{ "_id": "6a13bda0acfb0bcc41d2c754", "Package": "fuzzystring", "Title": "Fast Fuzzy String Joins for Data Frames", "Version": "0.0.5", "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": "2026-05-25 01:28:34 UTC", "RemoteUrl": "https://github.com/PaulESantos/fuzzystring", "RemoteRef": "HEAD", "RemoteSha": "8af2f2baf1d1d3180af54d29386db59ee0051f25", "NeedsCompilation": "yes", "Packaged": { "Date": "2026-05-25 03:05:04 UTC", "User": "root" }, "Author": "Paul E. Santos Andrade [aut, cre, cph] (ORCID:\n),\nDavid Robinson [ctb] (aut of fuzzyjoin)", "MD5sum": "00451f3f89f3e4ef3c74614853a8dac9", "_user": "paulesantos", "_type": "src", "_file": "fuzzystring_0.0.5.tar.gz", "_fileid": "eb3a6132d371d05eda56f4b8184988c34f10c9a4709f5ea42c3586f79ad7528c", "_filesize": 692176, "_sha256": "eb3a6132d371d05eda56f4b8184988c34f10c9a4709f5ea42c3586f79ad7528c", "_created": "2026-05-25T03:05:04.000Z", "_published": "2026-05-25T03:10:24.788Z", "_distro": "noble", "_jobs": [ { "job": 77650113023, "time": 138, "config": "linux-devel-arm64", "r": "4.7.0", "check": "OK", "artifact": "7190923438" }, { "job": 77650113004, "time": 140, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "7190923733" }, { "job": 77650113001, "time": 143, "config": "linux-release-arm64", "r": "4.6.0", "check": "OK", "artifact": "7190924238" }, { "job": 77650113015, "time": 126, "config": "linux-release-x86_64", "r": "4.6.0", "check": "OK", "artifact": "7190921641" }, { "job": 77650112988, "time": 95, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "7190917227" }, { "job": 77650112990, "time": 277, "config": "macos-oldrel-x86_64", "r": "4.5.3", "check": "OK", "artifact": "7190945264" }, { "job": 77650112995, "time": 95, "config": "macos-release-arm64", "r": "4.6.0", "check": "OK", "artifact": "7190916905" }, { "job": 77650112991, "time": 178, "config": "macos-release-x86_64", "r": "4.6.0", "check": "OK", "artifact": "7190929541" }, { "job": 77649864978, "time": 196, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "7190902458" }, { "job": 77650113009, "time": 116, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7190920308" }, { "job": 77650112999, "time": 121, "config": "windows-devel", "r": "4.7.0", "check": "OK", "artifact": "7190920768" }, { "job": 77650113027, "time": 102, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "7190918180" }, { "job": 77650113006, "time": 91, "config": "windows-release", "r": "4.6.0", "check": "OK", "artifact": "7190916638" } ], "_buildurl": "https://github.com/r-universe/paulesantos/actions/runs/26380932706", "_status": "success", "_host": "GitHub-Actions", "_upstream": "https://github.com/PaulESantos/fuzzystring", "_commit": { "id": "8af2f2baf1d1d3180af54d29386db59ee0051f25", "author": "PaulESantos ", "committer": "PaulESantos ", "message": "benchmark\n", "time": 1779672514 }, "_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" }, "_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 } ], "_tags": [], "_stars": 5, "_contributors": [ { "user": "paulesantos", "count": 33, "uuid": 16847375 } ], "_userbio": { "uuid": 16847375, "type": "user", "name": "Paul Efren", "description": "Plant ecology and R programming." }, "_downloads": { "count": 499, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/fuzzystring" }, "_devurl": "https://github.com/paulesantos/fuzzystring", "_pkgdown": "https://paulesantos.github.io/fuzzystring/", "_searchresults": 0, "_topics": [ "cpp" ], "_rbuild": "4.6.0", "_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", "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": "14.2.0-4ubuntu2~24.04.1", "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": 5.477121254719663, "_indexed": true, "_nocasepkg": "fuzzystring", "_universes": [ "paulesantos" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.0.5", "date": "2026-05-25T03:07:23.000Z", "distro": "noble", "arch": "aarch64", "commit": "8af2f2baf1d1d3180af54d29386db59ee0051f25", "fileid": "8ad45dc9f4656f156f477a205844289046edc6e12a8a8504842956f30104a1be", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/26380932706" }, { "r": "4.7.0", "os": "linux", "version": "0.0.5", "date": "2026-05-25T03:07:22.000Z", "distro": "noble", "arch": "x86_64", "commit": "8af2f2baf1d1d3180af54d29386db59ee0051f25", "fileid": "2aa707b4af1c862aeb4d304ed0c9bb973c4933359a79e7f6dfbf199108fec495", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/26380932706" }, { "r": "4.6.0", "os": "linux", "version": "0.0.5", "date": "2026-05-25T03:07:29.000Z", "distro": "noble", "arch": "aarch64", "commit": "8af2f2baf1d1d3180af54d29386db59ee0051f25", "fileid": "3a7a3096cf58f7697c5b358495ab101d693c69c0ce79197f2b5d077e3d35d925", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/26380932706" }, { "r": "4.6.0", "os": "linux", "version": "0.0.5", "date": "2026-05-25T03:07:09.000Z", "distro": "noble", "arch": "x86_64", "commit": "8af2f2baf1d1d3180af54d29386db59ee0051f25", "fileid": "72d10c58d618110c0039270e205b8f4f5bbe88a11dde850c06c2ff570c0ce58c", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/26380932706" }, { "r": "4.5.3", "os": "mac", "version": "0.0.5", "date": "2026-05-25T03:06:43.000Z", "arch": "aarch64", "commit": "8af2f2baf1d1d3180af54d29386db59ee0051f25", "fileid": "ca97c72f0d98871a07e6ce2239013f27acc2eed11cc41ff518897bae11c61d02", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/26380932706" }, { "r": "4.5.3", "os": "mac", "version": "0.0.5", "date": "2026-05-25T03:09:09.000Z", "arch": "x86_64", "commit": "8af2f2baf1d1d3180af54d29386db59ee0051f25", "fileid": "763c019a97024fd2e2b6c80f6632a97439509b3ca429c9c27bcba30dfbb25c24", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/26380932706" }, { "r": "4.6.0", "os": "mac", "version": "0.0.5", "date": "2026-05-25T03:06:38.000Z", "arch": "aarch64", "commit": "8af2f2baf1d1d3180af54d29386db59ee0051f25", "fileid": "6bb44dfdb70c1c456c54eae64bd19e67c9875f94334ec03c07cbc5b629b2144d", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/26380932706" }, { "r": "4.6.0", "os": "mac", "version": "0.0.5", "date": "2026-05-25T03:07:43.000Z", "arch": "x86_64", "commit": "8af2f2baf1d1d3180af54d29386db59ee0051f25", "fileid": "7326cac5c3962c9d8dc81361b690900f193f3ba9a7502d9184696e0bf4cde679", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/26380932706" }, { "r": "4.6.0", "os": "wasm", "version": "0.0.5", "date": "2026-05-25T03:07:16.000Z", "arch": "emscripten", "commit": "8af2f2baf1d1d3180af54d29386db59ee0051f25", "fileid": "60e2f5180083d1f02db8baaba44fa880938efc5e59a45e83b6ecf7abfc84fe40", "status": "success", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/26380932706" }, { "r": "4.7.0", "os": "win", "version": "0.0.5", "date": "2026-05-25T03:06:27.000Z", "arch": "x86_64", "commit": "8af2f2baf1d1d3180af54d29386db59ee0051f25", "fileid": "9f05a7992e1be490ce0aacbb45a33985279a78828141a02c29766fad51f6fbad", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/26380932706" }, { "r": "4.5.3", "os": "win", "version": "0.0.5", "date": "2026-05-25T03:06:25.000Z", "arch": "x86_64", "commit": "8af2f2baf1d1d3180af54d29386db59ee0051f25", "fileid": "d6ce5e358eacf78d571e4f4a10a66ebb7b7c97767c67c3d7ac159134d748f8f7", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/26380932706" }, { "r": "4.6.0", "os": "win", "version": "0.0.5", "date": "2026-05-25T03:06:15.000Z", "arch": "x86_64", "commit": "8af2f2baf1d1d3180af54d29386db59ee0051f25", "fileid": "c1b5a83b513e706d972663b503ffa1beb94548c2073b6b355ccd61f96d7949a4", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/26380932706" } ] }