lib/tests/html2text_test.php

   1 <?php
   2 // This file is part of Moodle - http://moodle.org/
   3 //
   4 // Moodle is free software: you can redistribute it and/or modify
   5 // it under the terms of the GNU General Public License as published by
   6 // the Free Software Foundation, either version 3 of the License, or
   7 // (at your option) any later version.
   8 //
   9 // Moodle is distributed in the hope that it will be useful,
  10 // but WITHOUT ANY WARRANTY; without even the implied warranty of
  11 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  12 // GNU General Public License for more details.
  13 //
  14 // You should have received a copy of the GNU General Public License
  15 // along with Moodle.  If not, see <http://www.gnu.org/licenses/>.
  16
  17 /**
  18  * Tests our html2text hacks
  19  *
  20  * Note: includes original tests from testweblib.php
  21  *
  22  * @package    core
  23  * @category   phpunit
  24  * @copyright  2012 Petr Skoda {@link http://skodak.org}
  25  * @license    http://www.gnu.org/copyleft/gpl.html GNU GPL v3 or later
  26  */
  27
  28
  29 defined('MOODLE_INTERNAL') || die();
  30
  31
  32 class html2text_testcase extends basic_testcase {
  33
  34     /**
  35      * ALT as image replacements
  36      */
  37     public function test_images() {
  38         $this->assertEquals('[edit]', html_to_text('<img src="edit.png" alt="edit" />'));
  39
  40         $text = 'xx<img src="gif.gif" alt="some gif" />xx';
  41         $result = html_to_text($text, null, false, false);
  42         $this->assertSame($result, 'xx[some gif]xx');
  43     }
  44
  45     /**
  46      * No magic quotes messing
  47      */
  48     public function test_no_strip_slashes() {
  49         $this->assertEquals('[\edit]', html_to_text('<img src="edit.png" alt="\edit" />'));
  50
  51         $text = '\\magic\\quotes\\are\\\\horrible';
  52         $result = html_to_text($text, null, false, false);
  53         $this->assertSame($result, $text);
  54     }
  55
  56     /**
  57      * Textlib integration
  58      */
  59     public function test_textlib() {
  60         $text = '<strong>Žluťoučký koníček</strong>';
  61         $result = html_to_text($text, null, false, false);
  62         $this->assertSame($result, 'ŽLUŤOUČKÝ KONÍČEK');
  63     }
  64
  65     /**
  66      * Protect 0
  67      */
  68     public function test_zero() {
  69         $text = '0';
  70         $result = html_to_text($text, null, false, false);
  71         $this->assertSame($result, $text);
  72
  73         $this->assertSame('0', html_to_text('0'));
  74     }
  75
  76     // ======= Standard html2text conversion features =======
  77
  78     /**
  79      * Various invalid HTML typed by users that ignore html strict
  80      **/
  81     public function test_invalid_html() {
  82         $text = 'Gin & Tonic';
  83         $result = html_to_text($text, null, false, false);
  84         $this->assertSame($result, $text);
  85
  86         $text = 'Gin > Tonic';
  87         $result = html_to_text($text, null, false, false);
  88         $this->assertSame($result, $text);
  89
  90         $text = 'Gin < Tonic';
  91         $result = html_to_text($text, null, false, false);
  92         $this->assertSame($result, $text);
  93     }
  94
  95     /**
  96      * Basic text formatting.
  97      */
  98     public function test_simple() {
  99         $this->assertEquals("_Hello_ WORLD!", html_to_text('<p><i>Hello</i> <b>world</b>!</p>'));
 100         $this->assertEquals("All the WORLD’S a stage.\n\n-- William Shakespeare", html_to_text('<p>All the <strong>world’s</strong> a stage.</p><p>-- William Shakespeare</p>'));
 101         $this->assertEquals("HELLO WORLD!\n\n", html_to_text('<h1>Hello world!</h1>'));
 102         $this->assertEquals("Hello\nworld!", html_to_text('Hello<br />world!'));
 103     }
 104
 105     /**
 106      * Test line wrapping
 107      */
 108     public function test_text_nowrap() {
 109         $long = "Here is a long string, more than 75 characters long, since by default html_to_text wraps text at 75 chars.";
 110         $wrapped = "Here is a long string, more than 75 characters long, since by default\nhtml_to_text wraps text at 75 chars.";
 111         $this->assertEquals($long, html_to_text($long, 0));
 112         $this->assertEquals($wrapped, html_to_text($long));
 113     }
 114
 115     /**
 116      * Whitespace removal
 117      */
 118     public function test_trailing_whitespace() {
 119         $this->assertEquals('With trailing whitespace and some more text', html_to_text("With trailing whitespace   \nand some   more text", 0));
 120     }
 121
 122     /**
 123      * PRE parsing
 124      */
 125     public function test_html_to_text_pre_parsing_problem() {
 126         $strorig = 'Consider the following function:<br /><pre><span style="color: rgb(153, 51, 102);">void FillMeUp(char* in_string) {'.
 127             '<br />  int i = 0;<br />  while (in_string[i] != \'\0\') {<br />    in_string[i] = \'X\';<br />    i++;<br />  }<br />'.
 128             '}</span></pre>What would happen if a non-terminated string were input to this function?<br /><br />';
 129
 130         $strconv = 'Consider the following function:
 131
 132 void FillMeUp(char* in_string) {
 133  int i = 0;
 134  while (in_string[i] != \'\0\') {
 135  in_string[i] = \'X\';
 136  i++;
 137  }
 138 }
 139 What would happen if a non-terminated string were input to this function?
 140
 141 ';
 142
 143         $this->assertSame($strconv, html_to_text($strorig));
 144     }
 145 }
 146