/usr/share/perl5/Data/Record.pm is in libdata-record-perl 0.02-4.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 | package Data::Record;
use warnings;
use strict;
=head1 NAME
Data::Record - "split" on steroids
=head1 VERSION
Version 0.02
=cut
our $VERSION = '0.02';
use constant NOT_FOUND => -1;
use constant ALL_RECORDS => -1;
use constant TRIM_RECORDS => 0;
=head1 SYNOPSIS
use Regexp::Common;
use Data::Record;
my $record = Data::Record->new({
split => "\n",
unless => $RE{quoted},
});
my @data = $record->records($data);
=head1 DESCRIPTION
Sometimes we need data split into records and a simple split on the input
record separator (C<$/>) or some other value fails because the values we're
splitting on may allowed in other parts of the data. Perhaps they're quoted.
Perhaps they're embedded in other data which should not be split up.
This module allows you to specify what you wish to split the data on, but also
speficy an "unless" regular expression. If the text in question matches the
"unless" regex, it will not be split there. This allows us to do things like
split on newlines unless newlines are embedded in quotes.
=head1 METHODS
=head2 new
Common usage:
my $record = Data::Record->new({
split => qr/$split/,
unless => qr/$unless/,
});
Advanced usage:
my $record = Data::Record->new({
split => qr/$split/,
unless => qr/$unless/, # optional
token => $token, # optional
chomp => 0, # optional
limit => $limit, # optional (do not use with trim)
trim => 1, # optional (do not use with limit)
fields => {
split => ',',
unless => $RE{quoted}, # from Regexp::Common
}
});
The constructor takes a hashref of key/value pairs to set the behavior of data
records to be created.
=over 4
=item * split
This is the value to split the data on. It may be either a regular expression
or a string.
Defaults to the current input record separator (C<$/>).
=item * unless
Data will be split into records matching the split value I<unless> they also
match this value. No default.
If you do not have an C<unless> value, use of this module is overkill.
=item * token
You will probably never need to set this value.
Internally, this module attempts to find a token which does not match any text
found in the data to be split and also does not match the split value. This is
necessary because we mask the data we don't want to split using this token.
This allows us to split the resulting text.
In the unlikely event that the module cannot find a token which is not in the
text, you may set the token value yourself to some string value. Do not set it
to a regular expression.
=item * chomp
By default, the split value is discarded (chomped) from each record. Set this
to a true value to keep the split value on each record. This differs slightly
from how it's done with split and capturing parentheses:
split /(\,)/, '3,4,5';
Ordinarily, this results in the following list:
( 3, ',', 4, ',', 5 )
This module assumes you want those values I<with> the preceding record. By
setting chomp to false, you get the following list:
( '3,', '4,' 5 )
=item * limit
The default split behavior is similar to this:
split $split_regex, $data;
Setting C<limit> will cause the behavior to act like this:
split $split_regex, $data, $limit
See C<perldoc -f split> for more information about the behavior of C<limit>.
You may not set both C<limit> and C<trim> in the constructor.
=item * trim
By default, we return all records. This means that due to the nature of split
and how we're doing things, we sometimes get a trailing null record. However,
setting this value causes the module to behave as if we had done this:
split $split_regex, $data, 0;
When C<split> is called with a zero as the third argument, trailing null values
are discarded. See C<perldoc -f split> for more information.
You may not set both C<limit> and C<trim> in the constructor.
B<Note>: This does I<not> trim white space around returned records.
=item * fields
By default, individual records are returned as strings. If you set C<fields>,
you pass in a hashref of arguments that are identical to what C<new> would take
and resulting records are returned as array references processed by a new
C<Data::Record> instance.
Example: a quick CSV parser which assumes that commas and newlines may both be
in quotes:
# four lines, but there are only three records! (newline in quotes)
$data = <<'END_DATA';
1,2,"programmer, perl",4,5
1,2,"programmer,
perl",4,5
1,2,3,4,5
END_DATA
$record = $RECORD->new({
split => "\n",
unless => $quoted,
trim => 1,
fields => {
split => ",",
unless => $quoted,
}
});
my @records = $record->records($data);
foreach my $fields (@records) {
foreach my $field = (@$fields);
# do something
}
}
Note that above example will not remove the quotes from individual fields.
=back
=cut
sub new {
my ( $class, $value_of ) = @_;
my %value_of = %$value_of;
# XXX fix this later after we have the core working
my $self = bless {}, $class;
unless ( exists $value_of{split} ) {
$value_of{split} = $/;
}
$self->split( $value_of{split} )->unless( $value_of{unless} )
->chomp( exists $value_of{chomp} ? $value_of{chomp} : 1 )
->limit( exists $value_of{limit} ? $value_of{limit} : ALL_RECORDS );
$self->token( $value_of{token} ) if exists $value_of{token};
if ( exists $value_of{trim} ) {
$self->_croak("You may not specify 'trim' if 'limit' is specified")
if exists $value_of{limit};
$self->trim(1);
}
$self->_fields( $value_of{fields} ) if exists $value_of{fields};
return $self;
}
##############################################################################
=head2 split
my $split = $record->split;
$record->split($on_value);
Getter/setter for split value. May be a regular expression or a scalar value.
=cut
sub split {
my $self = shift;
return $self->{split} unless @_;
my $split = shift;
$split = qr/\Q$split\E/ unless 'Regexp' eq ref $split;
$self->{split} = $split;
return $self;
}
##############################################################################
=head2 unless
my $unless = $self->unless;
$self->unless($is_value);
Getter/setter for unless value. May be a regular expression or a scalar value.
=cut
sub unless {
my $self = shift;
return $self->{unless} unless @_;
my $unless = shift;
$unless = '' unless defined $unless;
$unless = qr/\Q$unless\E/
unless 'Regexp' eq ref $unless
|| 'Regexp::Common' eq ref $unless;
$self->{unless} = $unless;
return $self;
}
##############################################################################
=head2 chomp
my $chomp = $record->chomp;
$record->chomp(0);
Getter/setter for boolean chomp value.
=cut
sub chomp {
my $self = shift;
return $self->{chomp} unless @_;
$self->{chomp} = shift;
return $self;
}
##############################################################################
=head2 limit
my $limit = $record->limit;
$record->limit(3);
Getter/setter for integer limit value.
=cut
sub limit {
my $self = shift;
return $self->{limit} unless @_;
my $limit = shift;
unless ( $limit =~ /^-?\d+$/ ) {
$self->_croak("limit must be an integer value, not ($limit)");
}
$self->{limit} = $limit;
return $self;
}
##############################################################################
=head2 trim
my $trim = $record->trim;
$record->trim(1);
Getter/setter for boolean limit value. Setting this value will cause any
previous C<limit> value to be overwritten.
=cut
sub trim {
my $self = shift;
return $self->{trim} unless @_;
my $limit = shift;
$self->{limit} = $limit ? TRIM_RECORDS : ALL_RECORDS;
}
##############################################################################
=head2 token
my $token = $record->token;
$record->token($string_not_found_in_text);
Getter/setter for token value. Token must be a string that does not match the
split value and is not found in the text.
You can return the current token value if you have set it in your code. If you
rely on this module to create a token (this is the normal behavior), it is not
available via this method until C<records> is called.
Setting the token to an undefined value causes L<Data::Record> to try and find
a token itself.
If the token matches the split value, this method will croak when you attempt
to set the token.
If the token is found in the data, the C<records> method will croak when it is
called.
=cut
sub token {
my $self = shift;
return $self->{token} unless @_;
my $token = shift;
if ( defined $token ) {
if ( $token =~ $self->split ) {
$self->_croak(
"Token ($token) must not match the split value (@{[$self->split]})"
);
}
}
$self->{token} = $token;
return $self;
}
##############################################################################
=head2 records
my @records = $record->records($data);
Returns C<@records> for C<$data> based upon current split criteria.
=cut
sub records {
my ( $self, $data ) = @_;
my $token = $self->_create_token($data);
my @values;
if ( defined( my $unless = $self->unless ) ) {
my $index = 0;
$data =~ s{($unless)}
{
$values[$index] = $1;
$token . $index++ . $token;
}gex;
#main::diag($data);
}
my $split = $self->split;
$split = $self->chomp ? $split : qr/($split)/;
# if they have a numeric split value, we don't want to split tokens
my $token_re = qr/\Q$token\E/;
$split = qr/(?<!$token_re)$split(?!$token_re)/
if 0 =~ $split;
my @records = split $split, $data, $self->limit;
unless ( $self->chomp ) {
my @new_records;
while ( defined( my $record = shift @records ) ) {
if (@records) {
$record = join '', $record, shift @records;
}
push @new_records, $record;
}
@records = @new_records;
}
foreach my $record (@records) {
unless ( NOT_FOUND eq index $record, $token ) {
$record =~ s{$token_re(\d+)$token_re}{$values[$1]}gex;
}
}
if ( my $field = $self->_fields ) {
$_ = [ $field->records($_) ] foreach @records;
}
return @records;
}
sub _fields {
my $self = shift;
return $self->{fields} unless @_;
my $fields = ref($self)->new(shift);
if ( defined( my $token = $self->token ) ) {
$fields->token($token);
}
$self->{fields} = $fields;
return $self;
}
my @tokens = map { $_ x 6 } qw( ~ ` ? " { } ! @ $ % ^ & * - _ + = );
sub _create_token {
my ( $self, $data ) = @_;
my $token;
if ( defined( $token = $self->token ) ) {
$self->_croak("Current token ($token) found in data")
unless NOT_FOUND eq index $data, $token;
}
foreach my $curr_token (@tokens) {
if ( NOT_FOUND eq index $data, $curr_token ) {
$token = $curr_token;
$self->token($token);
last;
}
}
if ( defined $token ) {
return $token;
}
my $tried = join ", ", @tokens;
$self->_croak(
"Could not determine a unique token for data. Tried ($tried)");
}
sub _croak {
my ( $self, $message ) = @_;
require Carp;
Carp::croak($message);
}
=head1 BUGS
It's possible to get erroneous results if the split value is C</\d+/>. I've
tried to work around this. Please let me know if there is a problem.
=head1 CAVEATS
This module must read I<all> of the data at once. This can make it slow for
larger data sets.
=head1 AUTHOR
Curtis "Ovid" Poe, C<< <ovid [at] cpan [dot] org> >>
=head1 BUGS
Please report any bugs or feature requests to
C<bug-data-record@rt.cpan.org>, or through the web interface at
L<http://rt.cpan.org/NoAuth/ReportBug.html?Queue=Data-Record>.
I will be notified, and then you'll automatically be notified of progress on
your bug as I make changes.
=head1 ACKNOWLEDGEMENTS
Thanks to the Monks for inspiration from
L<http://perlmonks.org/index.pl?node_id=492002>.
0.02 Thanks to Smylers and Stefano Rodighiero for catching POD errors.
=head1 COPYRIGHT & LICENSE
Copyright 2005 Curtis "Ovid" Poe, all rights reserved.
This program is free software; you can redistribute it and/or modify it
under the same terms as Perl itself.
=cut
1; # End of Data::Record
|