m105
1c9fc5d423
Adds Site/SitePage models and the crawlindex:fetch command, which pulls CDX index records from Common Crawl and optionally enriches them with page title/description/keywords/body text extracted from the WARC archive. CDX/WARC access and the site/page upsert logic live in CommonCrawlIndexService and WarcRecordFetcher.
37 lines
1.3 KiB
XML
37 lines
1.3 KiB
XML
<?xml version="1.0" encoding="UTF-8"?>
|
|
<phpunit xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
|
|
xsi:noNamespaceSchemaLocation="vendor/phpunit/phpunit/phpunit.xsd"
|
|
bootstrap="vendor/autoload.php"
|
|
colors="true"
|
|
>
|
|
<testsuites>
|
|
<testsuite name="Unit">
|
|
<directory>tests/Unit</directory>
|
|
</testsuite>
|
|
<testsuite name="Feature">
|
|
<directory>tests/Feature</directory>
|
|
</testsuite>
|
|
</testsuites>
|
|
<source>
|
|
<include>
|
|
<directory>app</directory>
|
|
</include>
|
|
</source>
|
|
<php>
|
|
<env name="APP_ENV" value="testing"/>
|
|
<env name="APP_MAINTENANCE_DRIVER" value="file"/>
|
|
<env name="BCRYPT_ROUNDS" value="4"/>
|
|
<env name="BROADCAST_CONNECTION" value="null"/>
|
|
<env name="CACHE_STORE" value="array"/>
|
|
<env name="DB_CONNECTION" value="sqlite"/>
|
|
<env name="DB_DATABASE" value=":memory:"/>
|
|
<env name="DB_URL" value=""/>
|
|
<env name="MAIL_MAILER" value="array"/>
|
|
<env name="QUEUE_CONNECTION" value="sync"/>
|
|
<env name="SESSION_DRIVER" value="array"/>
|
|
<env name="PULSE_ENABLED" value="false"/>
|
|
<env name="TELESCOPE_ENABLED" value="false"/>
|
|
<env name="NIGHTWATCH_ENABLED" value="false"/>
|
|
</php>
|
|
</phpunit>
|