jared
c682e6547d
Three core query verbs over the spending_annotated / revenue_annotated DuckDB views. Each verb accepts vector govid, vector years, optional category filter, per_capita flag, and adjust_to_year for CPI-U real-dollar conversion (bundled index). Amounts are returned in full USD (SUM(amt) * 1000) so callers can freely rescale to millions/billions. The $1,000s -> $USD conversion is recorded in provenance$transformations$units_conversion. Every result carries an attr(., "provenance") list matching inst/schemas/provenance-v1.json. cog_explain() prints the structured form via cli or returns the raw list for MCP/JSON consumers. Also: .fetch_or_cache_manifest() now handles local fixture paths so tests can point USCOGDATA_FIXTURE_URL at the pipeline publish_cache/ without a working HTTP server. Tests: 80 pass / 0 fail. devtools::check() 0E/0W/2N (both notes pre-existing / environmental).
57 lines
1.8 KiB
R
57 lines
1.8 KiB
R
# R/manifest.R
|
|
|
|
#' Fetch manifest.json from URL (or read from a local fixture path),
|
|
#' cache locally, validate TTL.
|
|
#' @noRd
|
|
.fetch_or_cache_manifest <- function(url, cache_dir) {
|
|
# Local fixture path: read manifest directly; skip cache/TTL plumbing so
|
|
# tests pick up regenerated manifests immediately.
|
|
if (.is_local_path(url)) {
|
|
local_manifest <- file.path(url, "manifest.json")
|
|
if (!file.exists(local_manifest)) {
|
|
cli::cli_abort("Local fixture has no manifest.json at {local_manifest}")
|
|
}
|
|
return(jsonlite::fromJSON(local_manifest, simplifyVector = FALSE))
|
|
}
|
|
|
|
cache_path <- file.path(cache_dir, "manifest.json")
|
|
ttl <- as.integer(.cfg("manifest_ttl_secs"))
|
|
|
|
needs_fetch <- !file.exists(cache_path) ||
|
|
difftime(Sys.time(), file.info(cache_path)$mtime, units = "secs") > ttl
|
|
|
|
if (needs_fetch) {
|
|
resp <- httr2::request(paste0(url, "manifest.json")) |>
|
|
httr2::req_error(is_error = function(r) httr2::resp_status(r) >= 400) |>
|
|
httr2::req_perform()
|
|
writeLines(httr2::resp_body_string(resp), cache_path)
|
|
}
|
|
|
|
jsonlite::fromJSON(cache_path, simplifyVector = FALSE)
|
|
}
|
|
|
|
#' @noRd
|
|
.is_local_path <- function(url) {
|
|
!grepl("^[a-zA-Z][a-zA-Z0-9+.-]*://", url)
|
|
}
|
|
|
|
#' @noRd
|
|
.validate_schema <- function(manifest, expected_version) {
|
|
if (manifest$schema_version != expected_version) {
|
|
cli::cli_abort(c(
|
|
"Corpus schema version mismatch.",
|
|
x = "Package expects schema_version = {expected_version}; corpus has {manifest$schema_version}.",
|
|
i = "Update uscogdata (install.packages or pak::pkg_install) or re-publish corpus."
|
|
))
|
|
}
|
|
}
|
|
|
|
#' @noRd
|
|
.validate_scope <- function(manifest) {
|
|
included <- manifest$scope$gov_types_included
|
|
.uscogdata_env$scope_included <- included
|
|
invisible(NULL)
|
|
}
|
|
|
|
`%||%` <- function(a, b) if (is.null(a) || (length(a) == 1 && is.na(a))) b else a
|