{ "_id": "6ac8af91de46216d5edd5a12", "Package": "wordpiece", "Type": "Package", "Title": "R Implementation of Wordpiece Tokenization", "Version": "2.1.3", "Authors@R": "c(\nperson(given = \"Jonathan\",\nfamily = \"Bratt\",\nrole = c(\"aut\", \"cre\"),\nemail = \"jonathan.bratt@macmillan.com\",\ncomment = c(ORCID = \"0000-0003-2859-0076\")),\nperson(given = \"Jon\",\nfamily = \"Harmon\",\nrole = c(\"aut\"),\nemail = \"jonthegeek@gmail.com\",\ncomment = c(ORCID = \"0000-0003-4781-4346\")),\nperson(given = \"Bedford Freeman & Worth Pub Grp LLC DBA Macmillan Learning\",\nrole = c(\"cph\"))\n)", "Description": "Apply 'Wordpiece' () tokenization to\ninput text, given an appropriate vocabulary. The 'BERT'\n() tokenization conventions are used by\ndefault.", "Encoding": "UTF-8", "URL": "https://github.com/macmillancontentscience/wordpiece", "BugReports": "https://github.com/macmillancontentscience/wordpiece/issues", "License": "Apache License (>= 2)", "RoxygenNote": "7.1.2", "Roxygen": "list(markdown = TRUE)", "VignetteBuilder": "knitr", "Config/testthat/edition": "3", "Config/pak/sysreqs": "cmake make libicu-dev libuv1-dev", "Repository": "https://macmillancontentscience.r-universe.dev", "Date/Publication": "2022-03-03 14:09:42 UTC", "RemoteUrl": "https://github.com/macmillancontentscience/wordpiece", "RemoteRef": "HEAD", "RemoteSha": "3eb92c759556e89d235202c45decb2dc859e661d", "NeedsCompilation": "no", "Packaged": { "Date": "2026-10-09 09:08:09 UTC", "User": "root" }, "Author": "Jonathan Bratt [aut, cre] (ORCID:\n),\nJon Harmon [aut] (ORCID: ),\nBedford Freeman & Worth Pub Grp LLC DBA Macmillan Learning [cph]", "Maintainer": "Jonathan Bratt ", "_user": "macmillancontentscience", "_type": "src", "_file": "wordpiece_2.1.3.tar.gz", "_fileid": "https://r2.ropensci.org/bcf36ebe9cc057dce8650cfcfae2e6119e824f49896b09040d1fe46868157097", "_filesize": 108598, "_sha256": "bcf36ebe9cc057dce8650cfcfae2e6119e824f49896b09040d1fe46868157097", "_expires": "2027-01-17T09:10:39.000Z", "_created": "2026-10-09T09:08:09.000Z", "_published": "2026-10-09T09:10:41.357Z", "_buildurl": "https://github.com/r-universe/macmillancontentscience/actions/runs/37908936619", "_status": "success", "_host": "GitHub-Actions", "_jobs": [ { "job": 113750475777, "time": 112, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "NOTE", "artifact": "11605444620" }, { "job": 113750475644, "time": 116, "config": "linux-release-x86_64", "r": "4.6.1", "check": "NOTE", "artifact": "11605429764" }, { "job": 113750475610, "time": 87, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "NOTE", "artifact": "11605882968" }, { "job": 113750475654, "time": 101, "config": "macos-release-arm64", "r": "4.6.1", "check": "NOTE", "artifact": "11605798184" }, { "job": 113749233184, "time": 210, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "11605906994" }, { "job": 113750475699, "time": 95, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "11605124336" }, { "job": 113750475578, "time": 79, "config": "windows-devel-x86_64", "r": "4.7.0", "check": "NOTE", "artifact": "11606182163" }, { "job": 113750475746, "time": 67, "config": "windows-oldrel-x86_64", "r": "4.5.3", "check": "NOTE", "artifact": "11605897881" }, { "job": 113750475640, "time": 66, "config": "windows-release-x86_64", "r": "4.6.1", "check": "NOTE", "artifact": "11605288532" } ], "_upstream": "https://github.com/macmillancontentscience/wordpiece", "_commit": { "id": "3eb92c759556e89d235202c45decb2dc859e661d", "author": "Jonathan Bratt <33073024+jonathanbratt@users.noreply.github.com>", "committer": "GitHub ", "message": "Cran prep (#32)\n\n* update vnum\r\n\r\n* update comments\r\n\r\n* Update cran-comments.md\r\n\r\nCo-authored-by: Jon Harmon \r\n\r\nCo-authored-by: Jon Harmon ", "time": 1646316582 }, "_maintainer": { "name": "Jonathan Bratt", "email": "jonathan.bratt@macmillan.com", "login": "jonathanbratt", "description": "", "uuid": 33073024, "orcid": "0000-0003-2859-0076" }, "_distro": "resolute", "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 3.3.0", "role": "Depends" }, { "package": "dlr", "version": ">= 1.0.0", "role": "Imports" }, { "package": "fastmatch", "version": ">= 1.1", "role": "Imports" }, { "package": "memoise", "version": ">= 2.0.0", "role": "Imports" }, { "package": "piecemaker", "version": ">= 1.0.0", "role": "Imports" }, { "package": "rlang", "role": "Imports" }, { "package": "stringi", "version": ">= 1.0", "role": "Imports" }, { "package": "wordpiece.data", "version": ">= 1.0.2", "role": "Imports" }, { "package": "covr", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" }, { "package": "testthat", "version": ">= 3.0.0", "role": "Suggests" } ], "_owner": "macmillancontentscience", "_selfowned": true, "_usedby": 1, "_updates": [], "_tags": [], "_stars": 8, "_contributors": [ { "user": "jonathanbratt", "count": 14, "uuid": 33073024 }, { "user": "jonthegeek", "count": 7, "uuid": 33983824 } ], "_userbio": { "uuid": 73667768, "type": "organization", "name": "Macmillan Learning Content Science", "followers": 5, "description": "A team of data scientists researching and applying content analysis techniques" }, "_downloads": { "count": 320, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/wordpiece" }, "_devurl": "https://github.com/macmillancontentscience/wordpiece", "_searchresults": 8, "_rbuild": "4.6.1", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/manual.pdf", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "extra/wordpiece.html" ], "_homeurl": "https://github.com/macmillancontentscience/wordpiece", "_realowner": "macmillancontentscience", "_cranurl": true, "_releases": [ { "version": "1.0.2", "date": "2021-02-11" }, { "version": "2.0.1", "date": "2021-10-18" }, { "version": "2.1.3", "date": "2022-03-03" } ], "_exports": [ "load_or_retrieve_vocab", "load_vocab", "prepare_vocab", "set_wordpiece_cache_dir", "wordpiece_cache_dir", "wordpiece_tokenize", "wordpiece_vocab" ], "_help": [ { "page": "load_or_retrieve_vocab", "title": "Load a vocabulary file, or retrieve from cache", "topics": [ "load_or_retrieve_vocab" ] }, { "page": "load_vocab", "title": "Load a vocabulary file", "topics": [ "load_vocab" ] }, { "page": "prepare_vocab", "title": "Format a Token List as a Vocabulary", "topics": [ "prepare_vocab" ] }, { "page": "set_wordpiece_cache_dir", "title": "Set a Cache Directory for wordpiece", "topics": [ "set_wordpiece_cache_dir" ] }, { "page": "wordpiece_cache_dir", "title": "Retrieve Directory for wordpiece Cache", "topics": [ "wordpiece_cache_dir" ] }, { "page": "wordpiece_tokenize", "title": "Tokenize Sequence with Word Pieces", "topics": [ "wordpiece_tokenize" ] } ], "_readme": "https://github.com/macmillancontentscience/wordpiece/raw/HEAD/README.md", "_rundeps": [ "cachem", "cli", "digest", "dlr", "fastmap", "fastmatch", "fs", "glue", "lifecycle", "magrittr", "memoise", "piecemaker", "rappdirs", "rlang", "stringi", "stringr", "vctrs", "wordpiece.data" ], "_vignettes": [ { "source": "basic_usage.Rmd", "filename": "basic_usage.html", "title": "Using wordpiece", "engine": "knitr::rmarkdown", "headings": [ "Provided Vocabularies", "Loading a Vocabulary", "Tokenizing Text", "Vocabulary Case", "Representing \"Unknown\" Tokens" ], "created": "2021-01-12 21:26:23", "modified": "2021-09-27 14:37:17", "commits": 2 } ], "_score": 5.079181246047625, "_indexed": true, "_nocasepkg": "wordpiece", "_universes": [ "macmillancontentscience", "jonathanbratt" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "2.1.3", "date": "2026-10-09T09:10:08.000Z", "distro": "resolute", "commit": "3eb92c759556e89d235202c45decb2dc859e661d", "fileid": "https://r2.ropensci.org/e76e269e5be121c3f1b6a675ad22c150fc7e681c586e9f81da54ac5093a6624a", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/macmillancontentscience/actions/runs/37908936619" }, { "r": "4.6.1", "os": "linux", "version": "2.1.3", "date": "2026-10-09T09:10:08.000Z", "distro": "resolute", "commit": "3eb92c759556e89d235202c45decb2dc859e661d", "fileid": "https://r2.ropensci.org/afcedd3291c1e14bb08529c6019226e50ca9b136260177cbaaa47158249013ad", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/macmillancontentscience/actions/runs/37908936619" }, { "r": "4.5.3", "os": "mac", "version": "2.1.3", "date": "2026-10-09T09:09:45.000Z", "commit": "3eb92c759556e89d235202c45decb2dc859e661d", "fileid": "https://r2.ropensci.org/798858bcbee9bdc0f9e16f9d3e6d8d6af326f11cdde1e8b9cb25ff49abe4ec59", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/macmillancontentscience/actions/runs/37908936619" }, { "r": "4.6.1", "os": "mac", "version": "2.1.3", "date": "2026-10-09T09:09:52.000Z", "commit": "3eb92c759556e89d235202c45decb2dc859e661d", "fileid": "https://r2.ropensci.org/6fe7b434a5dcbd18e4c8db63af8a8b34afe5dfe54da5c1b575ba2e794a641f1f", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/macmillancontentscience/actions/runs/37908936619" }, { "r": "4.6.0", "os": "wasm", "version": "2.1.3", "date": "2026-10-09T09:10:01.000Z", "commit": "3eb92c759556e89d235202c45decb2dc859e661d", "fileid": "https://r2.ropensci.org/041030e0dae478857f5f017a0b36811dda231934f3d223258172a85646e1cbd6", "status": "success", "buildurl": "https://github.com/r-universe/macmillancontentscience/actions/runs/37908936619" }, { "r": "4.7.0", "os": "win", "version": "2.1.3", "date": "2026-10-09T09:09:22.000Z", "commit": "3eb92c759556e89d235202c45decb2dc859e661d", "fileid": "https://r2.ropensci.org/5600603d7c59177e0f047b9a0628c0e67efd49ec313ca6b671c5d9644d093313", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/macmillancontentscience/actions/runs/37908936619" }, { "r": "4.5.3", "os": "win", "version": "2.1.3", "date": "2026-10-09T09:09:16.000Z", "commit": "3eb92c759556e89d235202c45decb2dc859e661d", "fileid": "https://r2.ropensci.org/026d226ef0bd6da85fafd985836ef84a5b5b28602bf3445c84f25784a5042b95", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/macmillancontentscience/actions/runs/37908936619" }, { "r": "4.6.1", "os": "win", "version": "2.1.3", "date": "2026-10-09T09:09:15.000Z", "commit": "3eb92c759556e89d235202c45decb2dc859e661d", "fileid": "https://r2.ropensci.org/ede9d734c983ab651fb63e8cf66f350a7e8c27569aa4828b41f39a82bbef9b8e", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/macmillancontentscience/actions/runs/37908936619" } ] }