source: other-projects/nightly-tasks/diffcol/trunk/diffcol/gdbdiff.pm@ 27604

package gdbdiff;

BEGIN {
    die "GSDLHOME not set\n" unless defined $ENV{'GSDLHOME'};
    die "GSDLOS not set\n" unless defined $ENV{'GSDLOS'};
    unshift (@INC, "$ENV{'GSDLHOME'}/perllib");
    unshift (@INC, "$ENV{'GSDLHOME'}/perllib/cpan");
}

use util;
use diffutil;
use Text::Diff;

sub readin_gdb
{
    my ($cmd) = @_;

    open(PIN,"$cmd|") 
    || die "Unable to open pipe to $cmd: $!\n";

    my $text_content = "";

    while (defined (my $line = <PIN>)) {
    $text_content .= $line;
    }

    close(PIN);
    return $text_content;
}


sub test_gdb
{
    my ($full_modeldb, $full_testdb,$strColName) = @_;


   # print "Now is testing database\n";
    
    # need to sort text output of both test and model col database files, to normalise them for the comparison
    # the -sort option to db2txt was added specifically to support diffcol
    my $model_cmd = "db2txt -sort $full_modeldb 2>&1";
    my $test_cmd  = "db2txt -sort $full_testdb 2>&1";

    my $model_text = readin_gdb($model_cmd);
    my $test_text = readin_gdb($test_cmd);


    # filter out the fields that can be ignored in the two database files
    my $ignore_line_re = "\n<(lastmodified|lastmodifieddate|oailastmodified|oailastmodifieddate)>([^\n])*";
    $model_text =~ s/$ignore_line_re//g;
    $test_text =~ s/$ignore_line_re//g;


    # ignore absolute path prefixes in modelcol and testcol (necessary for archiveinf-doc and -src.gdb files)

    # Remember the original model col on SVN could have been built anywhere, 
    # and in the gdb files, absolute paths are stored to the collection location. 
    # Crop these paths to the collect/<colname> point.
    
    # Entries are of the form [Entry] or <Entry>. In order to do a sensible diff,
    # need to remove the prefix to the collect/colname folder in any (absolute) path that occurs in Entry
    # E.g. [/full/path/collect/colname/import/file.ext] should become [collect/colname/import/file.ext]
    # Better regex is of the form /BEGIN((?:(?!BEGIN).)*)END/, see http://docstore.mik.ua/orelly/perl/cookbook/ch06_16.htm

    $model_text =~ s@^([^\\//]*).*(\\|/)(collect(\\|/)$strColName)(.*)$@$1$3$5@mg;
    $test_text =~ s@^([^\\//]*).*(\\|/)(collect(\\|/)$strColName)(.*)$@$1$3$5@mg;


    my $report_type = "OldStyle"; # Can not change this type.
    my $diff_gdb = diff \$model_text, \$test_text, { STYLE => $report_type };
    
    # leaving the ignore regex as it used to be in the following, in case it helps with single line comparisons
    $diff_gdb = &diffutil::GenerateOutput($diff_gdb,"^<(lastmodified|lastmodifieddate|oailastmodified|oailastmodifieddate)>.*");

    if($diff_gdb eq "")
    {
    return "";
    }
    else
    {
    return "Difference Report: Differences found in the Database file: \n$diff_gdb";
    }
    # Call diff?
}

1;