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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867
|
/*
* Copyright 2005-2009 Fabrice Colin
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program 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., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
*/
#include "config.h"
#include <string.h>
#include <strings.h>
#include <stdlib.h>
#include <sys/types.h>
#include <dirent.h>
#include <sys/stat.h>
#include <unistd.h>
#include <stdio.h>
#include <stdint.h>
#include <stdlib.h>
#ifdef HAVE_STATFS
#ifdef HAVE_SYS_VFS_H
#include <sys/vfs.h>
#define CHECK_DISK_SPACE 1
#else
#ifdef HAVE_SYS_STATFS_H
#include <sys/statfs.h>
#define CHECK_DISK_SPACE 1
#else
#ifdef HAVE_SYS_MOUNT_H
#if defined(__OpenBSD__)
#include <sys/param.h>
#endif
#include <sys/mount.h>
#define CHECK_DISK_SPACE 1
#endif
#endif
#endif
#else
#ifdef HAVE_STATVFS
#include <sys/statvfs.h>
#define CHECK_DISK_SPACE 1
#endif
#endif
#ifdef __FreeBSD__
#ifdef HAVE_SYSCTLBYNAME
#include <sys/sysctl.h>
#define CHECK_BATTERY_SYSCTL 1
#endif
#endif
#include <iostream>
#include <glibmm/ustring.h>
#include <glibmm/stringutils.h>
#include <glibmm/convert.h>
#include <glibmm/thread.h>
#include <glibmm/random.h>
#include "Memory.h"
#include "Url.h"
#include "MonitorFactory.h"
#include "CrawlHistory.h"
#ifdef HAVE_DBUS
#include "DBusIndex.h"
#endif
#include "DaemonState.h"
#include "OnDiskHandler.h"
#include "PinotSettings.h"
#include "ServerThreads.h"
using namespace std;
using namespace Glib;
static double getFSFreeSpace(const string &path)
{
double availableBlocks = 0.0;
double blockSize = 0.0;
int statSuccess = -1;
#ifdef HAVE_STATFS
struct statfs fsStats;
statSuccess = statfs(PinotSettings::getInstance().m_daemonIndexLocation.c_str(), &fsStats);
availableBlocks = (uintmax_t)fsStats.f_bavail;
blockSize = fsStats.f_bsize;
#else
#ifdef HAVE_STATVFS
struct statvfs vfsStats;
statSuccess = statvfs(path.c_str(), &vfsStats);
availableBlocks = (uintmax_t)vfsStats.f_bavail;
// f_frsize isn't supported by all implementations
blockSize = (vfsStats.f_frsize ? vfsStats.f_frsize : vfsStats.f_bsize);
#endif
#endif
// Did it fail ?
if ((statSuccess == -1) ||
(blockSize == 0.0))
{
return -1.0;
}
double mbRatio = blockSize / (1024 * 1024);
double availableMbSize = availableBlocks * mbRatio;
#ifdef DEBUG
cout << "DaemonState::getFSFreeSpace: " << availableBlocks << " blocks of " << blockSize
<< " bytes (" << mbRatio << ")" << endl;
#endif
return availableMbSize;
}
// A function object to stop Crawler threads with for_each()
struct StopCrawlerThreadFunc
{
public:
void operator()(map<unsigned int, WorkerThread *>::value_type &p)
{
string type(p.second->getType());
if (type == "CrawlerThread")
{
p.second->stop();
#ifdef DEBUG
cout << "StopCrawlerThreadFunc: stopped thread " << p.second->getId() << endl;
#endif
}
}
};
#ifdef HAVE_DBUS
DBusServletInfo::DBusServletInfo(DBusConnection *pConnection, DBusMessage *pRequest) :
m_pConnection(pConnection),
m_pRequest(pRequest),
m_pReply(NULL),
m_pArray(NULL),
m_simpleQuery(true),
m_pThread(NULL),
m_replied(false)
{
}
DBusServletInfo::~DBusServletInfo()
{
if (m_pReply != NULL)
{
dbus_message_unref(m_pReply);
}
if (m_pRequest != NULL)
{
dbus_message_unref(m_pRequest);
}
if (m_pConnection != NULL)
{
dbus_connection_unref(m_pConnection);
}
if (m_pArray != NULL)
{
// Free the array
g_ptr_array_free(m_pArray, TRUE);
}
}
bool DBusServletInfo::newReply(void)
{
if (m_pRequest == NULL)
{
return false;
}
m_pReply = dbus_message_new_method_return(m_pRequest);
if (m_pReply != NULL)
{
return true;
}
return false;
}
bool DBusServletInfo::newErrorReply(const string &name, const string &message)
{
if (m_pRequest == NULL)
{
return false;
}
if (m_pReply != NULL)
{
dbus_message_unref(m_pReply);
m_pReply = NULL;
}
string fullName(PINOT_DBUS_SERVICE_NAME);
fullName += ".";
fullName += name;
m_pReply = dbus_message_new_error(m_pRequest,
fullName.c_str(), message.c_str());
if (m_pReply != NULL)
{
return true;
}
return false;
}
bool DBusServletInfo::newReplyWithArray(void)
{
if (newReply() == true)
{
dbus_message_append_args(m_pReply,
DBUS_TYPE_ARRAY, DBUS_TYPE_STRING, &m_pArray->pdata, m_pArray->len,
DBUS_TYPE_INVALID);
return true;
}
return false;
}
bool DBusServletInfo::newQueryReply(const vector<DocumentInfo> &resultsList,
unsigned int resultsEstimate)
{
DBusMessageIter iter, subIter;
if (m_simpleQuery == false)
{
// Create the reply
if (newReply() == false)
{
return false;
}
// ...and attach a container
dbus_message_iter_init_append(m_pReply, &iter);
dbus_message_iter_append_basic(&iter, DBUS_TYPE_UINT32,
&resultsEstimate);
dbus_message_iter_open_container(&iter, DBUS_TYPE_ARRAY,
DBUS_TYPE_ARRAY_AS_STRING \
DBUS_STRUCT_BEGIN_CHAR_AS_STRING \
DBUS_TYPE_STRING_AS_STRING \
DBUS_TYPE_STRING_AS_STRING \
DBUS_STRUCT_END_CHAR_AS_STRING, &subIter);
}
else
{
// Create an array
// FIXME: use a container for this too
m_pArray = g_ptr_array_new();
}
for (vector<DocumentInfo>::const_iterator resultIter = resultsList.begin();
resultIter != resultsList.end(); ++resultIter)
{
unsigned int indexId = 0;
unsigned int docId = resultIter->getIsIndexed(indexId);
#ifdef DEBUG
cout << "DBusServletInfo::newQueryReply: adding result " << docId << endl;
#endif
if (m_simpleQuery == false)
{
// The document ID isn't needed here
if (DBusIndex::documentInfoToDBus(&subIter, 0, *resultIter) == false)
{
newErrorReply("Query", "Unknown error");
return false;
}
}
else if (docId > 0)
{
char docIdStr[64];
// We only need the document ID
snprintf(docIdStr, 64, "%u", docId);
g_ptr_array_add(m_pArray, const_cast<char*>(docIdStr));
}
}
if (m_simpleQuery == false)
{
// Close the container
dbus_message_iter_close_container(&iter, &subIter);
return true;
}
// Attach the array to the reply
return newReplyWithArray();
}
bool DBusServletInfo::reply(void)
{
// Send a reply ?
if ((m_pConnection != NULL) &&
(m_pReply != NULL) &&
(m_replied == false))
{
m_replied = true;
dbus_connection_send(m_pConnection, m_pReply, NULL);
dbus_connection_flush(m_pConnection);
#ifdef DEBUG
cout << "DBusServletInfo::reply: sent reply" << endl;
#endif
return true;
}
return false;
}
#endif
DaemonState::DaemonState() :
ThreadsManager(PinotSettings::getInstance().m_daemonIndexLocation, 4),
m_isReindex(false),
m_reload(false),
m_flush(false),
m_crawlHistory(PinotSettings::getInstance().getHistoryDatabaseName()),
m_pDiskMonitor(MonitorFactory::getMonitor()),
m_pDiskHandler(NULL),
m_crawlers(0)
{
FD_ZERO(&m_flagsSet);
// Override the number of indexing threads ?
char *pEnvVar = getenv("PINOT_MAXIMUM_INDEX_THREADS");
if ((pEnvVar != NULL) &&
(strlen(pEnvVar) > 0))
{
int threadsNum = atoi(pEnvVar);
if (threadsNum > 0)
{
m_maxIndexThreads = (unsigned int)threadsNum;
}
}
// Check disk usage every minute
m_timeoutConnection = Glib::signal_timeout().connect(sigc::mem_fun(*this,
&DaemonState::on_activity_timeout), 60000);
// Check right now before doing anything else
DaemonState::on_activity_timeout();
m_onThreadEndSignal.connect(sigc::mem_fun(*this, &DaemonState::on_thread_end));
}
DaemonState::~DaemonState()
{
// Don't delete m_pDiskMonitor and m_pDiskHandler, threads may need them
// Since DaemonState is destroyed when the program exits, it's a leak we can live with
}
bool DaemonState::on_activity_timeout(void)
{
if (m_timeoutConnection.blocked() == false)
{
#ifdef CHECK_DISK_SPACE
double availableMbSize = getFSFreeSpace(PinotSettings::getInstance().m_daemonIndexLocation);
if (availableMbSize >= 0)
{
#ifdef DEBUG
cout << "DaemonState::on_activity_timeout: " << availableMbSize << " Mb free for "
<< PinotSettings::getInstance().m_daemonIndexLocation << endl;
#endif
if (availableMbSize < PinotSettings::getInstance().m_minimumDiskSpace)
{
// Stop indexing
m_stopIndexing = true;
// Stop crawling
set_flag(LOW_DISK_SPACE);
stop_crawling();
cerr << "Stopped indexing because of low disk space" << endl;
}
else if (m_stopIndexing == true)
{
// Go ahead
m_stopIndexing = false;
reset_flag(LOW_DISK_SPACE);
cerr << "Resumed indexing following low disk space condition" << endl;
}
}
#endif
#ifdef CHECK_BATTERY_SYSCTL
// Check the battery state too
check_battery_state();
#endif
}
return true;
}
void DaemonState::check_battery_state(void)
{
#ifdef CHECK_BATTERY_SYSCTL
int acline = 1;
size_t len = sizeof(acline);
bool onBattery = false;
// Are we on battery power ?
if (sysctlbyname("hw.acpi.acline", &acline, &len, NULL, 0) == 0)
{
#ifdef DEBUG
cout << "DaemonState::check_battery_state: acline " << acline << endl;
#endif
if (acline == 0)
{
onBattery = true;
}
bool wasOnBattery = is_flag_set(ON_BATTERY);
if (onBattery != wasOnBattery)
{
if (onBattery == true)
{
// We are now on battery
set_flag(ON_BATTERY);
stop_crawling();
cout << "System is now on battery" << endl;
}
else
{
// Back on-line
reset_flag(ON_BATTERY);
start_crawling();
cout << "System is now on AC" << endl;
}
}
}
#endif
}
bool DaemonState::crawl_location(const PinotSettings::IndexableLocation &location)
{
string locationToCrawl(location.m_name);
bool doMonitoring = location.m_monitor;
bool isSource = location.m_isSource;
CrawlerThread *pCrawlerThread = NULL;
// Can we go ahead and crawl ?
if ((is_flag_set(LOW_DISK_SPACE) == true) ||
(is_flag_set(ON_BATTERY) == true))
{
#ifdef DEBUG
cout << "DaemonState::crawl_location: crawling was stopped" << endl;
#endif
return false;
}
if (locationToCrawl.empty() == true)
{
return false;
}
if (doMonitoring == false)
{
// Monitoring is not necessary, but we still have to pass the handler
// so that we can act on documents that have been deleted
pCrawlerThread = new CrawlerThread(locationToCrawl, isSource,
NULL, m_pDiskHandler);
}
else
{
pCrawlerThread = new CrawlerThread(locationToCrawl, isSource,
m_pDiskMonitor, m_pDiskHandler);
}
pCrawlerThread->getFileFoundSignal().connect(sigc::mem_fun(*this, &DaemonState::on_message_filefound));
if (start_thread(pCrawlerThread, true) == true)
{
++m_crawlers;
set_flag(CRAWLING);
return true;
}
return false;
}
void DaemonState::flush_and_reclaim(void)
{
IndexInterface *pIndex = PinotSettings::getInstance().getIndex(PinotSettings::getInstance().m_daemonIndexLocation);
if (pIndex != NULL)
{
#ifdef HAVE_DBUS
DBusServletThread::flushIndexAndSignal(pIndex);
#endif
delete pIndex;
}
int inUse = Memory::getUsage();
Memory::reclaim();
}
void DaemonState::start(bool isReindex)
{
// Disable implicit flushing after a change
WorkerThread::immediateFlush(false);
m_isReindex = isReindex;
// Fire up the disk monitor thread
if (m_pDiskHandler == NULL)
{
OnDiskHandler *pDiskHandler = new OnDiskHandler();
pDiskHandler->getFileFoundSignal().connect(sigc::mem_fun(*this, &DaemonState::on_message_filefound));
m_pDiskHandler = pDiskHandler;
}
MonitorThread *pDiskMonitorThread = new MonitorThread(m_pDiskMonitor, m_pDiskHandler);
start_thread(pDiskMonitorThread, true);
for (set<PinotSettings::IndexableLocation>::const_iterator locationIter = PinotSettings::getInstance().m_indexableLocations.begin();
locationIter != PinotSettings::getInstance().m_indexableLocations.end(); ++locationIter)
{
m_crawlQueue.push(*locationIter);
}
#ifdef DEBUG
cout << "DaemonState::start: " << m_crawlQueue.size() << " locations to crawl" << endl;
#endif
// Update all items status so that we can get rid of files from deleted sources
m_crawlHistory.updateItemsStatus(CrawlHistory::CRAWLING, CrawlHistory::TO_CRAWL, 0, true);
m_crawlHistory.updateItemsStatus(CrawlHistory::CRAWLED, CrawlHistory::TO_CRAWL, 0, true);
m_crawlHistory.updateItemsStatus(CrawlHistory::CRAWL_ERROR, CrawlHistory::TO_CRAWL, 0, true);
// Initiate crawling
start_crawling();
}
void DaemonState::reload(void)
{
// Reload whenever possible
m_reload = true;
}
bool DaemonState::start_crawling(void)
{
bool startedCrawler = false;
if (write_lock_lists() == true)
{
#ifdef DEBUG
cout << "DaemonState::start_crawling: " << m_crawlQueue.size() << " locations to crawl, "
<< m_crawlers << " crawlers" << endl;
#endif
// Get the next location, unless something is still being crawled
if (m_crawlers == 0)
{
reset_flag(CRAWLING);
if (m_crawlQueue.empty() == false)
{
PinotSettings::IndexableLocation nextLocation(m_crawlQueue.front());
startedCrawler = crawl_location(nextLocation);
}
else
{
set<string> deletedFiles;
// All files left with status TO_CRAWL belong to deleted sources
if ((m_pDiskHandler != NULL) &&
(m_crawlHistory.getItems(CrawlHistory::TO_CRAWL, deletedFiles) > 0))
{
#ifdef DEBUG
cout << "DaemonState::start_crawling: " << deletedFiles.size() << " orphaned files" << endl;
#endif
for(set<string>::const_iterator fileIter = deletedFiles.begin();
fileIter != deletedFiles.end(); ++fileIter)
{
// Inform the MonitorHandler
m_pDiskHandler->fileDeleted(fileIter->substr(7));
// Delete this item
m_crawlHistory.deleteItem(*fileIter);
}
}
}
}
unlock_lists();
}
return startedCrawler;
}
void DaemonState::stop_crawling(void)
{
if (write_lock_threads() == true)
{
if (m_threads.empty() == false)
{
// Stop all Crawler threads
for_each(m_threads.begin(), m_threads.end(), StopCrawlerThreadFunc());
}
unlock_threads();
}
}
void DaemonState::on_thread_end(WorkerThread *pThread)
{
string indexedUrl;
bool emptyQueue = false;
if (pThread == NULL)
{
return;
}
string type(pThread->getType());
bool isStopped = pThread->isStopped();
#ifdef DEBUG
cout << "DaemonState::on_thread_end: end of thread " << type << " " << pThread->getId() << endl;
#endif
// What type of thread was it ?
if (type == "CrawlerThread")
{
CrawlerThread *pCrawlerThread = dynamic_cast<CrawlerThread *>(pThread);
if (pCrawlerThread == NULL)
{
delete pThread;
return;
}
--m_crawlers;
#ifdef DEBUG
cout << "DaemonState::on_thread_end: done crawling " << pCrawlerThread->getDirectory() << endl;
#endif
if (isStopped == false)
{
// Pop the queue
m_crawlQueue.pop();
m_flush = true;
}
// Else, the directory wasn't fully crawled so better leave it in the queue
start_crawling();
}
else if (type == "IndexingThread")
{
IndexingThread *pIndexThread = dynamic_cast<IndexingThread *>(pThread);
if (pIndexThread == NULL)
{
delete pThread;
return;
}
// Get the URL we have just indexed
indexedUrl = pIndexThread->getURL();
// Did it fail ?
int errorNum = pThread->getErrorNum();
if ((errorNum > 0) &&
(indexedUrl.empty() == false))
{
// An entry should already exist for this
m_crawlHistory.updateItem(indexedUrl, CrawlHistory::CRAWL_ERROR, time(NULL), errorNum);
}
}
else if (type == "UnindexingThread")
{
// FIXME: anything to do ?
}
else if (type == "MonitorThread")
{
// FIXME: do something about this
}
#ifdef HAVE_DBUS
else if (type == "DBusServletThread")
{
DBusServletThread *pDBusThread = dynamic_cast<DBusServletThread *>(pThread);
if (pDBusThread == NULL)
{
delete pThread;
return;
}
// Send the reply ?
DBusServletInfo *pInfo = pDBusThread->getServletInfo();
if (pInfo != NULL)
{
if (pInfo->m_pThread != NULL)
{
m_servletsInfo.insert(pInfo);
start_thread(pInfo->m_pThread);
}
else
{
pInfo->reply();
delete pInfo;
}
}
if (pDBusThread->mustQuit() == true)
{
// Disconnect the timeout signal
if (m_timeoutConnection.connected() == true)
{
m_timeoutConnection.block();
m_timeoutConnection.disconnect();
}
m_signalQuit(0);
}
}
#endif
else if (type == "QueryingThread")
{
QueryingThread *pQueryThread = dynamic_cast<QueryingThread *>(pThread);
if (pQueryThread == NULL)
{
delete pThread;
return;
}
bool wasCorrected = false;
QueryProperties queryProps(pQueryThread->getQuery(wasCorrected));
const vector<DocumentInfo> &resultsList = pQueryThread->getDocuments();
#ifdef HAVE_DBUS
// Find the servlet info
for (set<DBusServletInfo *>::const_iterator servIter = m_servletsInfo.begin();
servIter != m_servletsInfo.end(); ++servIter)
{
DBusServletInfo *pInfo = const_cast<DBusServletInfo *>(*servIter);
if ((pInfo != NULL) &&
(pInfo->m_pThread->getId() == pThread->getId()))
{
#ifdef DEBUG
cout << "DaemonState::on_thread_end: ran query " << queryProps.getName() << endl;
#endif
// Prepare and send the reply
pInfo->newQueryReply(resultsList, pQueryThread->getDocumentsCount());
pInfo->reply();
m_servletsInfo.erase(servIter);
delete pInfo;
break;
}
}
#endif
}
else if (type == "RestoreMetaDataThread")
{
// Do the actual flush here
flush_and_reclaim();
}
// Delete the thread
delete pThread;
// Wait until there are no threads running (except background ones)
// to reload the configuration
if ((m_reload == true) &&
(get_threads_count() == 0))
{
#ifdef DEBUG
cout << "DaemonState::on_thread_end: stopping all threads" << endl;
#endif
// Stop background threads
stop_threads();
// ...clear the queues
clear_queues();
// Reload
PinotSettings &settings = PinotSettings::getInstance();
settings.clear();
settings.load(PinotSettings::LOAD_ALL);
m_reload = false;
// ...and restart everything
start(false);
}
// Try to run a queued action unless threads were stopped
if (isStopped == false)
{
emptyQueue = pop_queue(indexedUrl);
}
// Wait until there are no threads running (except background ones)
// and the queue is empty to flush the index
if ((m_flush == true) &&
(emptyQueue == true) &&
(get_threads_count() == 0))
{
m_flush = false;
if ((m_isReindex == true) &&
(m_crawlQueue.empty() == true))
{
// Restore metadata on documents and flush when the tread returns
RestoreMetaDataThread *pRestoreThread = new RestoreMetaDataThread();
start_thread(pRestoreThread);
}
else
{
// Flush now
flush_and_reclaim();
}
}
}
void DaemonState::on_message_filefound(DocumentInfo docInfo, bool isDirectory)
{
if (isDirectory == false)
{
queue_index(docInfo);
}
else
{
PinotSettings::IndexableLocation newLocation;
newLocation.m_monitor = true;
newLocation.m_name = docInfo.getLocation().substr(7);
newLocation.m_isSource = false;
#ifdef DEBUG
cout << "DaemonState::on_message_filefound: new directory " << newLocation.m_name << endl;
#endif
// Queue this directory for crawling
m_crawlQueue.push(newLocation);
start_crawling();
}
}
sigc::signal1<void, int>& DaemonState::getQuitSignal(void)
{
return m_signalQuit;
}
void DaemonState::set_flag(StatusFlag flag)
{
FD_SET((int)flag, &m_flagsSet);
}
bool DaemonState::is_flag_set(StatusFlag flag)
{
if (FD_ISSET((int)flag, &m_flagsSet))
{
return true;
}
return false;
}
void DaemonState::reset_flag(StatusFlag flag)
{
FD_CLR((int)flag, &m_flagsSet);
}
|