{"id":47944186,"url":"https://github.com/dataiku/dss-plugin-nlp-preparation","last_synced_at":"2026-04-04T08:20:44.895Z","repository":{"id":49399585,"uuid":"240504039","full_name":"dataiku/dss-plugin-nlp-preparation","owner":"dataiku","description":"Dataiku DSS plugin to detect languages, correct misspellings, and clean text data 🧼","archived":false,"fork":false,"pushed_at":"2026-01-28T13:49:32.000Z","size":18823,"stargazers_count":22,"open_issues_count":3,"forks_count":6,"subscribers_count":20,"default_branch":"main","last_synced_at":"2026-01-29T00:02:05.322Z","etag":null,"topics":["auto-correct","dataiku","dss-plugin","language-detection","language-identification","natural-language-processing","nlp","spell-checker","text-cleaning"],"latest_commit_sha":null,"homepage":"https://www.dataiku.com/product/plugins/nlp-preparation/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/dataiku.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2020-02-14T12:32:28.000Z","updated_at":"2025-02-12T23:10:26.000Z","dependencies_parsed_at":"2024-05-03T21:42:05.295Z","dependency_job_id":null,"html_url":"https://github.com/dataiku/dss-plugin-nlp-preparation","commit_stats":null,"previous_names":[],"tags_count":9,"template":false,"template_full_name":null,"purl":"pkg:github/dataiku/dss-plugin-nlp-preparation","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dataiku%2Fdss-plugin-nlp-preparation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dataiku%2Fdss-plugin-nlp-preparation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dataiku%2Fdss-plugin-nlp-preparation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dataiku%2Fdss-plugin-nlp-preparation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dataiku","download_url":"https://codeload.github.com/dataiku/dss-plugin-nlp-preparation/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dataiku%2Fdss-plugin-nlp-preparation/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31392728,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-04T04:26:24.776Z","status":"ssl_error","status_checked_at":"2026-04-04T04:23:34.147Z","response_time":60,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["auto-correct","dataiku","dss-plugin","language-detection","language-identification","natural-language-processing","nlp","spell-checker","text-cleaning"],"created_at":"2026-04-04T08:20:44.386Z","updated_at":"2026-04-04T08:20:44.888Z","avatar_url":"https://github.com/dataiku.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Text Preparation Plugin\n\n![Build status](https://github.com/dataiku/dss-plugin-nlp-preparation/actions/workflows/auto-make.yml/badge.svg) ![GitHub release (latest by date)](https://img.shields.io/github/v/release/dataiku/dss-plugin-nlp-preparation?logo=github)\n ![Support level](https://img.shields.io/badge/support-Tier%202-yellowgreen)\n\nThis Dataiku DSS plugin provides recipes to detect languages, correct misspellings and clean text data.\n\nDocumentation: https://www.dataiku.com/product/plugins/nlp-preparation/\n\n## Release notes\n\nSee the [changelog](CHANGELOG.md) for a history of notable changes to this plugin.\n\n## License\n\nThis plugin is distributed under the [Apache License version 2.0](LICENSE).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdataiku%2Fdss-plugin-nlp-preparation","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdataiku%2Fdss-plugin-nlp-preparation","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdataiku%2Fdss-plugin-nlp-preparation/lists"}