jared
9233c3d18e
Six skipped tests, one per issue opened from the Madison walkthrough audit (docs/walkthroughs/FINDINGS.md in cog_explorer). Each asserts the desired behaviour, so it fails today and goes green when the fix lands; each is guarded by a single skip() naming its issue and finding IDs, so the suite stays green and activating a test is a one-line deletion. test-expenditure-concepts.R #11 F-012, F-017, F-018 test-revenue-concept-insurance-trust.R #12 F-014 test-coverage-disclosure.R #13 F-020, F-023 test-peer-summary-scope.R #14 F-021 test-amount-units-documented.R #15 F-004 test-gov-search-literal-match.R #16 F-025 helper-walkthrough-raw.R reads the corpus's long parquet partitions directly, bypassing uscogdata's SQL views. Every expected amount comes from there rather than from the verb under test - verifying an absence through the filter that creates it proves nothing, which was the most common defect in the audit itself. Verified: with the skips removed all six fail (or error) against the bundled fixture; with them in place the full suite is 576 pass / 0 fail / 6 skip.
59 lines
3.2 KiB
R
59 lines
3.2 KiB
R
# Madison walkthrough audit -- finding F-025. Tracked as uscogdata#16.
|
|
# See docs/walkthroughs/FINDINGS.md in cog_explorer.
|
|
#
|
|
# cog_gov_search()'s UTILITY mode interpolates `name` into
|
|
# regexp_matches(gov_name, <name>, 'i')
|
|
# unescaped (R/search.R:102), while BASKET mode in the same file already routes
|
|
# it through .escape_regex() (R/search.R:307) with the comment "so `name` is
|
|
# treated as a literal substring". Two failure modes result:
|
|
# correctness -- a real government cannot be found by its own exact name, and
|
|
# a single "." matches everything (HTTP 200 both ways via the API);
|
|
# robustness -- malformed regex reaches the engine and errors, which cog-api
|
|
# surfaces as a 500, reachable by typing a real name one
|
|
# character at a time.
|
|
#
|
|
# NOT asserted here: the finding's `q=St. Louis` example. Under correct literal
|
|
# matching that search still returns 0 rows, because the stored name is
|
|
# "ST LOUIS CITY" with no period -- it demonstrates today's over-matching
|
|
# semantics, not a row the fix makes findable.
|
|
|
|
test_that("cog_gov_search() matches name literally, not as an unescaped regex", {
|
|
testthat::skip("Blocked on uscogdata#16 (finding F-025)")
|
|
|
|
# -- correctness (1): a government must be findable by its own exact name ---
|
|
# FREDONIA (BRISCOE) CITY is real; today the parentheses are read as regex
|
|
# grouping, so its own complete name matches nothing.
|
|
fredonia <- cog_gov_search(name = "FREDONIA (BRISCOE) CITY")
|
|
expect_equal(nrow(fredonia), 1L)
|
|
expect_equal(fredonia$canonical_govid, "052117184386")
|
|
expect_equal(cog_gov_search(name = "FREDONIA (BRISCOE)")$canonical_govid,
|
|
"052117184386")
|
|
|
|
# -- correctness (2): a metacharacter must not become a wildcard ------------
|
|
# No Wisconsin city or village name contains a literal period -- established
|
|
# against the raw registry below, NOT through the verb under test. A literal
|
|
# search for "." must therefore return nothing; today it returns all 608.
|
|
con <- DBI::dbConnect(duckdb::duckdb())
|
|
on.exit(DBI::dbDisconnect(con, shutdown = TRUE), add = TRUE)
|
|
xwalk <- paste0(sub("/$", "", Sys.getenv("USCOGDATA_URL")),
|
|
"/data/canonical_fips_xwalk.parquet")
|
|
with_dot <- DBI::dbGetQuery(con, paste0(
|
|
"SELECT COUNT(*) n FROM read_parquet('", xwalk, "') ",
|
|
"WHERE fips_state = '55' AND govs_type = 2 AND gov_name LIKE '%.%'"))
|
|
expect_equal(as.integer(with_dot$n[[1]]), 0L)
|
|
|
|
expect_equal(nrow(cog_gov_search(name = ".", state = "WI", type = "city")), 0L)
|
|
expect_equal(nrow(cog_gov_search(name = "M.dison", state = "WI", type = "city")), 0L)
|
|
expect_equal(nrow(cog_gov_search(name = "Mad(i|o)son", state = "WI", type = "city")), 0L)
|
|
|
|
# A metacharacter-free name still resolves exactly as before.
|
|
expect_equal(nrow(cog_gov_search(name = "Madison", state = "WI", type = "city")), 1L)
|
|
|
|
# -- robustness: malformed pattern text returns no rows, and does not error --
|
|
# "[" alone, and "Athens-Clarke County (bal" -- an in-progress substring of
|
|
# ATHENS-CLARKE COUNTY (BALANCE), a real government -- both currently raise
|
|
# (DuckDB: "Invalid Input Error: missing ]").
|
|
expect_equal(nrow(cog_gov_search(name = "[")), 0L)
|
|
expect_equal(nrow(cog_gov_search(name = "Athens-Clarke County (bal")), 0L)
|
|
})
|