{ "_id": "6a55dd5bff0138dec5d69f53", "Package": "fozziejoin", "Title": "Utilities for Joining Dataframes with Inexact Matching", "Version": "0.0.14", "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)", "RoxygenNote": "7.3.3", "URL": "https://github.com/fozzieverse/fozziejoin", "BugReports": "https://github.com/fozzieverse/fozziejoin/issues", "SystemRequirements": "Cargo (Rust's package manager), rustc, xz", "Config/pak/sysreqs": "xz-utils libclang-dev", "Repository": "https://fozzieverse.r-universe.dev", "Date/Publication": "2026-04-14 23:59:12 UTC", "RemoteUrl": "https://github.com/fozzieverse/fozziejoin", "RemoteRef": "HEAD", "RemoteSha": "f5318d67b34aa230c7e910cac42e2da776a1b9df", "NeedsCompilation": "yes", "Packaged": { "Date": "2026-07-14 06:48:24 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_0.0.14.tar.gz", "_fileid": "https://r2.ropensci.org/1f733fcf47e9960943c2bd3da9f33e4f2670c2896cfcd963890d43e5cddc0553", "_filesize": 2688477, "_sha256": "1f733fcf47e9960943c2bd3da9f33e4f2670c2896cfcd963890d43e5cddc0553", "_expires": "2026-10-22T06:55:21.000Z", "_created": "2026-07-14T06:48:24.000Z", "_published": "2026-07-14T06:55:23.261Z", "_jobs": [ { "job": 87019212781, "time": 195, "config": "linux-devel-arm64", "r": "4.7.0", "check": "OK", "artifact": "8302684043" }, { "job": 87019212790, "time": 155, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "8302667795" }, { "job": 87019212828, "time": 182, "config": "linux-release-arm64", "r": "4.6.1", "check": "OK", "artifact": "8302679320" }, { "job": 87019212815, "time": 158, "config": "linux-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "8302668799" }, { "job": 87019212792, "time": 157, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "8302661221" }, { "job": 87019212843, "time": 339, "config": "macos-oldrel-x86_64", "r": "4.5.3", "check": "OK", "artifact": "8302726694" }, { "job": 87019212808, "time": 202, "config": "macos-release-arm64", "r": "4.6.1", "check": "NOTE", "artifact": "8302672504" }, { "job": 87019212779, "time": 309, "config": "macos-release-x86_64", "r": "4.6.1", "check": "NOTE", "artifact": "8302719709" }, { "job": 87018247671, "time": 354, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "8302608803" }, { "job": 87019212733, "time": 158, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "8302668824" }, { "job": 87019212863, "time": 196, "config": "windows-devel", "r": "4.7.0", "check": "NOTE", "artifact": "8302683916" }, { "job": 87019212771, "time": 211, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "8302689178" }, { "job": 87019212783, "time": 231, "config": "windows-release", "r": "4.6.1", "check": "NOTE", "artifact": "8302696975" } ], "_host": "GitHub-Actions", "_buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/29312199111", "_status": "success", "_upstream": "https://github.com/fozzieverse/fozziejoin", "_commit": { "id": "f5318d67b34aa230c7e910cac42e2da776a1b9df", "author": "Jon Downs ", "committer": "GitHub ", "message": "Fix bad hyperlink in benchmark vignette", "time": 1776211152 }, "_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 } ], "_tags": [], "_stars": 13, "_contributors": [ { "user": "jonddowns", "count": 94, "uuid": 110783391 } ], "_userbio": { "uuid": 238895586, "type": "organization", "name": "fozzieverse", "followers": 4 }, "_downloads": { "count": 262, "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/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "LICENSE", "manual.pdf" ], "_homeurl": "https://github.com/fozzieverse/fozziejoin", "_realowner": "fozzieverse", "_cranurl": true, "_releases": [ { "version": "0.0.13", "date": "2026-03-09" } ], "_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": "2026-04-14 22:03:59", "commits": 1 }, { "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": "2026-04-14 23:59:12", "commits": 2 } ], "_score": 6.666611568419031, "_indexed": true, "_nocasepkg": "fozziejoin", "_universes": [ "fozzieverse", "jonddowns" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.0.14", "date": "2026-07-14T06:51:48.000Z", "distro": "resolute", "arch": "aarch64", "commit": "f5318d67b34aa230c7e910cac42e2da776a1b9df", "fileid": "https://r2.ropensci.org/f10ce67b549ea994b17b103b6983f47e2ee3ad44225db99838189fd55afeacb9", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/29312199111" }, { "r": "4.7.0", "os": "linux", "version": "0.0.14", "date": "2026-07-14T06:51:07.000Z", "distro": "resolute", "arch": "x86_64", "commit": "f5318d67b34aa230c7e910cac42e2da776a1b9df", "fileid": "https://r2.ropensci.org/0677b96b07f1996543d23298dbd6359a8dc2d733fe411d59181f0f5187124ae8", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/29312199111" }, { "r": "4.6.1", "os": "linux", "version": "0.0.14", "date": "2026-07-14T06:51:37.000Z", "distro": "resolute", "arch": "aarch64", "commit": "f5318d67b34aa230c7e910cac42e2da776a1b9df", "fileid": "https://r2.ropensci.org/4f0e049f73b922dbd9cb9bc1a9537413f32a9200977a94a413c00a4f66d6621f", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/29312199111" }, { "r": "4.6.1", "os": "linux", "version": "0.0.14", "date": "2026-07-14T06:51:17.000Z", "distro": "resolute", "arch": "x86_64", "commit": "f5318d67b34aa230c7e910cac42e2da776a1b9df", "fileid": "https://r2.ropensci.org/9f4142544b960c641e72f7d1f1e4e5c2e9e5f4581842cd4dd6a5e592c3aa57bc", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/29312199111" }, { "r": "4.5.3", "os": "mac", "version": "0.0.14", "date": "2026-07-14T06:50:54.000Z", "arch": "aarch64", "commit": "f5318d67b34aa230c7e910cac42e2da776a1b9df", "fileid": "https://r2.ropensci.org/60e6fe43bc8e2e7ee33775bc693ed50e5cb5df78135cbfa6c8013e1ad8309073", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/29312199111" }, { "r": "4.5.3", "os": "mac", "version": "0.0.14", "date": "2026-07-14T06:52:54.000Z", "arch": "x86_64", "commit": "f5318d67b34aa230c7e910cac42e2da776a1b9df", "fileid": "https://r2.ropensci.org/95b2e3ca3e2401084b3340cc8ceea1bf95eb665be4f1c4ced1279a8e72473174", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/29312199111" }, { "r": "4.6.1", "os": "mac", "version": "0.0.14", "date": "2026-07-14T06:50:58.000Z", "arch": "aarch64", "commit": "f5318d67b34aa230c7e910cac42e2da776a1b9df", "fileid": "https://r2.ropensci.org/4f32f2faad93d04b0e79d566fcf4264459927168d2be8c9b1fb1b60c7d8075ca", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/29312199111" }, { "r": "4.6.1", "os": "mac", "version": "0.0.14", "date": "2026-07-14T06:52:15.000Z", "arch": "x86_64", "commit": "f5318d67b34aa230c7e910cac42e2da776a1b9df", "fileid": "https://r2.ropensci.org/da6946dbcf2a4a748d7f95bf13a26abeb749db2bfc9df35a7e293fe582b673ca", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/29312199111" }, { "r": "4.6.0", "os": "wasm", "version": "0.0.14", "date": "2026-07-14T06:51:20.000Z", "arch": "emscripten", "commit": "f5318d67b34aa230c7e910cac42e2da776a1b9df", "fileid": "https://r2.ropensci.org/b8af69caad475fadd98ff3d18a6bb3552b7e9e98a10c8013ba68b3f225f501e8", "status": "success", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/29312199111" }, { "r": "4.7.0", "os": "win", "version": "0.0.14", "date": "2026-07-14T06:50:22.000Z", "arch": "x86_64", "commit": "f5318d67b34aa230c7e910cac42e2da776a1b9df", "fileid": "https://r2.ropensci.org/4692a601c717c5a82fe35875a946d6a869f733036f38dd14e3c58f26088c888d", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/29312199111" }, { "r": "4.5.3", "os": "win", "version": "0.0.14", "date": "2026-07-14T06:50:23.000Z", "arch": "x86_64", "commit": "f5318d67b34aa230c7e910cac42e2da776a1b9df", "fileid": "https://r2.ropensci.org/2581ea837ec846208e88314299b7fb18a4b4733644871a7869055a326bf92b54", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/29312199111" }, { "r": "4.6.1", "os": "win", "version": "0.0.14", "date": "2026-07-14T06:50:37.000Z", "arch": "x86_64", "commit": "f5318d67b34aa230c7e910cac42e2da776a1b9df", "fileid": "https://r2.ropensci.org/41f1e978154e9eb71b4a670f4adbc5810a54d6d0813c410701468f3200843a13", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/29312199111" } ] }