问Awk/Perl将文本文件转换为csv格式

EN

BEGIN {
    n=split("Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec",month,"|")
    for (i=1;i<=n;i++) {
        month_index[month[i]] = i
    }
    print "Date,Camera,Head,Duration,Activity"  
}
/^-*$/{
    i=0
    next
}
{
    i++
}
i==1{
    printf "%02d/%02d/%02d,",$3,month_index[$2],substr($6,3)
}
i==2{
    printf "%s,%d,",$1,$3
}
i==3{
    printf "%d,",$3
}
i==4{
    printf "%.1f\n",$3
}

$ awk -f script.awk file
08/07/10,BLUE,1,20,14.9
08/07/10,BLUE,1,20,14.9
08/07/10,RED,1,20,14.9
08/07/10,RED,1,20,14.9
19/07/10,BLUE,1,20,12.4
19/07/10,BLUE,1,20,12.4
19/07/10,RED,1,20,12.4
19/07/10,RED,1,20,12.4

$ cat tst.awk
BEGIN{ RS="---+\n"; OFS=","; months="JanFebMarAprMayJunJulAugSepOctNovDec" }
NR==1{ print "Date","Camera","Head","Duration","Activity"; next }
{ print sprintf("%04d%02d%02d",$6,(match(months,$2)+2)/3,$3),$7,$9,$12,$16 }

$ gawk -f tst.awk file
Date,Camera,Head,Duration,Activity
20100708,BLUE,1,20,14.9
20100708,BLUE,1,20,14.9
20100708,RED,1,20,14.9
20100708,RED,1,20,14.9
20100719,BLUE,1,20,12.4
20100719,BLUE,1,20,12.4
20100719,RED,1,20,12.4
20100719,RED,1,20,12.4

#! /usr/bin/env perl
use strict;
use warnings;
use Date::Parse;
use Date::Format;
use Text::CSV;

sub convert_date{
  my $time = str2time($_[0]);
  # iso 8601 style:
  return time2str('%Y-%m-%d',$time); # YYYY-MM-DD

  # or the outdated style output you wanted
  return time2str('%d/%m/%y',$time); # DD/MM/YY
}

my %multiply_table = (
  s => 1,
  m => 60,
  h => 60 * 60,
  d => 60 * 60 * 24,
);
sub convert_duration{
  my($d,$s) = $_[0] =~ /^ \s* (\d+) \s* (\w) \s* $/x;
  die "Invalid duration '$_[0]'" unless $d && $s;
  return $d * $multiply_table{$s};
}

my @field_list = qw'Date Camera Head Duration Activity';

my $csv = Text::CSV->new( { eol => "\n" } );

# print header
$csv->print( \*STDOUT, \@field_list );

# set record separator
local $/ = ('-' x 38) . "\n";

# parse data
while(<>){
  chomp; # remove record separator
  next unless $_; # skip empty section
  my($time,$camdat,@fields) = split m/\n/; # split up the fields

  my %data;


  # split camera and head fields
  @data{qw(Camera Head)} = split /\s+Head\s+/, $camdat;

  # parse lines like:
  #   Duration = 20 s
  #   Activity = 14.9 MBq
  #   Sensitivity = 305 cps/MBq
  for(@fields){
    my($key,$value) = /(\w+) \s* = \s* (.*) /x;
    $data{$key} = $value;
  }

  # at this point we start reducing precision

  $data{Date} = convert_date( $time );

  # remove measurement units
  $data{Duration} = convert_duration($data{Duration}); # safe
  $data{Activity} =~ s/[^\d]*$//; # unsafe

  $csv->print(\*STDOUT, [@data{@field_list}]);
}