to You under this License for that Work shall terminate as of the date such litigation is filed. 4. Redistribution. You may reproduce and distribute copies of the Work or Derivative Works thereof in any medium, with or without modifications, and in Source or Object form, provided that You meet the following conditions: (a) You must give any other recipients of the Work or Derivative Works a copy of this License; and (b) You must cause any modified files to carry prominent notices stating that You changed the files; and (c) You must retain, in the Source form of any Derivative Works that You distribute, all copyright, patent, trademark, and attribution notices from the Source form of the Work, excluding those notices that do not pertain to any part of the Derivative Works; and (d) If the Work includes a "NOTICE" text file as part of its distribution, then any Derivative Works that You distribute must include a readable copy of the attribution notices contained within such NOTICE file, excluding those notices that do not pertain to any part of the Derivative Works, in at least one of the following places: within a NOTICE text file distributed as part of the Derivative Works; within the Source form or documentation, if provided along with the Derivative Works; or, within a display generated by the Derivative Works, if and wherever such third-party notices normally appear. The contents of the NOTICE file are for informational purposes only and do not modify the License. You may add Your own attribution notices within Derivative Works that You distribute, alongside or as an addendum to the NOTICE text from the Work, provided that such additional attribution notices cannot be construed as modifying the License. You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions for use, reproduction, or distribution of Your modifications, or for any such Derivative Works as a whole, provided Your use, reproduction, and distribution of the Work otherwise complies with the conditions stated in this License. 5. Submission of Contributions. Unless You explicitly state otherwise, any Contribution intentionally submitted for inclusion in the Work by You to the Licensor shall be under the terms and conditions of this License, without any additional terms or conditions. Notwithstanding the above, nothing herein shall supersede or modify the terms of any separate license agreement you may have executed with Licensor regarding such Contributions. 6. Trademarks. This License does not grant permission to use the trade names, trademarks, service marks, or product names of the Licensor, except as required for reasonable and customary use in describing the origin of the Work and reproducing the content of the NOTICE file. 7. Disclaimer of Warranty. Unless required by applicable law or agreed to in writing, Licensor provides the Work (and each Contributor provides its Contributions) on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely responsible for determining the appropriateness of using or redistributing the Work and assume any risks associated with Your exercise of permissions under this License. 8. Limitation of Liability. In no event and under no legal theory, whether in tort (including negligence), contract, or otherwise, unless required by applicable law (such as deliberate and grossly negligent acts) or agreed to in writing, shall any Contributor be liable to You for damages, including any direct, indirect, special, incidental, or consequential damages of any character arising as a result of this License or out of the use or inability to use the Work (including but not limited to damages for loss of goodwill, work stoppage, computer failure or malfunction, or any and all other commercial damages or losses), even if such Contributor has been advised of the possibility of such damages. 9. Accepting Warranty or Additional Liability. While redistributing the Work or Derivative Works thereof, You may choose to offer, and charge a fee for, acceptance of support, warranty, indemnity, or other liability obligations and/or rights consistent with this License. However, in accepting such obligations, You may act only on Your own behalf and on Your sole responsibility, not on behalf of any other Contributor, and only if You agree to indemnify, defend, and hold each Contributor harmless for any liability incurred by, or claims asserted against, such Contributor by reason of your accepting any such warranty or additional liability. END OF TERMS AND CONDITIONS APPENDIX: How to apply the Apache License to your work. To apply the Apache License to your work, attach the following boilerplate notice, with the fields enclosed by brackets "[]" replaced with your own identifying information. (Don't include the brackets!) The text should be enclosed in the appropriate comment syntax for the file format. We also recommend that a file or class name and description of purpose be included on the same "printed page" as the copyright notice for easier identification within third-party archives. Copyright [yyyy] [name of copyright owner] Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License. ================================================ FILE: README.md ================================================ # name-fuzz 针对目标已知信息的字典生成工具 > 重构版: https://github.com/ffffffff0x/gendict > 原理简单粗暴,调用 pypinyin 这个库将中文信息转为拼音,然后与后缀名字典拼接成字符串即可 > 如果有其他的字典生成思路和规则欢迎在 issue 提出来 --- ## 开始 **下载 && 安装依赖** ```bash git clone https://github.com/ffffffff0x/name-fuzz.git pip3 install pyreadline pypinyin cd name-fuzz ``` **使用** ```bash python3 name-fuzz.py ``` ![](./assets/img/1.png) --- ## 支持规则 ### 基于组织 `公司/单位/组织全称`+`后缀` - jsxxyxgs123 (江苏XX有限公司) - jsxxyxgs@123 - ... `公司/单位/组织简称`+`后缀` - jiangsuxx123 (江苏XX) - jiangsuxx@123 - ... `公司/单位/组织简称(缩写)`+`后缀` - jsxx123 (江苏XX) - jsxx@123 - ... `业务名(缩写)`+`后缀` - zhjt123 (智慧交通) - zhjt@123 - ... `公司/单位/组织简称(缩写)`+`系统/业务简称(缩写)`+`后缀` - jsxxzhjt123 (江苏XX智慧交通) ### 基于人员 `人员名称` - zhangsanfeng (拼音) - zsf (缩写) - zhangsf (首字拼音+缩写) - zsfeng (缩写+尾字拼音) - sanfengzhang (拼音+首字拼音) - sanfengz (拼音+首字缩写) - sfz (缩写+首字缩写) - 张三丰 (中文) --- ## 参考项目 - https://github.com/mozillazg/python-pinyin - https://github.com/soxoj/username-generation-guide - https://github.com/WangYihang/ccupp - https://gist.github.com/yuikns/387be5e9cf450ae3589fa7037c94453e - https://www.yuque.com/pmiaowu/bomi9w/ougg6d#d70159da --- ## License [Apache License 2.0](https://github.com/ffffffff0x/name-fuzz/blob/main/LICENSE) --- > create by ffffffff0x ================================================ FILE: name-fuzz.py ================================================ #!/usr/bin/env python # -*- encoding: utf-8 -*- import readline from pypinyin import pinyin, lazy_pinyin, Style # suffix 字典 filename="suffix.txt" # 检验名称输入是否全是中文字符 def is_all_chinese(strs): for _char in strs: if not '\u4e00' <= _char <= '\u9fa5': return False return True # 拼音分词 class PyTrieNode(object): def __init__(self, key="", seq=[]): self.key = key self.end = len(seq) == 0 self.children = {} if len(seq) > 0: self.children[seq[0]] = PyTrieNode(seq[0], seq[1:]) def add(self, seq): if len(seq) == 0: self.end = True else: key = seq[0] value = seq[1:] if key in self.children: self.children[key].add(value) else: self.children[key] = PyTrieNode(key, value) def find(self, sent): for i in range(len(sent)): i = len(sent) - i if len(sent) >= i: key = sent[:i] if key in self.children: buf, succ = self.children[key].find(sent[i:]) if succ: return key + buf, True return "", self.end class PyTrie(object): def __init__(self): self.root = PyTrieNode() self.root.end = False def setup(self): self.add(["a"]) self.add(["ai"]) self.add(["an"]) self.add(["ang"]) self.add(["ao"]) self.add(["e"]) self.add(["ei"]) self.add(["en"]) self.add(["er"]) self.add(["o"]) self.add(["ou"]) self.add(["b", "a"]) self.add(["b", "ai"]) self.add(["b", "an"]) self.add(["b", "ang"]) self.add(["b", "ao"]) self.add(["b", "ei"]) self.add(["b", "en"]) self.add(["b", "eng"]) self.add(["b", "i"]) self.add(["b", "ian"]) self.add(["b", "iao"]) self.add(["b", "ie"]) self.add(["b", "in"]) self.add(["b", "ing"]) self.add(["b", "o"]) self.add(["b", "u"]) self.add(["c", "a"]) self.add(["c", "ai"]) self.add(["c", "an"]) self.add(["c", "ang"]) self.add(["c", "ao"]) self.add(["c", "e"]) self.add(["c", "en"]) self.add(["c", "eng"]) self.add(["c", "i"]) self.add(["c", "ong"]) self.add(["c", "ou"]) self.add(["c", "u"]) self.add(["c", "uan"]) self.add(["c", "ui"]) self.add(["c", "un"]) self.add(["c", "uo"]) self.add(["ch", "a"]) self.add(["ch", "ai"]) self.add(["ch", "an"]) self.add(["ch", "ang"]) self.add(["ch", "ao"]) self.add(["ch", "e"]) self.add(["ch", "en"]) self.add(["ch", "eng"]) self.add(["ch", "i"]) self.add(["ch", "ong"]) self.add(["ch", "ou"]) self.add(["ch", "u"]) self.add(["ch", "uai"]) self.add(["ch", "uan"]) self.add(["ch", "uang"]) self.add(["ch", "ui"]) self.add(["ch", "un"]) self.add(["ch", "uo"]) self.add(["d", "a"]) self.add(["d", "ai"]) self.add(["d", "an"]) self.add(["d", "ang"]) self.add(["d", "ao"]) self.add(["d", "e"]) self.add(["d", "eng"]) self.add(["d", "i"]) self.add(["d", "ia"]) self.add(["d", "ian"]) self.add(["d", "iao"]) self.add(["d", "ie"]) self.add(["d", "ing"]) self.add(["d", "iu"]) self.add(["d", "ong"]) self.add(["d", "ou"]) self.add(["d", "u"]) self.add(["d", "uan"]) self.add(["d", "ui"]) self.add(["d", "un"]) self.add(["d", "uo"]) self.add(["f", "a"]) self.add(["f", "an"]) self.add(["f", "ang"]) self.add(["f", "ei"]) self.add(["f", "en"]) self.add(["f", "eng"]) self.add(["f", "o"]) self.add(["f", "ou"]) self.add(["f", "u"]) self.add(["g", "a"]) self.add(["g", "ai"]) self.add(["g", "an"]) self.add(["g", "ang"]) self.add(["g", "ao"]) self.add(["g", "e"]) self.add(["g", "ei"]) self.add(["g", "en"]) self.add(["g", "eng"]) self.add(["g", "ong"]) self.add(["g", "ou"]) self.add(["g", "u"]) self.add(["g", "ua"]) self.add(["g", "uai"]) self.add(["g", "uan"]) self.add(["g", "uang"]) self.add(["g", "ui"]) self.add(["g", "un"]) self.add(["g", "uo"]) self.add(["h", "a"]) self.add(["h", "ai"]) self.add(["h", "an"]) self.add(["h", "ang"]) self.add(["h", "ao"]) self.add(["h", "e"]) self.add(["h", "ei"]) self.add(["h", "en"]) self.add(["h", "eng"]) self.add(["h", "ong"]) self.add(["h", "ou"]) self.add(["h", "u"]) self.add(["h", "ua"]) self.add(["h", "uai"]) self.add(["h", "uan"]) self.add(["h", "uang"]) self.add(["h", "ui"]) self.add(["h", "un"]) self.add(["h", "uo"]) self.add(["j", "i"]) self.add(["j", "ia"]) self.add(["j", "ian"]) self.add(["j", "iang"]) self.add(["j", "iao"]) self.add(["j", "ie"]) self.add(["j", "in"]) self.add(["j", "ing"]) self.add(["j", "iong"]) self.add(["j", "iu"]) self.add(["j", "u"]) self.add(["j", "uan"]) self.add(["j", "ue"]) self.add(["j", "un"]) self.add(["k", "a"]) self.add(["k", "ai"]) self.add(["k", "an"]) self.add(["k", "ang"]) self.add(["k", "ao"]) self.add(["k", "e"]) self.add(["k", "en"]) self.add(["k", "eng"]) self.add(["k", "ong"]) self.add(["k", "ou"]) self.add(["k", "u"]) self.add(["k", "ua"]) self.add(["k", "uai"]) self.add(["k", "uan"]) self.add(["k", "uang"]) self.add(["k", "ui"]) self.add(["k", "un"]) self.add(["k", "uo"]) self.add(["l", "a"]) self.add(["l", "ai"]) self.add(["l", "an"]) self.add(["l", "ang"]) self.add(["l", "ao"]) self.add(["l", "e"]) self.add(["l", "ei"]) self.add(["l", "eng"]) self.add(["l", "i"]) self.add(["l", "ia"]) self.add(["l", "ian"]) self.add(["l", "iang"]) self.add(["l", "iao"]) self.add(["l", "ie"]) self.add(["l", "in"]) self.add(["l", "ing"]) self.add(["l", "iu"]) self.add(["l", "ong"]) self.add(["l", "ou"]) self.add(["l", "u"]) self.add(["l", "u:"]) self.add(["l", "u:e"]) self.add(["l", "uan"]) self.add(["l", "un"]) self.add(["l", "uo"]) self.add(["m", ""]) self.add(["m", "a"]) self.add(["m", "ai"]) self.add(["m", "an"]) self.add(["m", "ang"]) self.add(["m", "ao"]) self.add(["m", "e"]) self.add(["m", "ei"]) self.add(["m", "en"]) self.add(["m", "eng"]) self.add(["m", "i"]) self.add(["m", "ian"]) self.add(["m", "iao"]) self.add(["m", "ie"]) self.add(["m", "in"]) self.add(["m", "ing"]) self.add(["m", "iu"]) self.add(["m", "o"]) self.add(["m", "ou"]) self.add(["m", "u"]) self.add(["n", "a"]) self.add(["n", "ai"]) self.add(["n", "an"]) self.add(["n", "ang"]) self.add(["n", "ao"]) self.add(["n", "e"]) self.add(["n", "ei"]) self.add(["n", "en"]) self.add(["n", "eng"]) self.add(["n", "g"]) self.add(["n", "i"]) self.add(["n", "ian"]) self.add(["n", "iang"]) self.add(["n", "iao"]) self.add(["n", "ie"]) self.add(["n", "in"]) self.add(["n", "ing"]) self.add(["n", "iu"]) self.add(["n", "ong"]) self.add(["n", "ou"]) self.add(["n", "u"]) self.add(["n", "u:"]) self.add(["n", "u:e"]) self.add(["n", "uan"]) self.add(["n", "uo"]) self.add(["p", "a"]) self.add(["p", "ai"]) self.add(["p", "an"]) self.add(["p", "ang"]) self.add(["p", "ao"]) self.add(["p", "ei"]) self.add(["p", "en"]) self.add(["p", "eng"]) self.add(["p", "i"]) self.add(["p", "ian"]) self.add(["p", "iao"]) self.add(["p", "ie"]) self.add(["p", "in"]) self.add(["p", "ing"]) self.add(["p", "o"]) self.add(["p", "ou"]) self.add(["p", "u"]) self.add(["q", "i"]) self.add(["q", "ia"]) self.add(["q", "ian"]) self.add(["q", "iang"]) self.add(["q", "iao"]) self.add(["q", "ie"]) self.add(["q", "in"]) self.add(["q", "ing"]) self.add(["q", "iong"]) self.add(["q", "iu"]) self.add(["q", "u"]) self.add(["q", "uan"]) self.add(["q", "ue"]) self.add(["q", "un"]) self.add(["r", "an"]) self.add(["r", "ang"]) self.add(["r", "ao"]) self.add(["r", "e"]) self.add(["r", "en"]) self.add(["r", "eng"]) self.add(["r", "i"]) self.add(["r", "ong"]) self.add(["r", "ou"]) self.add(["r", "u"]) self.add(["r", "uan"]) self.add(["r", "ui"]) self.add(["r", "un"]) self.add(["r", "uo"]) self.add(["s", "a"]) self.add(["s", "ai"]) self.add(["s", "an"]) self.add(["s", "ang"]) self.add(["s", "ao"]) self.add(["s", "e"]) self.add(["s", "en"]) self.add(["s", "eng"]) self.add(["s", "i"]) self.add(["s", "ong"]) self.add(["s", "ou"]) self.add(["s", "u"]) self.add(["s", "uan"]) self.add(["s", "ui"]) self.add(["s", "un"]) self.add(["s", "uo"]) self.add(["sh", "a"]) self.add(["sh", "ai"]) self.add(["sh", "an"]) self.add(["sh", "ang"]) self.add(["sh", "ao"]) self.add(["sh", "e"]) self.add(["sh", "ei"]) self.add(["sh", "en"]) self.add(["sh", "eng"]) self.add(["sh", "i"]) self.add(["sh", "ou"]) self.add(["sh", "u"]) self.add(["sh", "ua"]) self.add(["sh", "uai"]) self.add(["sh", "uan"]) self.add(["sh", "uang"]) self.add(["sh", "ui"]) self.add(["sh", "un"]) self.add(["sh", "uo"]) self.add(["t", "a"]) self.add(["t", "ai"]) self.add(["t", "an"]) self.add(["t", "ang"]) self.add(["t", "ao"]) self.add(["t", "e"]) self.add(["t", "eng"]) self.add(["t", "i"]) self.add(["t", "ian"]) self.add(["t", "iao"]) self.add(["t", "ie"]) self.add(["t", "ing"]) self.add(["t", "ong"]) self.add(["t", "ou"]) self.add(["t", "u"]) self.add(["t", "uan"]) self.add(["t", "ui"]) self.add(["t", "un"]) self.add(["t", "uo"]) self.add(["w", "a"]) self.add(["w", "ai"]) self.add(["w", "an"]) self.add(["w", "ang"]) self.add(["w", "ei"]) self.add(["w", "en"]) self.add(["w", "eng"]) self.add(["w", "o"]) self.add(["w", "u"]) self.add(["x", "i"]) self.add(["x", "ia"]) self.add(["x", "ian"]) self.add(["x", "iang"]) self.add(["x", "iao"]) self.add(["x", "ie"]) self.add(["x", "in"]) self.add(["x", "ing"]) self.add(["x", "iong"]) self.add(["x", "iu"]) self.add(["x", "u"]) self.add(["x", "uan"]) self.add(["x", "ue"]) self.add(["x", "un"]) self.add(["y", "a"]) self.add(["y", "an"]) self.add(["y", "ang"]) self.add(["y", "ao"]) self.add(["y", "e"]) self.add(["y", "i"]) self.add(["y", "iao"]) self.add(["y", "in"]) self.add(["y", "ing"]) self.add(["y", "o"]) self.add(["y", "ong"]) self.add(["y", "ou"]) self.add(["y", "u"]) self.add(["y", "uan"]) self.add(["y", "ue"]) self.add(["y", "un"]) self.add(["z", "a"]) self.add(["z", "ai"]) self.add(["z", "an"]) self.add(["z", "ang"]) self.add(["z", "ao"]) self.add(["z", "e"]) self.add(["z", "ei"]) self.add(["z", "en"]) self.add(["z", "eng"]) self.add(["z", "i"]) self.add(["z", "ong"]) self.add(["z", "ou"]) self.add(["z", "u"]) self.add(["z", "uan"]) self.add(["z", "ui"]) self.add(["z", "un"]) self.add(["z", "uo"]) self.add(["zh", "a"]) self.add(["zh", "ai"]) self.add(["zh", "an"]) self.add(["zh", "ang"]) self.add(["zh", "ao"]) self.add(["zh", "e"]) self.add(["zh", "en"]) self.add(["zh", "eng"]) self.add(["zh", "i"]) self.add(["zh", "ong"]) self.add(["zh", "ou"]) self.add(["zh", "u"]) self.add(["zh", "ua"]) self.add(["zh", "uai"]) self.add(["zh", "uan"]) self.add(["zh", "uang"]) self.add(["zh", "ui"]) self.add(["zh", "un"]) self.add(["zh", "uo"]) def add(self, seq): self.root.add(seq) def scan(self, sent): words = [] while len(sent) > 0: buf, succ = self.root.find(sent) # print("buf: {}, succ: {}".format(buf, succ)) if succ: words.append(buf) sent = sent[len(buf):] else: words.append('invalid:' + sent[0]) sent = sent[1:] return words # 生成相应规则(基于组织) def results_list_A(): results_list_0 = [] results_list_A = [] # 例如: 江苏XX有限公司 if CompanyName: CompanyName_array1=pinyin(CompanyName, style=Style.NORMAL, strict=False) CompanyName_array2=pinyin(CompanyName, style=Style.FIRST_LETTER, strict=False) CompanyName_str1 = "" CompanyName_str2 = "" for tempvar in CompanyName_array1: temp_str1 = "".join(tempvar) CompanyName_str1 = CompanyName_str1 + temp_str1 for tempvar in CompanyName_array2: temp_str2 = "".join(tempvar) CompanyName_str2 = CompanyName_str2 + temp_str2 CompanyName_str3 = CompanyName_str2[0].upper()+CompanyName_str2[1:] results_list_0.append(CompanyName_str1) results_list_0.append(CompanyName_str2) results_list_0.append(CompanyName_str3) # jiangsuxxyouxiangongsi print("CompanyName_str1 : ",CompanyName_str1) # jsxxyxgs print("CompanyName_str2 : ",CompanyName_str2) # Jsxxyxgs print("CompanyName_str3 : ",CompanyName_str3) # jsxxyxgs + 后缀 f1 = open(filename, "r") for line in f1: results_list_A.append(CompanyName_str2+line.replace('\n', '').replace('\r', '')) f1.close() # 例如: 江苏XX if ShortCompanyName: ShortCompanyName_array1=pinyin(ShortCompanyName, style=Style.NORMAL, strict=False) ShortCompanyName_array2=pinyin(ShortCompanyName, style=Style.FIRST_LETTER, strict=False) ShortCompanyName_str1 = "" ShortCompanyName_str2 = "" for tempvar in ShortCompanyName_array1: temp_str3 = "".join(tempvar) ShortCompanyName_str1 = ShortCompanyName_str1 + temp_str3 for tempvar in ShortCompanyName_array2: temp_str4 = "".join(tempvar) ShortCompanyName_str2 = ShortCompanyName_str2 + temp_str4 ShortCompanyName_str3 = ShortCompanyName_str1[0].upper()+ShortCompanyName_str1[1:] ShortCompanyName_str4 = ShortCompanyName_str2[0].upper()+ShortCompanyName_str2[1:] ShortCompanyName_str5 = ShortCompanyName_str2.upper() results_list_0.append(ShortCompanyName_str1) results_list_0.append(ShortCompanyName_str2) results_list_0.append(ShortCompanyName_str3) results_list_0.append(ShortCompanyName_str4) results_list_0.append(ShortCompanyName_str5) # jiangsuxx print("ShortCompanyName_str1 : ",ShortCompanyName_str1) # jsxx print("ShortCompanyName_str2 : ",ShortCompanyName_str2) # Jiangsuxx print("ShortCompanyName_str3 : ",ShortCompanyName_str3) # Jsxx print("ShortCompanyName_str4 : ",ShortCompanyName_str4) # JSXX print("ShortCompanyName_str5 : ",ShortCompanyName_str5) # jiangsuxx + 后缀 f1 = open(filename, "r") for line in f1: results_list_A.append(ShortCompanyName_str1+line.replace('\n', '').replace('\r', '')) f1.close() # jsxx + 后缀 f1 = open(filename, "r") for line in f1: results_list_A.append(ShortCompanyName_str2+line.replace('\n', '').replace('\r', '')) f1.close() # Jsxx + 后缀 f1 = open(filename, "r") for line in f1: results_list_A.append(ShortCompanyName_str4+line.replace('\n', '').replace('\r', '')) f1.close() # JSXX + 后缀 f1 = open(filename, "r") for line in f1: results_list_A.append(ShortCompanyName_str5+line.replace('\n', '').replace('\r', '')) f1.close() # 例如: 智慧交通 if SystemName: SystemName_array1=pinyin(SystemName, style=Style.NORMAL, strict=False) SystemName_array2=pinyin(SystemName, style=Style.FIRST_LETTER, strict=False) SystemName_str1 = "" SystemName_str2 = "" for tempvar in SystemName_array1: temp_str5 = "".join(tempvar) SystemName_str1 = SystemName_str1 + temp_str5 for tempvar in SystemName_array2: temp_str6 = "".join(tempvar) SystemName_str2 = SystemName_str2 + temp_str6 SystemName_str3 = SystemName_str2[0].upper()+SystemName_str2[1:] SystemName_str4 = SystemName_str2.upper() results_list_0.append(SystemName_str1) results_list_0.append(SystemName_str2) results_list_0.append(SystemName_str3) results_list_0.append(SystemName_str4) # zhihuijiaotong print("SystemName_str1 : ",SystemName_str1) # zhjt print("SystemName_str2 : ",SystemName_str2) # Zhjt print("SystemName_str3 : ",SystemName_str3) # ZHJT print("SystemName_str4 : ",SystemName_str4) # zhjt + 后缀 f1 = open(filename, "r") for line in f1: results_list_A.append(SystemName_str2+line.replace('\n', '').replace('\r', '')) f1.close() # Zhjt + 后缀 f1 = open(filename, "r") for line in f1: results_list_A.append(SystemName_str3+line.replace('\n', '').replace('\r', '')) f1.close() # ZHJT + 后缀 f1 = open(filename, "r") for line in f1: results_list_A.append(SystemName_str4+line.replace('\n', '').replace('\r', '')) f1.close() # 输出至 output0.txt if len(results_list_0) > 1: f = open("output0.txt", "w") for x in results_list_0: f.write(x+"\n") f.close() print("基于组织的简写内容已生成至 output0.txt") # 输出至 output1.txt if len(results_list_A) > 1: f = open("output1.txt", "w") for x in results_list_A: f.write(x+"\n") f.close() print("基于组织的字典内容已生成至 output1.txt") print("\n") # 生成相应规则(基于人员) def results_list_B(): results_list_B = [] results_list_B2 = [] if PersonName: PersonName_array1=pinyin(PersonName, style=Style.NORMAL, strict=False) PersonName_array2=pinyin(PersonName, style=Style.FIRST_LETTER, strict=False) PersonName_B1 = "" PersonName_B2 = "" PersonName_B4 = "" PersonName_B5 = "" PersonName_B6 = "" PersonName_B7 = "" for tempvar in PersonName_array1: temp_str1 = "".join(tempvar) PersonName_B1 = PersonName_B1 + temp_str1 for tempvar in PersonName_array2: temp_str2 = "".join(tempvar) PersonName_B2 = PersonName_B2 + temp_str2 PersonName_B3 = "".join(PersonName_array1[0]) for tempvar in PersonName_array2[1:]: temp_str2 = "".join(tempvar) PersonName_B3 = PersonName_B3 + temp_str2 for tempvar in PersonName_array2[0:-1]: temp_str2 = "".join(tempvar) PersonName_B4 = PersonName_B4 + temp_str2 PersonName_B4 += "".join(PersonName_array1[-1]) for tempvar in PersonName_array1[1:]: temp_str2 = "".join(tempvar) PersonName_B5 = PersonName_B5 + temp_str2 PersonName_B5 += "".join(PersonName_array1[0]) for tempvar in PersonName_array1[1:]: temp_str2 = "".join(tempvar) PersonName_B6 = PersonName_B6 + temp_str2 PersonName_B6 += "".join(PersonName_array2[0]) for tempvar in PersonName_array2[1:]: temp_str2 = "".join(tempvar) PersonName_B7 = PersonName_B7 + temp_str2 PersonName_B7 += "".join(PersonName_array2[0]) results_list_B.append(PersonName_B1) results_list_B.append(PersonName_B2) results_list_B.append(PersonName_B3) results_list_B.append(PersonName_B4) results_list_B.append(PersonName_B5) results_list_B.append(PersonName_B6) results_list_B.append(PersonName_B7) results_list_B.append(PersonName) # zhangsanfeng print("PersonName_B1 : ",PersonName_B1) # zsf print("PersonName_B2 : ",PersonName_B2) # zhangsf print("PersonName_B3 : ",PersonName_B3) # zsfeng print("PersonName_B4 : ",PersonName_B4) # sanfengzhang print("PersonName_B5 : ",PersonName_B5) # sanfengz print("PersonName_B6 : ",PersonName_B6) # sfz print("PersonName_B7 : ",PersonName_B7) # 张三丰 print("PersonName_B8 : ",PersonName) # 输出至 output2.txt if len(results_list_B) > 1: f = open("output2.txt", "w") for x in results_list_B: f.write(x+"\n") f.close() print("基于人员的字典规则已生成至 output2.txt") f1 = open("output2.txt", "r") for line1 in f1: f2 = open(filename, "r") for line2 in f2: results_list_B2.append(line1.replace('\n', '').replace('\r', '') + line2.replace('\n', '').replace('\r', '')) #print(line1.replace('\n', '').replace('\r', '') + line2.replace('\n', '').replace('\r', '')) f2.close() f1.close() # 输出至 output3.txt if len(results_list_B2) > 1: f = open("output3.txt", "w") for x in results_list_B2: f.write(x+"\n") f.close() print("基于用户的字典内容已生成至 output3.txt") print("\n") # 生成相应规则(基于人员拼音) def results_list_C(): results_list_C = [] results_list_C2 = [] if PersonName: pyt = PyTrie() pyt.setup() PersonName_array3 = pyt.scan(PersonName) PersonName_C1 = "" PersonName_C2 = "" PersonName_C4 = "" PersonName_C5 = "" PersonName_C6 = "" PersonName_C7 = "" for tempvar in PersonName_array3: temp_str1 = "".join(tempvar) PersonName_C1 = PersonName_C1 + temp_str1 for tempvar in PersonName_array3: temp_str2 = "".join(tempvar)[0] PersonName_C2 = PersonName_C2 + temp_str2 PersonName_C3 = "".join(PersonName_array3[0]) for tempvar in PersonName_array3[1:]: temp_str3 = "".join(tempvar)[0] PersonName_C3 = PersonName_C3 + temp_str3 for tempvar in PersonName_array3[0:-1]: temp_str3 = "".join(tempvar)[0] PersonName_C4 = PersonName_C4 + temp_str3 PersonName_C4 += "".join(PersonName_array3[-1]) for tempvar in PersonName_array3[1:]: temp_str2 = "".join(tempvar) PersonName_C5 = PersonName_C5 + temp_str2 PersonName_C5 += "".join(PersonName_array3[0]) for tempvar in PersonName_array3[1:]: temp_str2 = "".join(tempvar) PersonName_C6 = PersonName_C6 + temp_str2 PersonName_C6 += "".join(PersonName_array3[0][0]) for tempvar in PersonName_array3[1:]: temp_str2 = "".join(tempvar)[0] PersonName_C7 = PersonName_C7 + temp_str2 PersonName_C7 += "".join(PersonName_array3[0][0]) results_list_C.append(PersonName_C1) results_list_C.append(PersonName_C2) results_list_C.append(PersonName_C3) results_list_C.append(PersonName_C4) results_list_C.append(PersonName_C5) results_list_C.append(PersonName_C6) results_list_C.append(PersonName_C7) # zhangsanfeng print("PersonName_C1 : ",PersonName_C1) # zsf print("PersonName_C2 : ",PersonName_C2) # zhangsf print("PersonName_C3 : ",PersonName_C3) # zsfeng print("PersonName_C4 : ",PersonName_C4) # sanfengzhang print("PersonName_C5 : ",PersonName_C5) # sanfengz print("PersonName_C6 : ",PersonName_C6) # sfz print("PersonName_C7 : ",PersonName_C7) # 输出至 output2.txt if len(results_list_C) > 1: f = open("output2.txt", "w") for x in results_list_C: f.write(x+"\n") f.close() print("基于人员的字典内容已生成至 output2.txt") f1 = open("output2.txt", "r") for line1 in f1: f2 = open(filename, "r") for line2 in f2: results_list_C2.append(line1.replace('\n', '').replace('\r', '') + line2.replace('\n', '').replace('\r', '')) #print(line1.replace('\n', '').replace('\r', '') + line2.replace('\n', '').replace('\r', '')) f2.close() f1.close() # 输出至 output3.txt if len(results_list_C2) > 1: f = open("output3.txt", "w") for x in results_list_C2: f.write(x+"\n") f.close() print("基于用户的字典内容已生成至 output3.txt") print("\n") # 生成相应规则(基于地点) def results_list_D(): results_list_D = [] # print("省份名称: " + ProvinceName) # print("城市名称: " + CityName) # print("区县名称: " + DistrictName) def main(): global CompanyName global ShortCompanyName global SystemName global StreetName global PersonName global PersonPhoneNumber global PersonEmail #global ProvinceName #global CityName #global DistrictName CompanyName = input("公司/单位/组织全称 (例如: 江苏XX有限公司):").lower() ShortCompanyName = input("公司/单位/组织简称 (例如: 江苏XX):").lower() SystemName = input("系统/业务简称 (例如: 智慧交通):").lower() PersonName = input("人员名称 (例如: 申田由甲):").lower() #PhoneNumber = input("电话号码(例如:13333333333 可为空): ").lower() #Email = input("电子邮箱(例如:test@163.com 可为空): ").lower() #ProvinceName = input("省份名称(例如:江苏 ,可为空): ").lower() #CityName = input("城市名称(例如:南京 ,可为空): ").lower() #DistrictName = input("区县名称(例如:江宁 ,可为空): ").lower() print("\n") results_list_A() if is_all_chinese(PersonName): results_list_B() else: results_list_C() if __name__ == '__main__': main() ================================================ FILE: suffix.txt ================================================ 123 1234 123456 12345 888 666 2022 2021 2020 2019 2018 2017 @123 @1234 @123456 @12345 @888 @666 @2022 @2021 @2020 @2019 @2018 @2017 #123 #1234 #123456 #12345 #888 #666 #2022 #2021 #2020 #2019 #2018 #2017 _123 _1234 _123456 _12345 _888 _666 _2022 _2021 _2020 _2019 _2018 _2017 !@# !@#$ ~!@