--- trunk/lib/WebPAC/Input.pm	2007/04/11 12:22:37	823
+++ trunk/lib/WebPAC/Input.pm	2009/09/21 16:42:25	1307
@@ -3,24 +3,21 @@
 use warnings;
 use strict;
 
-use blib;
+use lib 'lib';
 
 use WebPAC::Common;
 use base qw/WebPAC::Common/;
 use Data::Dump qw/dump/;
-use Encode qw/from_to/;
+use Encode qw/decode from_to/;
+use YAML;
 
 =head1 NAME
 
 WebPAC::Input - read different file formats into WebPAC
 
-=head1 VERSION
-
-Version 0.18
-
 =cut
 
-our $VERSION = '0.18';
+our $VERSION = '0.19';
 
 =head1 SYNOPSIS
 
@@ -61,18 +58,16 @@
 
   my $db = new WebPAC::Input(
 	module => 'WebPAC::Input::MARC',
-	encoding => 'ISO-8859-2',
 	recode => 'char pairs',
 	no_progress_bar => 1,
+	input_config => {
+		mapping => [ 'foo', 'bar', 'baz' ],
+	},
   );
 
 C<module> is low-level file format module. See L<WebPAC::Input::ISIS> and
 L<WebPAC::Input::MARC>.
 
-Optional parametar C<encoding> specify application code page (which will be
-used internally). This should probably be your terminal encoding, and by
-default, it C<ISO-8859-2>.
-
 C<recode> is optional string constisting of character or words pairs that
 should be replaced in input stream.
 
@@ -90,9 +85,10 @@
 
 	my $log = $self->_get_logger;
 
-	$log->logconfess("code_page argument is not suppored any more. change it to encoding") if ($self->{lookup});
-	$log->logconfess("lookup argument is not suppored any more. rewrite call to lookup_ref") if ($self->{lookup});
-	$log->logconfess("low_mem argument is not suppored any more. rewrite it to load_row and save_row") if ($self->{low_mem});
+	$log->logconfess("code_page argument is not suppored any more.") if $self->{code_page};
+	$log->logconfess("encoding argument is not suppored any more.") if $self->{encoding};
+	$log->logconfess("lookup argument is not suppored any more. rewrite call to lookup_ref") if $self->{lookup};
+	$log->logconfess("low_mem argument is not suppored any more. rewrite it to load_row and save_row") if $self->{low_mem};
 
 	$log->logconfess("specify low-level file format module") unless ($self->{module});
 	my $module_path = $self->{module};
@@ -102,8 +98,6 @@
 
 	require $module_path;
 
-	$self->{'encoding'} ||= 'ISO-8859-2';
-
 	$self ? return $self : return undef;
 }
 
@@ -115,7 +109,8 @@
 
  $input->open(
  	path => '/path/to/database/file',
-	code_page => 'cp852',
+	input_encoding => 'cp852',
+	strict_encoding => 0,
 	limit => 500,
 	offset => 6000,
 	stats => 1,
@@ -140,9 +135,9 @@
 
  );
 
-By default, C<code_page> is assumed to be C<cp852>.
+By default, C<input_encoding> is assumed to be C<cp852>.
 
-C<offset> is optional parametar to position at some offset before reading from database.
+C<offset> is optional parametar to skip records at beginning.
 
 C<limit> is optional parametar to read just C<limit> records from database
 
@@ -161,6 +156,8 @@
 C<save_row> and C<load_row> are low-level implementation of store engine. Calling convention
 is documented in example above.
 
+C<strict_encoding> should really default to 1, but it doesn't for now.
+
 Returns size of database, regardless of C<offset> and C<limit>
 parametars, see also C<size>.
 
@@ -171,7 +168,10 @@
 	my $arg = {@_};
 
 	my $log = $self->_get_logger();
+	$log->debug( "arguments: ",dump( $arg ));
 
+	$log->logconfess("encoding argument is not suppored any more.") if $self->{encoding};
+	$log->logconfess("code_page argument is not suppored any more.") if $self->{code_page};
 	$log->logconfess("lookup argument is not suppored any more. rewrite call to lookup_coderef") if ($arg->{lookup});
 	$log->logconfess("lookup_coderef must be CODE, not ",ref($arg->{lookup_coderef}))
 		if ($arg->{lookup_coderef} && ref($arg->{lookup_coderef}) ne 'CODE');
@@ -179,13 +179,10 @@
 	$log->debug( $arg->{lookup_coderef} ? '' : 'not ', "using lookup_coderef");
 
 	$log->logcroak("need path") if (! $arg->{'path'});
-	my $code_page = $arg->{'code_page'} || 'cp852';
+	my $input_encoding = $arg->{'input_encoding'} || $self->{'input_encoding'} || 'cp852';
 
 	# store data in object
-	$self->{'input_code_page'} = $code_page;
-	foreach my $v (qw/path offset limit/) {
-		$self->{$v} = $arg->{$v} if ($arg->{$v});
-	}
+	$self->{$_} = $arg->{$_} foreach grep { defined $arg->{$_} } qw(path offset limit);
 
 	if ($arg->{load_row} || $arg->{save_row}) {
 		$log->logconfess("save_row and load_row must be defined in pair and be CODE") unless (
@@ -231,18 +228,24 @@
 
 	my $class = $self->{module} || $log->logconfess("can't get low-level module name!");
 
+	$arg->{$_} = $self->{$_} foreach qw(offset limit);
+
 	my $ll_db = $class->new(
 		path => $arg->{path},
+		input_config => $arg->{input_config} || $self->{input_config},
 #		filter => sub {
 #			my ($l,$f_nr) = @_;
 #			return unless defined($l);
-#			from_to($l, $code_page, $self->{'encoding'});
+#			$l = decode($input_encoding, $l);
 #			$l =~ s/($recode_regex)/$recode_map->{$1}/g if ($recode_regex && $recode_map);
 #			return $l;
 #		},
 		%{ $arg },
 	);
 
+	# save for dump and input_module
+	$self->{ll_db} = $ll_db;
+
 	unless (defined($ll_db)) {
 		$log->logwarn("can't open database $arg->{path}, skipping...");
 		return;
@@ -259,10 +262,10 @@
 	my $to_rec = $size;
 
 	if (my $s = $self->{offset}) {
-		$log->debug("skipping to MFN $s");
-		$from_rec = $s;
+		$log->debug("offset $s records");
+		$from_rec = $s + 1;
 	} else {
-		$self->{offset} = $from_rec;
+		$self->{offset} = $from_rec - 1;
 	}
 
 	if ($self->{limit}) {
@@ -271,16 +274,22 @@
 		$to_rec = $size if ($to_rec > $size);
 	}
 
-	# store size for later
-	$self->{size} = ($to_rec - $from_rec) ? ($to_rec - $from_rec + 1) : 0;
+	my $strict_encoding = $arg->{strict_encoding} || $self->{strict_encoding}; ## FIXME should be 1 really
 
-	$log->info("processing $self->{size}/$size records [$from_rec-$to_rec] convert $code_page -> $self->{encoding}", $self->{stats} ? ' [stats]' : '');
+	$log->info("processing $self->{size}/$size records [$from_rec-$to_rec]",
+		" encoding $input_encoding ", $strict_encoding ? ' [strict]' : '',
+		$self->{stats} ? ' [stats]' : '',
+	);
+
+	$self->{size} = 0;
 
 	# read database
 	for (my $pos = $from_rec; $pos <= $to_rec; $pos++) {
 
 		$log->debug("position: $pos\n");
 
+		$self->{size}++; # XXX I could move this more down if I didn't want empty records...
+
 		my $rec = $ll_db->fetch_rec($pos, sub {
 				my ($l,$f_nr,$debug) = @_;
 #				return unless defined($l);
@@ -292,7 +301,7 @@
 				$log->debug("-=> $f_nr ## $l");
 
 				# codepage conversion and recode_regex
-				from_to($l, $code_page, $self->{'encoding'});
+				$l = decode($input_encoding, $l, 1);
 				$l =~ s/($recode_regex)/$recode_map->{$1}/g if ($recode_regex && $recode_map);
 
 				# apply regexps
@@ -311,7 +320,7 @@
 							warn "*** $d\n" if ($debug);
 
 						}
-						$log->error("error applying regex: $r") if ($@);
+						$log->error("error applying regex: ",dump($r), $@) if $@;
 					}
 				}
 
@@ -349,8 +358,8 @@
 			foreach my $fld (keys %{ $rec }) {
 				$self->{_stats}->{fld}->{ $fld }++;
 
-				$log->logdie("invalid record fild $fld, not ARRAY")
-					unless (ref($rec->{ $fld }) eq 'ARRAY');
+				#$log->logdie("invalid record fild $fld, not ARRAY")
+				next unless (ref($rec->{ $fld }) eq 'ARRAY');
 	
 				foreach my $row (@{ $rec->{$fld} }) {
 
@@ -381,12 +390,11 @@
 	$self->{max_pos} = $to_rec;
 	$log->debug("max_pos: $to_rec");
 
-	# save for dump
-	$self->{ll_db} = $ll_db;
-
 	return $size;
 }
 
+sub input_module { $_[0]->{ll_db} }
+
 =head2 fetch
 
 Fetch next record from database. It will also displays progress bar.
@@ -406,7 +414,7 @@
 	$log->logconfess("it seems that you didn't load database!") unless ($self->{pos});
 
 	if ($self->{pos} == -1) {
-		$self->{pos} = $self->{offset};
+		$self->{pos} = $self->{offset} + 1;
 	} else {
 		$self->{pos}++;
 	}
@@ -464,7 +472,7 @@
 
 sub size {
 	my $self = shift;
-	return $self->{size};
+	return $self->{size}; # FIXME this is buggy if open is called multiple times!
 }
 
 =head2 seek
@@ -519,19 +527,26 @@
 
 	my $out = join("\n",
 		map {
-			my $f = $_ || die "no field";
+			my $f = $_;
+			die "no field in ", dump( $s->{fld} ) unless defined( $f );
 			my $v = $s->{fld}->{$f} || die "no s->{fld}->{$f}";
 			$max_fld = $v if ($v > $max_fld);
 
 			my $o = sprintf("%4s %d ~", $f, $v);
 
 			if (defined($s->{sf}->{$f})) {
+				my @subfields = keys %{ $s->{sf}->{$f} };
 				map {
 					$o .= sprintf(" %s:%d%s", $_, 
 						$s->{sf}->{$f}->{$_}->{count},
 						$s->{sf}->{$f}->{$_}->{repeatable} ? '*' : '',
 					);
-				} sort keys %{ $s->{sf}->{$f} };
+				} (
+					# first indicators and other special subfields
+					sort( grep { length($_)  > 1 } @subfields ),
+					# then subfileds (single char)
+					sort( grep { length($_) == 1 } @subfields ),
+				);
 			}
 
 			if (my $v_r = $s->{repeatable}->{$f}) {
@@ -539,11 +554,21 @@
 			}
 
 			$o;
-		} sort { $a cmp $b } keys %{ $s->{fld} }
+		} sort { 
+			if ( $a =~ m/^\d+$/ && $b =~ m/^\d+$/ ) {
+				$a <=> $b
+			} else {
+				$a cmp $b
+			}
+		} keys %{ $s->{fld} }
 	);
 
 	$log->debug( sub { dump($s) } );
 
+	my $path = 'var/stats.yml';
+	YAML::DumpFile( $path, $s );
+	$log->info( 'created ', $path, ' with ', -s $path, ' bytes' );
+
 	return $out;
 }
 
@@ -558,7 +583,7 @@
 
 	return unless $self->{ll_db};
 
-	if ($self->{ll_db}->can('dump_rec')) {
+	if ($self->{ll_db}->can('dump_ascii')) {
 		return $self->{ll_db}->dump_ascii( $self->{pos} );
 	} else {
 		return dump( $self->{ll_db}->fetch_rec( $self->{pos} ) );
@@ -702,6 +727,8 @@
 				line => $.,
 			};
 			$log->debug("regex: $regex");
+		} else {
+			die "can't parse: $_";
 		}
 	}