af_fulltext: rule-driven extraction with a pluggable renderer
Replaces subscribing feeds through a self-hosted Full-Text RSS proxy. Feed URLs go back to being real feed URLs and extraction happens inside tt-rss, using the same ftr-site-config rules the proxy used. The engine in lib/ has no tt-rss dependencies, so rules can be developed and audited from the command line; init.php is a thin adapter over it. Two findings from measuring the real subscription first, both of which shaped the design: - Firecrawl's own onlyMainContent is far too coarse to extract with (73KB of chrome on a Cloudflare post), but it is an excellent renderer. So it is used for rawHtml only and the rule engine does the extraction. - A body rule that stops matching after a redesign falls through to Readability and still produces a plausible article, so the breakage is invisible. Every extraction now records which rule matched and whether it fell back; auditing the 34 live feeds surfaced five community rules that match nothing. Custom rules included for the sites that needed them, including three comics where the article is an image and text-scoring extractors return the wrong thing or nothing at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011sSJdftQx5bW5HZHgUKF3i
This commit is contained in:
396
vendor/composer/InstalledVersions.php
vendored
Normal file
396
vendor/composer/InstalledVersions.php
vendored
Normal file
@@ -0,0 +1,396 @@
|
||||
<?php
|
||||
|
||||
/*
|
||||
* This file is part of Composer.
|
||||
*
|
||||
* (c) Nils Adermann <naderman@naderman.de>
|
||||
* Jordi Boggiano <j.boggiano@seld.be>
|
||||
*
|
||||
* For the full copyright and license information, please view the LICENSE
|
||||
* file that was distributed with this source code.
|
||||
*/
|
||||
|
||||
namespace Composer;
|
||||
|
||||
use Composer\Autoload\ClassLoader;
|
||||
use Composer\Semver\VersionParser;
|
||||
|
||||
/**
|
||||
* This class is copied in every Composer installed project and available to all
|
||||
*
|
||||
* See also https://getcomposer.org/doc/07-runtime.md#installed-versions
|
||||
*
|
||||
* To require its presence, you can require `composer-runtime-api ^2.0`
|
||||
*
|
||||
* @final
|
||||
*/
|
||||
class InstalledVersions
|
||||
{
|
||||
/**
|
||||
* @var string|null if set (by reflection by Composer), this should be set to the path where this class is being copied to
|
||||
* @internal
|
||||
*/
|
||||
private static $selfDir = null;
|
||||
|
||||
/**
|
||||
* @var mixed[]|null
|
||||
* @psalm-var array{root: array{name: string, pretty_version: string, version: string, reference: string|null, type: string, install_path: string, aliases: string[], dev: bool}, versions: array<string, array{pretty_version?: string, version?: string, reference?: string|null, type?: string, install_path?: string, aliases?: string[], dev_requirement: bool, replaced?: string[], provided?: string[]}>}|array{}|null
|
||||
*/
|
||||
private static $installed;
|
||||
|
||||
/**
|
||||
* @var bool
|
||||
*/
|
||||
private static $installedIsLocalDir;
|
||||
|
||||
/**
|
||||
* @var bool|null
|
||||
*/
|
||||
private static $canGetVendors;
|
||||
|
||||
/**
|
||||
* @var array[]
|
||||
* @psalm-var array<string, array{root: array{name: string, pretty_version: string, version: string, reference: string|null, type: string, install_path: string, aliases: string[], dev: bool}, versions: array<string, array{pretty_version?: string, version?: string, reference?: string|null, type?: string, install_path?: string, aliases?: string[], dev_requirement: bool, replaced?: string[], provided?: string[]}>}>
|
||||
*/
|
||||
private static $installedByVendor = array();
|
||||
|
||||
/**
|
||||
* Returns a list of all package names which are present, either by being installed, replaced or provided
|
||||
*
|
||||
* @return string[]
|
||||
* @psalm-return list<string>
|
||||
*/
|
||||
public static function getInstalledPackages()
|
||||
{
|
||||
$packages = array();
|
||||
foreach (self::getInstalled() as $installed) {
|
||||
$packages[] = array_keys($installed['versions']);
|
||||
}
|
||||
|
||||
if (1 === \count($packages)) {
|
||||
return $packages[0];
|
||||
}
|
||||
|
||||
return array_keys(array_flip(\call_user_func_array('array_merge', $packages)));
|
||||
}
|
||||
|
||||
/**
|
||||
* Returns a list of all package names with a specific type e.g. 'library'
|
||||
*
|
||||
* @param string $type
|
||||
* @return string[]
|
||||
* @psalm-return list<string>
|
||||
*/
|
||||
public static function getInstalledPackagesByType($type)
|
||||
{
|
||||
$packagesByType = array();
|
||||
|
||||
foreach (self::getInstalled() as $installed) {
|
||||
foreach ($installed['versions'] as $name => $package) {
|
||||
if (isset($package['type']) && $package['type'] === $type) {
|
||||
$packagesByType[] = $name;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return $packagesByType;
|
||||
}
|
||||
|
||||
/**
|
||||
* Checks whether the given package is installed
|
||||
*
|
||||
* This also returns true if the package name is provided or replaced by another package
|
||||
*
|
||||
* @param string $packageName
|
||||
* @param bool $includeDevRequirements
|
||||
* @return bool
|
||||
*/
|
||||
public static function isInstalled($packageName, $includeDevRequirements = true)
|
||||
{
|
||||
foreach (self::getInstalled() as $installed) {
|
||||
if (isset($installed['versions'][$packageName])) {
|
||||
return $includeDevRequirements || !isset($installed['versions'][$packageName]['dev_requirement']) || $installed['versions'][$packageName]['dev_requirement'] === false;
|
||||
}
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
|
||||
/**
|
||||
* Checks whether the given package satisfies a version constraint
|
||||
*
|
||||
* e.g. If you want to know whether version 2.3+ of package foo/bar is installed, you would call:
|
||||
*
|
||||
* Composer\InstalledVersions::satisfies(new VersionParser, 'foo/bar', '^2.3')
|
||||
*
|
||||
* @param VersionParser $parser Install composer/semver to have access to this class and functionality
|
||||
* @param string $packageName
|
||||
* @param string|null $constraint A version constraint to check for, if you pass one you have to make sure composer/semver is required by your package
|
||||
* @return bool
|
||||
*/
|
||||
public static function satisfies(VersionParser $parser, $packageName, $constraint)
|
||||
{
|
||||
$constraint = $parser->parseConstraints((string) $constraint);
|
||||
$provided = $parser->parseConstraints(self::getVersionRanges($packageName));
|
||||
|
||||
return $provided->matches($constraint);
|
||||
}
|
||||
|
||||
/**
|
||||
* Returns a version constraint representing all the range(s) which are installed for a given package
|
||||
*
|
||||
* It is easier to use this via isInstalled() with the $constraint argument if you need to check
|
||||
* whether a given version of a package is installed, and not just whether it exists
|
||||
*
|
||||
* @param string $packageName
|
||||
* @return string Version constraint usable with composer/semver
|
||||
*/
|
||||
public static function getVersionRanges($packageName)
|
||||
{
|
||||
foreach (self::getInstalled() as $installed) {
|
||||
if (!isset($installed['versions'][$packageName])) {
|
||||
continue;
|
||||
}
|
||||
|
||||
$ranges = array();
|
||||
if (isset($installed['versions'][$packageName]['pretty_version'])) {
|
||||
$ranges[] = $installed['versions'][$packageName]['pretty_version'];
|
||||
}
|
||||
if (array_key_exists('aliases', $installed['versions'][$packageName])) {
|
||||
$ranges = array_merge($ranges, $installed['versions'][$packageName]['aliases']);
|
||||
}
|
||||
if (array_key_exists('replaced', $installed['versions'][$packageName])) {
|
||||
$ranges = array_merge($ranges, $installed['versions'][$packageName]['replaced']);
|
||||
}
|
||||
if (array_key_exists('provided', $installed['versions'][$packageName])) {
|
||||
$ranges = array_merge($ranges, $installed['versions'][$packageName]['provided']);
|
||||
}
|
||||
|
||||
return implode(' || ', $ranges);
|
||||
}
|
||||
|
||||
throw new \OutOfBoundsException('Package "' . $packageName . '" is not installed');
|
||||
}
|
||||
|
||||
/**
|
||||
* @param string $packageName
|
||||
* @return string|null If the package is being replaced or provided but is not really installed, null will be returned as version, use satisfies or getVersionRanges if you need to know if a given version is present
|
||||
*/
|
||||
public static function getVersion($packageName)
|
||||
{
|
||||
foreach (self::getInstalled() as $installed) {
|
||||
if (!isset($installed['versions'][$packageName])) {
|
||||
continue;
|
||||
}
|
||||
|
||||
if (!isset($installed['versions'][$packageName]['version'])) {
|
||||
return null;
|
||||
}
|
||||
|
||||
return $installed['versions'][$packageName]['version'];
|
||||
}
|
||||
|
||||
throw new \OutOfBoundsException('Package "' . $packageName . '" is not installed');
|
||||
}
|
||||
|
||||
/**
|
||||
* @param string $packageName
|
||||
* @return string|null If the package is being replaced or provided but is not really installed, null will be returned as version, use satisfies or getVersionRanges if you need to know if a given version is present
|
||||
*/
|
||||
public static function getPrettyVersion($packageName)
|
||||
{
|
||||
foreach (self::getInstalled() as $installed) {
|
||||
if (!isset($installed['versions'][$packageName])) {
|
||||
continue;
|
||||
}
|
||||
|
||||
if (!isset($installed['versions'][$packageName]['pretty_version'])) {
|
||||
return null;
|
||||
}
|
||||
|
||||
return $installed['versions'][$packageName]['pretty_version'];
|
||||
}
|
||||
|
||||
throw new \OutOfBoundsException('Package "' . $packageName . '" is not installed');
|
||||
}
|
||||
|
||||
/**
|
||||
* @param string $packageName
|
||||
* @return string|null If the package is being replaced or provided but is not really installed, null will be returned as reference
|
||||
*/
|
||||
public static function getReference($packageName)
|
||||
{
|
||||
foreach (self::getInstalled() as $installed) {
|
||||
if (!isset($installed['versions'][$packageName])) {
|
||||
continue;
|
||||
}
|
||||
|
||||
if (!isset($installed['versions'][$packageName]['reference'])) {
|
||||
return null;
|
||||
}
|
||||
|
||||
return $installed['versions'][$packageName]['reference'];
|
||||
}
|
||||
|
||||
throw new \OutOfBoundsException('Package "' . $packageName . '" is not installed');
|
||||
}
|
||||
|
||||
/**
|
||||
* @param string $packageName
|
||||
* @return string|null If the package is being replaced or provided but is not really installed, null will be returned as install path. Packages of type metapackages also have a null install path.
|
||||
*/
|
||||
public static function getInstallPath($packageName)
|
||||
{
|
||||
foreach (self::getInstalled() as $installed) {
|
||||
if (!isset($installed['versions'][$packageName])) {
|
||||
continue;
|
||||
}
|
||||
|
||||
return isset($installed['versions'][$packageName]['install_path']) ? $installed['versions'][$packageName]['install_path'] : null;
|
||||
}
|
||||
|
||||
throw new \OutOfBoundsException('Package "' . $packageName . '" is not installed');
|
||||
}
|
||||
|
||||
/**
|
||||
* @return array
|
||||
* @psalm-return array{name: string, pretty_version: string, version: string, reference: string|null, type: string, install_path: string, aliases: string[], dev: bool}
|
||||
*/
|
||||
public static function getRootPackage()
|
||||
{
|
||||
$installed = self::getInstalled();
|
||||
|
||||
return $installed[0]['root'];
|
||||
}
|
||||
|
||||
/**
|
||||
* Returns the raw installed.php data for custom implementations
|
||||
*
|
||||
* @deprecated Use getAllRawData() instead which returns all datasets for all autoloaders present in the process. getRawData only returns the first dataset loaded, which may not be what you expect.
|
||||
* @return array[]
|
||||
* @psalm-return array{root: array{name: string, pretty_version: string, version: string, reference: string|null, type: string, install_path: string, aliases: string[], dev: bool}, versions: array<string, array{pretty_version?: string, version?: string, reference?: string|null, type?: string, install_path?: string, aliases?: string[], dev_requirement: bool, replaced?: string[], provided?: string[]}>}
|
||||
*/
|
||||
public static function getRawData()
|
||||
{
|
||||
@trigger_error('getRawData only returns the first dataset loaded, which may not be what you expect. Use getAllRawData() instead which returns all datasets for all autoloaders present in the process.', E_USER_DEPRECATED);
|
||||
|
||||
if (null === self::$installed) {
|
||||
// only require the installed.php file if this file is loaded from its dumped location,
|
||||
// and not from its source location in the composer/composer package, see https://github.com/composer/composer/issues/9937
|
||||
if (substr(__DIR__, -8, 1) !== 'C') {
|
||||
self::$installed = include __DIR__ . '/installed.php';
|
||||
} else {
|
||||
self::$installed = array();
|
||||
}
|
||||
}
|
||||
|
||||
return self::$installed;
|
||||
}
|
||||
|
||||
/**
|
||||
* Returns the raw data of all installed.php which are currently loaded for custom implementations
|
||||
*
|
||||
* @return array[]
|
||||
* @psalm-return list<array{root: array{name: string, pretty_version: string, version: string, reference: string|null, type: string, install_path: string, aliases: string[], dev: bool}, versions: array<string, array{pretty_version?: string, version?: string, reference?: string|null, type?: string, install_path?: string, aliases?: string[], dev_requirement: bool, replaced?: string[], provided?: string[]}>}>
|
||||
*/
|
||||
public static function getAllRawData()
|
||||
{
|
||||
return self::getInstalled();
|
||||
}
|
||||
|
||||
/**
|
||||
* Lets you reload the static array from another file
|
||||
*
|
||||
* This is only useful for complex integrations in which a project needs to use
|
||||
* this class but then also needs to execute another project's autoloader in process,
|
||||
* and wants to ensure both projects have access to their version of installed.php.
|
||||
*
|
||||
* A typical case would be PHPUnit, where it would need to make sure it reads all
|
||||
* the data it needs from this class, then call reload() with
|
||||
* `require $CWD/vendor/composer/installed.php` (or similar) as input to make sure
|
||||
* the project in which it runs can then also use this class safely, without
|
||||
* interference between PHPUnit's dependencies and the project's dependencies.
|
||||
*
|
||||
* @param array[] $data A vendor/composer/installed.php data set
|
||||
* @return void
|
||||
*
|
||||
* @psalm-param array{root: array{name: string, pretty_version: string, version: string, reference: string|null, type: string, install_path: string, aliases: string[], dev: bool}, versions: array<string, array{pretty_version?: string, version?: string, reference?: string|null, type?: string, install_path?: string, aliases?: string[], dev_requirement: bool, replaced?: string[], provided?: string[]}>} $data
|
||||
*/
|
||||
public static function reload($data)
|
||||
{
|
||||
self::$installed = $data;
|
||||
self::$installedByVendor = array();
|
||||
|
||||
// when using reload, we disable the duplicate protection to ensure that self::$installed data is
|
||||
// always returned, but we cannot know whether it comes from the installed.php in __DIR__ or not,
|
||||
// so we have to assume it does not, and that may result in duplicate data being returned when listing
|
||||
// all installed packages for example
|
||||
self::$installedIsLocalDir = false;
|
||||
}
|
||||
|
||||
/**
|
||||
* @return string
|
||||
*/
|
||||
private static function getSelfDir()
|
||||
{
|
||||
if (self::$selfDir === null) {
|
||||
self::$selfDir = strtr(__DIR__, '\\', '/');
|
||||
}
|
||||
|
||||
return self::$selfDir;
|
||||
}
|
||||
|
||||
/**
|
||||
* @return array[]
|
||||
* @psalm-return list<array{root: array{name: string, pretty_version: string, version: string, reference: string|null, type: string, install_path: string, aliases: string[], dev: bool}, versions: array<string, array{pretty_version?: string, version?: string, reference?: string|null, type?: string, install_path?: string, aliases?: string[], dev_requirement: bool, replaced?: string[], provided?: string[]}>}>
|
||||
*/
|
||||
private static function getInstalled()
|
||||
{
|
||||
if (null === self::$canGetVendors) {
|
||||
self::$canGetVendors = method_exists('Composer\Autoload\ClassLoader', 'getRegisteredLoaders');
|
||||
}
|
||||
|
||||
$installed = array();
|
||||
$copiedLocalDir = false;
|
||||
|
||||
if (self::$canGetVendors) {
|
||||
$selfDir = self::getSelfDir();
|
||||
foreach (ClassLoader::getRegisteredLoaders() as $vendorDir => $loader) {
|
||||
$vendorDir = strtr($vendorDir, '\\', '/');
|
||||
if (isset(self::$installedByVendor[$vendorDir])) {
|
||||
$installed[] = self::$installedByVendor[$vendorDir];
|
||||
} elseif (is_file($vendorDir.'/composer/installed.php')) {
|
||||
/** @var array{root: array{name: string, pretty_version: string, version: string, reference: string|null, type: string, install_path: string, aliases: string[], dev: bool}, versions: array<string, array{pretty_version?: string, version?: string, reference?: string|null, type?: string, install_path?: string, aliases?: string[], dev_requirement: bool, replaced?: string[], provided?: string[]}>} $required */
|
||||
$required = require $vendorDir.'/composer/installed.php';
|
||||
self::$installedByVendor[$vendorDir] = $required;
|
||||
$installed[] = $required;
|
||||
if (self::$installed === null && $vendorDir.'/composer' === $selfDir) {
|
||||
self::$installed = $required;
|
||||
self::$installedIsLocalDir = true;
|
||||
}
|
||||
}
|
||||
if (self::$installedIsLocalDir && $vendorDir.'/composer' === $selfDir) {
|
||||
$copiedLocalDir = true;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (null === self::$installed) {
|
||||
// only require the installed.php file if this file is loaded from its dumped location,
|
||||
// and not from its source location in the composer/composer package, see https://github.com/composer/composer/issues/9937
|
||||
if (substr(__DIR__, -8, 1) !== 'C') {
|
||||
/** @var array{root: array{name: string, pretty_version: string, version: string, reference: string|null, type: string, install_path: string, aliases: string[], dev: bool}, versions: array<string, array{pretty_version?: string, version?: string, reference?: string|null, type?: string, install_path?: string, aliases?: string[], dev_requirement: bool, replaced?: string[], provided?: string[]}>} $required */
|
||||
$required = require __DIR__ . '/installed.php';
|
||||
self::$installed = $required;
|
||||
} else {
|
||||
self::$installed = array();
|
||||
}
|
||||
}
|
||||
|
||||
if (self::$installed !== array() && !$copiedLocalDir) {
|
||||
$installed[] = self::$installed;
|
||||
}
|
||||
|
||||
return $installed;
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user