Nothing
test_that("source provenance survives only with the matching data file", {
path <- withr::local_tempfile()
writeLines("data", path)
meta <- list(source_last_published = "2026-10-01", source_fetched_at = "2026-10-26T12:00:00Z")
save_source_metadata(path, meta)
expect_equal(load_source_metadata(path)[names(meta)], meta)
Sys.setFileTime(path, as.POSIXct("2000-01-01", tz = "UTC"))
expect_equal(load_source_metadata(path)[names(meta)], meta)
writeLines("different data", path)
expect_true(all(is.na(unlist(load_source_metadata(path)))))
for (invalid in c("{broken", "1", "[]", "null")) {
writeLines(invalid, paste0(path, ".metadata.json"))
expect_true(all(is.na(unlist(load_source_metadata(path)))))
}
})
test_that("downloads distinguish server publication date from retrieval time", {
path <- withr::local_tempfile()
for (modified in c("Wed, 01 Oct 2025 12:00:00 GMT", "unknown", "")) {
local_mocked_bindings(req_perform = function(req, path) {
writeLines("downloaded", path)
headers <- if (nzchar(modified)) list(`last-modified` = modified) else list()
httr2::response(status_code = 200, headers = headers)
})
meta <- download_source("https://example.com/data", path)
expect_equal(readLines(path), "downloaded")
expect_equal(
meta$source_last_published,
if (startsWith(modified, "Wed")) "2025-10-01" else NA_character_
)
expect_match(meta$source_fetched_at, "^[0-9-]+T[0-9:]+Z$")
}
})
test_that("UT1 extraction resolves duplicates deterministically and records provenance", {
source <- withr::local_tempdir()
destination <- withr::local_tempdir()
lists <- list(
alpha = "shared.com", zeta = "shared.com",
broad = c("shared.com", "elsewhere.com"), liste_bu = "ignored.com"
)
for (name in names(lists)) {
dir.create(file.path(source, name))
writeLines(lists[[name]], file.path(source, name, "domains"))
writeLines(character(), file.path(source, name, "usage"))
}
archive <- withr::local_tempfile(fileext = ".tar.gz")
withr::with_dir(source, utils::tar(archive, files = names(lists), compression = "gzip"))
local_mocked_bindings(download_source = function(url, path) {
file.copy(archive, path)
list(source_last_published = "2026-10-25", source_fetched_at = "2026-10-26T12:00:00Z")
})
suppressMessages(get_ut1_data(destination))
result <- ut1_cat(
c("shared.com", "elsewhere.com", "ignored.com"),
file.path(destination, "ut1_domain_category.csv")
)
expect_equal(result$category, c(NA_character_, "broad", NA_character_))
expect_equal(result$labels[[1]]$category, c("alpha", "broad", "zeta"))
expect_true(all(is.na(result$details[[1]]$records$usage)))
expect_equal(result$source_last_published, rep("2026-10-25", 3))
})
Any scripts or data that you put into this service are public.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.