devxy/build-cran-binaries
Watch
1
0
Fork
You've already forked build-cran-binaries
0
build-cran-binaries/local/missing-packages-in-index.R
pat-s 2614d40bd9 feat(stats): collect CDN access logs and publish download statistics
Add an hourly download-stats pipeline that reads the cran-rpkgs Bunny
access logs into a download_stats schema in the build metadata database
and publishes aggregated counts to /stats/downloads.json for the
rpkgs.com /stats page.

- Classify each request (download, index, redirect reason, probe, noise)
  mirroring the edge router, and split cloud/CI networks from the rest.
- De-duplicate downloads per client, package version and day, and key
  clients on a salted HMAC so no IP is stored or published.
- Exclude our own CI runners and record run windows to show gaps.
- Declare the zone's logging settings and allow CORS for JSON.
2026-11-14 13:02:53 +01:00

115 lines
3.3 KiB
R

library(bincraft)
library(dplyr)
s3fs::s3_file_system(
aws_access_key_id = Sys.getenv("HETZNER_S3_ACCESS_KEY_K3S"),
aws_secret_access_key = Sys.getenv("HETZNER_S3_SECRET_KEY_K3S"),
endpoint = "https://hel1.your-objectstorage.com",
region_name = "hel1",
)
files <- s3fs::s3_dir_ls(sprintf(
"devxy-r-package-binaries-hel1/amd64/jammy/latest/src/contrib"
))
files <- s3fs::s3_dir_ls(sprintf(
"devxy-r-package-binaries-hel1/amd64/noble/latest/src/contrib"
))
files <- s3fs::s3_dir_ls(sprintf(
"devxy-r-package-binaries-hel1/amd64/rhel8/latest/src/contrib"
))
files <- s3fs::s3_dir_ls(sprintf(
"devxy-r-package-binaries-hel1/amd64/rhel9/latest/src/contrib"
))
files <- s3fs::s3_dir_ls(sprintf(
"devxy-r-package-binaries-hel1/amd64/alpine320/latest/src/contrib"
))
files <- s3fs::s3_dir_ls(sprintf(
"devxy-r-package-binaries-hel1/arm64/jammy/latest/src/contrib"
))
files <- s3fs::s3_dir_ls(sprintf(
"devxy-r-package-binaries-hel1/arm64/noble/latest/src/contrib"
))
files <- s3fs::s3_dir_ls(sprintf(
"devxy-r-package-binaries-hel1/arm64/rhel8/latest/src/contrib"
))
files <- s3fs::s3_dir_ls(sprintf(
"devxy-r-package-binaries-hel1/arm64/rhel9/latest/src/contrib"
))
files <- s3fs::s3_dir_ls(sprintf(
"devxy-r-package-binaries-hel1/arm64/alpine320/latest/src/contrib"
))
files_b <- basename(files)
files_b_split <- sapply(strsplit(basename(files_b), "_"), function(x) x[1])
files_b_split <- setdiff(
files_b_split,
c("PACKAGES", "PACKAGES.gz", "PACKAGES.rds", "PACKAGES.db", "Archive")
)
# windows-only
files_b_split <- setdiff(
files_b_split,
c(
"PACKAGES",
"PACKAGES.gz",
"PACKAGES.rds",
"PACKAGES.db",
"Archive",
"RInno",
"KeyboardSimulator",
"R2PPT",
"RWinEdt",
"blatr",
"excel.link",
"spectrino",
"taskscheduleR",
"MDSGUI",
"BiplotGUI",
"R2wd"
)
)
pkgs_index <- available.packages(
"https://cran.devxy.io/amd64/jammy/latest/src/contrib"
)[, "Package"]
pkgs_index_b <- basename(pkgs_index)
if (length(files_b_split) != length(pkgs_index_b)) {
pkgs_missing <- setdiff(files_b_split, pkgs_index_b)
message("Packages missing in index but present in S3:")
pkgs_missing
formatted_pkgs <- gsub(
'"',
"'",
capture.output(dput(as.character(na.omit(pkgs_missing[1:900]))))
)
formatted_pkgs_one_line <- paste(formatted_pkgs, collapse = " ")
cat(formatted_pkgs_one_line, "\n", sep = "")
}
files <- s3fs::s3_dir_ls(sprintf(
"devxy-r-package-binaries-hel1/amd64/noble/latest/src/contrib"
))
files <- s3fs::s3_dir_ls(sprintf(
"devxy-r-package-binaries-hel1/amd64/rhel8/latest/src/contrib"
))
files <- s3fs::s3_dir_ls(sprintf(
"devxy-r-package-binaries-hel1/amd64/rhel9/latest/src/contrib"
))
files <- s3fs::s3_dir_ls(sprintf(
"devxy-r-package-binaries-hel1/amd64/alpine320/latest/src/contrib"
))
files <- s3fs::s3_dir_ls(sprintf(
"devxy-r-package-binaries-hel1/arm64/jammy/latest/src/contrib"
))
files <- s3fs::s3_dir_ls(sprintf(
"devxy-r-package-binaries-hel1/arm64/noble/latest/src/contrib"
))
files <- s3fs::s3_dir_ls(sprintf(
"devxy-r-package-binaries-hel1/arm64/rhel8/latest/src/contrib"
))
files <- s3fs::s3_dir_ls(sprintf(
"devxy-r-package-binaries-hel1/arm64/rhel9/latest/src/contrib"
))
files <- s3fs::s3_dir_ls(sprintf(
"devxy-r-package-binaries-hel1/arm64/alpine320/latest/src/contrib"
))