in reply to Zip file CRC validation

I tried it like this, and on the first zip file I happened to look at, it worked just fine -- the computed crcs all matched the ones stated in the zip file itself: 
#!/usr/bin/perl

use strict;
use IO::File;
use Archive::Zip qw/:ERROR_CODES :CONSTANTS/;

my $Usage = "Usage: $0 file.zip\n";
die $Usage unless ( @ARGV == 1 and -f $ARGV[0] );

my $zip = Archive::Zip->new();
if ( $zip->read( $ARGV[0] ) != AZ_OK ) {
    die "Archive::Zip failed to read $ARGV[0]\n";
}

for my $zfile ( $zip->members ) {
    my $fh = IO::File->new_tmpfile
        or die "Unable to create temp file: $!\n";

    $fh->binmode;
    if ( $zfile->extractToFileHandle( $fh ) != AZ_OK ) {
        warn sprintf( "Extraction failed for %s\n", $zfile->fileName()
+ );
        next;
    }
    seek( $fh, 0, 0 );
    my ( $buffer, $nread );
    my $crc = 0;
    while ( $nread = $fh->read( $buffer, 32768 )) {
        $crc = Archive::Zip::computeCRC32( $buffer, $crc );
    }
    my $status = ( $crc == $zfile->crc32()) ? "good" : "broke";
    printf( "Status: %s\tcomp crc: %08x\tfile crc: %08x\t%s\n",
            $status, $crc, $zfile->crc32(), $zfile->fileName());
}

[download]

UPDATE: I wonder if the problem in the OP code might be here: 

            $member->extractToFileHandle($fh);
            if ($member->extractToFileHandle($fh) != 0){
                print "Error in $archivedir$filename\n";
                next;
            }

[download]
It looks like you are extracting the file twice to the same file handle, and maybe that is causing each file to have its contents doubled (and you would almost never get the same crc in that case). In fact, I just added a second "extractToFileHandle" call in my version, and all the data files failed the crc check.

Replies are listed 'Best First'.
Re^2: Zip file CRC validation
by msalerno (Beadle) on Jul 07, 2009 at 03:58 UTC
    Yikes!! You are correct sir. I can't believe that I overlooked such a simple mistake. Thanks for pointing it out. I was so damn focused on the crc check that didn't check myself. Thanks 
            # Zipfile validation
        ##
        my $zipvalidate = Archive::Zip->new();
        if ( $zipvalidate->read( $archivedir.$filename ) != 0 ) {
            print STDERR "ERROR Opening $archivedir$filename\n";
            next;
        }

        foreach my $member ($zipvalidate->members()){
            my $fh = IO::File->new_tmpfile or print "Unable to make ne
+w temp file: $!";
            binmode($fh);

            if ($member->extractToFileHandle($fh) != 0){
                print "Error in $archivedir$filename\n";
                next;
            }

            seek($fh, 0, 0);

            my $buffer;
            my $bytesRead;
            my $crc = 0;
            while ( $bytesRead = $fh->read( $buffer, 32768 ) ) {
                $crc = Archive::Zip::computeCRC32( $buffer, $crc );
            }
            printf( "\nFrom CALC: %08x", $crc );
            printf( "\tFrom ZIP: %08x", $member->crc32() );
            print "\t";
            print $member->fileName();
            print "\n";
            undef $fh;
            }
        }

    [download]
[reply]
[d/l]

In Section Seekers of Perl Wisdom