Created
March 28, 2024 05:44
-
-
Save ConnorBaker/afb55c4b99510d4d012904bb03aa24c3 to your computer and use it in GitHub Desktop.
find /nix/store/.links -type f -printf "%s\n" | awk --file=filesize_stats.awk
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| function human_readable(size) { | |
| split("B KB MB GB TB PB", units); # Include PB in the units array to avoid separate handling | |
| unit_idx = 1; # Start with bytes | |
| while (size >= 1024 && unit_idx < length(units)) { | |
| size /= 1024; | |
| unit_idx++; | |
| } | |
| return sprintf("%.6f %s", size, units[unit_idx]); | |
| } | |
| function compute_median(sorted_arr) { | |
| len = length(sorted_arr); | |
| if (len % 2 == 1) { | |
| return sorted_arr[(len + 1) / 2]; | |
| } else { | |
| return (sorted_arr[len / 2] + sorted_arr[len / 2 + 1]) / 2.0; | |
| } | |
| } | |
| function count_number_of_zero_byte_files(sorted_arr) { | |
| num_zero_byte_files = 0; | |
| i = 1; | |
| while (sorted_arr[i] == 0) { | |
| num_zero_byte_files++; | |
| i++; | |
| } | |
| return num_zero_byte_files; | |
| } | |
| function print_info() { | |
| asort(sizes_bytes); | |
| num_zero_byte_files = count_number_of_zero_byte_files(sizes_bytes); | |
| min_bytes = sizes_bytes[1]; | |
| max_bytes = sizes_bytes[num_files]; | |
| mean_bytes = total_size_bytes / num_files; | |
| median_bytes = compute_median(sizes_bytes); | |
| variance_bytes = (total_size_bytes_sqs - (total_size_bytes * total_size_bytes) / num_files) / num_files; | |
| stddev_bytes = sqrt(variance_bytes); | |
| print "Num files:", num_files; | |
| print "Num zero-byte files:", num_zero_byte_files; | |
| print "Total size:", human_readable(total_size_bytes); | |
| print "Min size:", human_readable(min_bytes); | |
| print "Max size:", human_readable(max_bytes); | |
| print "Mean size:", human_readable(mean_bytes); | |
| print "Median size:", human_readable(median_bytes); | |
| print "Standard deviation:", human_readable(stddev_bytes); | |
| } | |
| BEGIN { | |
| num_files = 0; | |
| total_size_bytes = 0; | |
| total_size_bytes_sqs = 0; | |
| } | |
| { | |
| num_files++; | |
| sizes_bytes[num_files] = $1; | |
| total_size_bytes += $1; | |
| total_size_bytes_sqs += $1 * $1; | |
| } | |
| END { | |
| if (num_files > 0) { | |
| print_info(); | |
| } else { | |
| print "No files found."; | |
| } | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment