Merge branch 'freshrss' into sync-upstream

.editorconfig

@@ -26,3 +26,6 @@ indent_style = space
 [*.{yaml,yml}]
 indent_size = 2
 indent_style = space
+
+[*.xml]
+indent_style = tab

.github/README.md

@@ -0,0 +1,21 @@
+# SimplePie
+
+> SimplePie is a very fast and easy-to-use class, written in PHP, that puts the
+> *simple* back into *Really Simple Syndication* (RSS). Flexible enough to suit
+> beginners and veterans alike, SimplePie is focused on [speed, ease of use,
+> compatibility and standards compliance](http://simplepie.org/wiki/faq/what_is_simplepie).
+
+[Read the rest of the original readme](../README.markdown).
+
+## FreshRSS fork
+
+[This repository `FreshRSS/simplepie`](https://github.com/FreshRSS/simplepie) is a fork of the [main repository `simplepie/simplepie`](https://github.com/simplepie/simplepie)
+intended to be used for [FreshRSS](https://github.com/FreshRSS/FreshRSS), which is a free, self-hostable news aggregator.
+
+The default branch [`freshrss`](https://github.com/FreshRSS/simplepie/tree/freshrss) is the one used in [the FreshRSS codebase](https://github.com/FreshRSS/FreshRSS/tree/edge/lib/simplepie).
+
+This allows in particular to use fixes and patches, which have not (yet) been submitted upstream or not (yet) merged upstream.
+
+### Differences
+
+[See the differences](https://github.com/simplepie/simplepie/compare/master...FreshRSS:simplepie:freshrss).

phpcs.xml

@@ -0,0 +1,29 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<ruleset name="SimplePie">
+	<arg name="extensions" value="php"/>
+	<exclude-pattern>./.git/</exclude-pattern>
+	<exclude-pattern>./compatibility_test/</exclude-pattern>
+	<exclude-pattern>./vendor/</exclude-pattern>
+	<rule ref="PSR12">
+		<exclude name="PSR1.Files.SideEffects.FoundWithSymbols"/>
+		<exclude name="PSR1.Methods.CamelCapsMethodName.NotCamelCaps"/>
+		<exclude name="PSR12.ControlStructures.ControlStructureSpacing.CloseParenthesisLine"/>
+		<exclude name="PSR12.ControlStructures.ControlStructureSpacing.FirstExpressionLine"/>
+		<exclude name="Squiz.ControlStructures.ControlSignature.SpaceAfterCloseBrace"/>
+	</rule>
+	<rule ref="Generic.Files.LineLength">
+		<properties>
+			<property name="lineLimit" value="165"/>
+			<property name="absoluteLineLimit" value="400"/>
+		</properties>
+	</rule>
+	<rule ref="Generic.WhiteSpace.DisallowTabIndent.TabsUsed">
+		<exclude-pattern>./demo/</exclude-pattern>
+	</rule>
+	<rule ref="PSR1.Classes.ClassDeclaration.MissingNamespace">
+		<exclude-pattern>./library/</exclude-pattern>
+	</rule>
+	<rule ref="Squiz.Classes.ValidClassName.NotCamelCaps">
+		<exclude-pattern>./library/</exclude-pattern>
+	</rule>
+</ruleset>

src/Cache/BaseDataCache.php

@@ -55,10 +55,11 @@ public function get_data(string $key, $default = null)
             return $default;
         }
 
-        // ignore data if internal cache expiration time is expired
-        if ($data['__cache_expiration_time'] < time()) {
-            return $default;
-        }
+        // FreshRSS commented out, to allow HTTP 304
+        // // ignore data if internal cache expiration time is expired
+        // if ($data['__cache_expiration_time'] < time()) {
+        //     return $default;
+        // }
 
         // remove internal cache expiration time
         unset($data['__cache_expiration_time']);

src/Content/Type/Sniffer.php

@@ -78,17 +78,18 @@ public function get_type()
             if ($official === 'unknown/unknown'
                 || $official === 'application/unknown') {
                 return $this->unknown();
-            } elseif (substr($official, -4) === '+xml'
-                || $official === 'text/xml'
-                || $official === 'application/xml') {
+            } elseif (substr($official, -4) === '+xml') { // FreshRSS
                 return $official;
             } elseif (substr($official, 0, 6) === 'image/') {
                 if ($return = $this->image()) {
                     return $return;
                 }
 
                 return $official;
-            } elseif ($official === 'text/html') {
+            } elseif ($official === 'text/html'
+                || $official === 'text/xml' // FreshRSS
+                || $official === 'application/xml' // FreshRSS
+            ) {
                 return $this->feed_or_html();
             }
 

src/File.php

@@ -124,7 +124,7 @@ public function __construct(string $url, int $timeout = 10, int $redirects = 5,
                 curl_setopt($fp, CURLOPT_FAILONERROR, 1);
                 curl_setopt($fp, CURLOPT_TIMEOUT, $timeout);
                 curl_setopt($fp, CURLOPT_CONNECTTIMEOUT, $timeout);
-                curl_setopt($fp, CURLOPT_REFERER, \SimplePie\Misc::url_remove_credentials($url));
+                // curl_setopt($fp, CURLOPT_REFERER, \SimplePie\Misc::url_remove_credentials($url)); // FreshRSS removed
                 curl_setopt($fp, CURLOPT_USERAGENT, $useragent);
                 curl_setopt($fp, CURLOPT_HTTPHEADER, $headers2);
                 foreach ($curl_options as $curl_param => $curl_value) {
@@ -133,14 +133,20 @@ public function __construct(string $url, int $timeout = 10, int $redirects = 5,
 
                 $responseHeaders = curl_exec($fp);
                 if (curl_errno($fp) === 23 || curl_errno($fp) === 61) {
+                    $this->error = 'cURL error ' . curl_errno($fp) . ': ' . curl_error($fp); // FreshRSS
+                    $this->status_code = curl_getinfo($fp, CURLINFO_HTTP_CODE); // FreshRSS
+                    $this->on_http_response();
+                    $this->error = null; // FreshRSS
                     curl_setopt($fp, CURLOPT_ENCODING, 'none');
                     $responseHeaders = curl_exec($fp);
                 }
                 $this->status_code = curl_getinfo($fp, CURLINFO_HTTP_CODE);
                 if (curl_errno($fp)) {
                     $this->error = 'cURL error ' . curl_errno($fp) . ': ' . curl_error($fp);
                     $this->success = false;
+                    $this->on_http_response();
                 } else {
+                    $this->on_http_response();
                     // Use the updated url provided by curl_getinfo after any redirects.
                     if ($info = curl_getinfo($fp)) {
                         $this->url = $info['url'];
@@ -176,6 +182,7 @@ public function __construct(string $url, int $timeout = 10, int $redirects = 5,
                 if (!$fp) {
                     $this->error = 'fsockopen error: ' . $errstr;
                     $this->success = false;
+                    $this->on_http_response();
                 } else {
                     stream_set_timeout($fp, $timeout);
                     if (isset($url_parts['path'])) {
@@ -216,6 +223,7 @@ public function __construct(string $url, int $timeout = 10, int $redirects = 5,
                             $this->set_headers($parser->headers);
                             $this->body = $parser->body;
                             $this->status_code = $parser->status_code;
+                            $this->on_http_response();
                             if ((in_array($this->status_code, [300, 301, 302, 303, 307]) || $this->status_code > 307 && $this->status_code < 400) && ($locationHeader = $this->get_header_line('location')) !== '' && $this->redirects < $redirects) {
                                 $this->redirects++;
                                 $location = \SimplePie\Misc::absolutize_url($locationHeader, $url);
@@ -255,10 +263,15 @@ public function __construct(string $url, int $timeout = 10, int $redirects = 5,
                                         $this->success = false;
                                 }
                             }
+                        } else {
+                            $this->error = 'Could not parse'; // FreshRSS
+                            $this->success = false; // FreshRSS
+                            $this->on_http_response();
                         }
                     } else {
                         $this->error = 'fsocket timed out';
                         $this->success = false;
+                        $this->on_http_response();
                     }
                     fclose($fp);
                 }
@@ -273,9 +286,19 @@ public function __construct(string $url, int $timeout = 10, int $redirects = 5,
                 $this->body = trim($filebody);
                 $this->status_code = 200;
             }
+            $this->on_http_response();
         }
     }
 
+    /**
+     * Event to allow inheriting classes to e.g. log the HTTP responses.
+     * Triggered just after an HTTP response is received.
+     * FreshRSS.
+     */
+    protected function on_http_response(): void
+    {
+    }
+
     public function get_permanent_uri(): string
     {
         return (string) $this->permanent_url;

src/HTTP/Utils.php

@@ -0,0 +1,79 @@
+<?php
+
+declare(strict_types=1);
+
+namespace SimplePie\HTTP;
+
+/**
+ * HTTP util functions
+ * FreshRSS
+ * @internal
+ */
+final class Utils
+{
+    /**
+     * Extracts `max-age` from the `Cache-Control` HTTP headers
+     *
+     * @param array<string,mixed> $http_headers HTTP headers of the response
+     * @return int|null The `max-age` value or `null` if not found
+     *
+     * FreshRSS
+     */
+    public static function get_http_max_age(array $http_headers): ?int
+    {
+        $cache_control = $http_headers['cache-control'] ?? null;
+        if (is_string($cache_control) && preg_match('/\bmax-age=(\d+)\b/', $cache_control, $matches)) {
+            return (int) $matches[1];
+        }
+        return null;
+    }
+
+    /**
+     * Negotiate the cache expiration time based on the HTTP response headers.
+     * Return the cache duration time in number of seconds since the Unix Epoch, accounting for:
+     * - `Cache-Control: max-age` minus `Age`, bounded by `$cache_duration_min` and `$cache_duration_max`
+     * - `Cache-Control: must-revalidate` will set `$cache_duration` to `$cache_duration_min`
+     * - `Cache-Control: no-cache` will return `time() + $cache_duration_min`
+     * - `Cache-Control: no-store` will return `time() + $cache_duration_min - 3`
+     * - `Expires` like `Cache-Control: max-age` but only if it is absent
+     *
+     * @param array<string,mixed> $http_headers HTTP headers of the response
+     * @param int $cache_duration Desired cache duration in seconds, potentially overridden by HTTP response headers
+     * @param int $cache_duration_min Minimal cache duration (in seconds), overriding HTTP response headers `Cache-Control` and `Expires`,
+     * @param int $cache_duration_max Maximal cache duration (in seconds), overriding HTTP response headers `Cache-Control: max-age` and `Expires`,
+     * @return int The negotiated cache expiration time in seconds since the Unix Epoch
+     *
+     * FreshRSS
+     */
+    public static function negociate_cache_expiration_time(array $http_headers, int $cache_duration, int $cache_duration_min, int $cache_duration_max): int
+    {
+        $cache_control = $http_headers['cache-control'] ?? '';
+        if ($cache_control !== '') {
+            if (preg_match('/\bno-store\b/', $cache_control)) {
+                return time() + $cache_duration_min - 3; // -3 to distinguish from no-cache if needed
+            }
+            if (preg_match('/\bno-cache\b/', $cache_control)) {
+                return time() + $cache_duration_min;
+            }
+            if (preg_match('/\bmust-revalidate\b/', $cache_control)) {
+                $cache_duration = $cache_duration_min;
+            }
+            if (preg_match('/\bmax-age=(\d+)\b/', $cache_control, $matches)) {
+                $max_age = (int) $matches[1];
+                $age = $http_headers['age'] ?? '';
+                if (is_numeric($age)) {
+                    $max_age -= (int) $age;
+                }
+                return time() + min(max($max_age, $cache_duration), $cache_duration_max);
+            }
+        }
+        $expires = $http_headers['expires'] ?? '';
+        if ($expires !== '') {
+            $expire_date = \SimplePie\Misc::parse_date($expires);
+            if ($expire_date !== false) {
+                return min(max($expire_date, time() + $cache_duration), time() + $cache_duration_max);
+            }
+        }
+        return time() + $cache_duration;
+    }
+}