Last active
January 10, 2019 05:00
-
-
Save acg/5312238 to your computer and use it in GitHub Desktop.
Convert tsv to csv with optional unescaping.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env perl | |
use Text::CSV; | |
use Getopt::Long qw/ GetOptionsFromArray :config pass_through /; | |
use warnings; | |
use strict; | |
my $usage = "usage: $0 [-e] < file.tsv\n"; | |
exit main( @ARGV ); | |
sub main | |
{ | |
my $escape = 0; | |
GetOptionsFromArray( \@_, 'escape|e' => \$escape ) or die $usage; | |
my $csv = Text::CSV->new( { binary => 1 } ); | |
my $out = \*STDOUT; | |
while (<STDIN>) | |
{ | |
chomp; | |
do { print $/; next } if /^\s*$/; | |
my @row = split /\t/; | |
@row = map c_unescape($_) => @row if $escape; | |
$csv->combine( @row ) or die "CSV error: ".$csv->error_diag; | |
print $out $csv->string.$/; | |
} | |
return 0; | |
} | |
sub c_unescape | |
{ | |
my $str = shift; | |
my %unescapes = | |
( | |
"\\\\" => "\\", | |
"\\n" => "\n", | |
"\\t" => "\t", | |
); | |
$str =~ s/(\\[\\nt])/ $unescapes{$1} /ge; | |
return $str; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment