--- trunk/lib/WebPAC/Input.pm	2005/12/18 21:06:39	285
+++ trunk/lib/WebPAC/Input.pm	2006/05/16 13:08:31	513
@@ -8,41 +8,53 @@
 use WebPAC::Common;
 use base qw/WebPAC::Common/;
 use Text::Iconv;
+use Data::Dumper;
 
 =head1 NAME
 
-WebPAC::Input - core module for input file format
+WebPAC::Input - read different file formats into WebPAC
 
 =head1 VERSION
 
-Version 0.02
+Version 0.05
 
 =cut
 
-our $VERSION = '0.02';
+our $VERSION = '0.05';
 
 =head1 SYNOPSIS
 
-This module is used as base class for all database specific modules
-(basically, files which have one handle, fixed size while indexing and some
-kind of numeric idefinirier which goes from 1 to filesize).
+This module implements input as database which have fixed and known
+I<size> while indexing and single unique numeric identifier for database
+position ranging from 1 to I<size>.
+
+Simply, something that is indexed by unmber from 1 .. I<size>.
+
+Examples of such databases are CDS/ISIS files, MARC files, lines in
+text file, and so on.
+
+Specific file formats are implemented using low-level interface modules,
+located in C<WebPAC::Input::*> namespace which export C<open_db>,
+C<fetch_rec> and optional C<init> functions.
 
 Perhaps a little code snippet.
 
     use WebPAC::Input;
 
     my $db = WebPAC::Input->new(
-    	format => 'NULL',
-	config => $config,
-	lookup => $lookup_obj,
-	low_mem => 1,
+    	module => 'WebPAC::Input::ISIS',
+		config => $config,
+		lookup => $lookup_obj,
+		low_mem => 1,
     );
 
     $db->open('/path/to/database');
-    print "database size: ",$db->size,"\n";
-    while (my $row = $db->fetch) {
-	...
-    }
+	print "database size: ",$db->size,"\n";
+	while (my $rec = $db->fetch) {
+		# do something with $rec
+	}
+
+
 
 =head1 FUNCTIONS
 
@@ -51,17 +63,27 @@
 Create new input database object.
 
   my $db = new WebPAC::Input(
-  	format => 'NULL'
+	module => 'WebPAC::Input::MARC',
 	code_page => 'ISO-8859-2',
 	low_mem => 1,
+	recode => 'char pairs',
+	no_progress_bar => 1,
   );
 
+C<module> is low-level file format module. See L<WebPAC::Input::Isis> and
+L<WebPAC::Input::MARC>.
+
 Optional parametar C<code_page> specify application code page (which will be
 used internally). This should probably be your terminal encoding, and by
 default, it C<ISO-8859-2>.
 
 Default is not to use C<low_mem> options (see L<MEMORY USAGE> below).
 
+C<recode> is optional string constisting of character or words pairs that
+should be replaced in input stream.
+
+C<no_progress_bar> disables progress bar output on C<STDOUT>
+
 This function will also call low-level C<init> if it exists with same
 parametars.
 
@@ -74,14 +96,29 @@
 
 	my $log = $self->_get_logger;
 
+	$log->logconfess("specify low-level file format module") unless ($self->{module});
+	my $module = $self->{module};
+	$module =~ s#::#/#g;
+	$module .= '.pm';
+	$log->debug("require low-level module $self->{module} from $module");
+
+	require $module;
+	#eval $self->{module} .'->import';
+
 	# check if required subclasses are implemented
-	foreach my $subclass (qw/open_db fetch_rec/) {
-		$log->logdie("missing implementation of $subclass") unless ($self->SUPER::can($subclass));
+	foreach my $subclass (qw/open_db fetch_rec init/) {
+		my $n = $self->{module} . '::' . $subclass;
+		if (! defined &{ $n }) {
+			my $missing = "missing $subclass in $self->{module}";
+			$self->{$subclass} = sub { $log->logwarn($missing) };
+		} else {
+			$self->{$subclass} = \&{ $n };
+		}
 	}
 
-	if ($self->can('init')) {
+	if ($self->{init}) {
 		$log->debug("calling init");
-		$self->init(@_);
+		$self->{init}->($self, @_);
 	}
 
 	$self->{'code_page'} ||= 'ISO-8859-2';
@@ -119,24 +156,25 @@
 
 This function will read whole database in memory and produce lookups.
 
- $isis->open(
+ $input->open(
  	path => '/path/to/database/file',
 	code_page => '852',
-	limit_mfn => 500,
-	start_mfn => 6000,
+	limit => 500,
+	offset => 6000,
 	lookup => $lookup_obj,
+	stats => 1,
  );
 
 By default, C<code_page> is assumed to be C<852>.
 
-If optional parametar C<start_mfn> is set, this will be first MFN to read
-from database (so you can skip beginning of your database if you need to).
+C<offset> is optional parametar to position at some offset before reading from database.
+
+C<limit> is optional parametar to read just C<limit> records from database
 
-If optional parametar C<limit_mfn> is set, it will read just 500 records
-from database in example above.
+C<stats> create optional report about usage of fields and subfields
 
-Returns size of database, regardless of C<start_mfn> and C<limit_mfn>
-parametars, see also C<$isis->size>.
+Returns size of database, regardless of C<offset> and C<limit>
+parametars, see also C<size>.
 
 =cut
 
@@ -150,19 +188,48 @@
 	my $code_page = $arg->{'code_page'} || '852';
 
 	# store data in object
-	$self->{'code_page'} = $code_page;
-	foreach my $v (qw/path start_mfn limit_mfn/) {
+	$self->{'input_code_page'} = $code_page;
+	foreach my $v (qw/path offset limit/) {
 		$self->{$v} = $arg->{$v} if ($arg->{$v});
 	}
 
 	# create Text::Iconv object
 	$self->{iconv} = Text::Iconv->new($code_page,$self->{'code_page'});
 
-	my ($db, $size) = $self->open_db(
+	my $filter_ref;
+
+	if ($self->{recode}) {
+		my @r = split(/\s/, $self->{recode});
+		if ($#r % 2 != 1) {
+			$log->logwarn("recode needs even number of elements (some number of valid pairs)");
+		} else {
+			my $recode;
+			while (@r) {
+				my $from = shift @r;
+				my $to = shift @r;
+				$recode->{$from} = $to;
+			}
+
+			my $regex = join '|' => keys %{ $recode };
+
+			$log->debug("using recode regex: $regex");
+			
+			$filter_ref = sub {
+				my $t = shift;
+				$t =~ s/($regex)/$recode->{$1}/g;
+				return $t;
+			};
+
+		}
+
+	}
+
+	my ($db, $size) = $self->{open_db}->( $self, 
 		path => $arg->{path},
+		filter => $filter_ref,
 	);
 
-	unless ($db) {
+	unless (defined($db)) {
 		$log->logwarn("can't open database $arg->{path}, skipping...");
 		return;
 	}
@@ -172,60 +239,80 @@
 		return;
 	}
 
-	my $startmfn = 1;
-	my $maxmfn = $size;
+	my $from_rec = 1;
+	my $to_rec = $size;
 
-	if (my $s = $self->{start_mfn}) {
-		$log->info("skipping to MFN $s");
-		$startmfn = $s;
+	if (my $s = $self->{offset}) {
+		$log->debug("skipping to MFN $s");
+		$from_rec = $s;
 	} else {
-		$self->{start_mfn} = $startmfn;
+		$self->{offset} = $from_rec;
 	}
 
-	if ($self->{limit_mfn}) {
-		$log->info("limiting to ",$self->{limit_mfn}," records");
-		$maxmfn = $startmfn + $self->{limit_mfn} - 1;
-		$maxmfn = $size if ($maxmfn > $size);
+	if ($self->{limit}) {
+		$log->debug("limiting to ",$self->{limit}," records");
+		$to_rec = $from_rec + $self->{limit} - 1;
+		$to_rec = $size if ($to_rec > $size);
 	}
 
 	# store size for later
-	$self->{size} = ($maxmfn - $startmfn) ? ($maxmfn - $startmfn + 1) : 0;
+	$self->{size} = ($to_rec - $from_rec) ? ($to_rec - $from_rec + 1) : 0;
 
-	$log->info("processing $self->{size} records in $code_page, convert to $self->{code_page}");
+	$log->info("processing $self->{size}/$size records [$from_rec-$to_rec] convert $code_page -> $self->{code_page}", $self->{stats} ? ' [stats]' : '');
 
 	# read database
-	for (my $mfn = $startmfn; $mfn <= $maxmfn; $mfn++) {
+	for (my $pos = $from_rec; $pos <= $to_rec; $pos++) {
 
-		$log->debug("mfn: $mfn\n");
+		$log->debug("position: $pos\n");
 
-		my $rec = $self->fetch_rec( $db, $mfn );
+		my $rec = $self->{fetch_rec}->($self, $db, $pos );
+
+		$log->debug(sub { Dumper($rec) });
 
 		if (! $rec) {
-			$log->warn("record $mfn empty? skipping...");
+			$log->warn("record $pos empty? skipping...");
 			next;
 		}
 
 		# store
-		if ($self->{'low_mem'}) {
-			$self->{'db'}->put($mfn, $rec);
+		if ($self->{low_mem}) {
+			$self->{db}->put($pos, $rec);
 		} else {
-			$self->{'data'}->{$mfn} = $rec;
+			$self->{data}->{$pos} = $rec;
 		}
 
 		# create lookup
 		$self->{'lookup'}->add( $rec ) if ($rec && $self->{'lookup'});
 
-		$self->progress_bar($mfn,$maxmfn);
+		# update counters for statistics
+		if ($self->{stats}) {
+			map {
+				my $fld = $_;
+				$self->{_stats}->{fld}->{ $fld }++;
+				if (ref($rec->{ $fld }) eq 'ARRAY') {
+					map {
+						if (ref($_) eq 'HASH') {
+							map {
+								$self->{_stats}->{sf}->{ $fld }->{ $_ }++;
+							} keys %{ $_ };
+						} else {
+							$self->{_stats}->{repeatable}->{ $fld }++;
+						}
+					} @{ $rec->{$fld} };
+				}
+			} keys %{ $rec };
+		}
 
-	}
+		$self->progress_bar($pos,$to_rec) unless ($self->{no_progress_bar});
 
-	$self->{'current_mfn'} = -1;
-	$self->{'last_pcnt'} = 0;
+	}
 
-	$log->debug("max mfn: $maxmfn");
+	$self->{pos} = -1;
+	$self->{last_pcnt} = 0;
 
 	# store max mfn and return it.
-	$self->{'max_mfn'} = $maxmfn;
+	$self->{max_pos} = $to_rec;
+	$log->debug("max_pos: $to_rec");
 
 	return $size;
 }
@@ -246,30 +333,30 @@
 
 	my $log = $self->_get_logger();
 
-	$log->logconfess("it seems that you didn't load database!") unless ($self->{'current_mfn'});
+	$log->logconfess("it seems that you didn't load database!") unless ($self->{pos});
 
-	if ($self->{'current_mfn'} == -1) {
-		$self->{'current_mfn'} = $self->{'start_mfn'};
+	if ($self->{pos} == -1) {
+		$self->{pos} = $self->{offset};
 	} else {
-		$self->{'current_mfn'}++;
+		$self->{pos}++;
 	}
 
-	my $mfn = $self->{'current_mfn'};
+	my $mfn = $self->{pos};
 
-	if ($mfn > $self->{'max_mfn'}) {
-		$self->{'current_mfn'} = $self->{'max_mfn'};
+	if ($mfn > $self->{max_pos}) {
+		$self->{pos} = $self->{max_pos};
 		$log->debug("at EOF");
 		return;
 	}
 
-	$self->progress_bar($mfn,$self->{'max_mfn'});
+	$self->progress_bar($mfn,$self->{max_pos}) unless ($self->{no_progress_bar});
 
 	my $rec;
 
-	if ($self->{'low_mem'}) {
-		$rec = $self->{'db'}->get($mfn);
+	if ($self->{low_mem}) {
+		$rec = $self->{db}->get($mfn);
 	} else {
-		$rec = $self->{'data'}->{$mfn};
+		$rec = $self->{data}->{$mfn};
 	}
 
 	$rec ||= 0E0;
@@ -287,7 +374,7 @@
 
 sub pos {
 	my $self = shift;
-	return $self->{'current_mfn'};
+	return $self->{pos};
 }
 
 
@@ -301,13 +388,13 @@
 
  foreach my $mfn ( 1 ... $isis->size ) { ... }
 
-because it takes into account C<start_mfn> and C<limit_mfn>.
+because it takes into account C<offset> and C<limit>.
 
 =cut
 
 sub size {
 	my $self = shift;
-	return $self->{'size'};
+	return $self->{size};
 }
 
 =head2 seek
@@ -329,14 +416,61 @@
 	if ($pos < 1) {
 		$log->warn("seek before first record");
 		$pos = 1;
-	} elsif ($pos > $self->{'max_mfn'}) {
+	} elsif ($pos > $self->{max_pos}) {
 		$log->warn("seek beyond last record");
-		$pos = $self->{'max_mfn'};
+		$pos = $self->{max_pos};
 	}
 
-	return $self->{'current_mfn'} = (($pos - 1) || -1);
+	return $self->{pos} = (($pos - 1) || -1);
 }
 
+=head2 stats
+
+Dump statistics about field and subfield usage
+
+  print $input->stats;
+
+=cut
+
+sub stats {
+	my $self = shift;
+
+	my $log = $self->_get_logger();
+
+	my $s = $self->{_stats};
+	if (! $s) {
+		$log->warn("called stats, but there is no statistics collected");
+		return;
+	}
+
+	my $max_fld = 0;
+
+	my $out = join("\n",
+		map {
+			my $f = $_ || die "no field";
+			my $v = $s->{fld}->{$f} || die "no s->{fld}->{$f}";
+			$max_fld = $v if ($v > $max_fld);
+
+			my $o = sprintf("%4d %d ~", $f, $v);
+
+			if (defined($s->{sf}->{$f})) {
+				map {
+					$o .= sprintf(" %s:%d", $_, $s->{sf}->{$f}->{$_});
+				} sort keys %{ $s->{sf}->{$f} };
+			}
+
+			if (my $v_r = $s->{repeatable}->{$f}) {
+				$o .= " ($v_r)" if ($v_r != $v);
+			}
+
+			$o;
+		} sort { $a <=> $b } keys %{ $s->{fld} }
+	);
+
+	$log->debug( sub { Dumper($s) } );
+
+	return $out;
+}
 
 =head1 MEMORY USAGE