{"id":20114837,"url":"https://github.com/gatenlp/gateplugin-documentnormalizer","last_synced_at":"2026-06-20T04:31:38.548Z","repository":{"id":57743541,"uuid":"95569141","full_name":"GateNLP/gateplugin-DocumentNormalizer","owner":"GateNLP","description":"Tools for normalizing documents before processing","archived":false,"fork":false,"pushed_at":"2023-02-10T12:00:13.000Z","size":16,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":14,"default_branch":"master","last_synced_at":"2025-01-13T06:11:03.247Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Java","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"lgpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/GateNLP.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"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}},"created_at":"2017-06-27T14:47:23.000Z","updated_at":"2023-01-24T12:25:25.000Z","dependencies_parsed_at":"2023-02-13T21:17:01.291Z","dependency_job_id":null,"html_url":"https://github.com/GateNLP/gateplugin-DocumentNormalizer","commit_stats":null,"previous_names":[],"tags_count":2,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GateNLP%2Fgateplugin-DocumentNormalizer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GateNLP%2Fgateplugin-DocumentNormalizer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GateNLP%2Fgateplugin-DocumentNormalizer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GateNLP%2Fgateplugin-DocumentNormalizer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/GateNLP","download_url":"https://codeload.github.com/GateNLP/gateplugin-DocumentNormalizer/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":241557194,"owners_count":19981881,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":[],"created_at":"2024-11-13T18:32:18.024Z","updated_at":"2025-11-29T05:04:41.068Z","avatar_url":"https://github.com/GateNLP.png","language":"Java","funding_links":[],"categories":[],"sub_categories":[],"readme":"A simple PR to allow for basic document normalization. Should usually be run as\nthe first PR in a pipeline after Document Reset. The PR edits the document\ncontent and so once it has been run over a document once, future executions\nwill have no effect although will require processing time.\n\nThe PR works from a file of replacements. Essentially this file consists of\npairs of lines. The first line specifics the text to replace, while the second\nline signifies what will be substituted in its place. The first line can be a\nregular expression, but back references cannot be used within the second line.\n\nThe most common use for this PR is to normalise punctuation symbols as WYSIWYG\neditors often automatically replace standard apostrophe and hyphen symbols with\nmore fancy versions. This makes processing text difficult as gazetteer lists,\nJAPE grammars and other resources usually assume the use of the standard\nsymbols, i.e. the ones on the keyboard. The default config file is aimed at\nnormalizing such cases.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgatenlp%2Fgateplugin-documentnormalizer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgatenlp%2Fgateplugin-documentnormalizer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgatenlp%2Fgateplugin-documentnormalizer/lists"}