Beefy Boxes and Bandwidth Generously Provided by pair Networks
"be consistent"
 
PerlMonks  

Re: Logic trouble parsing a formatted text file into hashes of hashes (of hashes, etc.)

by idnopheq (Chaplain)
on Nov 01, 2004 at 17:21 UTC ( [id://404356]=note: print w/replies, xml ) Need Help??


in reply to Logic trouble parsing a formatted text file into hashes of hashes (of hashes, etc.)

Hi, All!

Here is the working code. It needs a lot of love, sure. But here it is for the interested. When I'm done, this might be a module.

#!/usr/bin/perl -wT #-*-cperl-*- use strict; use Data::Dumper; my ( $laststate, $state, $nextstate ); # some states my $key; # some key my $value; # some value my %NML; # the master hash my @hohref = (); # the hash reference array my $href = \%NML; # the master hash reference open ( SOURCE, "< $ARGV[0]" ) or die "Couldn't open $ARGV[0] for reading: $!\n"; # There are three possible line beginnings (ignoring whitespace): # '(', ':', and ')' # There are three possible line endings (ignoring whitespace): # '(', ')', and neither one while ( <SOURCE> ) { SWITCH: { # the first line in the file always starts with '(' # no other line will match this /^\(/ && do { $state = $laststate = 0; # set the state $nextstate = 1; # elevate the state ( $key, # parse the line $value ) = ParseLine ( $_ ); $href->{"filename"} = $key; # slap it in the master hash re +ference last SWITCH; # move on to the next line }; # lines beginning with ':' always have whitespace before it # these lines either maintain or elevate the state, never lower th +e state /^\s+:/ && do { $laststate = $state; # set our old state $state = $nextstate; # set our new state # here is where we analyse the line endings STATE: { # if the line ends with '(', elevate the state /\($/ && do { $nextstate++; # elevate the state ( $key, $value ) = ParseLine ( $_ ); # parse the line push @hohref, $href; # track our master hash refe +rence if ( exists $$href{$key} ) { # if we all ready have an an +on hash ref $href = $$href{$key}; # then reuse it } elsif ( ! exists $$href{$key} ) { # if we don't have an anon has +h ref $href = $$href{$key} = {}; # so make a new one } last STATE; # move on }; # if the line ends with ')', maintain the state /\)$/ && do { ( $key, $value ) = ParseLine ( $_ ); # parse the line $$href{$key} = array_ref() # get an anon array +ref unless ( ref ( $$href{$key} ) eq 'ARRAY' ); # unless we all re +ady have an array ref push @{ $$href{$key} }, $value; # add a value to the + array ref last STATE; # move on }; # other line endings elevate the state $nextstate++; # elevate the state ( $key, $value ) = ParseLine ( $_ ); # parse the line push @hohref, $href; # track our master hash referenc +e $href = $$href{$key} = {} # make a new anon hash ref tied +to the master unless defined $value; # unless we have a value $href = $$href{$value} = {} # make a new anon hash ref tied +to the master if defined $value; # with the value as the key } last SWITCH; # next line }; # if the line contains only whitespace and ')', lower the state /^\s+\)$/ && do { $laststate = $state; # set our old state $state--; # decriment our state $nextstate--; # decrement our next state $href = pop @hohref; # remove our old master hash reference last SWITCH; # next line }; } # analyse our state if ( $state != $laststate ) { # we changed state print "State Change!\t\t" if $ARGV[1]; } print "$laststate\t$state\t$nextstate\n" if $ARGV[1]; } close SOURCE; # we only care about device files # other file types are small, so I don't mind reading them in and then # discarding them die "$ARGV[0] is not a device file!\n" unless $NML{type}[0] eq "device"; print Dumper \%NML; sub ParseLine { # this could use some severe help # strip the leading colon $_[0] =~ s/://; # strip any quotes $_[0] =~ s/\"//g; # strip the open parenthesis $_[0] =~ s/\(//; # strip the closing parenthesis $_[0] =~ s/\)$//; # strip any whitespace $_[0] =~ s/^\s+//; $_[0] =~ s/\s+$//; # assign both values to variables if ( $_[0] =~ / /) { return ( split / /, $_[0], 2 ); # split on the white space and ret +urn two elements } else { return ( $_[0], undef ); # or return one and undef } } sub array_ref { # return an anonymous array reference my @array; return \@array; }

HTH
--
idnopheq
Apply yourself to new problems without preparation, develop confidence in your ability to to meet situations as they arrise.

  • Comment on Re: Logic trouble parsing a formatted text file into hashes of hashes (of hashes, etc.)
  • Download Code

Log In?
Username:
Password:

What's my password?
Create A New User
Domain Nodelet?
Node Status?
node history
Node Type: note [id://404356]
help
Chatterbox?
and the web crawler heard nothing...

How do I use this?Last hourOther CB clients
Other Users?
Others browsing the Monastery: (3)
As of 2024-04-26 07:25 GMT
Sections?
Information?
Find Nodes?
Leftovers?
    Voting Booth?

    No recent polls found