Ifarchive-tuid-report: normalize urls

composer.json

@@ -0,0 +1,5 @@
+{
+    "require": {
+        "glenscott/url-normalizer": "^1.4"
+    }
+}

docker-php-composer-setup.sh

@@ -0,0 +1,10 @@
+#!/bin/bash -ex
+
+cp ./php-composer-setup.sh www
+cp ./composer.json www
+cp ./composer.lock www
+docker compose exec --privileged web bash ./php-composer-setup.sh
+docker compose exec --privileged web bash
+rm www/php-composer-setup.sh
+mv www/composer.json .
+mv www/composer.lock .

php-composer-setup.sh

@@ -0,0 +1,23 @@
+#!/bin/sh
+
+apt-get install -y p7zip-full
+
+# https://getcomposer.org/doc/faqs/how-to-install-composer-programmatically.md
+# this gets run in the image by docker-php-composer-setup.sh
+
+EXPECTED_CHECKSUM="$(php -r 'copy("https://composer.github.io/installer.sig", "php://stdout");')"
+php -r "copy('https://getcomposer.org/installer', 'composer-setup.php');"
+ACTUAL_CHECKSUM="$(php -r "echo hash_file('sha384', 'composer-setup.php');")"
+
+if [ "$EXPECTED_CHECKSUM" != "$ACTUAL_CHECKSUM" ]
+then
+    >&2 echo 'ERROR: Invalid installer checksum'
+    rm composer-setup.php
+    exit 1
+fi
+
+php composer-setup.php
+RESULT=$?
+rm composer-setup.php
+mv composer.phar /usr/local/bin/composer
+exit $RESULT

www/ifarchive-tuid-report

@@ -3,6 +3,7 @@
 include_once "util.php";
 include_once "pagetpl.php";
 include_once "dbconnect.php";
+require_once 'vendor/autoload.php';
 
 $json = $_GET['json'] ?? false;
 $refresh = $_GET['refresh'] ?? false;
@@ -87,9 +88,20 @@ $db = dbConnect();
 
 $output = [];
 foreach($tuids as $tuid => $path) {
-    $result = mysqli_execute_query($db, "select url from gamelinks where gameid = ? and url like ?", [$tuid, "%$path"]);
-    $row = mysqli_fetch_row($result);
-    if (!$row) {
+    // normalize the path using URL normalizer. First we make it an absolute URL, normalize it, then we strip the absolute part off
+    $path = substr((new URL\Normalizer("https://ifarchive.org/$path"))->normalize(), strlen("https://ifarchive.org/"));
+    $result = mysqli_execute_query($db, "select url from gamelinks where gameid = ?", [$tuid]);
+    $found = false;
+    foreach ($result->fetch_all(MYSQLI_NUM) as [$url]) {
+        $url = (new URL\Normalizer($url))->normalize();
+        // check whether the $url ends with $path
+        if (substr_compare($url, $path, -strlen($path)) === 0) {
+            $found = true;
+            break;
+        }
+    }
+
+    if (!$found) {
         [$title] = mysqli_fetch_row(mysqli_execute_query($db, "select title from games where id = ?", [$tuid]));
         $output[]= [
             "tuid" => $tuid,

www/vendor/autoload.php

@@ -0,0 +1,25 @@
+<?php
+
+// autoload.php @generated by Composer
+
+if (PHP_VERSION_ID < 50600) {
+    if (!headers_sent()) {
+        header('HTTP/1.1 500 Internal Server Error');
+    }
+    $err = 'Composer 2.3.0 dropped support for autoloading on PHP <5.6 and you are running '.PHP_VERSION.', please upgrade PHP or use Composer 2.2 LTS via "composer self-update --2.2". Aborting.'.PHP_EOL;
+    if (!ini_get('display_errors')) {
+        if (PHP_SAPI === 'cli' || PHP_SAPI === 'phpdbg') {
+            fwrite(STDERR, $err);
+        } elseif (!headers_sent()) {
+            echo $err;
+        }
+    }
+    trigger_error(
+        $err,
+        E_USER_ERROR
+    );
+}
+
+require_once __DIR__ . '/composer/autoload_real.php';
+
+return ComposerAutoloaderInit12212f8390cfa485f99929bb7a8f0797::getLoader();