{ "_id": "6a48d74eb5e98c40829ff619", "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": "2026-07-04 09:12:58 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_0.0.5.tar.gz", "_fileid": "https://r2.ropensci.org/4f7f894c62c96d63ad7db9fb0c812d07722eade81d824ab2b1ee4559a85072fe", "_filesize": 695470, "_sha256": "4f7f894c62c96d63ad7db9fb0c812d07722eade81d824ab2b1ee4559a85072fe", "_expires": "2026-10-12T09:50:04.000Z", "_created": "2026-07-04T09:12:58.000Z", "_published": "2026-07-04T09:50:06.117Z", "_jobs": [ { "job": 85120432454, "time": 147, "config": "linux-devel-arm64", "r": "4.7.0", "check": "OK", "artifact": "8080370883" }, { "job": 85120432444, "time": 149, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "8080370773" }, { "job": 85120432476, "time": 148, "config": "linux-release-arm64", "r": "4.6.1", "check": "OK", "artifact": "8080371117" }, { "job": 85120432456, "time": 128, "config": "linux-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "8080368315" }, { "job": 85120432462, "time": 79, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "8080592846" }, { "job": 85120432448, "time": 217, "config": "macos-oldrel-x86_64", "r": "4.5.3", "check": "OK", "artifact": "8080380901" }, { "job": 85120432455, "time": 99, "config": "macos-release-arm64", "r": "4.6.1", "check": "OK", "artifact": "8080604680" }, { "job": 85120432436, "time": 206, "config": "macos-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "8080378258" }, { "job": 85120213167, "time": 210, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "8080353125" }, { "job": 85120432459, "time": 147, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "8080370579" }, { "job": 85120432440, "time": 106, "config": "windows-devel", "r": "4.7.0", "check": "OK", "artifact": "8080365774" }, { "job": 85120432430, "time": 98, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "8080364832" }, { "job": 85120432432, "time": 104, "config": "windows-release", "r": "4.6.1", "check": "OK", "artifact": "8080365535" } ], "_host": "GitHub-Actions", "_buildurl": "https://github.com/r-universe/paulesantos/actions/runs/28701499587", "_status": "success", "_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" }, "_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 } ], "_tags": [], "_stars": 5, "_contributors": [ { "user": "paulesantos", "count": 33, "uuid": 16847375 } ], "_userbio": { "uuid": 16847375, "type": "user", "name": "Paul Efren", "followers": 32, "description": "Plant ecology and R programming." }, "_downloads": { "count": 475, "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": 5.477121254719663, "_indexed": true, "_nocasepkg": "fuzzystring", "_universes": [ "paulesantos" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.0.5", "date": "2026-07-04T09:15:33.000Z", "distro": "resolute", "arch": "aarch64", "commit": "8af2f2baf1d1d3180af54d29386db59ee0051f25", "fileid": "https://r2.ropensci.org/668412bbb50932e7034000d5ae9713184dea1311d90e6e9e58171a7d11db8768", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/28701499587" }, { "r": "4.7.0", "os": "linux", "version": "0.0.5", "date": "2026-07-04T09:15:28.000Z", "distro": "resolute", "arch": "x86_64", "commit": "8af2f2baf1d1d3180af54d29386db59ee0051f25", "fileid": "https://r2.ropensci.org/c24558aa4e8c54956098f313f3ccb75ac61d15ad44e19e3797e61a110ba47976", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/28701499587" }, { "r": "4.6.1", "os": "linux", "version": "0.0.5", "date": "2026-07-04T09:15:35.000Z", "distro": "resolute", "arch": "aarch64", "commit": "8af2f2baf1d1d3180af54d29386db59ee0051f25", "fileid": "https://r2.ropensci.org/9bc6c6d6c70dea53ba8a096471cf2c36b3f9b25f49dfc6d86ca80ed93eee2b7c", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/28701499587" }, { "r": "4.6.1", "os": "linux", "version": "0.0.5", "date": "2026-07-04T09:15:11.000Z", "distro": "resolute", "arch": "x86_64", "commit": "8af2f2baf1d1d3180af54d29386db59ee0051f25", "fileid": "https://r2.ropensci.org/a7cdcf4aea822bc47a2fce0d4227864d230c2c10debac7a7efc8b2e344f7a014", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/28701499587" }, { "r": "4.5.3", "os": "mac", "version": "0.0.5", "date": "2026-07-04T09:47:49.000Z", "arch": "aarch64", "commit": "8af2f2baf1d1d3180af54d29386db59ee0051f25", "fileid": "https://r2.ropensci.org/094de1f4e908fb90d7ce21d80659f1cb91f8e1c46a7eb87b05d328e097fbcc4e", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/28701499587" }, { "r": "4.5.3", "os": "mac", "version": "0.0.5", "date": "2026-07-04T09:16:32.000Z", "arch": "x86_64", "commit": "8af2f2baf1d1d3180af54d29386db59ee0051f25", "fileid": "https://r2.ropensci.org/144a122f1b1dadfbf4e9aadd3208cc2aab4928b801976fcdce18d14e24638429", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/28701499587" }, { "r": "4.6.1", "os": "mac", "version": "0.0.5", "date": "2026-07-04T09:49:20.000Z", "arch": "aarch64", "commit": "8af2f2baf1d1d3180af54d29386db59ee0051f25", "fileid": "https://r2.ropensci.org/193197738b9bc2eab51861d8c2bf99e835a1af9d0b770bb01c18b23a3874c678", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/28701499587" }, { "r": "4.6.1", "os": "mac", "version": "0.0.5", "date": "2026-07-04T09:16:09.000Z", "arch": "x86_64", "commit": "8af2f2baf1d1d3180af54d29386db59ee0051f25", "fileid": "https://r2.ropensci.org/d2f7fa4ead49dd507b1322a86658f5f083b93d17d4fa0092e46f9850975ffb48", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/28701499587" }, { "r": "4.6.0", "os": "wasm", "version": "0.0.5", "date": "2026-07-04T09:15:43.000Z", "arch": "emscripten", "commit": "8af2f2baf1d1d3180af54d29386db59ee0051f25", "fileid": "https://r2.ropensci.org/982ed4ebe9777040cdd071d220c6254e42e8b63e6833aa5459fa5b7334afe1c7", "status": "success", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/28701499587" }, { "r": "4.7.0", "os": "win", "version": "0.0.5", "date": "2026-07-04T09:14:19.000Z", "arch": "x86_64", "commit": "8af2f2baf1d1d3180af54d29386db59ee0051f25", "fileid": "https://r2.ropensci.org/9c08d0345d98c1a87dd8e783d6fd019d1162c2b93d9d44d878dcd6e44c973eac", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/28701499587" }, { "r": "4.5.3", "os": "win", "version": "0.0.5", "date": "2026-07-04T09:14:22.000Z", "arch": "x86_64", "commit": "8af2f2baf1d1d3180af54d29386db59ee0051f25", "fileid": "https://r2.ropensci.org/4a050595fc21db9447fa8241001f75125001663779c61d953363bfe97a83e50d", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/28701499587" }, { "r": "4.6.1", "os": "win", "version": "0.0.5", "date": "2026-07-04T09:14:19.000Z", "arch": "x86_64", "commit": "8af2f2baf1d1d3180af54d29386db59ee0051f25", "fileid": "https://r2.ropensci.org/332e8139ec355768270f21130c49449c08c90c96e6de6e07d455ecb3eb33e703", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/paulesantos/actions/runs/28701499587" } ] }