#!/usr/local/bin/perl

### extract marc data to standard output from Voyager database as
###   raw Marc records or human-readable data


# this is required for database access
use DBI;


# get input arguments
if ($#ARGV < 0) {usage();}
$searchtype = $ARGV[0];
$idstart = $ARGV[1];
$idend = $ARGV[2];
if ($#ARGV = 4) {$raw = $ARGV[3];}
if ($raw) {$raw = 1;}
else {$raw = 0;}


# show program usage
if (($searchtype ne "auth") and ($searchtype ne "bib") and ($searchtype ne "mfhd"))
  {usage();}


### connect to database
# specifying which type of database, the host name, the SID
#   and the database username and password
#   receive a database handle for this database connection
$dbh = DBI->connect('DBI:Oracle:host=voyager.library.wmich.edu;sid=LIBR',
                    'dbread', 'dbread')
  or die "connecting: $DBI::errstr";


# formulate the query statement to be used
#   parameters taken from program arguments above
$sqlquery = sprintf("select %s_id,
                            record_segment,
                            seqnum
                     from wmichdb.%s_data
                     where %s_id >= %s and %s_id <= %s
                     order by %s_id asc, seqnum desc",
                    $searchtype, $searchtype,
                    $searchtype, $idstart,
                    $searchtype, $idend,
                    $searchtype);


# have DBI prepare the query, identified by statement handle "sth"
$sth = $dbh->prepare($sqlquery) or die "preparing query statement";


# execute the query, getting a return code
$rc = $sth->execute;


### usual assembly of marc data in reverse order (per sort in query)
###   by auth/bib/mfhd id
# shunt complete records to stdout (screen) for raw output, or
#   write to array for processing to get human-readable output
$marcstuff = "";
$marc = "";
$oldrec_id = 0;
# following statement gets one row at a time from the query result set
while (($rec_id, $recseg, $seqnum) = $sth->fetchrow_array)
{
# when transitioning from one marc record to another,
#   print or store previous marc record, and
#   start storing this marc record
  if ($rec_id != $oldrec_id)
  {
    if (!$raw) {$marcstuff = $marcstuff . $marc;}
    else {print $marc;}
    $oldrec_id = $rec_id;
    $marc = $recseg;
  }
# else just prepend the record segment to the current marc record being built
  else {$marc = $recseg . $marc;}
}
# handle the last record at the end
if (!$raw) {$marcstuff = $marcstuff . $marc;}
else {print $marc;}


# release resources associated with this statement handle
$sth->finish;


# release the database connection associated with this database handle
$dbh->disconnect;


# if want human-readable output
if (!$raw)
{
# marc records are delimited by this character
# this creates the array of marc records from the
#   previously built string of marc data
  @marcrec = split /\x1d/, $marcstuff;

# loop through array of marc records
  $idx = 0;
  while ($idx < @marcrec)
  {
# output the leader
    $leader = substr($marcrec[$idx], 0, 24);
    if ($idx != 0) {printf("\n");}
    printf("LDR:%s\n", $leader);
# grab the record length and the data base-address,
#   "move" to the start of the directory
    $reclen = substr($marcrec[$idx], 1, 5);
    $baseaddr = substr($marcrec[$idx], 12, 5) - 1;
    $strptr = 24;
# loop through the directory
    while ($strptr < $baseaddr-1)
    {
# get the tag id, the tag's length, and the tag's offset
      $tagid = substr($marcrec[$idx], $strptr, 3);
      $taglen = substr($marcrec[$idx], $strptr+3, 4);
      $offset = substr($marcrec[$idx], $strptr+7, 5);
# read the tag's data from the computed start of the tag's data,
#   for tag length characters
      $tagdata = substr($marcrec[$idx], $baseaddr+$offset, $taglen);
# do the pretty printing formatting for human readability
      $tagdata =~ s/\x1f[a-z]/ \|$& /g;        # use " |x " for subfield ind,
      $tagdata =~ s/\x1f//g;                   #  remove original subfield ind,
      $tagdata =~ s/\x1e//g;                   #  remove field ind,
      if (substr($tagdata, 2, 2) eq " |")      #  & remove the "1st" space in the line
        {$tagdata = substr($tagdata, 0, 2) . substr($tagdata, 3);}
# output the tag parameters and its data
      printf("%3s:%4s:%5s:%s\n", $tagid, $taglen, $offset, $tagdata);
# move to the next tag in the directory
      $strptr+= 12;
    }
# move to the next record in the array of marc records
    $idx++;
  }
# provide count of marc records handled
  if ($idx > 1) {$plural = "s read";}
  else {$plural = " read";}
  printf ("\n<<%d Marc record%s>>\n\n", $idx, $plural);
}


# show this to illustrate program usage
sub usage()
{
  printf ("\nUsage: perl example1.pl [auth | bib | mfhd] startID endID [raw]\n");
  printf ("       Pick one of the 3 data types.\n");
  printf ("       Specify record ID numbers; specified range is inclusive.\n");
  printf ("       Parameters must be in the above order.\n");
  printf ("       All parameters are required except for the last one.\n");
  printf ("       Program extracts marc data from blobs in Oracle.\n");
  printf ("       Output is human-formatted unless *raw* is specified\n");
  printf ("       and it goes to STDOUT.\n");
  exit(0);
}