--- trunk/lib/WebPAC/Input.pm 2006/05/18 13:48:51 519 +++ trunk/lib/WebPAC/Input.pm 2006/07/13 13:55:15 598 @@ -16,11 +16,11 @@ =head1 VERSION -Version 0.05 +Version 0.08 =cut -our $VERSION = '0.05'; +our $VERSION = '0.08'; =head1 SYNOPSIS @@ -39,16 +39,14 @@ Perhaps a little code snippet. - use WebPAC::Input; + use WebPAC::Input; - my $db = WebPAC::Input->new( - module => 'WebPAC::Input::ISIS', - config => $config, - lookup => $lookup_obj, + my $db = WebPAC::Input->new( + module => 'WebPAC::Input::ISIS', low_mem => 1, - ); + ); - $db->open('/path/to/database'); + $db->open( path => '/path/to/database' ); print "database size: ",$db->size,"\n"; while (my $rec = $db->fetch) { # do something with $rec @@ -64,16 +62,16 @@ my $db = new WebPAC::Input( module => 'WebPAC::Input::MARC', - code_page => 'ISO-8859-2', + encoding => 'ISO-8859-2', low_mem => 1, recode => 'char pairs', no_progress_bar => 1, ); -C is low-level file format module. See L and +C is low-level file format module. See L and L. -Optional parametar C specify application code page (which will be +Optional parametar C specify application code page (which will be used internally). This should probably be your terminal encoding, and by default, it C. @@ -96,6 +94,9 @@ 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}); + $log->logconfess("specify low-level file format module") unless ($self->{module}); my $module = $self->{module}; $module =~ s#::#/#g; @@ -121,7 +122,7 @@ $self->{init}->($self, @_); } - $self->{'code_page'} ||= 'ISO-8859-2'; + $self->{'encoding'} ||= 'ISO-8859-2'; # running with low_mem flag? well, use DBM::Deep then. if ($self->{'low_mem'}) { @@ -163,6 +164,14 @@ offset => 6000, lookup => $lookup_obj, stats => 1, + lookup_ref => sub { + my ($k,$v) = @_; + # store lookup $k => $v + }, + modify_records => { + 900 => { '^a' => { ' : ' => '^b' } }, + 901 => { '*' => { '^b' => ' ; ' } }, + }, ); By default, C is assumed to be C<852>. @@ -173,6 +182,13 @@ C create optional report about usage of fields and subfields +C is closure to call when adding C<< key => 'value' >> combinations to +lookup. + +C specify mapping from subfields to delimiters or from +delimiters to subfields, as well as oprations on fields (if subfield is +defined as C<*>. + Returns size of database, regardless of C and C parametars, see also C. @@ -184,6 +200,10 @@ my $log = $self->_get_logger(); + $log->logconfess("lookup argument is not suppored any more. rewrite call to lookup_coderef") if ($arg->{lookup}); + $log->logconfess("lookup_coderef must be CODE, not ",ref($arg->{lookup_coderef})) + if ($arg->{lookup_coderef} && ref($arg->{lookup_coderef}) ne 'CODE'); + $log->logcroak("need path") if (! $arg->{'path'}); my $code_page = $arg->{'code_page'} || '852'; @@ -194,39 +214,59 @@ } # create Text::Iconv object - $self->{iconv} = Text::Iconv->new($code_page,$self->{'code_page'}); + $self->{iconv} = Text::Iconv->new($code_page,$self->{'encoding'}); ## FIXME remove! my $filter_ref; + my $recode_regex; + my $recode_map; if ($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; + $recode_map->{$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; - }; + $recode_regex = join '|' => keys %{ $recode_map }; + $log->debug("using recode regex: $recode_regex"); } } + my $rec_regex = $self->modify_record_regexps(%{ $arg->{modify_records} }); + $log->debug("rec_regex: ", Dumper($rec_regex)); + my ($db, $size) = $self->{open_db}->( $self, path => $arg->{path}, - filter => $filter_ref, + filter => sub { + my ($l,$f_nr) = @_; + return unless defined($l); + + ## FIXME remove iconv! + $l = $self->{iconv}->convert($l) if ($self->{iconv}); + + $l =~ s/($recode_regex)/$recode_map->{$1}/g if ($recode_regex && $recode_map); + + return $l unless ($rec_regex); + + # apply regexps + if ($rec_regex && defined($rec_regex->{$f_nr})) { + $log->logconfess("regexps->{$f_nr} must be ARRAY") if (ref($rec_regex->{$f_nr}) ne 'ARRAY'); + my $c = 0; + foreach my $r (@{ $rec_regex->{$f_nr} }) { + while ( eval '$l =~ ' . $r ) { $c++ }; + } + warn "## field $f_nr triggered $c regexpes\n" if ($c && $self->{debug}); + } + + return $l; + }, + %{ $arg }, ); unless (defined($db)) { @@ -258,7 +298,7 @@ # 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->{code_page}", $self->{stats} ? ' [stats]' : ''); + $log->info("processing $self->{size}/$size records [$from_rec-$to_rec] convert $code_page -> $self->{encoding}", $self->{stats} ? ' [stats]' : ''); # read database for (my $pos = $from_rec; $pos <= $to_rec; $pos++) { @@ -282,25 +322,32 @@ } # create lookup - $self->{'lookup'}->add( $rec ) if ($rec && $self->{'lookup'}); + $arg->{'lookup_coderef'}->( $rec ) if ($rec && $arg->{'lookup_coderef'}); # update counters for statistics if ($self->{stats}) { - map { - my $fld = $_; + + foreach my $fld (keys %{ $rec }) { $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 }++; + + $log->logdie("invalid record fild $fld, not ARRAY") + unless (ref($rec->{ $fld }) eq 'ARRAY'); + + foreach my $row (@{ $rec->{$fld} }) { + + if (ref($row) eq 'HASH') { + + foreach my $sf (keys %{ $row }) { + $self->{_stats}->{sf}->{ $fld }->{ $sf }->{count}++; + $self->{_stats}->{sf}->{ $fld }->{ $sf }->{repeatable}++ + if (ref($row->{$sf}) eq 'ARRAY'); } - } @{ $rec->{$fld} }; + + } else { + $self->{_stats}->{repeatable}->{ $fld }++; + } } - } keys %{ $rec }; + } } $self->progress_bar($pos,$to_rec) unless ($self->{no_progress_bar}); @@ -455,7 +502,10 @@ if (defined($s->{sf}->{$f})) { map { - $o .= sprintf(" %s:%d", $_, $s->{sf}->{$f}->{$_}); + $o .= sprintf(" %s:%d%s", $_, + $s->{sf}->{$f}->{$_}->{count}, + $s->{sf}->{$f}->{$_}->{repeatable} ? '*' : '', + ); } sort keys %{ $s->{sf}->{$f} }; } @@ -472,6 +522,51 @@ return $out; } +=head2 modify_record_regexps + +Generate hash with regexpes to be applied using L. + + my $regexpes = $input->modify_record_regexps( + 900 => { '^a' => { ' : ' => '^b' } }, + 901 => { '*' => { '^b' => ' ; ' } }, + ); + +=cut + +sub modify_record_regexps { + my $self = shift; + my $modify_record = {@_}; + + my $regexpes; + + foreach my $f (keys %$modify_record) { +warn "--- f: $f\n"; + foreach my $sf (keys %{ $modify_record->{$f} }) { +warn "---- sf: $sf\n"; + foreach my $from (keys %{ $modify_record->{$f}->{$sf} }) { + my $to = $modify_record->{$f}->{$sf}->{$from}; + #die "no field?" unless defined($to); +warn "----- transform: |$from| -> |$to|\n"; + + if ($sf =~ /^\^/) { + my $regex = + 's/\Q'. $sf .'\E([^\^]+)\Q'. $from .'\E([^\^]+)/'. $sf .'$1'. $to .'$2/g'; + push @{ $regexpes->{$f} }, $regex; +warn ">>>>> $regex [sf]\n"; + } else { + my $regex = + 's/\Q'. $from .'\E/'. $to .'/g'; + push @{ $regexpes->{$f} }, $regex; +warn ">>>>> $regex [global]\n"; + } + + } + } + } + + return $regexpes; +} + =head1 MEMORY USAGE C options is double-edged sword. If enabled, WebPAC