Skip to content

properly encode segment definitions from table so the hash will be the same as from query params #17029

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 15 commits into from
Feb 17, 2021
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions core/CronArchive.php
Original file line number Diff line number Diff line change
Expand Up @@ -885,11 +885,11 @@ private function invalidateWithSegments($idSites, $date, $period, $_forceInvalid
}

foreach ($this->segmentArchiving->getAllSegmentsToArchive($idSite) as $segmentDefinition) {
$params = new Parameters(new Site($idSite), $periodObj, new Segment($segmentDefinition, [$idSite], $periodObj->getDateStart(), $periodObj->getDateEnd()));
$params = new Parameters(new Site($idSite), $periodObj, new Segment(urlencode($segmentDefinition), [$idSite], $periodObj->getDateStart(), $periodObj->getDateEnd()));
if ($this->isThereExistingValidPeriod($params)) {
$this->logger->debug(' Found usable archive for {archive}, skipping invalidation.', ['archive' => $params]);
} else {
$this->getApiToInvalidateArchivedReport()->invalidateArchivedReports($idSite, $date, $period, $segmentDefinition,
$this->getApiToInvalidateArchivedReport()->invalidateArchivedReports($idSite, $date, $period, urlencode($segmentDefinition),
$cascadeDown = false, $_forceInvalidateNonexistant);
}
}
Expand Down
1 change: 1 addition & 0 deletions core/CronArchive/QueueConsumer.php
Original file line number Diff line number Diff line change
Expand Up @@ -510,6 +510,7 @@ private function findSegmentForArchive(&$archive)
$hash = substr($flag, 4);
$storedSegment = $this->segmentArchiving->findSegmentForHash($hash, $archive['idsite']);
if (!isset($storedSegment['definition'])) {
$this->logger->debug("Could not find stored segment for done flag hash: $flag");
$archive['segment'] = null;
return false;
}
Expand Down
12 changes: 6 additions & 6 deletions core/CronArchive/SegmentArchiving.php
Original file line number Diff line number Diff line change
Expand Up @@ -77,20 +77,20 @@ public function __construct($beginningOfTimeLastNInYears = self::DEFAULT_BEGINNI
$this->segmentListCache = $segmentListCache ?: new Transient();
$this->now = $now ?: Date::factory('now');
$this->logger = $logger ?: StaticContainer::get('Psr\Log\LoggerInterface');
$this->forceArchiveAllSegments = $this->getShouldForceArchiveAllSegments();
$this->forceArchiveAllSegments = self::getShouldForceArchiveAllSegments();
}

public function findSegmentForHash($hash, $idSite)
{
foreach ($this->getAllSegments() as $segment) {
if (!$this->isAutoArchivingEnabledFor($segment)
|| !$this->isSegmentForSite($segment, $idSite)
|| !self::isSegmentForSite($segment, $idSite)
) {
continue;
}

try {
$segmentObj = new Segment($segment['definition'], [$idSite]);
$segmentObj = new Segment(urlencode($segment['definition']), [$idSite]);
} catch (\Exception $ex) {
$this->logger->debug("Could not process segment {$segment['definition']} for site {$idSite}. Segment should not exist for the site, but does.");
continue;
Expand Down Expand Up @@ -205,7 +205,7 @@ public function getAllSegmentsToArchive($idSite)
return Rules::getSegmentsToProcess([$idSite]);
}

private function isSegmentForSite($segment, $idSite)
public static function isSegmentForSite($segment, $idSite)
{
return $segment['enable_only_idsite'] == 0
|| $segment['enable_only_idsite'] == $idSite;
Expand All @@ -216,7 +216,7 @@ public function isAutoArchivingEnabledFor($storedSegment)
return $this->forceArchiveAllSegments || !empty($storedSegment['auto_archive']);
}

private function getShouldForceArchiveAllSegments()
public static function getShouldForceArchiveAllSegments()
{
return !Rules::isBrowserTriggerEnabled() && !Rules::isBrowserArchivingAvailableForSegments();
}
Expand All @@ -227,7 +227,7 @@ public function reArchiveSegment($segmentInfo)
return;
}

$definition = $segmentInfo['definition'];
$definition = urlencode($segmentInfo['definition']);
$idSite = $segmentInfo['enable_only_idsite'] ?? 'all';

$idSites = Access::doAsSuperUser(function () use ($idSite) {
Expand Down
2 changes: 1 addition & 1 deletion core/DataAccess/Model.php
Original file line number Diff line number Diff line change
Expand Up @@ -621,7 +621,7 @@ public function getArchiveIdsForSegments($archiveTableName, array $segments, $ol
private function getDeletedSegmentWhereClause(array $segment)
{
$idSite = (int)$segment['enable_only_idsite'];
$segmentHash = Segment::getSegmentHash($segment['definition']);
$segmentHash = Segment::getSegmentHash(urlencode($segment['definition']));
// Valid segment hashes are md5 strings - just confirm that it is so it's safe for SQL injection
if (!ctype_xdigit($segmentHash)) {
throw new Exception($segment . ' expected to be an md5 hash');
Expand Down
55 changes: 29 additions & 26 deletions plugins/CoreConsole/tests/System/ArchiveCronTest.php
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,7 @@
namespace Piwik\Plugins\CoreConsole\tests\System;

use Piwik\CronArchive;
use Piwik\Http;
use Piwik\Plugins\SegmentEditor\API;
use Piwik\Site;
use Piwik\Tests\Framework\TestingEnvironmentVariables;
Expand Down Expand Up @@ -60,11 +61,35 @@ public static function setUpBeforeClass(): void
private static function addNewSegmentToPast()
{
Config::getInstance()->General['enable_browser_archiving_triggering'] = 0;
self::$fixture->getTestEnvironment()->overrideConfig('General', 'enable_browser_archiving_triggering', 0);
self::$fixture->getTestEnvironment()->save();

// add one segment and set it's created/updated time to some time in the past so we don't re-archive for it
$idSegment = API::getInstance()->add(self::NEW_SEGMENT_NAME, self::NEW_SEGMENT, self::$fixture->idSite, $autoArchive = 1, $enabledAllUsers = 1);
// add another segment w/ special encoded value
$idSegment2 = API::getInstance()->add(self::ENCODED_SEGMENT_NAME, self::ENCODED_SEGMENT, self::$fixture->idSite, $autoArchive = 1, $enabledAllUsers = 1);

// add another segment w/ special encoded value (but do it through the API which will use a definition query param which is not
// encoded the same as Request::getRawSegmentFromRequest()
$url = Fixture::getTestRooturl("") . '?' . http_build_query([
'module' => 'API',
'method' => 'SegmentEditor.add',
'name' => self::ENCODED_SEGMENT_NAME,
'definition' => self::ENCODED_SEGMENT,
'idSite' => self::$fixture->idSite,
'autoArchive' => 1,
'enabledAllUsers' => 1,
'format' => 'json',
'token_auth' => Fixture::getTokenAuth(),
]);
self::assertStringContainsString(urlencode(self::ENCODED_SEGMENT), $url);

$idSegment2 = Http::sendHttpRequest($url, 10);
$idSegment2 = json_decode($idSegment2, $isAssoc = true);
$idSegment2 = $idSegment2['value'];

Config::getInstance()->General['enable_browser_archiving_triggering'] = 1;
self::$fixture->getTestEnvironment()->overrideConfig('General', 'enable_browser_archiving_triggering', 1);
self::$fixture->getTestEnvironment()->save();

Db::exec("UPDATE " . Common::prefixTable('segment') . ' SET ts_created = \'2015-01-02 00:00:00\', ts_last_edit = \'2015-01-02 00:00:00\' WHERE idsegment IN (' . $idSegment . ", " . $idSegment2 . ")");
}

Expand Down Expand Up @@ -164,6 +189,7 @@ public function testArchivePhpCron()
{
self::$fixture->getTestEnvironment()->overrideConfig('General', 'enable_browser_archiving_triggering', 0);
self::$fixture->getTestEnvironment()->overrideConfig('General', 'browser_archiving_disabled_enforce', 1);
self::$fixture->getTestEnvironment()->save();

Config::getInstance()->General['enable_browser_archiving_triggering'] = 0;
Config::getInstance()->General['browser_archiving_disabled_enforce'] = 1;
Expand Down Expand Up @@ -197,12 +223,6 @@ public function testArchivePhpCron()
self::undoForceCurlCliMulti();
}

$expectedInvalidations = [];
$invalidationEntries = $this->getInvalidatedArchiveTableEntries();
$this->assertEquals($expectedInvalidations, $invalidationEntries);

$this->compareArchivePhpOutputAgainstExpected($output);

foreach ($this->getApiForTesting() as $testInfo) {

list($api, $params) = $testInfo;
Expand All @@ -228,6 +248,7 @@ public function testArchivePhpCronWithSingleReportRearchive()
{
self::$fixture->getTestEnvironment()->overrideConfig('General', 'enable_browser_archiving_triggering', 0);
self::$fixture->getTestEnvironment()->overrideConfig('General', 'browser_archiving_disabled_enforce', 1);
self::$fixture->getTestEnvironment()->save();

Config::getInstance()->General['enable_browser_archiving_triggering'] = 0;
Config::getInstance()->General['browser_archiving_disabled_enforce'] = 1;
Expand Down Expand Up @@ -323,24 +344,6 @@ private function runArchivePhpCron($options = array(), $archivePhpScript = false
return $output;
}

private function compareArchivePhpOutputAgainstExpected($output)
{
$fileName = 'test_ArchiveCronTest_archive_php_cron_output.txt';
list($pathProcessed, $pathExpected) = static::getProcessedAndExpectedDirs();

$expectedOutputFile = $pathExpected . $fileName;
$processedFile = $pathProcessed . $fileName;

file_put_contents($processedFile, $output);

try {
$this->assertTrue(is_readable($expectedOutputFile));
$this->assertEquals(file_get_contents($expectedOutputFile), $output);
} catch (Exception $ex) {
$this->comparisonFailures[] = $ex;
}
}

public static function provideContainerConfigBeforeClass()
{
return array(
Expand Down
Original file line number Diff line number Diff line change
@@ -1,6 +1,18 @@
<?xml version="1.0" encoding="utf-8" ?>
<results>
<result idSite="1" />
<result idSite="1">
<nb_uniq_visitors>4</nb_uniq_visitors>
<nb_users>0</nb_users>
<nb_visits>4</nb_visits>
<nb_actions>4</nb_actions>
<nb_visits_converted>4</nb_visits_converted>
<bounce_count>4</bounce_count>
<sum_visit_length>0</sum_visit_length>
<max_actions>1</max_actions>
<bounce_rate>100%</bounce_rate>
<nb_actions_per_visit>1</nb_actions_per_visit>
<avg_time_on_site>0</avg_time_on_site>
</result>
<result idSite="2" />
<result idSite="3" />
</results>
Original file line number Diff line number Diff line change
@@ -1,6 +1,42 @@
<?xml version="1.0" encoding="utf-8" ?>
<results>
<result idSite="1" />
<result idSite="2" />
<result idSite="3" />
<result idSite="1">
<nb_uniq_visitors>12</nb_uniq_visitors>
<nb_users>0</nb_users>
<nb_visits>12</nb_visits>
<nb_actions>15</nb_actions>
<nb_visits_converted>11</nb_visits_converted>
<bounce_count>10</bounce_count>
<sum_visit_length>305</sum_visit_length>
<max_actions>3</max_actions>
<bounce_rate>83%</bounce_rate>
<nb_actions_per_visit>1.3</nb_actions_per_visit>
<avg_time_on_site>25</avg_time_on_site>
</result>
<result idSite="2">
<nb_uniq_visitors>1</nb_uniq_visitors>
<nb_users>0</nb_users>
<nb_visits>1</nb_visits>
<nb_actions>1</nb_actions>
<nb_visits_converted>0</nb_visits_converted>
<bounce_count>1</bounce_count>
<sum_visit_length>0</sum_visit_length>
<max_actions>1</max_actions>
<bounce_rate>100%</bounce_rate>
<nb_actions_per_visit>1</nb_actions_per_visit>
<avg_time_on_site>0</avg_time_on_site>
</result>
<result idSite="3">
<nb_uniq_visitors>1</nb_uniq_visitors>
<nb_users>0</nb_users>
<nb_visits>1</nb_visits>
<nb_actions>3</nb_actions>
<nb_visits_converted>0</nb_visits_converted>
<bounce_count>0</bounce_count>
<sum_visit_length>1</sum_visit_length>
<max_actions>3</max_actions>
<bounce_rate>0%</bounce_rate>
<nb_actions_per_visit>3</nb_actions_per_visit>
<avg_time_on_site>1</avg_time_on_site>
</result>
</results>
Original file line number Diff line number Diff line change
@@ -1,6 +1,18 @@
<?xml version="1.0" encoding="utf-8" ?>
<results>
<result idSite="1" />
<result idSite="1">
<nb_uniq_visitors>11</nb_uniq_visitors>
<nb_users>0</nb_users>
<nb_visits>11</nb_visits>
<nb_actions>14</nb_actions>
<nb_visits_converted>10</nb_visits_converted>
<bounce_count>9</bounce_count>
<sum_visit_length>305</sum_visit_length>
<max_actions>3</max_actions>
<bounce_rate>82%</bounce_rate>
<nb_actions_per_visit>1.3</nb_actions_per_visit>
<avg_time_on_site>28</avg_time_on_site>
</result>
<result idSite="2" />
<result idSite="3" />
</results>
Original file line number Diff line number Diff line change
@@ -1,6 +1,36 @@
<?xml version="1.0" encoding="utf-8" ?>
<results>
<result idSite="1" />
<result idSite="2" />
<result idSite="3" />
<result idSite="1">
<nb_visits>12</nb_visits>
<nb_actions>15</nb_actions>
<nb_visits_converted>11</nb_visits_converted>
<bounce_count>10</bounce_count>
<sum_visit_length>305</sum_visit_length>
<max_actions>3</max_actions>
<bounce_rate>83%</bounce_rate>
<nb_actions_per_visit>1.3</nb_actions_per_visit>
<avg_time_on_site>25</avg_time_on_site>
</result>
<result idSite="2">
<nb_visits>1</nb_visits>
<nb_actions>1</nb_actions>
<nb_visits_converted>0</nb_visits_converted>
<bounce_count>1</bounce_count>
<sum_visit_length>0</sum_visit_length>
<max_actions>1</max_actions>
<bounce_rate>100%</bounce_rate>
<nb_actions_per_visit>1</nb_actions_per_visit>
<avg_time_on_site>0</avg_time_on_site>
</result>
<result idSite="3">
<nb_visits>1</nb_visits>
<nb_actions>3</nb_actions>
<nb_visits_converted>0</nb_visits_converted>
<bounce_count>0</bounce_count>
<sum_visit_length>1</sum_visit_length>
<max_actions>3</max_actions>
<bounce_rate>0%</bounce_rate>
<nb_actions_per_visit>3</nb_actions_per_visit>
<avg_time_on_site>1</avg_time_on_site>
</result>
</results>
14 changes: 14 additions & 0 deletions plugins/ExamplePlugin/API.php
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,8 @@
use Piwik\Archive;
use Piwik\DataTable;
use Piwik\DataTable\Row;
use Piwik\Piwik;
use Piwik\Segment;

/**
* API for plugin ExamplePlugin
Expand Down Expand Up @@ -48,6 +50,8 @@ public function getAnswerToLife($truth = true)
*/
public function getExampleReport($idSite, $period, $date, $segment = false)
{
Piwik::checkUserHasViewAccess($idSite);

$table = DataTable::makeFromSimpleArray(array(
array('label' => 'My Label 1', 'nb_visits' => '1'),
array('label' => 'My Label 2', 'nb_visits' => '5'),
Expand All @@ -66,8 +70,18 @@ public function getExampleReport($idSite, $period, $date, $segment = false)
*/
public function getExampleArchivedMetric($idSite, $period, $date, $segment = false)
{
Piwik::checkUserHasViewAccess($idSite);

$archive = Archive::build($idSite, $period, $date, $segment);
$dataTable = $archive->getDataTableFromNumeric([Archiver::EXAMPLEPLUGIN_METRIC_NAME, Archiver::EXAMPLEPLUGIN_CONST_METRIC_NAME]);
return $dataTable;
}

public function getSegmentHash($idSite, $segment)
{
Piwik::checkUserHasViewAccess($idSite);

$segment = new Segment($segment, [(int) $idSite]);
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

fyi do we maybe need to check for permissions here?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

it's the exampleplugin, so i guess it's not important, but it might be better to have a good demonstration, so I added it

return $segment->getHash();
}
}
8 changes: 8 additions & 0 deletions plugins/SegmentEditor/API.php
Original file line number Diff line number Diff line change
Expand Up @@ -390,6 +390,14 @@ public function getAll($idSite = false)

$segments = $this->sortSegmentsCreatedByUserFirst($segments);

$model = new \Piwik\Plugins\SitesManager\Model();
$allIdSites = $model->getSitesId();
foreach ($segments as &$segmentInfo) {
$idSites = !empty($segmentInfo['enable_only_idsite']) ? [(int) $segmentInfo['enable_only_idsite']] : $allIdSites;
$segmentObj = new Segment(urlencode($segmentInfo['definition']), $idSites);
$segmentInfo['hash'] = $segmentObj->getHash();
}

return $segments;
}

Expand Down
16 changes: 15 additions & 1 deletion plugins/SegmentEditor/SegmentEditor.php
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,7 @@
use Piwik\Common;
use Piwik\Config;
use Piwik\Container\StaticContainer;
use Piwik\CronArchive\SegmentArchiving;
use Piwik\DataAccess\ArchiveSelector;
use Piwik\Notification;
use Piwik\Piwik;
Expand Down Expand Up @@ -122,7 +123,20 @@ public function getKnownSegmentsToArchiveAllSites(&$segments)
public function getKnownSegmentsToArchiveForSite(&$segments, $idSite)
{
$model = new Model();
$segmentToAutoArchive = $model->getSegmentsToAutoArchive($idSite);
$segmentToAutoArchive = $model->getAllSegmentsAndIgnoreVisibility();

$forceAutoArchive = SegmentArchiving::getShouldForceArchiveAllSegments();
foreach ($segmentToAutoArchive as $index => $segmentInfo) {
if (!SegmentArchiving::isSegmentForSite($segmentInfo, $idSite)) {
unset($segmentToAutoArchive[$index]);
}

if (!$forceAutoArchive
&& empty($segmentInfo['auto_archive'])
) {
unset($segmentToAutoArchive[$index]);
}
}

foreach ($segmentToAutoArchive as $segmentInfo) {
$segments[] = $segmentInfo['definition'];
Expand Down
Loading