Merge pull request 'fix: cog_categories() surfaces balance subtypes and accepts type = "balance"' (#29) from fix/cog-categories-balance-subtype into main

Reviewed-on: #29

R/categories.R

@@ -5,12 +5,19 @@
 #' Returns the category taxonomy exposed by the corpus's
 #' `summary_categories` view, grouped to one row per
 #' `(category, subtype)` pair. Use this to discover valid `category`
-#' values for [cog_spending()] / [cog_revenue()] /
+#' values for [cog_spending()] / [cog_revenue()] / [cog_balances()] /
 #' [cog_geographic_rollup()] and to audit which Census item codes feed
 #' each category.
 #'
-#' @param type Either `NULL` (default, return both spending and revenue
-#'   rows), `"spending"`, or `"revenue"`.
+#' `subtype` COALESCEs the crosswalk's three subtype columns, so it carries
+#' `spend_subtype` on expenditure rows, `revenue_subtype` on revenue rows and
+#' `balance_subtype` on balance rows. Note that [cog_balances()] itself takes
+#' no `subtype` argument — for holdings, `category` is a strict coarsening of
+#' `balance_subtype` — but the value is surfaced here because it is the
+#' discovery surface downstream consumers build their vocabulary from.
+#'
+#' @param type Either `NULL` (default, every row: expenditure, revenue and
+#'   balance), `"spending"`, `"revenue"`, or `"balance"`.
 #' @param pattern Optional regex matched case-insensitively against the
 #'   `category` column (e.g. `"Police"` or `"Tax"`).
 #' @return Tibble with columns `category`, `category_type`, `subtype`,
@@ -20,8 +27,8 @@
 cog_categories <- function(type = NULL, pattern = NULL) {
   if (!is.null(type)) {
     if (!is.character(type) || length(type) != 1L ||
-        !type %in% c("spending", "revenue")) {
-      cli::cli_abort('`type` must be NULL, "spending", or "revenue".')
+        !type %in% c("spending", "revenue", "balance")) {
+      cli::cli_abort('`type` must be NULL, "spending", "revenue", or "balance".')
     }
   }
   if (!is.null(pattern) &&
@@ -48,7 +55,7 @@ cog_categories <- function(type = NULL, pattern = NULL) {
 
   sql <- paste(
     "SELECT category, category_type,
-            COALESCE(spend_subtype, revenue_subtype) AS subtype,
+            COALESCE(spend_subtype, revenue_subtype, balance_subtype) AS subtype,
             COUNT(DISTINCT item_code) AS n_codes,
             string_agg(DISTINCT item_code, ',' ORDER BY item_code) AS item_codes
      FROM summary_categories",

man/cog_categories.Rd

@@ -7,8 +7,8 @@
 cog_categories(type = NULL, pattern = NULL)
 }
 \arguments{
-\item{type}{Either `NULL` (default, return both spending and revenue
-rows), `"spending"`, or `"revenue"`.}
+\item{type}{Either `NULL` (default, every row: expenditure, revenue and
+balance), `"spending"`, `"revenue"`, or `"balance"`.}
 
 \item{pattern}{Optional regex matched case-insensitively against the
 `category` column (e.g. `"Police"` or `"Tax"`).}
@@ -22,7 +22,15 @@ Tibble with columns `category`, `category_type`, `subtype`,
 Returns the category taxonomy exposed by the corpus's
 `summary_categories` view, grouped to one row per
 `(category, subtype)` pair. Use this to discover valid `category`
-values for [cog_spending()] / [cog_revenue()] /
+values for [cog_spending()] / [cog_revenue()] / [cog_balances()] /
 [cog_geographic_rollup()] and to audit which Census item codes feed
 each category.
 }
+\details{
+`subtype` COALESCEs the crosswalk's three subtype columns, so it carries
+`spend_subtype` on expenditure rows, `revenue_subtype` on revenue rows and
+`balance_subtype` on balance rows. Note that [cog_balances()] itself takes
+no `subtype` argument — for holdings, `category` is a strict coarsening of
+`balance_subtype` — but the value is surfaced here because it is the
+discovery surface downstream consumers build their vocabulary from.
+}

tests/testthat/test-categories.R

@@ -93,3 +93,40 @@ test_that("cog_categories sorted by category_type, category, subtype", {
 test_that("cog_categories rejects invalid type", {
   expect_error(cog_categories(type = "both"), "type")
 })
+
+test_that("cog_categories() surfaces balance subtypes", {
+  skip_if_no_corpus()
+  with_fixture_corpus({
+    cc <- cog_categories()
+    b <- cc[cc$category_type == "balance", ]
+    expect_true(nrow(b) > 0L)
+
+    # Every balance row must carry its subtype. Before the COALESCE included
+    # balance_subtype these were all NA, which silently made the balance
+    # taxonomy undiscoverable -- cog-api derives its subtype vocabulary from
+    # this function, so an NA here becomes an unusable API parameter.
+    expect_false(any(is.na(b$subtype)))
+
+    # The exact set, read independently from the crosswalk rather than from
+    # the function under test.
+    con2 <- DBI::dbConnect(duckdb::duckdb())
+    on.exit(DBI::dbDisconnect(con2, shutdown = TRUE), add = TRUE)
+    p <- file.path(fixture_corpus_path(), "data", "summary_categories.parquet")
+    want <- DBI::dbGetQuery(con2, sprintf(
+      "SELECT DISTINCT balance_subtype FROM read_parquet(%s)
+       WHERE category_type = 'balance' AND balance_subtype IS NOT NULL
+       ORDER BY 1", uscogdata:::.sql_lit_chr(p)))$balance_subtype
+    expect_true(length(want) > 1L)
+    expect_identical(sort(unique(b$subtype)), sort(want))
+  })
+})
+
+test_that('cog_categories(type = "balance") filters to holdings', {
+  skip_if_no_corpus()
+  with_fixture_corpus({
+    b <- cog_categories(type = "balance")
+    expect_true(nrow(b) > 0L)
+    expect_identical(unique(b$category_type), "balance")
+    expect_false(any(is.na(b$subtype)))
+  })
+})