{ "_id": "6a55f91cff0138dec5d6b27b", "Package": "RmecabKo", "Type": "Package", "Title": "Korean Text Analysis with 'MeCab'", "Version": "0.3.0", "Authors@R": "person(\"Junhewk\", \"Kim\", role = c(\"aut\", \"cre\"),\nemail = \"junhewk.kim@gmail.com\")", "Description": "A Korean text-analysis layer over the 'MeCab'\nmorphological analyzer. Provides tokenizers that follow the\n'tokenizers' contract for use with 'tidytext', morpheme-aware\nn-grams, a curated Korean stopword table, access to the KNU\nsentiment lexicon, friendly user-dictionary management,\npredicate lemmatization, keyword extraction, keyword-in-context\nconcordances, and light text normalization. The native 'MeCab'\ninterface and dictionary compilation are provided by\n'RcppMeCab'.", "License": "GPL (>= 2)", "URL": "https://github.com/junhewk/RmecabKo", "BugReports": "https://github.com/junhewk/RmecabKo/issues", "Encoding": "UTF-8", "LazyData": "true", "VignetteBuilder": "knitr", "Config/testthat/edition": "3", "Config/roxygen2/version": "8.0.0", "Config/pak/sysreqs": "make libicu-dev", "Repository": "https://junhewk.r-universe.dev", "Date/Publication": "2026-07-14 07:05:31 UTC", "RemoteUrl": "https://github.com/junhewk/rmecabko", "RemoteRef": "HEAD", "RemoteSha": "2064b1b5a4a023e890cb724c1ceb6845625ce206", "NeedsCompilation": "yes", "Packaged": { "Date": "2026-07-14 08:47:24 UTC", "User": "root" }, "Author": "Junhewk Kim [aut, cre]", "Maintainer": "Junhewk Kim ", "_user": "junhewk", "_type": "src", "_file": "RmecabKo_0.3.0.tar.gz", "_fileid": "https://r2.ropensci.org/197f1500d92f7a7fdc21d44bec3fad210b55595bb45b10d10ac6bf1088919b68", "_filesize": 188684, "_sha256": "197f1500d92f7a7fdc21d44bec3fad210b55595bb45b10d10ac6bf1088919b68", "_expires": "2026-10-22T08:53:46.000Z", "_created": "2026-07-14T08:47:24.000Z", "_published": "2026-07-14T08:53:47.790Z", "_jobs": [ { "job": 87040559095, "time": 156, "config": "linux-devel-arm64", "r": "4.7.0", "check": "OK", "artifact": "8305275031" }, { "job": 87040559125, "time": 174, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "8305281933" }, { "job": 87040559206, "time": 163, "config": "linux-release-arm64", "r": "4.6.1", "check": "OK", "artifact": "8305278065" }, { "job": 87040559098, "time": 163, "config": "linux-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "8305277311" }, { "job": 87040559167, "time": 114, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "8305256418" }, { "job": 87040559177, "time": 335, "config": "macos-oldrel-x86_64", "r": "4.5.3", "check": "OK", "artifact": "8305350539" }, { "job": 87040559232, "time": 125, "config": "macos-release-arm64", "r": "4.6.1", "check": "OK", "artifact": "8305261197" }, { "job": 87040559136, "time": 293, "config": "macos-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "8305331798" }, { "job": 87039819117, "time": 218, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "8305207571" }, { "job": 87040559147, "time": 146, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "8305269519" }, { "job": 87040559122, "time": 121, "config": "windows-devel", "r": "4.7.0", "check": "OK", "artifact": "8305259384" }, { "job": 87040559100, "time": 130, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "8305263222" }, { "job": 87040559149, "time": 123, "config": "windows-release", "r": "4.6.1", "check": "OK", "artifact": "8305260753" } ], "_host": "GitHub-Actions", "_buildurl": "https://github.com/r-universe/junhewk/actions/runs/29319074914", "_status": "success", "_upstream": "https://github.com/junhewk/rmecabko", "_commit": { "id": "2064b1b5a4a023e890cb724c1ceb6845625ce206", "author": "Junhewk Kim ", "committer": "Junhewk Kim ", "message": "CI: install Pandoc for the vignette build\n\n0.3.0 adds an R Markdown (html_vignette) vignette, which requires Pandoc to\nbuild. The workflow had no Pandoc because 0.2.x shipped no vignette, so\nR CMD build failed at \"creating vignettes\". Add r-lib/actions/setup-pandoc.\n\nCo-Authored-By: Claude Fable 5 \n", "time": 1784012731 }, "_maintainer": { "name": "Junhewk Kim", "email": "junhewk.kim@gmail.com", "login": "junhewk", "description": "Medical Ethicist, AI-Based Edutech Developer", "uuid": 16641432 }, "_distro": "resolute", "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 3.6.0", "role": "Depends" }, { "package": "Rcpp", "role": "LinkingTo" }, { "package": "Rcpp", "role": "Imports" }, { "package": "RcppMeCab", "version": ">= 0.0.1.7", "role": "Imports" }, { "package": "stringi", "role": "Imports" }, { "package": "testthat", "version": ">= 3.0.0", "role": "Suggests" }, { "package": "withr", "role": "Suggests" }, { "package": "jsonlite", "role": "Suggests" }, { "package": "tibble", "role": "Suggests" }, { "package": "dplyr", "role": "Suggests" }, { "package": "tidytext", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" } ], "_owner": "junhewk", "_selfowned": true, "_usedby": 0, "_updates": [ { "week": "2026-28", "n": 4 }, { "week": "2026-29", "n": 8 } ], "_tags": [ { "name": "v0.3.0", "date": "2026-07-14" } ], "_topics": [ "korean", "nlp", "pos", "tagger", "cpp" ], "_stars": 10, "_contributors": [ { "user": "junhewk", "count": 37, "uuid": 16641432 } ], "_userbio": { "uuid": 16641432, "type": "user", "name": "Junhewk Kim", "followers": 25, "description": "Medical Ethicist, AI-Based Edutech Developer" }, "_downloads": { "count": 263, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/RmecabKo" }, "_devurl": "https://github.com/junhewk/rmecabko", "_searchresults": 100, "_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/RmecabKo.html", "manual.pdf" ], "_homeurl": "https://github.com/junhewk/rmecabko", "_realowner": "junhewk", "_cranurl": true, "_releases": [ { "version": "0.1.6", "date": "2017-10-06" }, { "version": "0.1.6.2", "date": "2018-02-13" } ], "_exports": [ "dict_add_words", "dict_compile", "dict_path", "dict_remove_words", "dict_use", "dict_words", "install_mecab", "keywords_textrank", "keywords_tfidf", "kwic", "lemmatize_morphemes", "lexicon_knu", "nouns", "pos", "stopwords_ko_tags", "stopwords_ko_words", "text_normalize", "token_lemma", "token_morph", "token_ngrams", "token_nouns", "token_words", "words" ], "_datasets": [ { "name": "demo_ko", "title": "Korean demonstration sentences", "object": "demo_ko", "class": [ "character" ], "fields": [], "table": false, "tojson": true }, { "name": "stopwords_ko", "title": "Korean stopword table", "object": "stopwords_ko", "class": [ "data.frame" ], "fields": [ "word", "tag", "category" ], "rows": 170, "table": true, "tojson": true } ], "_help": [ { "page": "demo_ko", "title": "Korean demonstration sentences", "topics": [ "demo_ko" ] }, { "page": "dictionary", "title": "Manage a MeCab user dictionary from R", "topics": [ "dict_add_words", "dict_compile", "dict_path", "dict_remove_words", "dict_use", "dict_words" ] }, { "page": "install_mecab", "title": "Deprecated MeCab installer", "topics": [ "install_mecab" ] }, { "page": "keywords_textrank", "title": "Keyword extraction with TextRank", "topics": [ "keywords_textrank" ] }, { "page": "keywords_tfidf", "title": "Keyword extraction with TF-IDF", "topics": [ "keywords_tfidf" ] }, { "page": "kwic", "title": "Keyword-in-context concordance", "topics": [ "kwic" ] }, { "page": "lemmatize_morphemes", "title": "Recover dictionary forms of Korean predicates", "topics": [ "lemmatize_morphemes" ] }, { "page": "lexicon_knu", "title": "Korean sentiment lexicon (KNU)", "topics": [ "lexicon_knu" ] }, { "page": "nouns", "title": "Extract Korean nouns", "topics": [ "nouns" ] }, { "page": "pos", "title": "Korean part-of-speech tagging", "topics": [ "pos" ] }, { "page": "stopwords_ko", "title": "Korean stopword table", "topics": [ "stopwords_ko" ] }, { "page": "stopwords_ko_tags", "title": "Korean stopword POS tags", "topics": [ "stopwords_ko_tags" ] }, { "page": "stopwords_ko_words", "title": "Korean stopword surfaces", "topics": [ "stopwords_ko_words" ] }, { "page": "text_normalize", "title": "Normalize Korean text before tokenizing", "topics": [ "text_normalize" ] }, { "page": "token_lemma", "title": "Tokenize Korean text into predicate dictionary forms", "topics": [ "token_lemma" ] }, { "page": "token", "title": "Korean morpheme tokenizers", "topics": [ "token_morph", "token_nouns", "token_words" ] }, { "page": "token_ngrams", "title": "Korean morpheme n-grams and skip-grams", "topics": [ "token_ngrams" ] }, { "page": "words", "title": "Extract Korean content words", "topics": [ "words" ] } ], "_readme": "https://github.com/junhewk/rmecabko/raw/HEAD/README.md", "_rundeps": [ "BH", "Rcpp", "RcppMeCab", "RcppParallel", "stringi" ], "_sysdeps": [ { "shlib": "libstdc++", "package": "libstdc++6", "source": "gcc", "version": "16-20260322-1ubuntu1", "name": "c++", "homepage": "http://gcc.gnu.org/", "description": "GNU Standard C++ Library v3" } ], "_vignettes": [ { "source": "korean-text-analysis.Rmd", "filename": "korean-text-analysis.html", "title": "Korean text analysis with RmecabKo", "engine": "knitr::rmarkdown", "headings": [ "Setup", "Normalizing text", "A tidy tokenization", "Removing stopwords", "Keywords and TF-IDF", "Sentiment", "N-grams, lemmas, and concordances", "Teaching the analyzer new words" ], "created": "2026-07-14 04:03:50", "modified": "2026-07-14 04:14:52", "commits": 2 } ], "_score": 6, "_indexed": true, "_nocasepkg": "rmecabko", "_universes": [ "junhewk" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.3.0", "date": "2026-07-14T08:50:08.000Z", "distro": "resolute", "arch": "aarch64", "commit": "2064b1b5a4a023e890cb724c1ceb6845625ce206", "fileid": "https://r2.ropensci.org/bf7ac1511a260301124c4d16e09e62af90f7e125c7141e29a39188c21b0febda", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/junhewk/actions/runs/29319074914" }, { "r": "4.7.0", "os": "linux", "version": "0.3.0", "date": "2026-07-14T08:50:19.000Z", "distro": "resolute", "arch": "x86_64", "commit": "2064b1b5a4a023e890cb724c1ceb6845625ce206", "fileid": "https://r2.ropensci.org/813cd0025bdb9542d498b759f2cbc776b7cbe62187849948d8388afaa813ef0c", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/junhewk/actions/runs/29319074914" }, { "r": "4.6.1", "os": "linux", "version": "0.3.0", "date": "2026-07-14T08:50:15.000Z", "distro": "resolute", "arch": "aarch64", "commit": "2064b1b5a4a023e890cb724c1ceb6845625ce206", "fileid": "https://r2.ropensci.org/97c507a6b954dcc75e257a6b30323af459272b0fc9f6ffd5335e67b928d11031", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/junhewk/actions/runs/29319074914" }, { "r": "4.6.1", "os": "linux", "version": "0.3.0", "date": "2026-07-14T08:50:10.000Z", "distro": "resolute", "arch": "x86_64", "commit": "2064b1b5a4a023e890cb724c1ceb6845625ce206", "fileid": "https://r2.ropensci.org/e6d80a28691b268480697a75acbe670bb4e64b32ea46e218bc4f7371348d557d", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/junhewk/actions/runs/29319074914" }, { "r": "4.5.3", "os": "mac", "version": "0.3.0", "date": "2026-07-14T08:49:20.000Z", "arch": "aarch64", "commit": "2064b1b5a4a023e890cb724c1ceb6845625ce206", "fileid": "https://r2.ropensci.org/a076cde57b69891c94629295b6af9c1e2ba0eeb79d22c68a625274d15381d2d2", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/junhewk/actions/runs/29319074914" }, { "r": "4.5.3", "os": "mac", "version": "0.3.0", "date": "2026-07-14T08:52:09.000Z", "arch": "x86_64", "commit": "2064b1b5a4a023e890cb724c1ceb6845625ce206", "fileid": "https://r2.ropensci.org/7138c2ed3e88edcfcac7d138c024673d411a4e9f8ad076f3991c3f9f482d215c", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/junhewk/actions/runs/29319074914" }, { "r": "4.6.1", "os": "mac", "version": "0.3.0", "date": "2026-07-14T08:49:25.000Z", "arch": "aarch64", "commit": "2064b1b5a4a023e890cb724c1ceb6845625ce206", "fileid": "https://r2.ropensci.org/b7ae9a76cd8714e7f6f92349e1f2b49be368255db34da380772368032c65c953", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/junhewk/actions/runs/29319074914" }, { "r": "4.6.1", "os": "mac", "version": "0.3.0", "date": "2026-07-14T08:51:34.000Z", "arch": "x86_64", "commit": "2064b1b5a4a023e890cb724c1ceb6845625ce206", "fileid": "https://r2.ropensci.org/fe860b1bdd2de0d81434426cd4c1de9f6baffb199e0698dab0a64f707c1cdc97", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/junhewk/actions/runs/29319074914" }, { "r": "4.6.0", "os": "wasm", "version": "0.3.0", "date": "2026-07-14T08:50:07.000Z", "arch": "emscripten", "commit": "2064b1b5a4a023e890cb724c1ceb6845625ce206", "fileid": "https://r2.ropensci.org/f3c3857212a0155b2e3dc4a44f86fdb2aabb3f246ab2d2a030e22be805e2e31d", "status": "success", "buildurl": "https://github.com/r-universe/junhewk/actions/runs/29319074914" }, { "r": "4.7.0", "os": "win", "version": "0.3.0", "date": "2026-07-14T08:49:02.000Z", "arch": "x86_64", "commit": "2064b1b5a4a023e890cb724c1ceb6845625ce206", "fileid": "https://r2.ropensci.org/9ad59237bf0509baa9d859eb38e5c1a08f8bfee70badea40ac4657554c1bce74", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/junhewk/actions/runs/29319074914" }, { "r": "4.5.3", "os": "win", "version": "0.3.0", "date": "2026-07-14T08:49:11.000Z", "arch": "x86_64", "commit": "2064b1b5a4a023e890cb724c1ceb6845625ce206", "fileid": "https://r2.ropensci.org/ffae8d7a7147a5016d244a31f249b66318eb9c572f789e034538de3c6920aef4", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/junhewk/actions/runs/29319074914" }, { "r": "4.6.1", "os": "win", "version": "0.3.0", "date": "2026-07-14T08:49:09.000Z", "arch": "x86_64", "commit": "2064b1b5a4a023e890cb724c1ceb6845625ce206", "fileid": "https://r2.ropensci.org/e7c94afdf3c0a6be2badfb4cf77dcddb64846b38f73a1d6c9abc901d9e57073b", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/junhewk/actions/runs/29319074914" } ] }