lib/WebPAC/Input.pm

package WebPAC::Input;

use warnings;
use strict;

use blib;

use WebPAC::Common;
use base qw/WebPAC::Common/;
use Data::Dump qw/dump/;
use Encode qw/from_to/;

=head1 NAME

WebPAC::Input - read different file formats into WebPAC

=head1 VERSION

Version 0.18

=cut

our $VERSION = '0.18';

=head1 SYNOPSIS

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 $db = WebPAC::Input->new(
                module => 'WebPAC::Input::ISIS',
        );

        $db->open( path => '/path/to/database' );
        print "database size: ",$db->size,"\n";
        while (my $rec = $db->fetch) {
                # do something with $rec
        }


=head1 FUNCTIONS

=head2 new

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,
  );

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.

C<no_progress_bar> disables progress bar output on C<STDOUT>

This function will also call low-level C<init> if it exists with same
parametars.

=cut

sub new {
        my $class = shift;
        my $self = {@_};
        bless($self, $class);

        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});

        $log->logconfess("specify low-level file format module") unless ($self->{module});
        my $module_path = $self->{module};
        $module_path =~ s#::#/#g;
        $module_path .= '.pm';
        $log->debug("require low-level module $self->{module} from $module_path");

        require $module_path;

        $self->{'encoding'} ||= 'ISO-8859-2';

        $self ? return $self : return undef;
}

=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',
        code_page => 'cp852',
        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<code_page> is assumed to be C<cp852>.

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

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.

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();

        $log->logconfess("lookup argument is not suppored any more. rewrite call to lookup_coderef") if ($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 $code_page = $arg->{'code_page'} || '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});
        }

        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;
                                $recode_map->{$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!");

        my $ll_db = $class->new(
                path => $arg->{path},
#               filter => sub {
#                       my ($l,$f_nr) = @_;
#                       return unless defined($l);
#                       from_to($l, $code_page, $self->{'encoding'});
#                       $l =~ s/($recode_regex)/$recode_map->{$1}/g if ($recode_regex && $recode_map);
#                       return $l;
#               },
                %{ $arg },
        );

        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("skipping to MFN $s");
                $from_rec = $s;
        } else {
                $self->{offset} = $from_rec;
        }

        if ($self->{limit}) {
                $log->debug("limiting to ",$self->{limit}," records");
                $to_rec = $from_rec + $self->{limit} - 1;
                $to_rec = $size if ($to_rec > $size);
        }

        # 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]' : '');

        # read database
        for (my $pos = $from_rec; $pos <= $to_rec; $pos++) {

                $log->debug("position: $pos\n");

                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) );

                                warn "-=> $f_nr ## |$l|\n" if ($debug);
                                $log->debug("-=> $f_nr ## $l");

                                # codepage conversion and recode_regex
                                from_to($l, $code_page, $self->{'encoding'});
                                $l =~ s/($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: $r") if ($@);
                                        }
                                }

                                $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 $fld, not ARRAY")
                                        unless (ref($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");

        # save for dump
        $self->{ll_db} = $ll_db;

        return $size;
}

=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};
        } 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};
}

=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})) {
                                map {
                                        $o .= sprintf(" %s:%d%s", $_, 
                                                $s->{sf}->{$f}->{$_}->{count},
                                                $s->{sf}->{$f}->{$_}->{repeatable} ? '*' : '',
                                        );
                                } sort keys %{ $s->{sf}->{$f} };
                        }

                        if (my $v_r = $s->{repeatable}->{$f}) {
                                $o .= " ($v_r)" if ($v_r != $v);
                        }

                        $o;
                } sort { $a <=> $b } keys %{ $s->{fld} }
        );

        $log->debug( sub { dump($s) } );

        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

Helper function called which create regexps to be execute on code.

  _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

sub _get_regex {
        my ($sf,$from,$to) = @_;

        # protect /
        $from =~ s!/!\\/!gs;
        $to =~ s!/!\\/!gs;

        if ($from =~ m/^regex:(.+)$/) {
                $from = $1;
        } else {
                $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([^\^]' . $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 = {@_};

        my $regexpes;

        my $log = $self->_get_logger();

        foreach my $f (keys %$modify_record) {
                $log->debug("field: $f");

                foreach my $sf (keys %{ $modify_record->{$f} }) {
                        $log->debug("subfield: $sf");

                        foreach my $from (keys %{ $modify_record->{$f}->{$sf} }) {
                                my $to = $modify_record->{$f}->{$sf}->{$from};
                                #die "no field?" unless defined($to);
                                my $d = "|$from| -> |$to|";
                                $log->debug("transform: $d");

                                my $regex = _get_regex($sf,$from,$to);
                                push @{ $regexpes->{$f} }, { regex => $regex, debug => $d };
                                $log->debug("regex: $regex");
                        }
                }
        }

        return $regexpes;
}

=head2 modify_file_regexps

Generate hash with regexpes to be applied using L<filter> from
pseudo hash/yaml format for regex mappings.

It should be obvious:

        200
          '^a'
            ' : ' => '^e'
            ' = ' => '^d'

In field I<200> find C<'^a'> and then C<' : '>, and replace it with C<'^e'>.
In field I<200> find C<'^a'> and then C<' = '>, and replace it with C<'^d'>.

  my $regexpes = $input->modify_file_regexps( 'conf/modify/common.pl' );

On undef path it will just return.

=cut

sub modify_file_regexps {
        my $self = shift;

        my $modify_path = shift || return;

        my $log = $self->_get_logger();

        my $regexpes;

        CORE::open(my $fh, $modify_path) || $log->logdie("can't open modify file $modify_path: $!");

        my ($f,$sf);

        while(<$fh>) {
                chomp;
                next if (/^#/ || /^\s*$/);

                if (/^\s*(\d+)\s*$/) {
                        $f = $1;
                        $log->debug("field: $f");
                        next;
                } elsif (/^\s*'([^']*)'\s*$/) {
                        $sf = $1;
                        $log->die("can't define subfiled before field in: $_") unless ($f);
                        $log->debug("subfield: $sf");
                } elsif (/^\s*'([^']*)'\s*=>\s*'([^']*)'\s*$/) {
                        my ($from,$to) = ($1, $2);

                        $log->debug("transform: |$from| -> |$to|");

                        my $regex = _get_regex($sf,$from,$to);
                        push @{ $regexpes->{$f} }, {
                                regex => $regex,
                                file => $modify_path,
                                line => $.,
                        };
                        $log->debug("regex: $regex");
                }
        }

        return $regexpes;
}

=head1 AUTHOR

Dobrica Pavlinusic, C<< <dpavlin@rot13.org> >>

=head1 COPYRIGHT & LICENSE

Copyright 2005-2006 Dobrica Pavlinusic, All Rights Reserved.

This program is free software; you can redistribute it and/or modify it
under the same terms as Perl itself.

=cut

1; # End of WebPAC::Input
1	dpavlin	1	package WebPAC::Input;
2
3			use warnings;
4			use strict;
5
6	dpavlin	507	use blib;
7
8	dpavlin	487	use WebPAC::Common;
9	dpavlin	285	use base qw/WebPAC::Common/;
10	dpavlin	771	use Data::Dump qw/dump/;
11	dpavlin	624	use Encode qw/from_to/;
12	dpavlin	285
13	dpavlin	1	=head1 NAME
14
15	dpavlin	286	WebPAC::Input - read different file formats into WebPAC
16	dpavlin	1
17			=head1 VERSION
18
19	dpavlin	823	Version 0.18
20	dpavlin	1
21			=cut
22
23	dpavlin	823	our $VERSION = '0.18';
24	dpavlin	1
25			=head1 SYNOPSIS
26
27	dpavlin	286	This module implements input as database which have fixed and known
28			I<size> while indexing and single unique numeric identifier for database
29			position ranging from 1 to I<size>.
30	dpavlin	1
31	dpavlin	286	Simply, something that is indexed by unmber from 1 .. I<size>.
32
33			Examples of such databases are CDS/ISIS files, MARC files, lines in
34			text file, and so on.
35
36			Specific file formats are implemented using low-level interface modules,
37			located in C<WebPAC::Input::*> namespace which export C<open_db>,
38			C<fetch_rec> and optional C<init> functions.
39
40	dpavlin	1	Perhaps a little code snippet.
41
42	dpavlin	597	use WebPAC::Input;
43	dpavlin	1
44	dpavlin	597	my $db = WebPAC::Input->new(
45			module => 'WebPAC::Input::ISIS',
46			);
47	dpavlin	1
48	dpavlin	597	$db->open( path => '/path/to/database' );
49	dpavlin	416	print "database size: ",$db->size,"\n";
50			while (my $rec = $db->fetch) {
51			# do something with $rec
52			}
53	dpavlin	1
54	dpavlin	286
55
56	dpavlin	1	=head1 FUNCTIONS
57
58	dpavlin	3	=head2 new
59	dpavlin	1
60	dpavlin	3	Create new input database object.
61
62	dpavlin	9	my $db = new WebPAC::Input(
63	dpavlin	286	module => 'WebPAC::Input::MARC',
64	dpavlin	585	encoding => 'ISO-8859-2',
65	dpavlin	416	recode => 'char pairs',
66	dpavlin	483	no_progress_bar => 1,
67	dpavlin	9	);
68	dpavlin	3
69	dpavlin	597	C<module> is low-level file format module. See L<WebPAC::Input::ISIS> and
70	dpavlin	286	L<WebPAC::Input::MARC>.
71
72	dpavlin	585	Optional parametar C<encoding> specify application code page (which will be
73	dpavlin	9	used internally). This should probably be your terminal encoding, and by
74			default, it C<ISO-8859-2>.
75
76	dpavlin	483	C<recode> is optional string constisting of character or words pairs that
77			should be replaced in input stream.
78
79			C<no_progress_bar> disables progress bar output on C<STDOUT>
80
81	dpavlin	285	This function will also call low-level C<init> if it exists with same
82			parametars.
83
84	dpavlin	1	=cut
85
86	dpavlin	3	sub new {
87	dpavlin	285	my $class = shift;
88			my $self = {@_};
89	dpavlin	3	bless($self, $class);
90
91	dpavlin	285	my $log = $self->_get_logger;
92
93	dpavlin	585	$log->logconfess("code_page argument is not suppored any more. change it to encoding") if ($self->{lookup});
94			$log->logconfess("lookup argument is not suppored any more. rewrite call to lookup_ref") if ($self->{lookup});
95	dpavlin	761	$log->logconfess("low_mem argument is not suppored any more. rewrite it to load_row and save_row") if ($self->{low_mem});
96	dpavlin	585
97	dpavlin	286	$log->logconfess("specify low-level file format module") unless ($self->{module});
98	dpavlin	726	my $module_path = $self->{module};
99			$module_path =~ s#::#/#g;
100			$module_path .= '.pm';
101			$log->debug("require low-level module $self->{module} from $module_path");
102	dpavlin	289
103	dpavlin	726	require $module_path;
104	dpavlin	286
105	dpavlin	585	$self->{'encoding'} \|\|= 'ISO-8859-2';
106	dpavlin	9
107	dpavlin	3	$self ? return $self : return undef;
108	dpavlin	1	}
109
110	dpavlin	285	=head2 open
111
112			This function will read whole database in memory and produce lookups.
113
114	dpavlin	761	my $store; # simple in-memory hash
115
116	dpavlin	286	$input->open(
117	dpavlin	285	path => '/path/to/database/file',
118	dpavlin	624	code_page => 'cp852',
119	dpavlin	286	limit => 500,
120			offset => 6000,
121	dpavlin	506	stats => 1,
122	dpavlin	707	lookup_coderef => sub {
123			my $rec = shift;
124			# store lookups
125	dpavlin	585	},
126	dpavlin	597	modify_records => {
127			900 => { '^a' => { ' : ' => '^b' } },
128			901 => { '*' => { '^b' => ' ; ' } },
129			},
130	dpavlin	636	modify_file => 'conf/modify/mapping.map',
131	dpavlin	761	save_row => sub {
132			my $a = shift;
133			$store->{ $a->{id} } = $a->{row};
134			},
135			load_row => sub {
136			my $a = shift;
137			return defined($store->{ $a->{id} }) &&
138			$store->{ $a->{id} };
139			},
140
141	dpavlin	285	);
142
143	dpavlin	624	By default, C<code_page> is assumed to be C<cp852>.
144	dpavlin	285
145	dpavlin	286	C<offset> is optional parametar to position at some offset before reading from database.
146	dpavlin	285
147	dpavlin	286	C<limit> is optional parametar to read just C<limit> records from database
148	dpavlin	285
149	dpavlin	506	C<stats> create optional report about usage of fields and subfields
150
151	dpavlin	707	C<lookup_coderef> is closure to called to save data into lookups
152	dpavlin	585
153	dpavlin	597	C<modify_records> specify mapping from subfields to delimiters or from
154			delimiters to subfields, as well as oprations on fields (if subfield is
155			defined as C<*>.
156
157	dpavlin	636	C<modify_file> is alternative for C<modify_records> above which preserves order and offers
158			(hopefully) simplier sintax than YAML or perl (see L</modify_file_regex>). This option
159			overrides C<modify_records> if both exists for same input.
160
161	dpavlin	761	C<save_row> and C<load_row> are low-level implementation of store engine. Calling convention
162			is documented in example above.
163
164	dpavlin	286	Returns size of database, regardless of C<offset> and C<limit>
165			parametars, see also C<size>.
166	dpavlin	285
167			=cut
168
169			sub open {
170			my $self = shift;
171			my $arg = {@_};
172
173			my $log = $self->_get_logger();
174
175	dpavlin	585	$log->logconfess("lookup argument is not suppored any more. rewrite call to lookup_coderef") if ($arg->{lookup});
176			$log->logconfess("lookup_coderef must be CODE, not ",ref($arg->{lookup_coderef}))
177			if ($arg->{lookup_coderef} && ref($arg->{lookup_coderef}) ne 'CODE');
178
179	dpavlin	707	$log->debug( $arg->{lookup_coderef} ? '' : 'not ', "using lookup_coderef");
180
181	dpavlin	285	$log->logcroak("need path") if (! $arg->{'path'});
182	dpavlin	624	my $code_page = $arg->{'code_page'} \|\| 'cp852';
183	dpavlin	285
184			# store data in object
185	dpavlin	292	$self->{'input_code_page'} = $code_page;
186	dpavlin	286	foreach my $v (qw/path offset limit/) {
187	dpavlin	285	$self->{$v} = $arg->{$v} if ($arg->{$v});
188			}
189
190	dpavlin	761	if ($arg->{load_row} \|\| $arg->{save_row}) {
191			$log->logconfess("save_row and load_row must be defined in pair and be CODE") unless (
192			ref($arg->{load_row}) eq 'CODE' &&
193			ref($arg->{save_row}) eq 'CODE'
194			);
195			$self->{load_row} = $arg->{load_row};
196			$self->{save_row} = $arg->{save_row};
197			$log->debug("using load_row and save_row instead of in-memory hash");
198			}
199
200	dpavlin	416	my $filter_ref;
201	dpavlin	597	my $recode_regex;
202			my $recode_map;
203	dpavlin	416
204			if ($self->{recode}) {
205			my @r = split(/\s/, $self->{recode});
206			if ($#r % 2 != 1) {
207			$log->logwarn("recode needs even number of elements (some number of valid pairs)");
208			} else {
209			while (@r) {
210			my $from = shift @r;
211			my $to = shift @r;
212	dpavlin	597	$recode_map->{$from} = $to;
213	dpavlin	416	}
214
215	dpavlin	597	$recode_regex = join '\|' => keys %{ $recode_map };
216	dpavlin	416
217	dpavlin	597	$log->debug("using recode regex: $recode_regex");
218	dpavlin	416	}
219
220			}
221
222	dpavlin	636	my $rec_regex;
223			if (my $p = $arg->{modify_file}) {
224			$log->debug("using modify_file $p");
225			$rec_regex = $self->modify_file_regexps( $p );
226			} elsif (my $h = $arg->{modify_records}) {
227	dpavlin	771	$log->debug("using modify_records ", sub { dump( $h ) });
228	dpavlin	636	$rec_regex = $self->modify_record_regexps(%{ $h });
229			}
230	dpavlin	771	$log->debug("rec_regex: ", sub { dump($rec_regex) }) if ($rec_regex);
231	dpavlin	597
232	dpavlin	726	my $class = $self->{module} \|\| $log->logconfess("can't get low-level module name!");
233
234			my $ll_db = $class->new(
235	dpavlin	285	path => $arg->{path},
236	dpavlin	624	# filter => sub {
237			# my ($l,$f_nr) = @_;
238			# return unless defined($l);
239			# from_to($l, $code_page, $self->{'encoding'});
240			# $l =~ s/($recode_regex)/$recode_map->{$1}/g if ($recode_regex && $recode_map);
241			# return $l;
242			# },
243	dpavlin	523	%{ $arg },
244	dpavlin	285	);
245
246	dpavlin	726	unless (defined($ll_db)) {
247	dpavlin	285	$log->logwarn("can't open database $arg->{path}, skipping...");
248			return;
249			}
250
251	dpavlin	726	my $size = $ll_db->size;
252
253	dpavlin	285	unless ($size) {
254			$log->logwarn("no records in database $arg->{path}, skipping...");
255			return;
256			}
257
258	dpavlin	339	my $from_rec = 1;
259			my $to_rec = $size;
260	dpavlin	285
261	dpavlin	286	if (my $s = $self->{offset}) {
262	dpavlin	513	$log->debug("skipping to MFN $s");
263	dpavlin	339	$from_rec = $s;
264	dpavlin	285	} else {
265	dpavlin	339	$self->{offset} = $from_rec;
266	dpavlin	285	}
267
268	dpavlin	286	if ($self->{limit}) {
269	dpavlin	301	$log->debug("limiting to ",$self->{limit}," records");
270	dpavlin	339	$to_rec = $from_rec + $self->{limit} - 1;
271			$to_rec = $size if ($to_rec > $size);
272	dpavlin	285	}
273
274			# store size for later
275	dpavlin	339	$self->{size} = ($to_rec - $from_rec) ? ($to_rec - $from_rec + 1) : 0;
276	dpavlin	285
277	dpavlin	585	$log->info("processing $self->{size}/$size records [$from_rec-$to_rec] convert $code_page -> $self->{encoding}", $self->{stats} ? ' [stats]' : '');
278	dpavlin	285
279			# read database
280	dpavlin	339	for (my $pos = $from_rec; $pos <= $to_rec; $pos++) {
281	dpavlin	285
282	dpavlin	286	$log->debug("position: $pos\n");
283	dpavlin	285
284	dpavlin	726	my $rec = $ll_db->fetch_rec($pos, sub {
285	dpavlin	799	my ($l,$f_nr,$debug) = @_;
286	dpavlin	624	# return unless defined($l);
287			# return $l unless ($rec_regex && $f_nr);
288	dpavlin	285
289	dpavlin	818	return unless ( defined($l) && defined($f_nr) );
290
291	dpavlin	800	warn "-=> $f_nr ## \|$l\|\n" if ($debug);
292	dpavlin	625	$log->debug("-=> $f_nr ## $l");
293
294	dpavlin	624	# codepage conversion and recode_regex
295	dpavlin	626	from_to($l, $code_page, $self->{'encoding'});
296	dpavlin	624	$l =~ s/($recode_regex)/$recode_map->{$1}/g if ($recode_regex && $recode_map);
297
298	dpavlin	619	# apply regexps
299			if ($rec_regex && defined($rec_regex->{$f_nr})) {
300			$log->logconfess("regexps->{$f_nr} must be ARRAY") if (ref($rec_regex->{$f_nr}) ne 'ARRAY');
301			my $c = 0;
302			foreach my $r (@{ $rec_regex->{$f_nr} }) {
303	dpavlin	626	my $old_l = $l;
304	dpavlin	800	$log->logconfess("expected regex in ", dump( $r )) unless defined($r->{regex});
305			eval '$l =~ ' . $r->{regex};
306	dpavlin	626	if ($old_l ne $l) {
307	dpavlin	800	my $d = "\|$old_l\| -> \|$l\| "; # . $r->{regex};
308			$d .= ' +' . $r->{line} . ' ' . $r->{file} if defined($r->{line});
309			$d .= ' ' . $r->{debug} if defined($r->{debug});
310			$log->debug("MODIFY $d");
311			warn "*** $d\n" if ($debug);
312
313	dpavlin	626	}
314	dpavlin	619	$log->error("error applying regex: $r") if ($@);
315			}
316			}
317
318	dpavlin	800	$log->debug("<=- $f_nr ## \|$l\|");
319	dpavlin	799	warn "<=- $f_nr ## $l\n" if ($debug);
320	dpavlin	619	return $l;
321			});
322
323	dpavlin	771	$log->debug(sub { dump($rec) });
324	dpavlin	308
325	dpavlin	285	if (! $rec) {
326	dpavlin	286	$log->warn("record $pos empty? skipping...");
327	dpavlin	285	next;
328			}
329
330			# store
331	dpavlin	761	if ($self->{save_row}) {
332			$self->{save_row}->({
333			id => $pos,
334			row => $rec,
335			});
336	dpavlin	285	} else {
337	dpavlin	286	$self->{data}->{$pos} = $rec;
338	dpavlin	285	}
339
340			# create lookup
341	dpavlin	585	$arg->{'lookup_coderef'}->( $rec ) if ($rec && $arg->{'lookup_coderef'});
342	dpavlin	285
343	dpavlin	506	# update counters for statistics
344			if ($self->{stats}) {
345	dpavlin	593
346	dpavlin	619	# fetch clean record with regexpes applied for statistics
347	dpavlin	726	my $rec = $ll_db->fetch_rec($pos);
348	dpavlin	619
349	dpavlin	593	foreach my $fld (keys %{ $rec }) {
350	dpavlin	506	$self->{_stats}->{fld}->{ $fld }++;
351	dpavlin	593
352			$log->logdie("invalid record fild $fld, not ARRAY")
353			unless (ref($rec->{ $fld }) eq 'ARRAY');
354
355			foreach my $row (@{ $rec->{$fld} }) {
356
357			if (ref($row) eq 'HASH') {
358
359			foreach my $sf (keys %{ $row }) {
360	dpavlin	619	next if ($sf eq 'subfields');
361	dpavlin	593	$self->{_stats}->{sf}->{ $fld }->{ $sf }->{count}++;
362			$self->{_stats}->{sf}->{ $fld }->{ $sf }->{repeatable}++
363			if (ref($row->{$sf}) eq 'ARRAY');
364	dpavlin	506	}
365	dpavlin	593
366			} else {
367			$self->{_stats}->{repeatable}->{ $fld }++;
368			}
369	dpavlin	506	}
370	dpavlin	593	}
371	dpavlin	506	}
372
373	dpavlin	483	$self->progress_bar($pos,$to_rec) unless ($self->{no_progress_bar});
374	dpavlin	285
375			}
376
377	dpavlin	286	$self->{pos} = -1;
378			$self->{last_pcnt} = 0;
379	dpavlin	285
380			# store max mfn and return it.
381	dpavlin	339	$self->{max_pos} = $to_rec;
382			$log->debug("max_pos: $to_rec");
383	dpavlin	285
384	dpavlin	757	# save for dump
385			$self->{ll_db} = $ll_db;
386
387	dpavlin	285	return $size;
388			}
389
390			=head2 fetch
391
392			Fetch next record from database. It will also displays progress bar.
393
394			my $rec = $isis->fetch;
395
396			Record from this function should probably go to C<data_structure> for
397			normalisation.
398
399			=cut
400
401			sub fetch {
402			my $self = shift;
403
404			my $log = $self->_get_logger();
405
406	dpavlin	286	$log->logconfess("it seems that you didn't load database!") unless ($self->{pos});
407	dpavlin	285
408	dpavlin	286	if ($self->{pos} == -1) {
409			$self->{pos} = $self->{offset};
410	dpavlin	285	} else {
411	dpavlin	286	$self->{pos}++;
412	dpavlin	285	}
413
414	dpavlin	286	my $mfn = $self->{pos};
415	dpavlin	285
416	dpavlin	286	if ($mfn > $self->{max_pos}) {
417			$self->{pos} = $self->{max_pos};
418	dpavlin	285	$log->debug("at EOF");
419			return;
420			}
421
422	dpavlin	483	$self->progress_bar($mfn,$self->{max_pos}) unless ($self->{no_progress_bar});
423	dpavlin	285
424			my $rec;
425
426	dpavlin	761	if ($self->{load_row}) {
427			$rec = $self->{load_row}->({ id => $mfn });
428	dpavlin	285	} else {
429	dpavlin	286	$rec = $self->{data}->{$mfn};
430	dpavlin	285	}
431
432			$rec \|\|= 0E0;
433			}
434
435			=head2 pos
436
437			Returns current record number (MFN).
438
439			print $isis->pos;
440
441			First record in database has position 1.
442
443			=cut
444
445			sub pos {
446			my $self = shift;
447	dpavlin	286	return $self->{pos};
448	dpavlin	285	}
449
450
451			=head2 size
452
453			Returns number of records in database
454
455			print $isis->size;
456
457			Result from this function can be used to loop through all records
458
459			foreach my $mfn ( 1 ... $isis->size ) { ... }
460
461	dpavlin	286	because it takes into account C<offset> and C<limit>.
462	dpavlin	285
463			=cut
464
465			sub size {
466			my $self = shift;
467	dpavlin	286	return $self->{size};
468	dpavlin	285	}
469
470			=head2 seek
471
472			Seek to specified MFN in file.
473
474			$isis->seek(42);
475
476			First record in database has position 1.
477
478			=cut
479
480			sub seek {
481			my $self = shift;
482	dpavlin	793	my $pos = shift;
483	dpavlin	285
484			my $log = $self->_get_logger();
485
486	dpavlin	797	$log->logconfess("called without pos") unless defined($pos);
487	dpavlin	793
488	dpavlin	285	if ($pos < 1) {
489			$log->warn("seek before first record");
490			$pos = 1;
491	dpavlin	286	} elsif ($pos > $self->{max_pos}) {
492	dpavlin	285	$log->warn("seek beyond last record");
493	dpavlin	286	$pos = $self->{max_pos};
494	dpavlin	285	}
495
496	dpavlin	286	return $self->{pos} = (($pos - 1) \|\| -1);
497	dpavlin	285	}
498
499	dpavlin	506	=head2 stats
500	dpavlin	285
501	dpavlin	506	Dump statistics about field and subfield usage
502
503	dpavlin	507	print $input->stats;
504	dpavlin	506
505			=cut
506
507			sub stats {
508			my $self = shift;
509	dpavlin	507
510			my $log = $self->_get_logger();
511
512			my $s = $self->{_stats};
513			if (! $s) {
514			$log->warn("called stats, but there is no statistics collected");
515			return;
516			}
517
518			my $max_fld = 0;
519
520			my $out = join("\n",
521			map {
522	dpavlin	844	my $f = $_;
523			die "no field in ", dump( $s->{fld} ) unless defined( $f );
524	dpavlin	507	my $v = $s->{fld}->{$f} \|\| die "no s->{fld}->{$f}";
525			$max_fld = $v if ($v > $max_fld);
526
527	dpavlin	519	my $o = sprintf("%4s %d ~", $f, $v);
528	dpavlin	507
529			if (defined($s->{sf}->{$f})) {
530			map {
531	dpavlin	593	$o .= sprintf(" %s:%d%s", $_,
532			$s->{sf}->{$f}->{$_}->{count},
533			$s->{sf}->{$f}->{$_}->{repeatable} ? '*' : '',
534			);
535	dpavlin	507	} sort keys %{ $s->{sf}->{$f} };
536			}
537
538			if (my $v_r = $s->{repeatable}->{$f}) {
539			$o .= " ($v_r)" if ($v_r != $v);
540			}
541
542			$o;
543	dpavlin	855	} sort { $a <=> $b } keys %{ $s->{fld} }
544	dpavlin	507	);
545
546	dpavlin	771	$log->debug( sub { dump($s) } );
547	dpavlin	507
548			return $out;
549	dpavlin	506	}
550
551	dpavlin	774	=head2 dump_ascii
552	dpavlin	652
553			Display humanly readable dump of record
554
555			=cut
556
557	dpavlin	774	sub dump_ascii {
558	dpavlin	652	my $self = shift;
559
560	dpavlin	771	return unless $self->{ll_db};
561	dpavlin	652
562	dpavlin	860	if ($self->{ll_db}->can('dump_ascii')) {
563	dpavlin	774	return $self->{ll_db}->dump_ascii( $self->{pos} );
564	dpavlin	771	} else {
565			return dump( $self->{ll_db}->fetch_rec( $self->{pos} ) );
566			}
567	dpavlin	652	}
568
569	dpavlin	823	=head2 _get_regex
570	dpavlin	597
571	dpavlin	823	Helper function called which create regexps to be execute on code.
572	dpavlin	597
573	dpavlin	823	_get_regex( 900, 'regex:[0-9]+' ,'numbers' );
574			_get_regex( 900, '^b', ' : ^b' );
575	dpavlin	597
576	dpavlin	823	It supports perl regexps with C<regex:> prefix to from value and has
577			additional logic to skip empty subfields.
578
579	dpavlin	597	=cut
580
581	dpavlin	636	sub _get_regex {
582			my ($sf,$from,$to) = @_;
583	dpavlin	797
584			# protect /
585			$from =~ s!/!\\/!gs;
586			$to =~ s!/!\\/!gs;
587
588	dpavlin	784	if ($from =~ m/^regex:(.+)$/) {
589			$from = $1;
590			} else {
591			$from = '\Q' . $from . '\E';
592			}
593	dpavlin	636	if ($sf =~ /^\^/) {
594	dpavlin	823	my $need_subfield_data = '*'; # no
595			# if from is also subfield, require some data in between
596			# to correctly skip empty subfields
597			$need_subfield_data = '+' if ($from =~ m/^\\Q\^/);
598	dpavlin	636	return
599	dpavlin	823	's/\Q'. $sf .'\E([^\^]' . $need_subfield_data . '?)'. $from .'([^\^]*?)/'. $sf .'$1'. $to .'$2/';
600	dpavlin	636	} else {
601			return
602	dpavlin	784	's/'. $from .'/'. $to .'/g';
603	dpavlin	636	}
604			}
605
606	dpavlin	823
607			=head2 modify_record_regexps
608
609			Generate hash with regexpes to be applied using L<filter>.
610
611			my $regexpes = $input->modify_record_regexps(
612			900 => { '^a' => { ' : ' => '^b' } },
613			901 => { '*' => { '^b' => ' ; ' } },
614			);
615
616			=cut
617
618	dpavlin	597	sub modify_record_regexps {
619			my $self = shift;
620			my $modify_record = {@_};
621
622			my $regexpes;
623
624	dpavlin	634	my $log = $self->_get_logger();
625
626	dpavlin	597	foreach my $f (keys %$modify_record) {
627	dpavlin	634	$log->debug("field: $f");
628
629	dpavlin	597	foreach my $sf (keys %{ $modify_record->{$f} }) {
630	dpavlin	634	$log->debug("subfield: $sf");
631
632	dpavlin	597	foreach my $from (keys %{ $modify_record->{$f}->{$sf} }) {
633			my $to = $modify_record->{$f}->{$sf}->{$from};
634			#die "no field?" unless defined($to);
635	dpavlin	800	my $d = "\|$from\| -> \|$to\|";
636			$log->debug("transform: $d");
637	dpavlin	597
638	dpavlin	636	my $regex = _get_regex($sf,$from,$to);
639	dpavlin	800	push @{ $regexpes->{$f} }, { regex => $regex, debug => $d };
640	dpavlin	636	$log->debug("regex: $regex");
641	dpavlin	597	}
642			}
643			}
644
645			return $regexpes;
646			}
647
648	dpavlin	636	=head2 modify_file_regexps
649
650	dpavlin	799	Generate hash with regexpes to be applied using L<filter> from
651	dpavlin	636	pseudo hash/yaml format for regex mappings.
652
653			It should be obvious:
654
655			200
656			'^a'
657			' : ' => '^e'
658			' = ' => '^d'
659
660			In field I<200> find C<'^a'> and then C<' : '>, and replace it with C<'^e'>.
661			In field I<200> find C<'^a'> and then C<' = '>, and replace it with C<'^d'>.
662
663			my $regexpes = $input->modify_file_regexps( 'conf/modify/common.pl' );
664
665			On undef path it will just return.
666
667			=cut
668
669			sub modify_file_regexps {
670			my $self = shift;
671
672			my $modify_path = shift \|\| return;
673
674			my $log = $self->_get_logger();
675
676			my $regexpes;
677
678	dpavlin	697	CORE::open(my $fh, $modify_path) \|\| $log->logdie("can't open modify file $modify_path: $!");
679	dpavlin	636
680			my ($f,$sf);
681
682			while(<$fh>) {
683			chomp;
684			next if (/^#/ \|\| /^\s*$/);
685
686			if (/^\s(\d+)\s$/) {
687			$f = $1;
688			$log->debug("field: $f");
689			next;
690			} elsif (/^\s'([^'])'\s*$/) {
691			$sf = $1;
692			$log->die("can't define subfiled before field in: $_") unless ($f);
693			$log->debug("subfield: $sf");
694			} elsif (/^\s'([^'])'\s=>\s'([^'])'\s$/) {
695			my ($from,$to) = ($1, $2);
696
697			$log->debug("transform: \|$from\| -> \|$to\|");
698
699			my $regex = _get_regex($sf,$from,$to);
700	dpavlin	800	push @{ $regexpes->{$f} }, {
701			regex => $regex,
702			file => $modify_path,
703			line => $.,
704			};
705	dpavlin	636	$log->debug("regex: $regex");
706			}
707			}
708
709			return $regexpes;
710			}
711
712	dpavlin	3	=head1 AUTHOR
713
714			Dobrica Pavlinusic, C<< <dpavlin@rot13.org> >>
715
716	dpavlin	1	=head1 COPYRIGHT & LICENSE
717
718	dpavlin	599	Copyright 2005-2006 Dobrica Pavlinusic, All Rights Reserved.
719	dpavlin	1
720			This program is free software; you can redistribute it and/or modify it
721			under the same terms as Perl itself.
722
723			=cut
724
725			1; # End of WebPAC::Input