{
  "_id": "6a103697acfb0bcc41c9a0c7",
  "Package": "NLP",
  "Version": "0.3-2",
  "Title": "Natural Language Processing Infrastructure",
  "Authors@R": "person(\"Kurt\", \"Hornik\", role = c(\"aut\", \"cre\"),\nemail = \"Kurt.Hornik@R-project.org\",\ncomment = c(ORCID = \"0000-0003-4198-9911\"))",
  "Description": "Basic classes and methods for Natural Language Processing.",
  "License": "GPL-3",
  "Encoding": "UTF-8",
  "NeedsCompilation": "no",
  "Packaged": {
    "Date": "2026-05-12 06:44:14 UTC",
    "User": "root"
  },
  "Author": "Kurt Hornik [aut, cre]\n(<https://orcid.org/0000-0003-4198-9911>)",
  "Maintainer": "Kurt Hornik <Kurt.Hornik@R-project.org>",
  "Repository": "https://kurthornik.r-universe.dev",
  "Date/Publication": "2024-11-20 08:04:45 UTC",
  "RemoteUrl": "https://github.com/cran/NLP",
  "RemoteRef": "HEAD",
  "RemoteSha": "486a6532266a3564e4edb847ce1eab03f19a38e1",
  "MD5sum": "775a68e9b67004ee0438a6c0b7247e8a",
  "_user": "kurthornik",
  "_type": "src",
  "_file": "NLP_0.3-2.tar.gz",
  "_fileid": "6773e164ab4af64e6e8aba323338fc70f2c90c71ca0322e052921a74eb8a0a78",
  "_filesize": 363406,
  "_sha256": "6773e164ab4af64e6e8aba323338fc70f2c90c71ca0322e052921a74eb8a0a78",
  "_created": "2026-05-12T06:44:14.000Z",
  "_published": "2026-05-22T10:57:27.296Z",
  "_distro": "noble",
  "_jobs": [
    {
      "job": 77365965581,
      "time": 109,
      "config": "linux-devel-x86_64",
      "r": "4.7.0",
      "check": "OK",
      "artifact": "6937445957"
    },
    {
      "job": 77365965920,
      "time": 102,
      "config": "linux-release-x86_64",
      "r": "4.6.0",
      "check": "OK",
      "artifact": "6937446007"
    },
    {
      "job": 77365965661,
      "time": 84,
      "config": "macos-oldrel-arm64",
      "r": "4.5.3",
      "check": "OK",
      "artifact": "6937439316"
    },
    {
      "job": 77365965615,
      "time": 118,
      "config": "macos-release-arm64",
      "r": "4.6.0",
      "check": "OK",
      "artifact": "6937447963"
    },
    {
      "job": 77365965236,
      "time": 148,
      "config": "source",
      "r": "4.6.0",
      "check": "OK",
      "artifact": "6937418117"
    },
    {
      "job": 77365965254,
      "time": 89,
      "config": "wasm-release",
      "r": "4.6.0",
      "check": "OK",
      "artifact": "7158841212"
    },
    {
      "job": 77365965548,
      "time": 82,
      "config": "windows-devel",
      "r": "4.7.0",
      "check": "OK",
      "artifact": "6937438948"
    },
    {
      "job": 77365966245,
      "time": 66,
      "config": "windows-oldrel",
      "r": "4.5.3",
      "check": "OK",
      "artifact": "6937435335"
    },
    {
      "job": 77365965634,
      "time": 71,
      "config": "windows-release",
      "r": "4.6.0",
      "check": "OK",
      "artifact": "6937436294"
    }
  ],
  "_buildurl": "https://github.com/r-universe/kurthornik/actions/runs/25718069023",
  "_status": "success",
  "_host": "GitHub-Actions",
  "_upstream": "https://github.com/cran/NLP",
  "_commit": {
    "id": "486a6532266a3564e4edb847ce1eab03f19a38e1",
    "author": "Kurt Hornik <Kurt.Hornik@R-project.org>",
    "committer": "cran-robot <csardi.gabor+cran@gmail.com>",
    "message": "version 0.3-2\n",
    "time": 1732089885
  },
  "_maintainer": {
    "name": "Kurt Hornik",
    "email": "kurt.hornik@r-project.org",
    "login": "kurthornik",
    "orcid": "0000-0003-4198-9911",
    "uuid": 124706059
  },
  "_registered": true,
  "_dependencies": [
    {
      "package": "R",
      "version": ">= 3.5.0",
      "role": "Depends"
    },
    {
      "package": "utils",
      "role": "Imports"
    },
    {
      "package": "udpipe",
      "role": "Enhances"
    },
    {
      "package": "spacyr",
      "role": "Enhances"
    },
    {
      "package": "cleanNLP",
      "role": "Enhances"
    }
  ],
  "_owner": "cran",
  "_selfowned": true,
  "_usedby": 123,
  "_updates": [],
  "_tags": [],
  "_stars": 6,
  "_contributors": [
    {
      "user": "kurthornik",
      "count": 17,
      "uuid": 124706059
    }
  ],
  "_userbio": {
    "uuid": 124706059,
    "type": "user",
    "name": "Kurt Hornik"
  },
  "_downloads": {
    "count": 36453,
    "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/NLP"
  },
  "_mentions": 43,
  "_searchresults": 1230,
  "_rbuild": "4.6.0",
  "_assets": [
    "extra/citation.cff",
    "extra/citation.html",
    "extra/citation.json",
    "extra/citation.txt",
    "extra/contents.json",
    "extra/NLP.html",
    "manual.pdf"
  ],
  "_realowner": "kurthornik",
  "_cranurl": false,
  "_releases": [
    {
      "version": "0.1-0",
      "date": "2013-08-17"
    },
    {
      "version": "0.1-1",
      "date": "2014-01-25"
    },
    {
      "version": "0.1-2",
      "date": "2014-04-19"
    },
    {
      "version": "0.1-3",
      "date": "2014-06-11"
    },
    {
      "version": "0.1-4",
      "date": "2014-08-17"
    },
    {
      "version": "0.1-5",
      "date": "2014-08-23"
    },
    {
      "version": "0.1-6",
      "date": "2015-01-24"
    },
    {
      "version": "0.1-7",
      "date": "2015-05-06"
    },
    {
      "version": "0.1-8",
      "date": "2015-07-03"
    },
    {
      "version": "0.1-9",
      "date": "2016-02-18"
    },
    {
      "version": "0.1-10",
      "date": "2017-02-21"
    },
    {
      "version": "0.1-11",
      "date": "2017-08-15"
    },
    {
      "version": "0.2-0",
      "date": "2018-10-18"
    },
    {
      "version": "0.2-1",
      "date": "2020-10-14"
    },
    {
      "version": "0.3-0",
      "date": "2024-08-05"
    },
    {
      "version": "0.3-1",
      "date": "2024-11-14"
    },
    {
      "version": "0.3-2",
      "date": "2024-11-20"
    }
  ],
  "_exports": [
    "annotate",
    "AnnotatedPlainTextDocument",
    "annotation",
    "Annotation",
    "annotations_in_spans",
    "Annotator",
    "Annotator_Pipeline",
    "as.Annotation",
    "as.Annotator_Pipeline",
    "as.Span",
    "as.Span_Tokenizer",
    "as.String",
    "as.Tagged_Token",
    "as.Token_Tokenizer",
    "blankline_tokenizer",
    "Brown_POS_tags",
    "chunked_sents",
    "CoNLLTextDocument",
    "CoNLLUTextDocument",
    "content",
    "content<-",
    "features",
    "is.Annotation",
    "is.Span",
    "is.Span_Tokenizer",
    "is.String",
    "is.Tagged_Token",
    "is.Token_Tokenizer",
    "meta",
    "meta<-",
    "next_id",
    "ngrams",
    "otoks",
    "paras",
    "parse_IETF_language_tag",
    "parse_ISO_8601_datetime",
    "parsed_paras",
    "parsed_sents",
    "Penn_Treebank_POS_tags",
    "Regexp_Tokenizer",
    "sents",
    "Simple_Chunk_Annotator",
    "Simple_Entity_Annotator",
    "Simple_Para_Token_Annotator",
    "Simple_POS_Tag_Annotator",
    "Simple_Sent_Token_Annotator",
    "Simple_Stem_Annotator",
    "Simple_Word_Token_Annotator",
    "single_feature",
    "Span",
    "Span_Tokenizer",
    "String",
    "tagged_paras",
    "tagged_sents",
    "Tagged_Token",
    "tagged_words",
    "TaggedTextDocument",
    "Token_Tokenizer",
    "Tree",
    "Tree_apply",
    "Tree_parse",
    "Universal_POS_tags",
    "Universal_POS_tags_map",
    "whitespace_tokenizer",
    "WordListDocument",
    "wordpunct_tokenizer",
    "words"
  ],
  "_help": [
    {
      "page": "annotate",
      "title": "Annotate text strings",
      "topics": [
        "annotate"
      ]
    },
    {
      "page": "AnnotatedPlainTextDocument",
      "title": "Annotated Plain Text Documents",
      "topics": [
        "AnnotatedPlainTextDocument",
        "annotation"
      ]
    },
    {
      "page": "Annotation",
      "title": "Annotation objects",
      "topics": [
        "$<-.Annotation",
        "Annotation",
        "as.Annotation",
        "as.Annotation.Span",
        "as.data.frame.Annotation",
        "as.list.Annotation",
        "c.Annotation",
        "duplicated.Annotation",
        "format.Annotation",
        "is.Annotation",
        "length.Annotation",
        "merge.Annotation",
        "meta.Annotation",
        "meta<-.Annotation",
        "names.Annotation",
        "print.Annotation",
        "subset.Annotation",
        "unique.Annotation",
        "[.Annotation",
        "[[.Annotation"
      ]
    },
    {
      "page": "annotations_in_spans",
      "title": "Annotations contained in character spans",
      "topics": [
        "annotations_in_spans"
      ]
    },
    {
      "page": "Annotator",
      "title": "Annotator (pipeline) objects",
      "topics": [
        "Annotator",
        "Annotator_Pipeline",
        "as.Annotator_Pipeline"
      ]
    },
    {
      "page": "annotators",
      "title": "Simple annotator generators",
      "topics": [
        "Simple annotator generators",
        "Simple_Chunk_Annotator",
        "Simple_Entity_Annotator",
        "Simple_Para_Token_Annotator",
        "Simple_POS_Tag_Annotator",
        "Simple_Sent_Token_Annotator",
        "Simple_Stem_Annotator",
        "Simple_Word_Token_Annotator"
      ]
    },
    {
      "page": "CoNLLTextDocument",
      "title": "CoNLL-Style Text Documents",
      "topics": [
        "CoNLLTextDocument"
      ]
    },
    {
      "page": "CoNLLUTextDocument",
      "title": "CoNNL-U Text Documents",
      "topics": [
        "CoNLLUTextDocument",
        "read_CoNNLU"
      ]
    },
    {
      "page": "datetime",
      "title": "Parse ISO 8601 Date/Time Strings",
      "topics": [
        "parse_ISO_8601_datetime"
      ]
    },
    {
      "page": "features",
      "title": "Extract Annotation Features",
      "topics": [
        "features"
      ]
    },
    {
      "page": "generics",
      "title": "Access or Modify Content or Metadata",
      "topics": [
        "content",
        "content<-",
        "meta",
        "meta<-"
      ]
    },
    {
      "page": "language",
      "title": "Parse IETF Language Tag",
      "topics": [
        "language",
        "parse_IETF_language_tag"
      ]
    },
    {
      "page": "ngrams",
      "title": "Compute N-Grams",
      "topics": [
        "ngrams"
      ]
    },
    {
      "page": "Span",
      "title": "Span objects",
      "topics": [
        "$<-.Span",
        "as.data.frame.Span",
        "as.list.Span",
        "as.Span",
        "c.Span",
        "duplicated.Span",
        "format.Span",
        "is.Span",
        "length.Span",
        "names.Span",
        "Ops.Span",
        "print.Span",
        "Span",
        "unique.Span",
        "[.Span",
        "[[.Span"
      ]
    },
    {
      "page": "String",
      "title": "String objects",
      "topics": [
        "as.String",
        "is.String",
        "String"
      ]
    },
    {
      "page": "Tagged_Token",
      "title": "Tagged_Token objects",
      "topics": [
        "$<-.Tagged_Token",
        "as.data.frame.Tagged_Token",
        "as.list.Tagged_Token",
        "as.Tagged_Token",
        "c.Tagged_Token",
        "duplicated.Tagged_Token",
        "format.Tagged_Token",
        "is.Tagged_Token",
        "length.Tagged_Token",
        "names.Tagged_Token",
        "print.Tagged_Token",
        "Tagged_Token",
        "unique.Tagged_Token",
        "[.Tagged_Token",
        "[[.Tagged_Token"
      ]
    },
    {
      "page": "TaggedTextDocument",
      "title": "POS-Tagged Word Text Documents",
      "topics": [
        "TaggedTextDocument"
      ]
    },
    {
      "page": "tagsets",
      "title": "NLP Tag Sets",
      "topics": [
        "Brown_POS_tags",
        "Penn_Treebank_POS_tags",
        "Universal_POS_tags",
        "Universal_POS_tags_map"
      ]
    },
    {
      "page": "TextDocument",
      "title": "Text Documents",
      "topics": [
        "TextDocument"
      ]
    },
    {
      "page": "Tokenizer",
      "title": "Tokenizer objects",
      "topics": [
        "as.Span_Tokenizer",
        "as.Token_Tokenizer",
        "is.Span_Tokenizer",
        "is.Token_Tokenizer",
        "Span_Tokenizer",
        "Token_Tokenizer"
      ]
    },
    {
      "page": "tokenizers",
      "title": "Regexp tokenizers",
      "topics": [
        "blankline_tokenizer",
        "Regexp_Tokenizer",
        "whitespace_tokenizer",
        "wordpunct_tokenizer"
      ]
    },
    {
      "page": "Tree",
      "title": "Tree objects",
      "topics": [
        "format.Tree",
        "print.Tree",
        "Tree",
        "Tree_apply",
        "Tree_parse"
      ]
    },
    {
      "page": "utils",
      "title": "Annotation Utilities",
      "topics": [
        "next_id",
        "single_feature"
      ]
    },
    {
      "page": "viewers",
      "title": "Text Document Viewers",
      "topics": [
        "chunked_sents",
        "otoks",
        "paras",
        "parsed_paras",
        "parsed_sents",
        "sents",
        "tagged_paras",
        "tagged_sents",
        "tagged_words",
        "words"
      ]
    },
    {
      "page": "WordListDocument",
      "title": "Word List Text Documents",
      "topics": [
        "WordListDocument"
      ]
    }
  ],
  "_rundeps": [],
  "_score": 8.996816003567016,
  "_indexed": true,
  "_nocasepkg": "nlp",
  "_universes": [
    "kurthornik"
  ],
  "_binaries": [
    {
      "r": "4.7.0",
      "os": "linux",
      "version": "0.3-2",
      "date": "2026-05-12T06:46:09.000Z",
      "distro": "noble",
      "commit": "486a6532266a3564e4edb847ce1eab03f19a38e1",
      "fileid": "9a77178a24b6de4e19d42c33d4680b959f594eb958b04852d7fb9ce23b216204",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/kurthornik/actions/runs/25718069023"
    },
    {
      "r": "4.6.0",
      "os": "linux",
      "version": "0.3-2",
      "date": "2026-05-12T06:46:10.000Z",
      "distro": "noble",
      "commit": "486a6532266a3564e4edb847ce1eab03f19a38e1",
      "fileid": "582e8d91caeab53b69389ef24c6ab604845432c94852559d5e082e22241c416f",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/kurthornik/actions/runs/25718069023"
    },
    {
      "r": "4.5.3",
      "os": "mac",
      "version": "0.3-2",
      "date": "2026-05-12T06:45:48.000Z",
      "commit": "486a6532266a3564e4edb847ce1eab03f19a38e1",
      "fileid": "7036ac76418f62af28a84ddb012a15875bf164af39d21a671b2770fbe8b9591e",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/kurthornik/actions/runs/25718069023"
    },
    {
      "r": "4.6.0",
      "os": "mac",
      "version": "0.3-2",
      "date": "2026-05-12T06:46:15.000Z",
      "commit": "486a6532266a3564e4edb847ce1eab03f19a38e1",
      "fileid": "fae4b15cfe819e2982d62297704201f08f23821f38b5ee3695c6aa3e8967cf04",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/kurthornik/actions/runs/25718069023"
    },
    {
      "r": "4.7.0",
      "os": "win",
      "version": "0.3-2",
      "date": "2026-05-12T06:45:35.000Z",
      "commit": "486a6532266a3564e4edb847ce1eab03f19a38e1",
      "fileid": "530dd57f3b7b77f0409041dfbd7528ca81674adc29bf65976ac6ac4627ab53d8",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/kurthornik/actions/runs/25718069023"
    },
    {
      "r": "4.5.3",
      "os": "win",
      "version": "0.3-2",
      "date": "2026-05-12T06:45:24.000Z",
      "commit": "486a6532266a3564e4edb847ce1eab03f19a38e1",
      "fileid": "72d04555edee01c4282ef9ec1a9658f74d512c6fff585e1f4505c96bf500df87",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/kurthornik/actions/runs/25718069023"
    },
    {
      "r": "4.6.0",
      "os": "win",
      "version": "0.3-2",
      "date": "2026-05-12T06:45:26.000Z",
      "commit": "486a6532266a3564e4edb847ce1eab03f19a38e1",
      "fileid": "486145a9e573d4d06b01ca3b4899ed4513223c0475b456df4547a8a0d8b77e10",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/kurthornik/actions/runs/25718069023"
    },
    {
      "r": "4.6.0",
      "os": "wasm",
      "version": "0.3-2",
      "date": "2026-05-22T10:57:03.000Z",
      "commit": "486a6532266a3564e4edb847ce1eab03f19a38e1",
      "fileid": "c66597a446e8a6dc7efeae723364bb92dca9abd70390e3b39c18d2c90f14f720",
      "status": "success",
      "buildurl": "https://github.com/r-universe/kurthornik/actions/runs/25718069023"
    }
  ]
}