Skip to content

wikiMetrics: fix zero count occassions #972

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.

Sign up for GitHub

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
deer-wmde merged 6 commits into from
Sep 5, 2025
Merged

wikiMetrics: fix zero count occassions #972

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
831ec42
add dataProvider for test
deer-wmde Sep 4, 2025
f05d687
add the fix
deer-wmde Sep 4, 2025
903fbe0
lintin
deer-wmde Sep 4, 2025
186d157
more linting
deer-wmde Sep 4, 2025
718ce14
even more linting
deer-wmde Sep 4, 2025
e163d9e
linting
deer-wmde Sep 4, 2025
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
13 changes: 9 additions & 4 deletions app/Metrics/App/WikiMetrics.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -199,10 +199,15 @@ private function getNumberOfEntities(): array {
$conn = $manager->connection('mw');
$pdo = $conn->getPdo();
$result = $pdo->query($query)->fetchAll(PDO::FETCH_ASSOC);
if (count($result) === 0) {
return [120 => 0, 122 => 0, 146 => 0, 640 => 0];
}

return array_column($result, 'count', 'namespace');
$result = array_column($result, 'count', 'namespace');

// make sure the array keys are set
$result[120] ??= 0;
$result[122] ??= 0;
$result[146] ??= 0;
$result[640] ??= 0;

return $result;
}
}
218 changes: 157 additions & 61 deletions tests/Metrics/WikiMetricsTest.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -168,7 +168,157 @@ public function testSaveNullForFailedRequestOfTriplesCount() {
]);
}

public function testSavesEntityCountsCorrectly() {
public static function dummyDataProvider() {
$item1 = [
'page_namespace' => 120,
'page_is_redirect' => 0,
'page_title' => 'foo',
'page_random' => 0,
'page_touched' => random_bytes(10),
'page_latest' => 1,
'page_len' => 2,
];

$item2 = [
'page_namespace' => 120,
'page_is_redirect' => 0,
'page_title' => 'bar',
'page_random' => 0,
'page_touched' => random_bytes(10),
'page_latest' => 0,
'page_len' => 2,
];

$property = [
'page_namespace' => 122,
'page_is_redirect' => 0,
'page_title' => 'foo',
'page_random' => 0,
'page_touched' => random_bytes(10),
'page_latest' => 1,
'page_len' => 2,
];

$entitySchema = [
'page_namespace' => 640,
'page_is_redirect' => 0,
'page_title' => 'bar',
'page_random' => 0,
'page_touched' => random_bytes(10),
'page_latest' => 1,
'page_len' => 2,
];

$entitySchemaRedirect = [
'page_namespace' => 640,
'page_is_redirect' => 1,
'page_title' => 'foo',
'page_random' => 0,
'page_touched' => random_bytes(10),
'page_latest' => 1,
'page_len' => 2,
];

$lexeme = [
'page_namespace' => 146,
'page_is_redirect' => 0,
'page_title' => 'foo',
'page_random' => 0,
'page_touched' => random_bytes(10),
'page_latest' => 1,
'page_len' => 2,
];

// all relevant data types
yield [
'expectedItemCount' => 2,
'expectedPropertyCount' => 1,
'expectedLexemeCount' => 1,
'expectedEntitySchemaCount' => 1,

'pageData' => [
$item1,
$item2,
$property,
$lexeme,
$entitySchema,
$entitySchemaRedirect,
],
];

// zero items
yield [
'expectedItemCount' => 0,
'expectedPropertyCount' => 1,
'expectedLexemeCount' => 1,
'expectedEntitySchemaCount' => 1,

'pageData' => [
// $item1,
// $item2,
$property,
$lexeme,
$entitySchema,
$entitySchemaRedirect,
],
];

// zero properties
yield [
'expectedItemCount' => 2,
'expectedPropertyCount' => 0,
'expectedLexemeCount' => 1,
'expectedEntitySchemaCount' => 1,

'pageData' => [
$item1,
$item2,
// $property,
$lexeme,
$entitySchema,
$entitySchemaRedirect,
],
];

// zero Lexemes
yield [
'expectedItemCount' => 2,
'expectedPropertyCount' => 1,
'expectedLexemeCount' => 0,
'expectedEntitySchemaCount' => 1,

'pageData' => [
$item1,
$item2,
$property,
// $lexeme,
$entitySchema,
$entitySchemaRedirect,
],
];

// zero EntitySchemas
yield [
'expectedItemCount' => 2,
'expectedPropertyCount' => 1,
'expectedLexemeCount' => 1,
'expectedEntitySchemaCount' => 0,

'pageData' => [
$item1,
$item2,
$property,
$lexeme,
// $entitySchema,
$entitySchemaRedirect, // should not count
],
];
}

/**
* @dataProvider dummyDataProvider
*/
public function testSavesEntityCountsCorrectly($expectedItemCount, $expectedPropertyCount, $expectedLexemeCount, $expectedEntitySchemaCount, $pageData) {
$wiki = Wiki::factory()->create([
'domain' => 'entitycounttest.wikibase.cloud',
]);
Expand All @@ -191,66 +341,12 @@ public function testSavesEntityCountsCorrectly() {
});

// Insert dummy data
DB::table($tablePage)->insert([
[
'page_namespace' => 120,
'page_is_redirect' => 0,
'page_title' => 'foo',
'page_random' => 0,
'page_touched' => random_bytes(10),
'page_latest' => 1,
'page_len' => 2,
], // item
[
'page_namespace' => 120,
'page_is_redirect' => 0,
'page_title' => 'bar',
'page_random' => 0,
'page_touched' => random_bytes(10),
'page_latest' => 0,
'page_len' => 2,
], // item
[
'page_namespace' => 122,
'page_is_redirect' => 0,
'page_title' => 'foo',
'page_random' => 0,
'page_touched' => random_bytes(10),
'page_latest' => 1,
'page_len' => 2], // property
[
'page_namespace' => 640,
'page_is_redirect' => 0,
'page_title' => 'bar',
'page_random' => 0,
'page_touched' => random_bytes(10),
'page_latest' => 1,
'page_len' => 2,
], // entity schema
[
'page_namespace' => 146,
'page_is_redirect' => 0,
'page_title' => 'foo',
'page_random' => 0,
'page_touched' => random_bytes(10),
'page_latest' => 1,
'page_len' => 2,
], // lexeme
[
'page_namespace' => 640,
'page_is_redirect' => 1,
'page_title' => 'foo',
'page_random' => 0,
'page_touched' => random_bytes(10),
'page_latest' => 1,
'page_len' => 2,
], // entity schema
]);
DB::table($tablePage)->insert($pageData);
WikiDailyMetrics::create([
'id' => $wiki->id . '_' . now()->subDay()->toDateString(),
'wiki_id' => $wiki->id,
'date' => now()->subDay()->toDateString(),
'pages' => 6,
'pages' => count($pageData),
'is_deleted' => 0,
]);

Expand All @@ -262,10 +358,10 @@ public function testSavesEntityCountsCorrectly() {

$this->assertDatabaseHas('wiki_daily_metrics', [
'wiki_id' => $wiki->id,
'item_count' => 2,
'property_count' => 1,
'lexeme_count' => 1,
'entity_schema_count' => 1, // the redirect should be ignored
'item_count' => $expectedItemCount,
'property_count' => $expectedPropertyCount,
'lexeme_count' => $expectedLexemeCount,
'entity_schema_count' => $expectedEntitySchemaCount, // redirects should be ignored
]);
}
}
Loading