[BACK]Return to harvestmeta.pl CVS log [TXT] [DIR] Up to [Repository] / foxridge-archiver

Diff for /foxridge-archiver/harvestmeta.pl between versions 1.3 and 1.4

version 1.3, 2004/07/08 21:23:53 version 1.4, 2004/07/13 18:32:49
Line 17  $|=1; Line 17  $|=1;
 #  #
   
 # program version  # program version
 my $version = "0.2 (08.07.2004)";  my $version = "0.2.1 (13.07.2004)";
   
 # read command line parameters  # read command line parameters
 my $args = MPIWGStor::parseargs;  my $args = MPIWGStor::parseargs;
Line 227  sub readURLIndex { Line 227  sub readURLIndex {
     foreach my $me (@indexdata) {      foreach my $me (@indexdata) {
     $cnt++;      $cnt++;
     my ($tag, $val, $attr) = @$me;      my ($tag, $val, $attr) = @$me;
     my $meta;      my $meta = "";
     my $file;      my $file = "";
     if ($tag =~ /index\/resource$/) {      if ($tag =~ /index\/resource$/) {
         if ($attr =~ /metaLink=\"([^\"]+)\"/) {          if ($attr =~ /metaLink=\"([^\"]+)\"/) {
         $meta = $1;          $meta = $1;
Line 263  sub harvestURL { Line 263  sub harvestURL {
     }      }
     my @data = $metaParserHandler->getData();      my @data = $metaParserHandler->getData();
     logger('DEBUG', "parsed $#data+1 elements");      logger('DEBUG', "parsed $#data+1 elements");
     if ($data[0][0] eq "html") {      if (lc $data[0][0] eq "html") {
     # oops, wrong      # oops, wrong
     logger('WARNING', "invalid HTML content from $metaurl");      logger('WARNING', "invalid HTML content from $metaurl");
     $warncnt++;      $warncnt++;
Line 384  sub initDB { Line 384  sub initDB {
 logger("INFO", "harvestmeta $version");  logger("INFO", "harvestmeta $version");
     
 initDB();  initDB();
 my $fnum;  my $fnum = 0;
   
 if ($basedir) {  if ($basedir) {
     # read and process all files under $basedir      # read and process all files under $basedir
     $fnum = readAllFiles($basedir, "");      $fnum = readAllFiles($basedir, "");
     # delete orphaned data (under $basedir)      # delete orphaned data (under $basedir)
     cleanUnmarkedFiles($basedir);      cleanUnmarkedFiles($basedir);
 } elsif ($baseurl) {  } elsif ($indexurl) {
     # read and process XML index      # read and process XML index
     $fnum = readURLIndex($indexurl);      $fnum = readURLIndex($indexurl);
     if ($baseurl) {      if ($baseurl) {
Removed from v.1.3  
changed lines
  Added in v.1.4

FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>