test: bundle fixture corpus + wire local-path test helpers

Adds inst/extdata/fixture_corpus/ — a 3.6 MB two-year (2019/2020) slice
of the published corpus (OH+VT+WY fixture from cog_pipeline test profile
plus all 50 states). Includes canonical_fips_xwalk.parquet,
summary_categories.parquet, docs/, and a trimmed manifest.json.

setup.R now points USCOGDATA_URL at the bundled fixture automatically,
bypassing HTTP / Nextcloud entirely. DuckDB reads local parquet via the
existing .is_local_path() fast-path in manifest.R; no httpfs required.
session is reset between test files via withr::defer(cog_close()).

helper-fixture.R gains fixture_corpus_path(), a richer skip_if_no_corpus()
that checks the bundled fixture first, and with_fixture_corpus() for
tests that need explicit session isolation.

test-spending.R: adjust the inflate-column test to use 2019 (fixture year)
instead of 2015 (absent from fixture).

Result: 181 PASS / 0 FAIL / 0 SKIP — all tests run against real parquet
data with real DuckDB queries and no network dependency.

inst/extdata/fixture_corpus/manifest.json

@@ -0,0 +1,86 @@
+{
+  "schema_version": 3,
+  "built_at": "2026-04-27T16:43:46Z",
+  "pipeline_commit": "899af37",
+  "fixture_note": "Two-year (2019-2020) fixture for uscogdata tests. Full corpus available via USCOGDATA_URL.",
+  "data_vintage": {
+    "census_source_downloaded": "unknown",
+    "cpi_vintage": "FRED CPIAUCSL",
+    "acs_vintage": "ACS 2018-2022 5-year"
+  },
+  "scope": {
+    "gov_types_included": [
+      0,
+      1,
+      2,
+      3
+    ],
+    "gov_types_excluded": [
+      4,
+      5
+    ],
+    "scope_note": "v0.1 covers state, county, city/municipality, and township governments. Special districts (type 4) and school districts (type 5) are excluded pending validation in a future cycle."
+  },
+  "schema": {
+    "long_column_count": 24,
+    "long_columns": [
+      "fips_state",
+      "type",
+      "fips_county",
+      "govid",
+      "gov_blank",
+      "gov_name",
+      "county_name",
+      "fips_state_code",
+      "fips_county_code",
+      "fips_place_code",
+      "population",
+      "popyear",
+      "enrollment",
+      "enrollyear",
+      "function_code",
+      "sch_level_code",
+      "fiscal_year_end",
+      "srvy_year",
+      "item_code",
+      "amt",
+      "srv_data",
+      "impute_flag",
+      "is_aggregate",
+      "canonical_govid"
+    ],
+    "data_dictionary": "docs/data_dictionary.md"
+  },
+  "files": {
+    "long_partitions": [
+      {
+        "year": 2019,
+        "path": "data/long/year=2019/part-0.parquet",
+        "sha256": "e1c9f426c6d7d3c51d06b3a652473b987b304836619c213f019cee4887714daa",
+        "row_count": 318139,
+        "size_bytes": 1424231
+      },
+      {
+        "year": 2020,
+        "path": "data/long/year=2020/part-0.parquet",
+        "sha256": "9b795853a848e8c955c80261b96b79630fc77394dcfb1a1ca288e2cd634053a3",
+        "row_count": 317500,
+        "size_bytes": 1427150
+      }
+    ],
+    "metadata": [
+      {
+        "path": "data/canonical_fips_xwalk.parquet",
+        "sha256": "86e53e04a35f6f90bb74bb1a273e053392afa782d6f518e3e3da9c976d47f7af",
+        "description": "canonical_fips_xwalk.parquet"
+      },
+      {
+        "path": "data/summary_categories.parquet",
+        "sha256": "60045e22bc2723318fa2cb73f8e5038250dc54d24b3447c6750dfe29035335b8",
+        "description": "summary_categories.parquet"
+      }
+    ]
+  },
+  "series_breaks_ref": "docs/series_breaks.md",
+  "reader_spec_ref": "docs/reader-specification.md"
+}

tests/testthat/helper-fixture.R

@@ -1,6 +1,28 @@
 # tests/testthat/helper-fixture.R
+
+# Returns the path to the bundled fixture corpus (trailing slash for DuckDB globs).
+fixture_corpus_path <- function() {
+  p <- system.file("extdata/fixture_corpus", package = "uscogdata")
+  if (nzchar(p)) paste0(p, "/") else ""
+}
+
+# Skip a test if no corpus is reachable (bundled fixture or explicit remote URL).
 skip_if_no_corpus <- function() {
-  testthat::skip_if(Sys.getenv("USCOGDATA_FIXTURE_URL", "") == "" &&
-                    !file.exists("~/.cache/R/uscogdata/manifest.json"),
-                    "No fixture corpus available")
+  p <- fixture_corpus_path()
+  has_fixture <- nzchar(p) && file.exists(sub("/$", "/manifest.json", p))
+  has_remote  <- nzchar(Sys.getenv("USCOGDATA_FIXTURE_URL", ""))
+  testthat::skip_if(!has_fixture && !has_remote, "No fixture corpus available")
+}
+
+# Run a block against the fixture corpus with a clean session.
+# Restores the previous URL and closes the DuckDB connection when done.
+with_fixture_corpus <- function(code) {
+  old_url <- Sys.getenv("USCOGDATA_URL", unset = NA)
+  uscogdata:::cog_close()
+  Sys.setenv(USCOGDATA_URL = fixture_corpus_path())
+  on.exit({
+    uscogdata:::cog_close()
+    if (is.na(old_url)) Sys.unsetenv("USCOGDATA_URL") else Sys.setenv(USCOGDATA_URL = old_url)
+  }, add = TRUE)
+  force(code)
 }

tests/testthat/setup.R

@@ -1,5 +1,13 @@
 # tests/testthat/setup.R
-# Point tests at a fixture corpus URL if provided.
-if (Sys.getenv("USCOGDATA_FIXTURE_URL", "") != "") {
-  options(uscogdata.url = Sys.getenv("USCOGDATA_FIXTURE_URL"))
-}
+# Priority: bundled fixture > USCOGDATA_FIXTURE_URL env var > whatever is already set.
+local({
+  p <- system.file("extdata/fixture_corpus", package = "uscogdata")
+  if (nzchar(p) && file.exists(file.path(p, "manifest.json"))) {
+    Sys.setenv(USCOGDATA_URL = paste0(p, "/"))
+  } else if (nzchar(Sys.getenv("USCOGDATA_FIXTURE_URL", ""))) {
+    Sys.setenv(USCOGDATA_URL = Sys.getenv("USCOGDATA_FIXTURE_URL"))
+  }
+})
+
+# Reset DuckDB session between test files so each file starts clean.
+withr::defer(uscogdata:::cog_close(), teardown_env())

tests/testthat/test-spending.R

@@ -34,11 +34,11 @@ test_that("cog_spending with per_capita adds per-capita nominal column", {
 
 test_that("cog_spending with adjust_to_year adds real column", {
   skip_if_no_corpus()
-  r <- cog_spending("101006006", 2015:2020, "Corrections",
+  r <- cog_spending("101006006", 2019:2020, "Corrections",
                     adjust_to_year = 2022L)
   expect_true("amt_real" %in% names(r))
-  r2015 <- dplyr::filter(r, year == 2015L)
-  expect_true(any(r2015$amt_nominal != r2015$amt_real))
+  r2019 <- dplyr::filter(r, year == 2019L)
+  expect_true(any(r2019$amt_nominal != r2019$amt_real))
 })
 
 test_that("cog_spending with per_capita + adjust_to_year adds all columns", {