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 0.17

=cut

our $VERSION = '0.17';

=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) = @_;
#                               return unless defined($l);
#                               return $l unless ($rec_regex && $f_nr);

                                $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 = $l;
                                                eval '$l =~ ' . $r;
                                                if ($old_l ne $l) {
                                                        $log->debug("REGEX on $f_nr eval \$l =~ $r\n## old l: [$old_l]\n## new l: [$l]");
                                                }
                                                $log->error("error applying regex: $r") if ($@);
                                        }
                                }

                                $log->debug("<=- $f_nr ## $l");
                                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();

        $log->confess("called without pos") unless defined($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";
                        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 cmp $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_rec')) {
                return $self->{ll_db}->dump_ascii( $self->{pos} );
        } else {
                return dump( $self->{ll_db}->fetch_rec( $self->{pos} ) );
        }
}

=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 _get_regex {
        my ($sf,$from,$to) = @_;
        if ($from =~ m/^regex:(.+)$/) {
                $from = $1;
        } else {
                $from = '\Q' . $from . '\E';
        }
        if ($sf =~ /^\^/) {
                return
                        's/\Q'. $sf .'\E([^\^]*?)'. $from .'([^\^]*?)/'. $sf .'$1'. $to .'$2/';
        } else {
                return
                        's/'. $from .'/'. $to .'/g';
        }
}

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

                                my $regex = _get_regex($sf,$from,$to);
                                push @{ $regexpes->{$f} }, $regex;
                                $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;
                        $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	793	Version 0.17
20	dpavlin	1
21			=cut
22
23	dpavlin	793	our $VERSION = '0.17';
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	619	my ($l,$f_nr) = @_;
286	dpavlin	624	# return unless defined($l);
287			# return $l unless ($rec_regex && $f_nr);
288	dpavlin	285
289	dpavlin	625	$log->debug("-=> $f_nr ## $l");
290
291	dpavlin	624	# codepage conversion and recode_regex
292	dpavlin	626	from_to($l, $code_page, $self->{'encoding'});
293	dpavlin	624	$l =~ s/($recode_regex)/$recode_map->{$1}/g if ($recode_regex && $recode_map);
294
295	dpavlin	619	# apply regexps
296			if ($rec_regex && defined($rec_regex->{$f_nr})) {
297			$log->logconfess("regexps->{$f_nr} must be ARRAY") if (ref($rec_regex->{$f_nr}) ne 'ARRAY');
298			my $c = 0;
299			foreach my $r (@{ $rec_regex->{$f_nr} }) {
300	dpavlin	626	my $old_l = $l;
301	dpavlin	619	eval '$l =~ ' . $r;
302	dpavlin	626	if ($old_l ne $l) {
303			$log->debug("REGEX on $f_nr eval \$l =~ $r\n## old l: [$old_l]\n## new l: [$l]");
304			}
305	dpavlin	619	$log->error("error applying regex: $r") if ($@);
306			}
307			}
308
309	dpavlin	625	$log->debug("<=- $f_nr ## $l");
310	dpavlin	619	return $l;
311			});
312
313	dpavlin	771	$log->debug(sub { dump($rec) });
314	dpavlin	308
315	dpavlin	285	if (! $rec) {
316	dpavlin	286	$log->warn("record $pos empty? skipping...");
317	dpavlin	285	next;
318			}
319
320			# store
321	dpavlin	761	if ($self->{save_row}) {
322			$self->{save_row}->({
323			id => $pos,
324			row => $rec,
325			});
326	dpavlin	285	} else {
327	dpavlin	286	$self->{data}->{$pos} = $rec;
328	dpavlin	285	}
329
330			# create lookup
331	dpavlin	585	$arg->{'lookup_coderef'}->( $rec ) if ($rec && $arg->{'lookup_coderef'});
332	dpavlin	285
333	dpavlin	506	# update counters for statistics
334			if ($self->{stats}) {
335	dpavlin	593
336	dpavlin	619	# fetch clean record with regexpes applied for statistics
337	dpavlin	726	my $rec = $ll_db->fetch_rec($pos);
338	dpavlin	619
339	dpavlin	593	foreach my $fld (keys %{ $rec }) {
340	dpavlin	506	$self->{_stats}->{fld}->{ $fld }++;
341	dpavlin	593
342			$log->logdie("invalid record fild $fld, not ARRAY")
343			unless (ref($rec->{ $fld }) eq 'ARRAY');
344
345			foreach my $row (@{ $rec->{$fld} }) {
346
347			if (ref($row) eq 'HASH') {
348
349			foreach my $sf (keys %{ $row }) {
350	dpavlin	619	next if ($sf eq 'subfields');
351	dpavlin	593	$self->{_stats}->{sf}->{ $fld }->{ $sf }->{count}++;
352			$self->{_stats}->{sf}->{ $fld }->{ $sf }->{repeatable}++
353			if (ref($row->{$sf}) eq 'ARRAY');
354	dpavlin	506	}
355	dpavlin	593
356			} else {
357			$self->{_stats}->{repeatable}->{ $fld }++;
358			}
359	dpavlin	506	}
360	dpavlin	593	}
361	dpavlin	506	}
362
363	dpavlin	483	$self->progress_bar($pos,$to_rec) unless ($self->{no_progress_bar});
364	dpavlin	285
365			}
366
367	dpavlin	286	$self->{pos} = -1;
368			$self->{last_pcnt} = 0;
369	dpavlin	285
370			# store max mfn and return it.
371	dpavlin	339	$self->{max_pos} = $to_rec;
372			$log->debug("max_pos: $to_rec");
373	dpavlin	285
374	dpavlin	757	# save for dump
375			$self->{ll_db} = $ll_db;
376
377	dpavlin	285	return $size;
378			}
379
380			=head2 fetch
381
382			Fetch next record from database. It will also displays progress bar.
383
384			my $rec = $isis->fetch;
385
386			Record from this function should probably go to C<data_structure> for
387			normalisation.
388
389			=cut
390
391			sub fetch {
392			my $self = shift;
393
394			my $log = $self->_get_logger();
395
396	dpavlin	286	$log->logconfess("it seems that you didn't load database!") unless ($self->{pos});
397	dpavlin	285
398	dpavlin	286	if ($self->{pos} == -1) {
399			$self->{pos} = $self->{offset};
400	dpavlin	285	} else {
401	dpavlin	286	$self->{pos}++;
402	dpavlin	285	}
403
404	dpavlin	286	my $mfn = $self->{pos};
405	dpavlin	285
406	dpavlin	286	if ($mfn > $self->{max_pos}) {
407			$self->{pos} = $self->{max_pos};
408	dpavlin	285	$log->debug("at EOF");
409			return;
410			}
411
412	dpavlin	483	$self->progress_bar($mfn,$self->{max_pos}) unless ($self->{no_progress_bar});
413	dpavlin	285
414			my $rec;
415
416	dpavlin	761	if ($self->{load_row}) {
417			$rec = $self->{load_row}->({ id => $mfn });
418	dpavlin	285	} else {
419	dpavlin	286	$rec = $self->{data}->{$mfn};
420	dpavlin	285	}
421
422			$rec \|\|= 0E0;
423			}
424
425			=head2 pos
426
427			Returns current record number (MFN).
428
429			print $isis->pos;
430
431			First record in database has position 1.
432
433			=cut
434
435			sub pos {
436			my $self = shift;
437	dpavlin	286	return $self->{pos};
438	dpavlin	285	}
439
440
441			=head2 size
442
443			Returns number of records in database
444
445			print $isis->size;
446
447			Result from this function can be used to loop through all records
448
449			foreach my $mfn ( 1 ... $isis->size ) { ... }
450
451	dpavlin	286	because it takes into account C<offset> and C<limit>.
452	dpavlin	285
453			=cut
454
455			sub size {
456			my $self = shift;
457	dpavlin	286	return $self->{size};
458	dpavlin	285	}
459
460			=head2 seek
461
462			Seek to specified MFN in file.
463
464			$isis->seek(42);
465
466			First record in database has position 1.
467
468			=cut
469
470			sub seek {
471			my $self = shift;
472	dpavlin	793	my $pos = shift;
473	dpavlin	285
474			my $log = $self->_get_logger();
475
476	dpavlin	793	$log->confess("called without pos") unless defined($pos);
477
478	dpavlin	285	if ($pos < 1) {
479			$log->warn("seek before first record");
480			$pos = 1;
481	dpavlin	286	} elsif ($pos > $self->{max_pos}) {
482	dpavlin	285	$log->warn("seek beyond last record");
483	dpavlin	286	$pos = $self->{max_pos};
484	dpavlin	285	}
485
486	dpavlin	286	return $self->{pos} = (($pos - 1) \|\| -1);
487	dpavlin	285	}
488
489	dpavlin	506	=head2 stats
490	dpavlin	285
491	dpavlin	506	Dump statistics about field and subfield usage
492
493	dpavlin	507	print $input->stats;
494	dpavlin	506
495			=cut
496
497			sub stats {
498			my $self = shift;
499	dpavlin	507
500			my $log = $self->_get_logger();
501
502			my $s = $self->{_stats};
503			if (! $s) {
504			$log->warn("called stats, but there is no statistics collected");
505			return;
506			}
507
508			my $max_fld = 0;
509
510			my $out = join("\n",
511			map {
512			my $f = $_ \|\| die "no field";
513			my $v = $s->{fld}->{$f} \|\| die "no s->{fld}->{$f}";
514			$max_fld = $v if ($v > $max_fld);
515
516	dpavlin	519	my $o = sprintf("%4s %d ~", $f, $v);
517	dpavlin	507
518			if (defined($s->{sf}->{$f})) {
519			map {
520	dpavlin	593	$o .= sprintf(" %s:%d%s", $_,
521			$s->{sf}->{$f}->{$_}->{count},
522			$s->{sf}->{$f}->{$_}->{repeatable} ? '*' : '',
523			);
524	dpavlin	507	} sort keys %{ $s->{sf}->{$f} };
525			}
526
527			if (my $v_r = $s->{repeatable}->{$f}) {
528			$o .= " ($v_r)" if ($v_r != $v);
529			}
530
531			$o;
532	dpavlin	519	} sort { $a cmp $b } keys %{ $s->{fld} }
533	dpavlin	507	);
534
535	dpavlin	771	$log->debug( sub { dump($s) } );
536	dpavlin	507
537			return $out;
538	dpavlin	506	}
539
540	dpavlin	774	=head2 dump_ascii
541	dpavlin	652
542			Display humanly readable dump of record
543
544			=cut
545
546	dpavlin	774	sub dump_ascii {
547	dpavlin	652	my $self = shift;
548
549	dpavlin	771	return unless $self->{ll_db};
550	dpavlin	652
551	dpavlin	771	if ($self->{ll_db}->can('dump_rec')) {
552	dpavlin	774	return $self->{ll_db}->dump_ascii( $self->{pos} );
553	dpavlin	771	} else {
554			return dump( $self->{ll_db}->fetch_rec( $self->{pos} ) );
555			}
556	dpavlin	652	}
557
558	dpavlin	598	=head2 modify_record_regexps
559	dpavlin	597
560	dpavlin	636	Generate hash with regexpes to be applied using l<filter>.
561	dpavlin	597
562			my $regexpes = $input->modify_record_regexps(
563			900 => { '^a' => { ' : ' => '^b' } },
564			901 => { '*' => { '^b' => ' ; ' } },
565			);
566
567			=cut
568
569	dpavlin	636	sub _get_regex {
570			my ($sf,$from,$to) = @_;
571	dpavlin	784	if ($from =~ m/^regex:(.+)$/) {
572			$from = $1;
573			} else {
574			$from = '\Q' . $from . '\E';
575			}
576	dpavlin	636	if ($sf =~ /^\^/) {
577			return
578	dpavlin	784	's/\Q'. $sf .'\E([^\^]?)'. $from .'([^\^]?)/'. $sf .'$1'. $to .'$2/';
579	dpavlin	636	} else {
580			return
581	dpavlin	784	's/'. $from .'/'. $to .'/g';
582	dpavlin	636	}
583			}
584
585	dpavlin	597	sub modify_record_regexps {
586			my $self = shift;
587			my $modify_record = {@_};
588
589			my $regexpes;
590
591	dpavlin	634	my $log = $self->_get_logger();
592
593	dpavlin	597	foreach my $f (keys %$modify_record) {
594	dpavlin	634	$log->debug("field: $f");
595
596	dpavlin	597	foreach my $sf (keys %{ $modify_record->{$f} }) {
597	dpavlin	634	$log->debug("subfield: $sf");
598
599	dpavlin	597	foreach my $from (keys %{ $modify_record->{$f}->{$sf} }) {
600			my $to = $modify_record->{$f}->{$sf}->{$from};
601			#die "no field?" unless defined($to);
602	dpavlin	634	$log->debug("transform: \|$from\| -> \|$to\|");
603	dpavlin	597
604	dpavlin	636	my $regex = _get_regex($sf,$from,$to);
605			push @{ $regexpes->{$f} }, $regex;
606			$log->debug("regex: $regex");
607	dpavlin	597	}
608			}
609			}
610
611			return $regexpes;
612			}
613
614	dpavlin	636	=head2 modify_file_regexps
615
616			Generate hash with regexpes to be applied using l<filter> from
617			pseudo hash/yaml format for regex mappings.
618
619			It should be obvious:
620
621			200
622			'^a'
623			' : ' => '^e'
624			' = ' => '^d'
625
626			In field I<200> find C<'^a'> and then C<' : '>, and replace it with C<'^e'>.
627			In field I<200> find C<'^a'> and then C<' = '>, and replace it with C<'^d'>.
628
629			my $regexpes = $input->modify_file_regexps( 'conf/modify/common.pl' );
630
631			On undef path it will just return.
632
633			=cut
634
635			sub modify_file_regexps {
636			my $self = shift;
637
638			my $modify_path = shift \|\| return;
639
640			my $log = $self->_get_logger();
641
642			my $regexpes;
643
644	dpavlin	697	CORE::open(my $fh, $modify_path) \|\| $log->logdie("can't open modify file $modify_path: $!");
645	dpavlin	636
646			my ($f,$sf);
647
648			while(<$fh>) {
649			chomp;
650			next if (/^#/ \|\| /^\s*$/);
651
652			if (/^\s(\d+)\s$/) {
653			$f = $1;
654			$log->debug("field: $f");
655			next;
656			} elsif (/^\s'([^'])'\s*$/) {
657			$sf = $1;
658			$log->die("can't define subfiled before field in: $_") unless ($f);
659			$log->debug("subfield: $sf");
660			} elsif (/^\s'([^'])'\s=>\s'([^'])'\s$/) {
661			my ($from,$to) = ($1, $2);
662
663			$log->debug("transform: \|$from\| -> \|$to\|");
664
665			my $regex = _get_regex($sf,$from,$to);
666			push @{ $regexpes->{$f} }, $regex;
667			$log->debug("regex: $regex");
668			}
669			}
670
671			return $regexpes;
672			}
673
674	dpavlin	3	=head1 AUTHOR
675
676			Dobrica Pavlinusic, C<< <dpavlin@rot13.org> >>
677
678	dpavlin	1	=head1 COPYRIGHT & LICENSE
679
680	dpavlin	599	Copyright 2005-2006 Dobrica Pavlinusic, All Rights Reserved.
681	dpavlin	1
682			This program is free software; you can redistribute it and/or modify it
683			under the same terms as Perl itself.
684
685			=cut
686
687			1; # End of WebPAC::Input