{ "_id": "6a49cf9c1b0c6c282ca7db47", "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": "2026-07-05 03:26:34 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 ", "_user": "jonthegeek", "_type": "src", "_file": "piecemaker_1.0.2.9000.tar.gz", "_fileid": "https://r2.ropensci.org/51fcf8426370f5212bf0dc98ee0628ed4c68a5d5e0254875f300b0b1379e35e7", "_filesize": 115315, "_sha256": "51fcf8426370f5212bf0dc98ee0628ed4c68a5d5e0254875f300b0b1379e35e7", "_expires": "2026-10-13T03:29:30.000Z", "_created": "2026-07-05T03:26:34.000Z", "_published": "2026-07-05T03:29:32.317Z", "_jobs": [ { "job": 85189252016, "time": 135, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "8087943086" }, { "job": 85189252021, "time": 113, "config": "linux-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "8087940973" }, { "job": 85189252031, "time": 70, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "8087936204" }, { "job": 85189252029, "time": 106, "config": "macos-release-arm64", "r": "4.6.1", "check": "OK", "artifact": "8087940000" }, { "job": 85189067050, "time": 177, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "8087928861" }, { "job": 85189251997, "time": 98, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "8087939330" }, { "job": 85189252034, "time": 71, "config": "windows-devel", "r": "4.7.0", "check": "OK", "artifact": "8087936412" }, { "job": 85189252038, "time": 64, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "8087935762" }, { "job": 85189252046, "time": 73, "config": "windows-release", "r": "4.6.1", "check": "OK", "artifact": "8087936509" } ], "_host": "GitHub-Actions", "_buildurl": "https://github.com/r-universe/jonthegeek/actions/runs/28728128787", "_status": "success", "_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" }, "_distro": "resolute", "_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", "followers": 361, "description": "Executive Director at DSLC.io (fka @r4ds) | Principal Developer (@atorus-research)" }, "_downloads": { "count": 356, "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": "4.6.1", "_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": "2026-07-05T03:28:57.000Z", "distro": "resolute", "commit": "b02c1a74923301545366805680e54091675305c6", "fileid": "https://r2.ropensci.org/79b6b163d6f08a94a4a7ff8eeb43355e2d53f37578149c7ca7729f9c9d4579ca", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/jonthegeek/actions/runs/28728128787" }, { "r": "4.6.1", "os": "linux", "version": "1.0.2.9000", "date": "2026-07-05T03:28:36.000Z", "distro": "resolute", "commit": "b02c1a74923301545366805680e54091675305c6", "fileid": "https://r2.ropensci.org/d196ecccf19917db01a579ae8077d4e36218e8b2e7ce35a2c73ece87da3976a2", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/jonthegeek/actions/runs/28728128787" }, { "r": "4.5.3", "os": "mac", "version": "1.0.2.9000", "date": "2026-07-05T03:27:55.000Z", "commit": "b02c1a74923301545366805680e54091675305c6", "fileid": "https://r2.ropensci.org/b561cbb3268ee388a4ed299ced4e7507b9cc8348e8338d017817795972c1679b", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/jonthegeek/actions/runs/28728128787" }, { "r": "4.6.1", "os": "mac", "version": "1.0.2.9000", "date": "2026-07-05T03:28:25.000Z", "commit": "b02c1a74923301545366805680e54091675305c6", "fileid": "https://r2.ropensci.org/db32ecd39d502f34e64b7d305a8b2016f08620af6178c8e02d602bfc98fcd3a7", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/jonthegeek/actions/runs/28728128787" }, { "r": "4.6.0", "os": "wasm", "version": "1.0.2.9000", "date": "2026-07-05T03:28:31.000Z", "commit": "b02c1a74923301545366805680e54091675305c6", "fileid": "https://r2.ropensci.org/044e150ea0720930fb3ddd1c73c6a565c70b4a4a378beb3d8ad8c50f7509f51a", "status": "success", "buildurl": "https://github.com/r-universe/jonthegeek/actions/runs/28728128787" }, { "r": "4.7.0", "os": "win", "version": "1.0.2.9000", "date": "2026-07-05T03:27:49.000Z", "commit": "b02c1a74923301545366805680e54091675305c6", "fileid": "https://r2.ropensci.org/82baa588c968c4ac83fc93cb6788810c5b90090e5c353a94c4dfa05e0aeb0d1a", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/jonthegeek/actions/runs/28728128787" }, { "r": "4.5.3", "os": "win", "version": "1.0.2.9000", "date": "2026-07-05T03:27:43.000Z", "commit": "b02c1a74923301545366805680e54091675305c6", "fileid": "https://r2.ropensci.org/fa2729c1ab2e82c2af651192a065344d5d65e2e38f84b3aa5bc3c97d889205b3", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/jonthegeek/actions/runs/28728128787" }, { "r": "4.6.1", "os": "win", "version": "1.0.2.9000", "date": "2026-07-05T03:27:50.000Z", "commit": "b02c1a74923301545366805680e54091675305c6", "fileid": "https://r2.ropensci.org/98777d6f241e105807ae5826797a1768e32c7dbfc7e811bb05f40919a8dd51b1", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/jonthegeek/actions/runs/28728128787" } ] }