Various updates

- Fix deprecation notices in PHP 8.x - Use DOMParser to parse HTML and XML documents - Update Robo, php-cs-fixer - Clean up tooling where practical
1 year ago · d50c7a527d
19 changed files with 1174 additions and 1372 deletions
--- a/.gitignore
+++ b/.gitignore
@ -3,3 +3,4 @@
 /tests/coverage
 /tests/.phpunit.result.cache
 /.php_cs.cache
+/.php-cs-fixer.cache
--- a/.php-cs-fixer.dist.php
+++ b/.php-cs-fixer.dist.php
@ -1,4 +1,7 @@
 <?php
+/** @license MIT
+ * Copyright 2017 J. King, Dustin Wilson et al.
+ * See LICENSE and AUTHORS files for details */

 declare(strict_types=1);

@ -19,6 +22,7 @@ $rules = [
        'operators' => ['=>' => "align_single_space"],
    ],
    'cast_spaces'                               => ['space' => "single"],
+    'concat_space'                              => ['spacing' => "none"],
    'list_syntax'                               => ['syntax' => "short"],
    'magic_constant_casing'                     => true,
    'magic_method_casing'                       => true,
@ -29,6 +33,7 @@ $rules = [
    'no_blank_lines_after_phpdoc'               => true,
    'no_empty_comment'                          => true,
    'no_empty_phpdoc'                           => true,
+    'no_empty_statement'                        => true,
    'no_extra_blank_lines'                      => true, // this could probably use more configuration
    'no_mixed_echo_print'                       => ['use' => "echo"],
    'no_short_bool_cast'                        => true,
@ -42,32 +47,14 @@ $rules = [
    'pow_to_exponentiation'                     => true,
    'set_type_to_cast'                          => true,
    'standardize_not_equals'                    => true,
-    'trailing_comma_in_multiline_array'         => true,
+    'trailing_comma_in_multiline'               => ['elements' => ["arrays"]],
    'unary_operator_spaces'                     => true,
    'yoda_style'                                => false,
    // PSR standard to apply
-    '@PSR2' => true,
-    // PSR-12 rules; php-cs-fixer does not yet support PSR-12 natively
-    'blank_line_after_opening_tag'              => true,
-    'compact_nullable_typehint'                 => true,
-    'declare_equal_normalize'                   => ['space' => "none"],
-    'function_typehint_space'                   => true,
-    'lowercase_cast'                            => true,
-    'lowercase_static_reference'                => true,
-    'method_argument_space'                     => ['on_multiline' => 'ensure_fully_multiline'],
-    'no_alternative_syntax'                     => true,
-    'no_empty_statement'                        => true,
-    'no_leading_import_slash'                   => true,
-    'no_leading_namespace_whitespace'           => true,
-    'no_whitespace_in_blank_line'               => true,
-    'return_type_declaration'                   => ['space_before' => "none"],
-    'single_trait_insert_per_statement'         => true,
-    'short_scalar_cast'                         => true,
-    'visibility_required'                       => ['elements' => ["const", "property", "method"]],
+    '@PSR12' => true,
    // house exceptions to PSR rules
    'braces'                                    => ['position_after_functions_and_oop_constructs' => "same"],
    'function_declaration'                      => ['closure_function_spacing' => "none"],
-    'concat_space'                              => ['spacing' => "none"],
    'new_with_braces'                           => false, // no option to specify absence of braces
 ];

@ -79,4 +66,4 @@ foreach ($paths as $path) {
        $finder = $finder->in($path);
    }
 }
-return \PhpCsFixer\Config::create()->setRiskyAllowed(true)->setRules($rules)->setFinder($finder);
+return (new \PhpCsFixer\Config)->setRiskyAllowed(true)->setRules($rules)->setFinder($finder);
--- a/RoboFile.php
+++ b/RoboFile.php
@ -6,6 +6,8 @@ const BASE = __DIR__.\DIRECTORY_SEPARATOR;
 const BASE_TEST = BASE."tests".\DIRECTORY_SEPARATOR;
 define("IS_WIN", defined("PHP_WINDOWS_VERSION_MAJOR"));
 define("IS_MAC", php_uname("s") === "Darwin");
+define("IS_LINUX", !IS_WIN && !IS_MAC);
+error_reporting(0);

 function norm(string $path): string {
    $out = realpath($path);
@ -53,8 +55,8 @@ class RoboFile extends \Robo\Tasks {
     * tests/coverage/. Additional reports may be produced by passing
     * arguments to this task as one would to PHPUnit.
     *
-     * Robo first tries to use pcov and will fall back first to xdebug then
-     * phpdbg. Neither pcov nor xdebug need to be enabled to be used; they
+     * Robo first tries to use pcov and will fall back to xdebug.
+     * Neither pcov nor xdebug need to be enabled to be used; they
     * only need to be present in the extension load path to be used.
     */
    public function coverage(array $args): Result {
@ -78,7 +80,7 @@ class RoboFile extends \Robo\Tasks {
        return $this->runTests($exec, "typical", array_merge(["--coverage-html", BASE_TEST."coverage"], $args));
    }

-    /** Runs the coding standards fixer */
+    /** Runs the coding-style fixer */
    public function clean($opts = ['demo|d' => false]): Result {
        $t = $this->taskExec(norm(BASE."vendor/bin/php-cs-fixer"));
        $t->arg("fix");
@ -88,39 +90,42 @@ class RoboFile extends \Robo\Tasks {
        return $t->run();
    }

+    /** Finds the first suitable means of computing code coverage, either pcov or xdebug. */
    protected function findCoverageEngine(): string {
        $dir = rtrim(ini_get("extension_dir"), "/").\DIRECTORY_SEPARATOR;
-        $ext = IS_WIN ? "dll" : (IS_MAC ? "dylib" : "so");
+        $ext = IS_WIN ? "dll" : "so";
        $php = escapeshellarg(\PHP_BINARY);
        $code = escapeshellarg(BASE."lib");
        if (extension_loaded("pcov")) {
            return "$php -d pcov.enabled=1 -d pcov.directory=$code";
        } elseif (extension_loaded("xdebug")) {
-            return $php;
+            return "$php -d xdebug.mode=coverage";
        } elseif (file_exists($dir."pcov.$ext")) {
            return "$php -d extension=pcov.$ext -d pcov.enabled=1 -d pcov.directory=$code";
-        } elseif (file_exists($dir."pcov.$ext")) {
-            return "$php -d zend_extension=xdebug.$ext";
+        } elseif (file_exists($dir."xdebug.$ext")) {
+            return "$php -d zend_extension=xdebug.$ext -d xdebug.mode=coverage";
        } else {
-            if (IS_WIN) {
-                $dbg = dirname(\PHP_BINARY)."\\phpdbg.exe";
-                $dbg = file_exists($dbg) ? $dbg : "";
-            } else {
-                $dbg = trim(`which phpdbg 2>/dev/null`);
-            }
-            if ($dbg) {
-                return escapeshellarg($dbg)." -qrr";
-            } else {
-                return $php;
-            }
+            return $php;
        }
    }

+    /** Returns the necessary shell arguments to print error output or all output to the bitbucket
+     *
+     * @param bool $all Whether all output (true) or only error output (false) should be suppressed
+     */
    protected function blackhole(bool $all = false): string {
        $hole = IS_WIN ? "nul" : "/dev/null";
        return $all ? ">$hole 2>&1" : "2>$hole";
    }

+    /** Executes PHPUnit, used by the test and coverage tasks.
+     *
+     * This also executes the built-in PHP Web server, which is required to fetch some newsfeeds during tests
+     *
+     * @param string $executor The path to the PHP binary to execute with any required extra arguments. Normally this is either "php" or the result of findCoverageEngine()
+     * @param string $set The set of tests to run, either "typical" (excludes redundant tests), "quick" (excludes redundant and slow tests), "coverage" (excludes tests not needed for coverage), or "full" (all tests)
+     * @param array $args Extra arguments passed by Robo from the command line
+     */
    protected function runTests(string $executor, string $set, array $args): Result {
        switch ($set) {
            case "typical":
@ -140,7 +145,6 @@ class RoboFile extends \Robo\Tasks {
        }
        $execpath = norm(BASE."vendor-bin/phpunit/vendor/phpunit/phpunit/phpunit");
        $confpath = realpath(BASE_TEST."phpunit.dist.xml") ?: norm(BASE_TEST."phpunit.xml");
-        //$this->taskServer(8000)->host("localhost")->dir(BASE_TEST."docroot")->rawArg("-n")->arg(BASE_TEST."server.php")->rawArg($this->blackhole())->background()->run();
        return $this->taskExec($executor)->option("-d", "zend.assertions=1")->arg($execpath)->option("-c", $confpath)->args(array_merge($set, $args))->run();
    }
 }
--- a/composer.json
+++ b/composer.json
@ -20,6 +20,7 @@
        "ralouphie/mimey": "^2.1",
        "psr/http-message": "^1.0",
        "mensbeam/mimesniff": "^0.2.0",
+        "mensbeam/html-parser": "^1.3.0",
        "psr/http-factory": "^1.0",
        "psr/http-client": "^1.0"
    },
--- a/composer.lock
+++ b/composer.lock
@ -4,8 +4,133 @@
        "Read more about it at https://getcomposer.org/doc/01-basic-usage.md#installing-dependencies",
        "This file is @generated automatically"
    ],
-    "content-hash": "2d0bef53f4eaeeba37004efdea63426e",
+    "content-hash": "18bcc0b76759cef8c7c71e72156431bf",
    "packages": [
+        {
+            "name": "mensbeam/html-parser",
+            "version": "1.3.0",
+            "source": {
+                "type": "git",
+                "url": "https://github.com/mensbeam/HTML-Parser.git",
+                "reference": "d499fac607ae06311df54887ba45c120797c76ed"
+            },
+            "dist": {
+                "type": "zip",
+                "url": "https://api.github.com/repos/mensbeam/HTML-Parser/zipball/d499fac607ae06311df54887ba45c120797c76ed",
+                "reference": "d499fac607ae06311df54887ba45c120797c76ed",
+                "shasum": ""
+            },
+            "require": {
+                "ext-dom": "*",
+                "mensbeam/intl": ">=0.9.1",
+                "mensbeam/mimesniff": ">=0.2.0",
+                "php": ">=7.1"
+            },
+            "require-dev": {
+                "bamarni/composer-bin-plugin": "^1.3"
+            },
+            "suggest": {
+                "ext-ctype": "Improved performance"
+            },
+            "type": "library",
+            "autoload": {
+                "files": [
+                    "lib/Parser/ctype.php"
+                ],
+                "psr-4": {
+                    "MensBeam\\HTML\\": [
+                        "lib/"
+                    ]
+                },
+                "classmap": [
+                    "lib/Parser/Token.php"
+                ]
+            },
+            "notification-url": "https://packagist.org/downloads/",
+            "license": [
+                "MIT"
+            ],
+            "authors": [
+                {
+                    "name": "Dustin Wilson",
+                    "email": "dustin@dustinwilson.com",
+                    "homepage": "https://dustinwilson.com/"
+                },
+                {
+                    "name": "J. King",
+                    "email": "jking@jkingweb.ca",
+                    "homepage": "https://jkingweb.ca/"
+                }
+            ],
+            "description": "Parser and serializer for modern HTML documents",
+            "keywords": [
+                "HTML5",
+                "WHATWG",
+                "dom",
+                "html",
+                "parser",
+                "parsing"
+            ],
+            "support": {
+                "source": "https://github.com/mensbeam/HTML-Parser/tree/1.3.0"
+            },
+            "time": "2023-04-02T01:38:10+00:00"
+        },
+        {
+            "name": "mensbeam/intl",
+            "version": "0.9.2",
+            "source": {
+                "type": "git",
+                "url": "https://github.com/mensbeam/intl.git",
+                "reference": "88dbf8398ab69e71164ac073f9ec011be2baa4ae"
+            },
+            "dist": {
+                "type": "zip",
+                "url": "https://api.github.com/repos/mensbeam/intl/zipball/88dbf8398ab69e71164ac073f9ec011be2baa4ae",
+                "reference": "88dbf8398ab69e71164ac073f9ec011be2baa4ae",
+                "shasum": ""
+            },
+            "require": {
+                "php": ">=7.1"
+            },
+            "require-dev": {
+                "bamarni/composer-bin-plugin": "*",
+                "ext-intl": "*"
+            },
+            "type": "library",
+            "autoload": {
+                "psr-4": {
+                    "MensBeam\\Intl\\": "lib/"
+                }
+            },
+            "notification-url": "https://packagist.org/downloads/",
+            "license": [
+                "MIT"
+            ],
+            "authors": [
+                {
+                    "name": "J. King",
+                    "email": "jking@jkingweb.ca",
+                    "homepage": "https://jkingweb.ca/"
+                }
+            ],
+            "description": "A set of dependency-free basic internationalization tools",
+            "keywords": [
+                "WHATWG",
+                "charset",
+                "encoding",
+                "internationalization",
+                "intl",
+                "unicode",
+                "utf-8",
+                "utf8"
+            ],
+            "support": {
+                "issues": "https://github.com/mensbeam/intl/issues",
+                "source": "https://github.com/mensbeam/intl/tree/0.9.2"
+            },
+            "time": "2023-01-25T22:12:58+00:00"
+        },
        {
            "name": "mensbeam/mimesniff",
            "version": "0.2.1",
--- a/lib/Collection.php
+++ b/lib/Collection.php
@ -15,6 +15,7 @@ abstract class Collection implements \IteratorAggregate, \ArrayAccess, \Countabl
    }

    /** Implementation for JsonSerializable */
+    #[\ReturnTypeWillChange]
    public function jsonSerialize() {
        return $this->data;
    }
@ -30,11 +31,13 @@ abstract class Collection implements \IteratorAggregate, \ArrayAccess, \Countabl
    }

    /** Implementation for ArrayAccess */
+    #[\ReturnTypeWillChange]
    public function offsetGet($offset) {
        return $this->data[$offset];
    }

    /** Implementation for ArrayAccess */
+    #[\ReturnTypeWillChange]
    public function offsetSet($offset, $value) {
        if (is_null($offset)) {
            $this->data[] = $value;
@ -44,6 +47,7 @@ abstract class Collection implements \IteratorAggregate, \ArrayAccess, \Countabl
    }

    /** Implementation for ArrayAccess */
+    #[\ReturnTypeWillChange]
    public function offsetUnset($offset) {
        unset($this->data[$offset]);
    }
--- a/lib/Date.php
+++ b/lib/Date.php
@ -174,11 +174,13 @@ class Date extends \DateTimeImmutable implements \JsonSerializable {
        return $time;
    }

+    #[\ReturnTypeWillChange]
    public static function createFromFormat($format, $time, $timezone = null): ?self {
        $temp = parent::createFromFormat("!".$format, $time, $timezone);
        return $temp ? static::create($temp) : null;
    }

+    #[\ReturnTypeWillChange]
    public static function createFromMutable($datetime): ?self {
        $temp = parent::createFromMutable($datetime);
        return $temp ? static::create($temp) : null;
@ -202,6 +204,7 @@ class Date extends \DateTimeImmutable implements \JsonSerializable {
        }
    }

+    #[\ReturnTypeWillChange]
    public function jsonSerialize() {
        return $this->__toString();
    }
--- a/lib/Enclosure/Enclosure.php
+++ b/lib/Enclosure/Enclosure.php
@ -47,6 +47,7 @@ class Enclosure implements \IteratorAggregate, \ArrayAccess, \Countable {
        return isset($this->data[$offset]);
    }

+    #[\ReturnTypeWillChange]
    public function offsetGet($offset) {
        return $this->data[$offset];
    }
--- a/lib/Parser/AbstractEntry.php
+++ b/lib/Parser/AbstractEntry.php
@ -10,6 +10,9 @@ use MensBeam\Lax\Feed as FeedStruct;
 use MensBeam\Lax\Entry as EntryStruct;

 trait AbstractEntry {
+    protected $data;
+    protected $feed;
+    
    public function __construct($data, FeedStruct $feed) {
        $this->data = $data;
        $this->feed = $feed;
--- a/lib/Parser/AbstractFeed.php
+++ b/lib/Parser/AbstractFeed.php
@ -10,6 +10,8 @@ use MensBeam\Lax\Url;
 use MensBeam\Lax\Feed as FeedStruct;

 trait AbstractFeed {
+    protected $version;
+
    /** Constructs a feed parser */
    public function __construct(string $data, string $contentType = null, string $url = null) {
        $this->data = $data;
--- a/lib/Parser/HTML/Feed.php
+++ b/lib/Parser/HTML/Feed.php
@ -16,6 +16,7 @@ use MensBeam\Lax\Parser\Exception;
 use MensBeam\Lax\Parser\XML\XPath;
 use MensBeam\Lax\Category\Collection as CategoryCollection;
 use MensBeam\Lax\Person\Collection as PersonCollection;
+use MensBeam\HTML\DOMParser;

 class Feed extends Construct implements \MensBeam\Lax\Parser\Feed {
    use \MensBeam\Lax\Parser\AbstractFeed;
@ -39,13 +40,14 @@ class Feed extends Construct implements \MensBeam\Lax\Parser\Feed {

    /** Performs initialization of the instance */
    protected function init(FeedStruct $feed): FeedStruct {
-        $type = MimeType::parse($this->contentType) ?? "";
+        $type = MimeType::parse($this->contentType);
        if ($type && !in_array($type->essence, self::MIME_TYPES)) {
            throw new Exception("notHTMLType");
        }
+        $parser = new DOMParser;
        if ($type && $type->essence === "application/xhtml+xml") {
-            $this->document = new \DOMDocument;
-            if (!$this->document->loadXML($this->data, self::LIBXML_OPTIONS)) {
+            $this->document = $parser->parseFromString($this->data, $this->contentType);
+            if ($this->document->documentElement->tagName === "parsererror" && $this->document->documentElement->namespaceURI === "http://www.mozilla.org/newlayout/xml/parsererror.xml") {
                // ignore XML parsing errors; we will reparse as HTML in this case
                $this->document = null;
            } elseif ($this->document->documentElement->namespaceURI !== XPath::NS['html']) {
@ -53,10 +55,7 @@ class Feed extends Construct implements \MensBeam\Lax\Parser\Feed {
            }
        }
        if (!$this->document) {
-            $this->document = new \DOMDocument;
-            if (!$this->document->loadHTML($this->data, self::LIBXML_OPTIONS)) {
-                throw new Exception("notHTML"); // @codeCoverageIgnore
-            }
+            $this->document = $parser->parseFromString($this->data, "text/html;charset=".($type->params['charset'] ?? ""));
        }
        $this->document->documentURI = $this->url;
        $this->xpath = new \DOMXPath($this->document);
--- a/lib/Parser/XML/Feed.php
+++ b/lib/Parser/XML/Feed.php
@ -17,6 +17,7 @@ use MensBeam\Lax\MimeType;
 use MensBeam\Lax\Schedule;
 use MensBeam\Lax\Text;
 use MensBeam\Lax\Url;
+use MensBeam\HTML\DOMParser;

 class Feed extends Construct implements \MensBeam\Lax\Parser\Feed {
    use \MensBeam\Lax\Parser\AbstractFeed;
@ -43,12 +44,12 @@ class Feed extends Construct implements \MensBeam\Lax\Parser\Feed {

    /** Performs initialization of the instance */
    protected function init(FeedStruct $feed): FeedStruct {
-        $type = MimeType::parse($this->contentType) ?? "";
+        $type = MimeType::parse($this->contentType) ?? null;
        if ($type && !in_array($type->essence, self::MIME_TYPES)) {
            throw new Exception("notXMLType");
        }
-        $this->document = new \DOMDocument();
-        if (!$this->document->loadXML($this->data, self::LIBXML_OPTIONS)) {
+        $this->document = (new DOMParser)->parseFromString($this->data, $type ?? "text/xml");
+        if ($this->document->documentElement->tagName === "parsererror" && $this->document->documentElement->namespaceURI === "http://www.mozilla.org/newlayout/xml/parsererror.xml") {
            throw new Exception("notXML");
        }
        $this->document->documentURI = $this->url;
--- a/lib/Parser/XML/XPath.php
+++ b/lib/Parser/XML/XPath.php
@ -36,6 +36,7 @@ class XPath extends \DOMXpath {
    }

    /** {@inheritDoc} */
+    #[\ReturnTypeWillChange]
    public function query($expression, $contextnode = null, $registerNS = true) {
        $expression = $this->rss2 ? str_replace("rss2:", "", $expression) : $expression;
        $expression = $this->html ? str_replace("html:", "", $expression) : $expression;
--- a/vendor-bin/csfixer/composer.json
+++ b/vendor-bin/csfixer/composer.json
@ -1,5 +1,5 @@
 {
    "require-dev": {
-        "friendsofphp/php-cs-fixer": "^2.16"
+        "friendsofphp/php-cs-fixer": "^3.0"
    }
 }
--- a/vendor-bin/csfixer/composer.lock
+++ b/vendor-bin/csfixer/composer.lock
--- a/vendor-bin/phpunit/composer.json
+++ b/vendor-bin/phpunit/composer.json
@ -4,6 +4,6 @@
        "symfony/yaml": "^5.0",
        "guzzlehttp/guzzle": "^6.5",
        "guzzlehttp/psr7": "^1.6",
-        "phake/phake": "^3.1"
+        "phake/phake": "^4.4"
    }
 }
--- a/vendor-bin/phpunit/composer.lock
+++ b/vendor-bin/phpunit/composer.lock
--- a/vendor-bin/robo/composer.json
+++ b/vendor-bin/robo/composer.json
@ -1,5 +1,5 @@
 {
    "require-dev": {
-        "consolidation/robo": "^2.0"
+        "consolidation/robo": "^4.0"
    }
 }
--- a/vendor-bin/robo/composer.lock
+++ b/vendor-bin/robo/composer.lock