+=head2 open
+
+This function will read whole database in memory and produce lookups.
+
+ my $store; # simple in-memory hash
+
+ $input->open(
+ path => '/path/to/database/file',
+ input_encoding => 'cp852',
+ strict_encoding => 0,
+ limit => 500,
+ offset => 6000,
+ stats => 1,
+ lookup_coderef => sub {
+ my $rec = shift;
+ # store lookups
+ },
+ modify_records => {
+ 900 => { '^a' => { ' : ' => '^b' } },
+ 901 => { '*' => { '^b' => ' ; ' } },
+ },
+ modify_file => 'conf/modify/mapping.map',
+ save_row => sub {
+ my $a = shift;
+ $store->{ $a->{id} } = $a->{row};
+ },
+ load_row => sub {
+ my $a = shift;
+ return defined($store->{ $a->{id} }) &&
+ $store->{ $a->{id} };
+ },
+
+ );
+
+By default, C<input_encoding> is assumed to be C<cp852>.
+
+C<offset> is optional parametar to skip records at beginning.
+
+C<limit> is optional parametar to read just C<limit> records from database
+
+C<stats> create optional report about usage of fields and subfields
+
+C<lookup_coderef> is closure to called to save data into lookups
+
+C<modify_records> specify mapping from subfields to delimiters or from
+delimiters to subfields, as well as oprations on fields (if subfield is
+defined as C<*>.
+
+C<modify_file> is alternative for C<modify_records> above which preserves order and offers
+(hopefully) simplier sintax than YAML or perl (see L</modify_file_regex>). This option
+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>.
+
+=cut
+
+sub open {
+ my $self = shift;
+ 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');
+
+ $log->debug( $arg->{lookup_coderef} ? '' : 'not ', "using lookup_coderef");
+
+ $log->logcroak("need path") if (! $arg->{'path'});
+ my $input_encoding = $arg->{'input_encoding'} || $self->{'input_encoding'} || 'cp852';
+
+ # store data in object
+ $self->{$_} = $arg->{$_} foreach grep { defined $arg->{$_} } qw(path offset limit);
+
+ if ($arg->{load_row} || $arg->{save_row}) {
+ $log->logconfess("save_row and load_row must be defined in pair and be CODE") unless (
+ ref($arg->{load_row}) eq 'CODE' &&
+ ref($arg->{save_row}) eq 'CODE'
+ );
+ $self->{load_row} = $arg->{load_row};
+ $self->{save_row} = $arg->{save_row};
+ $log->debug("using load_row and save_row instead of in-memory hash");
+ }
+
+ 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 {
+ while (@r) {
+ my $from = shift @r;
+ my $to = shift @r;
+ $from =~ s/^\\x([0-9a-f]{2})/chr(hex($1))/eig;
+ $recode_map->{$from} = $to;
+ }
+
+ $recode_regex = join '|' => keys %{ $recode_map };
+
+ $log->debug("using recode regex: $recode_regex");
+ }
+
+ }
+
+ my $rec_regex;
+ if (my $p = $arg->{modify_file}) {
+ $log->debug("using modify_file $p");
+ $rec_regex = $self->modify_file_regexps( $p );
+ } elsif (my $h = $arg->{modify_records}) {
+ $log->debug("using modify_records ", sub { dump( $h ) });
+ $rec_regex = $self->modify_record_regexps(%{ $h });
+ }
+ $log->debug("rec_regex: ", sub { dump($rec_regex) }) if ($rec_regex);
+
+ 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);
+# $l = decode($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;
+ }
+
+ my $size = $ll_db->size;
+
+ unless ($size) {
+ $log->logwarn("no records in database $arg->{path}, skipping...");
+ return;
+ }
+
+ my $from_rec = 1;
+ my $to_rec = $size;
+
+ if (my $s = $self->{offset}) {
+ $log->debug("offset $s records");
+ $from_rec = $s + 1;
+ } else {
+ $self->{offset} = $from_rec - 1;
+ }
+
+ if ($self->{limit}) {
+ $log->debug("limiting to ",$self->{limit}," records");
+ $to_rec = $from_rec + $self->{limit} - 1;
+ $to_rec = $size if ($to_rec > $size);
+ }
+
+ my $strict_encoding = $arg->{strict_encoding} || $self->{strict_encoding}; ## FIXME should be 1 really
+
+ $log->info("processing ", $self->{size} || 'all', "/$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);
+# return $l unless ($rec_regex && $f_nr);
+
+ return unless ( defined($l) && defined($f_nr) );
+
+ my $marc_subfields = $l =~ s/\x1F(\w)/\^$1/g; # fix MARC subfiled delimiters to ^
+
+ warn "-=> $f_nr ## |$l|\n" if ($debug);
+ $log->debug("-=> $f_nr ## $l");
+
+ # codepage conversion and recode_regex
+ $l = decode($input_encoding, $l, 1);
+ $l =~ s/($recode_regex)/$recode_map->{$1}/g if ($recode_regex && $recode_map);
+
+ # apply regexps
+ if ($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} }) {
+ my $old_l = $l;
+ $log->logconfess("expected regex in ", dump( $r )) unless defined($r->{regex});
+ eval '$l =~ ' . $r->{regex};
+ if ($old_l ne $l) {
+ 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);
+
+ }
+ $log->error("error applying regex: ",dump($r), $@) if $@;
+ }
+ }
+
+ $l =~ s/\^(\w)/\x1F$1/g if $marc_subfields;
+
+ $log->debug("<=- $f_nr ## |$l|");
+ warn "<=- $f_nr ## $l\n" if ($debug);
+ return $l;
+ });
+
+ $log->debug(sub { dump($rec) });
+
+ if (! $rec) {
+ $log->warn("record $pos empty? skipping...");
+ next;
+ }
+
+ # store
+ if ($self->{save_row}) {
+ $self->{save_row}->({
+ id => $pos,
+ row => $rec,
+ });
+ } else {
+ $self->{data}->{$pos} = $rec;
+ }
+
+ # create lookup
+ $arg->{'lookup_coderef'}->( $rec ) if ($rec && $arg->{'lookup_coderef'});
+
+ # update counters for statistics
+ if ($self->{stats}) {
+
+ # fetch clean record with regexpes applied for statistics
+ my $rec = $ll_db->fetch_rec($pos);
+
+ foreach my $fld (keys %{ $rec }) {
+ $self->{_stats}->{fld}->{ $fld }++;
+
+ #$log->logdie("invalid record fild $fld, not ARRAY")
+ next unless (ref($rec->{ $fld }) eq 'ARRAY');
+
+ foreach my $row (@{ $rec->{$fld} }) {
+
+ if (ref($row) eq 'HASH') {
+
+ foreach my $sf (keys %{ $row }) {
+ next if ($sf eq 'subfields');
+ $self->{_stats}->{sf}->{ $fld }->{ $sf }->{count}++;
+ $self->{_stats}->{sf}->{ $fld }->{ $sf }->{repeatable}++
+ if (ref($row->{$sf}) eq 'ARRAY');
+ }
+
+ } else {
+ $self->{_stats}->{repeatable}->{ $fld }++;
+ }
+ }
+ }
+ }
+
+ $self->progress_bar($pos,$to_rec) unless ($self->{no_progress_bar});
+
+ }
+
+ $self->{pos} = -1;
+ $self->{last_pcnt} = 0;
+
+ # store max mfn and return it.
+ $self->{max_pos} = $to_rec;
+ $log->debug("max_pos: $to_rec");
+
+ return $size;
+}
+
+sub input_module { $_[0]->{ll_db} }
+
+=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} + 1;
+ } 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,$self->{max_pos}) unless ($self->{no_progress_bar});
+
+ my $rec;
+
+ if ($self->{load_row}) {
+ $rec = $self->{load_row}->({ id => $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}; # FIXME this is buggy if open is called multiple times!
+}
+
+=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;
+
+ my $log = $self->_get_logger();
+
+ $log->logconfess("called without pos") unless defined($pos);
+
+ 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);
+}
+
+=head2 stats
+
+Dump statistics about field and subfield usage
+
+ print $input->stats;
+
+=cut
+
+sub stats {
+ my $self = shift;
+
+ my $log = $self->_get_logger();
+
+ my $s = $self->{_stats};
+ if (! $s) {
+ $log->warn("called stats, but there is no statistics collected");
+ return;
+ }
+
+ my $max_fld = 0;
+
+ my $out = join("\n",
+ map {
+ 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}->{$_}->{repeatable} ? '*' : '',
+ );
+ } (
+ # first indicators and other special subfields
+ sort( grep { length($_) > 1 } @subfields ),
+ # then subfileds (single char)
+ sort( grep { length($_) == 1 } @subfields ),
+ );
+ }
+
+ if (my $v_r = $s->{repeatable}->{$f}) {
+ $o .= " ($v_r)" if ($v_r != $v);
+ }
+
+ $o;
+ } 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;
+}
+
+=head2 dump_ascii
+
+Display humanly readable dump of record
+
+=cut
+
+sub dump_ascii {
+ my $self = shift;
+
+ return unless $self->{ll_db};
+
+ if ($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 _get_regex