printing out a multilevel hash perl 5 - perl

I have to make sense of this script , without making major changes and insulting the guy who made it. I can't change the hashes, even though it would be easy to load data into arrays and then split. The guy who wrote this (my boss) loves his multilevel hashes. I have to print out the %extend_hash multilevel hash - and I don't understand how to get to the last level. I need to print this out in to a CSV file that cane be read by salespeople.
It looks like it goes out like 6 levels.
I have to sort keys of a hash, of a hash, of a hash ...etc.
#!/scripts/perl/bin/perl
use strict;
use warnings;
use DBI;
my $dbUser = 'foo_01';
my $dbPass = 'foo_01';
my $dbSid = 'foo.WORLD';
my $dbh = DBI->connect("dbi:Oracle:$dbSid","$dbUser","$dbPass") or die( "Couldn't connect: $!" );
#sub read_extend
my %extend_hash = ();
my $query = "select level_id,e_risk_symbol,e_exch_dest,penny,specialist from etds_extend";
if(!$dbh) {
print "Error connecting to DataBase; $DBI::errstr\n";
}
my $cur_msg = $dbh->prepare($query) or die "\n\nCould not prepare statement: ".$dbh->errstr;
$cur_msg->execute();
while (my #row=$cur_msg->fetchrow_array) {
$extend_hash{$row[0]}{$row[1]}{$row[2]}{'penny'}=$row[3];
$extend_hash{$row[0]}{$row[1]}{$row[2]}{'specialist'}=$row[4];
}
for my $what_row0 (sort keys %extend_hash) {
for my $what_row1 (sort keys %{$extend_hash {$what_row0} }) {
for my $what_row2 (sort keys ..... I am lost.
I don't know how to print out the %extend_hash down to the lowest level
I am trying to make it comma delimited, able to be pumped into an email and read by salespeople.
6,ACI,ARCX,specialist,1
6,ACI,ARCX,penny,0
6,MCHP,ARCX,specialist,1,
6,MCHP,ARCX,penny,0
6,BC,AMXO,specialist,1
6,BC,AMXO,penny,0
6,WM,XISX,specialist,1
6,WM,XISX,penny,0
6,PK,AMXO,specialist,1
6,PK,AMXO,penny,0
6,SPLS,XISX,specialist,1
6,SPLS,XISX,penny,0
If I use Data::Dumper I get this which is great, but the sales/marketing guys will get confused. They will not be able to see ARCX penny0 in realtions to the group '6'. I don't think they are able to mentally walt through the data::dump
$VAR1 = {
'6' => {
'IACI' => {
'ARCX' => {
'specialist' => '1',
'penny' => '0'
}
},
'MCHP' => {
'ARCX' => {
'specialist' => '1',
'penny' => '0'
}
},
'BC' => {
'AMXO' => {
'specialist' => '1',
'penny' => '0'
}
},
'WM' => {
'XISX' => {
'specialist' => '1',
'penny' => '0'
}
},
'PKD' => {
'AMXO' => {
'specialist' => '1',
'penny' => '0'
}
},
'SPLS' => {
'XISX' => {
'specialist' => '1',
'penny' => '0'
}
}
}
};
update - amazing work I_alarmed_alien - this should be a good stackoverflow reference (my comments are disabled)
for my $level_1 (sort keys %extend_hash) {
for my $level_2 (sort keys %{$extend_hash{$level_1} }) {
for my $level_3 (sort keys %{$extend_hash{$level_1}{$level_2}}) {
for my $type (sort keys %{$extend_hash{$level_1}{$level_2}{$level_3}} ) {
print "$level_1, $level_2, $level_3 $type" . " $extend_hash{$level_1}{$level_2}{$level_3}{$type}" ."\n" ;
}
}
}
}
got it - I_alarmed_alien amazing work outputing a hash of a hash of a hash of a hash of a hash of a hash
6, XLNX, AMXO , specialist 1
6, XLP, AMXO , penny 0
6, XLP, AMXO , specialist 1
6, XLP, XISX , penny 0
6, XLP, XISX , specialist 1
6, XLV, AMXO , penny 0
6, XLV, AMXO , specialist 1
6, XLY, AMXO , penny 0
6, XLY, AMXO , specialist 1
6, YUM, AMXO , penny 0
6, YUM, AMXO , specialist 1
6, ZINC, XISX , penny 0
6, ZINC, XISX , specialist 1
6, ZMH, AMXO , penny 0
6, ZMH, AMXO , specialist 1

to traverse the whole structure and create the comma-separated table (quick and dirty, but working solution):
my $VAR1 = <insert the hash here>
sub printval
{
my ($val, $path) = #_;
if (ref($val) eq "HASH")
{
printval ($val->{$_}, ($path?"$path,":"")."$_") foreach (keys %{$val});
}
else
{
print "$path,$val\n";
}
}
printval($VAR1);

You're almost there with your code. Here is how to get to the bottom of the hash:
foreach my $l1 (keys %extend_hash) {
# '6'
foreach my $l2 (keys %{$extend_hash{$l1}}) {
# IACI, MCHP, BC, etc.
foreach my $l3 (keys %{$extend_hash{$l1}{$l2}}) {
# ARCX, AMXO, XISX, etc.
foreach my $k (keys %{$extend_hash{$l1}{$l2}{$l3}}) {
print "$l1, $l2, $l3, $k, " . $extend_hash{$l1}{$l2}{$l3}{$k} . "\n";
}
}
}
}
Note that the hash keys are not accessed in any particular order, so you may want to sort them -- e.g. foreach my $l1 (sort keys %extend_hash).
Hashes of hashes of hashes of hashes are fun! ;)
ETA: Here is a more generic function for recursing into arbitrarily deep hashes-of-hashes-of-hashes-of...
sub print_hash {
# href = reference to the hash we're examining (i.e. \%extend_hash)
# so_far = arrayref containing the hash keys we are accessing
my $href = shift;
my $so_far = shift;
foreach my $k (keys %$href) {
# put $k on to the array of keys
push #$so_far, $k;
# if $href->{$k} is a reference to another hash, call print_hash on that hash
if (ref($href->{$k}) eq 'HASH') {
print_hash($href->{$k}, $so_far);
} else {
# $href->{$k} is a scalar, so print out #$so_far (our list of hash keys)
# and the value in $href->{$k}
print join(", ", #$so_far, $href->{$k}) . "\n";
}
# we've finished looking at $href->{$k}, so remove $k from the array of keys
pop #$so_far;
}
}
print_hash($hash, []);

if you only want to print it, use Data::Dumper http://perldoc.perl.org/Data/Dumper.html
To check whether a certain variable is a hash reference, use:
if (ref($r) eq "HASH") {
print "r is a reference to a hash.\n";
}

use Data::Dumper;
print Dumper %extend_hash;

Related

Find key for greatest value in hash of hashes in Perl

I have a hash of hashes containing keys, values, and counts of the form ((k1, v1), c1). I am trying to write a subroutine that returns the value of the key passed as a parameter with the greatest count. For example, if I had:
%hash = (
"a" => {
"b" => 2,
"c" => 1,
},
"d" => {
"e" => 4,
},
);
and made the call:
print &function("a");
it should print "b" because key "a" has the highest count of 2 with "b" as its value. Here is the code I have so far:
sub function() {
$key = $_[0];
if(exists($hash{$key})) {
while (my ($value, $count) = each %{$hash{$key}}) {
#logic goes here
}
} else {
return "$key does not exist";
}
}
The sub doesn't need to know anything about the outer hash, so it makes far more sense to call the sub as follows:
print key_with_highest_val($hash{a});
The sub simply needs to iterate over all the elements of that hash, keeping track of the highest value seen, and the key at which it was seen.
sub key_with_highest_val {
my ($h) = #_;
my $hi_v;
my $hi_k;
for my $k (keys(%$h)) {
my $v = $h->{$k};
if (!defined($hi_v) || $v > $hi_v) {
$hi_v = $v;
$hi_k = $k;
}
}
return $hi_k;
}
As Chris Charley points out, List::Util's reduce can simply this function. With the calling convention I recommended above, the reduce solution becomes the following:
use List::Util qw( reduce );
sub key_with_highest_val {
my ($h) = #_;
return reduce { $h->{$a} >= $h->{$b} ? $a : $b } keys(%$h);
}
Both versions return an arbitrary key among those that tied when there's a tie.
Use the reduce function from List::Util (which is part of core perl).
#!/usr/bin/perl
use strict;
use warnings;
use List::Util qw/reduce/;
my %hash = (
"a" => {
"b" => 2,
"c" => 1,
},
"d" => {
"e" => 4,
},
);
my $key = 'a';
print "For key: $key, max key is ", max_key($key, %hash), "\n";
sub max_key {
my ($key, %hash) = #_;
return "$key does not exist" unless exists $hash{$key};
my $href = $hash{$key};
return reduce { $href->{$a} > $href->{$b} ? $a : $b } keys %$href;
}
You should always include use strict and use warnings at the top of your programs to catch errors so you can find and fix them. This requires declaring of your variables with my, like my $key = 'a';, for example and my %hash = ...
This program prints:
For key: a, max key is b
This code makes the following assumptions:
The values of your nested hashes are always numeric.
You don't have duplicate values.
Anything else is left as an exercise for the reader.
use strict;
use warnings;
use Data::Dump;
use List::Util qw(max);
my %hash = (
a => {
b => 2,
c => 1,
},
d => {
e => 4,
},
);
dd(max_hash_value(\%hash, $_)) for 'a' .. 'd';
sub max_hash_value {
my ($hash_ref, $search_key) = #_;
return unless $hash_ref->{$search_key};
my %lookup;
while (my ($key, $value) = each(%{$hash_ref->{$search_key}})) {
$lookup{$value} = $key;
}
return $lookup{max(keys(%lookup))};
}
Output:
"b"
()
()
"e"

How can I find which keys in a Perl multi-level hash correspond to a given value?

I have a data structure which looks like this:
my %hoh = (
'T431567' => {
machin => '01',
bidule => '02',
truc => '03',
},
'T123456' => {
machin => '97',
bidule => '99',
truc => '69',
},
'T444444' => {
machin => '12',
bidule => '64',
truc => '78',
},
);
I want to search the various values of truc for a particular value and find the top-level attribute which corresponds to that entry. For example, looking for a value of 78, I want to find the result 'T444444', because $hoh{T444444}{truc} is 78.
How can I do this, please?
You can do this with grep:
my #keys = grep { $hoh{$_}{truc} == 78 } keys %hoh;
Note that this can return more than one key, if there are duplicate values in the hash. Also note that this is not particularly efficient, since it has to search the entire hash. In most cases it's probably fine, but if the hash can be very large and you may need to run lots of such queries against it, it may be more efficient to build a reverse index as suggested by Sobrique:
my %trucs;
foreach my $part (keys %hoh) {
my $val = $hoh{$part}{truc};
push #{ $trucs{$val} }, $part;
}
my #keys = #{ $trucs{78} };
or, more generally:
my %index;
foreach my $part (keys %hoh) {
my %data = %{ $hoh{$part} };
foreach my $key (keys %data) {
my $val = $data{$key};
push #{ $index{$key}{$val} }, $part;
}
}
my #keys = #{ $index{truc}{78} };
Can't with that data structure as is - There is no 'backwards' relationship from value to key without you creating it.
You've two options - run a search, or create an 'index'. Practically speaking, these are the same, just one saves the results.
my %index;
foreach my $key ( keys %hoh ) {
my $truc = $hoh{$key}{'truc'};
$index{$truc} = $key;
}
Note - won't do anything clever if the 'truc' numbers are duplicated - it'll overwrite. (Handling this is left as an exercise to the reader).
This solution is similar to those already posted, but it uses the each operator to process the original hash in fewer lines of code, and probably more quickly.
I have added the dump output only so that you can see the form of the structure that is built.
use strict;
use warnings;
my %hoh = (
T123456 => { bidule => '99', machin => '97', truc => '69' },
T431567 => { bidule => '02', machin => '01', truc => '03' },
T444444 => { bidule => '64', machin => '12', truc => '78' },
);
my %trucs;
while ( my ($key, $val) = each %hoh ) {
next unless defined( my $truc = $val->{truc} );
push #{ $trucs{$truc} }, $key ;
}
use Data::Dump;
dd \%trucs;
print "\n";
print "$_\n" for #{ $trucs{78} };
output
{ "03" => ["T431567"], "69" => ["T123456"], "78" => ["T444444"] }
T444444
If you can guarantee that the answer is unique, i.e. that there is never more than one element of the original hash that has a given value for the truc entry, or you are interested only in the last one found, then you can write this still more neatly
my %trucs;
while ( my ($key, $val) = each %hoh ) {
next unless defined( my $truc = $val->{truc} );
$trucs{$truc} = $key ;
}
print $trucs{78}, "\n";
output
T444444
Simplest of all, if there is always a truc entry in each second-level hash, and its values is guaranteed to be unique, then this will do the job
my %trucs = map { $hoh{$_}{truc} => $_ } keys %hoh;
print $trucs{78}, "\n";
with the output as above.

not able to access hash of hash of array values

I have written the following code in Perl. The code is reading a pdb file and getting some values. Ignore the top part of the code,where everything is working perfect.
Problem is in the sub-routine part, where I try to store arrays in the hash3 with model as key another key position
the array values can be accessed inside the if condition using this :
$hash3{$model}{$coordinates}[1].
but when I go out of all foreach loop and try to access the elements I only get one value.
Please look at the end foreach loop and tell me is it the wrong way to access the hash values.
The pdb file I am using can be downloaded from this link http://www.rcsb.org/pdb/download/downloadFile.do?fileFormat=pdb&compression=NO&structureId=1NZS
#!/usr/bin/perl
open(IN,$ARGV[0]);
my #phosphosites;
my $model=1;
my %hash3;
while(<IN>)
{
#findmod(#line);
#finddist;
#findfreq;
if((/^MODRES/) && (/PHOSPHO/))
{
#line=split;
push(#phosphosites, $line[2]);
#print "$line[4]";
}
foreach $elements (#phosphosites){
if(/^HETATM\s+\d+\s+CA\s+$i/)
{
#line1=split;
#print "$line1[5]";
#print "$line1[6] $line1[7] $line1[8]\n";
push(#phosphositesnum, $line1[5]);
}
}
$pos=$line1[5];
#findspatial(\#line,\#line1);
}
my #ori_data=removeDuplicates(#phosphositesnum);
sub removeDuplicates {
my %seen = ();
my #vals = ();
foreach my $i (#_) {
unless ($seen{$i}) {
push #vals, $i;
$seen{$i} = 1;
}
}
return #vals;
}
$a=(#phosphosites);
print "$a\n";
print "#phosphosites\n";
print "#ori_data\n";
close(IN);
open(IN1,$ARGV[0]);
my (#data)=<IN1>;
spatial(\#ori_data);
sub spatial {
my #spatial_array1=#{$_[0]};
foreach $coordinates(#spatial_array1)
{
$model=1;
{foreach $data1(#data){
if($data1=~ m/^HETATM\s+\d+\s+CA\s+[A-Z]*\s+[A-Z]*\s+$coordinates/)
{
#cordivals=split(/\s+/,$data1);
push #{ $sphash{$model} },[$cordivals[6], $cordivals[7], $cordivals[8]];
$hash3{$model}{$coordinates}= \#cordivals;
#print "$model $coordinates $hash3{$model}{$coordinates}[6] $hash3{$model}{$coordinates}[7] $hash3{$model}{$coordinates}[8]\n";
#print "$model $sphash{$model}[$i][0] $sphash{$model}[$i][1] $sphash{$model}[$i][2]\n";
}
elsif($data1=~ m/^ENDMDL/)
{
$model++;
}
#print "$model $coordinates $hash3{$model}{$coordinates}[6] $hash3{$model}{$coordinates}[7] $hash3{$model}{$coordinates}[8]\n";
}
}
}
#foreach $z1 (sort keys %hash3)
# {
# foreach $z2(#spatial_array1){
# print "$z1 $z2";
# print "$hash3{$z1}{$z2}[6]\n";
# print "$z2\n";
# }
# }
}
After using the Data::Dumper option it is giving me this kind of output
$VAR1 = {
'11' => {
'334' => [
'HETATM',
'115',
'CA',
'SEP',
'A',
'343',
'-0.201',
'-2.884',
'1.022',
'1.00',
'99.99',
'C'
],
'342' => $VAR1->{'11'}{'334'},
'338' => $VAR1->{'11'}{'334'},
'335' => $VAR1->{'11'}{'334'},
'340' => $VAR1->{'11'}{'334'},
'343' => $VAR1->{'11'}{'334'},
'336' => $VAR1->{'11'}{'334'}
},
'7' => {
'334' => $VAR1->{'11'}{'334'},
'342' => $VAR1->{'11'}{'334'},
'338' => $VAR1->{'11'}{'334'},
'335' => $VAR1->{'11'}{'334'},
'340' => $VAR1->{'11'}{'334'},
'343' => $VAR1->{'11'}{'334'},
'336' => $VAR1->{'11'}{'334'}
},
'2' => {
'334' => $VAR1->{'11'}{'334'},
'342' => $VAR1->{'11'}{'334'},
...
Change:
#cordivals=split(/\s+/,$data1);
to:
my #cordivals=split(/\s+/,$data1);
What seems to be happening is that all the hash elements contain references to the same array variable, because you're not making the variable local to that iteration.
In general, you should use my with all variables.

Perl Working On Two Hash References

I would like to compare the values of two hash references.
The data dumper of my first hash is this:
$VAR1 = {
'42-MG-BA' => [
{
'chromosome' => '19',
'position' => '35770059',
'genotype' => 'TC'
},
{
'chromosome' => '2',
'position' => '68019584',
'genotype' => 'G'
},
{
'chromosome' => '16',
'position' => '9561557',
'genotype' => 'G'
},
And the second hash is similar to this but with more hashes in the array. I would like to compare the genotype of my first and second hash if the position and the choromosome matches.
map {print "$_= $cave_snp_list->{$_}->[0]->{chromosome}\n"}sort keys %$cave_snp_list;
map {print "$_= $geno_seq_list->{$_}->[0]->{chromosome}\n"}sort keys %$geno_seq_list;
I could do that for the first array of the hashes.
Could you help me in how to work for all the arrays?
This is my actual code in full
#!/software/bin/perl
use strict;
use warnings;
use Getopt::Long;
use Benchmark;
use Config::Config qw(Sequenom.ini);
useDatabase::Conn;
use Data::Dumper;
GetOptions("sam=s" => \my $sample);
my $geno_seq_list = getseqgenotypes($sample);
my $cave_snp_list = getcavemansnpfile($sample);
#print Dumper($geno_seq_list);
print scalar %$geno_seq_list, "\n";
foreach my $sam (keys %{$geno_seq_list}) {
my $seq_used = $geno_seq_list->{$sam};
my $cave_used = $cave_snp_list->{$sam};
print scalar(#$geno_seq_list->{$_}) if sort keys %$geno_seq_list, "\n";
print scalar(#$cave_used), "\n";
#foreach my $seq2com (# {$seq_used } ){
# foreach my $cave2com( # {$cave_used} ){
# print $seq2com->{chromosome},":" ,$cave2com->{chromosome},"\n";
# }
#}
map { print "$_= $cave_snp_list->{$_}->[0]->{chromosome}\n" } sort keys %$cave_snp_list;
map { print "$_= $geno_seq_list->{$_}->[0]->{chromosome}\n" } sort keys %$geno_seq_list;
}
sub getseqgenotypes {
my $snpconn;
my $gen_list = {};
$snpconn = Database::Conn->new('live');
$snpconn->addConnection(DBI->connect('dbi:Oracle:pssd.world', 'sn', 'ss', { RaiseError => 1, AutoCommit => 0 }),
'pssd');
#my $conn2 =Database::Conn->new('live');
#$conn2->addConnection(DBI->connect('dbi:Oracle:COSI.world','nst_owner','nst_owner', {RaiseError =>1 , AutoCommit=>0}),'nst');
my $id_ind = $snpconn->execute('snp::Sequenom::getIdIndforExomeSample', $sample);
my $genotype = $snpconn->executeArrRef('snp::Sequenom::getGenotypeCallsPosition', $id_ind);
foreach my $geno (#{$genotype}) {
push #{ $gen_list->{ $geno->[1] } }, {
chromosome => $geno->[2],
position => $geno->[3],
genotype => $geno->[4],
};
}
return ($gen_list);
} #end of sub getseqgenotypes
sub getcavemansnpfile {
my $nstconn;
my $caveman_list = {};
$nstconn = Database::Conn->new('live');
$nstconn->addConnection(
DBI->connect('dbi:Oracle:CANP.world', 'nst_owner', 'NST_OWNER', { RaiseError => 1, AutoCommit => 0 }), 'nst');
my $id_sample = $nstconn->execute('nst::Caveman::getSampleid', $sample);
#print "IDSample: $id_sample\n";
my $file_location = $nstconn->execute('nst::Caveman::getCaveManSNPSFile', $id_sample);
open(SNPFILE, "<$file_location") || die "Error: Cannot open the file $file_location:$!\n";
while (<SNPFILE>) {
chomp;
next if /^>/;
my #data = split;
my ($nor_geno, $tumor_geno) = split /\//, $data[5];
# array of hash
push #{ $caveman_list->{$sample} }, {
chromosome => $data[0],
position => $data[1],
genotype => $nor_geno,
};
} #end of while loop
close(SNPFILE);
return ($caveman_list);
}
The problem that I see is that you're constructing a tree for generic storage of data, when what you want is a graph, specific to the task. While you are constructing the record, you could also be constructing the part that groups data together. Below is just one example.
my %genotype_for;
my $record
= { chromosome => $data[0]
, position => $data[1]
, genotype => $nor_geno
};
push #{ $gen_list->{ $geno->[1] } }, $record;
# $genotype_for{ position }{ chromosome }{ name of array } = genotype code
$genotype_for{ $data[1] }{ $data[0] }{ $sample } = $nor_geno;
...
return ( $caveman_list, \%genotype_for );
In the main line, you receive them like so:
my ( $cave_snp_list, $geno_lookup ) = getcavemansnpfile( $sample );
This approach at least allows you to locate similar position and chromosome values. If you're going to do much with this, I might suggest an OO approach.
Update
Assuming that you wouldn't have to store the label, we could change the lookup to
$genotype_for{ $data[1] }{ $data[0] } = $nor_geno;
And then the comparison could be written:
foreach my $pos ( keys %$small_lookup ) {
next unless _HASH( my $sh = $small_lookup->{ $pos } )
and _HASH( my $lh = $large_lookup->{ $pos } )
;
foreach my $chrom ( keys %$sh ) {
next unless my $sc = $sh->{ $chrom }
and my $lc = $lh->{ $chrom }
;
print "$sc:$sc";
}
}
However, if you had limited use for the larger list, you could construct the specific case
and pass that in as a filter when creating the longer list.
Thus, in whichever loop creates the longer list, you could just go
...
next unless $sample{ $position }{ $chromosome };
my $record
= { chromosome => $chromosome
, position => $position
, genotype => $genotype
};
...

Recursively printing data structures in Perl

I am currently learning Perl. I have Perl hash that contains references to hashes and arrays. The hashes and arrays may in turn contain references to other hashes/arrays.
I wrote a subroutine to parse the hash recursively and print them with proper indentation. Though the routine works as expected, my instructor was not convinced about the readability and elegance of the below code.
I would really appreciate to get the views of Perl experts here on possible optimization of the below code.
Here is my complete code snippet..
# Array of Arrays
$ref_to_AoA = [
[ "fred", "barney" ],
[ "george", "jane", "elroy" ],
[ "homer", "marge", "bart" ],
];
#Array of Hashes
$ref_to_AoH = [
{
husband => "barney",
wife => "betty",
son => "bamm bamm",
},
{
husband => "george",
wife => "jane",
son => "elroy",
},
];
# Hash of Hashes
$ref_to_HoH = {
flintstones => {
husband => "fred",
pal => "barney",
},
jetsons => {
husband => "george",
wife => "jane",
"his boy" => "elroy", # Key quotes needed.
},
simpsons => {
husband => "homer",
wife => "marge",
kid => "bart",
},
};
# Hash which contains references to arrays and hashes
$finalHash = {
'arrayofArrays' => $ref_to_AoA,
'arrayofHash' => $ref_to_AoH,
'hashofHash' => $ref_to_HoH,
};
$string = str($finalHash);
print "$string\n";
#------------------------------------------------------------------
sub str {
my $hash = shift;
my ($space, $newline, $delimiter) = #_;
$space = "" unless (defined $space);
$newline = "\n\n\n" unless (defined $newline);
$delimiter = "\n--------------------------------------------" unless (defined $delimiter);
my $str = "";
for (sort keys %{$hash}) {
my $value = $hash->{$_};
$str .= "$newline$space$_ == $value$delimiter";
$str .= recurseErrors($value,$space);
}
$str;
}
#------------------------------------------------------------------
sub recurseErrors {
my $str;
my ($value,$space) = #_;
my $ref = ref $value;
if ($ref eq 'ARRAY') {
my $i = 0;
my $isEmpty = 1;
my #array = #$value;
$space .= "\t";
for my $a (#array) {
if (defined $a) {
$isEmpty = 0;
$str .= "\n$space$_\[$i\] :";
$str .= recurseErrors($a,$space);
}
$i++;
}
$str .= "= { }" if ($isEmpty);
} elsif ($ref eq 'HASH') {
$space .= "\t";
for my $k (sort keys %$value) {
if ( ( ref($value->{$k}) eq 'HASH') || (ref $value->{$k} eq 'ARRAY') ) {
my $val = $value->{$k};
$str .= "\n\n$space$k == ";
$str .= "$val";
}
else {
$str .= "\n$space$k == ";
}
$str .= recurseErrors($value->{$k},$space);
}
# we have reached a scalar (leaf)
} elsif ($ref eq '') {
$str .= "$value";
}
$str
}
#------------------------------------------------------------------
Output:
arrayofArrays == ARRAY(0x9d9baf8)
--------------------------------------------
arrayofArrays[0] :
arrayofArrays[0] :fred
arrayofArrays[1] :barney
arrayofArrays[1] :
arrayofArrays[0] :george
arrayofArrays[1] :jane
arrayofArrays[2] :elroy
arrayofArrays[2] :
arrayofArrays[0] :homer
arrayofArrays[1] :marge
arrayofArrays[2] :bart
arrayofHash == ARRAY(0x9d9bba8)
--------------------------------------------
arrayofHash[0] :
husband == barney
son == bamm bamm
wife == betty
arrayofHash[1] :
husband == george
son == elroy
wife == jane
hashofHash == HASH(0x9da45f8)
--------------------------------------------
flintstones == HASH(0x9d9bb48)
husband == fred
pal == barney
jetsons == HASH(0x9d9bbf8)
his boy == elroy
husband == george
wife == jane
simpsons == HASH(0x9d9bc48)
husband == homer
kid == bart
wife == marge
Always use use strict;
To be a good boy, use use warnings as well.
The names you use for subroutines should make it obvious what the subroutine does. "recurseErrors" kind of violates that principle. Yes, it does recurse. But what errors?
On the first line of each subroutine you should declare and initialize any parameters. recurseErrors first declares $str and then declares its parameters.
Don't mix shift and = #_ like you do in str()
You might consider breaking up what is now called recurseErrors into specialized routines for handling arrays and hashes.
There's no need to quote variables like you do on lines 99 and 109.
Apart from that I think your instructor had a bad day that day.
maybe Data::Dumper is what you want:
use Data::Dumper;
$str = Dumper($foo);
print($str);
If you are new to perl, I'd recommend running your code through perl-critic (there is also a script you can install from CPAN, normally I use it as a test so it gets run from the command line whenever I do "make test"). In addition to its output, you might want to break up your functions a bit more. recurseErrors has three cases that could be split into sub functions (or even put into a hash of ref-type to sub-function ref).
If this were a production job, I'd use Data::Dumper, but it sounds like this is homework, so your teacher might not be too pleased.
Here is one simple example why your code is not easily readable:
$delimiter = "\n--------------------------------------------" unless (defined $delimiter);
You could use the defined or operator:
$delimiter //= "\n" . '-' x 44;
If you are worried about earlier Perls:
defined $delimeter or $delimeter = "\n" . '-' x 44;
Conditionals going off the right margin are enough of a turn-off for me not to read the rest of the code.
My guess is that he doesn't like that you
expect a hash in the str function.
call the same function to print arrays as hashes, despite that there appears to be no common function between them.
allow various ways to call str, but it never figures into the final result.
allow configurable space to be passed in to the root function, but have a tab hardcoded in the recursive function.
omit undefined values that actually hold a place in the arrays
Those are issues that I can see, pretty quickly.
You could have separated out the code blocks that dealt with arrays, and hashes.
sub recurse{
...
recurse_A(#_) if $ref eq 'ARRAY';
recurse_H(#_) if $ref eq 'HASH';
...
}
sub recurse_A{ ... }
sub recurse_H{ ... }
I would recommend starting out your subroutines like this, unless you have a real good reason for doing otherwise.
sub example{
my( $one, $two, $three, $optional_four ) = #_;
( If you do it like this then Komodo, at least, will be able to figure out what the arguments are to your subroutine )
There is rarely any reason to put a variable into a string containing only the variable.
"$var" eq $var;
The only time I can think I would ever do that is when I am using an object that has an overloaded "" function, and I want to get the string, without also getting the object.
package My_Class;
use overload
'""' => 'Stringify',
;
sub new{
my( $class, $name ) = #_;
my $self = bless { name => $name }, $class;
return $self;
}
sub Stringify{
my( $self ) = #_;
return $self->{name};
}
my $object = My_Class->new;
my $string = "$object";
I've struggled with this same problem before, and found my way here. I almost used a solution posted here, but found a more suitable one (for me anyway). Read about Depth First Recursion here.
The sub in the above article works perfectly with a reference containing other Hashes, Arrays, or Scalars. It did not print Hash key names, though, so I slightly modified it:
#!/usr/bin/perl
#
# See:
#
# http://perldesignpatterns.com/?DepthFirstRecursion
#
use strict;
use warnings;
my %hash = (
'a' => {
'one' => 1111,
'two' => 222,
},
'b' => [ 'foo', 'bar' ],
'c' => 'test',
'd' => {
'states' => {
'virginia' => 'richmond',
'texas' => 'austin',
},
'planets' => [ 'venus','earth','mars' ],
'constellations' => ['orion','ursa major' ],
'galaxies' => {
'milky way' => 'barred spiral',
'm87' => 'elliptical',
},
},
);
&expand_references2(\%hash);
sub expand_references2 {
my $indenting = -1;
my $inner; $inner = sub {
my $ref = $_[0];
my $key = $_[1];
$indenting++;
if(ref $ref eq 'ARRAY'){
print ' ' x $indenting,'ARRAY:';
printf("%s\n",($key) ? $key : '');
$inner->($_) for #{$ref};
}elsif(ref $ref eq 'HASH'){
print ' ' x $indenting,'HASH:';
printf("%s\n",($key) ? $key : '');
for my $k(sort keys %{$ref}){
$inner->($ref->{$k},$k);
}
}else{
if($key){
print ' ' x $indenting,$key,' => ',$ref,"\n";
}else{
print ' ' x $indenting,$ref,"\n";
}
}
$indenting--;
};
$inner->($_) for #_;
}
#use strict ;
use warnings ;
# use module
use XML::Simple;
use Data::Dumper;
#debug print "START SCRIPT " ;
my $fileToParse = 'C:/Temp/CDIP/scripts/perl/nps_all_workflows.xml' ;
# create object
my $objXml= new XML::Simple;
# read XML file
my $data = $objXml->XMLin("$fileToParse");
# #debug print "\n FirstLevel is " . $objXml->{'POWERMART'} ;
my $level = 1 ;
#
printHashKeyValues ($data ) ;
sub printHashKeyValues
{
$level ++ ;
my $refHash = shift ;
my $parentKey = shift ;
my $parentValue = shift ;
while( my ($key, $value) = each %$refHash)
{
if ( defined ( $key ) )
{
if ( ref ($refHash->{"$key"}) eq 'HASH' )
{
my $newRefHash = $refHash->{"$key"} ;
#debug print " \n The key is a hash " ;
printHashKeyValues ($newRefHash , $key , $value) ;
}
if ( ref ($refHash->{"$key"}) eq 'ARRAY' )
{
#debug print " \n the key is an ARRAY " ;
printArrayValues ( $refHash->{"$key"} ) ;
}
} #eof if ( defined ( $key ))
if ( defined ( $value) )
{
if ( ref ($refHash->{"$value"}) eq 'HASH' )
{
my $newRefHash = $refHash->{"$value"} ;
#debug print " \n The value is a hash " ;
printHashKeyValues ($newRefHash , $key , $value) ;
}
if ( ref ($refHash->{"$value"}) eq 'ARRAY' )
{
#debug print " \n the value is an ARRAY " ;
printArrayValues ( $refHash->{"$value"} ) ;
}
} #eof if defined ( $value )
#debug print "\n key: $key, value: $value.\n";
} #eof while
} #eof sub
sub printArrayValues
{
my $arrRef = shift ;
my #array = #$arrRef;
my $parrentArrayElement = shift ;
#debug print "printArrayValues CALLED " ;
foreach my $arrayElement ( #array )
{
if (defined ( $arrayElement ) )
{
if ( ref ($arrayElement) eq 'HASH' )
{
#debug print " \n The \$arrayElement is a hash FROM THE ARRAY " ;
printHashKeyValues ($arrayElement ) ;
} #eof if
if ( ref ($arrayElement) eq 'ARRAY' )
{
#debug print " \n The \$arrayElement is a ARRAY FROM THE ARRAY " ;
printArrayValues ($arrayElement ) ;
} #eof if
#debug print "\n \$arrayElement is $arrayElement " ;
} #eof if ( defined ( $arrayElement ) )
} #eof foreach
} #eof sub
# #debug print output
##debug print Dumper($data);
1 ;