Extract programm listings from php-doc-en

extract.php

<?php

extractProgramListings($_SERVER['argv'][1]);

function extractProgramListings($path) {
    if (is_file($path)) {
        $files = [$path];
    } else {
        $files = new RecursiveIteratorIterator(new RecursiveDirectoryIterator($path));
    }
    
    foreach ($files as $file) {
        if (pathinfo($file, PATHINFO_EXTENSION) === 'xml') {
            $xmlContent = file_get_contents($file);
            $xmlContent = str_replace(
                '<?xml version="1.0" encoding="utf-8"?>',
                '<?xml version="1.0" encoding="utf-8"?>' .
                <<<DTD
                    <!DOCTYPE root [
                     <!ENTITY reftitle.description "Description">
                     <!ENTITY style.oop "OOP">
                     <!ENTITY style.procedural "Procedural">
                     <!ENTITY reftitle.parameters "Parameters">
                     <!ENTITY date.datetime.description "Date/Time Description">
                     <!ENTITY url.rfc "RFC URL">
                     <!ENTITY reftitle.returnvalues "Return Values">
                     <!ENTITY reftitle.changelog "Changelog">
                     <!ENTITY Description "Description">
                     <!ENTITY Version "Version">
                     <!ENTITY reftitle.examples "reftitle.examples">
                     <!ENTITY example.outputs "example.outputs">
                     <!ENTITY reftitle.notes "reftitle.notes">
                     <!ENTITY reftitle.required "reftitle.required">
                     <!ENTITY url.xattr "url.xattr">
                     <!ENTITY reftitle.returnvalues "reftitle.returnvalues">
                     <!ENTITY true "true">
                     <!ENTITY false "false">
                     <!ENTITY reference.xattr.configure "reference.xattr.configure">
                     <!ENTITY return.success "return.success">
                     <!ENTITY reftitle.seealso "reftitle.seealso">
                     <!ENTITY xattr.namespace "xattr.namespace">
                     <!ENTITY reftitle.setup "reftitle.setup">
                     <!ENTITY no.function.parameters "no.function.parameters">
                     <!ENTITY reftitle.seealso "reftitle.seealso">
                     ]>
                    DTD,
                $xmlContent
            );


            libxml_use_internal_errors(true);
            
            $dom = new DOMDocument();
            $dom->resolveExternals = true;
            $dom->strictErrorChecking = false;
            $dom->loadXML($xmlContent, LIBXML_DTDLOAD | LIBXML_DTDATTR | LIBXML_NOENT | LIBXML_NOERROR | LIBXML_NOWARNING);
            foreach (libxml_get_errors() as $error) {
                echo "XML Error: ", $error->message, "\n";
            }
            libxml_clear_errors();

            $xpath = new DOMXPath($dom);
            $xpath->registerNamespace('db', 'http://docbook.org/ns/docbook');
            $entries = $xpath->query('//db:programlisting[@role="php"]');

            if ($entries->length > 0) {
                echo "Extracting from: $file\n";
                foreach ($entries as $entry) {
                    echo trim($entry->textContent) . "\n\n";
                }
            }
        }
    }
}