pat-s
2614d40bd9
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.
44 lines
1.4 KiB
R
44 lines
1.4 KiB
R
### Scope: Archive packages that have more than one entry in repository root
|
|
library(bincraft)
|
|
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",
|
|
refresh = T
|
|
)
|
|
|
|
arch <- "arm64"
|
|
os <- "alpine321"
|
|
|
|
files <- s3fs::s3_dir_ls(sprintf(
|
|
"devxy-r-package-binaries-hel1/%s/%s/latest/src/contrib",
|
|
arch,
|
|
os
|
|
))
|
|
length(unique(sapply(strsplit(basename(files), "_"), function(x) x[1])))
|
|
non_archived <- unique(sapply(strsplit(basename(files), "_"), function(x) {
|
|
x[1]
|
|
})[duplicated(sapply(strsplit(basename(files), "_"), function(x) x[1]))])
|
|
# RInno is not built because it only exists for Windows
|
|
non_archived <- setdiff(non_archived, "RInno")
|
|
# future::plan("sequential", workers = 8)
|
|
future::plan("sequential", workers = 1)
|
|
# future.apply::future_lapply(non_archived, function(x) archive_package(x, codename = os, arch = arch))
|
|
lapply(non_archived, function(x) {
|
|
archive_package(
|
|
x,
|
|
codename = os,
|
|
arch = arch,
|
|
s3_region = "hel1",
|
|
s3_endpoint = "https://hel1.your-objectstorage.com",
|
|
s3_bucket = "devxy-r-package-binaries-hel1",
|
|
s3_access_key_id = Sys.getenv(
|
|
"HETZNER_S3_ACCESS_KEY_K3S",
|
|
s3_secret_access_key = Sys.getenv("HETZNER_S3_SECRET_KEY_K3S")
|
|
)
|
|
)
|
|
})
|
|
# archive_package()
|
|
|
|
# grep("duckdb_", files, value = T)
|