feat: cog_gov_search + cog_mirror + scope-aware verb behavior

Three pieces:

1. cog_gov_search: name/state/type search over canonical_fips_xwalk
   for resolving human-readable place names into canonical_govids.
   Accepts USPS abbrev ('FL') or FIPS int (12) for state; integer
   0-3 or name ('state','county','city','township') for type. Types
   4/5 emit an explanatory cli message and return an empty tibble
   (v0.1 corpus excludes them). USPS<->FIPS table hardcoded with
   50 states + DC + territories; FIPS 66 = GU (not GA).

2. cog_mirror: downloads manifest-listed files to a local directory
   with SHA-256 idempotency (files with matching hash return status
   'cached'). Supports HTTP and local-path fixture URLs. Round-trip
   test: mirror + re-open against the mirror + query Broward 2020
   returns identical results.

3. Scope-aware verbs: .check_govids_in_scope() helper in session.R
   queries canonical_fips_xwalk for the requested govids, emits a
   cli_inform listing any missing ones, and records the found/missing
   sets under provenance$scope. Wired into cog_spending (and
   transitively into cog_revenue, cog_geographic_rollup,
   cog_peer_compare via their cog_spending calls).

Also: dropped dbplyr from Imports (unused).

Tests: +29 (22 search + 12 mirror - 5 refactored) / 159 total pass.
devtools::check() now clean: 0E / 0W / 0N.
This commit is contained in:
2026-04-24 11:38:32 -04:00
parent cc4d21ec82
commit 377eed1240
11 changed files with 522 additions and 6 deletions
+67
View File
@@ -0,0 +1,67 @@
test_that("cog_mirror copies manifest + metadata files", {
skip_if_no_corpus()
tmp <- tempfile("uscogmirror_"); dir.create(tmp)
on.exit(unlink(tmp, recursive = TRUE))
r <- cog_mirror(tmp, include = "metadata", progress = FALSE)
expect_s3_class(r, "tbl_df")
expect_true(file.exists(file.path(tmp, "manifest.json")))
expect_true(file.exists(file.path(tmp, "data/canonical_fips_xwalk.parquet")))
expect_true(file.exists(file.path(tmp, "data/summary_categories.parquet")))
expect_true(all(r$status == "downloaded"))
expect_true(all(c("path", "sha256", "size_bytes", "status") %in% names(r)))
})
test_that("cog_mirror is idempotent when SHA matches (status = 'cached')", {
skip_if_no_corpus()
tmp <- tempfile("uscogmirror_"); dir.create(tmp)
on.exit(unlink(tmp, recursive = TRUE))
cog_mirror(tmp, include = "metadata", progress = FALSE)
r2 <- cog_mirror(tmp, include = "metadata", progress = FALSE)
expect_true(all(r2$status == "cached"))
})
test_that("cog_mirror overwrite = TRUE re-copies even when SHA matches", {
skip_if_no_corpus()
tmp <- tempfile("uscogmirror_"); dir.create(tmp)
on.exit(unlink(tmp, recursive = TRUE))
cog_mirror(tmp, include = "metadata", progress = FALSE)
r3 <- cog_mirror(tmp, include = "metadata", progress = FALSE, overwrite = TRUE)
expect_true(all(r3$status == "downloaded"))
})
test_that("cog_mirror verifies sha256 against manifest", {
skip_if_no_corpus()
tmp <- tempfile("uscogmirror_"); dir.create(tmp)
on.exit(unlink(tmp, recursive = TRUE))
r <- cog_mirror(tmp, include = "metadata", progress = FALSE)
for (i in seq_len(nrow(r))) {
got <- digest::digest(file.path(tmp, r$path[i]),
algo = "sha256", file = TRUE)
expect_equal(got, r$sha256[i])
}
})
test_that("cog_mirror reads back via a fresh session against the mirror", {
skip_if_no_corpus()
tmp <- tempfile("uscogmirror_"); dir.create(tmp)
on.exit(unlink(tmp, recursive = TRUE))
cog_mirror(tmp, include = c("long", "metadata"), progress = FALSE)
# Re-open against the local mirror and run a query.
old_url <- getOption("uscogdata.url")
on.exit({
cog_close()
options(uscogdata.url = old_url)
}, add = TRUE)
cog_close()
options(uscogdata.url = paste0(normalizePath(tmp), "/"))
r <- cog_spending("101006006", 2020L, "Corrections")
expect_gt(nrow(r), 0L)
expect_equal(unique(r$canonical_govid), "101006006")
})