### Fail when a pipeline still targets a slot the edge does not route.
#
# Usage:
#   Rscript local/check-slots.R
#
# A slot is only reachable by clients if it appears in `local.rpkgs_slots` in
# `cdn.tf`. That list feeds the `UNION_SLOTS` variable, and
# `edge/rpkgs-router.ts` gates all per-R-minor index rewriting on it. A slot
# missing from it is not merely unadvertised: every request falls through to
# the flat index, which holds a single build per package, so clients on any R
# minor other than the one the slot was built against die at dyn.load().
#
# Alpine 3.22 sat in that state for months. It was built nightly, its per-minor
# indexes were correct, and it was never routed. `verify_routing=all` found it
# only because the run happened to include it: 1056 of 1056 checks passed on
# the 16 published slots and every failure in the run was alpine322, on both
# architectures, identical across all three URL forms.
#
# The check is deliberately one-directional. A pipeline targeting an unpublished
# slot is an error, because it spends build capacity on binaries nobody can
# reach and turns `verify_routing=all` permanently red for a reason that is not
# a defect. A published slot missing from *some* pipeline is only reported:
# several pipelines cover a subset on purpose (archive-missed-packages has no
# ubuntu rows, weekly-rebuild-missing has no alpine-324 rows), and the coverage
# a pipeline needs is its own business.
#
# The website's `DistroId` union in `src/src/data/repos.ts` must agree with
# `cdn.tf` too, but it lives in another repository so it cannot be checked here.

options(error = function() {
  cat("ERROR:", geterrmessage(), "\n", file = stdout())
  q(status = 1)
})

# `cdn.tf` is the source of truth, so read it rather than restating the list.
# The shape this depends on is the second string array inside the
# `rpkgs_slots` local, i.e. the distro list of the setproduct:
#
#   rpkgs_slots = [
#     for pair in setproduct(
#       ["amd64", "arm64"],
#       ["resolute", "noble", ...]
#     ) : "${pair[0]}/${pair[1]}"
#   ]
published_codenames <- function(path = "cdn.tf") {
  if (!file.exists(path)) {
    stop(
      sprintf("%s not found; run this from the repository root.", path),
      call. = FALSE
    )
  }
  lines <- readLines(path, warn = FALSE)
  start <- grep("rpkgs_slots\\s*=", lines)
  if (length(start) != 1L) {
    stop(
      "Could not find exactly one `rpkgs_slots` local in cdn.tf.",
      call. = FALSE
    )
  }
  block <- paste(lines[start:min(start + 10L, length(lines))], collapse = "\n")
  arrays <- regmatches(block, gregexpr("\\[[^]]*\\]", block))[[1L]]
  # The first array is the setproduct's arch list, the second is the distros.
  if (length(arrays) < 2L) {
    stop(
      "The `rpkgs_slots` local no longer has the two-array setproduct shape this parser expects. Update local/check-slots.R alongside cdn.tf.", # nolint
      call. = FALSE
    )
  }
  codenames <- regmatches(arrays[[2L]], gregexpr('"[^"]+"', arrays[[2L]]))[[1L]]
  codenames <- gsub('"', "", codenames)
  if (length(codenames) == 0L) {
    stop(
      "Parsed an empty distro list from cdn.tf; refusing to report every pipeline slot as unpublished.",
      call. = FALSE
    )
  }
  codenames
}

# Pipelines name a slot `<os>-<version>`, the edge and the bucket name it by
# codename. The ubuntu half of this mapping is also in `edge/rpkgs-router.ts`
# (UBUNTU_CODENAMES) and `local/build-all.R`.
UBUNTU_CODENAMES <- c(
  resolute = "ubuntu-2604",
  noble = "ubuntu-2404",
  jammy = "ubuntu-2204"
)

as_pipeline_os <- function(codename) {
  ifelse(
    codename %in% names(UBUNTU_CODENAMES),
    UBUNTU_CODENAMES[codename],
    ifelse(
      grepl("^rhel[0-9]+$", codename),
      sub("^rhel", "redhat-", codename),
      ifelse(
        grepl("^alpine[0-9]+$", codename),
        sub("^alpine([0-9])([0-9]+)$", "alpine-\\1\\2", codename),
        NA_character_
      )
    )
  )
}

# Structural lines only, so a codename mentioned in a comment is not a finding.
# Three shapes carry a slot: a matrix row (`- OS: alpine-323`), a continuation
# key (`CODENAME: alpine323`), and a dropdown option (`- alpine-323-amd64`).
slots_in_pipeline <- function(path) {
  lines <- readLines(path, warn = FALSE)
  hits <- character(0)
  row <- regmatches(
    lines,
    regexec("^\\s*-?\\s*(OS|CODENAME|OS_ID):\\s*(\\S+)\\s*$", lines)
  )
  hits <- c(
    hits,
    vapply(row, function(m) if (length(m) == 3L) m[[3L]] else NA_character_, "")
  )
  opt <- regmatches(
    lines,
    regexec("^\\s*-\\s*([a-z0-9]+-[a-z0-9]+)-(amd64|arm64)\\s*$", lines)
  )
  hits <- c(
    hits,
    vapply(opt, function(m) if (length(m) == 4L) m[[2L]] else NA_character_, "")
  )
  hits <- hits[!is.na(hits)]
  # `OS: alpine` (build-all-versions' bare image name) is not a slot.
  unique(hits[grepl("^(alpine|redhat|ubuntu)-?[0-9]", hits)])
}

codenames <- published_codenames()
published_os <- unname(as_pipeline_os(codenames))
if (anyNA(published_os)) {
  stop(
    sprintf(
      "Unrecognised codename(s) in cdn.tf: %s",
      paste(codenames[is.na(published_os)], collapse = ", ")
    ),
    call. = FALSE
  )
}
# A slot is written either way depending on the file, so accept both spellings.
published <- unique(c(published_os, codenames))

cat(sprintf(
  "Published slots (cdn.tf): %s\n\n",
  paste(sort(published_os), collapse = ", ")
))

files <- sort(list.files(".crow", pattern = "\\.yaml$", full.names = TRUE))
findings <- list()
for (f in files) {
  found <- slots_in_pipeline(f)
  stale <- setdiff(found, published)
  if (length(stale) > 0L) {
    findings[[f]] <- stale
    cat(sprintf(
      "%-45s targets unpublished: %s\n",
      f,
      paste(sort(stale), collapse = ", ")
    ))
  }
}

covered <- unique(unlist(lapply(files, slots_in_pipeline)))
uncovered <- setdiff(published_os, covered)
if (length(uncovered) > 0L) {
  cat(sprintf(
    "\nNote: %s appear(s) in no pipeline at all. That is a gap, not necessarily a bug.\n",
    paste(sort(uncovered), collapse = ", ")
  ))
}

if (length(findings) == 0L) {
  cat("All pipeline slots are published and routed.\n")
  quit(status = 0)
}

cat(sprintf(
  "\n%d file(s) target a slot the edge does not route. Retire it with:\n  just retire-slot <codename>\n",
  length(findings)
))
quit(status = 1)