MDL-82828 core: Update Html2Text to version 4.3.2

lib/classes/component.php

@@ -102,6 +102,7 @@ class component {
     ];
     /** @var array<string|array<string>> associative array of PRS-4 namespaces and corresponding paths. */
     protected static $psr4namespaces = [
+        \Html2Text::class => 'lib/html2text/src',
         \MaxMind::class => 'lib/maxmind/MaxMind',
         \GeoIp2::class => 'lib/maxmind/GeoIp2',
         \Sabberworm\CSS::class => 'lib/php-css-parser',

lib/html2text/README.md

@@ -0,0 +1,26 @@
+# Html2Text
+
+A PHP library for converting HTML to formatted plain text.
+
+[![Build status](https://github.com/mtibben/html2text/actions/workflows/ci.yml/badge.svg)](https://github.com/mtibben/html2text/actions/workflows/ci.yml)
+
+## Installing
+
+```
+composer require html2text/html2text
+```
+
+## Basic Usage
+```php
+$html = new \Html2Text\Html2Text('Hello, &quot;<b>world</b>&quot;');
+
+echo $html->getText();  // Hello, "WORLD"
+```
+
+## History
+
+This library started life on the blog of Jon Abernathy http://www.chuggnutt.com/html2text
+
+A number of projects picked up the library and started using it - among those was RoundCube mail. They made a number of updates to it over time to suit their webmail client.
+
+Now it has been extracted as a standalone library. Hopefully it can be of use to others.

lib/html2text/composer.json

@@ -0,0 +1,23 @@
+{
+    "name": "html2text/html2text",
+    "description": "Converts HTML to formatted plain text",
+    "type": "library",
+    "license": "GPL-2.0-or-later",
+    "autoload": {
+        "psr-4": {
+            "Html2Text\\": "src/"
+        }
+    },
+    "autoload-dev": {
+        "psr-4": {
+            "Html2Text\\": "test/"
+        }
+    },
+    "require-dev": {
+        "phpunit/phpunit": "~4|^9.0"
+    },
+    "suggest": {
+        "ext-mbstring": "For best performance",
+        "symfony/polyfill-mbstring": "If you can't install ext-mbstring"
+    }
+}

lib/html2text/lib.php

@@ -26,7 +26,6 @@
 
 defined('MOODLE_INTERNAL') || die();
 
-require_once($CFG->libdir . '/html2text/Html2Text.php');
 require_once(__DIR__ . '/override.php');
 
 /**

lib/html2text/readme_moodle.txt

@@ -1,4 +1,4 @@
-Description of Html2Text v4.3.1 library import into Moodle
+Description of Html2Text library import into Moodle
 
 Please note that we override some mb_* functions in Html2Text's namespace at
 run time. Until Html2Text adds some sort of fallback for the mb_* functions
@@ -9,6 +9,8 @@ Instructions
 ------------
 1. Download the latest release of Html2Text from https://github.com/mtibben/html2text/releases/
 2. Extract the contents of the release archive into a directory.
-3. Copy src/Html2Text.php to lib/html2text/
+3. Copy src to lib/html2text/src
+4. Update README
+5. Update composer.json
 
 Imported from: https://github.com/mtibben/html2text/releases/

lib/html2text/src/Html2Text.php

@@ -236,16 +236,19 @@ class Html2Text
      */
     public function __construct($html = '', $options = array())
     {
+        $this->htmlFuncFlags = (PHP_VERSION_ID < 50400)
+            ? ENT_QUOTES
+            : ENT_QUOTES | ENT_HTML5;
+
         // for backwards compatibility
         if (!is_array($options)) {
-            return call_user_func_array(array($this, 'legacyConstruct'), func_get_args());
+            // phpcs:ignore (PHPCompatibility.FunctionUse.ArgumentFunctionsReportCurrentValue.NeedsInspection
+            call_user_func_array(array($this, 'legacyConstruct'), func_get_args());
+            return;
         }
 
         $this->html = $html;
         $this->options = array_merge($this->options, $options);
-        $this->htmlFuncFlags = (PHP_VERSION_ID < 50400)
-            ? ENT_COMPAT
-            : ENT_COMPAT | ENT_HTML5;
     }
 
     /**
@@ -351,7 +354,11 @@ class Html2Text
     {
         $this->linkList = array();
 
-        $text = trim($this->html);
+        if ($this->html === null) {
+            $text = '';
+        } else {
+            $text = trim($this->html);
+        }
 
         $this->converter($text);
 
@@ -389,6 +396,9 @@ class Html2Text
         $text = preg_replace("/[\n]{3,}/", "\n\n", $text);
 
         // remove leading empty lines (can be produced by eg. P tag on the beginning)
+        if ($text === null) {
+            $text = '';
+        }
         $text = ltrim($text, "\n");
 
         if ($this->options['width'] > 0) {
@@ -417,7 +427,7 @@ class Html2Text
         }
 
         // Ignored link types
-        if (preg_match('!^(javascript:|mailto:|#)!i', html_entity_decode($link))) {
+        if (preg_match('!^(javascript:|mailto:|#)!i', html_entity_decode($link, $this->htmlFuncFlags, self::ENCODING))) {
             return $display;
         }
 

lib/thirdpartylibs.xml

@@ -235,7 +235,7 @@
     <location>html2text</location>
     <name>HTML2Text</name>
     <description>PHP script to convert HTML into an approximate text equivalent.</description>
-    <version>4.3.1</version>
+    <version>4.3.2</version>
     <license>GPL</license>
     <licenseversion>2.0+</licenseversion>
     <repository>https://github.com/mtibben/html2text</repository>