--- trunk/lib/WebPAC/Input.pm	2005/07/16 20:54:28	11
+++ trunk/lib/WebPAC/Input.pm	2005/12/18 21:06:46	286
@@ -3,39 +3,57 @@
 use warnings;
 use strict;
 
+use blib;
+
+use WebPAC::Common;
+use base qw/WebPAC::Common/;
+use Text::Iconv;
+
 =head1 NAME
 
-WebPAC::Input - core module for input file format
+WebPAC::Input - read different file formats into WebPAC
 
 =head1 VERSION
 
-Version 0.01
+Version 0.03
 
 =cut
 
-our $VERSION = '0.01';
+our $VERSION = '0.03';
 
 =head1 SYNOPSIS
 
-This module will load particular loader module and execute it's functions.
+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) {
-	...
+    while (my $rec = $db->fetch) {
     }
 
+
+
 =head1 FUNCTIONS
 
 =head2 new
@@ -43,28 +61,56 @@
 Create new input database object.
 
   my $db = new WebPAC::Input(
-  	format => 'NULL'
+	module => 'WebPAC::Input::MARC',
 	code_page => 'ISO-8859-2',
 	low_mem => 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).
 
+This function will also call low-level C<init> if it exists with same
+parametars.
+
 =cut
 
 sub new {
-        my $class = shift;
-        my $self = {@_};
+	my $class = shift;
+	my $self = {@_};
 	bless($self, $class);
 
-	$self->{'code_page'} ||= 'ISO-8859-2';
-
 	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/) {
+		if ( $self->can($subclass) ) {
+			$log->debug("imported $subclass");
+		} else {
+			$log->warn("missing $subclass in $self->{module}");
+		}
+	}
+
+	if ($self->can('init')) {
+		$log->debug("calling init");
+		$self->init(@_);
+	}
+
+	$self->{'code_page'} ||= 'ISO-8859-2';
+
 	# running with low_mem flag? well, use DBM::Deep then.
 	if ($self->{'low_mem'}) {
 		$log->info("running with low_mem which impacts performance (<32 Mb memory usage)");
@@ -94,6 +140,226 @@
 	$self ? return $self : return undef;
 }
 
+=head2 open
+
+This function will read whole database in memory and produce lookups.
+
+ $input->open(
+ 	path => '/path/to/database/file',
+	code_page => '852',
+	limit => 500,
+	offset => 6000,
+	lookup => $lookup_obj,
+ );
+
+By default, C<code_page> is assumed to be C<852>.
+
+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
+
+Returns size of database, regardless of C<offset> and C<limit>
+parametars, see also C<size>.
+
+=cut
+
+sub open {
+	my $self = shift;
+	my $arg = {@_};
+
+	my $log = $self->_get_logger();
+
+	$log->logcroak("need path") if (! $arg->{'path'});
+	my $code_page = $arg->{'code_page'} || '852';
+
+	# store data in object
+	$self->{'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(
+		path => $arg->{path},
+	);
+
+	unless ($db) {
+		$log->logwarn("can't open database $arg->{path}, skipping...");
+		return;
+	}
+
+	unless ($size) {
+		$log->logwarn("no records in database $arg->{path}, skipping...");
+		return;
+	}
+
+	my $offset = 1;
+	my $limit = $size;
+
+	if (my $s = $self->{offset}) {
+		$log->info("skipping to MFN $s");
+		$offset = $s;
+	} else {
+		$self->{offset} = $offset;
+	}
+
+	if ($self->{limit}) {
+		$log->info("limiting to ",$self->{limit}," records");
+		$limit = $offset + $self->{limit} - 1;
+		$limit = $size if ($limit > $size);
+	}
+
+	# store size for later
+	$self->{size} = ($limit - $offset) ? ($limit - $offset + 1) : 0;
+
+	$log->info("processing $self->{size} records in $code_page, convert to $self->{code_page}");
+
+	# read database
+	for (my $pos = $offset; $pos <= $limit; $mfn++) {
+
+		$log->debug("position: $pos\n");
+
+		my $rec = $self->fetch_rec( $db, $pos );
+
+		if (! $rec) {
+			$log->warn("record $pos empty? skipping...");
+			next;
+		}
+
+		# store
+		if ($self->{low_mem}) {
+			$self->{db}->put($pos, $rec);
+		} else {
+			$self->{data}->{$pos} = $rec;
+		}
+
+		# create lookup
+		$self->{'lookup'}->add( $rec ) if ($rec && $self->{'lookup'});
+
+		$self->progress_bar($pos,$limit);
+
+	}
+
+	$self->{pos} = -1;
+	$self->{last_pcnt} = 0;
+
+	# store max mfn and return it.
+	$self->{max_pos} = $limit;
+	$log->debug("max_pos: $limit");
+
+	return $size;
+}
+
+=head2 fetch
+
+Fetch next record from database. It will also displays progress bar.
+
+ my $rec = $isis->fetch;
+
+Record from this function should probably go to C<data_structure> for
+normalisation.
+
+=cut
+
+sub fetch {
+	my $self = shift;
+
+	my $log = $self->_get_logger();
+
+	$log->logconfess("it seems that you didn't load database!") unless ($self->{pos});
+
+	if ($self->{pos} == -1) {
+		$self->{pos} = $self->{offset};
+	} else {
+		$self->{pos}++;
+	}
+
+	my $mfn = $self->{pos};
+
+	if ($mfn > $self->{max_pos}) {
+		$self->{pos} = $self->{max_pos};
+		$log->debug("at EOF");
+		return;
+	}
+
+	$self->progress_bar($mfn,$self->{max_pos});
+
+	my $rec;
+
+	if ($self->{low_mem}) {
+		$rec = $self->{db}->get($mfn);
+	} else {
+		$rec = $self->{data}->{$mfn};
+	}
+
+	$rec ||= 0E0;
+}
+
+=head2 pos
+
+Returns current record number (MFN).
+
+ print $isis->pos;
+
+First record in database has position 1.
+
+=cut
+
+sub pos {
+	my $self = shift;
+	return $self->{pos};
+}
+
+
+=head2 size
+
+Returns number of records in database
+
+ print $isis->size;
+
+Result from this function can be used to loop through all records
+
+ foreach my $mfn ( 1 ... $isis->size ) { ... }
+
+because it takes into account C<offset> and C<limit>.
+
+=cut
+
+sub size {
+	my $self = shift;
+	return $self->{size};
+}
+
+=head2 seek
+
+Seek to specified MFN in file.
+
+ $isis->seek(42);
+
+First record in database has position 1.
+
+=cut
+
+sub seek {
+	my $self = shift;
+	my $pos = shift || return;
+
+	my $log = $self->_get_logger();
+
+	if ($pos < 1) {
+		$log->warn("seek before first record");
+		$pos = 1;
+	} elsif ($pos > $self->{max_pos}) {
+		$log->warn("seek beyond last record");
+		$pos = $self->{max_pos};
+	}
+
+	return $self->{pos} = (($pos - 1) || -1);
+}
+
+
 =head1 MEMORY USAGE
 
 C<low_mem> options is double-edged sword. If enabled, WebPAC