tabdata/td-expand

   1 #!/usr/bin/env perl
   2
   3 =pod
   4
   5 =head1 NAME
   6
   7 td-expand - Generate multiple rows from each one row in a Tabular data stream.
   8
   9 =head1 SYNOPSIS
  10
  11 td-expand [-f I<FIELD>] [-s I<SEPARATOR>]
  12
  13 =head1 DESCRIPTION
  14
  15 It goes row-by-row and splits the given I<FIELD> at I<SEPARATOR> chars,
  16 creates as many rows on the output as many parts I<FIELD> is split into,
  17 fills the I<FIELD> column in each row by one of the parts,
  18 and fills all other columns in all resulted rows with the corresponding column's data in the input.
  19
  20 More illustratively:
  21
  22   | SHELL       | USERS         |
  23   | /bin/bash   | user1 user2   |
  24   | /bin/dash   | user3 user4   |
  25   | /bin/sh     | root          |
  26
  27   td-expand -f USERS -s ' ' | td-alter USER=USERS | td-select +ALL -USERS
  28
  29   | SHELL       | USER          |
  30   | /bin/bash   | user1         |
  31   | /bin/bash   | user2         |
  32   | /bin/dash   | user3         |
  33   | /bin/dash   | user4         |
  34   | /bin/sh     | root          |
  35
  36 =head1 OPTIONS
  37
  38 =over 4
  39
  40 =item -f, --field I<FIELD>
  41
  42 Which field to break up.
  43 Default is always the first one.
  44
  45 =item -s, --separator I<PATTERN>
  46
  47 Regexp pattern to split I<FIELD> at.
  48 Default is space.
  49
  50 =back
  51
  52 =head1 SEE ALSO
  53
  54 td-collapse(1) is a kind of inverse to td-expand(1).
  55
  56 =cut
  57
  58
  59 $OptFieldName = undef;
  60 $OptSeparatorRegexp = " ";
  61 %OptionDefs = (
  62         'f|field=s' => \$OptFieldName,
  63         's|separator=s' => \$OptSeparatorRegexp,
  64 );
  65
  66 no if ($] >= 5.018), 'warnings' => 'experimental::smartmatch';
  67 do '/usr/lib/tool/perl5/tabdata/common.pl' or die "$@";
  68
  69
  70 process_header(scalar <STDIN>);
  71 print join($FS, @Header).$RS;
  72
  73 while(not eof STDIN)
  74 {
  75         my @row = read_record(\*STDIN);
  76
  77         if(not defined $OptFieldName)
  78         {
  79                 $OptFieldName = $Header[0];
  80         }
  81
  82         my @parts = split /$OptSeparatorRegexp/, $row[$Header{$OptFieldName}];
  83
  84         for my $part (@parts)
  85         {
  86                 my @row_copy = @row;
  87                 $row_copy[$Header{$OptFieldName}] = $part;
  88                 print join($FS, @row_copy) . $RS;
  89         }
  90 }