--- trunk/lib/WebPAC/Input.pm	2005/06/25 20:23:23	1
+++ trunk/lib/WebPAC/Input.pm	2005/12/18 22:16:44	289
@@ -3,63 +3,399 @@
 use warnings;
 use strict;
 
+use blib;
+
+use WebPAC::Common;
+use base qw/WebPAC::Common/;
+use Text::Iconv;
+
 =head1 NAME
 
-WebPAC::Input - The great new WebPAC::Input!
+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
 
-Quick summary of what the module does.
+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 $foo = WebPAC::Input->new();
-    ...
+    my $db = WebPAC::Input->new(
+    	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 $rec = $db->fetch) {
+    }
 
-=head1 EXPORT
 
-A list of functions that can be exported.  You can delete this section
-if you don't export anything, such as for a purely object-oriented module.
 
 =head1 FUNCTIONS
 
-=head2 function1
+=head2 new
+
+Create new input database object.
+
+  my $db = new WebPAC::Input(
+	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 function1 {
+sub new {
+	my $class = shift;
+	my $self = {@_};
+	bless($self, $class);
+
+	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 init/) {
+		my $n = $self->{module} . '::' . $subclass;
+		if (! defined &{ $n }) {
+			$log->logwarn("missing implementation of $subclass");
+		} else {
+			$self->{$subclass} = \&{ $n };
+		}
+	}
+
+	if ($self->{init}) {
+		$log->debug("calling init");
+		$self->{init}->($self, @_);
+	}
+
+	$self->{'code_page'} ||= 'ISO-8859-2';
+
+	# running with low_mem flag? well, use DBM::Deep then.
+	if ($self->{'low_mem'}) {
+		$log->info("running with low_mem which impacts performance (<32 Mb memory usage)");
+
+		my $db_file = "data.db";
+
+		if (-e $db_file) {
+			unlink $db_file or $log->logdie("can't remove '$db_file' from last run");
+			$log->debug("removed '$db_file' from last run");
+		}
+
+		require DBM::Deep;
+
+		my $db = new DBM::Deep $db_file;
+
+		$log->logdie("DBM::Deep error: $!") unless ($db);
+
+		if ($db->error()) {
+			$log->logdie("can't open '$db_file' under low_mem: ",$db->error());
+		} else {
+			$log->debug("using file '$db_file' for DBM::Deep");
+		}
+
+		$self->{'db'} = $db;
+	}
+
+	$self ? return $self : return undef;
 }
 
-=head2 function2
+=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 function2 {
+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}->( $self, 
+		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; $pos++) {
+
+		$log->debug("position: $pos\n");
+
+		my $rec = $self->{fetch_rec}->($self, $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;
 }
 
-=head1 AUTHOR
+=head2 fetch
 
-Dobrica Pavlinusic, C<< <dpavlin@rot13.org> >>
+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
 
-=head1 BUGS
+sub fetch {
+	my $self = shift;
 
-Please report any bugs or feature requests to
-C<bug-webpac-input@rt.cpan.org>, or through the web interface at
-L<http://rt.cpan.org/NoAuth/ReportBug.html?Queue=WebPAC>.
-I will be notified, and then you'll automatically be notified of progress on
-your bug as I make changes.
+	my $log = $self->_get_logger();
 
-=head1 ACKNOWLEDGEMENTS
+	$log->logconfess("it seems that you didn't load database!") unless ($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
+will run on memory constraint machines (which doesn't have enough
+physical RAM to create memory structure for whole source database).
+
+If your machine has 512Mb or more of RAM and database is around 10000 records,
+memory shouldn't be an issue. If you don't have enough physical RAM, you
+might consider using virtual memory (if your operating system is handling it
+well, like on FreeBSD or Linux) instead of dropping to L<DBM::Deep> to handle
+parsed structure of ISIS database (this is what C<low_mem> option does).
+
+Hitting swap at end of reading source database is probably o.k. However,
+hitting swap before 90% will dramatically decrease performance and you will
+be better off with C<low_mem> and using rest of availble memory for
+operating system disk cache (Linux is particuallary good about this).
+However, every access to database record will require disk access, so
+generation phase will be slower 10-100 times.
+
+Parsed structures are essential - you just have option to trade RAM memory
+(which is fast) for disk space (which is slow). Be sure to have planty of
+disk space if you are using C<low_mem> and thus L<DBM::Deep>.
+
+However, when WebPAC is running on desktop machines (or laptops :-), it's
+highly undesireable for system to start swapping. Using C<low_mem> option can
+reduce WecPAC memory usage to around 64Mb for same database with lookup
+fields and sorted indexes which stay in RAM. Performance will suffer, but
+memory usage will really be minimal. It might be also more confortable to
+run WebPAC reniced on those machines.
+
+
+=head1 AUTHOR
+
+Dobrica Pavlinusic, C<< <dpavlin@rot13.org> >>
 
 =head1 COPYRIGHT & LICENSE