7 |
|
|
8 |
use WebPAC::Common; |
use WebPAC::Common; |
9 |
use base qw/WebPAC::Common/; |
use base qw/WebPAC::Common/; |
10 |
use Text::Iconv; |
use Data::Dump qw/dump/; |
11 |
use Data::Dumper; |
use Encode qw/from_to/; |
12 |
|
|
13 |
=head1 NAME |
=head1 NAME |
14 |
|
|
16 |
|
|
17 |
=head1 VERSION |
=head1 VERSION |
18 |
|
|
19 |
Version 0.08 |
Version 0.18 |
20 |
|
|
21 |
=cut |
=cut |
22 |
|
|
23 |
our $VERSION = '0.08'; |
our $VERSION = '0.18'; |
24 |
|
|
25 |
=head1 SYNOPSIS |
=head1 SYNOPSIS |
26 |
|
|
43 |
|
|
44 |
my $db = WebPAC::Input->new( |
my $db = WebPAC::Input->new( |
45 |
module => 'WebPAC::Input::ISIS', |
module => 'WebPAC::Input::ISIS', |
|
low_mem => 1, |
|
46 |
); |
); |
47 |
|
|
48 |
$db->open( path => '/path/to/database' ); |
$db->open( path => '/path/to/database' ); |
62 |
my $db = new WebPAC::Input( |
my $db = new WebPAC::Input( |
63 |
module => 'WebPAC::Input::MARC', |
module => 'WebPAC::Input::MARC', |
64 |
encoding => 'ISO-8859-2', |
encoding => 'ISO-8859-2', |
|
low_mem => 1, |
|
65 |
recode => 'char pairs', |
recode => 'char pairs', |
66 |
no_progress_bar => 1, |
no_progress_bar => 1, |
67 |
); |
); |
73 |
used internally). This should probably be your terminal encoding, and by |
used internally). This should probably be your terminal encoding, and by |
74 |
default, it C<ISO-8859-2>. |
default, it C<ISO-8859-2>. |
75 |
|
|
|
Default is not to use C<low_mem> options (see L<MEMORY USAGE> below). |
|
|
|
|
76 |
C<recode> is optional string constisting of character or words pairs that |
C<recode> is optional string constisting of character or words pairs that |
77 |
should be replaced in input stream. |
should be replaced in input stream. |
78 |
|
|
92 |
|
|
93 |
$log->logconfess("code_page argument is not suppored any more. change it to encoding") if ($self->{lookup}); |
$log->logconfess("code_page argument is not suppored any more. change it to encoding") if ($self->{lookup}); |
94 |
$log->logconfess("lookup argument is not suppored any more. rewrite call to lookup_ref") if ($self->{lookup}); |
$log->logconfess("lookup argument is not suppored any more. rewrite call to lookup_ref") if ($self->{lookup}); |
95 |
|
$log->logconfess("low_mem argument is not suppored any more. rewrite it to load_row and save_row") if ($self->{low_mem}); |
96 |
|
|
97 |
$log->logconfess("specify low-level file format module") unless ($self->{module}); |
$log->logconfess("specify low-level file format module") unless ($self->{module}); |
98 |
my $module = $self->{module}; |
my $module_path = $self->{module}; |
99 |
$module =~ s#::#/#g; |
$module_path =~ s#::#/#g; |
100 |
$module .= '.pm'; |
$module_path .= '.pm'; |
101 |
$log->debug("require low-level module $self->{module} from $module"); |
$log->debug("require low-level module $self->{module} from $module_path"); |
|
|
|
|
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} = \&{ $n }; |
|
|
} |
|
|
} |
|
102 |
|
|
103 |
if ($self->{init}) { |
require $module_path; |
|
$log->debug("calling init"); |
|
|
$self->{init}->($self, @_); |
|
|
} |
|
104 |
|
|
105 |
$self->{'encoding'} ||= 'ISO-8859-2'; |
$self->{'encoding'} ||= 'ISO-8859-2'; |
106 |
|
|
|
# running with low_mem flag? well, use DBM::Deep then. |
|
|
if ($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; |
|
|
} |
|
|
|
|
107 |
$self ? return $self : return undef; |
$self ? return $self : return undef; |
108 |
} |
} |
109 |
|
|
111 |
|
|
112 |
This function will read whole database in memory and produce lookups. |
This function will read whole database in memory and produce lookups. |
113 |
|
|
114 |
|
my $store; # simple in-memory hash |
115 |
|
|
116 |
$input->open( |
$input->open( |
117 |
path => '/path/to/database/file', |
path => '/path/to/database/file', |
118 |
code_page => '852', |
code_page => 'cp852', |
119 |
limit => 500, |
limit => 500, |
120 |
offset => 6000, |
offset => 6000, |
|
lookup => $lookup_obj, |
|
121 |
stats => 1, |
stats => 1, |
122 |
lookup_ref => sub { |
lookup_coderef => sub { |
123 |
my ($k,$v) = @_; |
my $rec = shift; |
124 |
# store lookup $k => $v |
# store lookups |
125 |
}, |
}, |
126 |
modify_records => { |
modify_records => { |
127 |
900 => { '^a' => { ' : ' => '^b' } }, |
900 => { '^a' => { ' : ' => '^b' } }, |
128 |
901 => { '*' => { '^b' => ' ; ' } }, |
901 => { '*' => { '^b' => ' ; ' } }, |
129 |
}, |
}, |
130 |
|
modify_file => 'conf/modify/mapping.map', |
131 |
|
save_row => sub { |
132 |
|
my $a = shift; |
133 |
|
$store->{ $a->{id} } = $a->{row}; |
134 |
|
}, |
135 |
|
load_row => sub { |
136 |
|
my $a = shift; |
137 |
|
return defined($store->{ $a->{id} }) && |
138 |
|
$store->{ $a->{id} }; |
139 |
|
}, |
140 |
|
|
141 |
); |
); |
142 |
|
|
143 |
By default, C<code_page> is assumed to be C<852>. |
By default, C<code_page> is assumed to be C<cp852>. |
144 |
|
|
145 |
C<offset> is optional parametar to position at some offset before reading from database. |
C<offset> is optional parametar to position at some offset before reading from database. |
146 |
|
|
148 |
|
|
149 |
C<stats> create optional report about usage of fields and subfields |
C<stats> create optional report about usage of fields and subfields |
150 |
|
|
151 |
C<lookup_coderef> is closure to call when adding C<< key => 'value' >> combinations to |
C<lookup_coderef> is closure to called to save data into lookups |
|
lookup. |
|
152 |
|
|
153 |
C<modify_records> specify mapping from subfields to delimiters or from |
C<modify_records> specify mapping from subfields to delimiters or from |
154 |
delimiters to subfields, as well as oprations on fields (if subfield is |
delimiters to subfields, as well as oprations on fields (if subfield is |
155 |
defined as C<*>. |
defined as C<*>. |
156 |
|
|
157 |
|
C<modify_file> is alternative for C<modify_records> above which preserves order and offers |
158 |
|
(hopefully) simplier sintax than YAML or perl (see L</modify_file_regex>). This option |
159 |
|
overrides C<modify_records> if both exists for same input. |
160 |
|
|
161 |
|
C<save_row> and C<load_row> are low-level implementation of store engine. Calling convention |
162 |
|
is documented in example above. |
163 |
|
|
164 |
Returns size of database, regardless of C<offset> and C<limit> |
Returns size of database, regardless of C<offset> and C<limit> |
165 |
parametars, see also C<size>. |
parametars, see also C<size>. |
166 |
|
|
176 |
$log->logconfess("lookup_coderef must be CODE, not ",ref($arg->{lookup_coderef})) |
$log->logconfess("lookup_coderef must be CODE, not ",ref($arg->{lookup_coderef})) |
177 |
if ($arg->{lookup_coderef} && ref($arg->{lookup_coderef}) ne 'CODE'); |
if ($arg->{lookup_coderef} && ref($arg->{lookup_coderef}) ne 'CODE'); |
178 |
|
|
179 |
|
$log->debug( $arg->{lookup_coderef} ? '' : 'not ', "using lookup_coderef"); |
180 |
|
|
181 |
$log->logcroak("need path") if (! $arg->{'path'}); |
$log->logcroak("need path") if (! $arg->{'path'}); |
182 |
my $code_page = $arg->{'code_page'} || '852'; |
my $code_page = $arg->{'code_page'} || 'cp852'; |
183 |
|
|
184 |
# store data in object |
# store data in object |
185 |
$self->{'input_code_page'} = $code_page; |
$self->{'input_code_page'} = $code_page; |
187 |
$self->{$v} = $arg->{$v} if ($arg->{$v}); |
$self->{$v} = $arg->{$v} if ($arg->{$v}); |
188 |
} |
} |
189 |
|
|
190 |
# create Text::Iconv object |
if ($arg->{load_row} || $arg->{save_row}) { |
191 |
$self->{iconv} = Text::Iconv->new($code_page,$self->{'encoding'}); ## FIXME remove! |
$log->logconfess("save_row and load_row must be defined in pair and be CODE") unless ( |
192 |
|
ref($arg->{load_row}) eq 'CODE' && |
193 |
|
ref($arg->{save_row}) eq 'CODE' |
194 |
|
); |
195 |
|
$self->{load_row} = $arg->{load_row}; |
196 |
|
$self->{save_row} = $arg->{save_row}; |
197 |
|
$log->debug("using load_row and save_row instead of in-memory hash"); |
198 |
|
} |
199 |
|
|
200 |
my $filter_ref; |
my $filter_ref; |
201 |
my $recode_regex; |
my $recode_regex; |
219 |
|
|
220 |
} |
} |
221 |
|
|
222 |
my $rec_regex = $self->modify_record_regexps(%{ $arg->{modify_records} }); |
my $rec_regex; |
223 |
$log->debug("rec_regex: ", Dumper($rec_regex)); |
if (my $p = $arg->{modify_file}) { |
224 |
|
$log->debug("using modify_file $p"); |
225 |
my ($db, $size) = $self->{open_db}->( $self, |
$rec_regex = $self->modify_file_regexps( $p ); |
226 |
path => $arg->{path}, |
} elsif (my $h = $arg->{modify_records}) { |
227 |
filter => sub { |
$log->debug("using modify_records ", sub { dump( $h ) }); |
228 |
my ($l,$f_nr) = @_; |
$rec_regex = $self->modify_record_regexps(%{ $h }); |
229 |
return unless defined($l); |
} |
230 |
|
$log->debug("rec_regex: ", sub { dump($rec_regex) }) if ($rec_regex); |
|
## 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); |
|
231 |
|
|
232 |
# apply regexps |
my $class = $self->{module} || $log->logconfess("can't get low-level module name!"); |
|
if ($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}); |
|
|
} |
|
233 |
|
|
234 |
return $l; |
my $ll_db = $class->new( |
235 |
}, |
path => $arg->{path}, |
236 |
|
# filter => sub { |
237 |
|
# my ($l,$f_nr) = @_; |
238 |
|
# return unless defined($l); |
239 |
|
# from_to($l, $code_page, $self->{'encoding'}); |
240 |
|
# $l =~ s/($recode_regex)/$recode_map->{$1}/g if ($recode_regex && $recode_map); |
241 |
|
# return $l; |
242 |
|
# }, |
243 |
%{ $arg }, |
%{ $arg }, |
244 |
); |
); |
245 |
|
|
246 |
unless (defined($db)) { |
unless (defined($ll_db)) { |
247 |
$log->logwarn("can't open database $arg->{path}, skipping..."); |
$log->logwarn("can't open database $arg->{path}, skipping..."); |
248 |
return; |
return; |
249 |
} |
} |
250 |
|
|
251 |
|
my $size = $ll_db->size; |
252 |
|
|
253 |
unless ($size) { |
unless ($size) { |
254 |
$log->logwarn("no records in database $arg->{path}, skipping..."); |
$log->logwarn("no records in database $arg->{path}, skipping..."); |
255 |
return; |
return; |
281 |
|
|
282 |
$log->debug("position: $pos\n"); |
$log->debug("position: $pos\n"); |
283 |
|
|
284 |
my $rec = $self->{fetch_rec}->($self, $db, $pos ); |
my $rec = $ll_db->fetch_rec($pos, sub { |
285 |
|
my ($l,$f_nr,$debug) = @_; |
286 |
|
# return unless defined($l); |
287 |
|
# return $l unless ($rec_regex && $f_nr); |
288 |
|
|
289 |
|
return unless ( defined($l) && defined($f_nr) ); |
290 |
|
|
291 |
|
warn "-=> $f_nr ## |$l|\n" if ($debug); |
292 |
|
$log->debug("-=> $f_nr ## $l"); |
293 |
|
|
294 |
|
# codepage conversion and recode_regex |
295 |
|
from_to($l, $code_page, $self->{'encoding'}); |
296 |
|
$l =~ s/($recode_regex)/$recode_map->{$1}/g if ($recode_regex && $recode_map); |
297 |
|
|
298 |
|
# apply regexps |
299 |
|
if ($rec_regex && defined($rec_regex->{$f_nr})) { |
300 |
|
$log->logconfess("regexps->{$f_nr} must be ARRAY") if (ref($rec_regex->{$f_nr}) ne 'ARRAY'); |
301 |
|
my $c = 0; |
302 |
|
foreach my $r (@{ $rec_regex->{$f_nr} }) { |
303 |
|
my $old_l = $l; |
304 |
|
$log->logconfess("expected regex in ", dump( $r )) unless defined($r->{regex}); |
305 |
|
eval '$l =~ ' . $r->{regex}; |
306 |
|
if ($old_l ne $l) { |
307 |
|
my $d = "|$old_l| -> |$l| "; # . $r->{regex}; |
308 |
|
$d .= ' +' . $r->{line} . ' ' . $r->{file} if defined($r->{line}); |
309 |
|
$d .= ' ' . $r->{debug} if defined($r->{debug}); |
310 |
|
$log->debug("MODIFY $d"); |
311 |
|
warn "*** $d\n" if ($debug); |
312 |
|
|
313 |
$log->debug(sub { Dumper($rec) }); |
} |
314 |
|
$log->error("error applying regex: $r") if ($@); |
315 |
|
} |
316 |
|
} |
317 |
|
|
318 |
|
$log->debug("<=- $f_nr ## |$l|"); |
319 |
|
warn "<=- $f_nr ## $l\n" if ($debug); |
320 |
|
return $l; |
321 |
|
}); |
322 |
|
|
323 |
|
$log->debug(sub { dump($rec) }); |
324 |
|
|
325 |
if (! $rec) { |
if (! $rec) { |
326 |
$log->warn("record $pos empty? skipping..."); |
$log->warn("record $pos empty? skipping..."); |
328 |
} |
} |
329 |
|
|
330 |
# store |
# store |
331 |
if ($self->{low_mem}) { |
if ($self->{save_row}) { |
332 |
$self->{db}->put($pos, $rec); |
$self->{save_row}->({ |
333 |
|
id => $pos, |
334 |
|
row => $rec, |
335 |
|
}); |
336 |
} else { |
} else { |
337 |
$self->{data}->{$pos} = $rec; |
$self->{data}->{$pos} = $rec; |
338 |
} |
} |
343 |
# update counters for statistics |
# update counters for statistics |
344 |
if ($self->{stats}) { |
if ($self->{stats}) { |
345 |
|
|
346 |
|
# fetch clean record with regexpes applied for statistics |
347 |
|
my $rec = $ll_db->fetch_rec($pos); |
348 |
|
|
349 |
foreach my $fld (keys %{ $rec }) { |
foreach my $fld (keys %{ $rec }) { |
350 |
$self->{_stats}->{fld}->{ $fld }++; |
$self->{_stats}->{fld}->{ $fld }++; |
351 |
|
|
357 |
if (ref($row) eq 'HASH') { |
if (ref($row) eq 'HASH') { |
358 |
|
|
359 |
foreach my $sf (keys %{ $row }) { |
foreach my $sf (keys %{ $row }) { |
360 |
|
next if ($sf eq 'subfields'); |
361 |
$self->{_stats}->{sf}->{ $fld }->{ $sf }->{count}++; |
$self->{_stats}->{sf}->{ $fld }->{ $sf }->{count}++; |
362 |
$self->{_stats}->{sf}->{ $fld }->{ $sf }->{repeatable}++ |
$self->{_stats}->{sf}->{ $fld }->{ $sf }->{repeatable}++ |
363 |
if (ref($row->{$sf}) eq 'ARRAY'); |
if (ref($row->{$sf}) eq 'ARRAY'); |
381 |
$self->{max_pos} = $to_rec; |
$self->{max_pos} = $to_rec; |
382 |
$log->debug("max_pos: $to_rec"); |
$log->debug("max_pos: $to_rec"); |
383 |
|
|
384 |
|
# save for dump |
385 |
|
$self->{ll_db} = $ll_db; |
386 |
|
|
387 |
return $size; |
return $size; |
388 |
} |
} |
389 |
|
|
423 |
|
|
424 |
my $rec; |
my $rec; |
425 |
|
|
426 |
if ($self->{low_mem}) { |
if ($self->{load_row}) { |
427 |
$rec = $self->{db}->get($mfn); |
$rec = $self->{load_row}->({ id => $mfn }); |
428 |
} else { |
} else { |
429 |
$rec = $self->{data}->{$mfn}; |
$rec = $self->{data}->{$mfn}; |
430 |
} |
} |
479 |
|
|
480 |
sub seek { |
sub seek { |
481 |
my $self = shift; |
my $self = shift; |
482 |
my $pos = shift || return; |
my $pos = shift; |
483 |
|
|
484 |
my $log = $self->_get_logger(); |
my $log = $self->_get_logger(); |
485 |
|
|
486 |
|
$log->logconfess("called without pos") unless defined($pos); |
487 |
|
|
488 |
if ($pos < 1) { |
if ($pos < 1) { |
489 |
$log->warn("seek before first record"); |
$log->warn("seek before first record"); |
490 |
$pos = 1; |
$pos = 1; |
519 |
|
|
520 |
my $out = join("\n", |
my $out = join("\n", |
521 |
map { |
map { |
522 |
my $f = $_ || die "no field"; |
my $f = $_; |
523 |
|
die "no field in ", dump( $s->{fld} ) unless defined( $f ); |
524 |
my $v = $s->{fld}->{$f} || die "no s->{fld}->{$f}"; |
my $v = $s->{fld}->{$f} || die "no s->{fld}->{$f}"; |
525 |
$max_fld = $v if ($v > $max_fld); |
$max_fld = $v if ($v > $max_fld); |
526 |
|
|
543 |
} sort { $a cmp $b } keys %{ $s->{fld} } |
} sort { $a cmp $b } keys %{ $s->{fld} } |
544 |
); |
); |
545 |
|
|
546 |
$log->debug( sub { Dumper($s) } ); |
$log->debug( sub { dump($s) } ); |
547 |
|
|
548 |
return $out; |
return $out; |
549 |
} |
} |
550 |
|
|
551 |
|
=head2 dump_ascii |
552 |
|
|
553 |
|
Display humanly readable dump of record |
554 |
|
|
555 |
|
=cut |
556 |
|
|
557 |
|
sub dump_ascii { |
558 |
|
my $self = shift; |
559 |
|
|
560 |
|
return unless $self->{ll_db}; |
561 |
|
|
562 |
|
if ($self->{ll_db}->can('dump_rec')) { |
563 |
|
return $self->{ll_db}->dump_ascii( $self->{pos} ); |
564 |
|
} else { |
565 |
|
return dump( $self->{ll_db}->fetch_rec( $self->{pos} ) ); |
566 |
|
} |
567 |
|
} |
568 |
|
|
569 |
|
=head2 _get_regex |
570 |
|
|
571 |
|
Helper function called which create regexps to be execute on code. |
572 |
|
|
573 |
|
_get_regex( 900, 'regex:[0-9]+' ,'numbers' ); |
574 |
|
_get_regex( 900, '^b', ' : ^b' ); |
575 |
|
|
576 |
|
It supports perl regexps with C<regex:> prefix to from value and has |
577 |
|
additional logic to skip empty subfields. |
578 |
|
|
579 |
|
=cut |
580 |
|
|
581 |
|
sub _get_regex { |
582 |
|
my ($sf,$from,$to) = @_; |
583 |
|
|
584 |
|
# protect / |
585 |
|
$from =~ s!/!\\/!gs; |
586 |
|
$to =~ s!/!\\/!gs; |
587 |
|
|
588 |
|
if ($from =~ m/^regex:(.+)$/) { |
589 |
|
$from = $1; |
590 |
|
} else { |
591 |
|
$from = '\Q' . $from . '\E'; |
592 |
|
} |
593 |
|
if ($sf =~ /^\^/) { |
594 |
|
my $need_subfield_data = '*'; # no |
595 |
|
# if from is also subfield, require some data in between |
596 |
|
# to correctly skip empty subfields |
597 |
|
$need_subfield_data = '+' if ($from =~ m/^\\Q\^/); |
598 |
|
return |
599 |
|
's/\Q'. $sf .'\E([^\^]' . $need_subfield_data . '?)'. $from .'([^\^]*?)/'. $sf .'$1'. $to .'$2/'; |
600 |
|
} else { |
601 |
|
return |
602 |
|
's/'. $from .'/'. $to .'/g'; |
603 |
|
} |
604 |
|
} |
605 |
|
|
606 |
|
|
607 |
=head2 modify_record_regexps |
=head2 modify_record_regexps |
608 |
|
|
609 |
Generate hash with regexpes to be applied using L<filter>. |
Generate hash with regexpes to be applied using L<filter>. |
621 |
|
|
622 |
my $regexpes; |
my $regexpes; |
623 |
|
|
624 |
|
my $log = $self->_get_logger(); |
625 |
|
|
626 |
foreach my $f (keys %$modify_record) { |
foreach my $f (keys %$modify_record) { |
627 |
warn "--- f: $f\n"; |
$log->debug("field: $f"); |
628 |
|
|
629 |
foreach my $sf (keys %{ $modify_record->{$f} }) { |
foreach my $sf (keys %{ $modify_record->{$f} }) { |
630 |
warn "---- sf: $sf\n"; |
$log->debug("subfield: $sf"); |
631 |
|
|
632 |
foreach my $from (keys %{ $modify_record->{$f}->{$sf} }) { |
foreach my $from (keys %{ $modify_record->{$f}->{$sf} }) { |
633 |
my $to = $modify_record->{$f}->{$sf}->{$from}; |
my $to = $modify_record->{$f}->{$sf}->{$from}; |
634 |
#die "no field?" unless defined($to); |
#die "no field?" unless defined($to); |
635 |
warn "----- transform: |$from| -> |$to|\n"; |
my $d = "|$from| -> |$to|"; |
636 |
|
$log->debug("transform: $d"); |
|
if ($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"; |
|
|
} |
|
637 |
|
|
638 |
|
my $regex = _get_regex($sf,$from,$to); |
639 |
|
push @{ $regexpes->{$f} }, { regex => $regex, debug => $d }; |
640 |
|
$log->debug("regex: $regex"); |
641 |
} |
} |
642 |
} |
} |
643 |
} |
} |
645 |
return $regexpes; |
return $regexpes; |
646 |
} |
} |
647 |
|
|
648 |
=head1 MEMORY USAGE |
=head2 modify_file_regexps |
649 |
|
|
650 |
|
Generate hash with regexpes to be applied using L<filter> from |
651 |
|
pseudo hash/yaml format for regex mappings. |
652 |
|
|
653 |
|
It should be obvious: |
654 |
|
|
655 |
|
200 |
656 |
|
'^a' |
657 |
|
' : ' => '^e' |
658 |
|
' = ' => '^d' |
659 |
|
|
660 |
|
In field I<200> find C<'^a'> and then C<' : '>, and replace it with C<'^e'>. |
661 |
|
In field I<200> find C<'^a'> and then C<' = '>, and replace it with C<'^d'>. |
662 |
|
|
663 |
|
my $regexpes = $input->modify_file_regexps( 'conf/modify/common.pl' ); |
664 |
|
|
665 |
|
On undef path it will just return. |
666 |
|
|
667 |
|
=cut |
668 |
|
|
669 |
|
sub modify_file_regexps { |
670 |
|
my $self = shift; |
671 |
|
|
672 |
|
my $modify_path = shift || return; |
673 |
|
|
674 |
|
my $log = $self->_get_logger(); |
675 |
|
|
676 |
|
my $regexpes; |
677 |
|
|
678 |
|
CORE::open(my $fh, $modify_path) || $log->logdie("can't open modify file $modify_path: $!"); |
679 |
|
|
680 |
C<low_mem> options is double-edged sword. If enabled, WebPAC |
my ($f,$sf); |
|
will run on memory constraint machines (which doesn't have enough |
|
|
physical RAM to create memory structure for whole source database). |
|
|
|
|
|
If your machine has 512Mb or more of RAM and database is around 10000 records, |
|
|
memory shouldn't be an issue. If you don't have enough physical RAM, you |
|
|
might consider using virtual memory (if your operating system is handling it |
|
|
well, like on FreeBSD or Linux) instead of dropping to L<DBM::Deep> to handle |
|
|
parsed structure of ISIS database (this is what C<low_mem> option does). |
|
|
|
|
|
Hitting swap at end of reading source database is probably o.k. However, |
|
|
hitting swap before 90% will dramatically decrease performance and you will |
|
|
be better off with C<low_mem> and using rest of availble memory for |
|
|
operating system disk cache (Linux is particuallary good about this). |
|
|
However, every access to database record will require disk access, so |
|
|
generation phase will be slower 10-100 times. |
|
|
|
|
|
Parsed structures are essential - you just have option to trade RAM memory |
|
|
(which is fast) for disk space (which is slow). Be sure to have planty of |
|
|
disk space if you are using C<low_mem> and thus L<DBM::Deep>. |
|
|
|
|
|
However, when WebPAC is running on desktop machines (or laptops :-), it's |
|
|
highly undesireable for system to start swapping. Using C<low_mem> option can |
|
|
reduce WecPAC memory usage to around 64Mb for same database with lookup |
|
|
fields and sorted indexes which stay in RAM. Performance will suffer, but |
|
|
memory usage will really be minimal. It might be also more confortable to |
|
|
run WebPAC reniced on those machines. |
|
681 |
|
|
682 |
|
while(<$fh>) { |
683 |
|
chomp; |
684 |
|
next if (/^#/ || /^\s*$/); |
685 |
|
|
686 |
|
if (/^\s*(\d+)\s*$/) { |
687 |
|
$f = $1; |
688 |
|
$log->debug("field: $f"); |
689 |
|
next; |
690 |
|
} elsif (/^\s*'([^']*)'\s*$/) { |
691 |
|
$sf = $1; |
692 |
|
$log->die("can't define subfiled before field in: $_") unless ($f); |
693 |
|
$log->debug("subfield: $sf"); |
694 |
|
} elsif (/^\s*'([^']*)'\s*=>\s*'([^']*)'\s*$/) { |
695 |
|
my ($from,$to) = ($1, $2); |
696 |
|
|
697 |
|
$log->debug("transform: |$from| -> |$to|"); |
698 |
|
|
699 |
|
my $regex = _get_regex($sf,$from,$to); |
700 |
|
push @{ $regexpes->{$f} }, { |
701 |
|
regex => $regex, |
702 |
|
file => $modify_path, |
703 |
|
line => $., |
704 |
|
}; |
705 |
|
$log->debug("regex: $regex"); |
706 |
|
} |
707 |
|
} |
708 |
|
|
709 |
|
return $regexpes; |
710 |
|
} |
711 |
|
|
712 |
=head1 AUTHOR |
=head1 AUTHOR |
713 |
|
|
715 |
|
|
716 |
=head1 COPYRIGHT & LICENSE |
=head1 COPYRIGHT & LICENSE |
717 |
|
|
718 |
Copyright 2005 Dobrica Pavlinusic, All Rights Reserved. |
Copyright 2005-2006 Dobrica Pavlinusic, All Rights Reserved. |
719 |
|
|
720 |
This program is free software; you can redistribute it and/or modify it |
This program is free software; you can redistribute it and/or modify it |
721 |
under the same terms as Perl itself. |
under the same terms as Perl itself. |