Related
I am trying to read text file content into hash but having some problem reading as well as accessing it.
resctrl_top
/path/to/a/
vdm05top
/path/to/b/
/path/to/c/
/path/to/d/
/path/to/e/
/path/to/f/
The file format will be as above. My desired output is a hash with the non spacing line as key, and the path lines as values. I would like to know also how to access each values for different keys.
resctrl_top => /path/to/a/
vdm05top => /path/to/b/,/path/to/c/,...
Below are the effort I tried:
use strict;
use warnings;
my %hash;
open FILE, "filename.txt" or die $!;
my $key;
while (my $line = <FILE>) {
chomp($line);
if ($line !~ /^\s/) {
($key) = $line =~ /^\S+/g;
$hash{$key} = [];
} else {
$line =~ s/^\s+//;
push #{ $hash{$key} }, $line;
}
}
close FILE;
foreach (keys %hash){
print "$key => $hash{$key}\n";
}
Try this way:
use strict;
use warnings;
use Data::Dumper;
my %hash;
my $key;
while (my $line = <DATA>) {
chomp($line);
if ($line !~ /^\s/) {
$key = $line;
} else {
$line =~ s/\s//g;
push (#{$hash{$key}} , $line);
}
}
my %final;
foreach my $k (keys %hash){
my $val = join(",", #{$hash{$k}});
$final{$k} = $val; #New hash will have key and respective values
}
print Dumper(\%final);
__DATA__
resctrl_top
/path/to/a/
vdm05top
/path/to/b/
/path/to/c/
/path/to/d/
/path/to/e/
/path/to/f/
Result:
$VAR1 = {
'vdm05top' => '/path/to/b/,/path/to/c/,/path/to/d/,/path/to/e/,/path/to/f/',
'resctrl_top' => '/path/to/a/'
};
Hope this solves your problem.
Here's a pretty simple solution.
#!/usr/bin/perl
use strict;
use warnings;
use feature 'say';
use Data::Dumper; # Just for output
my ($key, %hash); # Declare globals
while (<DATA>) { # Quick hack - read from DATA
chomp;
if (/^\s/) { # If the line starts with a space
s/^\s+//;
push #{$hash{$key}}, $_;
} else { # The line is a key
$key = $_;
}
}
say Dumper \%hash;
__DATA__
resctrl_top
/path/to/a/
vdm05top
/path/to/b/
/path/to/c/
/path/to/d/
/path/to/e/
/path/to/f/
I have written a script which processes data from $data variable and get the count of values of each key.
The script works fine but I am producing 2 hashes called %data_hash, %count_hash. One for storing the data and another to get the count of those key values.
#!/usr/bin/perl
use strict;
use warnings;
use Data::Dumper;
my $data = "KEY1,VAL1
KEY2,VAL1
KEY1,VAL2
KEY1,VAL3
KEY1,VAL4
KEY2,VAL2
KEY2,VAL3
KEY2,VAL4
KEY1,VAL5
";
my (%data_hash, %count_hash);
foreach my $each_data (split /\n/, $data){
my ($key, $val) = (split /,/, $each_data);
push( #{$data_hash{$key}}, $val );
}
print Dumper(\%data_hash);
foreach my $key (sort keys %data_hash) {
$count_hash{$key} = scalar #{$data_hash{$key}};
}
print Dumper(\%count_hash);
Can I have a single hash instead of 2 and get the count by retaining the data?
Sure you can:
#!/usr/bin/perl
use strict;
use warnings;
use Data::Dumper;
my $data = "KEY1,VAL1
KEY2,VAL1
KEY1,VAL2
KEY1,VAL3
KEY1,VAL4
KEY2,VAL2
KEY2,VAL3
KEY2,VAL4
KEY1,VAL5
";
my (%data_hash, %count_hash);
foreach my $each_data (split /\n/, $data){
my ($key, $val) = (split /,/, $each_data);
push( #{$data_hash{$key}{vals}}, $val );
$data_hash{$key}{num_vals}++;
}
print Dumper(\%data_hash);
If id gets repeated I am appending app1, app2 and printing it once.
Input:
id|Name|app1|app2
1|abc|234|231|
2|xyz|123|215|
1|abc|265|321|
3|asd|213|235|
Output:
id|Name|app1|app2
1|abc|234,265|231,321|
2|xyz|123|215|
3|asd|213|235|
Output I'm getting:
id|Name|app1|app2
1|abc|234,231|
2|xyz|123,215|
1|abc|265,321|
3|asd|213,235|
My Code:
#! usr/bin/perl
use strict;
use warnings;
my $basedir = 'E:\Perl\Input\\';
my $file ='doctor.txt';
my $counter = 0;
my %RepeatNumber;
my $pos=0;
open(OUTFILE, '>', 'E:\Perl\Output\DoctorOpFile.csv') || die $!;
open(FH, '<', join('', $basedir, $file)) || die $!;
my $line = readline(FH);
unless ($counter) {
chomp $line;
print OUTFILE $line;
print OUTFILE "\n";
}
while ($line = readline(FH)) {
chomp $line;
my #obj = split('\|',$line);
if($RepeatNumber{$obj[0]}++) {
my $str1= join("|",$obj[0]);
my $str2=join(",",$obj[2],$obj[3]);
print OUTFILE join("|",$str1,$str2);
print OUTFILE "\n";
}
}
This should do the trick:
use strict;
use warnings;
my $file_in = "doctor.txt";
open (FF, "<$file_in");
my $temp = <FF>; # remove first line
my %out;
while (<FF>)
{
my ($id, $Name, $app1, $app2) = split /\|/, $_;
$out{$id}[0] = $Name;
push #{$out{$id}[1]}, $app1;
push #{$out{$id}[2]}, $app2;
}
foreach my $key (keys %out)
{
print $key, "|", $out{$key}[0], "|", join (",", #{$out{$key}[1]}), "|", join (",", #{$out{$key}[2]}), "\n";
}
EDIT
To see what the %out contains (in case it's not clear), you can use
use Data::Dumper;
and print it via
print Dumper(%out);
I'd tackle it like this:
#!/usr/bin/env perl
use strict;
use warnings;
use Data::Dumper;
use 5.14.0;
my %stuff;
#extract the header row.
#use the regex to remove the linefeed, because
#we can't chomp it inline like this.
#works since perl 5.14
#otherwise we could just chomp (#header) later.
my ( $id, #header ) = split( /\|/, <DATA> =~ s/\n//r );
while (<DATA>) {
#turn this row into a hash of key-values.
my %row;
( $id, #row{#header} ) = split(/\|/);
#print for diag
print Dumper \%row;
#iterate each key, and insert into $row.
foreach my $key ( keys %row ) {
push( #{ $stuff{$id}{$key} }, $row{$key} );
}
}
#print for diag
print Dumper \%stuff;
print join ("|", "id", #header ),"\n";
#iterate ids in the hash
foreach my $id ( sort keys %stuff ) {
#join this record by '|'.
print join('|',
$id,
#turn inner arrays into comma separated via map.
map {
my %seen;
#use grep to remove dupes - e.g. "abc,abc" -> "abc"
join( ",", grep !$seen{$_}++, #$_ )
} #{ $stuff{$id} }{#header}
),
"\n";
}
__DATA__
id|Name|app1|app2
1|abc|234|231|
2|xyz|123|215|
1|abc|265|321|
3|asd|213|235|
This is perhaps a bit overkill for your application, but it should handle arbitrary column headings and arbitary numbers of duplicates. I'll coalesce them though - so the two abc entries don't end up abc,abc.
Output is:
id|Name|app1|app2
1|abc|234,265|231,321
2|xyz|123|215
3|asd|213|235
Another way of doing it which doesn't use a hash (in case you want to be more memory efficient), my contribution lies under the opens:
#!/usr/bin/perl
use strict;
use warnings;
my $basedir = 'E:\Perl\Input\\';
my $file ='doctor.txt';
open(OUTFILE, '>', 'E:\Perl\Output\DoctorOpFile.csv') || die $!;
select(OUTFILE);
open(FH, '<', join('', $basedir, $file)) || die $!;
print(scalar(<FH>));
my #lastobj = (undef);
foreach my $obj (sort {$a->[0] <=> $b->[0]}
map {chomp;[split('|')]} <FH>) {
if(defined($lastobj[0]) &&
$obj[0] eq $lastobj[0])
{#lastobj = (#obj[0..1],
$lastobj[2].','.$obj[2],
$lastobj[3].','.$obj[3])}
else
{
if($lastobj[0] ne '')
{print(join('|',#lastobj),"|\n")}
#lastobj = #obj[0..3];
}
}
print(join('|',#lastobj),"|\n");
Note that split, without it's third argument ignores empty elements, which is why you have to add the last bar. If you don't do a chomp, you won't need to supply the bar or the trailing hard return, but you would have to record $obj[4].
If I open a file with strings like "233445", how can I then split that string into digits "2 3 3 4 4 5" and add each one to each other "2 + 3 + 3 etc..." and print out the result.
My code so far looks like this:
use strict;
#open (FILE, '<', shift);
#my #strings = <FILE>;
#strings = qw(12243434, 345, 676744); ## or a contents of a file
foreach my $numbers (#strings) {
my #done = split(undef, $numbers);
print "#done\n";
}
But I don't know where to start for the actual add function.
use strict;
use warnings;
my #strings = qw( 12243434 345 676744 );
for my $string (#strings) {
my $sum;
$sum += $_ for split(//, $string);
print "$sum\n";
}
or
use strict;
use warnings;
use List::Util qw( sum );
my #strings = qw( 12243434 345 676744 );
for my $string (#strings) {
my $sum = sum split(//, $string);
print "$sum\n";
}
PS — Always use use strict; use warnings;. It would have detected your misuse of commas in qw, and it would have dected your misuse of undef for split's first argument.
use strict;
my #done;
#open (FILE, '<', shift);
#my #strings = <FILE>;
my #strings = qw(12243434, 345, 676744); ## or a contents of a file
foreach my $numbers (#strings) {
#done = split(undef, $numbers);
print "#done\n";
}
my $tot;
map { $tot += $_} #done;
print $tot, "\n";
No one suggested an eval solution?
my #strings = qw( 12243434 345 676744 );
foreach my $string (#strings) {
my $sum = eval join '+',split //, $string;
print "$sum\n";
}
If your numbers are in a file, a one-liner might be nice:
perl -lnwe 'my $sum; s/(\d)/$sum += $1/eg; print $sum' numbers.txt
Since addition only uses numbers, it is safe to ignore all other characters. So just extract them one at the time with the regex and sum them up.
TIMTOWTDI:
perl -MList::Util=sum -lnwe 'print sum(/\d/g);' numbers.txt
perl -lnwe 'my $a; $a+=$_ for /\d/g; print $a' numbers.txt
Options:
-l auto-chomp input and add newline to print
-n implicit while(<>) loop around program -- open the file name given as argument and read each line into $_.
I have a string like this
field1=1 field2=2 field3=abc
I want to ouput this as
2,1,abc
Any ideas as to how I can go about this? I can write a small C or Java program to do this, trying I'm trying to find out a simple way to do it in Perl.
use strict;
use warnings;
my $string = 'field1=1 field2=2 field3=abc';
my #values = ($string =~ m/=(\S+)/g);
print join(',', #values), "\n";
#!/usr/bin/perl
use strict;
use warnings;
# Input string
my $string = "field1=1 field2=2 field3=abc";
# Split string into a list of "key=value" strings
my #pairs = split(/\s+/,$string);
# Convert pair strings into hash
my %hash = map { split(/=/, $_, 2) } #pairs;
# Output hash
printf "%s,%s,%s\n", $hash{field2}, $hash{field1}, $hash{field3}; # => 2,1,abc
# Output hash, alternate method
print join(",", #hash{qw(field2 field1 field3)}), "\n";
Use m//g in list context:
#!/usr/bin/perl
use strict;
use warnings;
my $x = "field1=1 field2=2 field3=abc";
if ( my #matches = $x =~ /(?:field[1-3]=(\S+))/g ) {
print join(',', #matches), "\n";
}
__END__
Output:
C:\Temp> klm
1,2,abc
$_='field1=1 field2=2 field3=abc';
$,=',';
say /=(\S+)/g
Let's play Perl golf :D
my $str = 'field1=1 field2=2 field3=abc';
print(join(',', map { (split('=', $_))[1] } split(' ', $str)));
There's several ways you can do that:
Regex match
my $s = "field1=1 field2=2 field3=abc";
$s =~ /field1=(\w*) field2=(\w*) field3=(\w*)$/; //pick out each field
print $1,$2,$3;'
12abc
Split the string on match
my $s = "field1=1 field2=2 field3=abc";
my #arr = split / /, $s; print #arr,"\n"; //make an array of name=value pairs
my #vals = map { #pairs = split /=/, $_; $pairs[1] } #arr; //get the values only from each pair
print #vals'
field1=1field2=2field3=abc
12abc
Split and put in a hash (I think that's the most useful one)
my $s = "field1=1 field2=2 field3=abc";
my #arr = split / /, $s;
my %pairs = map { split=/, $_; } #arr;
print $pairs{field1}, $pairs{field2}, $pairs{field3}
12abc
Assuming your ordering was a typo:
#!/usr/bin/perl
use strict; use warnings;
my $str='a=1 b=2 c=abc';
my #v;
while ($str =~ /=(\S+)/g) {
push #v, $1;
}
print join (',', #v);
Perl is definitely the right tool for this.
#! /usr/bin/perl
$str = "field1=1 field2=2 field3=abc";
$str =~ /field1=(\S+)\ field2=(\S+)\ field3=(\S+)/;
print "$1,$2,$3", "\n";
my $a = "field1=1 field2=2 field3=abc";
my #f = split /\s*\w+=/, $a;
shift(#f);
print join(",", #f), "\n";
$string="field1=1 field2=2 field3=abc";
#s=split /\s+/,$string;
$temp=$s[1];$s[1]=$s[0];$s[0]=$temp;
foreach (#s){s/.*=//; push(#a,$_ );}
print join(",",#a);
If you actually need both the keys and the values. I would put them into a hash. You could just capture both sides of the "=", and put directly into the hash.
use strict;
use warnings;
my $str = 'field1=1 field2=2 field3=abc';
my %fields = $str =~ / (\S+) \s* = \s* (\S+) /xg;
use YAML;
print Dump \%fields
---
field1: 1
field2: 2
field3: abc
For further information please read perldoc perlre.
If you are just a beginner, you may want to read perldoc perlretut.