From 4c7e1399fed7905c86aa6a1c9d0f767dac0dc6c6 Mon Sep 17 00:00:00 2001
From: Roman Syroeshko <syroeshkoro@gmail.com>
Date: Tue, 28 Jun 2016 21:37:36 +0400
Subject: [PATCH] #483. Output escaping for HTML.

---
 README.md                                     | 11 +++---
 composer.json                                 | 20 +++++-----
 docs/installing.rst                           |  4 +-
 docs/intro.rst                                |  4 +-
 .../Writer/HTML/Element/AbstractElement.php   |  7 ++++
 src/PhpWord/Writer/HTML/Element/Link.php      |  7 +++-
 src/PhpWord/Writer/HTML/Element/ListItem.php  |  8 +++-
 src/PhpWord/Writer/HTML/Element/Text.php      | 14 ++++++-
 src/PhpWord/Writer/HTML/Element/Title.php     |  7 +++-
 src/PhpWord/Writer/HTML/Part/AbstractPart.php | 11 ++++++
 src/PhpWord/Writer/HTML/Part/Head.php         | 19 +++++-----
 src/PhpWord/Writer/HTML/Style/Paragraph.php   | 37 ++++++++++++++++++-
 12 files changed, 114 insertions(+), 35 deletions(-)

diff --git a/README.md b/README.md
index 1d7a4802..3c2bd5c1 100644
--- a/README.md
+++ b/README.md
@@ -24,7 +24,7 @@ Read more about PHPWord:
 
 ## Features
 
-With PHPWord, you can create DOCX, ODT, or RTF documents dynamically using your PHP 5.3+ scripts. Below are some of the things that you can do with PHPWord library:
+With PHPWord, you can create OOXML, ODF, or RTF documents dynamically using your PHP 5.3.3+ scripts. Below are some of the things that you can do with PHPWord library:
 
 - Set document properties, e.g. title, subject, and creator.
 - Create document sections with different settings, e.g. portrait/landscape, page size, and page numbering
@@ -52,12 +52,14 @@ With PHPWord, you can create DOCX, ODT, or RTF documents dynamically using your
 
 PHPWord requires the following:
 
-- PHP 5.3+
+- PHP 5.3.3+
 - [XML Parser extension](http://www.php.net/manual/en/xml.installation.php)
+- [Zend\Escaper component](http://framework.zend.com/manual/current/en/modules/zend.escaper.introduction.html)
+- Zend\Stdlib component
 - [Zend\Validator component](http://framework.zend.com/manual/current/en/modules/zend.validator.html)
-- [Zip extension](http://php.net/manual/en/book.zip.php) (optional, used to write DOCX and ODT)
+- [Zip extension](http://php.net/manual/en/book.zip.php) (optional, used to write OOXML and ODF)
 - [GD extension](http://php.net/manual/en/book.image.php) (optional, used to add images)
-- [XMLWriter extension](http://php.net/manual/en/book.xmlwriter.php) (optional, used to write DOCX and ODT)
+- [XMLWriter extension](http://php.net/manual/en/book.xmlwriter.php) (optional, used to write OOXML and ODF)
 - [XSL extension](http://php.net/manual/en/book.xsl.php) (optional, used to apply XSL style sheet to template )
 - [dompdf library](https://github.com/dompdf/dompdf) (optional, used to write PDF)
 
@@ -149,7 +151,6 @@ $objWriter->save('helloWorld.html');
 /* Note: we skip RTF, because it's not XML-based and requires a different example. */
 /* Note: we skip PDF, because "HTML-to-PDF" approach is used to create PDF documents. */
 ```
-:warning: Escape any string you pass to HTML document, otherwise it may get broken.
 
 More examples are provided in the [samples folder](samples/). You can also read the [Developers' Documentation](http://phpword.readthedocs.org/) and the [API Documentation](http://phpoffice.github.io/PHPWord/docs/master/) for more detail.
 
diff --git a/composer.json b/composer.json
index 48d39ada..e9399914 100644
--- a/composer.json
+++ b/composer.json
@@ -1,10 +1,10 @@
 {
     "name": "phpoffice/phpword",
-    "description": "PHPWord - A pure PHP library for reading and writing word processing documents (DOCX, ODT, RTF, HTML, PDF)",
+    "description": "PHPWord - A pure PHP library for reading and writing word processing documents (OOXML, ODF, RTF, HTML, PDF)",
     "keywords": [
-        "PHP", "PhpOffice", "office", "PhpWord", "word", "template", "template processor", "reader", "writer",
+        "PHP", "PHPOffice", "office", "PHPWord", "word", "template", "template processor", "reader", "writer",
         "docx", "OOXML", "OpenXML", "Office Open XML", "ISO IEC 29500", "WordprocessingML",
-        "RTF", "Rich Text Format", "doc", "odt", "OpenDocument", "PDF", "HTML"
+        "RTF", "Rich Text Format", "doc", "odt", "ODF", "OpenDocument", "PDF", "HTML"
     ],
     "homepage": "http://phpoffice.github.io",
     "type": "library",
@@ -34,8 +34,9 @@
     "require": {
         "php": ">=5.3.3",
         "ext-xml": "*",
-        "zendframework/zend-stdlib": "~2.5",
-        "zendframework/zend-validator": "2.5.*",
+        "zendframework/zend-escaper": "2.4.*",
+        "zendframework/zend-stdlib": "2.4.*",
+        "zendframework/zend-validator": "2.4.*",
         "phpoffice/common": "0.2.*"
     },
     "require-dev": {
@@ -46,15 +47,12 @@
         "phploc/phploc": "2.*",
         "dompdf/dompdf":"0.6.*",
         "tecnickcom/tcpdf": "6.*",
-        "mpdf/mpdf": "5.*",
-        "zendframework/zend-stdlib": "~2.5",
-        "zendframework/zend-validator": "2.5.*",
-        "phpoffice/common": "0.2.*"
+        "mpdf/mpdf": "5.*"
     },
     "suggest": {
-        "ext-zip": "Allows writing DOCX and ODT",
+        "ext-zip": "Allows writing OOXML and ODF",
         "ext-gd2": "Allows adding images",
-        "ext-xmlwriter": "Allows writing DOCX and ODT",
+        "ext-xmlwriter": "Allows writing OOXML and ODF",
         "ext-xsl": "Allows applying XSL style sheet to main document part of OOXML template",
         "dompdf/dompdf": "Allows writing PDF"
     },
diff --git a/docs/installing.rst b/docs/installing.rst
index dc1f40f3..9593484a 100644
--- a/docs/installing.rst
+++ b/docs/installing.rst
@@ -8,8 +8,10 @@ Requirements
 
 Mandatory:
 
-- PHP 5.3+
+- PHP 5.3.3+
 - `XML Parser <http://www.php.net/manual/en/xml.installation.php>`__ extension
+- `Zend\\Escaper <http://framework.zend.com/manual/current/en/modules/zend.escaper.introduction.html>`__ component
+- Zend\\Stdlib component
 - `Zend\\Validator <http://framework.zend.com/manual/current/en/modules/zend.validator.html>`__ component
 
 Optional:
diff --git a/docs/intro.rst b/docs/intro.rst
index 8e3d2d05..0ef27c9f 100644
--- a/docs/intro.rst
+++ b/docs/intro.rst
@@ -63,7 +63,7 @@ Writers
 ~~~~~~~
 
 +---------------------------+----------------------+--------+-------+-------+--------+-------+
-| Features                  |                      | DOCX   | ODT   | RTF   | HTML   | PDF   |
+| Features                  |                      | OOXML  | ODF   | RTF   | HTML   | PDF   |
 +===========================+======================+========+=======+=======+========+=======+
 | **Document Properties**   | Standard             | ✓      | ✓     | ✓     | ✓      | ✓     |
 +---------------------------+----------------------+--------+-------+-------+--------+-------+
@@ -122,7 +122,7 @@ Readers
 ~~~~~~~
 
 +---------------------------+----------------------+--------+-------+-------+-------+-------+
-| Features                  |                      | DOCX   | DOC   | ODT   | RTF   | HTML  |
+| Features                  |                      | OOXML  | DOC   | ODF   | RTF   | HTML  |
 +===========================+======================+========+=======+=======+=======+=======+
 | **Document Properties**   | Standard             | ✓      |       |       |       |       |
 +---------------------------+----------------------+--------+-------+-------+-------+-------+
diff --git a/src/PhpWord/Writer/HTML/Element/AbstractElement.php b/src/PhpWord/Writer/HTML/Element/AbstractElement.php
index 13681423..9eae024c 100644
--- a/src/PhpWord/Writer/HTML/Element/AbstractElement.php
+++ b/src/PhpWord/Writer/HTML/Element/AbstractElement.php
@@ -19,6 +19,7 @@ namespace PhpOffice\PhpWord\Writer\HTML\Element;
 
 use PhpOffice\PhpWord\Element\AbstractElement as Element;
 use PhpOffice\PhpWord\Writer\AbstractWriter;
+use Zend\Escaper\Escaper;
 
 /**
  * Abstract HTML element writer
@@ -48,6 +49,11 @@ abstract class AbstractElement
      */
     protected $withoutP = false;
 
+    /**
+     * @var \Zend\Escaper\Escaper
+     */
+    protected $escaper;
+
     /**
      * Write element
      */
@@ -65,6 +71,7 @@ abstract class AbstractElement
         $this->parentWriter = $parentWriter;
         $this->element = $element;
         $this->withoutP = $withoutP;
+        $this->escaper = new Escaper();
     }
 
     /**
diff --git a/src/PhpWord/Writer/HTML/Element/Link.php b/src/PhpWord/Writer/HTML/Element/Link.php
index 50c4e6af..ec0e1746 100644
--- a/src/PhpWord/Writer/HTML/Element/Link.php
+++ b/src/PhpWord/Writer/HTML/Element/Link.php
@@ -16,6 +16,7 @@
  */
 
 namespace PhpOffice\PhpWord\Writer\HTML\Element;
+use PhpOffice\PhpWord\Settings;
 
 /**
  * Link element HTML writer
@@ -37,7 +38,11 @@ class Link extends Text
 
         $content = '';
         $content .= $this->writeOpening();
-        $content .= "<a href=\"{$this->element->getSource()}\">{$this->element->getText()}</a>";
+        if (Settings::isOutputEscapingEnabled()) {
+            $content .= "<a href=\"{$this->escaper->escapeHtmlAttr($this->element->getSource())}\">{$this->escaper->escapeHtml($this->element->getText())}</a>";
+        } else {
+            $content .= "<a href=\"{$this->element->getSource()}\">{$this->element->getText()}</a>";
+        }
         $content .= $this->writeClosing();
 
         return $content;
diff --git a/src/PhpWord/Writer/HTML/Element/ListItem.php b/src/PhpWord/Writer/HTML/Element/ListItem.php
index a046a0d4..d1d0ae9b 100644
--- a/src/PhpWord/Writer/HTML/Element/ListItem.php
+++ b/src/PhpWord/Writer/HTML/Element/ListItem.php
@@ -16,6 +16,7 @@
  */
 
 namespace PhpOffice\PhpWord\Writer\HTML\Element;
+use PhpOffice\PhpWord\Settings;
 
 /**
  * ListItem element HTML writer
@@ -35,8 +36,11 @@ class ListItem extends AbstractElement
             return '';
         }
 
-        $text = $this->element->getTextObject()->getText();
-        $content = '<p>' . $text . '</p>' . PHP_EOL;
+        if (Settings::isOutputEscapingEnabled()) {
+            $content = '<p>' . $this->escaper->escapeHtml($this->element->getTextObject()->getText()) . '</p>' . PHP_EOL;
+        } else {
+            $content = '<p>' . $this->element->getTextObject()->getText() . '</p>' . PHP_EOL;
+        }
 
         return $content;
     }
diff --git a/src/PhpWord/Writer/HTML/Element/Text.php b/src/PhpWord/Writer/HTML/Element/Text.php
index f57e9c21..66455c1f 100644
--- a/src/PhpWord/Writer/HTML/Element/Text.php
+++ b/src/PhpWord/Writer/HTML/Element/Text.php
@@ -17,6 +17,7 @@
 
 namespace PhpOffice\PhpWord\Writer\HTML\Element;
 
+use PhpOffice\PhpWord\Settings;
 use PhpOffice\PhpWord\Style\Font;
 use PhpOffice\PhpWord\Style\Paragraph;
 use PhpOffice\PhpWord\Writer\HTML\Style\Font as FontStyleWriter;
@@ -72,7 +73,11 @@ class Text extends AbstractElement
         $content .= $this->writeOpening();
         $content .= $this->openingText;
         $content .= $this->openingTags;
-        $content .= $element->getText();
+        if (Settings::isOutputEscapingEnabled()) {
+            $content .= $this->escaper->escapeHtml($element->getText());
+        } else {
+            $content .= $element->getText();
+        }
         $content .= $this->closingTags;
         $content .= $this->closingText;
         $content .= $this->writeClosing();
@@ -130,7 +135,12 @@ class Text extends AbstractElement
     {
         $content = '';
         if (!$this->withoutP) {
-            $content .= $this->closingText;
+            if (Settings::isOutputEscapingEnabled()) {
+                $content .= $this->escaper->escapeHtml($this->closingText);
+            } else {
+                $content .= $this->closingText;
+            }
+
             $content .= "</p>" . PHP_EOL;
         }
 
diff --git a/src/PhpWord/Writer/HTML/Element/Title.php b/src/PhpWord/Writer/HTML/Element/Title.php
index 8018178c..b4674612 100644
--- a/src/PhpWord/Writer/HTML/Element/Title.php
+++ b/src/PhpWord/Writer/HTML/Element/Title.php
@@ -16,6 +16,7 @@
  */
 
 namespace PhpOffice\PhpWord\Writer\HTML\Element;
+use PhpOffice\PhpWord\Settings;
 
 /**
  * TextRun element HTML writer
@@ -36,7 +37,11 @@ class Title extends AbstractElement
         }
 
         $tag = 'h' . $this->element->getDepth();
-        $text = $this->element->getText();
+        if (Settings::isOutputEscapingEnabled()) {
+            $text = $this->escaper->escapeHtml($this->element->getText());
+        } else {
+            $text = $this->element->getText();
+        }
         $content = "<{$tag}>{$text}</{$tag}>" . PHP_EOL;
 
         return $content;
diff --git a/src/PhpWord/Writer/HTML/Part/AbstractPart.php b/src/PhpWord/Writer/HTML/Part/AbstractPart.php
index cf4da1b0..4c5f66e9 100644
--- a/src/PhpWord/Writer/HTML/Part/AbstractPart.php
+++ b/src/PhpWord/Writer/HTML/Part/AbstractPart.php
@@ -19,6 +19,7 @@ namespace PhpOffice\PhpWord\Writer\HTML\Part;
 
 use PhpOffice\PhpWord\Exception\Exception;
 use PhpOffice\PhpWord\Writer\AbstractWriter;
+use Zend\Escaper\Escaper;
 
 /**
  * Abstract HTML part writer
@@ -34,6 +35,16 @@ abstract class AbstractPart
      */
     private $parentWriter;
 
+    /**
+     * @var \Zend\Escaper\Escaper
+     */
+    protected $escaper;
+    
+    public function __construct()
+    {
+        $this->escaper = new Escaper();
+    }
+    
     /**
      * Write part
      *
diff --git a/src/PhpWord/Writer/HTML/Part/Head.php b/src/PhpWord/Writer/HTML/Part/Head.php
index 438c7ad7..c9f947cf 100644
--- a/src/PhpWord/Writer/HTML/Part/Head.php
+++ b/src/PhpWord/Writer/HTML/Part/Head.php
@@ -41,14 +41,14 @@ class Head extends AbstractPart
     {
         $docProps = $this->getParentWriter()->getPhpWord()->getDocInfo();
         $propertiesMapping = array(
-            'creator' => 'author',
-            'title' => '',
+            'creator'     => 'author',
+            'title'       => '',
             'description' => '',
-            'subject' => '',
-            'keywords' => '',
-            'category' => '',
-            'company' => '',
-            'manager' => ''
+            'subject'     => '',
+            'keywords'    => '',
+            'category'    => '',
+            'company'     => '',
+            'manager'     => ''
         );
         $title = $docProps->getTitle();
         $title = ($title != '') ? $title : 'PHPWord';
@@ -62,8 +62,9 @@ class Head extends AbstractPart
             $value = ($value == '') ? $key : $value;
             $method = "get" . $key;
             if ($docProps->$method() != '') {
-                $content .= '<meta name="' . $value . '" content="' .
-                    $docProps->$method() . '" />' . PHP_EOL;
+                $content .= '<meta name="' . $value . '"'
+                          . ' content="' . (Settings::isOutputEscapingEnabled() ? $this->escaper->escapeHtmlAttr($docProps->$method()) : $docProps->$method()) . '"'
+                          .' />' . PHP_EOL;
             }
         }
         $content .= $this->writeStyles();
diff --git a/src/PhpWord/Writer/HTML/Style/Paragraph.php b/src/PhpWord/Writer/HTML/Style/Paragraph.php
index 52708dcb..78a6f4bb 100644
--- a/src/PhpWord/Writer/HTML/Style/Paragraph.php
+++ b/src/PhpWord/Writer/HTML/Style/Paragraph.php
@@ -17,6 +17,8 @@
 
 namespace PhpOffice\PhpWord\Writer\HTML\Style;
 
+use PhpOffice\PhpWord\SimpleType\Jc;
+
 /**
  * Paragraph style HTML writer
  *
@@ -39,7 +41,40 @@ class Paragraph extends AbstractStyle
 
         // Alignment
         if ('' !== $style->getAlignment()) {
-            $css['text-align'] = $style->getAlignment(); // todo: convert OpenXml to Html values
+            $textAlign = '';
+
+            switch ($style->getAlignment()) {
+                case Jc::START:
+                case Jc::NUM_TAB:
+                case Jc::LEFT:
+                    $textAlign = 'left';
+                    break;
+
+                case Jc::CENTER:
+                    $textAlign = 'center';
+                    break;
+
+                case Jc::END:
+                case Jc::MEDIUM_KASHIDA:
+                case Jc::HIGH_KASHIDA:
+                case Jc::LOW_KASHIDA:
+                case Jc::RIGHT:
+                    $textAlign = 'right';
+                    break;
+
+                case Jc::BOTH:
+                case Jc::DISTRIBUTE:
+                case Jc::THAI_DISTRIBUTE:
+                case Jc::JUSTIFY:
+                    $textAlign = 'justify';
+                    break;
+
+                default:
+                    $textAlign = 'left';
+                    break;
+            }
+
+            $css['text-align'] = $textAlign;
         }
 
         // Spacing