{ "_id": "6a4b5208a6574ff277f99853", "Package": "fuzzystring", "Title": "Fast Fuzzy String Joins for Data Frames", "Version": "0.0.6", "Authors@R": "c(person(given = \"Paul E.\",\nfamily = \"Santos Andrade\",\nrole = c(\"aut\", \"cre\", \"cph\"),\nemail = \"paulefrens@gmail.com\",\ncomment = c(ORCID = \"0000-0002-6635-0375\")),\nperson(given = \"David\",\nfamily = \"Robinson\",\nrole = \"ctb\",\nemail = \"admiral.david@gmail.com\",\ncomment = \"aut of fuzzyjoin\"))", "Description": "Perform fuzzy joins on data frames using approximate\nstring matching. Implements inner, left, right, full, semi, and\nanti joins with string distance metrics from the 'stringdist'\npackage, including Optimal String Alignment, Levenshtein,\nDamerau-Levenshtein, Jaro-Winkler, q-gram, cosine, Jaccard, and\nSoundex. Uses a 'data.table' backend plus compiled 'C++' result\nassembly to reduce overhead in large joins, while adaptive\ncandidate planning avoids unnecessary distance evaluations in\nsingle-column string joins. Suitable for reconciling\nmisspellings, inconsistent labels, and other near-match\nidentifiers while optionally returning the computed distance\nfor each match. Bibliographic references include Van der Loo,\nM. P. J. (2014) \nand Robinson, D. (2015) .", "License": "MIT + file LICENSE", "Config/testthat/edition": "3", "Encoding": "UTF-8", "LazyData": "true", "Roxygen": "list(markdown = TRUE)", "URL": "https://github.com/PaulESantos/fuzzystring,\nhttps://paulesantos.github.io/fuzzystring/", "BugReports": "https://github.com/PaulESantos/fuzzystring/issues", "VignetteBuilder": "knitr", "Maintainer": "Paul E. Santos Andrade ", "Config/roxygen2/version": "8.0.0", "Repository": "https://paulesantos.r-universe.dev", "Date/Publication": "2026-07-06 03:54:32 UTC", "RemoteUrl": "https://github.com/PaulESantos/fuzzystring", "RemoteRef": "HEAD", "RemoteSha": "d5687a21b7f1a733c37bd9903e7a6b6afd583e14", "NeedsCompilation": "yes", "Packaged": { "Date": "2026-07-06 06:54:34 UTC", "User": "root" }, "Author": "Paul E. Santos Andrade [aut, cre, cph] (ORCID:\n),\nDavid Robinson [ctb] (aut of fuzzyjoin)", "_user": "paulesantos", "_type": "src", "_file": "fuzzystring_0.0.6.tar.gz", "_fileid": "https://r2.ropensci.org/be33b4c0fe10c030eb68bbe7d584ee847a20584125fd487c717c15016198e617", "_filesize": 699532, "_sha256": "be33b4c0fe10c030eb68bbe7d584ee847a20584125fd487c717c15016198e617", "_expires": "2026-10-14T06:58:14.000Z", "_created": "2026-07-06T06:54:34.000Z", "_published": "2026-07-06T06:58:16.013Z", "_jobs": [ { "job": 85312227890, "time": 153, "config": "linux-devel-arm64", "r": "4.7.0", "check": "OK", "artifact": "8101744945" }, { "job": 85312227943, "time": 172, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "8101749271" }, { "job": 85312228059, "time": 143, "config": "linux-release-arm64", "r": "4.6.1", "check": "OK", "artifact": "8101742085" }, { "job": 85312227898, "time": 157, "config": "linux-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "8101745215" }, { "job": 85312227901, "time": 111, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "8101732530" }, { "job": 85312227945, "time": 155, "config": "macos-oldrel-x86_64", "r": "4.5.3", "check": "OK", "artifact": "8101744704" }, { "job": 85312227896, "time": 105, "config": "macos-release-arm64", "r": "4.6.1", "check": "OK", "artifact": "8101730866" }, { "job": 85312227882, "time": 176, "config": "macos-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "8101750685" }, { "job": 85311782190, "time": 198, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "8101701593" }, { "job": 85312227858, "time": 166, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "8101747566" }, { "job": 85312227872, "time": 139, "config": "windows-devel", "r": "4.7.0", "check": "OK", "artifact": "8101740255" }, { "job": 85312227875, "time": 107, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "8101731822" }, { "job": 85312227860, "time": 133, "config": "windows-release", "r": "4.6.1", "check": "OK", "artifact": "8101738767" } ], "_host": "GitHub-Actions", "_buildurl": "https://github.com/r-universe/paulesantos/actions/runs/28773360122", "_status": "success", "_upstream": "https://github.com/PaulESantos/fuzzystring", "_commit": { "id": "d5687a21b7f1a733c37bd9903e7a6b6afd583e14", "author": "PaulESantos ", "committer": "PaulESantos ", "message": "Increment version number to 0.0.6\n", "time": 1783310072 }, "_maintainer": { "name": "Paul E. Santos Andrade", "email": "paulefrens@gmail.com", "login": "paulesantos", "linkedin": "in/paulesantosandrade", "twitter": "@PaulEfrenSantos", "description": "Plant ecology and R programming.", "uuid": 16847375, "orcid": "0000-0002-6635-0375" }, "_distro": "resolute", "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 4.1", "role": "Depends" }, { "package": "Rcpp", "role": "LinkingTo" }, { "package": "data.table", "role": "Imports" }, { "package": "Rcpp", "role": "Imports" }, { "package": "stringdist", "role": "Imports" }, { "package": "dplyr", "role": "Suggests" }, { "package": "ggplot2", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "qdapDictionaries", "role": "Suggests" }, { "package": "readr", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" }, { "package": "rvest", "role": "Suggests" }, { "package": "stringr", "role": "Suggests" }, { "package": "testthat", "version": ">= 3.0.0", "role": "Suggests" }, { "package": "tibble", "role": "Suggests" }, { "package": "tidyr", "role": "Suggests" } ], "_owner": "paulesantos", "_selfowned": true, "_usedby": 0, "_updates": [ { "week": "2026-04", "n": 13 }, { "week": "2026-05", "n": 5 }, { "week": "2026-06", "n": 1 }, { "week": "2026-07", "n": 6 }, { "week": "2026-13", "n": 6 }, { "week": "2026-22", "n": 2 }, { "week": "2026-28", "n": 2 } ], "_tags": [], "_stars": 5, "_contributors": [ { "user": "paulesantos", "count": 35, "uuid": 16847375 } ], "_userbio": { "uuid": 16847375, "type": "user", "name": "Paul Efren", "followers": 32, "description": "Plant ecology and R programming." }, "_downloads": { "count": 462, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/fuzzystring" }, "_devurl": "https://github.com/paulesantos/fuzzystring", "_pkgdown": "https://paulesantos.github.io/fuzzystring/", "_searchresults": 1, "_topics": [ "cpp" ], "_rbuild": "4.6.1", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/fuzzystring.html", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "LICENSE", "manual.pdf" ], "_homeurl": "https://github.com/paulesantos/fuzzystring", "_realowner": "paulesantos", "_cranurl": true, "_releases": [ { "version": "0.0.1", "date": "2026-02-08" }, { "version": "0.0.5", "date": "2026-03-28" } ], "_exports": [ "fuzzystring_anti_join", "fuzzystring_full_join", "fuzzystring_inner_join", "fuzzystring_join", "fuzzystring_left_join", "fuzzystring_right_join", "fuzzystring_semi_join" ], "_datasets": [ { "name": "misspellings", "title": "A corpus of common misspellings, for examples and practice", "object": "misspellings", "class": [ "tbl_df", "tbl", "data.frame" ], "fields": [ "misspelling", "correct" ], "rows": 4505, "table": true, "tojson": true } ], "_help": [ { "page": "fuzzystring", "title": "fuzzystring: Fast fuzzy string joins for data frames", "topics": [ "fuzzystring-package", "fuzzystring" ] }, { "page": "fuzzystring_join", "title": "Join two tables based on fuzzy string matching", "topics": [ "fuzzystring_anti_join", "fuzzystring_full_join", "fuzzystring_inner_join", "fuzzystring_join", "fuzzystring_left_join", "fuzzystring_right_join", "fuzzystring_semi_join" ] }, { "page": "misspellings", "title": "A corpus of common misspellings, for examples and practice", "topics": [ "misspellings" ] } ], "_readme": "https://github.com/PaulESantos/fuzzystring/raw/HEAD/README.md", "_rundeps": [ "data.table", "Rcpp", "stringdist" ], "_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": "benchmark_fuzzyjoin_comparison.Rmd", "filename": "benchmark_fuzzyjoin_comparison.html", "title": "Benchmarking fuzzystring against fuzzyjoin", "author": "Paul Efren Santos Andrade", "engine": "knitr::rmarkdown", "headings": [ "Overview", "Benchmark Script", "Results", "Absolute Runtime", "Relative Runtime", "Interpretation" ], "created": "2026-03-27 03:59:51", "modified": "2026-05-25 01:28:34", "commits": 2 }, { "source": "getting_started.Rmd", "filename": "getting_started.html", "title": "Getting Started with fuzzystring", "author": "Paul Efren Santos Andrade", "engine": "knitr::rmarkdown", "headings": [ "Introduction", "Installation", "Quick Start", "Key Features", "All Join Types Supported", "Inner join", "Left join", "Right join", "Full join", "Semi join (rows from x with a match in y)", "Anti join (rows from x without a match in y)", "Using the generic fuzzystring_join()", "Multiple Distance Methods", "Case-Insensitive Matching", "Advanced Usage", "Multiple Column Joins", "Performance" ], "created": "2026-01-25 02:22:17", "modified": "2026-03-27 03:59:51", "commits": 3 } ], "_score": 5.544068044350276, "_indexed": true, "_nocasepkg": "fuzzystring", "_universes": [ "paulesantos" ], "_previous": "0.0.5", "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.0.6", "date": "2026-07-06T06:57:12.000Z", "distro": "resolute", "arch": "aarch64", "commit": "d5687a21b7f1a733c37bd9903e7a6b6afd583e14", "fileid": "https://r2.ropensci.org/e009349bbc49b1dd3b93d7fe5cf7a58480fece96516ec41a642f4a7765347667", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/28773360122" }, { "r": "4.7.0", "os": "linux", "version": "0.0.6", "date": "2026-07-06T06:57:21.000Z", "distro": "resolute", "arch": "x86_64", "commit": "d5687a21b7f1a733c37bd9903e7a6b6afd583e14", "fileid": "https://r2.ropensci.org/cc6907ba5e3e53275c716b1a0c9c31c6db2edcfcdf9e3464bdaa475d4de56748", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/28773360122" }, { "r": "4.6.1", "os": "linux", "version": "0.0.6", "date": "2026-07-06T06:57:03.000Z", "distro": "resolute", "arch": "aarch64", "commit": "d5687a21b7f1a733c37bd9903e7a6b6afd583e14", "fileid": "https://r2.ropensci.org/0278c14dc7134b3419721d2061d79640d6c781ff59f567bdc2d0f853d86e85c3", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/28773360122" }, { "r": "4.6.1", "os": "linux", "version": "0.0.6", "date": "2026-07-06T06:57:10.000Z", "distro": "resolute", "arch": "x86_64", "commit": "d5687a21b7f1a733c37bd9903e7a6b6afd583e14", "fileid": "https://r2.ropensci.org/9ffdea5844bbaaeb2ed18851cb0c018e91f1cf725087ead5da292b0f3e2f9727", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/28773360122" }, { "r": "4.5.3", "os": "mac", "version": "0.0.6", "date": "2026-07-06T06:56:21.000Z", "arch": "aarch64", "commit": "d5687a21b7f1a733c37bd9903e7a6b6afd583e14", "fileid": "https://r2.ropensci.org/cdd3b949f2e490736161d40f802429afd65a085d2d977f2e20731c0a4ac9d31e", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/28773360122" }, { "r": "4.5.3", "os": "mac", "version": "0.0.6", "date": "2026-07-06T06:56:56.000Z", "arch": "x86_64", "commit": "d5687a21b7f1a733c37bd9903e7a6b6afd583e14", "fileid": "https://r2.ropensci.org/41cb9b70e6c30e01a4e851121acca37d556f0a1f3e3d5db2b8bb847a94f948b8", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/28773360122" }, { "r": "4.6.1", "os": "mac", "version": "0.0.6", "date": "2026-07-06T06:56:15.000Z", "arch": "aarch64", "commit": "d5687a21b7f1a733c37bd9903e7a6b6afd583e14", "fileid": "https://r2.ropensci.org/6a2203cd932914c9068948d95df465b97250e099e0d5cf58444314a4bb72502e", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/28773360122" }, { "r": "4.6.1", "os": "mac", "version": "0.0.6", "date": "2026-07-06T06:57:10.000Z", "arch": "x86_64", "commit": "d5687a21b7f1a733c37bd9903e7a6b6afd583e14", "fileid": "https://r2.ropensci.org/630dba9502b063f7fc378e4fb3775ecfbfd55c8d65e7374f6cc44fa824e25bb5", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/28773360122" }, { "r": "4.6.0", "os": "wasm", "version": "0.0.6", "date": "2026-07-06T06:57:34.000Z", "arch": "emscripten", "commit": "d5687a21b7f1a733c37bd9903e7a6b6afd583e14", "fileid": "https://r2.ropensci.org/29b3a61873dd5d606621015a865170687029ee6ae9d93861ea1e2a3606234096", "status": "success", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/28773360122" }, { "r": "4.7.0", "os": "win", "version": "0.0.6", "date": "2026-07-06T06:56:43.000Z", "arch": "x86_64", "commit": "d5687a21b7f1a733c37bd9903e7a6b6afd583e14", "fileid": "https://r2.ropensci.org/e44c779451173ee6fdc9847ff1d8897268bdd7e4f367aabff8fcb59e5d78e58d", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/28773360122" }, { "r": "4.5.3", "os": "win", "version": "0.0.6", "date": "2026-07-06T06:55:56.000Z", "arch": "x86_64", "commit": "d5687a21b7f1a733c37bd9903e7a6b6afd583e14", "fileid": "https://r2.ropensci.org/59f06ba1d46c7d8046497c8b0733bcdcb24872346f93b9c3d2a27494dbc21a36", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/28773360122" }, { "r": "4.6.1", "os": "win", "version": "0.0.6", "date": "2026-07-06T06:56:27.000Z", "arch": "x86_64", "commit": "d5687a21b7f1a733c37bd9903e7a6b6afd583e14", "fileid": "https://r2.ropensci.org/248f79e2177a1eeb5428b6e96078fa3aed7a4179f68cd44db945f8738841c4d6", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/28773360122" } ] }