Reader: Read section settings and font/paragraph styles

Classes/PHPWord/Reader/Word2007.php

@@ -35,7 +35,8 @@ if (!defined('PHPWORD_BASE_PATH')) {
 /**
  * PHPWord_Reader_Word2007
  */
-class PHPWord_Reader_Word2007 extends PHPWord_Reader_Abstract implements PHPWord_Reader_IReader
+class PHPWord_Reader_Word2007 extends PHPWord_Reader_Abstract implements
+    PHPWord_Reader_IReader
 {
 
     /**
@@ -54,7 +55,8 @@ class PHPWord_Reader_Word2007 extends PHPWord_Reader_Abstract implements PHPWord
     {
         // Check if file exists
         if (!file_exists($pFilename)) {
-            throw new PHPWord_Exception("Could not open " . $pFilename . " for reading! File does not exist.");
+            throw new PHPWord_Exception("Could not open " . $pFilename .
+                " for reading! File does not exist.");
         }
 
         $return = false;
@@ -86,9 +88,13 @@ class PHPWord_Reader_Word2007 extends PHPWord_Reader_Abstract implements PHPWord
      *
      * @param   ZipArchive  $archive
      * @param   string      $fileName
+     * @param   bool        $removeNamespace
      */
-    public function getFromZipArchive($archive, $fileName = '')
+    public function getFromZipArchive(
-    {
+        $archive,
+        $fileName = '',
+        $removeNamespace = false
+    ) {
         // Root-relative paths
         if (strpos($fileName, '//') !== false)
         {
@@ -103,9 +109,9 @@ class PHPWord_Reader_Word2007 extends PHPWord_Reader_Abstract implements PHPWord
             $contents = $archive->getFromName(substr($fileName, 1));
         }
 
-        // Stupid hack for namespace
+        // Remove namespaces from elements and attributes name
-        if ($contents != '' && $fileName = 'word/document.xml') {
+        if ($removeNamespace) {
-            $contents = preg_replace('~(</?)w:~is', '$1', $contents);
+            $contents = preg_replace('~(</?|\s)w:~is', '$1', $contents);
         }
 
         return $contents;
@@ -122,7 +128,8 @@ class PHPWord_Reader_Word2007 extends PHPWord_Reader_Abstract implements PHPWord
     {
         // Check if file exists
         if (!file_exists($pFilename)) {
-            throw new PHPWord_Exception("Could not open " . $pFilename . " for reading! File does not exist.");
+            throw new PHPWord_Exception("Could not open " . $pFilename .
+                " for reading! File does not exist.");
         }
 
         // Initialisations
@@ -130,17 +137,17 @@ class PHPWord_Reader_Word2007 extends PHPWord_Reader_Abstract implements PHPWord
         $zip = new ZipArchive;
         $zip->open($pFilename);
 
-        // Read relationships
+        // Read properties and documents
         $rels = simplexml_load_string($this->getFromZipArchive($zip, "_rels/.rels"));
         foreach ($rels->Relationship as $rel) {
             switch ($rel["Type"]) {
                 // Core properties
-                case "http://schemas.openxmlformats.org/package/2006//relationships/metadata/core-properties":
+                case "http://schemas.openxmlformats.org/package/2006/relationships/metadata/core-properties":
                     $xmlCore = simplexml_load_string($this->getFromZipArchive($zip, "{$rel['Target']}"));
                     if (is_object($xmlCore)) {
                         $xmlCore->registerXPathNamespace("dc", "http://purl.org/dc/elements/1.1/");
                         $xmlCore->registerXPathNamespace("dcterms", "http://purl.org/dc/terms/");
-                        $xmlCore->registerXPathNamespace("cp", "http://schemas.openxmlformats.org/package/2006//metadata/core-properties");
+                        $xmlCore->registerXPathNamespace("cp", "http://schemas.openxmlformats.org/package/2006/metadata/core-properties");
                         $docProps = $word->getProperties();
                         $docProps->setCreator((string) self::array_item($xmlCore->xpath("dc:creator")));
                         $docProps->setLastModifiedBy((string) self::array_item($xmlCore->xpath("cp:lastModifiedBy")));
@@ -188,32 +195,75 @@ class PHPWord_Reader_Word2007 extends PHPWord_Reader_Abstract implements PHPWord
                     $dir = dirname($rel["Target"]);
                     $archive = "$dir/_rels/" . basename($rel["Target"]) . ".rels";
                     $relsDoc = simplexml_load_string($this->getFromZipArchive($zip, $archive));
-                    $relsDoc->registerXPathNamespace("rel", "http://schemas.openxmlformats.org/package/2006//relationships");
+                    $relsDoc->registerXPathNamespace("rel", "http://schemas.openxmlformats.org/package/2006/relationships");
                     $xpath = self::array_item($relsDoc->xpath("rel:Relationship[@Type='" .
                         "http://schemas.openxmlformats.org/officeDocument/2006/relationships/styles']"));
-                    $xmlDoc = simplexml_load_string($this->getFromZipArchive($zip, "{$rel['Target']}"));
+                    $xmlDoc = simplexml_load_string($this->getFromZipArchive($zip, "{$rel['Target']}", true));
-                    if ($xmlDoc->body) {
+                    if (is_object($xmlDoc)) {
                         $section = $word->createSection();
-                        foreach ($xmlDoc->body->children() as $element) {
+
-                            switch ($element->getName()) {
+                        foreach ($xmlDoc->body->children() as $elm) {
-                                case 'p':
+                            $elmName = $elm->getName();
-                                    if ($element->pPr->sectPr) {
+                            if ($elmName == 'p') { // Paragraph/section
-                                        $section = $word->createSection();
+                                // Create new section if section section found
-                                        continue;
+                                if ($elm->pPr->sectPr) {
-                                    }
+                                    $section->setSettings($this->loadSectionSettings($elm->pPr));
-                                    if ($element->r) {
+                                    $section = $word->createSection();
-                                        if (count($element->r) == 1) {
+                                    continue;
-                                            $section->addText($element->r->t);
+                                }
-                                        } else {
+                                // Has w:r? It's either text or textrun
-                                            $textRun = $section->createTextRun();
+                                if ($elm->r) {
-                                            foreach ($element->r as $r) {
+                                    // w:r = 1? It's a plain paragraph
-                                                $textRun->addText($r->t);
+                                    if (count($elm->r) == 1) {
-                                            }
+                                        $section->addText($elm->r->t,
-                                        }
+                                            $this->loadFontStyle($elm->r));
+                                    // w:r more than 1? It's a textrun
                                     } else {
-                                        $section->addTextBreak();
+                                        $textRun = $section->createTextRun();
+                                        foreach ($elm->r as $r) {
+                                            $textRun->addText($r->t,
+                                                $this->loadFontStyle($r));
+                                        }
                                     }
-                                    break;
+                                // No, it's a textbreak
+                                } else {
+                                    $section->addTextBreak();
+                                }
+                            } elseif ($elmName == 'sectPr') {
+                                // Last section setting
+                                $section->setSettings($this->loadSectionSettings($xmlDoc->body));
+                            }
+                        }
+                    }
+                    break;
+            }
+        }
+
+        //  Read styles
+        $docRels = simplexml_load_string($this->getFromZipArchive($zip, "word/_rels/document.xml.rels"));
+        foreach ($docRels->Relationship as $rel) {
+            switch ($rel["Type"]) {
+                case "http://schemas.openxmlformats.org/officeDocument/2006/relationships/styles":
+                    $xmlStyle = simplexml_load_string($this->getFromZipArchive($zip, "word/{$rel['Target']}", true));
+                    if (is_object($xmlStyle)) {
+                        foreach ($xmlStyle->children() as $elm) {
+                            if ($elm->getName() != 'style') {
+                                continue;
+                            }
+                            unset($pStyle);
+                            unset($fStyle);
+                            $hasParagraphStyle = $elm->pPr && ($elm->pPr != '');
+                            $hasFontStyle = $elm->rPr && ($elm->rPr != '');
+                            $styleName = (string)$elm->name['val'];
+                            if ($hasParagraphStyle) {
+                                $pStyle = $this->loadParagraphStyle($elm);
+                                if (!$hasFontStyle) {
+                                    $word->addParagraphStyle($styleName, $pStyle);
+                                }
+                            }
+                            if ($hasFontStyle) {
+                                $fStyle = $this->loadFontStyle($elm);
+                                $word->addFontStyle($styleName, $fStyle, $pStyle);
                             }
                         }
                     }
@@ -225,6 +275,181 @@ class PHPWord_Reader_Word2007 extends PHPWord_Reader_Abstract implements PHPWord
         return $word;
     }
 
+    /**
+     * Load section settings from SimpleXMLElement
+     *
+     * @param   SimpleXMLElement    $elm
+     * @return  array|string|null
+     *
+     * @todo    Implement gutter
+     */
+    private function loadSectionSettings($elm)
+    {
+        if ($xml = $elm->sectPr) {
+            $setting = array();
+            if ($xml->type) {
+                $setting['breakType'] = (string)$xml->type['val'];
+            }
+            if ($xml->pgSz) {
+                if (isset($xml->pgSz['w'])) {
+                    $setting['pageSizeW'] = (int)$xml->pgSz['w'];
+                }
+                if (isset($xml->pgSz['h'])) {
+                    $setting['pageSizeH'] = (int)$xml->pgSz['h'];
+                }
+                if (isset($xml->pgSz['orient'])) {
+                    $setting['orientation'] = (string)$xml->pgSz['orient'];
+                }
+            }
+            if ($xml->pgMar) {
+                if (isset($xml->pgMar['top'])) {
+                    $setting['topMargin'] = (int)$xml->pgMar['top'];
+                }
+                if (isset($xml->pgMar['left'])) {
+                    $setting['leftMargin'] = (int)$xml->pgMar['left'];
+                }
+                if (isset($xml->pgMar['bottom'])) {
+                    $setting['bottomMargin'] = (int)$xml->pgMar['bottom'];
+                }
+                if (isset($xml->pgMar['right'])) {
+                    $setting['rightMargin'] = (int)$xml->pgMar['right'];
+                }
+                if (isset($xml->pgMar['header'])) {
+                    $setting['headerHeight'] = (int)$xml->pgMar['header'];
+                }
+                if (isset($xml->pgMar['footer'])) {
+                    $setting['footerHeight'] = (int)$xml->pgMar['footer'];
+                }
+                if (isset($xml->pgMar['gutter'])) {
+                    // $setting['gutter'] = (int)$xml->pgMar['gutter'];
+                }
+            }
+            if ($xml->cols) {
+                if (isset($xml->cols['num'])) {
+                    $setting['colsNum'] = (int)$xml->cols['num'];
+                }
+                if (isset($xml->cols['space'])) {
+                    $setting['colsSpace'] = (int)$xml->cols['space'];
+                }
+            }
+            return $setting;
+        } else {
+            return null;
+        }
+    }
+
+    /**
+     * Load paragraph style from SimpleXMLElement
+     *
+     * @param   SimpleXMLElement    $elm
+     * @return  array|string|null
+     */
+    private function loadParagraphStyle($elm)
+    {
+        if ($xml = $elm->pPr) {
+            if ($xml->pStyle) {
+                return (string)$xml->pStyle['val'];
+            }
+            $style = array();
+            if ($xml->jc) {
+                $style['align'] = (string)$xml->jc['val'];
+            }
+            if ($xml->ind) {
+                if (isset($xml->ind->left)) {
+                    $style['indent'] = (int)$xml->ind->left;
+                }
+                if (isset($xml->ind->hanging)) {
+                    $style['hanging'] = (int)$xml->ind->hanging;
+                }
+                if (isset($xml->ind->line)) {
+                    $style['spacing'] = (int)$xml->ind->line;
+                }
+            }
+            if ($xml->spacing) {
+                if (isset($xml->spacing['after'])) {
+                    $style['spaceAfter'] = (int)$xml->spacing['after'];
+                }
+                if (isset($xml->spacing['before'])) {
+                    $style['spaceBefore'] = (int)$xml->spacing['before'];
+                }
+                if (isset($xml->spacing['line'])) {
+                    $style['spacing'] = (int)$xml->spacing['line'];
+                }
+            }
+            if ($xml->basedOn) {
+                $style['basedOn'] = (string)$xml->basedOn['val'];
+            }
+            if ($xml->next) {
+                $style['next'] = (string)$xml->next['val'];
+            }
+            if ($xml->widowControl) {
+                $style['widowControl'] = false;
+            }
+            if ($xml->keepNext) {
+                $style['keepNext'] = true;
+            }
+            if ($xml->keepLines) {
+                $style['keepLines'] = true;
+            }
+            if ($xml->pageBreakBefore) {
+                $style['pageBreakBefore'] = true;
+            }
+            return $style;
+        } else {
+            return null;
+        }
+    }
+
+    /**
+     * Load font style from SimpleXMLElement
+     *
+     * @param   SimpleXMLElement    $elm
+     * @return  array|string|null
+     */
+    private function loadFontStyle($elm)
+    {
+        if ($xml = $elm->rPr) {
+            if ($xml->rStyle) {
+                return (string)$xml->rStyle['val'];
+            }
+            $style = array();
+            if ($xml->rFonts) {
+                $style['name'] = (string)$xml->rFonts['ascii'];
+            }
+            if ($xml->sz) {
+                $style['size'] = (int)$xml->sz['val'] / 2;
+            }
+            if ($xml->color) {
+                $style['color'] = (string)$xml->color['val'];
+            }
+            if ($xml->b) {
+                $style['bold'] = true;
+            }
+            if ($xml->i) {
+                $style['italic'] = true;
+            }
+            if ($xml->u) {
+                $style['underline'] = (string)$xml->u['val'];
+            }
+            if ($xml->strike) {
+                $style['strikethrough'] = true;
+            }
+            if ($xml->highlight) {
+                $style['fgColor'] = (string)$xml->highlight['val'];
+            }
+            if ($xml->vertAlign) {
+                if ($xml->vertAlign['val'] == 'superscript') {
+                    $style['superScript'] = true;
+                } else {
+                    $style['subScript'] = true;
+                }
+            }
+            return $style;
+        } else {
+            return null;
+        }
+    }
+
     /**
      * Get array item
      *

Classes/PHPWord/Section.php

@@ -77,7 +77,16 @@ class PHPWord_Section
     {
         $this->_sectionCount = $sectionCount;
         $this->_settings = new PHPWord_Section_Settings();
+        $this->setSettings($settings);
+    }
 
+    /**
+     * Set Section Settings
+     *
+     * @param   array   $settings
+     */
+    public function setSettings($settings = null)
+    {
         if (!is_null($settings) && is_array($settings)) {
             foreach ($settings as $key => $value) {
                 if (substr($key, 0, 1) != '_') {

Classes/PHPWord/Shared/File.php

@@ -76,7 +76,7 @@ class PHPWord_Shared_File
 
         // Found something?
         if ($returnValue == '' || is_null($returnValue)) {
-            $pathArray = split('/', $pFilename);
+            $pathArray = explode('/', $pFilename);
             while (in_array('..', $pathArray) && $pathArray[0] != '..') {
                 for ($i = 0; $i < count($pathArray); ++$i) {
                     if ($pathArray[$i] == '..' && $i > 0) {

Classes/PHPWord/Style/Paragraph.php

@@ -506,4 +506,4 @@ class PHPWord_Style_Paragraph
     {
         return $this->lineHeight;
     }
-}
+}

Classes/PHPWord/Writer/Word2007/Base.php

@@ -128,8 +128,8 @@ class PHPWord_Writer_Word2007_Base extends PHPWord_Writer_Word2007_WriterPart
     protected function _writeParagraphStyle(
         PHPWord_Shared_XMLWriter $objWriter = null,
         PHPWord_Style_Paragraph $style,
-        $withoutPPR = false)
+        $withoutPPR = false
-    {
+    ) {
         $align = $style->getAlign();
         $spacing = $style->getSpacing();
         $spaceBefore = $style->getSpaceBefore();
@@ -926,4 +926,4 @@ class PHPWord_Writer_Word2007_Base extends PHPWord_Writer_Word2007_WriterPart
             $objWriter->endElement(); // w:p
         }
     }
-}
+}

changelog.txt

@@ -50,6 +50,7 @@ Changes in branch for release 0.7.1 :
 - Bugfix:   (ivanlanin)       GH-94             - General: PHPWord_Shared_Drawing::centimetersToPixels() conversion
 - Feature:  (ivanlanin)                         - Paragraph: setTabs() function
 - Feature:  (ivanlanin)       GH-99             - General: Basic support for TextRun on ODT and RTF
+- Feature:  (ivanlanin)                         - Reader: Initial effort for Word2007
 - QA:       (Progi1984)                         - UnitTests
 
 Changes in branch for release 0.7.0 :

samples/Sample_10_ReadWord2007.php

@@ -5,74 +5,29 @@ define('EOL', (PHP_SAPI == 'cli') ? PHP_EOL : '<br />');
 
 require_once '../Classes/PHPWord.php';
 
-$files = array(
+// Read contents
-    "Sample_01_SimpleText.docx",
+$sample = 'Sample_10_ReadWord2007';
-    "Sample_02_TabStops.docx",
+$source = "resources/{$sample}.docx";
-    "Sample_03_Sections.docx",
+$target = "results/{$sample}";
-    "Sample_04_Textrun.docx",
+echo '<p><strong>', date('H:i:s'), " Reading contents from `{$source}`</strong></p>";
-    "Sample_05_Multicolumn.docx",
+$PHPWord = PHPWord_IOFactory::load($source);
-    "Sample_06_Footnote.docx",
-    "Sample_07_TemplateCloneRow.docx",
-    "Sample_08_ParagraphPagination.docx",
-    "Sample_09_Tables.docx",
-);
 
-foreach ($files as $file) {
+// Rewrite contents
-    echo '<hr />';
+echo date('H:i:s') , " Write to Word2007 format" , EOL;
-    echo '<p><strong>', date('H:i:s'), " Load from {$file} with contents:</strong></p>";
+$objWriter = PHPWord_IOFactory::createWriter($PHPWord, 'Word2007');
-    unset($PHPWord);
+$objWriter->save("{$sample}.docx");
-    try {
+rename("{$sample}.docx", "{$target}.docx");
-        $PHPWord = PHPWord_IOFactory::load($file);
-    } catch (Exception $e) {
-        echo '<p style="color: red;">Caught exception: ',  $e->getMessage(), '</p>';
-        continue;
-    }
-    $sections = $PHPWord->getSections();
-    $countSections = count($sections);
-    $pSection = 0;
 
-    if ($countSections > 0) {
+echo date('H:i:s') , ' Write to OpenDocumentText format' , EOL;
-        foreach ($sections as $section) {
+$objWriter = PHPWord_IOFactory::createWriter($PHPWord, 'ODText');
-            $pSection++;
+$objWriter->save("{$sample}.odt");
-            echo "<p><strong>Section {$pSection}:</strong></p>";
+rename("{$sample}.odt", "{$target}.odt");
-            $elements = $section->getElements();
-            foreach ($elements as $element) {
-                if ($element instanceof PHPWord_Section_Text) {
-                    echo '<p>' . htmlspecialchars($element->getText()) . '</p>';
-                } elseif ($element instanceof PHPWord_Section_TextRun) {
-                    $subelements = $element->getElements();
-                    echo '<p>';
-                    if (count($subelements) > 0) {
-                        foreach ($subelements as $subelement) {
-                            if ($subelement instanceof PHPWord_Section_Text) {
-                                echo htmlspecialchars($subelement->getText());
-                            }
-                        }
-                    }
-                    echo '</p>';
-                } elseif ($element instanceof PHPWord_Section_Link) {
-                    echo '<p style="color: red;">Link not yet supported.</p>';
-                } elseif ($element instanceof PHPWord_Section_Title) {
-                    echo '<p style="color: red;">Title not yet supported.</p>';
-                } elseif ($element instanceof PHPWord_Section_TextBreak) {
-                    echo '<br />';
-                } elseif ($element instanceof PHPWord_Section_PageBreak) {
-                    echo '<p style="color: red;">Page break not yet supported.</p>';
-                } elseif ($element instanceof PHPWord_Section_Table) {
-                    echo '<p style="color: red;">Table not yet supported.</p>';
-                } elseif ($element instanceof PHPWord_Section_ListItem) {
-                    echo '<p style="color: red;">List item not yet supported.</p>';
-                } elseif ($element instanceof PHPWord_Section_Image ||
-                    $element instanceof PHPWord_Section_MemoryImage
-                ) {
-                    echo '<p style="color: red;">Image not yet supported.</p>';
-                } elseif ($element instanceof PHPWord_TOC) {
-                    echo '<p style="color: red;">TOC not yet supported.</p>';
-                } elseif($element instanceof PHPWord_Section_Footnote) {
-                    echo '<p style="color: red;">Footnote not yet supported.</p>';
-                }
-            }
-        }
-    }
-}
 
+echo date('H:i:s') , ' Write to RTF format' , EOL;
+$objWriter = PHPWord_IOFactory::createWriter($PHPWord, 'RTF');
+$objWriter->save("{$sample}.rtf");
+rename("{$sample}.rtf", "{$target}.rtf");
+
+// Echo memory peak usage
+echo date('H:i:s') , " Peak memory usage: " , (memory_get_peak_usage(true) / 1024 / 1024) , " MB" , EOL;
+echo date('H:i:s') , " Done writing file" , EOL;