{
  "_id": "6abe29c199f7aa8c6aa530e3",
  "Package": "NUSS",
  "Title": "Mixed N-Grams and Unigram Sequence Segmentation",
  "Version": "0.1.0",
  "Authors@R": "person(\"Oskar\", \"Kosch\", , \"contact@oskarkosch.com\", role = c(\"aut\", \"cre\"),\ncomment = c(ORCID = \"0000-0003-2697-1393\"))",
  "Description": "Segmentation of short text sequences - like hashtags -\ninto the separated words sequence, done with the use of\ndictionary, which may be built on custom corpus of texts.\nUnigram dictionary is used to find most probable sequence, and\nn-grams approach is used to determine possible segmentation\ngiven the text corpus.",
  "License": "GPL (>= 3)",
  "URL": "https://github.com/theogrost/NUSS",
  "BugReports": "https://github.com/theogrost/NUSS/issues",
  "Config/testthat/edition": "3",
  "Encoding": "UTF-8",
  "Language": "en",
  "LazyData": "true",
  "Roxygen": "list(markdown = TRUE)",
  "RoxygenNote": "7.3.1",
  "Config/pak/sysreqs": "libicu-dev",
  "Repository": "https://theogrost.r-universe.dev",
  "Date/Publication": "2024-07-31 10:40:05 UTC",
  "RemoteUrl": "https://github.com/theogrost/nuss",
  "RemoteRef": "HEAD",
  "RemoteSha": "2e104423fab7ec8a0fe241f285f9107a6c7865f2",
  "NeedsCompilation": "yes",
  "Packaged": {
    "Date": "2026-10-01 09:29:43 UTC",
    "User": "root"
  },
  "Author": "Oskar Kosch [aut, cre] (ORCID: <https://orcid.org/0000-0003-2697-1393>)",
  "Maintainer": "Oskar Kosch <contact@oskarkosch.com>",
  "_user": "theogrost",
  "_type": "src",
  "_file": "NUSS_0.1.0.tar.gz",
  "_fileid": "https://r2.ropensci.org/a75feab553ec8bb86babab0131f6c7c25da81da1ab2cb21bcbb4b194cf5095d8",
  "_filesize": 432117,
  "_sha256": "a75feab553ec8bb86babab0131f6c7c25da81da1ab2cb21bcbb4b194cf5095d8",
  "_expires": "2027-01-09T09:37:03.000Z",
  "_created": "2026-10-01T09:29:43.000Z",
  "_published": "2026-10-01T09:37:05.290Z",
  "_jobs": [
    {
      "job": 110306776836,
      "time": 154,
      "config": "linux-devel-arm64",
      "r": "4.7.0",
      "check": "OK",
      "artifact": "11152960318"
    },
    {
      "job": 110306776897,
      "time": 180,
      "config": "linux-devel-x86_64",
      "r": "4.7.0",
      "check": "OK",
      "artifact": "11151749205"
    },
    {
      "job": 110306776745,
      "time": 148,
      "config": "linux-release-arm64",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "11151862992"
    },
    {
      "job": 110306776844,
      "time": 164,
      "config": "linux-release-x86_64",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "11152871279"
    },
    {
      "job": 110306777013,
      "time": 230,
      "config": "macos-oldrel-arm64",
      "r": "4.5.3",
      "check": "OK",
      "artifact": "11152790883"
    },
    {
      "job": 110306776826,
      "time": 330,
      "config": "macos-oldrel-x86_64",
      "r": "4.5.3",
      "check": "OK",
      "artifact": "11152192579"
    },
    {
      "job": 110306776858,
      "time": 149,
      "config": "macos-release-arm64",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "11151857880"
    },
    {
      "job": 110306776802,
      "time": 386,
      "config": "macos-release-x86_64",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "11152463076"
    },
    {
      "job": 110305124292,
      "time": 279,
      "config": "source",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "11152596502"
    },
    {
      "job": 110306776922,
      "time": 134,
      "config": "wasm-release",
      "r": "4.6.0",
      "check": "OK",
      "artifact": "11152491209"
    },
    {
      "job": 110306776905,
      "time": 351,
      "config": "windows-devel-arm64",
      "r": "4.7.0",
      "check": "OK",
      "artifact": "11152576615"
    },
    {
      "job": 110306776949,
      "time": 167,
      "config": "windows-devel-x86_64",
      "r": "4.7.0",
      "check": "OK",
      "artifact": "11152351227"
    },
    {
      "job": 110306777001,
      "time": 124,
      "config": "windows-oldrel-x86_64",
      "r": "4.5.3",
      "check": "OK",
      "artifact": "11152182525"
    },
    {
      "job": 110306777045,
      "time": 346,
      "config": "windows-release-arm64",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "11152676599"
    },
    {
      "job": 110306776877,
      "time": 121,
      "config": "windows-release-x86_64",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "11152252468"
    }
  ],
  "_host": "GitHub-Actions",
  "_buildurl": "https://github.com/r-universe/theogrost/actions/runs/36842607935",
  "_status": "success",
  "_upstream": "https://github.com/theogrost/nuss",
  "_commit": {
    "id": "2e104423fab7ec8a0fe241f285f9107a6c7865f2",
    "author": "theogrost <35686723+theogrost@users.noreply.github.com>",
    "committer": "theogrost <35686723+theogrost@users.noreply.github.com>",
    "message": "Fixed arguments\n",
    "time": 1722422405
  },
  "_maintainer": {
    "name": "Oskar Kosch",
    "email": "contact@oskarkosch.com",
    "orcid": "0000-0003-2697-1393"
  },
  "_distro": "resolute",
  "_registered": true,
  "_dependencies": [
    {
      "package": "R",
      "version": ">= 3.5",
      "role": "Depends"
    },
    {
      "package": "BH",
      "role": "LinkingTo"
    },
    {
      "package": "Rcpp",
      "role": "LinkingTo"
    },
    {
      "package": "dplyr",
      "role": "Imports"
    },
    {
      "package": "magrittr",
      "role": "Imports"
    },
    {
      "package": "Rcpp",
      "role": "Imports"
    },
    {
      "package": "stringr",
      "role": "Imports"
    },
    {
      "package": "text2vec",
      "role": "Imports"
    },
    {
      "package": "textclean",
      "role": "Imports"
    },
    {
      "package": "utils",
      "role": "Imports"
    },
    {
      "package": "testthat",
      "version": ">= 3.0.0",
      "role": "Suggests"
    }
  ],
  "_owner": "theogrost",
  "_selfowned": true,
  "_usedby": 0,
  "_updates": [],
  "_tags": [],
  "_stars": 0,
  "_contributors": [
    {
      "user": "theogrost",
      "count": 12,
      "uuid": 35686723
    }
  ],
  "_userbio": {
    "uuid": 35686723,
    "type": "user",
    "name": "theogrost",
    "followers": 2
  },
  "_downloads": {
    "count": 226,
    "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/NUSS"
  },
  "_devurl": "https://github.com/theogrost/nuss",
  "_searchresults": 0,
  "_topics": [
    "cpp"
  ],
  "_rbuild": "4.6.1",
  "_assets": [
    "extra/citation.cff",
    "extra/citation.html",
    "extra/citation.json",
    "extra/citation.txt",
    "extra/contents.json",
    "extra/manual.pdf",
    "extra/NUSS.html",
    "extra/readme.html",
    "extra/readme.md"
  ],
  "_homeurl": "https://github.com/theogrost/nuss",
  "_realowner": "theogrost",
  "_cranurl": true,
  "_releases": [
    {
      "version": "0.1.0",
      "date": "2024-08-19"
    }
  ],
  "_exports": [
    "igrepl",
    "ngrams_dictionary",
    "ngrams_segmentation",
    "nuss",
    "unigram_dictionary",
    "unigram_sequence_segmentation"
  ],
  "_datasets": [
    {
      "name": "base_dictionary",
      "title": "Base dictionary with unigrams",
      "object": "base_dictionary",
      "class": [
        "data.frame"
      ],
      "fields": [
        "to_search",
        "to_replace",
        "id",
        "points"
      ],
      "rows": 62983,
      "table": true,
      "tojson": true
    }
  ],
  "_help": [
    {
      "page": "base_dictionary",
      "title": "Base dictionary with unigrams",
      "topics": [
        "base_dictionary"
      ]
    },
    {
      "page": "igrepl",
      "title": "Perform inverse regex search (C++)",
      "topics": [
        "igrepl"
      ]
    },
    {
      "page": "ngrams_dictionary",
      "title": "Create n-grams dictionary",
      "topics": [
        "ngrams_dictionary"
      ]
    },
    {
      "page": "ngrams_segmentation",
      "title": "Segmenting sequences with n-grams.",
      "topics": [
        "ngrams_segmentation"
      ]
    },
    {
      "page": "nuss",
      "title": "Mixed N-Grams and Unigram Sequence Segmentation (NUSS) function",
      "topics": [
        "nuss"
      ]
    },
    {
      "page": "unigram_dictionary",
      "title": "Create unigram dictionary",
      "topics": [
        "unigram_dictionary"
      ]
    },
    {
      "page": "unigram_sequence_segmentation",
      "title": "Segmenting sequences with unigrams",
      "topics": [
        "unigram_sequence_segmentation"
      ]
    }
  ],
  "_readme": "https://github.com/theogrost/nuss/raw/HEAD/README.md",
  "_rundeps": [
    "BH",
    "cli",
    "cpp11",
    "data.table",
    "digest",
    "dplyr",
    "dtt",
    "english",
    "float",
    "generics",
    "glue",
    "lattice",
    "lexicon",
    "lgr",
    "lifecycle",
    "magrittr",
    "Matrix",
    "MatrixExtra",
    "mgsub",
    "mlapi",
    "NLP",
    "pillar",
    "pkgconfig",
    "purrr",
    "qdapRegex",
    "R6",
    "Rcpp",
    "RcppArmadillo",
    "RhpcBLASctl",
    "rlang",
    "rsparse",
    "slam",
    "stringi",
    "stringr",
    "syuzhet",
    "text2vec",
    "textclean",
    "textshape",
    "tibble",
    "tidyr",
    "tidyselect",
    "utf8",
    "vctrs",
    "withr",
    "zoo"
  ],
  "_sysdeps": [
    {
      "shlib": "libstdc++",
      "package": "libstdc++6",
      "source": "gcc",
      "version": "16-20260322-1ubuntu1",
      "name": "c++",
      "homepage": "http://gcc.gnu.org/",
      "description": "GNU Standard C++ Library v3"
    }
  ],
  "_score": 2.6989700043360187,
  "_indexed": true,
  "_nocasepkg": "nuss",
  "_universes": [
    "theogrost"
  ],
  "_binaries": [
    {
      "r": "4.7.0",
      "os": "linux",
      "version": "0.1.0",
      "date": "2026-10-01T09:32:26.000Z",
      "distro": "resolute",
      "arch": "aarch64",
      "commit": "2e104423fab7ec8a0fe241f285f9107a6c7865f2",
      "fileid": "https://r2.ropensci.org/41ea9897ae1677588ead948960dad3266d4207b3aa54237d6dce8a039537ab93",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/theogrost/actions/runs/36842607935"
    },
    {
      "r": "4.7.0",
      "os": "linux",
      "version": "0.1.0",
      "date": "2026-10-01T09:32:44.000Z",
      "distro": "resolute",
      "arch": "x86_64",
      "commit": "2e104423fab7ec8a0fe241f285f9107a6c7865f2",
      "fileid": "https://r2.ropensci.org/b7237355c8a52fa07ee015146ce4667682d3805c580f002467527c03f8493cfa",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/theogrost/actions/runs/36842607935"
    },
    {
      "r": "4.6.1",
      "os": "linux",
      "version": "0.1.0",
      "date": "2026-10-01T09:32:24.000Z",
      "distro": "resolute",
      "arch": "aarch64",
      "commit": "2e104423fab7ec8a0fe241f285f9107a6c7865f2",
      "fileid": "https://r2.ropensci.org/b8f2ddbc502e9cbb4185628205c66faf4b2f19ba8a9ce315d3d6e401d23d9fa6",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/theogrost/actions/runs/36842607935"
    },
    {
      "r": "4.6.1",
      "os": "linux",
      "version": "0.1.0",
      "date": "2026-10-01T09:32:31.000Z",
      "distro": "resolute",
      "arch": "x86_64",
      "commit": "2e104423fab7ec8a0fe241f285f9107a6c7865f2",
      "fileid": "https://r2.ropensci.org/b0718ca5832b71fe052593d9dc65988281a1680d90fd1b2a30e21184c173a510",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/theogrost/actions/runs/36842607935"
    },
    {
      "r": "4.5.3",
      "os": "mac",
      "version": "0.1.0",
      "date": "2026-10-01T09:32:43.000Z",
      "arch": "aarch64",
      "commit": "2e104423fab7ec8a0fe241f285f9107a6c7865f2",
      "fileid": "https://r2.ropensci.org/b04c0c32f3b97a8cf55ea91ce8f6440f72dc3bb80a73caeb3a3cc6e0de9655f4",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/theogrost/actions/runs/36842607935"
    },
    {
      "r": "4.5.3",
      "os": "mac",
      "version": "0.1.0",
      "date": "2026-10-01T09:34:15.000Z",
      "arch": "x86_64",
      "commit": "2e104423fab7ec8a0fe241f285f9107a6c7865f2",
      "fileid": "https://r2.ropensci.org/12a11733785e14a8c85cd266265e9e0cccfd8470916ac229738236b6edd6455a",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/theogrost/actions/runs/36842607935"
    },
    {
      "r": "4.6.1",
      "os": "mac",
      "version": "0.1.0",
      "date": "2026-10-01T09:31:56.000Z",
      "arch": "aarch64",
      "commit": "2e104423fab7ec8a0fe241f285f9107a6c7865f2",
      "fileid": "https://r2.ropensci.org/cf6b1fca6e03d3b64c5b9d59cbfe87156e64386a9e74d07c66365d8bd51881af",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/theogrost/actions/runs/36842607935"
    },
    {
      "r": "4.6.1",
      "os": "mac",
      "version": "0.1.0",
      "date": "2026-10-01T09:35:15.000Z",
      "arch": "x86_64",
      "commit": "2e104423fab7ec8a0fe241f285f9107a6c7865f2",
      "fileid": "https://r2.ropensci.org/5885d9199f5160120fd48bbc74036060485859ecb7165b7f8b2ec88c37de7265",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/theogrost/actions/runs/36842607935"
    },
    {
      "r": "4.6.0",
      "os": "wasm",
      "version": "0.1.0",
      "date": "2026-10-01T09:32:21.000Z",
      "arch": "emscripten",
      "commit": "2e104423fab7ec8a0fe241f285f9107a6c7865f2",
      "fileid": "https://r2.ropensci.org/8e1ed47a2a8f5cd752475270e31dbba0d5383182ddc2cfe8c149addb94dbaaea",
      "status": "success",
      "buildurl": "https://github.com/r-universe/theogrost/actions/runs/36842607935"
    },
    {
      "r": "4.7.0",
      "os": "win",
      "version": "0.1.0",
      "date": "2026-10-01T09:34:56.000Z",
      "arch": "aarch64",
      "commit": "2e104423fab7ec8a0fe241f285f9107a6c7865f2",
      "fileid": "https://r2.ropensci.org/7f27022f349b03b0cd4a400e3396e7810839ba6a8e3656c4cee9f8785fb77dd2",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/theogrost/actions/runs/36842607935"
    },
    {
      "r": "4.7.0",
      "os": "win",
      "version": "0.1.0",
      "date": "2026-10-01T09:31:27.000Z",
      "arch": "x86_64",
      "commit": "2e104423fab7ec8a0fe241f285f9107a6c7865f2",
      "fileid": "https://r2.ropensci.org/2e4ec365800b29c089599b21dc54d5cf44d191d4cc3cf3b98d679c065b7139e1",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/theogrost/actions/runs/36842607935"
    },
    {
      "r": "4.5.3",
      "os": "win",
      "version": "0.1.0",
      "date": "2026-10-01T09:31:26.000Z",
      "arch": "x86_64",
      "commit": "2e104423fab7ec8a0fe241f285f9107a6c7865f2",
      "fileid": "https://r2.ropensci.org/85ce57492f1a5a6ca542e91a69aecf3382b5ce6a54d18f8dd909d7d813c7aead",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/theogrost/actions/runs/36842607935"
    },
    {
      "r": "4.6.1",
      "os": "win",
      "version": "0.1.0",
      "date": "2026-10-01T09:35:01.000Z",
      "arch": "aarch64",
      "commit": "2e104423fab7ec8a0fe241f285f9107a6c7865f2",
      "fileid": "https://r2.ropensci.org/0d099658e5a26b724f4f83dfdea803098133a27cec7398d18c948e9f8832ec34",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/theogrost/actions/runs/36842607935"
    },
    {
      "r": "4.6.1",
      "os": "win",
      "version": "0.1.0",
      "date": "2026-10-01T09:31:21.000Z",
      "arch": "x86_64",
      "commit": "2e104423fab7ec8a0fe241f285f9107a6c7865f2",
      "fileid": "https://r2.ropensci.org/248919c585c4b087b07d8c34bbd4a7c4b0041fec728d1060804a7af156b4f639",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/theogrost/actions/runs/36842607935"
    }
  ]
}