--- trunk/lib/WebPAC/Input.pm 2006/11/03 20:56:21 774 +++ trunk/lib/WebPAC/Input.pm 2009/07/10 13:54:55 1236 @@ -3,24 +3,21 @@ use warnings; use strict; -use blib; +use lib 'lib'; use WebPAC::Common; use base qw/WebPAC::Common/; use Data::Dump qw/dump/; -use Encode qw/from_to/; +use Encode qw/decode from_to/; +use YAML; =head1 NAME WebPAC::Input - read different file formats into WebPAC -=head1 VERSION - -Version 0.16 - =cut -our $VERSION = '0.16'; +our $VERSION = '0.19'; =head1 SYNOPSIS @@ -61,18 +58,16 @@ my $db = new WebPAC::Input( module => 'WebPAC::Input::MARC', - encoding => 'ISO-8859-2', recode => 'char pairs', no_progress_bar => 1, + input_config => { + mapping => [ 'foo', 'bar', 'baz' ], + }, ); C is low-level file format module. See L and L. -Optional parametar C specify application code page (which will be -used internally). This should probably be your terminal encoding, and by -default, it C. - C is optional string constisting of character or words pairs that should be replaced in input stream. @@ -90,9 +85,10 @@ 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("code_page argument is not suppored any more.") if $self->{code_page}; + $log->logconfess("encoding argument is not suppored any more.") if $self->{encoding}; + $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}; @@ -102,8 +98,6 @@ require $module_path; - $self->{'encoding'} ||= 'ISO-8859-2'; - $self ? return $self : return undef; } @@ -115,7 +109,8 @@ $input->open( path => '/path/to/database/file', - code_page => 'cp852', + input_encoding => 'cp852', + strict_encoding => 0, limit => 500, offset => 6000, stats => 1, @@ -140,7 +135,7 @@ ); -By default, C is assumed to be C. +By default, C is assumed to be C. C is optional parametar to position at some offset before reading from database. @@ -161,6 +156,8 @@ C and C are low-level implementation of store engine. Calling convention is documented in example above. +C should really default to 1, but it doesn't for now. + Returns size of database, regardless of C and C parametars, see also C. @@ -171,7 +168,10 @@ my $arg = {@_}; my $log = $self->_get_logger(); + $log->debug( "arguments: ",dump( $arg )); + $log->logconfess("encoding argument is not suppored any more.") if $self->{encoding}; + $log->logconfess("code_page argument is not suppored any more.") if $self->{code_page}; $log->logconfess("lookup argument is not suppored any more. rewrite call to lookup_coderef") if ($arg->{lookup}); $log->logconfess("lookup_coderef must be CODE, not ",ref($arg->{lookup_coderef})) if ($arg->{lookup_coderef} && ref($arg->{lookup_coderef}) ne 'CODE'); @@ -179,10 +179,9 @@ $log->debug( $arg->{lookup_coderef} ? '' : 'not ', "using lookup_coderef"); $log->logcroak("need path") if (! $arg->{'path'}); - my $code_page = $arg->{'code_page'} || 'cp852'; + my $input_encoding = $arg->{'input_encoding'} || $self->{'input_encoding'} || '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}); } @@ -233,16 +232,20 @@ my $ll_db = $class->new( path => $arg->{path}, + input_config => $arg->{input_config} || $self->{input_config}, # filter => sub { # my ($l,$f_nr) = @_; # return unless defined($l); -# from_to($l, $code_page, $self->{'encoding'}); +# $l = decode($input_encoding, $l); # $l =~ s/($recode_regex)/$recode_map->{$1}/g if ($recode_regex && $recode_map); # return $l; # }, %{ $arg }, ); + # save for dump and input_module + $self->{ll_db} = $ll_db; + unless (defined($ll_db)) { $log->logwarn("can't open database $arg->{path}, skipping..."); return; @@ -274,7 +277,12 @@ # 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]' : ''); + my $strict_encoding = $arg->{strict_encoding} || $self->{strict_encoding}; ## FIXME should be 1 really + + $log->info("processing $self->{size}/$size records [$from_rec-$to_rec]", + " encoding $input_encoding ", $strict_encoding ? ' [strict]' : '', + $self->{stats} ? ' [stats]' : '', + ); # read database for (my $pos = $from_rec; $pos <= $to_rec; $pos++) { @@ -282,14 +290,17 @@ $log->debug("position: $pos\n"); my $rec = $ll_db->fetch_rec($pos, sub { - my ($l,$f_nr) = @_; + 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'}); + $l = decode($input_encoding, $l, 1); $l =~ s/($recode_regex)/$recode_map->{$1}/g if ($recode_regex && $recode_map); # apply regexps @@ -298,15 +309,22 @@ my $c = 0; foreach my $r (@{ $rec_regex->{$f_nr} }) { my $old_l = $l; - eval '$l =~ ' . $r; + $log->logconfess("expected regex in ", dump( $r )) unless defined($r->{regex}); + eval '$l =~ ' . $r->{regex}; if ($old_l ne $l) { - $log->debug("REGEX on $f_nr eval \$l =~ $r\n## old l: [$old_l]\n## new l: [$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: $r") if ($@); + $log->error("error applying regex: ",dump($r), $@) if $@; } } - $log->debug("<=- $f_nr ## $l"); + $log->debug("<=- $f_nr ## |$l|"); + warn "<=- $f_nr ## $l\n" if ($debug); return $l; }); @@ -339,8 +357,8 @@ foreach my $fld (keys %{ $rec }) { $self->{_stats}->{fld}->{ $fld }++; - $log->logdie("invalid record fild $fld, not ARRAY") - unless (ref($rec->{ $fld }) eq 'ARRAY'); + #$log->logdie("invalid record fild $fld, not ARRAY") + next unless (ref($rec->{ $fld }) eq 'ARRAY'); foreach my $row (@{ $rec->{$fld} }) { @@ -371,12 +389,11 @@ $self->{max_pos} = $to_rec; $log->debug("max_pos: $to_rec"); - # save for dump - $self->{ll_db} = $ll_db; - return $size; } +sub input_module { $_[0]->{ll_db} } + =head2 fetch Fetch next record from database. It will also displays progress bar. @@ -469,10 +486,12 @@ sub seek { my $self = shift; - my $pos = shift || return; + 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; @@ -507,19 +526,26 @@ my $out = join("\n", map { - my $f = $_ || die "no field"; + my $f = $_; + die "no field in ", dump( $s->{fld} ) unless defined( $f ); my $v = $s->{fld}->{$f} || die "no s->{fld}->{$f}"; $max_fld = $v if ($v > $max_fld); my $o = sprintf("%4s %d ~", $f, $v); if (defined($s->{sf}->{$f})) { + my @subfields = keys %{ $s->{sf}->{$f} }; map { $o .= sprintf(" %s:%d%s", $_, $s->{sf}->{$f}->{$_}->{count}, $s->{sf}->{$f}->{$_}->{repeatable} ? '*' : '', ); - } sort keys %{ $s->{sf}->{$f} }; + } ( + # first indicators and other special subfields + sort( grep { length($_) > 1 } @subfields ), + # then subfileds (single char) + sort( grep { length($_) == 1 } @subfields ), + ); } if (my $v_r = $s->{repeatable}->{$f}) { @@ -527,11 +553,21 @@ } $o; - } sort { $a cmp $b } keys %{ $s->{fld} } + } sort { + if ( $a =~ m/^\d+$/ && $b =~ m/^\d+$/ ) { + $a <=> $b + } else { + $a cmp $b + } + } keys %{ $s->{fld} } ); $log->debug( sub { dump($s) } ); + my $path = 'var/stats.yml'; + YAML::DumpFile( $path, $s ); + $log->info( 'created ', $path, ' with ', -s $path, ' bytes' ); + return $out; } @@ -546,35 +582,62 @@ return unless $self->{ll_db}; - if ($self->{ll_db}->can('dump_rec')) { + 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 modify_record_regexps +=head2 _get_regex -Generate hash with regexpes to be applied using l. +Helper function called which create regexps to be execute on code. - my $regexpes = $input->modify_record_regexps( - 900 => { '^a' => { ' : ' => '^b' } }, - 901 => { '*' => { '^b' => ' ; ' } }, - ); + _get_regex( 900, 'regex:[0-9]+' ,'numbers' ); + _get_regex( 900, '^b', ' : ^b' ); + +It supports perl regexps with C prefix to from value and has +additional logic to skip empty subfields. =cut sub _get_regex { my ($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([^\^]*?)\Q'. $from .'\E([^\^]*?)/'. $sf .'$1'. $to .'$2/'; + 's/\Q'. $sf .'\E([^\^]' . $need_subfield_data . '?)'. $from .'([^\^]*?)/'. $sf .'$1'. $to .'$2/'; } else { return - 's/\Q'. $from .'\E/'. $to .'/g'; + 's/'. $from .'/'. $to .'/g'; } } + +=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 modify_record_regexps { my $self = shift; my $modify_record = {@_}; @@ -592,10 +655,11 @@ 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 $d = "|$from| -> |$to|"; + $log->debug("transform: $d"); my $regex = _get_regex($sf,$from,$to); - push @{ $regexpes->{$f} }, $regex; + push @{ $regexpes->{$f} }, { regex => $regex, debug => $d }; $log->debug("regex: $regex"); } } @@ -606,7 +670,7 @@ =head2 modify_file_regexps -Generate hash with regexpes to be applied using l from +Generate hash with regexpes to be applied using L from pseudo hash/yaml format for regex mappings. It should be obvious: @@ -656,8 +720,14 @@ $log->debug("transform: |$from| -> |$to|"); my $regex = _get_regex($sf,$from,$to); - push @{ $regexpes->{$f} }, $regex; + push @{ $regexpes->{$f} }, { + regex => $regex, + file => $modify_path, + line => $., + }; $log->debug("regex: $regex"); + } else { + die "can't parse: $_"; } }