/usr/sbin/rt-fulltext-indexer-4 is in request-tracker4 4.4.2-2.
This file is owned by root:root, with mode 0o755.
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 | #!/usr/bin/perl
# BEGIN BPS TAGGED BLOCK {{{
#
# COPYRIGHT:
#
# This software is Copyright (c) 1996-2017 Best Practical Solutions, LLC
# <sales@bestpractical.com>
#
# (Except where explicitly superseded by other copyright notices)
#
#
# LICENSE:
#
# This work is made available to you under the terms of Version 2 of
# the GNU General Public License. A copy of that license should have
# been provided with this software, but in any event can be snarfed
# from www.gnu.org.
#
# This work is distributed in the hope that it will be useful, but
# WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
# General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
# 02110-1301 or visit their web page on the internet at
# http://www.gnu.org/licenses/old-licenses/gpl-2.0.html.
#
#
# CONTRIBUTION SUBMISSION POLICY:
#
# (The following paragraph is not intended to limit the rights granted
# to you to modify and distribute this software under the terms of
# the GNU General Public License and is only of importance to you if
# you choose to contribute your changes and enhancements to the
# community by submitting them to Best Practical Solutions, LLC.)
#
# By intentionally submitting any modifications, corrections or
# derivatives to this work, or any other work intended for use with
# Request Tracker, to Best Practical Solutions, LLC, you confirm that
# you are the copyright holder for those contributions and you grant
# Best Practical Solutions, LLC a nonexclusive, worldwide, irrevocable,
# royalty-free, perpetual, license to use, copy, create derivative
# works based on those contributions, and sublicense and distribute
# those contributions and any derivatives thereof.
#
# END BPS TAGGED BLOCK }}}
use strict;
use warnings;
use 5.010;
# fix lib paths, some may be relative
BEGIN { # BEGIN RT CMD BOILERPLATE
require File::Spec;
require Cwd;
my @libs = ("/usr/share/request-tracker4/lib", "/usr/local/share/request-tracker4/lib");
my $bin_path;
for my $lib (@libs) {
unless ( File::Spec->file_name_is_absolute($lib) ) {
$bin_path ||= ( File::Spec->splitpath(Cwd::abs_path(__FILE__)) )[1];
$lib = File::Spec->catfile( $bin_path, File::Spec->updir, $lib );
}
unshift @INC, $lib;
}
}
use RT -init;
use RT::Interface::CLI ();
use HTML::Entities;
use Getopt::Long qw(GetOptions);
my %OPT = ( memory => '2M', limit => 0 );
GetOptions( \%OPT,
"help|h!",
"debug!",
"quiet!",
"all!",
"limit=i",
"memory=s",
);
$OPT{limit} ||= 200;
RT::Interface::CLI->ShowHelp if $OPT{help};
use Fcntl ':flock';
if ( !flock main::DATA, LOCK_EX | LOCK_NB ) {
if ( $OPT{quiet} ) {
RT::Logger->info("$0 is already running; aborting silently, as requested");
exit;
}
else {
print STDERR "$0 is already running\n";
exit 1;
}
}
my $max_size = RT->Config->Get('MaxFulltextAttachmentSize');
my $db_type = RT->Config->Get('DatabaseType');
my $fts_config = $ENV{RT_FTS_CONFIG} ? JSON::from_json($ENV{RT_FTS_CONFIG})
: RT->Config->Get('FullTextSearch') || {};
unless ( $fts_config->{'Enable'} ) {
print STDERR <<EOT;
Full text search is disabled in your RT configuration. Run
/usr/sbin/rt-setup-fulltext-index to configure and enable it.
EOT
exit 1;
}
unless ( $fts_config->{'Indexed'} ) {
print STDERR <<EOT;
Full text search is enabled in your RT configuration, but not with any
full-text database indexing -- hence this tool is not required. Read
the documentation for %FullTextSearch in your RT_Config for more details.
EOT
exit 1;
}
if ( $db_type eq 'Oracle' ) {
my $index = $fts_config->{'IndexName'} || 'rt_fts_index';
$RT::Handle->dbh->do(
"begin ctx_ddl.sync_index(?, ?); end;", undef,
$index, $OPT{'memory'}
);
exit;
} elsif ( $fts_config->{Sphinx} ) {
print STDERR <<EOT;
Updates to the external Sphinx index are done via running the sphinx
`indexer` tool:
indexer rt
EOT
exit 1;
}
# Skip ACL checks. This saves a large number of unnecessary queries
# (for tickets, ACLs, and users) which are unnecessary, as we are
# running as the system user.
{
no warnings 'redefine';
no warnings 'once';
*RT::Attachment::_Value = \&DBIx::SearchBuilder::Record::_Value;
*RT::Attachments::Next = \&DBIx::SearchBuilder::Next;
}
my $LAST;
if ($db_type eq 'mysql') {
process_mysql();
} elsif ($db_type eq 'Pg') {
process_pg();
}
sub attachment_loop {
my $subref = shift;
my $table = $fts_config->{'Table'};
$LAST //= 0;
# Fetch in batches of size --limit
{
# Indexes all text/plain and text/html attachments
my $attachments = RT::Attachments->new( RT->SystemUser );
my $txn_alias = $attachments->Join(
ALIAS1 => 'main',
FIELD1 => 'TransactionId',
TABLE2 => 'Transactions',
FIELD2 => 'id',
);
$attachments->Limit(
ALIAS => $txn_alias,
FIELD => 'Type',
OPERATOR => 'NOT IN',
VALUE => ['EmailRecord', 'CommentEmailRecord'],
);
$attachments->Limit(
FIELD => 'ContentType',
OPERATOR => 'IN',
VALUE => ['text/plain', 'text/html'],
);
$attachments->Limit( FIELD => 'id', OPERATOR => '>', VALUE => $LAST );
$attachments->OrderBy( FIELD => 'id', ORDER => 'asc' );
$attachments->RowsPerPage( $OPT{'limit'} );
# Call back to the DB-specific part
$subref->($attachments);
$LAST = $attachments->Last->id if $attachments->Count;
redo if $OPT{'all'} and $attachments->Count == $OPT{'limit'};
}
}
sub process_bulk_insert {
my $dbh = $RT::Handle->dbh;
my ($statement, $error) = @_;
# Doing large inserts is faster than individual statements, but
# comes at a parsing cost; cache the statement handles (99% of which
# will be the same size) for a notable (2x) speed gain.
my %sthandles;
$sthandles{1} =
$dbh->prepare($statement->(1));
attachment_loop( sub {
my ($attachments) = @_;
my @insert;
my $found = 0;
while ( my $a = $attachments->Next ) {
debug("Found attachment #". $a->id );
if ( $max_size and $a->ContentLength > $max_size ){
debug("Attachment #" . $a->id . " is " . $a->ContentLength .
" bytes which is larger than configured MaxFulltextAttachmentSize " .
" of " . $max_size . ", skipping");
next;
}
my $text = $a->Content // "";
HTML::Entities::decode_entities($text) if $a->ContentType eq "text/html";
push @insert, join("\n", $a->Subject // "", $text), $a->id;
$found++;
}
return unless $found;
# $found should be the limit size on all but the last go-around.
$sthandles{$found} ||= $dbh->prepare($statement->($found));
return if eval { $sthandles{$found}->execute(@insert); };
# We can catch and recover from some errors; re-do row-by-row to
# know which row had which errors
while (@insert) {
my ($content, $id) = splice(@insert,0,2);
next if eval { $sthandles{1}->execute($content, $id); };
$error->($id, $content);
# If this was a semi-expected error, insert an empty
# tsvector, so we count this row as "indexed" for
# purposes of knowing where to pick up
eval { $sthandles{1}->execute( "", $id ) }
or die "Failed to insert empty row for attachment $id: " . $dbh->errstr;
}
});
}
sub process_mysql {
my $dbh = $RT::Handle->dbh;
my $table = $fts_config->{'Table'};
($LAST) = $dbh->selectrow_array("SELECT MAX(id) FROM $table");
my $insert = $fts_config->{Engine} eq "MyISAM" ? "INSERT DELAYED" : "INSERT";
process_bulk_insert(
sub {
my ($n) = @_;
return "$insert INTO $table(Content, id) VALUES "
. join(", ", ("(?,?)") x $n);
},
sub {
my ($id) = @_;
if ($dbh->err == 1366 and $dbh->state eq "HY000") {
warn "Attachment $id cannot be indexed. Most probably it contains invalid UTF8 bytes. ".
"Error: ". $dbh->errstr;
} else {
die "Attachment $id cannot be indexed: " . $dbh->errstr;
}
}
);
}
sub process_pg {
if ( $fts_config->{'Table'} ne 'Attachments' ) {
process_pg_insert();
} else {
process_pg_update();
}
}
sub process_pg_insert {
my $dbh = $RT::Handle->dbh;
my $table = $fts_config->{'Table'};
my $column = $fts_config->{'Column'};
($LAST) = $dbh->selectrow_array("SELECT MAX(id) FROM $table");
process_bulk_insert(
sub {
my ($n) = @_;
return "INSERT INTO $table($column, id) VALUES "
. join(", ", ("(TO_TSVECTOR(?),?)") x $n);
},
sub {
my ($id) = @_;
if ( $dbh->err == 7 && $dbh->state eq '54000' ) {
warn "Attachment $id cannot be indexed. Most probably it contains too many unique words. ".
"Error: ". $dbh->errstr;
} elsif ( $dbh->err == 7 && $dbh->state eq '22021' ) {
warn "Attachment $id cannot be indexed. Most probably it contains invalid UTF8 bytes. ".
"Error: ". $dbh->errstr;
} else {
die "Attachment $id cannot be indexed: " . $dbh->errstr;
}
}
);
}
sub process_pg_update {
my $dbh = $RT::Handle->dbh;
my $column = $fts_config->{'Column'};
($LAST) = $dbh->selectrow_array("SELECT MAX(id) FROM Attachments WHERE $column IS NOT NULL");
my $sth = $dbh->prepare("UPDATE Attachments SET $column = TO_TSVECTOR(?) WHERE id = ?");
attachment_loop( sub {
my ($attachments) = @_;
my @insert;
while ( my $a = $attachments->Next ) {
debug("Found attachment #". $a->id );
if ( $max_size and $a->ContentLength > $max_size ){
debug("Attachment #" . $a->id . " is " . $a->ContentLength .
" bytes which is larger than configured MaxFulltextAttachmentSize " .
" of " . $max_size . ", skipping");
next;
}
my $text = $a->Content // "";
HTML::Entities::decode_entities($text) if $a->ContentType eq "text/html";
push @insert, [join("\n", $a->Subject // "", $text), $a->id];
}
# Try in one database transaction; if it fails, we roll it back
# and try one statement at a time.
$dbh->begin_work;
my $ok = 1;
for (@insert) {
$ok = eval { $sth->execute( $_->[0], $_->[1] ) };
last unless $ok;
}
if ($ok) {
$dbh->commit;
return;
}
$dbh->rollback;
# Things didn't go well. Retry the UPDATE statements one row at
# a time, outside of the transaction.
for (@insert) {
my ($content, $id) = ($_->[0], $_->[1]);
next if eval { $sth->execute( $content, $id ) };
if ( $dbh->err == 7 && $dbh->state eq '54000' ) {
warn "Attachment $id cannot be indexed. Most probably it contains too many unique words. ".
"Error: ". $dbh->errstr;
} elsif ( $dbh->err == 7 && $dbh->state eq '22021' ) {
warn "Attachment $id cannot be indexed. Most probably it contains invalid UTF8 bytes. ".
"Error: ". $dbh->errstr;
} else {
die "Attachment $id cannot be indexed: " . $dbh->errstr;
}
# If this was a semi-expected error, insert an empty
# tsvector, so we count this row as "indexed" for
# purposes of knowing where to pick up
eval { $sth->execute( "", $id ) }
or die "Failed to insert empty row for attachment $id: " . $dbh->errstr;
}
});
}
# helper functions
sub debug { print @_, "\n" if $OPT{debug}; 1 }
sub error { $RT::Logger->error(_(@_)); 1 }
sub warning { $RT::Logger->warn(_(@_)); 1 }
=head1 NAME
rt-fulltext-indexer - Indexer for full text search
=head1 DESCRIPTION
This is a helper script to keep full text indexes in sync with data.
Read F<docs/full_text_indexing.pod> for complete details on how and when
to run it.
=cut
__DATA__
|