File: sn.sh
   1 #!/bin/sh
   2 
   3 # The MIT License (MIT)
   4 #
   5 # Copyright © 2024 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 # handle help options
  33 case "$1" in
  34     -h|--h|-help|--help)
  35         awk '/^# +sn/, /^$/ { gsub(/^# ?/, ""); print }' "$0"
  36         exit 0
  37     ;;
  38 esac
  39 
  40 awk '
  41 # initialize stats
  42 BEGIN {
  43     inf = "+inf" + 0
  44 
  45     min = inf
  46     max = -inf
  47     count = 0
  48     sum = 0
  49     mean = 0
  50     prod = 1
  51 
  52     ints = 0
  53     pos = 0
  54     zero = 0
  55     neg = 0
  56 }
  57 
  58 # update stats using all detected numbers from every line
  59 {
  60     for (i = 1; i <= NF; i++) {
  61         s = $i
  62         if (s == "" || s ~ / +/ || s ~ /[^0-9.-]/) {
  63             continue
  64         }
  65 
  66         v = s + 0
  67         if (s !~ /\./ || s ~ /\.0*$/) { ints++ }
  68 
  69         count++
  70         min = min < v ? min : v
  71         max = max > v ? max : v
  72         sum += v
  73         prod *= v
  74         lnSum += v <= 0 ? nan : log(v)
  75 
  76         if (v > 0) { pos++ }
  77         else if (v < 0) { neg++ }
  78         else if (v == 0) { zero++ }
  79 
  80         # advance welford`s algorithm
  81         d1 = v - mean
  82         mean += d1 / count
  83         d2 = v - mean
  84         meanSq += d1 * d2
  85     }
  86 }
  87 
  88 # report final numeric stats
  89 END {
  90     #sum = mean * count
  91 
  92     # separate name-value pairs using tabs, and prepare a
  93     # pipeable command which ignores all-zero decimals
  94     OFS = "\t"
  95 
  96     # pipe all output lines into the special command, even
  97     # when it is seemingly unneeded due to integer values,
  98     # since not doing so can scramble the final order of
  99     # the output lines
 100     print "numeric", count
 101     print "min", sprintf("%f", min)
 102     print "max", sprintf("%f", max)
 103     print "sum", sprintf("%f", sum)
 104     print "mean", sprintf("%f", mean)
 105     if (lnSum != -inf && count > 0) {
 106         geomean = exp(lnSum / count)
 107         print "geomean", sprintf("%f", geomean)
 108     } else {
 109         print "geomean", ""
 110     }
 111     if (count > 0) {
 112         sd = sqrt(meanSq / count)
 113         print "sd", sprintf("%f", sd)
 114         #print "product", prod
 115         print "product", sprintf("%g", prod)
 116     } else {
 117         print "sd", ""
 118         print "product", ""
 119     }
 120     print "integer", ints
 121     print "positive", pos
 122     print "zero", zero
 123     print "negative", neg
 124 }
 125 ' "$@" | sed 's-\\.00*$--'