File: dcol.sh 1 #!/bin/sh 2 3 # The MIT License (MIT) 4 # 5 # Copyright (c) 2026 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 # dcol [options...] [column names...] 27 # 28 # 29 # Drop COLumns lets you ignore a subset of a table's columns, matching the 30 # column names given using the first line from the standard input. Input lines 31 # can be either space-separated or tab-separated; output lines are always TSV 32 # (Tab-Separated Values) ones, where trailing tabs are added if any values are 33 # missing. 34 # 35 # When a column name isn't matched exactly, a case-insensitive match is tried: 36 # if the latter also fails, number-matching is finally tried, before giving up 37 # on that column name. Column numbers start at 1, and can be negative to count 38 # backward from the last column. 39 # 40 # Running this with no arguments is also useful, since no columns are dropped, 41 # and you get TSV output with always the same number of fields per line. 42 # 43 # The options are, available both in single and double-dash versions 44 # 45 # -h, -help show this help message 46 47 48 case "$1" in 49 -h|--h|-help|--help) 50 awk '/^# +dcol /, /^$/ { gsub(/^# ?/, ""); print }' "$0" 51 exit 0 52 ;; 53 54 --) shift ;; 55 esac 56 57 flush=0 58 if [ -p /dev/stdout ] || [ -t 1 ]; then 59 flush=1 60 fi 61 62 awk -v flush="${flush}" ' 63 function findcol(name, lowname, i) { 64 for (i = 1; i <= NF; i++) if (name == $i) return i 65 for (i = 1; i <= NF; i++) if (lowname == tolower($i)) return i 66 67 if (1 <= name && name <= NF) return name + 0 68 if (name < 0 && -name <= NF) return NF + name + 1 69 70 return 0 71 } 72 73 BEGIN { 74 for (i = 1; i < ARGC; i++) { 75 colnames[++n] = ARGV[i] 76 lownames[n] = tolower(ARGV[i]) 77 delete ARGV[i] 78 } 79 } 80 81 { gsub(/\r$/, "") } 82 83 FNR == 1 { FS = /\t/ ? "\t" : " "; $0 = $0 } 84 85 NR == 1 { 86 ncols = NF 87 for (i = 1; i <= ncols; i++) keep[i] = 1 88 89 used = ncols 90 for (i = 1; i <= n; i++) { 91 j = findcol(colnames[i], lownames[i]) 92 if (j > 0) { 93 keep[j] = 0 94 used-- 95 } 96 97 if (j == 0) { 98 fmt = "no column match for \"%s\"\n" 99 printf(fmt, colnames[i]) > "/dev/stderr" 100 errors++ 101 } 102 } 103 104 if (errors > 0) exit 1 105 if (used == 0) exit 106 } 107 108 { 109 c = 0 110 for (i = 1; i <= ncols; i++) { 111 if (keep[i] == 1) { 112 if (c > 0) printf "\t" 113 printf "%s", $i 114 c++ 115 } 116 } 117 118 print "" 119 if (flush) fflush() 120 } 121 ' "$@"