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 "$1" in
  34     -h|--h|-help|--help)
  35         # show help message, extracting the info-comment at the start
  36         # of this file, and quit
  37         awk '/^# +sn/, /^$/ { gsub(/^# ?/, ""); print }' "$0"
  38         exit 0
  39     ;;
  40 esac
  41 
  42 awk '
  43 # initialize stats
  44 BEGIN {
  45     inf = "+inf" + 0
  46 
  47     min = inf
  48     max = -inf
  49     count = 0
  50     sum = 0
  51     mean = 0
  52     prod = 1
  53 
  54     ints = 0
  55     pos = 0
  56     zero = 0
  57     neg = 0
  58 }
  59 
  60 # update stats using all detected numbers from every line
  61 {
  62     for (i = 1; i <= NF; i++) {
  63         s = $i
  64         if (s == "" || s ~ / +/ || s ~ /[^0-9.-]/) {
  65             continue
  66         }
  67 
  68         v = s + 0
  69         if (s !~ /\./ || s ~ /\.0*$/) { ints++ }
  70 
  71         count++
  72         min = min < v ? min : v
  73         max = max > v ? max : v
  74         sum += v
  75         prod *= v
  76         lnSum += v <= 0 ? nan : log(v)
  77 
  78         if (v > 0) { pos++ }
  79         else if (v < 0) { neg++ }
  80         else if (v == 0) { zero++ }
  81 
  82         # advance welford`s algorithm
  83         d1 = v - mean
  84         mean += d1 / count
  85         d2 = v - mean
  86         meanSq += d1 * d2
  87     }
  88 }
  89 
  90 # report final numeric stats
  91 END {
  92     #sum = mean * count
  93 
  94     # separate name-value pairs using tabs, and prepare a
  95     # pipeable command which ignores all-zero decimals
  96     OFS = "\t"
  97 
  98     # pipe all output lines into the special command, even
  99     # when it is seemingly unneeded due to integer values,
 100     # since not doing so can scramble the final order of
 101     # the output lines
 102     print "numeric", count
 103     print "min", sprintf("%f", min)
 104     print "max", sprintf("%f", max)
 105     print "sum", sprintf("%f", sum)
 106     print "mean", sprintf("%f", mean)
 107     if (lnSum != -inf && count > 0) {
 108         geomean = exp(lnSum / count)
 109         print "geomean", sprintf("%f", geomean)
 110     } else {
 111         print "geomean", ""
 112     }
 113     if (count > 0) {
 114         sd = sqrt(meanSq / count)
 115         print "sd", sprintf("%f", sd)
 116         #print "product", prod
 117         print "product", sprintf("%g", prod)
 118     } else {
 119         print "sd", ""
 120         print "product", ""
 121     }
 122     print "integer", ints
 123     print "positive", pos
 124     print "zero", zero
 125     print "negative", neg
 126 }
 127 ' "$@" | sed 's-\\.00*$--'