.crow/archive-missed-packages.yaml

@@ -28,10 +28,6 @@ matrix:
       ARCH: amd64
     - CODENAME: redhat-10
       ARCH: arm64
-    - CODENAME: alpine321
-      ARCH: amd64
-    - CODENAME: alpine321
-      ARCH: arm64
     - CODENAME: alpine322
       ARCH: amd64
     - CODENAME: alpine322

.crow/repair-built-stamp.yaml

@@ -0,0 +1,97 @@
+### Manual repair of a slot whose PACKAGES index advertises a broken `Built`
+### stamp (e.g. `Built: R 4.5.0; NA; ...`).
+#
+# uvr matches the stamp's platform triple plus R minor to decide binary vs
+# source, so an unusable triple turns a whole slot source-only. See
+# local/repair-built-stamp.R for why this patches PACKAGES.db in place instead
+# of forcing a full reparse.
+#
+# Run with `dry_run: true` first: it reports how many entries are broken per
+# slot and changes nothing. Pick the R version the slot should advertise, which
+# is the R_VERSION its entry in .crow/process-updates.yaml uses.
+variables:
+  target_arch:
+    description: 'Architecture of the slot to repair.'
+    options:
+      - amd64
+      - arm64
+    default: arm64
+  OS:
+    description: 'Base OS image name.'
+    options:
+      - alpine
+      - redhat
+      - ubuntu
+    default: alpine
+  OS_VERSION:
+    description: 'OS image tag. Must match OS (alpine: 3.22/3.23/3.24; redhat: 8/9/10; ubuntu: jammy/noble/resolute).'
+    options:
+      - '3.22'
+      - '3.23'
+      - '3.24'
+      - '8'
+      - '9'
+      - '10'
+      - 'jammy'
+      - 'noble'
+      - 'resolute'
+    default: '3.22'
+  R_VERSION:
+    description: 'R version whose stamp the slot should advertise.'
+    options:
+      - 4.5.3
+      - 4.4.3
+    default: 4.5.3
+  dry_run:
+    description: 'Report what would change without writing anything.'
+    options:
+      - 'true'
+      - 'false'
+    default: 'true'
+
+when:
+  - event: manual
+    evaluate: 'target_arch == "${ARCH}"'
+
+skip_clone: true
+
+labels:
+  platform: linux/${ARCH}
+  group: rpkgs-${ARCH}
+
+matrix:
+  include:
+    - ARCH: amd64
+    - ARCH: arm64
+
+steps:
+  - name: 'Repair Built stamp'
+    image: 'reg.devxy.io/rpkgs/build-env-${OS}:${OS_VERSION}'
+    pull: true
+    environment:
+      B2_S3_ACCESS_KEY:
+        from_secret: B2_S3_ACCESS_KEY
+      B2_S3_SECRET_KEY:
+        from_secret: B2_S3_SECRET_KEY
+      REPO_RO_TOKEN:
+        from_secret: REPO_RO_TOKEN
+      GIT_USER: pat-s
+    commands:
+      - git clone -q https://pat-s:$$REPO_RO_TOKEN@git.devxy.io/devxy/build-cran-binaries.git .
+      - /opt/R/$R_VERSION/bin/Rscript local/install-bincraft.R
+      - /opt/R/$R_VERSION/bin/R -q -e 'packageVersion("bincraft")'
+      - |
+        if [ "$dry_run" = "false" ]; then
+          /opt/R/$R_VERSION/bin/Rscript local/repair-built-stamp.R "$ARCH" --apply
+        else
+          /opt/R/$R_VERSION/bin/Rscript local/repair-built-stamp.R "$ARCH"
+        fi
+    backend_options:
+      docker:
+        resources:
+          requests:
+            memory: 2Gi
+            cpu: 1000m
+          limits:
+            memory: 8Gi
+            cpu: 2000m

local/repair-built-stamp.R

@@ -0,0 +1,175 @@
+#!/usr/bin/env Rscript
+
+### Rewrite a broken `Built` stamp across one arch/codename slot.
+###
+### A slot's index can end up advertising a stamp whose platform triple is
+### unusable, e.g. `Built: R 4.5.0; NA; ...`. uvr picks binary vs source by
+### matching that triple plus the R minor, so no client matches it and the whole
+### slot silently reverts to source-only, which makes uvr compile everything and
+### fail wherever a system `-dev` library is missing.
+###
+### Rewriting it is not a matter of re-running the normal index update.
+### `upload_package_index()` reuses the slot's remote `PACKAGES.db`, and
+### cranlike's `update_db()` only reparses files whose md5 changed, so entries
+### already in the database keep the stamp they were written with. Dropping
+### `PACKAGES.db` to force a full reparse does work, but for an S3 repo cranlike
+### reads each package's metadata from the CRAN *source* mirror on GitHub, so a
+### 25k-entry slot means 25k requests to raw.githubusercontent.com and a real
+### risk of being rate-limited part-way through.
+###
+### Only the `Built` column is wrong, so correct it in place instead: patch the
+### column in `PACKAGES.db`, put the database back, and let
+### `upload_package_index()` re-emit `PACKAGES*` from it. `update_db()` always
+### rewrites the index files even when nothing was reparsed, so no tarball is
+### re-read and nothing is fetched from GitHub.
+###
+### The replacement comes from `bincraft::built_stamp()` under the R running
+### this script, so run it under the R version the slot should advertise (the
+### `R_VERSION` its entry in `.crow/process-updates.yaml` uses). That is what a
+### healthy `upload_package_index()` run would have written.
+###
+### Usage, inside the platform's build image:
+###   Rscript local/repair-built-stamp.R <arch> [--apply]
+###
+### Without `--apply` it reports what it would change and touches nothing.
+
+suppressPackageStartupMessages({
+  library(bincraft)
+})
+
+args <- commandArgs(trailingOnly = TRUE)
+arch <- args[1L]
+apply_changes <- "--apply" %in% args
+
+if (is.na(arch) || !nzchar(arch)) {
+  stop(
+    "Usage: Rscript local/repair-built-stamp.R <arch> [--apply]",
+    call. = FALSE
+  )
+}
+
+bucket <- "devxy-rpkgs-binaries"
+endpoint <- "https://s3.eu-central-003.backblazeb2.com"
+region <- "eu-central-003"
+
+codename <- bincraft::set_codename(NULL)
+if (is.null(codename) || is.na(codename) || !nzchar(codename)) {
+  stop(
+    "Could not detect a codename from /etc/os-release; run this in a build image.",
+    call. = FALSE
+  )
+}
+
+# built_stamp() refuses an unusable platform, so a broken build image fails here
+# rather than writing a second bad stamp over the first one.
+stamp <- bincraft::built_stamp()
+message(sprintf("Slot:        %s/%s", arch, codename))
+message(sprintf("New stamp:   %s", stamp))
+
+s3fs::s3_file_system(
+  aws_access_key_id = Sys.getenv("B2_S3_ACCESS_KEY"),
+  aws_secret_access_key = Sys.getenv("B2_S3_SECRET_KEY"),
+  endpoint = endpoint,
+  region_name = region,
+  refresh = TRUE
+)
+
+base_dir <- file.path(bucket, arch, codename, "latest", "src", "contrib")
+
+# A stamp is broken when its platform component is absent or literally "NA".
+broken_stamp_where <- paste(
+  "Built IS NULL",
+  "OR Built LIKE '%; NA;%'",
+  "OR Built LIKE '%;  ;%'"
+)
+
+# The generic slot plus every per-minor sub-slot, which carry the same stamp and
+# are poisoned by the same run.
+r_minors <- sub(
+  "^.*/R/([0-9]+\\.[0-9]+)\\.[0-9]+$",
+  "\\1",
+  list.dirs("/opt/R", recursive = FALSE)
+)
+r_minors <- unique(grep("^[0-9]+\\.[0-9]+$", r_minors, value = TRUE))
+slots <- c(base_dir, file.path(base_dir, r_minors))
+
+repair_slot <- function(slot) {
+  db_remote <- file.path(slot, "PACKAGES.db")
+  if (!s3fs::s3_file_exists(db_remote)) {
+    message(sprintf("  %s: no PACKAGES.db, skipping", slot))
+    return(invisible(NULL))
+  }
+
+  db_local <- tempfile(fileext = ".db")
+  s3fs::s3_file_download(db_remote, db_local, overwrite = TRUE)
+
+  con <- DBI::dbConnect(RSQLite::SQLite(), db_local)
+  on.exit(DBI::dbDisconnect(con), add = TRUE)
+
+  total <- DBI::dbGetQuery(con, "SELECT COUNT(*) AS n FROM packages")$n
+  broken <- DBI::dbGetQuery(
+    con,
+    sprintf("SELECT COUNT(*) AS n FROM packages WHERE %s", broken_stamp_where)
+  )$n
+
+  message(sprintf("  %s: %s entries, %s broken", slot, total, broken))
+  if (broken == 0L) {
+    return(invisible(NULL))
+  }
+  if (!apply_changes) {
+    message("    (dry run, pass --apply to rewrite)")
+    return(invisible(NULL))
+  }
+
+  DBI::dbExecute(
+    con,
+    sprintf("UPDATE packages SET Built = ? WHERE %s", broken_stamp_where),
+    params = list(stamp)
+  )
+  DBI::dbDisconnect(con)
+  on.exit()
+
+  s3fs::s3_file_upload(db_local, db_remote, overwrite = TRUE)
+  message(sprintf("    rewrote %s entries and uploaded PACKAGES.db", broken))
+  invisible(NULL)
+}
+
+invisible(lapply(slots, repair_slot))
+
+if (!apply_changes) {
+  message("Dry run complete; nothing was changed.")
+  quit(save = "no")
+}
+
+# Re-emit PACKAGES/PACKAGES.gz/PACKAGES.rds from the corrected database. Nothing
+# is reparsed, because no tarball's md5 changed.
+message("Re-emitting index files from the corrected database...")
+bincraft::upload_package_index(
+  codename = codename,
+  s3_endpoint = endpoint,
+  s3_region = region,
+  s3_bucket = bucket,
+  s3_access_key_id = Sys.getenv("B2_S3_ACCESS_KEY"),
+  s3_secret_access_key = Sys.getenv("B2_S3_SECRET_KEY")
+)
+for (minor in r_minors) {
+  try(
+    bincraft::upload_package_index(
+      codename = codename,
+      r_minor = minor,
+      s3_endpoint = endpoint,
+      s3_region = region,
+      s3_bucket = bucket,
+      s3_access_key_id = Sys.getenv("B2_S3_ACCESS_KEY"),
+      s3_secret_access_key = Sys.getenv("B2_S3_SECRET_KEY")
+    ),
+    silent = FALSE
+  )
+}
+
+message("Done. Verify with:")
+message(sprintf(
+  "  curl -sS https://cran.devxy.io/%s/%s/latest/src/contrib/PACKAGES | grep '^Built:' | sort | uniq -c",
+  arch,
+  codename
+))