{ "_id": "6a30fec73efcd9bda4351648", "Package": "morphemepiece", "Type": "Package", "Title": "Morpheme Tokenization", "Version": "1.2.3", "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": "Tokenize text into morphemes. The morphemepiece algorithm\nuses a lookup table to determine the morpheme breakdown of\nwords, and falls back on a modified wordpiece tokenization\nalgorithm for words not found in the lookup table.", "URL": "https://github.com/macmillancontentscience/morphemepiece", "BugReports": "https://github.com/macmillancontentscience/morphemepiece/issues", "License": "Apache License (>= 2)", "Encoding": "UTF-8", "RoxygenNote": "7.1.2", "Roxygen": "list(markdown = TRUE)", "VignetteBuilder": "knitr", "Config/testthat/edition": "3", "Config/pak/sysreqs": "cmake make libicu-dev libuv1-dev libx11-dev", "Repository": "https://macmillancontentscience.r-universe.dev", "Date/Publication": "2022-04-15 21:02:22 UTC", "RemoteUrl": "https://github.com/macmillancontentscience/morphemepiece", "RemoteRef": "HEAD", "RemoteSha": "bc071b1a03226b2441c431d263982f862e4dc7fd", "NeedsCompilation": "no", "Packaged": { "Date": "2026-06-16 07:41:14 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 ", "MD5sum": "6160f0f7b9556004fa3534369ef91350", "_user": "macmillancontentscience", "_type": "src", "_file": "morphemepiece_1.2.3.tar.gz", "_fileid": "1d7d9ff237da837b49148917439b593a3ef8dafad32bb6af552099c4f60b17d8", "_filesize": 142805, "_sha256": "1d7d9ff237da837b49148917439b593a3ef8dafad32bb6af552099c4f60b17d8", "_created": "2026-06-16T07:41:14.000Z", "_published": "2026-06-16T07:44:07.681Z", "_distro": "noble", "_jobs": [ { "job": 81605363179, "time": 134, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "NOTE", "artifact": "7660340933" }, { "job": 81605363298, "time": 137, "config": "linux-release-x86_64", "r": "4.6.0", "check": "NOTE", "artifact": "7660341810" }, { "job": 81605363294, "time": 97, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "NOTE", "artifact": "7660327759" }, { "job": 81605363173, "time": 89, "config": "macos-release-arm64", "r": "4.6.0", "check": "NOTE", "artifact": "7660325247" }, { "job": 81604877605, "time": 183, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "7660296835" }, { "job": 81605363111, "time": 122, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7660335220" }, { "job": 81605363186, "time": 76, "config": "windows-devel", "r": "4.7.0", "check": "NOTE", "artifact": "7660322254" }, { "job": 81605363221, "time": 82, "config": "windows-oldrel", "r": "4.5.3", "check": "NOTE", "artifact": "7660323266" }, { "job": 81605363184, "time": 84, "config": "windows-release", "r": "4.6.0", "check": "NOTE", "artifact": "7660324321" } ], "_buildurl": "https://github.com/r-universe/macmillancontentscience/actions/runs/27601943712", "_status": "success", "_host": "GitHub-Actions", "_upstream": "https://github.com/macmillancontentscience/morphemepiece", "_commit": { "id": "bc071b1a03226b2441c431d263982f862e4dc7fd", "author": "Jonathan Bratt <33073024+jonathanbratt@users.noreply.github.com>", "committer": "GitHub ", "message": "prep for CRAN (#30)\n\n", "time": 1650056542 }, "_maintainer": { "name": "Jonathan Bratt", "email": "jonathan.bratt@macmillan.com", "login": "jonathanbratt", "description": "", "uuid": 33073024, "orcid": "0000-0003-2859-0076" }, "_registered": true, "_dependencies": [ { "package": "dlr", "version": ">= 1.0.0", "role": "Imports" }, { "package": "fastmatch", "role": "Imports" }, { "package": "magrittr", "role": "Imports" }, { "package": "memoise", "version": ">= 2.0.0", "role": "Imports" }, { "package": "morphemepiece.data", "role": "Imports" }, { "package": "piecemaker", "version": ">= 1.0.0", "role": "Imports" }, { "package": "purrr", "version": ">= 0.3.4", "role": "Imports" }, { "package": "readr", "role": "Imports" }, { "package": "rlang", "role": "Imports" }, { "package": "stringr", "version": ">= 1.4.0", "role": "Imports" }, { "package": "dplyr", "role": "Suggests" }, { "package": "fs", "role": "Suggests" }, { "package": "ggplot2", "role": "Suggests" }, { "package": "here", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "remotes", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" }, { "package": "testthat", "version": ">= 3.0.0", "role": "Suggests" }, { "package": "utils", "role": "Suggests" } ], "_owner": "macmillancontentscience", "_selfowned": true, "_usedby": 0, "_updates": [], "_tags": [], "_stars": 11, "_contributors": [ { "user": "jonathanbratt", "count": 16, "uuid": 33073024 }, { "user": "jonthegeek", "count": 11, "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": 267, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/morphemepiece" }, "_devurl": "https://github.com/macmillancontentscience/morphemepiece", "_searchresults": 11, "_rbuild": "4.6.0", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/morphemepiece.html", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "manual.pdf" ], "_homeurl": "https://github.com/macmillancontentscience/morphemepiece", "_realowner": "macmillancontentscience", "_cranurl": true, "_releases": [ { "version": "1.0.0", "date": "2021-09-09" }, { "version": "1.0.1", "date": "2021-09-17" }, { "version": "1.1.0", "date": "2021-10-27" }, { "version": "1.1.2", "date": "2021-12-06" }, { "version": "1.2.1", "date": "2022-04-08" }, { "version": "1.2.3", "date": "2022-04-16" } ], "_exports": [ "load_lookup", "load_or_retrieve_lookup", "load_or_retrieve_vocab", "load_vocab", "morphemepiece_cache_dir", "morphemepiece_lookup", "morphemepiece_tokenize", "morphemepiece_vocab", "prepare_vocab", "set_morphemepiece_cache_dir" ], "_help": [ { "page": "morphemepiece-package", "title": "morphemepiece: Morpheme Tokenization", "topics": [ "morphemepiece-package" ] }, { "page": "load_lookup", "title": "Load a morphemepiece lookup file", "topics": [ "load_lookup" ] }, { "page": "load_or_retrieve_lookup", "title": "Load a lookup file, or retrieve from cache", "topics": [ "load_or_retrieve_lookup" ] }, { "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": "morphemepiece_cache_dir", "title": "Retrieve Directory for Morphemepiece Cache", "topics": [ "morphemepiece_cache_dir" ] }, { "page": "morphemepiece_tokenize", "title": "Tokenize Sequence with Morpheme Pieces", "topics": [ "morphemepiece_tokenize" ] }, { "page": "prepare_vocab", "title": "Format a Token List as a Vocabulary", "topics": [ "prepare_vocab" ] }, { "page": "set_morphemepiece_cache_dir", "title": "Set a Cache Directory for Morphemepiece", "topics": [ "set_morphemepiece_cache_dir" ] } ], "_readme": "https://github.com/macmillancontentscience/morphemepiece/raw/HEAD/README.md", "_rundeps": [ "bit", "bit64", "cachem", "cli", "clipr", "cpp11", "crayon", "digest", "dlr", "fastmap", "fastmatch", "fs", "glue", "hms", "lifecycle", "magrittr", "memoise", "morphemepiece.data", "piecemaker", "pillar", "pkgconfig", "prettyunits", "progress", "purrr", "R6", "rappdirs", "readr", "rlang", "stringi", "stringr", "tibble", "tidyselect", "tzdb", "utf8", "vctrs", "vroom", "withr" ], "_vignettes": [ { "source": "generating_vocab.Rmd", "filename": "generating_vocab.html", "title": "Generating a Vocabulary and Lookup", "engine": "knitr::rmarkdown", "headings": [ "Check coverage", "Other measures of coverage quality" ], "created": "2021-07-29 19:56:28", "modified": "2021-10-26 20:24:03", "commits": 5 }, { "source": "algorithm_test.Rmd", "filename": "algorithm_test.html", "title": "Testing the fall-through algorithm", "engine": "knitr::rmarkdown", "headings": [], "created": "2021-07-29 19:56:28", "modified": "2021-09-06 19:26:32", "commits": 3 } ], "_score": 5.08278537031645, "_indexed": true, "_nocasepkg": "morphemepiece", "_universes": [ "macmillancontentscience", "jonathanbratt" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "1.2.3", "date": "2026-06-16T07:43:33.000Z", "distro": "noble", "commit": "bc071b1a03226b2441c431d263982f862e4dc7fd", "fileid": "f7cc2b17207280c0c4b59df460ac51abe2b1ae208cc3fd381481970135da8f1a", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/macmillancontentscience/actions/runs/27601943712" }, { "r": "4.6.0", "os": "linux", "version": "1.2.3", "date": "2026-06-16T07:43:34.000Z", "distro": "noble", "commit": "bc071b1a03226b2441c431d263982f862e4dc7fd", "fileid": "c03ddccb549735a40dae6878b6444d2b9d08fcd0a1d1a4e9794423d02c752126", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/macmillancontentscience/actions/runs/27601943712" }, { "r": "4.5.3", "os": "mac", "version": "1.2.3", "date": "2026-06-16T07:42:52.000Z", "commit": "bc071b1a03226b2441c431d263982f862e4dc7fd", "fileid": "4557a2e66fe6eedf672393f3c616a2c4127c4a90048034680c06480f04c5f19e", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/macmillancontentscience/actions/runs/27601943712" }, { "r": "4.6.0", "os": "mac", "version": "1.2.3", "date": "2026-06-16T07:42:43.000Z", "commit": "bc071b1a03226b2441c431d263982f862e4dc7fd", "fileid": "43d3f0b974643249f31b2a5b7ffedcfdf3ab63329af10a6828b82174a8e37bae", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/macmillancontentscience/actions/runs/27601943712" }, { "r": "4.6.0", "os": "wasm", "version": "1.2.3", "date": "2026-06-16T07:43:28.000Z", "commit": "bc071b1a03226b2441c431d263982f862e4dc7fd", "fileid": "70c21181ad620973919e60a85caf07312d8298e7bd40e21e027bd0a2b4f36e61", "status": "success", "buildurl": "https://github.com/r-universe/macmillancontentscience/actions/runs/27601943712" }, { "r": "4.7.0", "os": "win", "version": "1.2.3", "date": "2026-06-16T07:42:28.000Z", "commit": "bc071b1a03226b2441c431d263982f862e4dc7fd", "fileid": "70b2497d00532d43115137bd1626ae3de2c8ad59816d5111ce148e2eb7376943", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/macmillancontentscience/actions/runs/27601943712" }, { "r": "4.5.3", "os": "win", "version": "1.2.3", "date": "2026-06-16T07:42:28.000Z", "commit": "bc071b1a03226b2441c431d263982f862e4dc7fd", "fileid": "f13e41fb919e6f1fe454ed81ab8534bff6c0012835cd40fcc39b76e8d74df477", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/macmillancontentscience/actions/runs/27601943712" }, { "r": "4.6.0", "os": "win", "version": "1.2.3", "date": "2026-06-16T07:42:29.000Z", "commit": "bc071b1a03226b2441c431d263982f862e4dc7fd", "fileid": "9fb86da355b4ed6a30f2eeda017445c4e2d53c0884810ccc8d3903639932b007", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/macmillancontentscience/actions/runs/27601943712" } ] }