{ "_id": "6a1fe56cb401979e7343c15e", "Package": "tmcn", "License": "LGPL", "Title": "A Text Mining Toolkit for Chinese", "Type": "Package", "LazyLoad": "yes", "Author": "Jian Li", "Maintainer": "Jian Li ", "Description": "A Text mining toolkit for Chinese, which includes\nfacilities for Chinese string processing, Chinese NLP\nsupporting, encoding detecting and converting. Moreover, it\nprovides some functions to support 'tm' package in Chinese.", "Version": "0.2-13", "Date": "2019-08-04", "RoxygenNote": "6.1.1", "NeedsCompilation": "yes", "Packaged": { "Date": "2026-06-03 08:24:40 UTC", "User": "root" }, "Repository": "https://cran.r-universe.dev", "Date/Publication": "2019-08-08 03:40:02 UTC", "RemoteUrl": "https://github.com/cran/tmcn", "RemoteRef": "HEAD", "RemoteSha": "408a39fe1ab2da1d9afd95fc8df5419c8b2e13d9", "MD5sum": "c264e24b42eb2cc0bb4593e7c92cdb05", "_user": "cran", "_type": "src", "_file": "tmcn_0.2-13.tar.gz", "_fileid": "e8aa0191e3ebdcbc572d265d491f9d93cacee06024cf8f96523436be655eb098", "_filesize": 1087423, "_sha256": "e8aa0191e3ebdcbc572d265d491f9d93cacee06024cf8f96523436be655eb098", "_created": "2026-06-03T08:24:40.000Z", "_published": "2026-06-03T08:27:24.228Z", "_distro": "noble", "_jobs": [ { "job": 79252336660, "time": 127, "config": "linux-devel-arm64", "r": "4.7.0", "check": "OK", "artifact": "7379430243" }, { "job": 79252336351, "time": 121, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "7379427074" }, { "job": 79252336827, "time": 116, "config": "linux-release-arm64", "r": "4.6.0", "check": "OK", "artifact": "7379425698" }, { "job": 79252336248, "time": 124, "config": "linux-release-x86_64", "r": "4.6.0", "check": "OK", "artifact": "7379427415" }, { "job": 79251899963, "time": 155, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "7379384522" }, { "job": 79252336257, "time": 111, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7379423277" } ], "_buildurl": "https://github.com/r-universe/cran/actions/runs/26872709987", "_status": "success", "_host": "GitHub-Actions", "_upstream": "https://github.com/cran/tmcn", "_commit": { "id": "408a39fe1ab2da1d9afd95fc8df5419c8b2e13d9", "author": "Jian Li ", "committer": "cran-robot ", "message": "version 0.2-13\n", "time": 1565235602 }, "_maintainer": { "name": "Jian Li", "email": "rweibo@sina.com" }, "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 3.0.0", "role": "Depends" }, { "package": "utils", "role": "Depends" }, { "package": "tm", "role": "Suggests" } ], "_owner": "cran", "_selfowned": false, "_usedby": 5, "_updates": [], "_tags": [], "_stars": 1, "_userbio": { "uuid": 6899542, "type": "organization", "name": "cran", "description": "Unofficial read-only mirror of all CRAN R packages" }, "_downloads": { "count": 1319, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/tmcn" }, "_mentions": 1, "_searchresults": 187, "_rbuild": "4.6.0", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/tmcn.html", "manual.pdf" ], "_realowner": "cran", "_cranurl": false, "_releases": [ { "version": "0.2-8", "date": "2017-06-12" }, { "version": "0.2-12", "date": "2018-03-03" }, { "version": "0.2-13", "date": "2019-08-08" } ], "_exports": [ "catUTF8", "createDTM", "createTDM", "createWordFreq", "getCharset", "isBIG5", "isGB18030", "isGB2312", "isGBK", "isUTF8", "left", "revUTF8", "right", "setchs", "setcht", "setuk", "stopwordsCN", "strcap", "strextract", "strpad", "strstrip", "toPinyin", "toTrad", "toUTF8" ], "_datasets": [ { "name": "GBK", "title": "GBK character set", "object": "GBK", "file": "GBK.rda", "class": [ "data.frame" ], "fields": [ "GBK", "py0", "py", "Radical", "Stroke_Num_Radical", "Stroke_Order", "Structure", "Freq" ], "rows": 20902, "table": true, "tojson": true }, { "name": "NTUSD", "title": "National Taiwan University Semantic Dictionary", "object": "NTUSD", "file": "NTUSD.rda", "class": [ "list" ], "fields": [], "table": false, "tojson": true }, { "name": "SIMTRA", "title": "Dictionary of simplified and traditional Chinese", "object": "SIMTRA", "file": "SIMTRA.rda", "class": [ "data.frame" ], "fields": [ "Sim", "Tra" ], "rows": 1, "table": true, "tojson": true }, { "name": "SPORT", "title": "Sport news.", "object": "SPORT", "file": "SPORT.rda", "class": [ "data.frame" ], "fields": [ "id", "time", "title", "class", "abstract", "content" ], "rows": 2357, "table": true, "tojson": true }, { "name": "STOPWORDS", "title": "Dictionary of Chinese stop words", "object": "STOPWORDS", "file": "STOPWORDS.rda", "class": [ "data.frame" ], "fields": [ "word" ], "rows": 504, "table": true, "tojson": true } ], "_help": [ { "page": "catUTF8", "title": "Print the UTF-8 codes of a string.", "topics": [ "catUTF8" ] }, { "page": "createDTM", "title": "Create a Chinese term-document matrix or a document-term matrix.", "topics": [ "createDTM", "createTDM" ] }, { "page": "createWordFreq", "title": "Create a word frequency data.frame.", "topics": [ "createWordFreq" ] }, { "page": "GBK", "title": "GBK character set", "topics": [ "GBK" ] }, { "page": "getCharset", "title": "Get the current encoding of the locale.", "topics": [ "getCharset" ] }, { "page": "isBIG5", "title": "Indicate whether the encoding of input string is BIG5.", "topics": [ "isBIG5" ] }, { "page": "isGB18030", "title": "Indicate whether the encoding of input string is GB18030.", "topics": [ "isGB18030" ] }, { "page": "isGB2312", "title": "Indicate whether the encoding of input string is GB2312.", "topics": [ "isGB2312" ] }, { "page": "isGBK", "title": "Indicate whether the encoding of input string is GBK.", "topics": [ "isGBK" ] }, { "page": "isUTF8", "title": "Indicate whether the encoding of input string is UTF-8.", "topics": [ "isUTF8" ] }, { "page": "left", "title": "Extract the left or right substrings in a character vector.", "topics": [ "left", "right" ] }, { "page": "NTUSD", "title": "National Taiwan University Semantic Dictionary", "topics": [ "NTUSD" ] }, { "page": "revUTF8", "title": "Revert UTF-8 string to Chinese character.", "topics": [ "revUTF8" ] }, { "page": "setchs", "title": "Set locale to Simplified Chinese/Traditional Chinese/UK.", "topics": [ "setchs", "setcht", "setuk" ] }, { "page": "SIMTRA", "title": "Dictionary of simplified and traditional Chinese", "topics": [ "SIMTRA" ] }, { "page": "SPORT", "title": "Sport news.", "topics": [ "SPORT" ] }, { "page": "STOPWORDS", "title": "Dictionary of Chinese stop words", "topics": [ "STOPWORDS" ] }, { "page": "stopwordsCN", "title": "Return Chinese stop words.", "topics": [ "stopwordsCN" ] }, { "page": "strcap", "title": "Mixed case capitalizing.", "topics": [ "strcap" ] }, { "page": "strextract", "title": "Extract matched substrings by regular expression.", "topics": [ "strextract" ] }, { "page": "strpad", "title": "Pad a string to a specified length with a padding character.", "topics": [ "strpad" ] }, { "page": "strstrip", "title": "Trim space of a string.", "topics": [ "strstrip" ] }, { "page": "toPinyin", "title": "Convert a chinese text to pinyin format.", "topics": [ "toPinyin" ] }, { "page": "toTrad", "title": "Convert a Chinese text from simplified to traditional characters and vice versa.", "topics": [ "toTrad" ] }, { "page": "toUTF8", "title": "Convert encoding of Chinese string to UTF-8.", "topics": [ "toUTF8" ] } ], "_rundeps": [], "_score": 3.5681776611385456, "_indexed": true, "_nocasepkg": "tmcn", "_universes": [ "cran" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.2-13", "date": "2026-06-03T08:27:01.000Z", "distro": "noble", "arch": "aarch64", "commit": "408a39fe1ab2da1d9afd95fc8df5419c8b2e13d9", "fileid": "b3d4ff229175bd155e9e8ffb7c948375108357d03dc894c9e71a12e600457098", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cran/actions/runs/26872709987" }, { "r": "4.7.0", "os": "linux", "version": "0.2-13", "date": "2026-06-03T08:26:49.000Z", "distro": "noble", "arch": "x86_64", "commit": "408a39fe1ab2da1d9afd95fc8df5419c8b2e13d9", "fileid": "05948ca05b8a13ca113412a013fab2af257e93e63ae32fe605a29e88059cdb33", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cran/actions/runs/26872709987" }, { "r": "4.6.0", "os": "linux", "version": "0.2-13", "date": "2026-06-03T08:26:49.000Z", "distro": "noble", "arch": "aarch64", "commit": "408a39fe1ab2da1d9afd95fc8df5419c8b2e13d9", "fileid": "6192e6de63334667ffca9fa98d12b4f9c481c0fd88a1f6e7dcd70ecddf002098", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cran/actions/runs/26872709987" }, { "r": "4.6.0", "os": "linux", "version": "0.2-13", "date": "2026-06-03T08:26:51.000Z", "distro": "noble", "arch": "x86_64", "commit": "408a39fe1ab2da1d9afd95fc8df5419c8b2e13d9", "fileid": "ccc35c85cad352e170cd8235a520bc653eafbbfe2c9ba7e39c99a637d3524460", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cran/actions/runs/26872709987" }, { "r": "4.6.0", "os": "wasm", "version": "0.2-13", "date": "2026-06-03T08:26:48.000Z", "arch": "emscripten", "commit": "408a39fe1ab2da1d9afd95fc8df5419c8b2e13d9", "fileid": "a2e02ad189fb0fe8d25ab3c10c93d6296a1e5bb8ba7c003ebe43867671033065", "status": "success", "buildurl": "https://github.com/r-universe/cran/actions/runs/26872709987" } ] }