{ "_id": "6a1f2f8cb401979e73427524", "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": "2026-05-15 09:10:17 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 ", "MD5sum": "87079c0c4d3813a5271206f6bc28836c", "_user": "fozzieverse", "_type": "src", "_file": "fozziejoin_0.0.14.tar.gz", "_fileid": "14457e505d1958f22f556c31aa4ab2db03a22bde1593931ca42e87ea4391111e", "_filesize": 2686933, "_sha256": "14457e505d1958f22f556c31aa4ab2db03a22bde1593931ca42e87ea4391111e", "_created": "2026-05-15T09:10:17.000Z", "_published": "2026-06-02T19:31:24.007Z", "_distro": "noble", "_jobs": [ { "job": 79154947966, "time": 234, "config": "linux-devel-arm64", "r": "4.7.0", "check": "OK", "artifact": "7013820962" }, { "job": 79154947744, "time": 174, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "7013805318" }, { "job": 79154948203, "time": 206, "config": "linux-release-arm64", "r": "4.6.0", "check": "OK", "artifact": "7013814102" }, { "job": 79154947763, "time": 163, "config": "linux-release-x86_64", "r": "4.6.0", "check": "OK", "artifact": "7013801889" }, { "job": 79154948412, "time": 222, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "7013808030" }, { "job": 79154948358, "time": 362, "config": "macos-oldrel-x86_64", "r": "4.5.3", "check": "OK", "artifact": "7013847731" }, { "job": 79154947753, "time": 214, "config": "macos-release-arm64", "r": "4.6.0", "check": "NOTE", "artifact": "7013805880" }, { "job": 79154948087, "time": 373, "config": "macos-release-x86_64", "r": "4.6.0", "check": "NOTE", "artifact": "7013850120" }, { "job": 79154947166, "time": 349, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "7013753689" }, { "job": 79154946812, "time": 159, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7367818684" }, { "job": 79154948007, "time": 213, "config": "windows-devel", "r": "4.7.0", "check": "NOTE", "artifact": "7013815980" }, { "job": 79154947569, "time": 188, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "7013809153" }, { "job": 79154948015, "time": 197, "config": "windows-release", "r": "4.6.0", "check": "NOTE", "artifact": "7013811580" } ], "_buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/25909639760", "_status": "success", "_host": "GitHub-Actions", "_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", "uuid": 110783391 }, "_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": 9, "_contributors": [ { "user": "jonddowns", "count": 94, "uuid": 110783391 } ], "_userbio": { "uuid": 238895586, "type": "organization", "name": "fozzieverse" }, "_downloads": { "count": 204, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/fozziejoin" }, "_devurl": "https://github.com/fozzieverse/fozziejoin", "_searchresults": 9, "_cargo": true, "_topics": [ "rust", "cargo" ], "_rbuild": "4.6.0", "_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", "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": 6.276461804173244, "_indexed": true, "_nocasepkg": "fozziejoin", "_universes": [ "fozzieverse", "jonddowns" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.0.14", "date": "2026-05-15T09:14:09.000Z", "distro": "noble", "arch": "aarch64", "commit": "f5318d67b34aa230c7e910cac42e2da776a1b9df", "fileid": "ee87ffd77a0d156cbd849874b21c4cdd0e024a73c10eff1cdfa97fcc7cc5648a", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/25909639760" }, { "r": "4.7.0", "os": "linux", "version": "0.0.14", "date": "2026-05-15T09:13:11.000Z", "distro": "noble", "arch": "x86_64", "commit": "f5318d67b34aa230c7e910cac42e2da776a1b9df", "fileid": "365f627f11e6f10c1e4d2366726baf7dc8453df0744cf8865af43d0ad478e293", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/25909639760" }, { "r": "4.6.0", "os": "linux", "version": "0.0.14", "date": "2026-05-15T09:13:46.000Z", "distro": "noble", "arch": "aarch64", "commit": "f5318d67b34aa230c7e910cac42e2da776a1b9df", "fileid": "98c3e5a2bafcc6b732b17d6b874af0baa3432c5ee0c031bf2a030f3031f35360", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/25909639760" }, { "r": "4.6.0", "os": "linux", "version": "0.0.14", "date": "2026-05-15T09:13:03.000Z", "distro": "noble", "arch": "x86_64", "commit": "f5318d67b34aa230c7e910cac42e2da776a1b9df", "fileid": "6181d7d6b6e4372ea8b0dcf9d4dbef7ab8b988a00522e8d6a467a39179052956", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/25909639760" }, { "r": "4.5.3", "os": "mac", "version": "0.0.14", "date": "2026-05-15T09:13:09.000Z", "arch": "aarch64", "commit": "f5318d67b34aa230c7e910cac42e2da776a1b9df", "fileid": "c3c95b508ede31cd7904ed93bfed67aeced63ed1cac0319eacd25ad135719a31", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/25909639760" }, { "r": "4.5.3", "os": "mac", "version": "0.0.14", "date": "2026-05-15T09:14:21.000Z", "arch": "x86_64", "commit": "f5318d67b34aa230c7e910cac42e2da776a1b9df", "fileid": "9dec5bfda7594718df19bd7aac4d3e45fff221f822eb36709922a630b93a54bb", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/25909639760" }, { "r": "4.6.0", "os": "mac", "version": "0.0.14", "date": "2026-05-15T09:13:04.000Z", "arch": "aarch64", "commit": "f5318d67b34aa230c7e910cac42e2da776a1b9df", "fileid": "19519ca1e8a0fc3e8045d479da9a3f2ca45af81b7992dd3cfd5f161a0dffee12", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/25909639760" }, { "r": "4.6.0", "os": "mac", "version": "0.0.14", "date": "2026-05-15T09:14:42.000Z", "arch": "x86_64", "commit": "f5318d67b34aa230c7e910cac42e2da776a1b9df", "fileid": "8f95a7050048ba6b50d32af78adc49d5faedf6773b33eb637005129343a1a0a8", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/25909639760" }, { "r": "4.7.0", "os": "win", "version": "0.0.14", "date": "2026-05-15T09:12:18.000Z", "arch": "x86_64", "commit": "f5318d67b34aa230c7e910cac42e2da776a1b9df", "fileid": "a41c608f31dca46d3c07b1faf42f7c3bc410ae55a769f2e8cfc8f9aeec9e05ab", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/25909639760" }, { "r": "4.5.3", "os": "win", "version": "0.0.14", "date": "2026-05-15T09:12:10.000Z", "arch": "x86_64", "commit": "f5318d67b34aa230c7e910cac42e2da776a1b9df", "fileid": "499d509ca764b7509a239c58fc26ca02b6ba51b5881e745efe79b837eefde86b", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/25909639760" }, { "r": "4.6.0", "os": "win", "version": "0.0.14", "date": "2026-05-15T09:12:08.000Z", "arch": "x86_64", "commit": "f5318d67b34aa230c7e910cac42e2da776a1b9df", "fileid": "b632f39c983fd7ded69bfb6e8ab6d62b6699bf094efe719577351f1803abe8df", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/25909639760" }, { "r": "4.6.0", "os": "wasm", "version": "0.0.14", "date": "2026-06-02T19:30:24.000Z", "arch": "emscripten", "commit": "f5318d67b34aa230c7e910cac42e2da776a1b9df", "fileid": "58bcd23b55f7f991e94309738dc94a603a19e12ac7f92153ec78909db6415e22", "status": "success", "buildurl": "https://github.com/r-universe/fozzieverse/actions/runs/25909639760" } ] }