X-Git-Url: http://git.rot13.org/?a=blobdiff_plain;f=lib%2FWebPAC%2FInput.pm;h=218a9696ca0c4555746c4dc163f4d1a62bf9bd51;hb=640203e47fc3ef06a8b73b01bdb9ee76a2baa569;hp=3c6c9c9363c53e97ffe2858b43eb191e8c120a14;hpb=4227c492b24a820e144f8398de90c70a567712f0;p=webpac2

diff --git a/lib/WebPAC/Input.pm b/lib/WebPAC/Input.pm
index 3c6c9c9..218a969 100644
--- a/lib/WebPAC/Input.pm
+++ b/lib/WebPAC/Input.pm
@@ -8,19 +8,15 @@ use blib;
 use WebPAC::Common;
 use base qw/WebPAC::Common/;
 use Data::Dump qw/dump/;
-use Encode qw/from_to/;
+use Encode qw/decode from_to/;
 
 =head1 NAME
 
 WebPAC::Input - read different file formats into WebPAC
 
-=head1 VERSION
-
-Version 0.17
-
 =cut
 
-our $VERSION = '0.17';
+our $VERSION = '0.19';
 
 =head1 SYNOPSIS
 
@@ -61,18 +57,16 @@ Create new input database object.
 
   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 +84,10 @@ sub new {
 
 	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 +97,6 @@ sub new {
 
 	require $module_path;
 
-	$self->{'encoding'} ||= 'ISO-8859-2';
-
 	$self ? return $self : return undef;
 }
 
@@ -115,7 +108,8 @@ This function will read whole database in memory and produce lookups.
 
  $input->open(
  	path => '/path/to/database/file',
-	code_page => 'cp852',
+	input_encoding => 'cp852',
+	strict_encoding => 0,
 	limit => 500,
 	offset => 6000,
 	stats => 1,
@@ -140,7 +134,7 @@ This function will read whole database in memory and produce lookups.
 
  );
 
-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.
 
@@ -161,6 +155,8 @@ overrides C<modify_records> if both exists for same input.
 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 +167,10 @@ sub open {
 	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');
@@ -179,10 +178,9 @@ sub open {
 	$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});
 	}
@@ -233,10 +231,11 @@ sub open {
 
 	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;
 #		},
@@ -274,7 +273,12 @@ sub open {
 	# store size for later
 	$self->{size} = ($to_rec - $from_rec) ? ($to_rec - $from_rec + 1) : 0;
 
-	$log->info("processing $self->{size}/$size records [$from_rec-$to_rec] convert $code_page -> $self->{encoding}", $self->{stats} ? ' [stats]' : '');
+	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]",
+		" encoding $input_encoding ", $strict_encoding ? ' [strict]' : '',
+		$self->{stats} ? ' [stats]' : '',
+	);
 
 	# read database
 	for (my $pos = $from_rec; $pos <= $to_rec; $pos++) {
@@ -286,11 +290,14 @@ sub open {
 #				return unless defined($l);
 #				return $l unless ($rec_regex && $f_nr);
 
-				warn "-=> $f_nr ## $l\n" if ($debug);
+				return unless ( defined($l) && defined($f_nr) );
+
+				warn "-=> $f_nr ## |$l|\n" if ($debug);
 				$log->debug("-=> $f_nr ## $l");
 
 				# codepage conversion and recode_regex
-				from_to($l, $code_page, $self->{'encoding'});
+#				$l = decode($input_encoding, $l, 1);
+				from_to( $l, $input_encoding, 'utf-8', 1 );
 				$l =~ s/($recode_regex)/$recode_map->{$1}/g if ($recode_regex && $recode_map);
 
 				# apply regexps
@@ -299,16 +306,21 @@ sub open {
 					my $c = 0;
 					foreach my $r (@{ $rec_regex->{$f_nr} }) {
 						my $old_l = $l;
-						eval '$l =~ ' . $r;
+						$log->logconfess("expected regex in ", dump( $r )) unless defined($r->{regex});
+						eval '$l =~ ' . $r->{regex};
 						if ($old_l ne $l) {
-							$log->debug("REGEX on $f_nr eval \$l =~ $r\n## old l: [$old_l]\n## new l: [$l]");
-							warn "*** $r |$old_l| -> |$l|\n" if ($debug);
+							my $d = "|$old_l| -> |$l| "; # . $r->{regex};
+							$d .= ' +' . $r->{line} . ' ' . $r->{file} if defined($r->{line});
+							$d .= ' ' . $r->{debug} if defined($r->{debug});
+							$log->debug("MODIFY $d");
+							warn "*** $d\n" if ($debug);
+
 						}
 						$log->error("error applying regex: $r") if ($@);
 					}
 				}
 
-				$log->debug("<=- $f_nr ## $l");
+				$log->debug("<=- $f_nr ## |$l|");
 				warn "<=- $f_nr ## $l\n" if ($debug);
 				return $l;
 		});
@@ -342,8 +354,8 @@ sub open {
 			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} }) {
 
@@ -512,19 +524,26 @@ sub stats {
 
 	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}) {
@@ -532,7 +551,13 @@ sub stats {
 			}
 
 			$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) } );
@@ -551,21 +576,22 @@ sub dump_ascii {
 
 	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} ) );
 	}
 }
 
-=head2 modify_record_regexps
+=head2 _get_regex
 
-Generate hash with regexpes to be applied using L<filter>.
+Helper function called which create regexps to be execute on code.
 
-  my $regexpes = $input->modify_record_regexps(
-		900 => { '^a' => { ' : ' => '^b' } },
-		901 => { '*' => { '^b' => ' ; ' } },
-  );
+  _get_regex( 900, 'regex:[0-9]+' ,'numbers' );
+  _get_regex( 900, '^b', ' : ^b' );
+
+It supports perl regexps with C<regex:> prefix to from value and has
+additional logic to skip empty subfields.
 
 =cut
 
@@ -582,14 +608,30 @@ sub _get_regex {
 		$from = '\Q' . $from . '\E';
 	}
 	if ($sf =~ /^\^/) {
+		my $need_subfield_data = '*';	# no
+		# if from is also subfield, require some data in between
+		# to correctly skip empty subfields
+		$need_subfield_data = '+' if ($from =~ m/^\\Q\^/);
 		return
-			's/\Q'. $sf .'\E([^\^]*?)'. $from .'([^\^]*?)/'. $sf .'$1'. $to .'$2/';
+			's/\Q'. $sf .'\E([^\^]' . $need_subfield_data . '?)'. $from .'([^\^]*?)/'. $sf .'$1'. $to .'$2/';
 	} else {
 		return
 			's/'. $from .'/'. $to .'/g';
 	}
 }
 
+
+=head2 modify_record_regexps
+
+Generate hash with regexpes to be applied using L<filter>.
+
+  my $regexpes = $input->modify_record_regexps(
+		900 => { '^a' => { ' : ' => '^b' } },
+		901 => { '*' => { '^b' => ' ; ' } },
+  );
+
+=cut
+
 sub modify_record_regexps {
 	my $self = shift;
 	my $modify_record = {@_};
@@ -607,10 +649,11 @@ sub modify_record_regexps {
 			foreach my $from (keys %{ $modify_record->{$f}->{$sf} }) {
 				my $to = $modify_record->{$f}->{$sf}->{$from};
 				#die "no field?" unless defined($to);
-				$log->debug("transform: |$from| -> |$to|");
+				my $d = "|$from| -> |$to|";
+				$log->debug("transform: $d");
 
 				my $regex = _get_regex($sf,$from,$to);
-				push @{ $regexpes->{$f} }, $regex;
+				push @{ $regexpes->{$f} }, { regex => $regex, debug => $d };
 				$log->debug("regex: $regex");
 			}
 		}
@@ -671,7 +714,11 @@ sub modify_file_regexps {
 			$log->debug("transform: |$from| -> |$to|");
 
 			my $regex = _get_regex($sf,$from,$to);
-			push @{ $regexpes->{$f} }, $regex;
+			push @{ $regexpes->{$f} }, {
+				regex => $regex,
+				file => $modify_path,
+				line => $.,
+			};
 			$log->debug("regex: $regex");
 		}
 	}