From 7798c2771142fd67dd37a45106fe2b6cdfb150d5 Mon Sep 17 00:00:00 2001
From: Felipe Nunes Azambuja <felipenunesazambuja@gmail.com>
Date: Wed, 8 Apr 2020 21:25:25 -0300
Subject: [PATCH] update to php 7.3

regex update
---
 .../simplehtmldom_1_5/simple_html_dom.php          | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/Src/Sunra/PhpSimple/simplehtmldom_1_5/simple_html_dom.php b/Src/Sunra/PhpSimple/simplehtmldom_1_5/simple_html_dom.php
index 279d589..6fa1363 100644
--- a/Src/Sunra/PhpSimple/simplehtmldom_1_5/simple_html_dom.php
+++ b/Src/Sunra/PhpSimple/simplehtmldom_1_5/simple_html_dom.php
@@ -73,7 +73,7 @@
 // -----------------------------------------------------------------------------
 // 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=0, $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 = -1, $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, $defaultSpanText);
@@ -693,7 +693,7 @@ protected function parse_selector($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 = "/([\w\-:\*]*)(?:\#([\w\-]+)|\.([\w\-]+))?(?:\[@?(!?[\w\-:]+)(?:([!*^$]?=)[\"']?(.*?)[\"']?)?\])?([\/, ]+)/is";
         preg_match_all($pattern, trim($selector_string).' ', $matches, PREG_SET_ORDER);
         if (is_object($debugObject)) {$debugObject->debugLog(2, "Matches Array: ", $matches);}
 
@@ -899,7 +899,7 @@ function get_display_size()
         {
             // Thanks to user gnarf from stackoverflow for this regular expression.
             $attributes = array();
-            preg_match_all("/([\w-]+)\s*:\s*([^;]+)\s*;?/", $this->attr['style'], $matches, PREG_SET_ORDER);
+            preg_match_all("/([\w\-]+)\s*:\s*([^;]+)\s*;?/", $this->attr['style'], $matches, PREG_SET_ORDER);
             foreach ($matches as $match) {
               $attributes[$match[1]] = $match[2];
             }
@@ -952,8 +952,8 @@ function get_display_size()
     }
 
     // camel naming conventions
-    function getAllAttributes() {return array_map('html_entity_decode', $this->attr);}
-    function getAttribute($name) {return html_entity_decode($this->__get($name));}
+    function getAllAttributes() {return $this->attr;}
+    function getAttribute($name) {return $this->__get($name);}
     function setAttribute($name, $value) {$this->__set($name, $value);}
     function hasAttribute($name) {return $this->__isset($name);}
     function removeAttribute($name) {$this->__set($name, null);}
@@ -1245,7 +1245,7 @@ protected function parse_charset()
         if (empty($charset))
         {
             // Have php try to detect the encoding from the text given to us.
-            $charset = (function_exists('mb_detect_encoding')) ? mb_detect_encoding($this->root->plaintext . "ascii", $encoding_list = array( "UTF-8", "CP1252" ) ) : false;
+            $charset = mb_detect_encoding($this->root->plaintext . "ascii", $encoding_list = array( "UTF-8", "CP1252" ) );
             if (is_object($debugObject)) {$debugObject->debugLog(2, 'mb_detect found: ' . $charset);}
 
             // and if this doesn't work...  then we need to just wrongheadedly assume it's UTF-8 so that we can move on - cause this will usually give us most of what we need...
@@ -1375,7 +1375,7 @@ protected function read_tag()
             return true;
         }
 
-        if (!preg_match("/^[\w-:]+$/", $tag)) {
+        if (!preg_match("/^[\w\-:]+$/", $tag)) {
             $node->_[HDOM_INFO_TEXT] = '<' . $tag . $this->copy_until('<>');
             if ($this->char==='<') {
                 $this->link_nodes($node, false);