feat: cog_categories

Discovery verb over the summary_categories view, grouped one row per (category, subtype). Parallels cog_gov_search: analysts use it to find the valid `category` values to pass into cog_spending(), cog_revenue(), cog_geographic_rollup(). Columns: category, category_type, subtype, n_codes, item_codes (comma-separated, alphabetical). Optional filters: type = NULL | "spending" | "revenue" pattern = regex matched case-insensitively on category The user-facing "spending" alias is translated internally to the corpus-native "expenditure" so callers don't have to learn Census vocabulary, while the returned category_type column preserves the native value for auditability. Also: fix @noRd placement in session.R so devtools::document() stops warning. Tests: +16 new / 181 total pass. check 0E/0W/0N.
2026-04-24 18:15:26 -04:00
parent a778d790d8
commit 488d03d74b
5 changed files with 161 additions and 10 deletions
@@ -0,0 +1,62 @@
+test_that("cog_categories returns all categories grouped by subtype", {
+  skip_if_no_corpus()
+  r <- cog_categories()
+  expect_s3_class(r, "tbl_df")
+  expected <- c("category", "category_type", "subtype",
+                "n_codes", "item_codes")
+  expect_true(all(expected %in% names(r)))
+  expect_gt(nrow(r), 10L)
+  # corpus preserves Census-native "expenditure" vocabulary; the API takes
+  # "spending" as a friendlier alias.
+  expect_setequal(unique(r$category_type), c("expenditure", "revenue"))
+})
+
+test_that("cog_categories(type = 'spending') returns only expenditure rows", {
+  skip_if_no_corpus()
+  r <- cog_categories(type = "spending")
+  expect_true(all(r$category_type == "expenditure"))
+  expect_true(all(r$subtype %in% c("operations", "capital")))
+})
+
+test_that("cog_categories(type = 'revenue') returns only revenue rows", {
+  skip_if_no_corpus()
+  r <- cog_categories(type = "revenue")
+  expect_true(all(r$category_type == "revenue"))
+  expect_true(all(r$subtype %in%
+                  c("own_source", "federal", "state", "local_aid")))
+})
+
+test_that("cog_categories(pattern = ...) filters case-insensitively", {
+  skip_if_no_corpus()
+  r <- cog_categories(pattern = "police")
+  expect_gt(nrow(r), 0L)
+  expect_true(all(grepl("Police", r$category, ignore.case = TRUE)))
+})
+
+test_that("cog_categories has one row per (category, subtype)", {
+  skip_if_no_corpus()
+  r <- cog_categories()
+  key <- paste(r$category, r$subtype, sep = "|")
+  expect_equal(length(key), length(unique(key)))
+})
+
+test_that("cog_categories item_codes is non-empty comma-separated string", {
+  skip_if_no_corpus()
+  r <- cog_categories()
+  expect_true(all(nzchar(r$item_codes)))
+  expect_true(all(r$n_codes >= 1L))
+  # n_codes should equal count of commas + 1
+  expect_equal(r$n_codes,
+               vapply(strsplit(r$item_codes, ","), length, integer(1)))
+})
+
+test_that("cog_categories sorted by category_type, category, subtype", {
+  skip_if_no_corpus()
+  r <- cog_categories()
+  sorted <- r[order(r$category_type, r$category, r$subtype), ]
+  expect_identical(r, sorted)
+})
+
+test_that("cog_categories rejects invalid type", {
+  expect_error(cog_categories(type = "both"), "type")
+})