fix(#3): normalize the corpus URL's trailing slash at resolution

Investigating "gov search doesn't work" (#3) turned up two separate things.

THE REPORTED SYMPTOM IS ALREADY FIXED.
#3 reported `cog_gov_search("Orange")` dying in jsonlite with
`lexical error: invalid char in json text. <html> <head>`. That was fixed the
same day the issue was filed, by 8743472 "fix(manifest): actionable errors when
USCOGDATA_URL is unset or returns non-JSON" (issue filed 2026-05-27 11:30;
commit 2026-05-27). The issue was simply never closed. Verified now: injecting
an HTML manifest.json raises a typed `uscogdata_invalid_manifest` condition
naming the likely causes, with the raw parse error demoted to a footnote, and
`cog_gov_search("Orange")` returns 62 rows against the live corpus.

THE ROOT CAUSE OF THAT HTML WAS STILL LIVE -- and is what this commit fixes.

Every consumer builds locations by CONCATENATION:
  manifest.R:95   paste0(url, "manifest.json")
  mirror.R:48,125 paste0(url, e$path)
  views.R         the parquet glob
and mirror.R:104 documents the invariant outright ('url ends in "/"'). The
error messages tell users to set `"<url-or-local-path>/"`. But `.resolve_url()`
was a bare `.cfg("url")` passthrough -- the invariant was assumed everywhere and
enforced nowhere.

So a URL entered without the slash failed silently and misleadingly:
  HTTPS -> ".../downloadmanifest.json"; the host answers with an HTML 404 page,
           which lands in the JSON parser as EXACTLY the #3 symptom -- and the
           guard then blames "login page / 404 / wrong share" when the real
           cause was one missing character.
  local -> ".../corpusdata/long/**/*.parquet" and a DuckDB "No files found".

Reproduced both: pointing USCOGDATA_URL at the bundled fixture without a
trailing slash gave
  No files found that match ".../fixture_corpusdata/long/**/*.parquet"

Normalizing once at resolution fixes every consumer at the same time, rather
than having each call site re-derive the invariant. An empty setting passes
through untouched so manifest.R's "not configured" guard still fires instead of
the value degrading into a bare "/" filesystem root.

RED->GREEN: 4 tests added, 2 failed first (append-missing-slash, local-path
normalization); the already-correct cases (slash present, empty setting) passed
throughout and pin them against regression. Same fixture path that produced the
DuckDB error above now returns 62 rows.

Suite: FAIL 0 | WARN 0 | SKIP 0 | PASS 471 (was 463; +8 = the new tests).

R/config.R

@@ -21,7 +21,30 @@
   .uscogdata_defaults[[key]]
 }
 
-.resolve_url <- function() .cfg("url")
+#' Resolve the corpus URL, guaranteeing the trailing slash the package assumes.
+#'
+#' Every consumer builds locations by CONCATENATION -- `paste0(url,
+#' "manifest.json")` in manifest.R, `paste0(url, e$path)` in mirror.R, and the
+#' parquet glob in views.R -- and mirror.R:104 documents the invariant outright
+#' ('url ends in "/"'). Nothing enforced it, so a URL entered without the slash
+#' failed silently and misleadingly:
+#'
+#'   HTTPS -> ".../downloadmanifest.json"; the host answers with an HTML 404
+#'            page, which lands in the JSON parser as the lexical error
+#'            reported in issue #3 -- pointing the user at "login page / wrong
+#'            share" when the real cause was one missing character.
+#'   local -> ".../corpusdata/long/**/*.parquet" and a DuckDB "No files found".
+#'
+#' Normalizing here fixes every consumer at once, rather than each call site
+#' re-deriving the same invariant. An empty setting is passed through
+#' untouched so manifest.R's "not configured" guard still fires instead of the
+#' value degrading into a bare "/" filesystem root.
+#' @noRd
+.resolve_url <- function() {
+  url <- .cfg("url")
+  if (is.null(url) || !nzchar(url) || grepl("/$", url)) return(url)
+  paste0(url, "/")
+}
 
 .resolve_cache_dir <- function() {
   v <- .cfg("cache_dir")

R/manifest.R

@@ -128,7 +128,17 @@
 }
 
 #' @noRd
-.validate_schema <- function(manifest, supported = c(4L, 5L)) {
+#' Schema v6 (FIPS geography harmonization, 2026-07-22) is accepted alongside
+#' 4/5. v6 renamed the long table's fips_state_code/fips_county_code to
+#' fips_state_asof/fips_county_asof and added cog_legacy_state/
+#' cog_legacy_county (26 -> 28 cols); this package references NONE of those
+#' columns, so no code change was needed. NOTE the SILENT semantic change for
+#' any consumer of the raw long table: long fips_state/fips_county are now
+#' PRESENT/harmonized geography (current county identity carried back to every
+#' year, matching canonical_fips_xwalk) rather than as-of-year; as-of-year
+#' moved to the *_asof columns. This package's own geography always came from
+#' the xwalk (already present-based), so behaviour is unchanged.
+.validate_schema <- function(manifest, supported = c(4L, 5L, 6L)) {
   if (!manifest$schema_version %in% supported) {
     cli::cli_abort(c(
       "Corpus schema version mismatch.",

R/session.R

@@ -12,7 +12,7 @@ cog_open <- function(url = .resolve_url(),
   DBI::dbExecute(con, "INSTALL httpfs; LOAD httpfs;")
 
   manifest <- .fetch_or_cache_manifest(url, cache_dir)
-  .validate_schema(manifest, supported = c(4L, 5L))
+  .validate_schema(manifest, supported = c(4L, 5L, 6L))
   .validate_scope(manifest)
 
   .register_views(con, url, manifest)

inst/extdata/fixture_corpus/manifest.json

@@ -1,11 +1,24 @@
 {
-  "schema_version": 5,
+  "schema_version": 6,
-  "built_at": "2026-07-19T03:08:41Z",
+  "built_at": "2026-07-23T16:14:30Z",
-  "pipeline_commit": "ece9b32",
+  "pipeline_commit": "4f992a0",
   "fixture_note": "Four-year (2011, 2012, 2019, 2020) fixture for uscogdata tests. Full corpus available via USCOGDATA_URL. Regenerated for Phase R2 (schema_version 5, harmonization_map/harmonization_recipes/ series_breaks parquet tables added). 2011/2012 straddle the wide-aggregate -> modern-leaf format boundary exercised by basis= \"harmonized\" and recipe= queries; 2019/2020 retain the prior per-capita/CPI regression anchors. Full canonical_fips_xwalk master and canonical_alias lookup table included via data-raw/regenerate_fixture_corpus.R.",
   "data_vintage": {
-    "census_source_downloaded": "unknown",
+    "source_vintages": {
-    "cpi_vintage": "FRED CPIAUCSL",
+      "2012": "10162019",
+      "2013": "10162019",
+      "2014": "10162019",
+      "2015": "10162019",
+      "2016": "10162019",
+      "2017": "06102021",
+      "2018": "06102021",
+      "2019": "06102021",
+      "2020": "06122023",
+      "2021": "06122023",
+      "2022": "06052025",
+      "2023": "06052025"
+    },
+    "registry_rows": 148,
     "acs_vintage": "ACS 2018-2022 5-year"
   },
   "scope": {
@@ -14,8 +27,8 @@
     "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": 26,
+    "long_column_count": 28,
-    "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", "harmonized_code", "survey_weight"],
+    "long_columns": ["fips_state", "type", "fips_county", "govid", "gov_blank", "gov_name", "county_name", "fips_state_asof", "fips_county_asof", "cog_legacy_state", "cog_legacy_county", "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", "harmonized_code", "survey_weight"],
     "data_dictionary": "docs/data_dictionary.md"
   },
   "files": {
@@ -23,41 +36,41 @@
       {
         "year": 2011,
         "path": "data/long/year=2011/part-0.parquet",
-        "sha256": "76c2153ef0a94c3551a24751aa08225fc937fafb579f10fd0750848d781dc471",
+        "sha256": "84302ab364dc9fc3b3fbbc3c3f8b826e3508b4d73ff7c42d094d3863cd1e37b5",
-        "row_count": 3037606,
+        "row_count": 2864212,
-        "size_bytes": 4985667
+        "size_bytes": 3845911
       },
       {
         "year": 2012,
         "path": "data/long/year=2012/part-0.parquet",
-        "sha256": "a9bb10d04887490376a4b030a03a4ca1e0f1f9fbca5f7d99ea7ca7434c42b2bc",
+        "sha256": "b82ac82d5e35f844b26c887445601f3748438c52c998ba4e403b025941a6f170",
         "row_count": 1163338,
-        "size_bytes": 5900191
+        "size_bytes": 5929917
       },
       {
         "year": 2019,
         "path": "data/long/year=2019/part-0.parquet",
-        "sha256": "475481fcfbb030f96cae457cbda824512a2da6f97f4c6d12a75130979e4331f9",
+        "sha256": "5cbd4726dcc7d0dab5c2a05a64702e979533ae119ed0587073cd31c089e0d737",
         "row_count": 318139,
-        "size_bytes": 1717345
+        "size_bytes": 1719548
       },
       {
         "year": 2020,
         "path": "data/long/year=2020/part-0.parquet",
-        "sha256": "7cdf3eb1a73c34e6a3d22befdf7ccdd0b44b1e6b1cf4491159a38a5a24a1b005",
+        "sha256": "ee548fec80bf1beda844fe03916ac145f10dd34c45968407cc330ec260935f00",
         "row_count": 317500,
-        "size_bytes": 1720794
+        "size_bytes": 1722918
       }
     ],
     "metadata": [
       {
         "path": "data/canonical_alias.parquet",
-        "sha256": "fa27ce4b59e286ace05fbcb9f59a910b8e483fd6c58ddf01875a210b966809cb",
+        "sha256": "3f617051c23a99bea322889857f7106df0c92954564afeec181df7083ee6698e",
         "description": "canonical_alias.parquet"
       },
       {
         "path": "data/canonical_fips_xwalk.parquet",
-        "sha256": "b6e2c4cb748141f6f2e324d6704c13830d2a68ad57bbb73d04ac54b881d1285b",
+        "sha256": "f98742f941269dacf8f7de5c273aa4dd4e75017a5bb70c054da35852a95a8d46",
         "description": "canonical_fips_xwalk.parquet"
       },
       {
@@ -67,7 +80,7 @@
       },
       {
         "path": "data/harmonization_map.parquet",
-        "sha256": "52b4f3f94e65231aa869445946df7a0cfebf8fef1940f800e08287b53d09ab42",
+        "sha256": "4cf32d0f817079ba4f28dc0ce65450d3247ebbf08d94c0c26c0d02af597bf812",
         "description": "harmonization_map.parquet"
       },
       {
@@ -77,7 +90,7 @@
       },
       {
         "path": "data/series_breaks.parquet",
-        "sha256": "049bd7365dae14e357f6e57765dc5a069440bab46facce237d7ba2ec94b0b113",
+        "sha256": "b0b6794b6887a4f300079adfa10029c2a77109faa4952fbff1c5a270793cc02b",
         "description": "series_breaks.parquet"
       }
     ]

tests/testthat/test-config.R

@@ -26,3 +26,41 @@ test_that(".resolve_cache_dir falls back to R_user_dir", {
     })
   })
 })
+
+# ---------------------------------------------------------------------------
+# Trailing-slash normalization (uscogdata #3 follow-up).
+#
+# EVERY consumer builds paths by concatenation: paste0(url, "manifest.json")
+# (manifest.R), paste0(url, e$path) (mirror.R), and the parquet glob in
+# views.R. mirror.R:104 even comments 'url ends in "/"' -- an assumption the
+# package documents and relies on but never enforced.
+#
+# A URL missing its trailing slash therefore fails SILENTLY and confusingly:
+#   HTTPS -> ".../downloadmanifest.json" -> the host answers with an HTML 404
+#            page -> the jsonlite lexical error that issue #3 reported;
+#   local -> ".../corpusdata/long/**/*.parquet" -> DuckDB "No files found".
+# Neither message points at the real cause. Normalize once, at resolution.
+# ---------------------------------------------------------------------------
+
+test_that(".resolve_url appends a missing trailing slash", {
+  withr::local_envvar(USCOGDATA_URL = "https://example.org/s/TOKEN/download")
+  expect_equal(.resolve_url(), "https://example.org/s/TOKEN/download/")
+})
+
+test_that(".resolve_url leaves an existing trailing slash alone", {
+  withr::local_envvar(USCOGDATA_URL = "https://example.org/s/TOKEN/download/")
+  expect_equal(.resolve_url(), "https://example.org/s/TOKEN/download/")
+})
+
+test_that(".resolve_url normalizes a local path without a trailing slash", {
+  withr::local_envvar(USCOGDATA_URL = "/tmp/corpus")
+  expect_equal(.resolve_url(), "/tmp/corpus/")
+})
+
+test_that(".resolve_url does not invent a slash for an empty setting", {
+  # An unset/empty URL must stay empty so the "not configured" guard in
+  # manifest.R still fires, rather than degrading into a bare "/" root.
+  withr::local_envvar(USCOGDATA_URL = "")
+  withr::local_options(uscogdata.url = "")
+  expect_equal(.resolve_url(), "")
+})

tests/testthat/test-manifest.R

@@ -111,15 +111,20 @@ test_that("cog_manifest returns the active session's parsed manifest", {
   })
 })
 
-test_that(".validate_schema accepts schema_version 4 and 5, rejects others", {
+test_that(".validate_schema accepts schema_version 4, 5 and 6, rejects others", {
   expect_silent(uscogdata:::.validate_schema(list(schema_version = 4L)))
   expect_silent(uscogdata:::.validate_schema(list(schema_version = 5L)))
+  # v6 = FIPS geography harmonization (2026-07-22): _code -> _asof rename +
+  # cog_legacy_* columns (26 -> 28 cols). This package references none of the
+  # renamed columns and its geography comes from the xwalk, so v6 is accepted
+  # without behavioural change -- see .validate_schema()'s note.
+  expect_silent(uscogdata:::.validate_schema(list(schema_version = 6L)))
   expect_error(
     uscogdata:::.validate_schema(list(schema_version = 3L)),
     "schema_version"
   )
   expect_error(
-    uscogdata:::.validate_schema(list(schema_version = 6L)),
+    uscogdata:::.validate_schema(list(schema_version = 7L)),
     "schema_version"
   )
 })

tests/testthat/test-spending.R

@@ -250,12 +250,17 @@ test_that("provenance carries basis + harmonization block with na_rows_excluded"
     expect_true(prov$harmonization$applied)
     expect_true(prov$harmonization$na_rows_excluded >= 0L)
     expect_true(prov$harmonization$na_amount_excluded >= 0)
-    # Data-verified for this fixture: none of the discontinued_na rulings
+    # Data-verified for the v6 fixture (corpus 2026-07-22). The Task 18 map
-    # (S74, Z61, X04, X06, the debt-detail family, L24) fall inside the
+    # extension added E/F/G-prefix discontinued_na rulings the earlier pin's
-    # E/F/G/K spending prefixes, so the exclusion count is exactly zero for
+    # comment predated: E21/F21/G21 (Education NEC local, SB184-186,
-    # every year in the bundled window -- see
+    # "trivial; explicit-NA, full wide-era window"). Broward's 2011 legacy
-    # docs/phase_r_harmonization_review.md § 1.3/1.4.
+    # partition zero-pads exactly those three codes, so this query now
-    expect_equal(prov$harmonization$na_rows_excluded, 0L)
+    # excludes 3 NA-harmonized rows -- all with amt = 0, hence the excluded
+    # AMOUNT stays exactly zero. (The other discontinued_na rulings -- S74,
+    # Z61, X04, X06, the debt-detail family, L24 -- remain outside the
+    # E/F/G/K prefixes.) See docs/phase_r_harmonization_review.md § 1.3/1.4
+    # and cog_pipeline data/harmonization_map.csv E21/F21/G21 rows.
+    expect_equal(prov$harmonization$na_rows_excluded, 3L)
     expect_equal(prov$harmonization$na_amount_excluded, 0)
   })
 })