{ "_id": "6a156416acfb0bcc41d61663", "Package": "piecemaker", "Title": "Tools for Preparing Text for Tokenizers", "Version": "1.0.2.9000", "Authors@R": "c(\nperson(\"Jon\", \"Harmon\", , \"jonthegeek@gmail.com\", role = c(\"aut\", \"cre\"),\ncomment = c(ORCID = \"0000-0003-4781-4346\")),\nperson(\"Jonathan\", \"Bratt\", , \"jonathan.bratt@macmillan.com\", role = \"aut\",\ncomment = c(ORCID = \"0000-0003-2859-0076\")),\nperson(\"Bedford Freeman & Worth Pub Grp LLC DBA Macmillan Learning\", role = \"cph\")\n)", "Description": "Tokenizers break text into pieces that are more usable by\nmachine learning models. Many tokenizers share some preparation\nsteps. This package provides those shared steps, along with a\nsimple tokenizer.", "License": "Apache License (>= 2)", "URL": "https://github.com/macmillancontentscience/piecemaker,\nhttps://macmillancontentscience.github.io/piecemaker/", "BugReports": "https://github.com/macmillancontentscience/piecemaker/issues", "Config/testthat/edition": "3", "Encoding": "UTF-8", "Roxygen": "list(markdown = TRUE)", "RoxygenNote": "7.2.3", "Config/pak/sysreqs": "libicu-dev", "Repository": "https://jonthegeek.r-universe.dev", "Date/Publication": "2023-06-02 19:46:08 UTC", "RemoteUrl": "https://github.com/macmillancontentscience/piecemaker", "RemoteRef": "HEAD", "RemoteSha": "b02c1a74923301545366805680e54091675305c6", "NeedsCompilation": "no", "Packaged": { "Date": "2026-05-26 09:10:15 UTC", "User": "root" }, "Author": "Jon Harmon [aut, cre] (ORCID: ),\nJonathan Bratt [aut] (ORCID: ),\nBedford Freeman & Worth Pub Grp LLC DBA Macmillan Learning [cph]", "Maintainer": "Jon Harmon ", "MD5sum": "a758a674aa068c414e6c53bc5bdd467f", "_user": "jonthegeek", "_type": "src", "_file": "piecemaker_1.0.2.9000.tar.gz", "_fileid": "bb3ea7cd85f9966b7ea90efa1e5c12448e1d4be83798da08e67afd101b4d6b3f", "_filesize": 112471, "_sha256": "bb3ea7cd85f9966b7ea90efa1e5c12448e1d4be83798da08e67afd101b4d6b3f", "_created": "2026-05-26T09:10:15.000Z", "_published": "2026-05-26T09:12:54.822Z", "_distro": "noble", "_jobs": [ { "job": 77842796843, "time": 124, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "7213172476" }, { "job": 77842797048, "time": 110, "config": "linux-release-x86_64", "r": "4.6.0", "check": "OK", "artifact": "7213167382" }, { "job": 77842796786, "time": 94, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "7213161012" }, { "job": 77842796851, "time": 96, "config": "macos-release-arm64", "r": "4.6.0", "check": "OK", "artifact": "7213162451" }, { "job": 77842323706, "time": 173, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "7213126981" }, { "job": 77842796747, "time": 114, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7213168673" }, { "job": 77842796799, "time": 84, "config": "windows-devel", "r": "4.7.0", "check": "OK", "artifact": "7213158201" }, { "job": 77842796812, "time": 55, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "7213147574" }, { "job": 77842796819, "time": 73, "config": "windows-release", "r": "4.6.0", "check": "OK", "artifact": "7213153611" } ], "_buildurl": "https://github.com/r-universe/jonthegeek/actions/runs/26443086680", "_status": "success", "_host": "GitHub-Actions", "_upstream": "https://github.com/macmillancontentscience/piecemaker", "_commit": { "id": "b02c1a74923301545366805680e54091675305c6", "author": "Jon Harmon ", "committer": "Jon Harmon ", "message": "Increment version number to 1.0.2.9000\n", "time": 1685735168 }, "_maintainer": { "name": "Jon Harmon", "email": "jonthegeek@gmail.com", "login": "jonthegeek", "mastodon": "@jonthegeek@fosstodon.org", "bluesky": "@jonthegeek.com", "linkedin": "in/jonthegeek", "description": "Executive Director at DSLC.io (fka @r4ds) | Principal Developer (@atorus-research)", "uuid": 33983824, "orcid": "0000-0003-4781-4346" }, "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 2.10", "role": "Depends" }, { "package": "cli", "role": "Imports" }, { "package": "glue", "role": "Imports" }, { "package": "rlang", "version": ">= 0.4.2", "role": "Imports" }, { "package": "stringi", "role": "Imports" }, { "package": "stringr", "role": "Imports" }, { "package": "covr", "role": "Suggests" }, { "package": "testthat", "version": ">= 3.0.0", "role": "Suggests" } ], "_owner": "macmillancontentscience", "_selfowned": true, "_usedby": 2, "_updates": [], "_tags": [], "_stars": 0, "_contributors": [ { "user": "jonthegeek", "count": 20, "uuid": 33983824 }, { "user": "jonathanbratt", "count": 1, "uuid": 33073024 } ], "_userbio": { "uuid": 33983824, "type": "user", "name": "Jon Harmon", "description": "Executive Director at DSLC.io (fka @r4ds) | Principal Developer (@atorus-research)" }, "_downloads": { "count": 278, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/piecemaker" }, "_devurl": "https://github.com/macmillancontentscience/piecemaker", "_pkgdown": "https://macmillancontentscience.github.io/piecemaker/", "_searchresults": 7, "_rbuild": "4.6.0", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/NEWS.html", "extra/NEWS.txt", "extra/piecemaker.html", "extra/readme.html", "extra/readme.md", "manual.pdf" ], "_homeurl": "https://github.com/macmillancontentscience/piecemaker", "_realowner": "macmillancontentscience", "_cranurl": true, "_releases": [ { "version": "1.0.0", "date": "2021-08-06" }, { "version": "1.0.1", "date": "2022-03-03" }, { "version": "1.0.2", "date": "2023-06-02" } ], "_exports": [ "prepare_and_tokenize", "prepare_text", "remove_control_characters", "remove_diacritics", "remove_replacement_characters", "space_cjk", "space_punctuation", "squish_whitespace", "tokenize_space", "validate_utf8" ], "_help": [ { "page": "prepare_and_tokenize", "title": "Split Text on Spaces", "topics": [ "prepare_and_tokenize" ] }, { "page": "prepare_text", "title": "Prepare Text for Tokenization", "topics": [ "prepare_text" ] }, { "page": "remove_control_characters", "title": "Remove Non-Character Characters", "topics": [ "remove_control_characters" ] }, { "page": "remove_diacritics", "title": "Remove Diacritical Marks on Characters", "topics": [ "remove_diacritics" ] }, { "page": "remove_replacement_characters", "title": "Remove the Unicode Replacement Character", "topics": [ "remove_replacement_characters" ] }, { "page": "space_cjk", "title": "Add Spaces Around CJK Ideographs", "topics": [ "space_cjk" ] }, { "page": "space_punctuation", "title": "Add Spaces Around Punctuation", "topics": [ "space_punctuation" ] }, { "page": "squish_whitespace", "title": "Remove Extra Whitespace", "topics": [ "squish_whitespace" ] }, { "page": "tokenize_space", "title": "Break Text at Spaces", "topics": [ "tokenize_space" ] }, { "page": "validate_utf8", "title": "Clean Up Text to UTF-8", "topics": [ "validate_utf8" ] } ], "_readme": "https://github.com/macmillancontentscience/piecemaker/raw/HEAD/README.md", "_rundeps": [ "cli", "glue", "lifecycle", "magrittr", "rlang", "stringi", "stringr", "vctrs" ], "_score": 3.4771212547196626, "_indexed": false, "_nocasepkg": "piecemaker", "_universes": [ "jonthegeek" ], "_indexurl": "https://macmillancontentscience.r-universe.dev/piecemaker", "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "1.0.2.9000", "date": "2026-05-26T09:12:25.000Z", "distro": "noble", "commit": "b02c1a74923301545366805680e54091675305c6", "fileid": "8a9158d150a2a7ce21b6baa4f82cf752031df5130a74d3ec23262fb8d411475a", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/jonthegeek/actions/runs/26443086680" }, { "r": "4.6.0", "os": "linux", "version": "1.0.2.9000", "date": "2026-05-26T09:12:13.000Z", "distro": "noble", "commit": "b02c1a74923301545366805680e54091675305c6", "fileid": "3296536feb196b88473d72a92b580a2edadc226c04873d41eb847b5b5d7c9acb", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/jonthegeek/actions/runs/26443086680" }, { "r": "4.5.3", "os": "mac", "version": "1.0.2.9000", "date": "2026-05-26T09:11:56.000Z", "commit": "b02c1a74923301545366805680e54091675305c6", "fileid": "56acf31033531255dba9472d165840d92b58a57c80fd4de3c19bc21ec7a25790", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/jonthegeek/actions/runs/26443086680" }, { "r": "4.6.0", "os": "mac", "version": "1.0.2.9000", "date": "2026-05-26T09:12:00.000Z", "commit": "b02c1a74923301545366805680e54091675305c6", "fileid": "3a778b95938d39d2656b76d0dd798d6a609bc7e9d9ec0a734034ae17d512c23d", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/jonthegeek/actions/runs/26443086680" }, { "r": "4.6.0", "os": "wasm", "version": "1.0.2.9000", "date": "2026-05-26T09:12:27.000Z", "commit": "b02c1a74923301545366805680e54091675305c6", "fileid": "23d92e41c203390fd2c264ec4c80ffd1d1b170732a821079b5ce04911ea72bab", "status": "success", "buildurl": "https://github.com/r-universe/jonthegeek/actions/runs/26443086680" }, { "r": "4.7.0", "os": "win", "version": "1.0.2.9000", "date": "2026-05-26T09:11:45.000Z", "commit": "b02c1a74923301545366805680e54091675305c6", "fileid": "0bbebe51bacce5add24a4925b48dce2a6b45d6deefd8f453bfacf6fbcdfeb40a", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/jonthegeek/actions/runs/26443086680" }, { "r": "4.5.3", "os": "win", "version": "1.0.2.9000", "date": "2026-05-26T09:11:16.000Z", "commit": "b02c1a74923301545366805680e54091675305c6", "fileid": "c408d0f5f2361e1553cd5b075cf53fbe6c47b07de3031342aa472f840697407d", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/jonthegeek/actions/runs/26443086680" }, { "r": "4.6.0", "os": "win", "version": "1.0.2.9000", "date": "2026-05-26T09:11:32.000Z", "commit": "b02c1a74923301545366805680e54091675305c6", "fileid": "faa3a8b80d0a7c24cff25eaa9205e91685e1bb62df76633d512acda075cd4e9f", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/jonthegeek/actions/runs/26443086680" } ] }