Allow a hash of options to be passed to html2text

README.md

@@ -64,6 +64,23 @@ $text = \Soundasleep\Html2Text::convert($html);
 
 You can also include the supplied `html2text.php` and use `$text = convert_html_to_text($html);` instead.
 
+### Options
+
+| Option | Default | Description |
+|--------|---------|-------------|
+| **ignore_errors** | `false` | Set to `true` to ignore any XML parsing errors. |
+| **drop_links** | `false` | Set to `true` to not render links as `[http://foo.com](My Link)`, but rather just `My Link`. |
+
+Pass along options as a second argument to `convert`, for example:
+
+```php
+$options = array(
+  'ignore_errors' => true,
+  // other options go here
+);
+$text = \Soundasleep\Html2Text::convert($html, $options);
+```
+
 ## Tests
 
 Some very basic tests are provided in the `tests/` directory. Run them with `composer install && vendor/bin/phpunit`.

src/Html2Text.php

@@ -4,6 +4,13 @@
 
 class Html2Text {
 
+	public static function defaultOptions() {
+		return array(
+			'ignore_errors' => false,
+			'drop_links'    => false,
+		);
+	}
+
 	/**
 	 * Tries to convert the given HTML into a plain text format - best suited for
 	 * e-mail display, etc.
@@ -19,7 +26,21 @@ class Html2Text {
 	 * @return string the HTML converted, as best as possible, to text
 	 * @throws Html2TextException if the HTML could not be loaded as a {@link \DOMDocument}
 	 */
-	public static function convert($html, $ignore_error = false) {
+	public static function convert($html, $options = array()) {
+
+		if ($options === false || $options === true) {
+			// Using old style (< 1.0) of passing in options
+			$options = array('ignore_errors' => $options);
+		}
+
+		$options = array_merge(static::defaultOptions(), $options);
+
+		// check all options are valid
+		foreach ($options as $key => $value) {
+			if (!in_array($key, array_keys(static::defaultOptions()))) {
+				throw new \InvalidArgumentException("Unknown html2text option '$key'");
+			}
+		}
 
 		$is_office_document = static::isOfficeDocument($html);
 
@@ -33,9 +54,9 @@ public static function convert($html, $ignore_error = false) {
 			$html = mb_convert_encoding($html, "HTML-ENTITIES", "UTF-8");
 		}
 
-		$doc = static::getDocument($html, $ignore_error);
+		$doc = static::getDocument($html, $options['ignore_errors']);
 
-		$output = static::iterateOverNode($doc, null, false, $is_office_document);
+		$output = static::iterateOverNode($doc, null, false, $is_office_document, $options);
 
 		// process output for whitespace/newlines
 		$output = static::processWhitespaceNewlines($output);
@@ -186,7 +207,7 @@ static function nextChildName($node) {
 		return $nextName;
 	}
 
-	static function iterateOverNode($node, $prevName = null, $in_pre = false, $is_office_document = false) {
+	static function iterateOverNode($node, $prevName = null, $in_pre = false, $is_office_document = false, $options) {
 		if ($node instanceof \DOMText) {
 		  // Replace whitespace characters with a space (equivilant to \s)
 			if ($in_pre) {
@@ -307,7 +328,7 @@ static function iterateOverNode($node, $prevName = null, $in_pre = false, $is_of
 
 			while ($n != null) {
 
-				$text = static::iterateOverNode($n, $previousSiblingName, $in_pre || $name == 'pre', $is_office_document);
+				$text = static::iterateOverNode($n, $previousSiblingName, $in_pre || $name == 'pre', $is_office_document, $options);
 
 				// Pass current node name to next child, as previousSibling does not appear to get populated
 				if ($n instanceof \DOMDocumentType
@@ -391,19 +412,27 @@ static function iterateOverNode($node, $prevName = null, $in_pre = false, $is_of
 				if ($href == null) {
 					// it doesn't link anywhere
 					if ($node->getAttribute("name") != null) {
-						$output = "[$output]";
+						if ($options['drop_links']) {
+							$output = "$output";
+						} else {
+							$output = "[$output]";
+						}
 					}
 				} else {
 					if ($href == $output || $href == "mailto:$output" || $href == "http://$output" || $href == "https://$output") {
 						// link to the same address: just use link
-						$output;
+						$output = "$output";
 					} else {
 						// replace it
 						if ($output) {
-							$output = "[$output]($href)";
+							if ($options['drop_links']) {
+								$output = "$output";
+							} else {
+								$output = "[$output]($href)";
+							}
 						} else {
 							// empty string
-							$output = $href;
+							$output = "$href";
 						}
 					}
 				}

tests/Html2TextTest.php

@@ -4,16 +4,20 @@
 
 class Html2TextTest extends \PHPUnit\Framework\TestCase {
 
-	function doTest($test, $ignoreXmlError = false) {
+	function doTest($test, $options = array()) {
+		return $this->doTestWithResults($test, $test, $options);
+	}
+
+	function doTestWithResults($test, $result, $options = array()) {
 		$this->assertTrue(file_exists(__DIR__ . "/$test.html"), "File '$test.html' did not exist");
-		$this->assertTrue(file_exists(__DIR__ . "/$test.txt"), "File '$test.txt' did not exist");
+		$this->assertTrue(file_exists(__DIR__ . "/$result.txt"), "File '$result.txt' did not exist");
 		$input = file_get_contents(__DIR__ . "/$test.html");
-		$expected = \Soundasleep\Html2Text::fixNewlines(file_get_contents(__DIR__ . "/$test.txt"));
+		$expected = \Soundasleep\Html2Text::fixNewlines(file_get_contents(__DIR__ . "/$result.txt"));
 
-		$output = \Soundasleep\Html2Text::convert($input, $ignoreXmlError);
+		$output = \Soundasleep\Html2Text::convert($input, $options);
 
 		if ($output != $expected) {
-			file_put_contents(__DIR__ . "/$test.output", $output);
+			file_put_contents(__DIR__ . "/$result.output", $output);
 		}
 		$this->assertEquals($output, $expected);
 	}
@@ -103,14 +107,34 @@ function testHugeMsoffice() {
 	}
 
 	/**
-     * @expectedException PHPUnit\Framework\Error\Warning
-     */
+	 * @expectedException PHPUnit\Framework\Error\Warning
+	 */
 	function testInvalidXML() {
-		$this->doTest("invalid", false);
+		$this->doTest("invalid", array('ignore_errors' => false));
 	}
 
 	function testInvalidXMLIgnore() {
+		$this->doTest("invalid", array('ignore_errors' => true));
+	}
+
+	function testInvalidXMLIgnoreOldSyntax() {
+		// for BC, allow old #convert(text, bool) syntax
 		$this->doTest("invalid", true);
 	}
 
-}
+	/**
+	 * @expectedException InvalidArgumentException
+	 */
+	function testInvalidOption() {
+		$this->doTest("basic", array('invalid_option' => true));
+	}
+
+	function testBasicDropLinks() {
+		$this->doTestWithResults("basic", "basic.no-links", array('drop_links' => true));
+	}
+
+	function testAnchorsDropLinks() {
+		$this->doTestWithResults("anchors", "anchors.no-links", array('drop_links' => true));
+	}
+
+}

tests/anchors.no-links.txt

@@ -0,0 +1,5 @@
+A document without any HTML open/closing tags.
+---------------------------------------------------------------
+We try and use the representation given by common browsers of the HTML document, so that it looks similar when converted to plain text. visit foo.com - or http://www.foo.com link
+
+An anchor which will not appear

tests/basic.no-links.txt

@@ -0,0 +1,15 @@
+Hello, World!
+
+This is some e-mail content. Even though it has whitespace and newlines, the e-mail converter will handle it correctly.
+
+Even mismatched tags.
+
+A div
+Another div
+A div
+within a div
+
+Another line
+Yet another line
+
+A link