feat: register balance_long / balance_annotated behind a column gate (#25)

2026-08-03 09:46:36 -04:00
parent a11e29a0e0
commit d09bfd6aef
5 changed files with 142 additions and 0 deletions
@@ -154,3 +154,36 @@ with_corpus_missing_ig_categories <- function(code) {
  }, add = TRUE)
  force(code)
 }
+
+# Copy the bundled fixture to a temp dir with summary_categories.parquet
+# rewritten to DROP the balance_subtype column, then run `code` against it.
+# Models a corpus published before cog_pipeline #76/#77. schema_version is
+# left untouched deliberately: that change shipped without a version bump, so
+# column presence is the only honest signal -- this helper is what proves the
+# package keys off it. Mirrors with_corpus_missing_ig_categories().
+with_corpus_missing_balance_subtype <- function(code) {
+  src <- fixture_corpus_path()
+  tmp <- withr::local_tempdir(.local_envir = parent.frame())
+  file.copy(list.files(src, full.names = TRUE), tmp, recursive = TRUE)
+
+  cats_path <- file.path(tmp, "data", "summary_categories.parquet")
+  filtered_path <- file.path(tmp, "data", "summary_categories_filtered.parquet")
+  write_con <- DBI::dbConnect(duckdb::duckdb())
+  on.exit(DBI::dbDisconnect(write_con, shutdown = TRUE), add = TRUE)
+  DBI::dbExecute(write_con, sprintf(
+    "COPY (SELECT * EXCLUDE (balance_subtype) FROM read_parquet(%s))
+     TO %s (FORMAT PARQUET)",
+    uscogdata:::.sql_lit_chr(cats_path), uscogdata:::.sql_lit_chr(filtered_path)
+  ))
+  file.remove(cats_path)
+  file.rename(filtered_path, cats_path)
+
+  old_url <- Sys.getenv("USCOGDATA_URL", unset = NA)
+  uscogdata:::cog_close()
+  Sys.setenv(USCOGDATA_URL = paste0(tmp, "/"))
+  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)
+}
@@ -0,0 +1,47 @@
+test_that("balance views register and carry only balance codes", {
+  skip_if_no_corpus()
+  con <- cog_open()
+  on.exit(cog_close())
+
+  views <- DBI::dbGetQuery(con,
+    "SELECT table_name FROM information_schema.tables
+     WHERE table_schema = 'main' AND table_type = 'VIEW'"
+  )$table_name
+  expect_true(all(c("balance_long", "balance_annotated") %in% views))
+
+  # Every item_code in balance_long is a category_type = 'balance' member.
+  leak <- DBI::dbGetQuery(con,
+    "SELECT COUNT(*) AS n FROM balance_long
+     WHERE item_code NOT IN (
+       SELECT item_code FROM summary_categories WHERE category_type = 'balance')"
+  )$n
+  expect_identical(as.integer(leak), 0L)
+
+  # And no aggregate row survives, mirroring revenue_long.
+  agg <- DBI::dbGetQuery(con,
+    "SELECT COUNT(*) AS n FROM balance_long WHERE is_aggregate"
+  )$n
+  expect_identical(as.integer(agg), 0L)
+
+  # balance_annotated exposes the subtype column the verb groups on.
+  cols <- DBI::dbGetQuery(con,
+    "SELECT column_name FROM information_schema.columns
+     WHERE table_name = 'balance_annotated'"
+  )$column_name
+  expect_true(all(c("category", "category_type", "balance_subtype") %in% cols))
+})
+
+test_that("balance views are skipped on a corpus without balance_subtype", {
+  skip_if_no_corpus()
+  with_corpus_missing_balance_subtype({
+    con <- cog_open()
+    on.exit(cog_close())
+    views <- DBI::dbGetQuery(con,
+      "SELECT table_name FROM information_schema.tables
+       WHERE table_schema = 'main' AND table_type = 'VIEW'"
+    )$table_name
+    # Registration must SKIP them, not error -- an older corpus stays usable.
+    expect_false(any(c("balance_long", "balance_annotated") %in% views))
+    expect_true("revenue_long" %in% views)
+  })
+})