{ "_id": "6a2002bbb401979e73445f43", "Package": "textclean", "Title": "Text Cleaning Tools", "Version": "0.9.8", "Authors@R": "c( \nperson(\"Tyler\", \"Rinker\", email = \"tyler.rinker@gmail.com\", role = c(\"aut\", \"cre\")),\nperson(\"ctwheels\", \"StackOverflow\", role = \"ctb\"),\nperson(\"Surin\", \"Space\", role = \"ctb\")\n)", "Maintainer": "Tyler Rinker ", "Description": "Tools to clean and process text. Tools are geared at\nchecking for substrings that are not optimal for analysis and\nreplacing or removing them (normalizing) with more analysis\nfriendly substrings (see Sproat, Black, Chen, Kumar, Ostendorf,\n& Richards (2001) ) or extracting\nthem into new variables. For example, emoticons are often used\nin text but not always easily handled by analysis algorithms.\nThe replace_emoticon() function replaces emoticons with word\nequivalents.", "License": "GPL-2", "LazyData": "TRUE", "RoxygenNote": "7.3.3", "Encoding": "UTF-8", "URL": "https://github.com/trinker/textclean", "BugReports": "https://github.com/trinker/textclean/issues", "Collate": "'add_comma_space.R' 'add_missing_endmark.R' 'utils.R'\n'replace_html.R' 'check_text_logicals.R' 'check_text.R'\n'drop_element.R' 'drop_row.R' 'fgsub.R' 'fix_mdyyyy.R'\n'glue-reexports.R' 'has_endmark.R' 'like.R' 'make_plural.R'\n'match_tokens.R' 'mgsub.R' 'replace_contraction.R'\n'replace_date.R' 'replace_email.R' 'replace_emoji.R'\n'replace_emoticon.R' 'replace_grade.R' 'replace_hash.R'\n'replace_incomplete.R' 'replace_internet_slang.R'\n'replace_kerning.R' 'replace_misspelling.R' 'replace_money.R'\n'replace_names.R' 'replace_non_ascii.R' 'replace_number.R'\n'replace_ordinal.R' 'replace_rating.R' 'replace_symbol.R'\n'replace_tag.R' 'replace_time.R' 'replace_to.R'\n'replace_tokens.R' 'replace_url.R' 'replace_white.R'\n'replace_word_elongation.R' 'strip.R' 'sub_holder.R' 'swap.R'\n'textclean-package.R'", "Config/pak/sysreqs": "libicu-dev", "Repository": "https://trinker.r-universe.dev", "Date/Publication": "2026-03-05 04:56:58 UTC", "RemoteUrl": "https://github.com/trinker/textclean", "RemoteRef": "HEAD", "RemoteSha": "80a30ed4677900c976cc301b9c4f26069ca824fe", "NeedsCompilation": "no", "Packaged": { "Date": "2026-06-03 10:29:10 UTC", "User": "root" }, "Author": "Tyler Rinker [aut, cre],\nctwheels StackOverflow [ctb],\nSurin Space [ctb]", "MD5sum": "831e7f436871c4ebf2b8de01e2e14594", "_user": "trinker", "_type": "src", "_file": "textclean_0.9.8.tar.gz", "_fileid": "e00639b134aa5e9ad4066c91ebe6e92b268d8f83c2756f1f2b760ecee3145b40", "_filesize": 2175065, "_sha256": "e00639b134aa5e9ad4066c91ebe6e92b268d8f83c2756f1f2b760ecee3145b40", "_created": "2026-06-03T10:29:10.000Z", "_published": "2026-06-03T10:32:26.983Z", "_distro": "noble", "_jobs": [ { "job": 79273763484, "time": 131, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "7382125481" }, { "job": 79273763492, "time": 122, "config": "linux-release-x86_64", "r": "4.6.0", "check": "OK", "artifact": "7382121991" }, { "job": 79273763522, "time": 154, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "7382132756" }, { "job": 79273763496, "time": 114, "config": "macos-release-arm64", "r": "4.6.0", "check": "OK", "artifact": "7382119136" }, { "job": 79273221036, "time": 199, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "7382079762" }, { "job": 79273763503, "time": 107, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7382116965" }, { "job": 79273763481, "time": 86, "config": "windows-devel", "r": "4.7.0", "check": "OK", "artifact": "7382109906" }, { "job": 79273763498, "time": 96, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "7382113017" }, { "job": 79273763528, "time": 98, "config": "windows-release", "r": "4.6.0", "check": "OK", "artifact": "7382114406" } ], "_buildurl": "https://github.com/r-universe/trinker/actions/runs/26878807982", "_status": "success", "_host": "GitHub-Actions", "_upstream": "https://github.com/trinker/textclean", "_commit": { "id": "80a30ed4677900c976cc301b9c4f26069ca824fe", "author": "Tyler Rinker ", "committer": "Tyler Rinker ", "message": "Fixing a number of cran warnings and errors.\n", "time": 1772686618 }, "_maintainer": { "name": "Tyler Rinker", "email": "tyler.rinker@gmail.com", "login": "trinker", "description": "Director, Data Scientist, open-source developer , #python/#rstats enthusiast, #dataviz geek, and #nlp buff", "uuid": 1763278 }, "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 3.4.0", "role": "Depends" }, { "package": "data.table", "role": "Imports" }, { "package": "english", "version": ">= 1.0-2", "role": "Imports" }, { "package": "glue", "version": ">= 1.3.0", "role": "Imports" }, { "package": "lexicon", "version": ">= 1.0.0", "role": "Imports" }, { "package": "mgsub", "version": ">= 1.5.0", "role": "Imports" }, { "package": "qdapRegex", "role": "Imports" }, { "package": "stringi", "role": "Imports" }, { "package": "textshape", "version": ">= 1.0.1", "role": "Imports" }, { "package": "utils", "role": "Imports" }, { "package": "hunspell", "role": "Suggests" }, { "package": "testthat", "role": "Suggests" } ], "_owner": "trinker", "_selfowned": true, "_usedby": 28, "_updates": [ { "week": "2026-10", "n": 5 } ], "_tags": [], "_topics": [ "data-munging", "emoticons", "regex", "text-analysis", "text-cleaning" ], "_stars": 258, "_contributors": [ { "user": "trinker", "count": 177, "uuid": 1763278 }, { "user": "tylerrinker-dev", "count": 4, "uuid": 237491193 }, { "user": "foehammer-419", "count": 2, "uuid": 44418830 }, { "user": "eliocamp", "count": 1, "uuid": 8617595 }, { "user": "kguidonimartins", "count": 1, "uuid": 8163542 }, { "user": "tonyelhabr", "count": 1, "uuid": 15663460 } ], "_userbio": { "uuid": 1763278, "type": "user", "name": "Tyler Rinker", "description": "Director, Data Scientist, open-source developer , #python/#rstats enthusiast, #dataviz geek, and #nlp buff" }, "_downloads": { "count": 6542, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/textclean" }, "_mentions": 1, "_devurl": "https://github.com/trinker/textclean", "_searchresults": 848, "_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/readme.html", "extra/readme.md", "extra/textclean.html", "manual.pdf" ], "_homeurl": "https://github.com/trinker/textclean", "_realowner": "trinker", "_cranurl": true, "_releases": [ { "version": "0.2.0", "date": "2017-01-10" }, { "version": "0.3.0", "date": "2017-01-25" }, { "version": "0.3.1", "date": "2017-02-22" }, { "version": "0.5.1", "date": "2017-12-12" }, { "version": "0.6.3", "date": "2018-01-14" }, { "version": "0.7.2", "date": "2018-04-19" }, { "version": "0.7.3", "date": "2018-04-24" }, { "version": "0.9.2", "date": "2018-06-09" }, { "version": "0.9.3", "date": "2018-07-23" }, { "version": "0.9.7", "date": "2026-03-05" } ], "_exports": [ "%like%", "%LIKE%", "%slike%", "%SLIKE%", "add_comma_space", "add_missing_endmark", "as_ordinal", "available_checks", "check_text", "drop_element", "drop_element_fixed", "drop_element_regex", "drop_empty_row", "drop_NA", "drop_row", "fgsub", "fix_mdyyyy", "glue", "glue_collapse", "has_endmark", "is_it", "keep_element", "keep_element_fixed", "keep_element_regex", "keep_row", "make_plural", "match_tokens", "mgsub", "mgsub_fixed", "mgsub_regex", "mgsub_regex_safe", "replace_contraction", "replace_curly_quote", "replace_date", "replace_email", "replace_emoji", "replace_emoji_identifier", "replace_emoticon", "replace_from", "replace_grade", "replace_hash", "replace_html", "replace_incomplete", "replace_internet_slang", "replace_kern", "replace_misspelling", "replace_money", "replace_names", "replace_non_ascii", "replace_non_ascii2", "replace_number", "replace_ordinal", "replace_rating", "replace_symbol", "replace_tag", "replace_time", "replace_to", "replace_tokens", "replace_url", "replace_white", "replace_word_elongation", "strip", "sub_holder", "swap", "which_are" ], "_datasets": [ { "name": "DATA", "title": "Fictitious Classroom Dialogue", "object": "DATA", "class": [ "data.frame" ], "fields": [ "person", "sex", "adult", "state", "code" ], "rows": 11, "table": true, "tojson": true } ], "_help": [ { "page": "like", "title": "SQL Style LIKE", "topics": [ "%LIKE%", "%like%", "%SLIKE%", "%slike%" ] }, { "page": "add_comma_space", "title": "Ensure Space After Comma", "topics": [ "add_comma_space" ] }, { "page": "add_missing_endmark", "title": "Add Missing Endmarks", "topics": [ "add_missing_endmark" ] }, { "page": "check_text", "title": "Check Text For Potential Problems", "topics": [ "available_checks", "check_text" ] }, { "page": "DATA", "title": "Fictitious Classroom Dialogue", "topics": [ "DATA" ] }, { "page": "drop_element", "title": "Filter Elements in a Vetor", "topics": [ "drop_element", "drop_element_fixed", "drop_element_regex", "keep_element", "keep_element_fixed", "keep_element_regex" ] }, { "page": "drop_row", "title": "Filter Rows That Contain Markers", "topics": [ "drop_empty_row", "drop_NA", "drop_row", "keep_row" ] }, { "page": "fgsub", "title": "Replace a Regex with an Functional Operation on the Regex Match", "topics": [ "fgsub" ] }, { "page": "fix_mdyyyy", "title": "Coerce Character m/d/yyyy to Date", "topics": [ "fix_mdyyyy" ] }, { "page": "has_endmark", "title": "Test for Incomplete Sentences", "topics": [ "has_endmark" ] }, { "page": "make_plural", "title": "Make Plural (or Verb to Singular) Versions of Words", "topics": [ "make_plural" ] }, { "page": "match_tokens", "title": "Find Tokens that Match a Regex", "topics": [ "match_tokens" ] }, { "page": "mgsub", "title": "Multiple 'gsub'", "topics": [ "mgsub", "mgsub_fixed", "mgsub_regex", "mgsub_regex_safe" ] }, { "page": "print.check_text", "title": "Prints a check_text Object", "topics": [ "print.check_text" ] }, { "page": "print.sub_holder", "title": "Prints a sub_holder object", "topics": [ "print.sub_holder" ] }, { "page": "print.which_are_locs", "title": "Prints a which_are_locs Object", "topics": [ "print.which_are_locs" ] }, { "page": "replace_contraction", "title": "Replace Contractions", "topics": [ "replace_contraction" ] }, { "page": "replace_date", "title": "Replace Dates With Words", "topics": [ "replace_date" ] }, { "page": "replace_email", "title": "Replace Email Addresses", "topics": [ "replace_email" ] }, { "page": "replace_emoji", "title": "Replace Emojis With Words/Identifier", "topics": [ "replace_emoji", "replace_emoji_identifier" ] }, { "page": "replace_emoticon", "title": "Replace Emoticons With Words", "topics": [ "replace_emoticon" ] }, { "page": "replace_grade", "title": "Replace Grades With Words", "topics": [ "replace_grade" ] }, { "page": "replace_hash", "title": "Replace Hashes", "topics": [ "replace_hash" ] }, { "page": "replace_html", "title": "Replace HTML Markup", "topics": [ "replace_html" ] }, { "page": "replace_incomplete", "title": "Denote Incomplete End Marks With \"|\"", "topics": [ "replace_incomplete" ] }, { "page": "replace_internet_slang", "title": "Replace Internet Slang", "topics": [ "replace_internet_slang" ] }, { "page": "replace_kern", "title": "Replace Kerned (Spaced) with No Space Version", "topics": [ "replace_kern" ] }, { "page": "replace_misspelling", "title": "Replace Misspelled Words", "topics": [ "replace_misspelling" ] }, { "page": "replace_money", "title": "Replace Money With Words", "topics": [ "replace_money" ] }, { "page": "replace_names", "title": "Replace First/Last Names", "topics": [ "replace_names" ] }, { "page": "replace_non_ascii", "title": "Replace Common Non-ASCII Characters", "topics": [ "replace_curly_quote", "replace_non_ascii", "replace_non_ascii2" ] }, { "page": "replace_number", "title": "Replace Numbers With Text Representation", "topics": [ "as_ordinal", "replace_number" ] }, { "page": "replace_ordinal", "title": "Replace Mixed Ordinal Numbers With Text Representation", "topics": [ "replace_ordinal" ] }, { "page": "replace_rating", "title": "Replace Ratings With Words", "topics": [ "replace_rating" ] }, { "page": "replace_symbol", "title": "Replace Symbols With Word Equivalents", "topics": [ "replace_symbol" ] }, { "page": "replace_tag", "title": "Replace Handle Tags", "topics": [ "replace_tag" ] }, { "page": "replace_time", "title": "Replace Time Stamps With Words", "topics": [ "replace_time" ] }, { "page": "replace_to", "title": "Grab Begin/End of String to/from Character", "topics": [ "replace_from", "replace_to" ] }, { "page": "replace_tokens", "title": "Replace Tokens", "topics": [ "replace_tokens" ] }, { "page": "replace_url", "title": "Replace URLs", "topics": [ "replace_url" ] }, { "page": "replace_white", "title": "Remove White Space Characters", "topics": [ "replace_white" ] }, { "page": "replace_word_elongation", "title": "Replace Word Elongations", "topics": [ "replace_word_elongation" ] }, { "page": "strip", "title": "Strip Text", "topics": [ "strip", "strip.character", "strip.default", "strip.factor", "strip.list" ] }, { "page": "sub_holder", "title": "Hold the Place of Characters Prior to Subbing", "topics": [ "sub_holder" ] }, { "page": "swap", "title": "Swap Two Patterns Simultaneously", "topics": [ "swap" ] }, { "page": "which_are", "title": "Detect/Locate Potential Non-Normalized Text", "topics": [ "is_it", "which_are" ] } ], "_readme": "https://github.com/trinker/textclean/raw/HEAD/README.md", "_rundeps": [ "cli", "cpp11", "data.table", "dplyr", "dtt", "english", "generics", "glue", "lattice", "lexicon", "lifecycle", "magrittr", "mgsub", "NLP", "pillar", "pkgconfig", "purrr", "qdapRegex", "R6", "rlang", "slam", "stringi", "stringr", "syuzhet", "textshape", "tibble", "tidyr", "tidyselect", "utf8", "vctrs", "withr", "zoo" ], "_score": 10.477945392742825, "_indexed": true, "_nocasepkg": "textclean", "_universes": [ "trinker" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.9.8", "date": "2026-06-03T10:31:25.000Z", "distro": "noble", "commit": "80a30ed4677900c976cc301b9c4f26069ca824fe", "fileid": "06ae907851c8d206b4d46edd7842d5d59fad8887829b16e5aaef7bbb98b10f97", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/trinker/actions/runs/26878807982" }, { "r": "4.6.0", "os": "linux", "version": "0.9.8", "date": "2026-06-03T10:31:13.000Z", "distro": "noble", "commit": "80a30ed4677900c976cc301b9c4f26069ca824fe", "fileid": "1c0f4fb33a52d734c1c12a079e404a4b7c29dbb2e74ac78dc0ba19b0af473017", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/trinker/actions/runs/26878807982" }, { "r": "4.5.3", "os": "mac", "version": "0.9.8", "date": "2026-06-03T10:30:52.000Z", "commit": "80a30ed4677900c976cc301b9c4f26069ca824fe", "fileid": "c21195c21c875f020774360019ef53c9e106fbc8b687ffab90930b7e40984a82", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/trinker/actions/runs/26878807982" }, { "r": "4.6.0", "os": "mac", "version": "0.9.8", "date": "2026-06-03T10:31:03.000Z", "commit": "80a30ed4677900c976cc301b9c4f26069ca824fe", "fileid": "5ca948072b72fafd71b97be4a0d232f3bfea1634375aaa21d9e111ed11055e65", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/trinker/actions/runs/26878807982" }, { "r": "4.6.0", "os": "wasm", "version": "0.9.8", "date": "2026-06-03T10:31:19.000Z", "commit": "80a30ed4677900c976cc301b9c4f26069ca824fe", "fileid": "306e84d8bb3e865e79762e2c431941e01f976cd2fd748c8c9d971b1ec16cb2c4", "status": "success", "buildurl": "https://github.com/r-universe/trinker/actions/runs/26878807982" }, { "r": "4.7.0", "os": "win", "version": "0.9.8", "date": "2026-06-03T10:30:31.000Z", "commit": "80a30ed4677900c976cc301b9c4f26069ca824fe", "fileid": "39294ddbba4b39fcbe2297c338b77f2bcdbbff4fdb341937a2b265b3077bf1f2", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/trinker/actions/runs/26878807982" }, { "r": "4.5.3", "os": "win", "version": "0.9.8", "date": "2026-06-03T10:30:42.000Z", "commit": "80a30ed4677900c976cc301b9c4f26069ca824fe", "fileid": "f6be01a01776f7352b4665201d6615eae896e3c0583503aaa4b80cdac6ba739e", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/trinker/actions/runs/26878807982" }, { "r": "4.6.0", "os": "win", "version": "0.9.8", "date": "2026-06-03T10:30:51.000Z", "commit": "80a30ed4677900c976cc301b9c4f26069ca824fe", "fileid": "83f695a41e7905a0c6ac42d9b44c6ff70e16a4df240077d5d69621b3b841eebc", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/trinker/actions/runs/26878807982" } ] }