{ "_id": "6a494c46f6c47c4419499520", "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://jonthegeek.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": "2026-07-04 18:06:10 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": "jonthegeek", "_type": "src", "_file": "wordpiece_2.1.3.tar.gz", "_fileid": "https://r2.ropensci.org/6f91359ed890267e35a43fed901d32fdfcfdc2f9d268150ac4a6cad5d09ba322", "_filesize": 109314, "_sha256": "6f91359ed890267e35a43fed901d32fdfcfdc2f9d268150ac4a6cad5d09ba322", "_expires": "2026-10-12T18:09:08.000Z", "_created": "2026-07-04T18:06:10.000Z", "_published": "2026-07-04T18:09:10.382Z", "_jobs": [ { "job": 85154845026, "time": 138, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "NOTE", "artifact": "8084158473" }, { "job": 85154845027, "time": 147, "config": "linux-release-x86_64", "r": "4.6.1", "check": "NOTE", "artifact": "8084159462" }, { "job": 85154845049, "time": 72, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "NOTE", "artifact": "8084150713" }, { "job": 85154845036, "time": 85, "config": "macos-release-arm64", "r": "4.6.1", "check": "NOTE", "artifact": "8084152223" }, { "job": 85154622091, "time": 192, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "8084142001" }, { "job": 85154845014, "time": 119, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "8084156152" }, { "job": 85154845034, "time": 67, "config": "windows-devel", "r": "4.7.0", "check": "NOTE", "artifact": "8084150369" }, { "job": 85154845048, "time": 128, "config": "windows-oldrel", "r": "4.5.3", "check": "NOTE", "artifact": "8084157286" }, { "job": 85154845032, "time": 69, "config": "windows-release", "r": "4.6.1", "check": "NOTE", "artifact": "8084150461" } ], "_host": "GitHub-Actions", "_buildurl": "https://github.com/r-universe/jonthegeek/actions/runs/28714954773", "_status": "success", "_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": false, "_usedby": 0, "_updates": [], "_tags": [], "_stars": 8, "_contributors": [ { "user": "jonathanbratt", "count": 14, "uuid": 33073024 }, { "user": "jonthegeek", "count": 7, "uuid": 33983824 } ], "_userbio": { "uuid": 33983824, "type": "user", "name": "Jon Harmon", "followers": 361, "description": "Executive Director at DSLC.io (fka @r4ds) | Principal Developer (@atorus-research)" }, "_downloads": { "count": 342, "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/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "extra/wordpiece.html", "manual.pdf" ], "_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": 4.6020599913279625, "_indexed": false, "_nocasepkg": "wordpiece", "_universes": [ "jonthegeek" ], "_indexurl": "https://macmillancontentscience.r-universe.dev/wordpiece", "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "2.1.3", "date": "2026-07-04T18:08:30.000Z", "distro": "resolute", "commit": "3eb92c759556e89d235202c45decb2dc859e661d", "fileid": "https://r2.ropensci.org/4edc1b0497d65d839d17476f25c1d80cf111c1f79e16c5ab30a909ad54ec579a", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/jonthegeek/actions/runs/28714954773" }, { "r": "4.6.1", "os": "linux", "version": "2.1.3", "date": "2026-07-04T18:08:42.000Z", "distro": "resolute", "commit": "3eb92c759556e89d235202c45decb2dc859e661d", "fileid": "https://r2.ropensci.org/2c10aa00f1665d1494816e313285a9c33f0cc87ad5369144bf11556db99dfca4", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/jonthegeek/actions/runs/28714954773" }, { "r": "4.5.3", "os": "mac", "version": "2.1.3", "date": "2026-07-04T18:07:28.000Z", "commit": "3eb92c759556e89d235202c45decb2dc859e661d", "fileid": "https://r2.ropensci.org/1efa5a177420e1ea6a857404b6f55c727bc31d3a4ff8e88073c2e47fdbefb37e", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/jonthegeek/actions/runs/28714954773" }, { "r": "4.6.1", "os": "mac", "version": "2.1.3", "date": "2026-07-04T18:07:39.000Z", "commit": "3eb92c759556e89d235202c45decb2dc859e661d", "fileid": "https://r2.ropensci.org/e365f7ab4e919e69116d66a293c71cc6bb511ae472c38d5fc3741421ffddd8b0", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/jonthegeek/actions/runs/28714954773" }, { "r": "4.6.0", "os": "wasm", "version": "2.1.3", "date": "2026-07-04T18:08:24.000Z", "commit": "3eb92c759556e89d235202c45decb2dc859e661d", "fileid": "https://r2.ropensci.org/9328e1cecb495549aa8481c5a333a167ae0402327acf34d86186daabe2d0fd47", "status": "success", "buildurl": "https://github.com/r-universe/jonthegeek/actions/runs/28714954773" }, { "r": "4.7.0", "os": "win", "version": "2.1.3", "date": "2026-07-04T18:07:16.000Z", "commit": "3eb92c759556e89d235202c45decb2dc859e661d", "fileid": "https://r2.ropensci.org/fe7c61753317df027d7045ce6503e6154700a846e2d523f67ac4f39667a11864", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/jonthegeek/actions/runs/28714954773" }, { "r": "4.5.3", "os": "win", "version": "2.1.3", "date": "2026-07-04T18:08:15.000Z", "commit": "3eb92c759556e89d235202c45decb2dc859e661d", "fileid": "https://r2.ropensci.org/59d87c1d88a8eed5a183b13826ffe4bf7762797e5734ba5988f3030c21bc7d8f", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/jonthegeek/actions/runs/28714954773" }, { "r": "4.6.1", "os": "win", "version": "2.1.3", "date": "2026-07-04T18:07:16.000Z", "commit": "3eb92c759556e89d235202c45decb2dc859e661d", "fileid": "https://r2.ropensci.org/85e5812667c7a6e08bd05bdcac878aac1c4add0ef229d090cbb577b2e8aba60f", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/jonthegeek/actions/runs/28714954773" } ] }