From 7e152ccaeac9800768af2737fc4fab7fc8518cd4 Mon Sep 17 00:00:00 2001
From: Michael Klein <Omegatcu@googlemail.com>
Date: Sat, 2 Dec 2017 23:05:47 +0100
Subject: [PATCH 1/2] Fix file_get_contents(): stream does not support seeking

Fixes an error in PHP 7.1 for the file_get_contents() function.
---
 src/simple_html_dom.php | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/simple_html_dom.php b/src/simple_html_dom.php
index 70abf50..417170b 100755
--- a/src/simple_html_dom.php
+++ b/src/simple_html_dom.php
@@ -68,7 +68,7 @@
 // -----------------------------------------------------------------------------
 // get html dom from file
 // $maxlen is defined in the code as PHP_STREAM_COPY_ALL which is defined as -1.
-function file_get_html($url, $use_include_path = false, $context=null, $offset = -1, $maxLen=-1, $lowercase = true, $forceTagsClosed=true, $target_charset = DEFAULT_TARGET_CHARSET, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT, $defaultSpanText=DEFAULT_SPAN_TEXT)
+function file_get_html($url, $use_include_path = false, $context=null, $offset = 0, $maxLen=-1, $lowercase = true, $forceTagsClosed=true, $target_charset = DEFAULT_TARGET_CHARSET, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT, $defaultSpanText=DEFAULT_SPAN_TEXT)
 {
     // We DO force the tags to be terminated.
     $dom = new simple_html_dom(null, $lowercase, $forceTagsClosed, $target_charset, $stripRN, $defaultBRText, $defaultSpanText);
@@ -1719,4 +1719,4 @@ function getElementsByTagName($name, $idx=-1) {return $this->find($name, $idx);}
     function loadFile() {$args = func_get_args();$this->load_file($args);}
 }
 
-?>
\ No newline at end of file
+?>

From c2d3d884cc013390b400aa7480dd97265e00efb2 Mon Sep 17 00:00:00 2001
From: Gregory Duchatelet <greg@easyflirt.com>
Date: Thu, 4 Aug 2022 10:36:13 +0200
Subject: [PATCH 2/2] fix regex

---
 src/simple_html_dom.php | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/src/simple_html_dom.php b/src/simple_html_dom.php
index 417170b..997d5b5 100755
--- a/src/simple_html_dom.php
+++ b/src/simple_html_dom.php
@@ -681,7 +681,7 @@ protected function parse_selector($selector_string) {
 // This implies that an html attribute specifier may start with an @ sign that is NOT captured by the expression.
 // farther study is required to determine of this should be documented or removed.
 //        $pattern = "/([\w-:\*]*)(?:\#([\w-]+)|\.([\w-]+))?(?:\[@?(!?[\w-]+)(?:([!*^$]?=)[\"']?(.*?)[\"']?)?\])?([\/, ]+)/is";
-        $pattern = "/([\w-:\*]*)(?:\#([\w-]+)|\.([\w-]+))?(?:\[@?(!?[\w-:]+)(?:([!*^$]?=)[\"']?(.*?)[\"']?)?\])?([\/, ]+)/is";
+        $pattern = "/([a-zA-Z_0-9:\*-]*)(?:\#([a-zA-Z_0-9-]+)|\.([a-zA-Z_0-9-]+))?(?:\[@?(!?[a-zA-Z_0-9-:]+)(?:([!*^$]?=)[\"']?(.*?)[\"']?)?\])?([\/, ]+)/is";
         preg_match_all($pattern, trim($selector_string).' ', $matches, PREG_SET_ORDER);
         if (is_object($debugObject)) {$debugObject->debugLog(2, "Matches Array: ", $matches);}
 
@@ -703,7 +703,7 @@ protected function parse_selector($selector_string) {
             if (!empty($m[6])) {$val=$m[6];}
 
             // convert to lowercase
-            if ($this->dom->lowercase) {$tag=strtolower($tag); $key=strtolower($key);}
+            if ($this->dom->lowercase) {$tag=strtolower($tag); $key=strtolower($key ?? '');}
             //elements that do NOT have the specified attribute
             if (isset($key[0]) && $key[0]==='!') {$key=substr($key, 1); $no_key=true;}
 
@@ -1362,7 +1362,7 @@ protected function read_tag()
             return true;
         }
 
-        if (!preg_match("/^[\w-:]+$/", $tag)) {
+        if (!preg_match("/^[a-zA-Z_0-9:-]+$/", $tag)) {
             $node->_[HDOM_INFO_TEXT] = '<' . $tag . $this->copy_until('<>');
             if ($this->char==='<') {
                 $this->link_nodes($node, false);