Parse formatting inside HTML lists

CHANGELOG.md

@@ -7,6 +7,7 @@ v0.15.0 (?? ??? 2018)
 ----------------------
 ### Added
 - Parsing of "align" HTML attribute - @troosan #1231
+- Parse formatting inside HTML lists - @troosan @samimussbach #1239 #945 #1215 #508
 
 ### Fixed
 

README.md

@@ -10,7 +10,7 @@
 
 PHPWord is a library written in pure PHP that provides a set of classes to write to and read from different document file formats. The current version of PHPWord supports Microsoft [Office Open XML](http://en.wikipedia.org/wiki/Office_Open_XML) (OOXML or OpenXML), OASIS [Open Document Format for Office Applications](http://en.wikipedia.org/wiki/OpenDocument) (OpenDocument or ODF), [Rich Text Format](http://en.wikipedia.org/wiki/Rich_Text_Format) (RTF), HTML, and PDF.
 
-PHPWord is an open source project licensed under the terms of [LGPL version 3](https://github.com/PHPOffice/PHPWord/blob/develop/COPYING.LESSER). PHPWord is aimed to be a high quality software product by incorporating [continuous integration](https://travis-ci.org/PHPOffice/PHPWord) and [unit testing](http://phpoffice.github.io/PHPWord/coverage/develop/). You can learn more about PHPWord by reading the [Developers' Documentation](http://phpword.readthedocs.org/) and the [API Documentation](http://phpoffice.github.io/PHPWord/docs/develop/).
+PHPWord is an open source project licensed under the terms of [LGPL version 3](https://github.com/PHPOffice/PHPWord/blob/develop/COPYING.LESSER). PHPWord is aimed to be a high quality software product by incorporating [continuous integration](https://travis-ci.org/PHPOffice/PHPWord) and [unit testing](http://phpoffice.github.io/PHPWord/coverage/develop/). You can learn more about PHPWord by reading the [Developers' Documentation](http://phpword.readthedocs.org/).
 
 If you have any questions, please ask on [StackOverFlow](https://stackoverflow.com/questions/tagged/phpword)
 

docs/elements.rst

@@ -406,8 +406,10 @@ For instance for the INDEX field, you can do the following (See `Index Field for
     $fieldText->addText('My ');
     $fieldText->addText('bold index', ['bold' => true]);
     $fieldText->addText(' entry');
+    $section->addField('XE', array(), array(), $fieldText);
 
-    $section->addField('INDEX', array(), array('\\e "	" \\h "A" \\c "3"'), $fieldText);
+    //this actually adds the index
+    $section->addField('INDEX', array(), array('\\e "	" \\h "A" \\c "3"'), 'right click to update index');
 
 Line
 ----

samples/Sample_26_Html.php

@@ -9,25 +9,50 @@
 $html = '<h1>Adding element via HTML</h1>';
 $html .= '<p>Some well formed HTML snippet needs to be used</p>';
 $html .= '<p>With for example <strong>some<sup>1</sup> <em>inline</em> formatting</strong><sub>1</sub></p>';
-$html .= '<p>Unordered (bulleted) list:</p>';
+
+$html .= '<p style="margin-top: 240pt;">Unordered (bulleted) list:</p>';
 $html .= '<ul><li>Item 1</li><li>Item 2</li><ul><li>Item 2.1</li><li>Item 2.1</li></ul></ul>';
-$html .= '<p>Ordered (numbered) list:</p>';
-$html .= '<ol><li>Item 1</li><li>Item 2</li></ol>';
 
-$html .= '<p>List with complex content:</p>';
+$html .= '<p style="margin-top: 240pt;">Ordered (numbered) list:</p>';
+$html .= '<ol>
+                <li><p style="font-weight: bold;">List 1 item 1</p></li>
+                <li>List 1 item 2</li>
+                <ol>
+                    <li>sub list 1</li>
+                    <li>sub list 2</li>
+                </ol>
+                <li>List 1 item 3</li>
+            </ol>
+            <p style="margin-top: 15px;">A second list, numbering should restart</p>
+            <ol>
+                <li>List 2 item 1</li>
+                <li>List 2 item 2</li>
+                <ol>
+                    <li>sub list 1</li>
+                    <li>sub list 2</li>
+                </ol>
+                <li>List 2 item 3</li>
+                <ol>
+                    <li>sub list 1, restarts with a</li>
+                    <li>sub list 2</li>
+                </ol>
+            </ol>';
+
+$html .= '<p style="margin-top: 240pt;">List with formatted content:</p>';
 $html .= '<ul>
                 <li>
                     <span style="font-family: arial,helvetica,sans-serif;">
-                        <span style="font-size: 12px;">list item1</span>
+                        <span style="font-size: 16px;">big list item1</span>
                     </span>
                 </li>
                 <li>
                     <span style="font-family: arial,helvetica,sans-serif;">
-                        <span style="font-size: 12px;">list item2</span>
+                        <span style="font-size: 10px; font-weight: bold;">list item2 in bold</span>
                     </span>
                 </li>
             </ul>';
 
+$html .= '<p style="margin-top: 240pt;">A table with formatting:</p>';
 $html .= '<table align="center" style="width: 50%; border: 6px #0000FF double;">
                 <thead>
                     <tr style="background-color: #FF0000; text-align: center; color: #FFFFFF; font-weight: bold; ">

src/PhpWord/Element/AbstractContainer.php

@@ -33,11 +33,10 @@
  * @method CheckBox addCheckBox(string $name, $text, mixed $fStyle = null, mixed $pStyle = null)
  * @method Title addTitle(string $text, int $depth = 1)
  * @method TOC addTOC(mixed $fontStyle = null, mixed $tocStyle = null, int $minDepth = 1, int $maxDepth = 9)
- *
  * @method PageBreak addPageBreak()
  * @method Table addTable(mixed $style = null)
  * @method Image addImage(string $source, mixed $style = null, bool $isWatermark = false)
- * @method \PhpOffice\PhpWord\Element\OLEObject addObject(string $source, mixed $style = null)
+ * @method OLEObject addOLEObject(string $source, mixed $style = null)
  * @method TextBox addTextBox(mixed $style = null)
  * @method Field addField(string $type = null, array $properties = array(), array $options = array(), mixed $text = null)
  * @method Line addLine(mixed $lineStyle = null)
@@ -46,6 +45,8 @@
  * @method FormField addFormField(string $type, mixed $fStyle = null, mixed $pStyle = null)
  * @method SDT addSDT(string $type)
  *
+ * @method \PhpOffice\PhpWord\Element\OLEObject addObject(string $source, mixed $style = null) deprecated, use addOLEObject instead
+ *
  * @since 0.10.0
  */
 abstract class AbstractContainer extends AbstractElement
@@ -200,7 +201,7 @@ private function checkValidity($method)
             'FormField'     => $generalContainers,
             'SDT'           => $generalContainers,
             'TrackChange'   => $generalContainers,
-            'TextRun'       => array('Section', 'Header', 'Footer', 'Cell', 'TextBox', 'TrackChange'),
+            'TextRun'       => array('Section', 'Header', 'Footer', 'Cell', 'TextBox', 'TrackChange', 'ListItemRun'),
             'ListItem'      => array('Section', 'Header', 'Footer', 'Cell', 'TextBox'),
             'ListItemRun'   => array('Section', 'Header', 'Footer', 'Cell', 'TextBox'),
             'Table'         => array('Section', 'Header', 'Footer', 'Cell', 'TextBox'),

src/PhpWord/Shared/Html.php

@@ -18,10 +18,10 @@
 namespace PhpOffice\PhpWord\Shared;
 
 use PhpOffice\PhpWord\Element\AbstractContainer;
-use PhpOffice\PhpWord\Element\Cell;
 use PhpOffice\PhpWord\Element\Row;
 use PhpOffice\PhpWord\Element\Table;
 use PhpOffice\PhpWord\SimpleType\Jc;
+use PhpOffice\PhpWord\SimpleType\NumberFormat;
 
 /**
  * Common Html functions
@@ -30,6 +30,8 @@
  */
 class Html
 {
+    private static $listIndex = 0;
+
     /**
      * Add HTML parts.
      *
@@ -135,8 +137,8 @@ protected static function parseNode($node, $element, $styles = array(), $data =
             'tr'        => array('Row',         $node,  $element,   $styles,    null,   null,           null),
             'td'        => array('Cell',        $node,  $element,   $styles,    null,   null,           null),
             'th'        => array('Cell',        $node,  $element,   $styles,    null,   null,           null),
-            'ul'        => array('List',        null,   null,       $styles,    $data,  3,              null),
-            'ol'        => array('List',        null,   null,       $styles,    $data,  7,              null),
+            'ul'        => array('List',        $node,  $element,   $styles,    $data,  null,           null),
+            'ol'        => array('List',        $node,  $element,   $styles,    $data,  null,           null),
             'li'        => array('ListItem',    $node,  $element,   $styles,    $data,  null,           null),
             'img'       => array('Image',       $node,  $element,   $styles,    null,   null,           null),
             'br'        => array('LineBreak',   null,   $element,   $styles,    null,   null,           null),
@@ -330,7 +332,7 @@ private static function parseRow($node, $element, &$styles)
      * @param \DOMNode $node
      * @param \PhpOffice\PhpWord\Element\Table $element
      * @param array &$styles
-     * @return Cell $element
+     * @return \PhpOffice\PhpWord\Element\Cell $element
      */
     private static function parseCell($node, $element, &$styles)
     {
@@ -365,18 +367,56 @@ private static function recursiveParseStylesInHierarchy(\DOMNode $node, array $s
     /**
      * Parse list node
      *
+     * @param \DOMNode $node
+     * @param \PhpOffice\PhpWord\Element\AbstractContainer $element
      * @param array &$styles
      * @param array &$data
-     * @param string $argument1 List type
      */
-    private static function parseList(&$styles, &$data, $argument1)
+    private static function parseList($node, $element, &$styles, &$data)
     {
+        $isOrderedList = $node->nodeName == 'ol';
         if (isset($data['listdepth'])) {
             $data['listdepth']++;
         } else {
             $data['listdepth'] = 0;
+            $styles['list'] = 'listStyle_' . self::$listIndex++;
+            $element->getPhpWord()->addNumberingStyle($styles['list'], self::getListStyle($isOrderedList));
+        }
+    }
+
+    private static function getListStyle($isOrderedList)
+    {
+        if ($isOrderedList) {
+            return array(
+                'type'   => 'multilevel',
+                'levels' => array(
+                    array('format' => NumberFormat::DECIMAL,      'text' => '%1.', 'alignment' => 'left',  'tabPos' => 720,  'left' => 720,  'hanging' => 360),
+                    array('format' => NumberFormat::LOWER_LETTER, 'text' => '%2.', 'alignment' => 'left',  'tabPos' => 1440, 'left' => 1440, 'hanging' => 360),
+                    array('format' => NumberFormat::LOWER_ROMAN,  'text' => '%3.', 'alignment' => 'right', 'tabPos' => 2160, 'left' => 2160, 'hanging' => 180),
+                    array('format' => NumberFormat::DECIMAL,      'text' => '%4.', 'alignment' => 'left',  'tabPos' => 2880, 'left' => 2880, 'hanging' => 360),
+                    array('format' => NumberFormat::LOWER_LETTER, 'text' => '%5.', 'alignment' => 'left',  'tabPos' => 3600, 'left' => 3600, 'hanging' => 360),
+                    array('format' => NumberFormat::LOWER_ROMAN,  'text' => '%6.', 'alignment' => 'right', 'tabPos' => 4320, 'left' => 4320, 'hanging' => 180),
+                    array('format' => NumberFormat::DECIMAL,      'text' => '%7.', 'alignment' => 'left',  'tabPos' => 5040, 'left' => 5040, 'hanging' => 360),
+                    array('format' => NumberFormat::LOWER_LETTER, 'text' => '%8.', 'alignment' => 'left',  'tabPos' => 5760, 'left' => 5760, 'hanging' => 360),
+                    array('format' => NumberFormat::LOWER_ROMAN,  'text' => '%9.', 'alignment' => 'right', 'tabPos' => 6480, 'left' => 6480, 'hanging' => 180),
+                ),
+            );
         }
-        $styles['list']['listType'] = $argument1;
+
+        return array(
+            'type'   => 'hybridMultilevel',
+            'levels' => array(
+                array('format' => NumberFormat::BULLET, 'text' => '', 'alignment' => 'left', 'tabPos' => 720,  'left' => 720,  'hanging' => 360, 'font' => 'Symbol',      'hint' => 'default'),
+                array('format' => NumberFormat::BULLET, 'text' => 'o',  'alignment' => 'left', 'tabPos' => 1440, 'left' => 1440, 'hanging' => 360, 'font' => 'Courier New', 'hint' => 'default'),
+                array('format' => NumberFormat::BULLET, 'text' => '', 'alignment' => 'left', 'tabPos' => 2160, 'left' => 2160, 'hanging' => 360, 'font' => 'Wingdings',   'hint' => 'default'),
+                array('format' => NumberFormat::BULLET, 'text' => '', 'alignment' => 'left', 'tabPos' => 2880, 'left' => 2880, 'hanging' => 360, 'font' => 'Symbol',      'hint' => 'default'),
+                array('format' => NumberFormat::BULLET, 'text' => 'o',  'alignment' => 'left', 'tabPos' => 3600, 'left' => 3600, 'hanging' => 360, 'font' => 'Courier New', 'hint' => 'default'),
+                array('format' => NumberFormat::BULLET, 'text' => '', 'alignment' => 'left', 'tabPos' => 4320, 'left' => 4320, 'hanging' => 360, 'font' => 'Wingdings',   'hint' => 'default'),
+                array('format' => NumberFormat::BULLET, 'text' => '', 'alignment' => 'left', 'tabPos' => 5040, 'left' => 5040, 'hanging' => 360, 'font' => 'Symbol',      'hint' => 'default'),
+                array('format' => NumberFormat::BULLET, 'text' => 'o',  'alignment' => 'left', 'tabPos' => 5760, 'left' => 5760, 'hanging' => 360, 'font' => 'Courier New', 'hint' => 'default'),
+                array('format' => NumberFormat::BULLET, 'text' => '', 'alignment' => 'left', 'tabPos' => 6480, 'left' => 6480, 'hanging' => 360, 'font' => 'Wingdings',   'hint' => 'default'),
+            ),
+        );
     }
 
     /**
@@ -394,17 +434,10 @@ private static function parseListItem($node, $element, &$styles, $data)
     {
         $cNodes = $node->childNodes;
         if (!empty($cNodes)) {
-            $text = '';
+            $listRun = $element->addListItemRun($data['listdepth'], $styles['list'], $styles['paragraph']);
             foreach ($cNodes as $cNode) {
-                if ($cNode->nodeName == '#text') {
-                    $text = $cNode->nodeValue;
-                }
+                self::parseNode($cNode, $listRun, $styles, $data);
             }
-            //ideally we should be parsing child nodes for any style, for now just take the text
-            if ('' == trim($text) && '' != trim($node->textContent)) {
-                $text = trim($node->textContent);
-            }
-            $element->addListItem($text, $data['listdepth'], $styles['font'], $styles['list'], $styles['paragraph']);
         }
     }
 
@@ -462,6 +495,12 @@ private static function parseStyle($attribute, $styles)
                     }
                     $styles['italic'] = $tValue;
                     break;
+                case 'margin-top':
+                    $styles['spaceBefore'] = Converter::cssToPoint($cValue);
+                    break;
+                case 'margin-bottom':
+                    $styles['spaceAfter'] = Converter::cssToPoint($cValue);
+                    break;
                 case 'border-color':
                     $styles['color'] = trim($cValue, '#');
                     break;
@@ -582,14 +621,14 @@ private static function mapBorderStyle($cssBorderStyle)
     private static function mapAlign($cssAlignment)
     {
         switch ($cssAlignment) {
-            case 'left':
-                return Jc::START;
             case 'right':
                 return Jc::END;
             case 'center':
                 return Jc::CENTER;
             case 'justify':
                 return Jc::BOTH;
+            default:
+                return Jc::START;
         }
 
         return null;