Merge pull request 'chore: regenerate fixture corpus at pipeline_commit e64a046 (#11 groundwork)' (#26) from feat/expenditure-concepts-11 into main

Reviewed-on: #26

inst/extdata/fixture_corpus/manifest.json

@@ -1,7 +1,7 @@
 {
   "schema_version": 6,
-  "built_at": "2026-07-30T14:07:36Z",
+  "built_at": "2026-07-30T20:01:56Z",
-  "pipeline_commit": "83f9715",
+  "pipeline_commit": "e64a046",
   "fixture_note": "Four-year (2011, 2012, 2019, 2020) fixture for uscogdata tests. Full corpus available via USCOGDATA_URL. Regenerated from the sparsified schema-v6 corpus: the wide era (<= FY2011) no longer stores explicit zeros, so FY2011 absence means Census published $0 while FY2012+ absence means not reported. representation.parquet and code_set.parquet carry that rule and ship in full, as do every other metadata table in the publish tree. 2011/2012 straddle both the wide-aggregate -> modern-leaf format boundary (exercised by basis=\"harmonized\" and recipe= queries) and the dense -> sparse representation boundary (SB194); 2019/2020 retain the prior per-capita/CPI regression anchors. Regenerated via data-raw/regenerate_fixture_corpus.R.",
   "data_vintage": {
     "source_vintages": {
@@ -105,12 +105,12 @@
       },
       {
         "path": "data/series_breaks.parquet",
-        "sha256": "5ae050dd7a76c4d25e5f99e7c2e81c1896482e3504e0443b47ab5d78ba148953",
+        "sha256": "381090660c8b8a1bee852e7f63d29b9ecaf10f71870f41c63de92017c83b6f1f",
         "description": "series_breaks.parquet"
       },
       {
         "path": "data/summary_categories.parquet",
-        "sha256": "e71d6d70d767c26c983fe56213baf204355f879582aa94841e62d9aea1877f83",
+        "sha256": "e4918abf8e9e6d1372d7ddc255dc199f9c303e250f4106449241b48c68abee67",
         "description": "summary_categories.parquet"
       }
     ]

tests/testthat/test-categories.R

@@ -8,7 +8,14 @@ test_that("cog_categories returns all categories grouped by subtype", {
   expect_gt(nrow(r), 10L)
   # corpus preserves Census-native "expenditure" vocabulary; the API takes
   # "spending" as a friendlier alias.
-  expect_setequal(unique(r$category_type), c("expenditure", "revenue"))
+  #
+  # `balance` joined as a third category_type with the cash-and-security
+  # holding codes (pipeline#76). `cog_categories()` is a CATALOGUE verb, not a
+  # money verb, so it surfaces every category_type the corpus carries -- the
+  # stock/flow guard belongs on cog_spending()/cog_revenue(), which must never
+  # return a balance row.
+  expect_setequal(unique(r$category_type),
+                  c("expenditure", "revenue", "balance"))
 })
 
 test_that("cog_categories(type = 'spending') returns only expenditure rows", {
@@ -18,8 +25,13 @@ test_that("cog_categories(type = 'spending') returns only expenditure rows", {
   # "assistance" (the J-prefix aid/benefit codes) joined the vocabulary with
   # the crosswalk completion in cog_pipeline#60/#65 -- every flow code
   # carrying dollars now maps to a category.
+  # `interest` (I89, I91-I94) and `insurance_benefits` (Y05/Y06/Y14/Y53)
+  # joined with the I/Q/Y flow batch -- the last two characters of Census's
+  # expenditure taxonomy. `interest` is what makes the three-concept model
+  # computable: primary = direct minus debt service.
   expect_true(all(r$subtype %in%
-                  c("operations", "capital", "intergovernmental", "assistance")))
+                  c("operations", "capital", "intergovernmental", "assistance",
+                    "interest", "insurance_benefits")))
 })
 
 test_that("cog_categories surfaces the intergovernmental spending subtype", {
@@ -37,8 +49,12 @@ 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"))
+  # `insurance_trust` (Y01/Y02/Y04/Y11/Y12/Y51/Y52) is deliberately NOT
+  # own_source: Census's "General Revenue" excludes insurance trust revenue,
+  # and Y01 alone is $1.31T corpus-wide.
   expect_true(all(r$subtype %in%
-                  c("own_source", "federal", "state", "local_aid")))
+                  c("own_source", "federal", "state", "local_aid",
+                    "insurance_trust")))
 })
 
 test_that("cog_categories(pattern = ...) filters case-insensitively", {