--- trunk/lib/WebPAC/Input.pm 2006/07/09 15:22:39 593 +++ trunk/lib/WebPAC/Input.pm 2006/09/29 19:52:17 726 @@ -7,8 +7,8 @@ use WebPAC::Common; use base qw/WebPAC::Common/; -use Text::Iconv; use Data::Dumper; +use Encode qw/from_to/; =head1 NAME @@ -16,11 +16,11 @@ =head1 VERSION -Version 0.08 +Version 0.13 =cut -our $VERSION = '0.08'; +our $VERSION = '0.13'; =head1 SYNOPSIS @@ -39,15 +39,14 @@ Perhaps a little code snippet. - use WebPAC::Input; + use WebPAC::Input; - my $db = WebPAC::Input->new( - module => 'WebPAC::Input::ISIS', - config => $config, + my $db = WebPAC::Input->new( + module => 'WebPAC::Input::ISIS', low_mem => 1, - ); + ); - $db->open('/path/to/database'); + $db->open( path => '/path/to/database' ); print "database size: ",$db->size,"\n"; while (my $rec = $db->fetch) { # do something with $rec @@ -69,7 +68,7 @@ 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 @@ -99,28 +98,16 @@ $log->logconfess("lookup argument is not suppored any more. rewrite call to lookup_ref") if ($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"); + 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; - #eval $self->{module} .'->import'; + require $module_path; # check if required subclasses are implemented - 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 { - $self->{$subclass} = \&{ $n }; - } - } - - if ($self->{init}) { - $log->debug("calling init"); - $self->{init}->($self, @_); + foreach my $subclass (qw/open_db fetch_rec init dump_rec/) { + # FIXME } $self->{'encoding'} ||= 'ISO-8859-2'; @@ -160,18 +147,22 @@ $input->open( path => '/path/to/database/file', - code_page => '852', + code_page => 'cp852', limit => 500, offset => 6000, - lookup => $lookup_obj, stats => 1, - lookup_ref => sub { - my ($k,$v) = @_; - # store lookup $k => $v + lookup_coderef => sub { + my $rec = shift; + # store lookups }, + modify_records => { + 900 => { '^a' => { ' : ' => '^b' } }, + 901 => { '*' => { '^b' => ' ; ' } }, + }, + modify_file => 'conf/modify/mapping.map', ); -By default, C is assumed to be C<852>. +By default, C is assumed to be C. C is optional parametar to position at some offset before reading from database. @@ -179,8 +170,15 @@ C create optional report about usage of fields and subfields -C is closure to call when adding key => $value combinations to -lookup. +C is closure to called to save data into lookups + +C specify mapping from subfields to delimiters or from +delimiters to subfields, as well as oprations on fields (if subfield is +defined as C<*>. + +C is alternative for C above which preserves order and offers +(hopefully) simplier sintax than YAML or perl (see L). This option +overrides C if both exists for same input. Returns size of database, regardless of C and C parametars, see also C. @@ -197,8 +195,10 @@ $log->logconfess("lookup_coderef must be CODE, not ",ref($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'} || '852'; + my $code_page = $arg->{'code_page'} || 'cp852'; # store data in object $self->{'input_code_page'} = $code_page; @@ -206,48 +206,59 @@ $self->{$v} = $arg->{$v} if ($arg->{$v}); } - # create Text::Iconv object - $self->{iconv} = Text::Iconv->new($code_page,$self->{'encoding'}); ## FIXME remove! - my $filter_ref; + my $recode_regex; + my $recode_map; if ($self->{recode}) { my @r = split(/\s/, $self->{recode}); if ($#r % 2 != 1) { $log->logwarn("recode needs even number of elements (some number of valid pairs)"); } else { - my $recode; while (@r) { my $from = shift @r; my $to = shift @r; - $recode->{$from} = $to; + $recode_map->{$from} = $to; } - my $regex = join '|' => keys %{ $recode }; - - $log->debug("using recode regex: $regex"); - - $filter_ref = sub { - my $t = shift; - $t =~ s/($regex)/$recode->{$1}/g; - return $t; - }; + $recode_regex = join '|' => keys %{ $recode_map }; + $log->debug("using recode regex: $recode_regex"); } } - my ($db, $size) = $self->{open_db}->( $self, + 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 ", Dumper( $h )); + $rec_regex = $self->modify_record_regexps(%{ $h }); + } + $log->debug("rec_regex: ", Dumper($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 => $filter_ref, +# filter => sub { +# my ($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; +# }, %{ $arg }, ); - unless (defined($db)) { + unless (defined($ll_db)) { $log->logwarn("can't open database $arg->{path}, skipping..."); return; } + my $size = $ll_db->size; + unless ($size) { $log->logwarn("no records in database $arg->{path}, skipping..."); return; @@ -279,7 +290,34 @@ $log->debug("position: $pos\n"); - my $rec = $self->{fetch_rec}->($self, $db, $pos ); + 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; + }); $log->debug(sub { Dumper($rec) }); @@ -301,6 +339,9 @@ # 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}->{ $fld }++; @@ -312,6 +353,7 @@ if (ref($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'); @@ -496,6 +538,130 @@ return $out; } +=head2 dump + +Display humanly readable dump of record + +=cut + +sub dump { + my $self = shift; + + return $self->{dump_rec}->($self, $self->{pos}); + +} + +=head2 modify_record_regexps + +Generate hash with regexpes to be applied using l. + + my $regexpes = $input->modify_record_regexps( + 900 => { '^a' => { ' : ' => '^b' } }, + 901 => { '*' => { '^b' => ' ; ' } }, + ); + +=cut + +sub _get_regex { + my ($sf,$from,$to) = @_; + if ($sf =~ /^\^/) { + return + 's/\Q'. $sf .'\E([^\^]*?)\Q'. $from .'\E([^\^]*?)/'. $sf .'$1'. $to .'$2/'; + } else { + return + 's/\Q'. $from .'\E/'. $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 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 MEMORY USAGE C options is double-edged sword. If enabled, WebPAC @@ -533,7 +699,7 @@ =head1 COPYRIGHT & LICENSE -Copyright 2005 Dobrica Pavlinusic, All Rights Reserved. +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.