--- trunk/lib/WebPAC/Input.pm 2006/07/13 11:54:33 597 +++ trunk/lib/WebPAC/Input.pm 2008/08/04 21:47:27 1107 @@ -7,20 +7,16 @@ use WebPAC::Common; use base qw/WebPAC::Common/; -use Text::Iconv; -use Data::Dumper; +use Data::Dump qw/dump/; +use Encode qw/decode from_to/; =head1 NAME WebPAC::Input - read different file formats into WebPAC -=head1 VERSION - -Version 0.08 - =cut -our $VERSION = '0.08'; +our $VERSION = '0.19'; =head1 SYNOPSIS @@ -43,7 +39,6 @@ my $db = WebPAC::Input->new( module => 'WebPAC::Input::ISIS', - low_mem => 1, ); $db->open( path => '/path/to/database' ); @@ -62,21 +57,16 @@ my $db = new WebPAC::Input( module => 'WebPAC::Input::MARC', - encoding => 'ISO-8859-2', - low_mem => 1, 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. - -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. @@ -94,61 +84,18 @@ 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("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 = $self->{module}; - $module =~ s#::#/#g; - $module .= '.pm'; - $log->debug("require low-level module $self->{module} from $module"); - - require $module; - #eval $self->{module} .'->import'; - - # 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, @_); - } - - $self->{'encoding'} ||= 'ISO-8859-2'; - - # running with low_mem flag? well, use DBM::Deep then. - if ($self->{'low_mem'}) { - $log->info("running with low_mem which impacts performance (<32 Mb memory usage)"); - - my $db_file = "data.db"; - - if (-e $db_file) { - unlink $db_file or $log->logdie("can't remove '$db_file' from last run"); - $log->debug("removed '$db_file' from last run"); - } - - require DBM::Deep; + my $module_path = $self->{module}; + $module_path =~ s#::#/#g; + $module_path .= '.pm'; + $log->debug("require low-level module $self->{module} from $module_path"); - my $db = new DBM::Deep $db_file; - - $log->logdie("DBM::Deep error: $!") unless ($db); - - if ($db->error()) { - $log->logdie("can't open '$db_file' under low_mem: ",$db->error()); - } else { - $log->debug("using file '$db_file' for DBM::Deep"); - } - - $self->{'db'} = $db; - } + require $module_path; $self ? return $self : return undef; } @@ -157,24 +104,37 @@ 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 => '852', + input_encoding => 'cp852', + strict_encoding => 0, 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', + 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 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. @@ -182,13 +142,21 @@ C create optional report about usage of fields and subfields -C is closure to call when adding C<< 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. + +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. @@ -199,22 +167,33 @@ 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'); + $log->debug( $arg->{lookup_coderef} ? '' : 'not ', "using lookup_coderef"); + $log->logcroak("need path") if (! $arg->{'path'}); - my $code_page = $arg->{'code_page'} || '852'; + 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}); } - # create Text::Iconv object - $self->{iconv} = Text::Iconv->new($code_page,$self->{'encoding'}); ## FIXME remove! + if ($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; @@ -238,42 +217,38 @@ } - my $rec_regex = $self->modify_record_regexps(%{ $arg->{modify_records} }); - $log->debug("rec_regex: ", Dumper($rec_regex)); - - 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); + 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 ($rec_regex); - # apply regexps - if ($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}); - } + my $class = $self->{module} || $log->logconfess("can't get low-level module name!"); - return $l; - }, + 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); +# $l = decode($input_encoding, $l); +# $l =~ s/($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; @@ -298,16 +273,58 @@ # 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++) { $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,$debug) = @_; +# return unless defined($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"); - $log->debug(sub { Dumper($rec) }); + # codepage conversion and recode_regex + $l = decode($input_encoding, $l, 1); + $l =~ s/($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 $pos empty? skipping..."); @@ -315,8 +332,11 @@ } # store - if ($self->{low_mem}) { - $self->{db}->put($pos, $rec); + if ($self->{save_row}) { + $self->{save_row}->({ + id => $pos, + row => $rec, + }); } else { $self->{data}->{$pos} = $rec; } @@ -327,17 +347,21 @@ # update counters for statistics if ($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->{ $fld }) eq 'ARRAY'); + #$log->logdie("invalid record fild $fld, not ARRAY") + next unless (ref($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'); @@ -361,6 +385,9 @@ $self->{max_pos} = $to_rec; $log->debug("max_pos: $to_rec"); + # save for dump + $self->{ll_db} = $ll_db; + return $size; } @@ -400,8 +427,8 @@ my $rec; - if ($self->{low_mem}) { - $rec = $self->{db}->get($mfn); + if ($self->{load_row}) { + $rec = $self->{load_row}->({ id => $mfn }); } else { $rec = $self->{data}->{$mfn}; } @@ -456,10 +483,12 @@ 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; @@ -494,19 +523,26 @@ 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}) { @@ -514,15 +550,77 @@ } $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} } ); - $log->debug( sub { Dumper($s) } ); + $log->debug( sub { dump($s) } ); return $out; } -=head1 modify_record_regexps +=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( $self->{pos} ) ); + } +} + +=head2 _get_regex + +Helper function called which create regexps to be execute on code. + + _get_regex( 900, 'regex:[0-9]+' ,'numbers' ); + _get_regex( 900, '^b', ' : ^b' ); + +It supports perl regexps with C prefix to from value and has +additional logic to skip empty subfields. + +=cut + +sub _get_regex { + my ($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. @@ -539,27 +637,23 @@ my $regexpes; + my $log = $self->_get_logger(); + foreach my $f (keys %$modify_record) { -warn "--- f: $f\n"; + $log->debug("field: $f"); + foreach my $sf (keys %{ $modify_record->{$f} }) { -warn "---- sf: $sf\n"; + $log->debug("subfield: $sf"); + foreach my $from (keys %{ $modify_record->{$f}->{$sf} }) { my $to = $modify_record->{$f}->{$sf}->{$from}; #die "no field?" unless defined($to); -warn "----- transform: |$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"; - } + 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"); } } } @@ -567,36 +661,69 @@ return $regexpes; } -=head1 MEMORY USAGE +=head2 modify_file_regexps -C options is double-edged sword. If enabled, WebPAC -will run on memory constraint machines (which doesn't have enough -physical RAM to create memory structure for whole source database). - -If your machine has 512Mb or more of RAM and database is around 10000 records, -memory shouldn't be an issue. If you don't have enough physical RAM, you -might consider using virtual memory (if your operating system is handling it -well, like on FreeBSD or Linux) instead of dropping to L to handle -parsed structure of ISIS database (this is what C option does). - -Hitting swap at end of reading source database is probably o.k. However, -hitting swap before 90% will dramatically decrease performance and you will -be better off with C and using rest of availble memory for -operating system disk cache (Linux is particuallary good about this). -However, every access to database record will require disk access, so -generation phase will be slower 10-100 times. - -Parsed structures are essential - you just have option to trade RAM memory -(which is fast) for disk space (which is slow). Be sure to have planty of -disk space if you are using C and thus L. - -However, when WebPAC is running on desktop machines (or laptops :-), it's -highly undesireable for system to start swapping. Using C option can -reduce WecPAC memory usage to around 64Mb for same database with lookup -fields and sorted indexes which stay in RAM. Performance will suffer, but -memory usage will really be minimal. It might be also more confortable to -run WebPAC reniced on those machines. +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 => $regex, + file => $modify_path, + line => $., + }; + $log->debug("regex: $regex"); + } + } + + return $regexpes; +} =head1 AUTHOR @@ -604,7 +731,7 @@ =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.