R/config.R

@@ -5,7 +5,18 @@
 .uscogdata_env <- new.env(parent = emptyenv())
 
 .uscogdata_defaults <- list(
-  url               = "https://cloud.civilytics.org/s/REPLACE_WITH_SHARE_TOKEN/download/",
+  # Public HuggingFace mirror of the published corpus: CC-BY-4.0, no
+  # credential, CDN-backed. This is the default so `library(uscogdata)`
+  # followed by a verb works with zero configuration -- previously the
+  # default was a REPLACE_WITH_SHARE_TOKEN sentinel and no document in the
+  # package supplied a working URL, so a new user had no path to a session.
+  #
+  # The trailing slash is required: every consumer concatenates onto this
+  # (see .resolve_url(), which enforces it anyway).
+  #
+  # Override with USCOGDATA_URL or options(uscogdata.url=) to read a
+  # Nextcloud share or a local copy made by cog_mirror().
+  url               = "https://huggingface.co/datasets/civilytics/us-cog-finance/resolve/main/",
   cache_dir         = NULL,
   manifest_ttl_secs = 3600L
 )

R/manifest.R

@@ -28,7 +28,7 @@
       "*" = "{.code Sys.setenv(USCOGDATA_URL = \"<url-or-local-path>/\")}",
       "*" = "{.code options(uscogdata.url = \"<url-or-local-path>/\")}",
       i = "For an offline smoke test, use the bundled fixture: {.code system.file(\"extdata/fixture_corpus\", package = \"uscogdata\")}.",
-      i = "For the live Civilytics corpus, request the Nextcloud share URL from the package maintainer."
+      i = "The public corpus is the default: unset USCOGDATA_URL to use it, or point it at a local copy made by {.code cog_mirror()}."
     ), class = "uscogdata_url_not_configured")
   }
   invisible(url)

tests/testthat/test-config.R

@@ -64,3 +64,26 @@ test_that(".resolve_url does not invent a slash for an empty setting", {
   withr::local_options(uscogdata.url = "")
   expect_equal(.resolve_url(), "")
 })
+
+test_that("the default corpus URL is real, not a placeholder", {
+  # setup.R points USCOGDATA_URL at the bundled fixture for the whole suite,
+  # so both the env var and the option have to be cleared to see the default.
+  withr::local_envvar(USCOGDATA_URL = NA)
+  withr::local_options(uscogdata.url = NULL)
+  url <- .resolve_url()
+  expect_false(grepl("REPLACE_WITH", url, fixed = TRUE))
+  expect_match(url, "^https://")
+  expect_match(url, "/$")
+})
+
+test_that("an explicitly-set sentinel URL still aborts", {
+  # The guard must survive the default change: a user who half-edited a
+  # copied config still gets the actionable error.
+  withr::local_envvar(
+    USCOGDATA_URL = "https://other.example/s/REPLACE_WITH_SHARE_TOKEN/x/"
+  )
+  expect_error(
+    .check_url_configured(.resolve_url()),
+    class = "uscogdata_url_not_configured"
+  )
+})

tests/testthat/test-manifest.R

@@ -4,12 +4,14 @@
 # protect users from silent failures when USCOGDATA_URL is misconfigured
 # or returns non-JSON content.
 
-test_that("cog_open aborts with actionable error when URL is the placeholder default", {
+test_that("cog_open aborts with actionable error when URL contains the sentinel", {
   uscogdata:::cog_close()
   on.exit(uscogdata:::cog_close(), add = TRUE)
 
-  placeholder <- "https://cloud.civilytics.org/s/REPLACE_WITH_SHARE_TOKEN/download/"
-  withr::with_envvar(c(USCOGDATA_URL = placeholder), {
+  # No longer the package default (that is the public HF corpus). This is a
+  # user who copied a config template and did not finish editing it.
+  sentinel_url <- "https://cloud.civilytics.org/s/REPLACE_WITH_SHARE_TOKEN/download/"
+  withr::with_envvar(c(USCOGDATA_URL = sentinel_url), {
     expect_error(
       uscogdata:::cog_open(),
       class = "uscogdata_url_not_configured"
@@ -35,8 +37,10 @@ test_that("placeholder guard error names both env var and option as remediation"
   uscogdata:::cog_close()
   on.exit(uscogdata:::cog_close(), add = TRUE)
 
-  placeholder <- "https://cloud.civilytics.org/s/REPLACE_WITH_SHARE_TOKEN/download/"
-  withr::with_envvar(c(USCOGDATA_URL = placeholder), {
+  # No longer the package default (that is the public HF corpus). This is a
+  # user who copied a config template and did not finish editing it.
+  sentinel_url <- "https://cloud.civilytics.org/s/REPLACE_WITH_SHARE_TOKEN/download/"
+  withr::with_envvar(c(USCOGDATA_URL = sentinel_url), {
     msg <- tryCatch(uscogdata:::cog_open(), error = conditionMessage)
     expect_match(msg, "USCOGDATA_URL", fixed = TRUE)
     expect_match(msg, "uscogdata.url", fixed = TRUE)