File: sn.sh
   1 #!/bin/sh
   2 
   3 # The MIT License (MIT)
   4 #
   5 # Copyright © 2020-2025 pacman64
   6 #
   7 # Permission is hereby granted, free of charge, to any person obtaining a copy
   8 # of this software and associated documentation files (the “Software”), to deal
   9 # in the Software without restriction, including without limitation the rights
  10 # to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
  11 # copies of the Software, and to permit persons to whom the Software is
  12 # furnished to do so, subject to the following conditions:
  13 #
  14 # The above copyright notice and this permission notice shall be included in
  15 # all copies or substantial portions of the Software.
  16 #
  17 # THE SOFTWARE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
  18 # IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
  19 # FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
  20 # AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
  21 # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
  22 # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  23 # SOFTWARE.
  24 
  25 
  26 # sn [filepaths...]
  27 #
  28 # Summarize Numbers does what it says, using all numbers detected from the
  29 # input(s). When given no filepaths, it reads from standard input.
  30 
  31 
  32 case "$1" in
  33     -h|--h|-help|--help)
  34         awk '/^# +sn /, /^$/ { gsub(/^# ?/, ""); print }' "$0"
  35         exit 0
  36     ;;
  37 esac
  38 
  39 [ "$1" = "--" ] && shift
  40 
  41 # show all non-existing files given
  42 failed=0
  43 for arg in "$@"; do
  44     if [ "${arg}" = "-" ]; then
  45         continue
  46     fi
  47     if [ ! -e "${arg}" ]; then
  48         printf "no file named \"%s\"\n" "${arg}" > /dev/stderr
  49         failed=1
  50     fi
  51 done
  52 
  53 if [ "${failed}" -gt 0 ]; then
  54     exit 2
  55 fi
  56 
  57 awk '
  58     BEGIN {
  59         numeric = ints = pos = zero = neg = 0
  60 
  61         inf = "+inf" + 0
  62 
  63         min = inf
  64         max = -inf
  65         sum = 0
  66         mean = 0
  67         prod = 1
  68     }
  69 
  70     # update stats using all detected numbers from every line
  71     {
  72         for (i = 1; i <= NF; i++) {
  73             s = $i
  74             if (s == "" || s ~ / +/ || s ~ /[^0-9\.-]/) {
  75                 continue
  76             }
  77             v = s + 0
  78 
  79             numeric++
  80             ints += v % 1 == 0
  81             if (v > 0) pos++
  82             else if (v < 0) neg++
  83             else if (v == 0) zero++
  84 
  85             min = min < v ? min : v
  86             max = max > v ? max : v
  87             sum += v
  88             prod *= v
  89             lnSum += v <= 0 ? -inf : log(v)
  90 
  91             # advance welford`s algorithm
  92             d1 = v - mean
  93             mean += d1 / numeric
  94             d2 = v - mean
  95             meanSq += d1 * d2
  96         }
  97     }
  98 
  99     END {
 100         sum = mean * numeric
 101         if (numeric == 0) lnSum = -inf
 102 
 103         # separate name-value pairs using tabs, and prepare a
 104         # pipeable command which ignores all-zero decimals
 105         OFS = "\t"
 106 
 107         print "numeric", numeric
 108         if (numeric > 0) {
 109             print "min", sprintf("%f", min)
 110             print "max", sprintf("%f", max)
 111             print "sum", sprintf("%f", sum)
 112             print "mean", sprintf("%f", mean)
 113             print "geomean", (zero == 0 && neg == 0) ?
 114                 sprintf("%f", exp(lnSum / numeric)) :
 115                 ""
 116             print "sd", sprintf("%f", sqrt(meanSq / numeric))
 117             print "product", sprintf("%g", prod)
 118         } else {
 119             print "min", ""
 120             print "max", ""
 121             print "sum", ""
 122             print "mean", ""
 123             print "geomean", ""
 124             print "sd", ""
 125             print "product", ""
 126         }
 127         print "integer", ints
 128         print "positive", pos
 129         print "zero", zero
 130         print "negative", neg
 131     }
 132 ' "$@" | sed -E 's-([0-9]+)\.0+$-\1-g; s-([0-9]+\.[0-9]*[1-9])0+$-\1-g'