{ "_id": "6a105089acfb0bcc41ca1178", "Package": "validate", "Maintainer": "Mark van der Loo ", "License": "GPL-3", "Title": "Data Validation Infrastructure", "LazyData": "no", "Type": "Package", "LazyLoad": "yes", "Authors@R": "c(person(\"Mark\", \"van der Loo\"\n, role = c(\"cre\",\"aut\")\n, email = \"mark.vanderloo@gmail.com\"\n, comment= c(ORCID=\"0000-0002-9807-4686\"))\n, person(\"Edwin\", \"de Jonge\"\n, role = \"aut\"\n, comment=c(ORCID=\"0000-0002-6580-4718\"))\n, person(\"Paul\",\"Hsieh\"\n, role = \"ctb\" ))", "Description": "Declare data validation rules and data quality indicators;\nconfront data with them and analyze or visualize the results.\nThe package supports rules that are per-field, in-record,\ncross-record or cross-dataset. Rules can be automatically\nanalyzed for rule type and connectivity. Supports checks\nimplied by an SDMX DSD file as well. See also Van der Loo and\nDe Jonge (2018) , Chapter 6 and the\nJSS paper (2021) .", "Version": "1.1.7", "URL": "https://github.com/data-cleaning/validate", "BugReports": "https://github.com/data-cleaning/validate/issues", "VignetteBuilder": "knitr", "Collate": "'rule.R' 'sugar.R' 'validate_pkg.R' 'parse.R'\n'expressionset.R' 'indicator.R' 'validator.R' 'confrontation.R'\n'compare.R' 'factory.R' 'genericrules.R' 'lumberjack.R'\n'plot.R' 'retailers.R' 'run_validation.R' 'sdmx.R' 'syntax.R'\n'utils.R' 'yaml.R'", "RoxygenNote": "7.3.2", "Encoding": "UTF-8", "Repository": "https://data-cleaning.r-universe.dev", "Date/Publication": "2025-12-10 15:35:17 UTC", "RemoteUrl": "https://github.com/data-cleaning/validate", "RemoteRef": "HEAD", "RemoteSha": "cb1e94528d3ede03776cb102bdf7017f821886c7", "RemoteSubdir": "pkg", "NeedsCompilation": "yes", "Packaged": { "Date": "2026-05-10 05:27:35 UTC", "User": "root" }, "Author": "Mark van der Loo [cre, aut] (ORCID:\n),\nEdwin de Jonge [aut] (ORCID: ),\nPaul Hsieh [ctb]", "MD5sum": "fa0cb30e9830dd579b421119c7dfc246", "_user": "data-cleaning", "_type": "src", "_file": "validate_1.1.7.tar.gz", "_fileid": "858c4fc22043b3fbd76ec384ee2ea6ace446b1632338c9045f627aadb21f5a02", "_filesize": 2583057, "_sha256": "858c4fc22043b3fbd76ec384ee2ea6ace446b1632338c9045f627aadb21f5a02", "_created": "2026-05-10T05:27:35.000Z", "_published": "2026-05-22T12:48:09.940Z", "_distro": "noble", "_jobs": [ { "job": 77382494560, "time": 130, "config": "linux-devel-arm64", "r": "4.7.0", "check": "ERROR", "artifact": "6901229199" }, { "job": 77382494621, "time": 133, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "ERROR", "artifact": "6901229597" }, { "job": 77382494631, "time": 137, "config": "linux-release-arm64", "r": "4.6.0", "check": "ERROR", "artifact": "6901229933" }, { "job": 77382494591, "time": 123, "config": "linux-release-x86_64", "r": "4.6.0", "check": "ERROR", "artifact": "6901228534" }, { "job": 77382495225, "time": 134, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "ERROR", "artifact": "6901229603" }, { "job": 77382494594, "time": 251, "config": "macos-oldrel-x86_64", "r": "4.5.3", "check": "ERROR", "artifact": "6901243095" }, { "job": 77382494730, "time": 97, "config": "macos-release-arm64", "r": "4.6.0", "check": "ERROR", "artifact": "6901225888" }, { "job": 77382494985, "time": 237, "config": "macos-release-x86_64", "r": "4.6.0", "check": "ERROR", "artifact": "6901240934" }, { "job": 77382494444, "time": 191, "config": "source", "r": "4.6.0", "check": "ERROR", "artifact": "6901215432" }, { "job": 77382494097, "time": 89, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7160840200" }, { "job": 77382494418, "time": 114, "config": "windows-devel", "r": "4.7.0", "check": "ERROR", "artifact": "6901227533" }, { "job": 77382494531, "time": 96, "config": "windows-oldrel", "r": "4.5.3", "check": "ERROR", "artifact": "6901225789" }, { "job": 77382495004, "time": 103, "config": "windows-release", "r": "4.6.0", "check": "ERROR", "artifact": "6901226475" } ], "_buildurl": "https://github.com/r-universe/data-cleaning/actions/runs/25620719657", "_status": "failure", "_host": "GitHub-Actions", "_upstream": "https://github.com/data-cleaning/validate", "_commit": { "id": "cb1e94528d3ede03776cb102bdf7017f821886c7", "author": "Mark van der Loo ", "committer": "Mark van der Loo ", "message": "fixed oecd link\n", "time": 1765380917 }, "_maintainer": { "name": "Mark van der Loo", "email": "mark.vanderloo@gmail.com", "login": "markvanderloo", "uuid": 1927426, "orcid": "0000-0002-9807-4686" }, "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 3.5.0", "role": "Depends" }, { "package": "methods", "role": "Depends" }, { "package": "stats", "role": "Imports" }, { "package": "graphics", "role": "Imports" }, { "package": "grid", "role": "Imports" }, { "package": "settings", "role": "Imports" }, { "package": "yaml", "role": "Imports" }, { "package": "rsdmx", "role": "Suggests" }, { "package": "tinytest", "version": ">= 0.9.6", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "bookdown", "role": "Suggests" }, { "package": "lumberjack", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" } ], "_owner": "data-cleaning", "_selfowned": true, "_usedby": 9, "_updates": [ { "week": "2025-26", "n": 1 }, { "week": "2025-46", "n": 2 }, { "week": "2025-50", "n": 3 } ], "_tags": [], "_topics": [ "data-cleaning", "validation" ], "_stars": 431, "_contributors": [ { "user": "markvanderloo", "count": 716, "uuid": 1927426 }, { "user": "edwindj", "count": 81, "uuid": 542492 }, { "user": "mayeulk", "count": 10, "uuid": 768570 }, { "user": "rmsharp", "count": 2, "uuid": 386848 }, { "user": "daniel-barnett", "count": 1, "uuid": 16076593 }, { "user": "dpritchard", "count": 1, "uuid": 358971 }, { "user": "etiennebacher", "count": 1, "uuid": 52219252 }, { "user": "erm-eanway", "count": 1, "uuid": 64024762 }, { "user": "jonmcalder", "count": 1, "uuid": 5055818 }, { "user": "kylegrealis", "count": 1, "uuid": 84798289 }, { "user": "michaelchirico", "count": 1, "uuid": 7606389 }, { "user": "mutahiwachira", "count": 1, "uuid": 44994677 }, { "user": "phorikx", "count": 1, "uuid": 82879823 }, { "user": "earcanal", "count": 1, "uuid": 1086888 }, { "user": "flother", "count": 1, "uuid": 48392 }, { "user": "gerrymanoim", "count": 1, "uuid": 194147 }, { "user": "probjects", "count": 1, "uuid": 168487681 } ], "_userbio": { "uuid": 10775432, "type": "organization", "name": "Data cleaning for statistical purpose", "description": "Software for cleaning data" }, "_downloads": { "count": 2369, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/validate" }, "_mentions": 2, "_devurl": "https://github.com/data-cleaning/validate", "_searchresults": 588, "_rbuild": "4.6.0", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "extra/validate.html" ], "_homeurl": "https://github.com/data-cleaning/validate", "_realowner": "data-cleaning", "_cranurl": true, "_releases": [ { "version": "0.1.2", "date": "2015-09-01" }, { "version": "0.1.3", "date": "2015-09-09" }, { "version": "0.1.4", "date": "2016-04-15" }, { "version": "0.1.5", "date": "2016-06-24" }, { "version": "0.1.7", "date": "2017-04-07" }, { "version": "0.2.0", "date": "2017-08-07" }, { "version": "0.2.4", "date": "2018-03-28" }, { "version": "0.2.5", "date": "2018-06-22" }, { "version": "0.2.6", "date": "2018-08-01" }, { "version": "0.9.1", "date": "2019-08-23" }, { "version": "0.9.2", "date": "2019-08-28" }, { "version": "0.9.3", "date": "2019-12-16" }, { "version": "1.0.1", "date": "2020-12-08" }, { "version": "1.0.2", "date": "2021-03-30" }, { "version": "1.0.4", "date": "2021-04-29" }, { "version": "1.1.0", "date": "2021-10-07" }, { "version": "1.1.1", "date": "2022-03-24" }, { "version": "1.1.3", "date": "2023-03-28" }, { "version": "1.1.5", "date": "2024-02-14" }, { "version": "1.1.6", "date": "2025-11-14" }, { "version": "1.1.7", "date": "2025-12-11" } ], "_exports": [ ".blocks_expressionset", ".get_exprs", ".ini_expressionset_cli", ".ini_expressionset_df", ".ini_expressionset_yml", ".PKGOPT", ".show_expressionset", "%vin%", "add_indicators", "aggregate", "all_complete", "all_unique", "as_yaml", "as.data.frame", "barplot", "cells", "check_that", "compare", "confront", "contains_at_least", "contains_at_most", "contains_exactly", "created", "created<-", "description", "description<-", "do_by", "does_not_contain", "errors", "estat_codelist", "event", "event<-", "exists_any", "exists_one", "export_yaml", "expr", "field_format", "field_length", "glob", "global_codelist", "hb", "hierarchy", "in_linear_sequence", "in_range", "indicator", "is_complete", "is_linear_sequence", "is_unique", "keyset", "label", "label<-", "lacking", "lbj_cells", "lbj_rules", "match_cells", "max_by", "mean_by", "meta", "meta<-", "min_by", "number_format", "origin", "origin<-", "part_whole_relation", "plot", "reset", "run_validation_dir", "run_validation_file", "rx", "satisfying", "sdmx_codelist", "sdmx_endpoint", "sort", "sum_by", "summary", "validate_options", "validator", "validator_from_dsd", "values", "variables", "violating", "voptions", "warnings" ], "_datasets": [ { "name": "nace_rev2", "title": "", "object": "nace_rev2", "file": "nace_rev2.csv.gz", "class": [ "data.frame" ], "fields": [ "Order", "Level", "Code", "Parent", "Description", "This_item_includes", "This_item_also_includes", "Rulings", "This_item_excludes", "Reference_to_ISIC_Rev._4" ], "rows": 996, "table": true, "tojson": true }, { "name": "retailers", "title": "", "object": "retailers", "file": "retailers.csv.gz", "class": [ "data.frame" ], "fields": [ "size", "incl.prob", "staff", "turnover", "other.rev", "total.rev", "staff.costs", "total.costs", "profit", "vat" ], "rows": 60, "table": true, "tojson": true }, { "name": "samplonomy", "title": "", "object": "samplonomy", "file": "samplonomy.RData", "class": [ "data.frame" ], "fields": [ "region", "freq", "period", "measure", "value" ], "rows": 1199, "table": true, "tojson": true }, { "name": "SBS2000", "title": "", "object": "SBS2000", "file": "SBS2000.csv.gz", "class": [ "data.frame" ], "fields": [ "id", "size", "incl.prob", "staff", "turnover", "other.rev", "total.rev", "staff.costs", "total.costs", "profit", "vat" ], "rows": 60, "table": true, "tojson": true } ], "_help": [], "_readme": "https://github.com/data-cleaning/validate/raw/HEAD/README.md", "_rundeps": [ "settings", "yaml" ], "_vignettes": [ { "source": "JSS_3483.Rnw", "filename": "JSS_3483.pdf", "title": "Data Validation Infrastructure for R", "engine": "utils::Sweave", "headings": [], "created": "2019-12-16 12:58:41", "modified": "2021-06-09 06:47:13", "commits": 2 }, { "source": "cookbook.Rmd", "filename": "cookbook.html", "title": "The Data Validation Cookbook", "author": "Mark P.J. van der Loo", "engine": "knitr::rmarkdown", "headings": [ "Preface", "Prerequisites", "Citing this work", "Acknowledgements", "Contributing", "License", "Introduction to validate", "A quick example", "Variable checks", "Variable type", "Missingness", "Field length", "Format of numeric fields", "General field format", "Numeric ranges", "Ranges for times and periods", "Code lists", "Availability and uniqueness", "Long data", "Uniqueness", "Availability of records", "Gaps in (time) series", "Multivariate checks", "Completeness of records", "Balance equalities and inequalities", "Conditional restrictions", "Forbidden value combinations", "Statistical checks", "Statistical and groupwise characteristics", "Group properties", "Code hierarchies and aggregation", "General aggregates in long-form data", "Notes", "Aggregates of time series in long format", "Indicators", "A first example", "Getting indicator values", "Working with validate", "Manipulating rule sets", "Rule metadata", "Rules in data frames", "Validation rule syntax", "Confrontation objects", "Confrontation options", "Using reference data", "Rules in text files", "Reading rules from file", "Metadata in text files: YAML", "Setting options", "Including other rule files", "Exporting validator objects", "Rules from SDMX", "SDMX and validate", "SDMX and API locations", "Code lists from SDMX registries", "Derive rules from DSD", "More on SDMX", "Comparing data sets", "Cell counts", "Comparing rule violations", "validate and lumberjack", "Bibliographical notes" ], "created": "2020-11-19 15:56:54", "modified": "2025-12-10 15:35:17", "commits": 31 } ], "_score": 12.192054654158193, "_indexed": true, "_nocasepkg": "validate", "_universes": [ "data-cleaning", "markvanderloo" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "1.1.7", "date": "2026-05-10T05:29:45.000Z", "distro": "noble", "arch": "aarch64", "commit": "cb1e94528d3ede03776cb102bdf7017f821886c7", "fileid": "55a31822d5fe77b287eec2f1c7824b6c2de756af623296e9c8217940b66ff708", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/data-cleaning/actions/runs/25620719657" }, { "r": "4.7.0", "os": "linux", "version": "1.1.7", "date": "2026-05-10T05:29:42.000Z", "distro": "noble", "arch": "x86_64", "commit": "cb1e94528d3ede03776cb102bdf7017f821886c7", "fileid": "a119b6b416f0ada0e588a0a521125c9ca7932cdee794f6b267a218d553a2a3f4", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/data-cleaning/actions/runs/25620719657" }, { "r": "4.6.0", "os": "linux", "version": "1.1.7", "date": "2026-05-10T05:29:53.000Z", "distro": "noble", "arch": "aarch64", "commit": "cb1e94528d3ede03776cb102bdf7017f821886c7", "fileid": "84c7b96d547ab09b961a0ef471e8bce565d1812925988df41388a83b4dc11027", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/data-cleaning/actions/runs/25620719657" }, { "r": "4.6.0", "os": "linux", "version": "1.1.7", "date": "2026-05-10T05:29:36.000Z", "distro": "noble", "arch": "x86_64", "commit": "cb1e94528d3ede03776cb102bdf7017f821886c7", "fileid": "a08903c26cfc66520d20c9a301189154a2a15a4039132e2b960c5c0736a3f1d5", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/data-cleaning/actions/runs/25620719657" }, { "r": "4.5.3", "os": "mac", "version": "1.1.7", "date": "2026-05-10T05:29:45.000Z", "arch": "aarch64", "commit": "cb1e94528d3ede03776cb102bdf7017f821886c7", "fileid": "46b4717ac07ec70e3b6b1830047130a045063f3df98ee6babb2e54c436603be0", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/data-cleaning/actions/runs/25620719657" }, { "r": "4.5.3", "os": "mac", "version": "1.1.7", "date": "2026-05-10T05:31:17.000Z", "arch": "x86_64", "commit": "cb1e94528d3ede03776cb102bdf7017f821886c7", "fileid": "e76bd7fc451b57221f15c41371f1747073aa65ab73bc6231db73b9fa02fdcd8c", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/data-cleaning/actions/runs/25620719657" }, { "r": "4.6.0", "os": "mac", "version": "1.1.7", "date": "2026-05-10T05:29:14.000Z", "arch": "aarch64", "commit": "cb1e94528d3ede03776cb102bdf7017f821886c7", "fileid": "634fd5a904b50d165513d2ba4784caffc5a4822c900b4a60c6c1f77fdc4582c6", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/data-cleaning/actions/runs/25620719657" }, { "r": "4.6.0", "os": "mac", "version": "1.1.7", "date": "2026-05-10T05:31:02.000Z", "arch": "x86_64", "commit": "cb1e94528d3ede03776cb102bdf7017f821886c7", "fileid": "f1c56d206eaa01b60efbcf84234b0ab43ce8c5d9830c758df47e41ba92aaa38b", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/data-cleaning/actions/runs/25620719657" }, { "r": "4.7.0", "os": "win", "version": "1.1.7", "date": "2026-05-10T05:28:58.000Z", "arch": "x86_64", "commit": "cb1e94528d3ede03776cb102bdf7017f821886c7", "fileid": "2dba3062fb35d396d969a88a8c68c196f0c7cadeac8b6cd040d838e2836403ae", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/data-cleaning/actions/runs/25620719657" }, { "r": "4.5.3", "os": "win", "version": "1.1.7", "date": "2026-05-10T05:28:56.000Z", "arch": "x86_64", "commit": "cb1e94528d3ede03776cb102bdf7017f821886c7", "fileid": "ac28006ffdcadc97c782a3a1e6545ef7969fc08ea2761e68df41603de1c04b32", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/data-cleaning/actions/runs/25620719657" }, { "r": "4.6.0", "os": "win", "version": "1.1.7", "date": "2026-05-10T05:29:02.000Z", "arch": "x86_64", "commit": "cb1e94528d3ede03776cb102bdf7017f821886c7", "fileid": "7ed04d4f7efcd6204a832b024002eb13b67aec165e15f79ab1a2640631737d81", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/data-cleaning/actions/runs/25620719657" }, { "r": "4.6.0", "os": "wasm", "version": "1.1.7", "date": "2026-05-22T12:47:55.000Z", "arch": "emscripten", "commit": "cb1e94528d3ede03776cb102bdf7017f821886c7", "fileid": "5c03130b49b16cb70751b47acd39719505626283f06bd69e75190573a25d0446", "status": "success", "buildurl": "https://github.com/r-universe/data-cleaning/actions/runs/25620719657" } ] }