feat: record expenditure_concept in provenance and its JSON schema

Always populated, never implicit, so a downstream artifact says which concept
produced it. cog-api passes provenance through verbatim.
This commit is contained in:
2026-07-27 10:27:12 -04:00
parent 887acf7e81
commit 7913b0f664
4 changed files with 43 additions and 0 deletions
+4
View File
@@ -6,6 +6,8 @@
per_capita, adjust_to_year, result, sql,
subtype_col, basis = NA_character_,
basis_note = NA_character_,
expenditure_concept = "direct",
expenditure_concept_note = NA_character_,
harmonization = NULL, recipe = NULL,
suggestions = list()) {
manifest <- .uscogdata_env$manifest
@@ -51,6 +53,8 @@
category = category,
basis = basis,
basis_note = basis_note,
expenditure_concept = expenditure_concept,
expenditure_concept_note = expenditure_concept_note,
harmonization = harmonization %||% list(
applied = FALSE, na_rows_excluded = 0L, na_amount_excluded = 0,
note = NA_character_
+10
View File
@@ -220,6 +220,14 @@ cog_spending <- function(govid, years, category = NULL,
suggestions <- .build_suggestions(con, govid, years, category, result, resolved$basis)
}
# Determine expenditure_concept_note: only non-empty for "total", explains
# how the IG leg was assembled from legacy-era aggregates.
expenditure_concept_note_for_prov <- if (identical(expenditure_concept, "total")) {
"Total = Direct + intergovernmental (M to local govts + L to state govts). Legacy-era IG is assembled from aggregate-flagged rows, which are year-disjoint from their modern leaf components; the L-- family total is excluded."
} else {
NA_character_
}
prov <- .build_provenance(
verb = verb,
call = call,
@@ -233,6 +241,8 @@ cog_spending <- function(govid, years, category = NULL,
subtype_col = subtype_col,
basis = basis_for_prov,
basis_note = basis_note_for_prov,
expenditure_concept = expenditure_concept,
expenditure_concept_note = expenditure_concept_note_for_prov,
harmonization = harmonization,
recipe = recipe_block,
suggestions = suggestions