Merge pull request #4003 from oleibman/issue3999

Improvements to Xml Reader

Author: oleibman

CHANGELOG.md

@@ -22,7 +22,7 @@ and this project adheres to [Semantic Versioning](https://semver.org).
 
 ### Deprecated
 
-- Nothing
+- Reader/Xml trySimpleXMLLoadString should not have had public visibility, and will be removed.
 
 ### Removed
 
@@ -42,6 +42,9 @@ and this project adheres to [Semantic Versioning](https://semver.org).
 - Invalid Builtin Defined Name in Xls Reader [Issue #3935](https://github.com/PHPOffice/PhpSpreadsheet/issues/3935) [PR #3942](https://github.com/PHPOffice/PhpSpreadsheet/pull/3942)
 - Hidden Rows and Columns Tcpdf/Mpdf [PR #3945](https://github.com/PHPOffice/PhpSpreadsheet/pull/3945)
 - Protect Sheet But Allow Sort [Issue #3951](https://github.com/PHPOffice/PhpSpreadsheet/issues/3951) [PR #3956](https://github.com/PHPOffice/PhpSpreadsheet/pull/3956)
+- Default Value for Conditional::$text [PR #3946](https://github.com/PHPOffice/PhpSpreadsheet/pull/3946)
+- Table Filter Buttons [Issue #3988](https://github.com/PHPOffice/PhpSpreadsheet/issues/3988) [PR #3992](https://github.com/PHPOffice/PhpSpreadsheet/pull/3992)
+- Improvements to Xml Reader [Issue #3999](https://github.com/PHPOffice/PhpSpreadsheet/issues/3999) [Issue #4000](https://github.com/PHPOffice/PhpSpreadsheet/issues/4000) [Issue #4002](https://github.com/PHPOffice/PhpSpreadsheet/issues/4002) [PR #4003](https://github.com/PHPOffice/PhpSpreadsheet/pull/4003)
 
 ## 2.0.0 - 2024-01-04
 

src/PhpSpreadsheet/Reader/Xlsx/SheetViews.php

@@ -70,6 +70,20 @@ private function zoomScale(): void
 
             $this->worksheet->getSheetView()->setZoomScaleNormal($zoomScaleNormal);
         }
+
+        if (isset($this->sheetViewAttributes->zoomScalePageLayoutView)) {
+            $zoomScaleNormal = (int) ($this->sheetViewAttributes->zoomScalePageLayoutView);
+            if ($zoomScaleNormal > 0) {
+                $this->worksheet->getSheetView()->setZoomScalePageLayoutView($zoomScaleNormal);
+            }
+        }
+
+        if (isset($this->sheetViewAttributes->zoomScaleSheetLayoutView)) {
+            $zoomScaleNormal = (int) ($this->sheetViewAttributes->zoomScaleSheetLayoutView);
+            if ($zoomScaleNormal > 0) {
+                $this->worksheet->getSheetView()->setZoomScaleSheetLayoutView($zoomScaleNormal);
+            }
+        }
     }
 
     private function view(): void

src/PhpSpreadsheet/Reader/Xml.php

@@ -19,8 +19,10 @@
 use PhpOffice\PhpSpreadsheet\Shared\File;
 use PhpOffice\PhpSpreadsheet\Shared\StringHelper;
 use PhpOffice\PhpSpreadsheet\Spreadsheet;
+use PhpOffice\PhpSpreadsheet\Worksheet\SheetView;
 use PhpOffice\PhpSpreadsheet\Worksheet\Worksheet;
 use SimpleXMLElement;
+use Throwable;
 
 /**
  * Reader for SpreadsheetML, the XML schema for Microsoft Office Excel 2003.
@@ -45,6 +47,8 @@ public function __construct()
 
     private string $fileContents = '';
 
+    private string $xmlFailMessage = '';
+
     public static function xmlMappings(): array
     {
         return array_merge(
@@ -106,17 +110,44 @@ public function canRead(string $filename): bool
      * Check if the file is a valid SimpleXML.
      *
      * @return false|SimpleXMLElement
+     *
+     * @deprecated 2.0.1 Should never have had public visibility
+     *
+     * @codeCoverageIgnore
      */
-    public function trySimpleXMLLoadString(string $filename): SimpleXMLElement|bool
+    public function trySimpleXMLLoadString(string $filename, string $fileOrString = 'file'): SimpleXMLElement|bool
+    {
+        return $this->trySimpleXMLLoadStringPrivate($filename, $fileOrString);
+    }
+
+    /** @return false|SimpleXMLElement */
+    private function trySimpleXMLLoadStringPrivate(string $filename, string $fileOrString = 'file'): SimpleXMLElement|bool
     {
+        $this->xmlFailMessage = "Cannot load invalid XML $fileOrString: " . $filename;
+        $xml = false;
+
         try {
-            $xml = simplexml_load_string(
-                $this->getSecurityScannerOrThrow()->scan($this->fileContents ?: file_get_contents($filename)),
-                'SimpleXMLElement',
-                Settings::getLibXmlLoaderOptions()
-            );
-        } catch (\Exception $e) {
-            throw new Exception('Cannot load invalid XML file: ' . $filename, 0, $e);
+            $data = $this->fileContents;
+            $continue = true;
+            if ($data === '' && $fileOrString === 'file') {
+                if ($filename === '') {
+                    $this->xmlFailMessage = 'Cannot load empty path';
+                    $continue = false;
+                } else {
+                    $datax = @file_get_contents($filename);
+                    $data = $datax ?: '';
+                    $continue = $datax !== false;
+                }
+            }
+            if ($continue) {
+                $xml = @simplexml_load_string(
+                    $this->getSecurityScannerOrThrow()->scan($data),
+                    'SimpleXMLElement',
+                    Settings::getLibXmlLoaderOptions()
+                );
+            }
+        } catch (Throwable $e) {
+            throw new Exception($this->xmlFailMessage, 0, $e);
         }
         $this->fileContents = '';
 
@@ -135,7 +166,7 @@ public function listWorksheetNames(string $filename): array
 
         $worksheetNames = [];
 
-        $xml = $this->trySimpleXMLLoadString($filename);
+        $xml = $this->trySimpleXMLLoadStringPrivate($filename);
         if ($xml === false) {
             throw new Exception("Problem reading {$filename}");
         }
@@ -161,7 +192,7 @@ public function listWorksheetInfo(string $filename): array
 
         $worksheetInfo = [];
 
-        $xml = $this->trySimpleXMLLoadString($filename);
+        $xml = $this->trySimpleXMLLoadStringPrivate($filename);
         if ($xml === false) {
             throw new Exception("Problem reading {$filename}");
         }
@@ -252,16 +283,18 @@ public function loadIntoExisting(string $filename, Spreadsheet $spreadsheet, boo
     {
         if ($useContents) {
             $this->fileContents = $filename;
+            $fileOrString = 'string';
         } else {
             File::assertFile($filename);
             if (!$this->canRead($filename)) {
                 throw new Exception($filename . ' is an Invalid Spreadsheet file.');
             }
+            $fileOrString = 'file';
         }
 
-        $xml = $this->trySimpleXMLLoadString($filename);
+        $xml = $this->trySimpleXMLLoadStringPrivate($filename, $fileOrString);
         if ($xml === false) {
-            throw new Exception("Problem reading {$filename}");
+            throw new Exception($this->xmlFailMessage);
         }
 
         $namespaces = $xml->getNamespaces(true);
@@ -505,6 +538,25 @@ public function loadIntoExisting(string $filename, Spreadsheet $spreadsheet, boo
             $dataValidations->loadDataValidations($worksheet, $spreadsheet);
             $xmlX = $worksheet->children(Namespaces::URN_EXCEL);
             if (isset($xmlX->WorksheetOptions)) {
+                if (isset($xmlX->WorksheetOptions->ShowPageBreakZoom)) {
+                    $spreadsheet->getActiveSheet()->getSheetView()->setView(SheetView::SHEETVIEW_PAGE_BREAK_PREVIEW);
+                }
+                if (isset($xmlX->WorksheetOptions->Zoom)) {
+                    $zoomScaleNormal = (int) $xmlX->WorksheetOptions->Zoom;
+                    if ($zoomScaleNormal > 0) {
+                        $spreadsheet->getActiveSheet()->getSheetView()->setZoomScaleNormal($zoomScaleNormal);
+                        $spreadsheet->getActiveSheet()->getSheetView()->setZoomScale($zoomScaleNormal);
+                    }
+                }
+                if (isset($xmlX->WorksheetOptions->PageBreakZoom)) {
+                    $zoomScaleNormal = (int) $xmlX->WorksheetOptions->PageBreakZoom;
+                    if ($zoomScaleNormal > 0) {
+                        $spreadsheet->getActiveSheet()->getSheetView()->setZoomScaleSheetLayoutView($zoomScaleNormal);
+                    }
+                }
+                if (isset($xmlX->WorksheetOptions->ShowPageBreakZoom)) {
+                    $spreadsheet->getActiveSheet()->getSheetView()->setView(SheetView::SHEETVIEW_PAGE_BREAK_PREVIEW);
+                }
                 if (isset($xmlX->WorksheetOptions->FreezePanes)) {
                     $freezeRow = $freezeColumn = 1;
                     if (isset($xmlX->WorksheetOptions->SplitHorizontal)) {
@@ -590,6 +642,20 @@ public function loadIntoExisting(string $filename, Spreadsheet $spreadsheet, boo
                     }
                 }
             }
+            if (isset($xmlX->PageBreaks)) {
+                if (isset($xmlX->PageBreaks->ColBreaks)) {
+                    foreach ($xmlX->PageBreaks->ColBreaks->ColBreak as $colBreak) {
+                        $colBreak = (string) $colBreak->Column;
+                        $spreadsheet->getActiveSheet()->setBreak([1 + (int) $colBreak, 1], Worksheet::BREAK_COLUMN);
+                    }
+                }
+                if (isset($xmlX->PageBreaks->RowBreaks)) {
+                    foreach ($xmlX->PageBreaks->RowBreaks->RowBreak as $rowBreak) {
+                        $rowBreak = (string) $rowBreak->Row;
+                        $spreadsheet->getActiveSheet()->setBreak([1, (int) $rowBreak], Worksheet::BREAK_ROW);
+                    }
+                }
+            }
             ++$worksheetID;
         }
 

src/PhpSpreadsheet/Reader/Xml/Style.php

@@ -14,7 +14,9 @@ class Style
 
     public function parseStyles(SimpleXMLElement $xml, array $namespaces): array
     {
-        if (!isset($xml->Styles) || !is_iterable($xml->Styles[0])) {
+        $children = $xml->children('urn:schemas-microsoft-com:office:spreadsheet');
+        $stylesXml = $children->Styles[0];
+        if (!isset($stylesXml) || !is_iterable($stylesXml)) {
             return [];
         }
 
@@ -24,7 +26,7 @@ public function parseStyles(SimpleXMLElement $xml, array $namespaces): array
         $fillStyleParser = new Style\Fill();
         $numberFormatStyleParser = new Style\NumberFormat();
 
-        foreach ($xml->Styles[0] as $style) {
+        foreach ($stylesXml as $style) {
             $style_ss = self::getAttributes($style, $namespaces['ss']);
             $styleID = (string) $style_ss['ID'];
             $this->styles[$styleID] = $this->styles['Default'] ?? [];

src/PhpSpreadsheet/Reader/Xml/Style/Border.php

@@ -20,6 +20,18 @@ class Border extends StyleBase
      */
     public const BORDER_MAPPINGS = [
         'borderStyle' => [
+            'continuous' => BorderStyle::BORDER_HAIR,
+            'dash' => BorderStyle::BORDER_DASHED,
+            'dashdot' => BorderStyle::BORDER_DASHDOT,
+            'dashdotdot' => BorderStyle::BORDER_DASHDOTDOT,
+            'dot' => BorderStyle::BORDER_DOTTED,
+            'double' => BorderStyle::BORDER_DOUBLE,
+            '0continuous' => BorderStyle::BORDER_HAIR,
+            '0dash' => BorderStyle::BORDER_DASHED,
+            '0dashdot' => BorderStyle::BORDER_DASHDOT,
+            '0dashdotdot' => BorderStyle::BORDER_DASHDOTDOT,
+            '0dot' => BorderStyle::BORDER_DOTTED,
+            '0double' => BorderStyle::BORDER_DOUBLE,
             '1continuous' => BorderStyle::BORDER_THIN,
             '1dash' => BorderStyle::BORDER_DASHED,
             '1dashdot' => BorderStyle::BORDER_DASHDOT,

src/PhpSpreadsheet/Worksheet/SheetView.php

@@ -31,6 +31,20 @@ class SheetView
      */
     private ?int $zoomScaleNormal = 100;
 
+    /**
+     * ZoomScalePageLayoutView.
+     *
+     * Valid values range from 10 to 400.
+     */
+    private int $zoomScalePageLayoutView = 100;
+
+    /**
+     * ZoomScaleSheetLayoutView.
+     *
+     * Valid values range from 10 to 400.
+     */
+    private int $zoomScaleSheetLayoutView = 100;
+
     /**
      * ShowZeros.
      *
@@ -105,6 +119,38 @@ public function setZoomScaleNormal(?int $zoomScaleNormal): static
         return $this;
     }
 
+    public function getZoomScalePageLayoutView(): int
+    {
+        return $this->zoomScalePageLayoutView;
+    }
+
+    public function setZoomScalePageLayoutView(int $zoomScalePageLayoutView): static
+    {
+        if ($zoomScalePageLayoutView >= 1) {
+            $this->zoomScalePageLayoutView = $zoomScalePageLayoutView;
+        } else {
+            throw new PhpSpreadsheetException('Scale must be greater than or equal to 1.');
+        }
+
+        return $this;
+    }
+
+    public function getZoomScaleSheetLayoutView(): int
+    {
+        return $this->zoomScaleSheetLayoutView;
+    }
+
+    public function setZoomScaleSheetLayoutView(int $zoomScaleSheetLayoutView): static
+    {
+        if ($zoomScaleSheetLayoutView >= 1) {
+            $this->zoomScaleSheetLayoutView = $zoomScaleSheetLayoutView;
+        } else {
+            throw new PhpSpreadsheetException('Scale must be greater than or equal to 1.');
+        }
+
+        return $this;
+    }
+
     /**
      * Set ShowZeroes setting.
      */

src/PhpSpreadsheet/Writer/Xlsx/Worksheet.php

@@ -264,11 +264,21 @@ private function writeSheetViews(XMLWriter $objWriter, PhpspreadsheetWorksheet $
         $objWriter->writeAttribute('workbookViewId', '0');
 
         // Zoom scales
-        if ($worksheet->getSheetView()->getZoomScale() != 100) {
-            $objWriter->writeAttribute('zoomScale', (string) $worksheet->getSheetView()->getZoomScale());
+        $zoomScale = $worksheet->getSheetView()->getZoomScale();
+        if ($zoomScale !== 100 && $zoomScale !== null) {
+            $objWriter->writeAttribute('zoomScale', (string) $zoomScale);
         }
-        if ($worksheet->getSheetView()->getZoomScaleNormal() != 100) {
-            $objWriter->writeAttribute('zoomScaleNormal', (string) $worksheet->getSheetView()->getZoomScaleNormal());
+        $zoomScale = $worksheet->getSheetView()->getZoomScaleNormal();
+        if ($zoomScale !== 100 && $zoomScale !== null) {
+            $objWriter->writeAttribute('zoomScaleNormal', (string) $zoomScale);
+        }
+        $zoomScale = $worksheet->getSheetView()->getZoomScalePageLayoutView();
+        if ($zoomScale !== 100) {
+            $objWriter->writeAttribute('zoomScalePageLayoutView', (string) $zoomScale);
+        }
+        $zoomScale = $worksheet->getSheetView()->getZoomScaleSheetLayoutView();
+        if ($zoomScale !== 100) {
+            $objWriter->writeAttribute('zoomScaleSheetLayoutView', (string) $zoomScale);
         }
 
         // Show zeros (Excel also writes this attribute only if set to false)
@@ -1210,7 +1220,7 @@ private function writeBreaks(XMLWriter $objWriter, PhpspreadsheetWorksheet $work
             $objWriter->writeAttribute('manualBreakCount', (string) count($aColumnBreaks));
 
             foreach ($aColumnBreaks as $cell => $break) {
-                $coords = Coordinate::coordinateFromString($cell);
+                $coords = Coordinate::indexesFromString($cell);
 
                 $objWriter->startElement('brk');
                 $objWriter->writeAttribute('id', (string) ((int) $coords[0] - 1));