--- trunk/lib/WebPAC/Input.pm 2005/12/18 21:06:39 285 +++ trunk/lib/WebPAC/Input.pm 2006/10/25 15:56:44 760 @@ -7,42 +7,52 @@ use WebPAC::Common; use base qw/WebPAC::Common/; -use Text::Iconv; +use Data::Dumper; +use Encode qw/from_to/; =head1 NAME -WebPAC::Input - core module for input file format +WebPAC::Input - read different file formats into WebPAC =head1 VERSION -Version 0.02 +Version 0.13 =cut -our $VERSION = '0.02'; +our $VERSION = '0.13'; =head1 SYNOPSIS -This module is used as base class for all database specific modules -(basically, files which have one handle, fixed size while indexing and some -kind of numeric idefinirier which goes from 1 to filesize). +This module implements input as database which have fixed and known +I while indexing and single unique numeric identifier for database +position ranging from 1 to I. + +Simply, something that is indexed by unmber from 1 .. I. + +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 namespace which export C, +C and optional C functions. Perhaps a little code snippet. - use WebPAC::Input; + use WebPAC::Input; + + my $db = WebPAC::Input->new( + module => 'WebPAC::Input::ISIS', + low_mem => 1, + ); + + $db->open( path => '/path/to/database' ); + print "database size: ",$db->size,"\n"; + while (my $rec = $db->fetch) { + # do something with $rec + } - my $db = WebPAC::Input->new( - format => 'NULL', - config => $config, - lookup => $lookup_obj, - low_mem => 1, - ); - $db->open('/path/to/database'); - print "database size: ",$db->size,"\n"; - while (my $row = $db->fetch) { - ... - } =head1 FUNCTIONS @@ -51,17 +61,27 @@ Create new input database object. my $db = new WebPAC::Input( - format => 'NULL' - code_page => 'ISO-8859-2', + module => 'WebPAC::Input::MARC', + encoding => 'ISO-8859-2', low_mem => 1, + recode => 'char pairs', + no_progress_bar => 1, ); -Optional parametar C specify application code page (which will be +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. + +C disables progress bar output on C + This function will also call low-level C if it exists with same parametars. @@ -74,44 +94,24 @@ my $log = $self->_get_logger; - # check if required subclasses are implemented - foreach my $subclass (qw/open_db fetch_rec/) { - $log->logdie("missing implementation of $subclass") unless ($self->SUPER::can($subclass)); - } + $log->logconfess("code_page argument is not suppored any more. change it to encoding") if ($self->{lookup}); + $log->logconfess("lookup argument is not suppored any more. rewrite call to lookup_ref") if ($self->{lookup}); - if ($self->can('init')) { - $log->debug("calling init"); - $self->init(@_); - } + $log->logconfess("specify low-level file format module") unless ($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"); - $self->{'code_page'} ||= 'ISO-8859-2'; + require $module_path; - # running with low_mem flag? well, use DBM::Deep then. - if ($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 $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; + # check if required subclasses are implemented + foreach my $subclass (qw/open_db fetch_rec init dump_rec/) { + # FIXME } + $self->{'encoding'} ||= 'ISO-8859-2'; + $self ? return $self : return undef; } @@ -119,24 +119,43 @@ This function will read whole database in memory and produce lookups. - $isis->open( + $input->open( path => '/path/to/database/file', - code_page => '852', - limit_mfn => 500, - start_mfn => 6000, - lookup => $lookup_obj, + code_page => 'cp852', + limit => 500, + offset => 6000, + stats => 1, + lookup_coderef => sub { + my $rec = shift; + # store lookups + }, + modify_records => { + 900 => { '^a' => { ' : ' => '^b' } }, + 901 => { '*' => { '^b' => ' ; ' } }, + }, + modify_file => 'conf/modify/mapping.map', ); -By default, C is assumed to be C<852>. +By default, C is assumed to be C. + +C is optional parametar to position at some offset before reading from database. + +C is optional parametar to read just C records from database + +C create optional report about usage of fields and subfields + +C is closure to called to save data into lookups -If optional parametar C is set, this will be first MFN to read -from database (so you can skip beginning of your database if you need to). +C specify mapping from subfields to delimiters or from +delimiters to subfields, as well as oprations on fields (if subfield is +defined as C<*>. -If optional parametar C is set, it will read just 500 records -from database in example above. +C is alternative for C above which preserves order and offers +(hopefully) simplier sintax than YAML or perl (see L). This option +overrides C if both exists for same input. -Returns size of database, regardless of C and C -parametars, see also C<$isis->size>. +Returns size of database, regardless of C and C +parametars, see also C. =cut @@ -146,86 +165,226 @@ 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'} || '852'; + my $code_page = $arg->{'code_page'} || 'cp852'; # store data in object - $self->{'code_page'} = $code_page; - foreach my $v (qw/path start_mfn limit_mfn/) { + $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'}); + 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 ", Dumper( $h )); + $rec_regex = $self->modify_record_regexps(%{ $h }); + } + $log->debug("rec_regex: ", Dumper($rec_regex)) if ($rec_regex); + + my $class = $self->{module} || $log->logconfess("can't get low-level module name!"); - my ($db, $size) = $self->open_db( + 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; +# }, + %{ $arg }, ); - unless ($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; } - my $startmfn = 1; - my $maxmfn = $size; + my $from_rec = 1; + my $to_rec = $size; - if (my $s = $self->{start_mfn}) { - $log->info("skipping to MFN $s"); - $startmfn = $s; + if (my $s = $self->{offset}) { + $log->debug("skipping to MFN $s"); + $from_rec = $s; } else { - $self->{start_mfn} = $startmfn; + $self->{offset} = $from_rec; } - if ($self->{limit_mfn}) { - $log->info("limiting to ",$self->{limit_mfn}," records"); - $maxmfn = $startmfn + $self->{limit_mfn} - 1; - $maxmfn = $size if ($maxmfn > $size); + if ($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 - $self->{size} = ($maxmfn - $startmfn) ? ($maxmfn - $startmfn + 1) : 0; + $self->{size} = ($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]' : ''); + + # turn on low_mem for databases with more than 100000 records! + if (! $self->{low_mem} && $size > 100000) { + $log->warn("Using on-disk storage instead of memory for input data. This will affect performance."); + $self->{low_mem}++; + } + + # running with low_mem flag? well, use DBM::Deep then. + if ($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 $db = new DBM::Deep $db_file; - $log->info("processing $self->{size} records in $code_page, convert to $self->{code_page}"); + $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; + } # read database - for (my $mfn = $startmfn; $mfn <= $maxmfn; $mfn++) { + for (my $pos = $from_rec; $pos <= $to_rec; $pos++) { - $log->debug("mfn: $mfn\n"); + $log->debug("position: $pos\n"); - my $rec = $self->fetch_rec( $db, $mfn ); + 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) }); if (! $rec) { - $log->warn("record $mfn empty? skipping..."); + $log->warn("record $pos empty? skipping..."); next; } # store - if ($self->{'low_mem'}) { - $self->{'db'}->put($mfn, $rec); + if ($self->{low_mem}) { + $self->{db}->put($pos, $rec); } else { - $self->{'data'}->{$mfn} = $rec; + $self->{data}->{$pos} = $rec; } # create lookup - $self->{'lookup'}->add( $rec ) if ($rec && $self->{'lookup'}); + $arg->{'lookup_coderef'}->( $rec ) if ($rec && $arg->{'lookup_coderef'}); - $self->progress_bar($mfn,$maxmfn); + # update counters for statistics + if ($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->{'current_mfn'} = -1; - $self->{'last_pcnt'} = 0; + } - $log->debug("max mfn: $maxmfn"); + $self->{pos} = -1; + $self->{last_pcnt} = 0; # store max mfn and return it. - $self->{'max_mfn'} = $maxmfn; + $self->{max_pos} = $to_rec; + $log->debug("max_pos: $to_rec"); + + # save for dump + $self->{ll_db} = $ll_db; return $size; } @@ -246,30 +405,30 @@ my $log = $self->_get_logger(); - $log->logconfess("it seems that you didn't load database!") unless ($self->{'current_mfn'}); + $log->logconfess("it seems that you didn't load database!") unless ($self->{pos}); - if ($self->{'current_mfn'} == -1) { - $self->{'current_mfn'} = $self->{'start_mfn'}; + if ($self->{pos} == -1) { + $self->{pos} = $self->{offset}; } else { - $self->{'current_mfn'}++; + $self->{pos}++; } - my $mfn = $self->{'current_mfn'}; + my $mfn = $self->{pos}; - if ($mfn > $self->{'max_mfn'}) { - $self->{'current_mfn'} = $self->{'max_mfn'}; + if ($mfn > $self->{max_pos}) { + $self->{pos} = $self->{max_pos}; $log->debug("at EOF"); return; } - $self->progress_bar($mfn,$self->{'max_mfn'}); + $self->progress_bar($mfn,$self->{max_pos}) unless ($self->{no_progress_bar}); my $rec; - if ($self->{'low_mem'}) { - $rec = $self->{'db'}->get($mfn); + if ($self->{low_mem}) { + $rec = $self->{db}->get($mfn); } else { - $rec = $self->{'data'}->{$mfn}; + $rec = $self->{data}->{$mfn}; } $rec ||= 0E0; @@ -287,7 +446,7 @@ sub pos { my $self = shift; - return $self->{'current_mfn'}; + return $self->{pos}; } @@ -301,13 +460,13 @@ foreach my $mfn ( 1 ... $isis->size ) { ... } -because it takes into account C and C. +because it takes into account C and C. =cut sub size { my $self = shift; - return $self->{'size'}; + return $self->{size}; } =head2 seek @@ -329,14 +488,188 @@ if ($pos < 1) { $log->warn("seek before first record"); $pos = 1; - } elsif ($pos > $self->{'max_mfn'}) { + } elsif ($pos > $self->{max_pos}) { $log->warn("seek beyond last record"); - $pos = $self->{'max_mfn'}; + $pos = $self->{max_pos}; } - return $self->{'current_mfn'} = (($pos - 1) || -1); + 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; +} + +=head2 dump + +Display humanly readable dump of record + +=cut + +sub dump { + my $self = shift; + + return $self->{ll_db}->dump_rec( $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 @@ -375,7 +708,7 @@ =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.