Skip to content

Instantly share code, notes, and snippets.

@vjcitn
Created March 11, 2024 11:08
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save vjcitn/d485624d73d1e1cfb57bbbe76b786927 to your computer and use it in GitHub Desktop.
Save vjcitn/d485624d73d1e1cfb57bbbe76b786927 to your computer and use it in GitHub Desktop.
code to explore info.csv collected by BiocBuildDB process
allinf = c(
"buildResults/08150976a8cce9f7bf2d08a6ff86160c-info.csv.gz",
"buildResults/19dfe90f431098a035502d632404e0f2-info.csv.gz",
"buildResults/27dc71f7942ea33a660ca2495d2701d0-info.csv.gz",
"buildResults/2a0158be35acdff034889a8b072b823d-info.csv.gz",
"buildResults/2cc2a659a35d607f71655f3c9c9e4283-info.csv.gz",
"buildResults/3ebd0a185863d3d036726be357bedc60-info.csv.gz",
"buildResults/4104e02fcdf0685bf51735c7abb2c06e-info.csv.gz",
"buildResults/519f35883478df30fd90189f094770d7-info.csv.gz",
"buildResults/64744d6015f8f931cae0c13d1e50b092-info.csv.gz",
"buildResults/6852ab248878e416cc90a511126b8820-info.csv.gz",
"buildResults/6dcb4993e5b974a9fda8e0df80c7967d-info.csv.gz",
"buildResults/720123111c2b0a89ff99d299da16b35b-info.csv.gz",
"buildResults/7417c4f35bea65fc804a711bd523cbb5-info.csv.gz",
"buildResults/7d0263fd1ba33bc46fd90ed35ca33cb2-info.csv.gz",
"buildResults/7ed88d658d1afc2af60e57e5d40cda89-info.csv.gz",
"buildResults/82d41e20afac37e22bcbd43f960ae443-info.csv.gz",
"buildResults/8b3af5d1581133c77b82489003b49b80-info.csv.gz",
"buildResults/8e123541025ecd22c34dfddc0e98bb26-info.csv.gz",
"buildResults/9ce8fd8b9b4b44ff7a0565b6af55c82c-info.csv.gz",
"buildResults/a4b0827a2367c1a69163bbd6f5543686-info.csv.gz",
"buildResults/a4b96cd0144cda7995e3081c4852db65-info.csv.gz",
"buildResults/afc256f76ab6e5eb293dfd75c9a9da5a-info.csv.gz",
"buildResults/b0dc7d18988e0d06786b443c18bd14e3-info.csv.gz",
"buildResults/b0e50af261966e090388524f021bb139-info.csv.gz",
"buildResults/b9ccf9827b0c06f92c0b2ba3f0f815c3-info.csv.gz",
"buildResults/bca627c9675a897f5114b0e45aa212da-info.csv.gz",
"buildResults/bd9ffe295a9b837dc79b38a870462a42-info.csv.gz",
"buildResults/c65a6001bef3899f3d87d63945aa61f1-info.csv.gz",
"buildResults/d341cb12d9167958aa42761814e96904-info.csv.gz",
"buildResults/d3953a88573233bc3bd4028effb9ef6e-info.csv.gz",
"buildResults/f42db83bc13ea15f4120237a6b43530d-info.csv.gz",
"buildResults/f4fe7a8496477079b6bbc716b0d1b656-info.csv.gz",
"buildResults/f6f4a3a3ac68f1dd21ab45f79473ed7a-info.csv.gz",
"buildResults/ff7941d1efa918835d8679e3402702b9-info.csv.gz")
pa = sprintf('s3://bioc-builddb-mirror/%s', devinf)
con <- dbConnect(duckdb::duckdb(), read_only=TRUE)
dbExecute(con, "install 'httpfs'")
dbExecute(con, "load 'httpfs'")
gethead = function(pa) {
path = sprintf('s3://bioc-builddb-mirror/%s', pa)
sqlstring = sprintf("FROM read_csv('%s')", path)
Sys.sleep(1)
cat(".")
con |>
dplyr::tbl(dplyr::sql(sqlstring)) |> head(1) |> as.data.frame()
}
alli = lapply(allinf, gethead)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment