├── .gitignore ├── LICENSE ├── README.md ├── bun.lockb ├── index.ts ├── package.json └── tsconfig.json /.gitignore: -------------------------------------------------------------------------------- 1 | # Based on https://raw.githubusercontent.com/github/gitignore/main/Node.gitignore 2 | releases 3 | 4 | # Logs 5 | 6 | logs 7 | _.log 8 | npm-debug.log_ 9 | yarn-debug.log* 10 | yarn-error.log* 11 | lerna-debug.log* 12 | .pnpm-debug.log* 13 | 14 | # Caches 15 | 16 | .cache 17 | 18 | # Diagnostic reports (https://nodejs.org/api/report.html) 19 | 20 | report.[0-9]_.[0-9]_.[0-9]_.[0-9]_.json 21 | 22 | # Runtime data 23 | 24 | pids 25 | _.pid 26 | _.seed 27 | *.pid.lock 28 | 29 | # Directory for instrumented libs generated by jscoverage/JSCover 30 | 31 | lib-cov 32 | 33 | # Coverage directory used by tools like istanbul 34 | 35 | coverage 36 | *.lcov 37 | 38 | # nyc test coverage 39 | 40 | .nyc_output 41 | 42 | # Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files) 43 | 44 | .grunt 45 | 46 | # Bower dependency directory (https://bower.io/) 47 | 48 | bower_components 49 | 50 | # node-waf configuration 51 | 52 | .lock-wscript 53 | 54 | # Compiled binary addons (https://nodejs.org/api/addons.html) 55 | 56 | build/Release 57 | 58 | # Dependency directories 59 | 60 | node_modules/ 61 | jspm_packages/ 62 | 63 | # Snowpack dependency directory (https://snowpack.dev/) 64 | 65 | web_modules/ 66 | 67 | # TypeScript cache 68 | 69 | *.tsbuildinfo 70 | 71 | # Optional npm cache directory 72 | 73 | .npm 74 | 75 | # Optional eslint cache 76 | 77 | .eslintcache 78 | 79 | # Optional stylelint cache 80 | 81 | .stylelintcache 82 | 83 | # Microbundle cache 84 | 85 | .rpt2_cache/ 86 | .rts2_cache_cjs/ 87 | .rts2_cache_es/ 88 | .rts2_cache_umd/ 89 | 90 | # Optional REPL history 91 | 92 | .node_repl_history 93 | 94 | # Output of 'npm pack' 95 | 96 | *.tgz 97 | 98 | # Yarn Integrity file 99 | 100 | .yarn-integrity 101 | 102 | # dotenv environment variable files 103 | 104 | .env 105 | .env.development.local 106 | .env.test.local 107 | .env.production.local 108 | .env.local 109 | 110 | # parcel-bundler cache (https://parceljs.org/) 111 | 112 | .parcel-cache 113 | 114 | # Next.js build output 115 | 116 | .next 117 | out 118 | 119 | # Nuxt.js build / generate output 120 | 121 | .nuxt 122 | dist 123 | 124 | # Gatsby files 125 | 126 | # Comment in the public line in if your project uses Gatsby and not Next.js 127 | 128 | # https://nextjs.org/blog/next-9-1#public-directory-support 129 | 130 | # public 131 | 132 | # vuepress build output 133 | 134 | .vuepress/dist 135 | 136 | # vuepress v2.x temp and cache directory 137 | 138 | .temp 139 | 140 | # Docusaurus cache and generated files 141 | 142 | .docusaurus 143 | 144 | # Serverless directories 145 | 146 | .serverless/ 147 | 148 | # FuseBox cache 149 | 150 | .fusebox/ 151 | 152 | # DynamoDB Local files 153 | 154 | .dynamodb/ 155 | 156 | # TernJS port file 157 | 158 | .tern-port 159 | 160 | # Stores VSCode versions used for testing VSCode extensions 161 | 162 | .vscode-test 163 | 164 | # yarn v2 165 | 166 | .yarn/cache 167 | .yarn/unplugged 168 | .yarn/build-state.yml 169 | .yarn/install-state.gz 170 | .pnp.* 171 | 172 | # IntelliJ based IDEs 173 | .idea 174 | 175 | # Finder (MacOS) folder config 176 | .DS_Store 177 | -------------------------------------------------------------------------------- /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 2024 Shoubhit Dash 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 | # text2regex 2 | 3 | generate regular expressions validated against a thorough test suite 4 | 5 | 6 | https://github.com/nexxeln/text2regex/assets/95541290/d7cb782d-5f72-4641-a63c-93ef30ab451d 7 | 8 | 9 | ## usage 10 | 11 | ```sh 12 | text2regex "match three consecutive odd digits" 13 | ``` 14 | 15 | ## working 16 | 17 | llm generates tests, writes regex, iterates based on test feedback until it passes 18 | -------------------------------------------------------------------------------- /bun.lockb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nexxeln/text2regex/b076ccb7f7228352abef783a82882345335799a6/bun.lockb -------------------------------------------------------------------------------- /index.ts: -------------------------------------------------------------------------------- 1 | import fs from "node:fs"; 2 | import { z } from "zod"; 3 | import { generateText, tool } from "ai"; 4 | import { createOpenAI } from "@ai-sdk/openai"; 5 | import { $ } from "bun"; 6 | 7 | if (!process.env.OPENAI_API_KEY) { 8 | throw new Error("OPENAI_API_KEY is required"); 9 | } 10 | 11 | const openai = createOpenAI({ 12 | apiKey: process.env.OPENAI_API_KEY, 13 | }); 14 | 15 | const generateTestCases = async (prompt: string): Promise => { 16 | const result = await generateText({ 17 | model: openai("gpt-4o"), 18 | tools: { 19 | createFile: tool({ 20 | description: "Create a file", 21 | parameters: z.object({ 22 | code: z.string().describe("The code to write to the file"), 23 | }), 24 | execute: async ({ code }) => { 25 | fs.writeFileSync("regex_test.py", code); 26 | }, 27 | }), 28 | }, 29 | system: `You are an expert designed to generate a complete Python test program for regular expressions based on natural language descriptions. Your task is to create a comprehensive set of test cases and the surrounding test program structure, leaving a placeholder for the actual regex pattern. 30 | 31 | When presented with a user's description of a desired regex pattern, follow these guidelines: 32 | 33 | 1. Create at least 5 positive test cases (strings that should match the pattern). 34 | 2. Create at least 5 negative test cases (strings that should not match the pattern). 35 | 3. Include edge cases and boundary conditions in your test cases. 36 | 4. Consider common mistakes or misunderstandings that might occur when implementing the regex. 37 | 5. Provide a brief explanation for each test case as a comment. 38 | 39 | Your output should be a complete Python script using the \`unittest\` framework, structured as follows: 40 | 41 | \`\`\`python 42 | import unittest 43 | import re 44 | 45 | class RegexTest(unittest.TestCase): 46 | def setUp(self): 47 | # The actual regex pattern will be replaced here 48 | self.regex_pattern = r"YOUR_REGEX_PATTERN_HERE" 49 | self.pattern = re.compile(self.regex_pattern) 50 | 51 | def test_positive_cases(self): 52 | positive_cases = [ 53 | ("test_string1", "explanation for why this should match"), 54 | ("test_string2", "explanation for why this should match"), 55 | # Add more positive test cases here 56 | ] 57 | for test_string, explanation in positive_cases: 58 | with self.subTest(test_string=test_string): 59 | self.assertTrue(self.pattern.match(test_string), f"Should match: {explanation}") 60 | 61 | def test_negative_cases(self): 62 | negative_cases = [ 63 | ("test_string1", "explanation for why this should not match"), 64 | ("test_string2", "explanation for why this should not match"), 65 | # Add more negative test cases here 66 | ] 67 | for test_string, explanation in negative_cases: 68 | with self.subTest(test_string=test_string): 69 | self.assertFalse(self.pattern.match(test_string), f"Should not match: {explanation}") 70 | 71 | if __name__ == '__main__': 72 | unittest.main() 73 | \`\`\` 74 | 75 | Remember: 76 | - Be thorough and creative in your test case generation. 77 | - Ensure your test cases cover a wide range of possibilities. 78 | - Keep in mind the specific requirements mentioned in the user's description. 79 | - If the user's description is ambiguous, generate test cases for multiple interpretations and note the ambiguity. 80 | - Ensure all test cases are valid Python strings. 81 | - Do not implement the actual regex pattern; use the placeholder "YOUR_REGEX_PATTERN_HERE". 82 | - Output the code in a file named "regex_test.py". Use the createFile tool provided to you to create the file.`, 83 | 84 | prompt: `Generate test cases for the following prompt: ${prompt}`, 85 | }); 86 | 87 | return result.text; 88 | }; 89 | 90 | const generateRegex = async ( 91 | userPrompt: string, 92 | testCases: string, 93 | testResults: string 94 | ): Promise => { 95 | const result = await generateText({ 96 | model: openai("gpt-4o"), 97 | prompt: `Based on the following user prompt and Python test cases, generate a regex pattern that matches all positive cases and none of the negative cases. If any tests failed, use the provided test results to refine the pattern: 98 | 99 | User Prompt: ${userPrompt} 100 | 101 | \`\`\`python 102 | ${testCases} 103 | \`\`\` 104 | 105 | Test Results: 106 | ${testResults} 107 | 108 | Your response should be the regex pattern only, without any additional text. Don't include it in a code block, just the pattern.`, 109 | }); 110 | 111 | return result.text.trim(); 112 | }; 113 | 114 | const runTests = async (): Promise => { 115 | try { 116 | const result = await $`python3 regex_test.py`.text(); 117 | return result; 118 | } catch (err: any) { 119 | return err.stderr.toString(); 120 | } 121 | }; 122 | 123 | const updateRegexPattern = (filePath: string, newPattern: string): void => { 124 | let content = fs.readFileSync(filePath, "utf-8"); 125 | const regex = /self\.regex_pattern\s*=\s*r".*"/; 126 | content = content.replace(regex, `self.regex_pattern = r"${newPattern}"`); 127 | fs.writeFileSync(filePath, content, "utf-8"); 128 | }; 129 | 130 | const userPrompt = process.argv[2]; 131 | console.log("Generating tests"); 132 | const testCases = await generateTestCases(userPrompt); 133 | 134 | let attempts = 0; 135 | const maxAttempts = 10; 136 | let success = false; 137 | 138 | while (attempts < maxAttempts && !success) { 139 | attempts += 1; 140 | let testResults = "This is the initial try, so no test results yet."; 141 | 142 | if (attempts > 1) { 143 | testResults = await runTests(); 144 | } 145 | 146 | const regexPattern = await generateRegex(userPrompt, testCases, testResults); 147 | 148 | updateRegexPattern("regex_test.py", regexPattern); 149 | 150 | const newTestResults = await runTests(); 151 | success = !newTestResults.includes("FAILED"); 152 | console.log(`Attempt ${attempts}: ${success ? "Success" : "Failed"}`); 153 | console.log(`Test Results: ${newTestResults}`); 154 | 155 | if (success) { 156 | console.log("Successfully generated regex pattern:", regexPattern); 157 | } 158 | } 159 | 160 | if (!success) { 161 | console.log( 162 | "Failed to generate a working regex pattern within the maximum number of attempts." 163 | ); 164 | } 165 | 166 | // Delete the python file after the program ends 167 | fs.unlinkSync("regex_test.py"); 168 | -------------------------------------------------------------------------------- /package.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "text2regex", 3 | "module": "index.ts", 4 | "type": "module", 5 | "devDependencies": { 6 | "@types/bun": "latest" 7 | }, 8 | "peerDependencies": { 9 | "typescript": "^5.0.0" 10 | }, 11 | "dependencies": { 12 | "@ai-sdk/openai": "^0.0.36", 13 | "ai": "^3.2.19", 14 | "execa": "^9.3.0", 15 | "zod": "^3.23.8" 16 | } 17 | } -------------------------------------------------------------------------------- /tsconfig.json: -------------------------------------------------------------------------------- 1 | { 2 | "compilerOptions": { 3 | // Enable latest features 4 | "lib": ["ESNext", "DOM"], 5 | "target": "ESNext", 6 | "module": "ESNext", 7 | "moduleDetection": "force", 8 | "jsx": "react-jsx", 9 | "allowJs": true, 10 | 11 | // Bundler mode 12 | "moduleResolution": "bundler", 13 | "allowImportingTsExtensions": true, 14 | "verbatimModuleSyntax": true, 15 | "noEmit": true, 16 | 17 | // Best practices 18 | "strict": true, 19 | "skipLibCheck": true, 20 | "noFallthroughCasesInSwitch": true, 21 | 22 | // Some stricter flags (disabled by default) 23 | "noUnusedLocals": false, 24 | "noUnusedParameters": false, 25 | "noPropertyAccessFromIndexSignature": false 26 | } 27 | } 28 | --------------------------------------------------------------------------------