--- trunk/lib/WebPAC/Input.pm 2005/12/18 21:06:46 286 +++ trunk/lib/WebPAC/Input.pm 2006/07/13 11:54:33 597 @@ -8,6 +8,7 @@ use WebPAC::Common; use base qw/WebPAC::Common/; use Text::Iconv; +use Data::Dumper; =head1 NAME @@ -15,11 +16,11 @@ =head1 VERSION -Version 0.03 +Version 0.08 =cut -our $VERSION = '0.03'; +our $VERSION = '0.08'; =head1 SYNOPSIS @@ -38,19 +39,18 @@ Perhaps a little code snippet. - use WebPAC::Input; + use WebPAC::Input; - my $db = WebPAC::Input->new( - module => 'WebPAC::Input::ISIS', - config => $config, - lookup => $lookup_obj, + my $db = WebPAC::Input->new( + module => 'WebPAC::Input::ISIS', low_mem => 1, - ); + ); - $db->open('/path/to/database'); - print "database size: ",$db->size,"\n"; - while (my $rec = $db->fetch) { - } + $db->open( path => '/path/to/database' ); + print "database size: ",$db->size,"\n"; + while (my $rec = $db->fetch) { + # do something with $rec + } @@ -62,19 +62,26 @@ my $db = new WebPAC::Input( module => 'WebPAC::Input::MARC', - code_page => 'ISO-8859-2', + encoding => 'ISO-8859-2', low_mem => 1, + recode => 'char pairs', + no_progress_bar => 1, ); -C is low-level file format module. See L and +C is low-level file format module. See L and L. -Optional parametar C specify application code page (which will be +Optional parametar C specify application code page (which will be used internally). This should probably be your terminal encoding, and by default, it C. Default is not to use C options (see L below). +C is optional string constisting of character or words pairs that +should be replaced in input stream. + +C disables progress bar output on C + This function will also call low-level C if it exists with same parametars. @@ -87,29 +94,35 @@ my $log = $self->_get_logger; + $log->logconfess("code_page argument is not suppored any more. change it to encoding") if ($self->{lookup}); + $log->logconfess("lookup argument is not suppored any more. rewrite call to lookup_ref") if ($self->{lookup}); + $log->logconfess("specify low-level file format module") unless ($self->{module}); my $module = $self->{module}; $module =~ s#::#/#g; $module .= '.pm'; $log->debug("require low-level module $self->{module} from $module"); + require $module; - eval $self->{module} .'->import'; + #eval $self->{module} .'->import'; # check if required subclasses are implemented - foreach my $subclass (qw/open_db fetch_rec/) { - if ( $self->can($subclass) ) { - $log->debug("imported $subclass"); + foreach my $subclass (qw/open_db fetch_rec init/) { + my $n = $self->{module} . '::' . $subclass; + if (! defined &{ $n }) { + my $missing = "missing $subclass in $self->{module}"; + $self->{$subclass} = sub { $log->logwarn($missing) }; } else { - $log->warn("missing $subclass in $self->{module}"); + $self->{$subclass} = \&{ $n }; } } - if ($self->can('init')) { + if ($self->{init}) { $log->debug("calling init"); - $self->init(@_); + $self->{init}->($self, @_); } - $self->{'code_page'} ||= 'ISO-8859-2'; + $self->{'encoding'} ||= 'ISO-8859-2'; # running with low_mem flag? well, use DBM::Deep then. if ($self->{'low_mem'}) { @@ -150,6 +163,15 @@ limit => 500, offset => 6000, lookup => $lookup_obj, + stats => 1, + lookup_ref => sub { + my ($k,$v) = @_; + # store lookup $k => $v + }, + modify_records => { + 900 => { '^a' => { ' : ' => '^b' } }, + 901 => { '*' => { '^b' => ' ; ' } }, + }, ); By default, C is assumed to be C<852>. @@ -158,6 +180,15 @@ C is optional parametar to read just C records from database +C create optional report about usage of fields and subfields + +C is closure to call when adding C<< key => 'value' >> combinations to +lookup. + +C specify mapping from subfields to delimiters or from +delimiters to subfields, as well as oprations on fields (if subfield is +defined as C<*>. + Returns size of database, regardless of C and C parametars, see also C. @@ -169,23 +200,76 @@ my $log = $self->_get_logger(); + $log->logconfess("lookup argument is not suppored any more. rewrite call to lookup_coderef") if ($arg->{lookup}); + $log->logconfess("lookup_coderef must be CODE, not ",ref($arg->{lookup_coderef})) + if ($arg->{lookup_coderef} && ref($arg->{lookup_coderef}) ne 'CODE'); + $log->logcroak("need path") if (! $arg->{'path'}); my $code_page = $arg->{'code_page'} || '852'; # store data in object - $self->{'code_page'} = $code_page; + $self->{'input_code_page'} = $code_page; foreach my $v (qw/path offset limit/) { $self->{$v} = $arg->{$v} if ($arg->{$v}); } # create Text::Iconv object - $self->{iconv} = Text::Iconv->new($code_page,$self->{'code_page'}); + $self->{iconv} = Text::Iconv->new($code_page,$self->{'encoding'}); ## FIXME remove! + + my $filter_ref; + my $recode_regex; + my $recode_map; + + if ($self->{recode}) { + my @r = split(/\s/, $self->{recode}); + if ($#r % 2 != 1) { + $log->logwarn("recode needs even number of elements (some number of valid pairs)"); + } else { + 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 = $self->modify_record_regexps(%{ $arg->{modify_records} }); + $log->debug("rec_regex: ", Dumper($rec_regex)); - my ($db, $size) = $self->open_db( + my ($db, $size) = $self->{open_db}->( $self, path => $arg->{path}, + filter => sub { + my ($l,$f_nr) = @_; + return unless defined($l); + + ## FIXME remove iconv! + $l = $self->{iconv}->convert($l) if ($self->{iconv}); + + $l =~ s/($recode_regex)/$recode_map->{$1}/g if ($recode_regex && $recode_map); + + return $l unless ($rec_regex); + + # apply regexps + if ($rec_regex && defined($rec_regex->{$f_nr})) { + $log->logconfess("regexps->{$f_nr} must be ARRAY") if (ref($rec_regex->{$f_nr}) ne 'ARRAY'); + my $c = 0; + foreach my $r (@{ $rec_regex->{$f_nr} }) { + while ( eval '$l =~ ' . $r ) { $c++ }; + } + warn "## field $f_nr triggered $c regexpes\n" if ($c && $self->{debug}); + } + + return $l; + }, + %{ $arg }, ); - unless ($db) { + unless (defined($db)) { $log->logwarn("can't open database $arg->{path}, skipping..."); return; } @@ -195,33 +279,35 @@ return; } - my $offset = 1; - my $limit = $size; + my $from_rec = 1; + my $to_rec = $size; if (my $s = $self->{offset}) { - $log->info("skipping to MFN $s"); - $offset = $s; + $log->debug("skipping to MFN $s"); + $from_rec = $s; } else { - $self->{offset} = $offset; + $self->{offset} = $from_rec; } if ($self->{limit}) { - $log->info("limiting to ",$self->{limit}," records"); - $limit = $offset + $self->{limit} - 1; - $limit = $size if ($limit > $size); + $log->debug("limiting to ",$self->{limit}," records"); + $to_rec = $from_rec + $self->{limit} - 1; + $to_rec = $size if ($to_rec > $size); } # store size for later - $self->{size} = ($limit - $offset) ? ($limit - $offset + 1) : 0; + $self->{size} = ($to_rec - $from_rec) ? ($to_rec - $from_rec + 1) : 0; - $log->info("processing $self->{size} records in $code_page, convert to $self->{code_page}"); + $log->info("processing $self->{size}/$size records [$from_rec-$to_rec] convert $code_page -> $self->{encoding}", $self->{stats} ? ' [stats]' : ''); # read database - for (my $pos = $offset; $pos <= $limit; $mfn++) { + for (my $pos = $from_rec; $pos <= $to_rec; $pos++) { $log->debug("position: $pos\n"); - my $rec = $self->fetch_rec( $db, $pos ); + my $rec = $self->{fetch_rec}->($self, $db, $pos ); + + $log->debug(sub { Dumper($rec) }); if (! $rec) { $log->warn("record $pos empty? skipping..."); @@ -236,9 +322,35 @@ } # create lookup - $self->{'lookup'}->add( $rec ) if ($rec && $self->{'lookup'}); + $arg->{'lookup_coderef'}->( $rec ) if ($rec && $arg->{'lookup_coderef'}); + + # update counters for statistics + if ($self->{stats}) { + + foreach my $fld (keys %{ $rec }) { + $self->{_stats}->{fld}->{ $fld }++; - $self->progress_bar($pos,$limit); + $log->logdie("invalid record fild $fld, not ARRAY") + unless (ref($rec->{ $fld }) eq 'ARRAY'); + + foreach my $row (@{ $rec->{$fld} }) { + + if (ref($row) eq 'HASH') { + + foreach my $sf (keys %{ $row }) { + $self->{_stats}->{sf}->{ $fld }->{ $sf }->{count}++; + $self->{_stats}->{sf}->{ $fld }->{ $sf }->{repeatable}++ + if (ref($row->{$sf}) eq 'ARRAY'); + } + + } else { + $self->{_stats}->{repeatable}->{ $fld }++; + } + } + } + } + + $self->progress_bar($pos,$to_rec) unless ($self->{no_progress_bar}); } @@ -246,8 +358,8 @@ $self->{last_pcnt} = 0; # store max mfn and return it. - $self->{max_pos} = $limit; - $log->debug("max_pos: $limit"); + $self->{max_pos} = $to_rec; + $log->debug("max_pos: $to_rec"); return $size; } @@ -284,7 +396,7 @@ return; } - $self->progress_bar($mfn,$self->{max_pos}); + $self->progress_bar($mfn,$self->{max_pos}) unless ($self->{no_progress_bar}); my $rec; @@ -359,6 +471,101 @@ 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} } + ); + + $log->debug( sub { Dumper($s) } ); + + return $out; +} + +=head1 modify_record_regexps + +Generate hash with regexpes to be applied using L. + + my $regexpes = $input->modify_record_regexps( + 900 => { '^a' => { ' : ' => '^b' } }, + 901 => { '*' => { '^b' => ' ; ' } }, + ); + +=cut + +sub modify_record_regexps { + my $self = shift; + my $modify_record = {@_}; + + my $regexpes; + + foreach my $f (keys %$modify_record) { +warn "--- f: $f\n"; + foreach my $sf (keys %{ $modify_record->{$f} }) { +warn "---- sf: $sf\n"; + foreach my $from (keys %{ $modify_record->{$f}->{$sf} }) { + my $to = $modify_record->{$f}->{$sf}->{$from}; + #die "no field?" unless defined($to); +warn "----- transform: |$from| -> |$to|\n"; + + if ($sf =~ /^\^/) { + my $regex = + 's/\Q'. $sf .'\E([^\^]+)\Q'. $from .'\E([^\^]+)/'. $sf .'$1'. $to .'$2/g'; + push @{ $regexpes->{$f} }, $regex; +warn ">>>>> $regex [sf]\n"; + } else { + my $regex = + 's/\Q'. $from .'\E/'. $to .'/g'; + push @{ $regexpes->{$f} }, $regex; +warn ">>>>> $regex [global]\n"; + } + + } + } + } + + return $regexpes; +} =head1 MEMORY USAGE