{ "_id": "6ad494f0104c877e3b414a6d", "Package": "fozziejoin", "Title": "Utilities for Joining Dataframes with Inexact Matching", "Version": "0.0.16", "Authors@R": "c(\nperson(\"Jon\", \"Downs\", , \"jon@jondowns.net\", role = c(\"aut\", \"cre\")),\nperson(\"The authors of the dependency Rust crates\", role = c(\"ctb\", \"cph\"),\ncomment = \"see inst/AUTHORS file for details\")\n)", "Description": "Provides functions for joining data frames based on\ninexact criteria, including string distance, Manhattan\ndistance, Euclidean distance, and interval overlap. This API is\ndesigned as a modern, performance-oriented alternative to the\n'fuzzyjoin' package (Robinson 2026)\n. String distance\nfunctions utilizing 'q-grams' are adapted with permission from\nthe 'textdistance' 'Rust' crate (Orsinium 2024)\n. Other\nstring distance calculations rely on the 'rapidfuzz' 'Rust'\ncrate (Bachmann 2023)\n. Interval joins\nare backed by a Adelson-Velsky and Landis tree as implemented\nby the 'interavl' 'Rust' crate\n.", "License": "MIT + file LICENSE", "VignetteBuilder": "knitr", "Config/CodeOfConduct": "https://github.com/fozzieverse/.github/blob/main/profile/CODE_OF_CONDUCT.md", "Config/rextendr/version": "0.4.2", "Config/testthat/edition": "3", "Encoding": "UTF-8", "LazyData": "true", "Roxygen": "list(markdown = TRUE)", "URL": "https://github.com/fozzieverse/fozziejoin", "BugReports": "https://github.com/fozzieverse/fozziejoin/issues", "SystemRequirements": "Cargo (Rust's package manager), rustc, xz", "Config/roxygen2/version": "8.1.0", "Config/pak/sysreqs": "xz-utils libclang-dev", "Repository": "https://fozzieverse.r-universe.dev", "Date/Publication": "2026-09-02 05:36:34 UTC", "RemoteUrl": "https://github.com/fozzieverse/fozziejoin", "RemoteRef": "HEAD", "RemoteSha": "c28410fd8778d709fe339c48c8aafe37d42f65d8", "NeedsCompilation": "yes", "Packaged": { "Date": "2026-10-18 09:35:19 UTC", "User": "root" }, "Author": "Jon Downs [aut, cre],\nThe authors of the dependency Rust crates [ctb, cph] (see inst/AUTHORS\nfile for details)", "Maintainer": "Jon Downs ", "_user": "fozzieverse", "_type": "src", "_file": "fozziejoin_0.0.16.tar.gz", "_fileid": "https://r2.ropensci.org/253fb1b44d685d1badaa6b53c847ff4d4b4b32810c31ff514d85370f5d99b6b1", "_filesize": 2274623, "_sha256": "253fb1b44d685d1badaa6b53c847ff4d4b4b32810c31ff514d85370f5d99b6b1", "_expires": "2027-01-26T09:44:14.000Z", "_created": "2026-10-18T09:35:19.000Z", "_published": "2026-10-18T09:44:15.977Z", "_buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/39115617208", "_status": "success", "_host": "GitHub-Actions", "_jobs": [ { "job": 117641730418, "time": 174, "config": "linux-devel-arm64", "r": "4.7.0", "check": "WARNING", "artifact": "12132367237" }, { "job": 117641730364, "time": 152, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "WARNING", "artifact": "12132830710" }, { "job": 117641730393, "time": 163, "config": "linux-release-arm64", "r": "4.6.1", "check": "WARNING", "artifact": "12132426184" }, { "job": 117641730406, "time": 161, "config": "linux-release-x86_64", "r": "4.6.1", "check": "WARNING", "artifact": "12132029792" }, { "job": 117641730430, "time": 223, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "12132511878" }, { "job": 117641730413, "time": 462, "config": "macos-oldrel-x86_64", "r": "4.5.3", "check": "OK", "artifact": "12133000606" }, { "job": 117641730388, "time": 225, "config": "macos-release-arm64", "r": "4.6.1", "check": "OK", "artifact": "12131723935" }, { "job": 117641730415, "time": 347, "config": "macos-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "12132337712" }, { "job": 117640742637, "time": 311, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "12132009598" }, { "job": 117641730378, "time": 171, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "12132097988" }, { "job": 117641730380, "time": 420, "config": "windows-devel-arm64", "r": "4.7.0", "check": "WARNING", "artifact": "12132557064" }, { "job": 117641730370, "time": 210, "config": "windows-devel-x86_64", "r": "4.7.0", "check": "WARNING", "artifact": "12131728966" }, { "job": 117641730562, "time": 206, "config": "windows-oldrel-x86_64", "r": "4.5.3", "check": "WARNING", "artifact": "12132107778" }, { "job": 117641730417, "time": 439, "config": "windows-release-arm64", "r": "4.6.1", "check": "WARNING", "artifact": "12132820547" }, { "job": 117641730433, "time": 201, "config": "windows-release-x86_64", "r": "4.6.1", "check": "WARNING", "artifact": "12132049643" } ], "_upstream": "https://github.com/fozzieverse/fozziejoin", "_commit": { "id": "c28410fd8778d709fe339c48c8aafe37d42f65d8", "author": "Jon Downs ", "committer": "GitHub ", "message": "Merge pull request #31 from fozzieverse/vignetteCores\n\nVignettes now use at most 2 cores", "time": 1788327394 }, "_maintainer": { "name": "Jon Downs", "email": "jon@jondowns.net", "login": "jonddowns", "linkedin": "in/jon-downs-epi", "description": "Epidemiologist and data scientist. My stack is R, Python, SQL, and Rust. This is my personal repo.", "uuid": 110783391 }, "_distro": "resolute", "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 4.2", "role": "Depends" }, { "package": "stats", "role": "Imports" }, { "package": "tibble", "role": "Imports" }, { "package": "utils", "role": "Imports" }, { "package": "babynames", "role": "Suggests" }, { "package": "dplyr", "role": "Suggests" }, { "package": "fuzzyjoin", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "microbenchmark", "role": "Suggests" }, { "package": "qdapDictionaries", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" }, { "package": "testthat", "version": ">= 3.0.0", "role": "Suggests" } ], "_owner": "fozzieverse", "_selfowned": true, "_usedby": 1, "_updates": [ { "week": "2025-42", "n": 3 }, { "week": "2025-43", "n": 3 }, { "week": "2026-09", "n": 7 }, { "week": "2026-10", "n": 9 }, { "week": "2026-11", "n": 9 }, { "week": "2026-15", "n": 1 }, { "week": "2026-16", "n": 5 }, { "week": "2026-32", "n": 2 }, { "week": "2026-35", "n": 2 }, { "week": "2026-36", "n": 1 } ], "_tags": [], "_stars": 13, "_contributors": [ { "user": "jonddowns", "count": 105, "uuid": 110783391 }, { "user": "jeroen", "count": 1, "uuid": 216319 } ], "_userbio": { "uuid": 238895586, "type": "organization", "name": "fozzieverse", "followers": 4 }, "_downloads": { "count": 357, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/fozziejoin" }, "_devurl": "https://github.com/fozzieverse/fozziejoin", "_searchresults": 17, "_cargo": true, "_topics": [ "rust", "cargo" ], "_rbuild": "4.6.1", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/fozziejoin.html", "extra/manual.pdf", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "LICENSE" ], "_homeurl": "https://github.com/fozzieverse/fozziejoin", "_realowner": "fozzieverse", "_cranurl": true, "_releases": [ { "version": "0.0.13", "date": "2026-03-09" }, { "version": "0.0.16", "date": "2026-09-08" } ], "_exports": [ "fozzie_difference_anti_join", "fozzie_difference_full_join", "fozzie_difference_inner_join", "fozzie_difference_join", "fozzie_difference_left_join", "fozzie_difference_right_join", "fozzie_difference_semi_join", "fozzie_distance_anti_join", "fozzie_distance_full_join", "fozzie_distance_inner_join", "fozzie_distance_join", "fozzie_distance_left_join", "fozzie_distance_right_join", "fozzie_distance_semi_join", "fozzie_interval_anti_join", "fozzie_interval_full_join", "fozzie_interval_inner_join", "fozzie_interval_join", "fozzie_interval_left_join", "fozzie_interval_right_join", "fozzie_interval_semi_join", "fozzie_regex_anti_join", "fozzie_regex_full_join", "fozzie_regex_inner_join", "fozzie_regex_join", "fozzie_regex_left_join", "fozzie_regex_right_join", "fozzie_regex_semi_join", "fozzie_string_anti_join", "fozzie_string_full_join", "fozzie_string_inner_join", "fozzie_string_join", "fozzie_string_left_join", "fozzie_string_right_join", "fozzie_string_semi_join", "fozzie_temporal_anti_join", "fozzie_temporal_full_join", "fozzie_temporal_inner_join", "fozzie_temporal_interval_anti_join", "fozzie_temporal_interval_full_join", "fozzie_temporal_interval_inner_join", "fozzie_temporal_interval_join", "fozzie_temporal_interval_left_join", "fozzie_temporal_interval_right_join", "fozzie_temporal_interval_semi_join", "fozzie_temporal_join", "fozzie_temporal_left_join", "fozzie_temporal_right_join", "fozzie_temporal_semi_join", "get_nthread_default", "normalize_by" ], "_datasets": [ { "name": "test_df", "title": "Baby Names Dataset", "object": "test_df", "class": [ "data.frame" ], "fields": [ "Name", "int_col", "real_col", "logical_col", "date_col", "posixct_col", "posixlt_col", "factor_col" ], "rows": 10, "table": true, "tojson": true } ], "_help": [ { "page": "fozzie_difference_join_family", "title": "Perform a fuzzy join between two data frames using numeric difference matching.", "topics": [ "fozzie_difference_anti_join", "fozzie_difference_full_join", "fozzie_difference_inner_join", "fozzie_difference_join", "fozzie_difference_join_family", "fozzie_difference_left_join", "fozzie_difference_right_join", "fozzie_difference_semi_join" ] }, { "page": "fozzie_distance_join_family", "title": "Perform a fuzzy join between two data frames using vector distance matching.", "topics": [ "fozzie_distance_anti_join", "fozzie_distance_full_join", "fozzie_distance_inner_join", "fozzie_distance_join", "fozzie_distance_join_family", "fozzie_distance_left_join", "fozzie_distance_right_join", "fozzie_distance_semi_join" ] }, { "page": "fozzie_interval_join_family", "title": "Perform a fuzzy join between two data frames using interval overlap matching.", "topics": [ "fozzie_interval_anti_join", "fozzie_interval_full_join", "fozzie_interval_inner_join", "fozzie_interval_join", "fozzie_interval_join_family", "fozzie_interval_left_join", "fozzie_interval_right_join", "fozzie_interval_semi_join" ] }, { "page": "fozzie_regex_join_family", "title": "Perform a fuzzy join between two data frames using regex pattern matching.", "topics": [ "fozzie_regex_anti_join", "fozzie_regex_full_join", "fozzie_regex_inner_join", "fozzie_regex_join", "fozzie_regex_join_family", "fozzie_regex_left_join", "fozzie_regex_right_join", "fozzie_regex_semi_join" ] }, { "page": "fozzie_string_join_family", "title": "Perform a fuzzy join between two data frames using approximate string matching.", "topics": [ "fozzie_string_anti_join", "fozzie_string_full_join", "fozzie_string_inner_join", "fozzie_string_join", "fozzie_string_join_family", "fozzie_string_left_join", "fozzie_string_right_join", "fozzie_string_semi_join" ] }, { "page": "fozzie_temporal_interval_join_family", "title": "Perform a fuzzy join between two data frames using time-based interval overlap matching.", "topics": [ "fozzie_temporal_interval_anti_join", "fozzie_temporal_interval_full_join", "fozzie_temporal_interval_inner_join", "fozzie_temporal_interval_join", "fozzie_temporal_interval_join_family", "fozzie_temporal_interval_left_join", "fozzie_temporal_interval_right_join", "fozzie_temporal_interval_semi_join" ] }, { "page": "fozzie_temporal_join_family", "title": "Perform a fuzzy join between two data frames using temporal difference matching.", "topics": [ "fozzie_temporal_anti_join", "fozzie_temporal_full_join", "fozzie_temporal_inner_join", "fozzie_temporal_join", "fozzie_temporal_join_family", "fozzie_temporal_left_join", "fozzie_temporal_right_join", "fozzie_temporal_semi_join" ] }, { "page": "get_nthread_default", "title": "Get Number of Threads in the Global Thread Pool", "topics": [ "get_nthread_default" ] }, { "page": "normalize_by", "title": "Normalize Join Columns", "topics": [ "normalize_by" ] }, { "page": "test_df", "title": "Baby Names Dataset", "topics": [ "test_df" ] } ], "_readme": "https://github.com/fozzieverse/fozziejoin/raw/HEAD/README.md", "_rundeps": [ "cli", "glue", "lifecycle", "magrittr", "pillar", "pkgconfig", "rlang", "tibble", "utf8", "vctrs" ], "_vignettes": [ { "source": "overview.Rmd", "filename": "overview.html", "title": "Fuzzy Matching with fozziejoin", "author": "Jon Downs", "engine": "knitr::rmarkdown", "headings": [ "Introduction", "String Distance joins", "Difference and Distance joins", "Interval Joins", "Interval Modes Explained", "Temporal joins", "Summary of fozziejoin Join Types" ], "created": "2026-04-14 22:03:59", "modified": "2026-09-02 05:36:34", "commits": 2 }, { "source": "string_dist_benchmarking.Rmd", "filename": "string_dist_benchmarking.html", "title": "String Distance Benchmarking", "author": "Jon Downs", "engine": "knitr::rmarkdown", "headings": [ "Introduction", "Benchmark Setup", "Summary results", "Considerations when Benchmarking", "Results may not be Identical", "Multithreading", "Smart Search strategies", "fozzie_string_join", "fozzie_difference_join", "fozzie_interval_join" ], "created": "2026-04-14 22:03:59", "modified": "2026-09-02 05:36:34", "commits": 3 } ], "_score": 6.821513528404774, "_indexed": true, "_nocasepkg": "fozziejoin", "_universes": [ "fozzieverse", "jonddowns" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.0.16", "date": "2026-10-18T09:38:18.000Z", "distro": "resolute", "arch": "aarch64", "commit": "c28410fd8778d709fe339c48c8aafe37d42f65d8", "fileid": "https://r2.ropensci.org/af71103601981ce5580c1304839d5a167d75b3c8feec44b37fc2317a9b19dc57", "status": "success", "check": "WARNING", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/39115617208" }, { "r": "4.7.0", "os": "linux", "version": "0.0.16", "date": "2026-10-18T09:37:51.000Z", "distro": "resolute", "arch": "x86_64", "commit": "c28410fd8778d709fe339c48c8aafe37d42f65d8", "fileid": "https://r2.ropensci.org/f5918aa7f98c081205f74b129b6fd0db8ea288923ca502cd535eb751a72a07de", "status": "success", "check": "WARNING", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/39115617208" }, { "r": "4.6.1", "os": "linux", "version": "0.0.16", "date": "2026-10-18T09:38:11.000Z", "distro": "resolute", "arch": "aarch64", "commit": "c28410fd8778d709fe339c48c8aafe37d42f65d8", "fileid": "https://r2.ropensci.org/742235b631123b1dbca952508ebfac2d5acf973f2d2a683f6ee682ec06723e08", "status": "success", "check": "WARNING", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/39115617208" }, { "r": "4.6.1", "os": "linux", "version": "0.0.16", "date": "2026-10-18T09:37:59.000Z", "distro": "resolute", "arch": "x86_64", "commit": "c28410fd8778d709fe339c48c8aafe37d42f65d8", "fileid": "https://r2.ropensci.org/ccddc5e59ffc8b622a92bffc48c869f752737faa040207c7c9bb4ad35ec22358", "status": "success", "check": "WARNING", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/39115617208" }, { "r": "4.5.3", "os": "mac", "version": "0.0.16", "date": "2026-10-18T09:38:08.000Z", "arch": "aarch64", "commit": "c28410fd8778d709fe339c48c8aafe37d42f65d8", "fileid": "https://r2.ropensci.org/85674e5965188c112e7792c6cc10b1e1bf2ba3a56260391b00d6d8a632c1463e", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/39115617208" }, { "r": "4.5.3", "os": "mac", "version": "0.0.16", "date": "2026-10-18T09:41:02.000Z", "arch": "x86_64", "commit": "c28410fd8778d709fe339c48c8aafe37d42f65d8", "fileid": "https://r2.ropensci.org/f2ae59a900126d3ad888fd877190d63229e3222aa6c38e43576d892126fac683", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/39115617208" }, { "r": "4.6.1", "os": "mac", "version": "0.0.16", "date": "2026-10-18T09:38:18.000Z", "arch": "aarch64", "commit": "c28410fd8778d709fe339c48c8aafe37d42f65d8", "fileid": "https://r2.ropensci.org/4efc6fcf54e3c35052e305fa6fda20cffcfd718ba9a0fa660f23c0290cd53b7b", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/39115617208" }, { "r": "4.6.1", "os": "mac", "version": "0.0.16", "date": "2026-10-18T09:39:07.000Z", "arch": "x86_64", "commit": "c28410fd8778d709fe339c48c8aafe37d42f65d8", "fileid": "https://r2.ropensci.org/b589c0634532d8c2d36c67cee00b26612e3ee7e15b5ccf107a9d9d7bac95afe4", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/39115617208" }, { "r": "4.6.0", "os": "wasm", "version": "0.0.16", "date": "2026-10-18T09:38:23.000Z", "arch": "emscripten", "commit": "c28410fd8778d709fe339c48c8aafe37d42f65d8", "fileid": "https://r2.ropensci.org/165d9e9fbb412fb4369ebcefb1ea53ae8f16e7071ac01aee22538f30914ca4fb", "status": "success", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/39115617208" }, { "r": "4.7.0", "os": "win", "version": "0.0.16", "date": "2026-10-18T09:40:52.000Z", "arch": "aarch64", "commit": "c28410fd8778d709fe339c48c8aafe37d42f65d8", "fileid": "https://r2.ropensci.org/f82266146c7ce6cb25cd82d49e548014193458212da81940525e5d30a556af11", "status": "success", "check": "WARNING", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/39115617208" }, { "r": "4.7.0", "os": "win", "version": "0.0.16", "date": "2026-10-18T09:37:10.000Z", "arch": "x86_64", "commit": "c28410fd8778d709fe339c48c8aafe37d42f65d8", "fileid": "https://r2.ropensci.org/499f72c35ee921abec66bb5a3db864877f8f4d1db9ad6d937b1a407f43c9793d", "status": "success", "check": "WARNING", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/39115617208" }, { "r": "4.5.3", "os": "win", "version": "0.0.16", "date": "2026-10-18T09:37:14.000Z", "arch": "x86_64", "commit": "c28410fd8778d709fe339c48c8aafe37d42f65d8", "fileid": "https://r2.ropensci.org/90575d19e5a4ecbcec2a58db16e008f3262c964a88dc7708124b65b80aaba9e4", "status": "success", "check": "WARNING", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/39115617208" }, { "r": "4.6.1", "os": "win", "version": "0.0.16", "date": "2026-10-18T09:41:20.000Z", "arch": "aarch64", "commit": "c28410fd8778d709fe339c48c8aafe37d42f65d8", "fileid": "https://r2.ropensci.org/20803bf5baae46b4813aba58a43a1d1af0cc38e6660c327cfee3b53590e61f2c", "status": "success", "check": "WARNING", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/39115617208" }, { "r": "4.6.1", "os": "win", "version": "0.0.16", "date": "2026-10-18T09:37:05.000Z", "arch": "x86_64", "commit": "c28410fd8778d709fe339c48c8aafe37d42f65d8", "fileid": "https://r2.ropensci.org/cf16e6ea5f7e1be2861e3e54a32ec04b80f80aa42eed898469af66cf877f74d0", "status": "success", "check": "WARNING", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/39115617208" } ] }