Xml Reader Rich Text

Fix #4001. Thanks to @SlowFox71 who reported the problem and developed most of the solution. This PR adds Rich Text support to the XML reader. The Xml Spreadsheet stores Rich Text as Html tags, children of the ss:Data tag using a specific namespace. These can be parsed into a RichText object using existing method Helper/Html::toRichTextObject. There are 2 items which need special attention. First, for attributes like bold or italic, Excel uses the appropriate Html tag (e.g. `<B>`). However, for an attribute like color, Excel uses `<Font html:Color="#FF0000">`, with a prefix on the Color tag. PhpSpreadsheet's Html parser cannot cope with the prefix. The parser is changed to strip `html:` from attribute names for the Font tag. The example cited by the user used a `<BR />` to indicate a line break in the data. However, it appears that, at least some of the time, Excel will instead use `
` to indicate a line break. The existing parser reduces one or more whitespace characters in the text to a single space, and so `
` will wind up disappearing. I am not sure why the existing code does this, but I do know that I am not willing to break it. Instead, I've added an optional boolean parameter `$preserveWhiteSpace` to `toRichTextObject`. If false (default), the existing logic will be used; but if true, substitution for whitespace characters in the text will not happen.
2026-09-15 04:26:25 +00:00 · 2024-04-30 23:51:13 -07:00
parent 35030fa66d
commit d40a1cfa52
3 changed files with 188 additions and 6 deletions
@@ -595,6 +595,8 @@ class Html

    private RichText $richTextObject;

+    private bool $preserveWhiteSpace = false;
+
    private function initialise(): void
    {
        $this->face = $this->size = $this->color = null;
@@ -608,7 +610,7 @@ class Html
    /**
     * Parse HTML formatting and return the resulting RichText.
     */
-    public function toRichTextObject(string $html): RichText
+    public function toRichTextObject(string $html, bool $preserveWhiteSpace = false): RichText
    {
        $this->initialise();

@@ -622,7 +624,9 @@ class Html
        $dom->preserveWhiteSpace = false;

        $this->richTextObject = new RichText();
+        $this->preserveWhiteSpace = $preserveWhiteSpace;
        $this->parseElements($dom);
+        $this->preserveWhiteSpace = false;

        // Clean any further spurious whitespace
        $this->cleanWhitespace();
@@ -706,6 +710,7 @@ class Html
        if ($attrs !== null) {
            foreach ($attrs as $attribute) {
                $attributeName = strtolower($attribute->name);
+                $attributeName = preg_replace('/^html:/', '', $attributeName) ?? $attributeName; // in case from Xml spreadsheet
                $attributeValue = $attribute->value;

                if ($attributeName == 'color') {
@@ -795,11 +800,15 @@ class Html

    private function parseTextNode(DOMText $textNode): void
    {
-        $domText = (string) preg_replace(
-            '/\s+/u',
-            ' ',
-            str_replace(["\r", "\n"], ' ', $textNode->nodeValue ?? '')
-        );
+        if ($this->preserveWhiteSpace) {
+            $domText = $textNode->nodeValue ?? '';
+        } else {
+            $domText = (string) preg_replace(
+                '/\s+/u',
+                ' ',
+                str_replace(["\r", "\n"], ' ', $textNode->nodeValue ?? '')
+            );
+        }
        $this->stringData .= $domText;
        $this->buildTextRun();
    }
@@ -8,6 +8,7 @@ use PhpOffice\PhpSpreadsheet\Cell\AddressHelper;
 use PhpOffice\PhpSpreadsheet\Cell\Coordinate;
 use PhpOffice\PhpSpreadsheet\Cell\DataType;
 use PhpOffice\PhpSpreadsheet\DefinedName;
+use PhpOffice\PhpSpreadsheet\Helper\Html as HelperHtml;
 use PhpOffice\PhpSpreadsheet\Reader\Security\XmlScanner;
 use PhpOffice\PhpSpreadsheet\Reader\Xlsx\Namespaces;
 use PhpOffice\PhpSpreadsheet\Reader\Xml\PageSettings;
@@ -426,6 +427,14 @@ class Xml extends BaseReader
                                    */
                                    case 'String':
                                        $type = DataType::TYPE_STRING;
+                                        $rich = $cellData->children('http://www.w3.org/TR/REC-html40');
+                                        if ($rich) {
+                                            // in case of HTML content we extract the payload
+                                            // and convert it into a rich text object
+                                            $content = $cellData->asXML() ?: '';
+                                            $html = new HelperHtml();
+                                            $cellValue = $html->toRichTextObject($content, true);
+                                        }

                                        break;
                                    case 'Number':
@@ -0,0 +1,164 @@
+<?php
+
+declare(strict_types=1);
+
+namespace PhpOffice\PhpSpreadsheetTests\Reader\Xml;
+
+use PhpOffice\PhpSpreadsheet\Reader\Xml;
+use PhpOffice\PhpSpreadsheet\RichText\RichText;
+use PhpOffice\PhpSpreadsheet\RichText\Run;
+use PHPUnit\Framework\TestCase;
+
+class XmlRichTextTest extends TestCase
+{
+    public function testBreakTag(): void
+    {
+        $xmldata = <<< 'EOT'
+            <?xml version="1.0"?>
+            <?mso-application progid="Excel.Sheet"?>
+            <Workbook xmlns="urn:schemas-microsoft-com:office:spreadsheet"
+                xmlns:o="urn:schemas-microsoft-com:office:office"
+                xmlns:x="urn:schemas-microsoft-com:office:excel"
+                xmlns:ss="urn:schemas-microsoft-com:office:spreadsheet"
+                xmlns:html="http://www.w3.org/TR/REC-html40">
+            <Worksheet ss:Name="Test">
+                <ss:Table>
+                    <ss:Row>
+                        <ss:Cell>
+                            <ss:Data ss:Type="String" xmlns="http://www.w3.org/TR/REC-html40"><I>italic</I><B>bold</B><BR />second line</ss:Data>
+                        </ss:Cell>
+                    </ss:Row>
+                </ss:Table>
+            </Worksheet>
+            </Workbook>
+            EOT;
+        $reader = new Xml();
+        $spreadsheet = $reader->loadSpreadsheetFromString($xmldata);
+        self::assertEquals(1, $spreadsheet->getSheetCount());
+
+        $sheet = $spreadsheet->getActiveSheet();
+        self::assertEquals('Test', $sheet->getTitle());
+        $richText = $sheet->getCell('A1')->getValue();
+        self::assertInstanceOf(RichText::class, $richText);
+        $elements = $richText->getRichTextElements();
+        self::assertCount(3, $elements);
+        $run = $elements[0];
+        self::assertInstanceOf(Run::class, $run);
+        self::assertSame('italic', $run->getText());
+        self::assertNotNull($run->getFont());
+        self::assertTrue($run->getFont()->getItalic());
+        self::assertFalse($run->getFont()->getBold());
+
+        $run = $elements[1];
+        self::assertInstanceOf(Run::class, $run);
+        self::assertSame('bold', $run->getText());
+        self::assertNotNull($run->getFont());
+        self::assertFalse($run->getFont()->getItalic());
+        self::assertTrue($run->getFont()->getBold());
+
+        $run = $elements[2];
+        self::assertInstanceOf(Run::class, $run);
+        self::assertSame("\nsecond line", $run->getText());
+
+        $spreadsheet->disconnectWorksheets();
+    }
+
+    public function testNewlineAndFontTag(): void
+    {
+        $xmldata = <<< 'EOT'
+            <?xml version="1.0"?>
+            <?mso-application progid="Excel.Sheet"?>
+            <Workbook xmlns="urn:schemas-microsoft-com:office:spreadsheet"
+             xmlns:o="urn:schemas-microsoft-com:office:office"
+             xmlns:x="urn:schemas-microsoft-com:office:excel"
+             xmlns:ss="urn:schemas-microsoft-com:office:spreadsheet"
+             xmlns:html="http://www.w3.org/TR/REC-html40">
+             <DocumentProperties xmlns="urn:schemas-microsoft-com:office:office">
+              <LastAuthor>Owen Leibman</LastAuthor>
+              <Created>2024-04-28T06:03:14Z</Created>
+              <Version>16.00</Version>
+             </DocumentProperties>
+             <OfficeDocumentSettings xmlns="urn:schemas-microsoft-com:office:office">
+              <AllowPNG/>
+             </OfficeDocumentSettings>
+             <ExcelWorkbook xmlns="urn:schemas-microsoft-com:office:excel">
+              <WindowHeight>6510</WindowHeight>
+              <WindowWidth>19200</WindowWidth>
+              <WindowTopX>32767</WindowTopX>
+              <WindowTopY>32767</WindowTopY>
+              <ProtectStructure>False</ProtectStructure>
+              <ProtectWindows>False</ProtectWindows>
+             </ExcelWorkbook>
+             <Styles>
+              <Style ss:ID="Default" ss:Name="Normal">
+               <Alignment ss:Vertical="Bottom"/>
+               <Borders/>
+               <Font ss:FontName="Aptos Narrow" x:Family="Swiss" ss:Size="11"
+                ss:Color="#000000"/>
+               <Interior/>
+               <NumberFormat/>
+               <Protection/>
+              </Style>
+              <Style ss:ID="s63">
+               <Alignment ss:Vertical="Bottom" ss:WrapText="1"/>
+               <Borders/>
+               <Font ss:FontName="Aptos Narrow" x:Family="Swiss" ss:Size="11" ss:Italic="1"/>
+               <Interior/>
+               <NumberFormat/>
+               <Protection/>
+              </Style>
+             </Styles>
+             <Worksheet ss:Name="Test">
+              <Table ss:ExpandedColumnCount="1" ss:ExpandedRowCount="1" x:FullColumns="1"
+               x:FullRows="1" ss:DefaultRowHeight="14.5">
+               <Row ss:AutoFitHeight="0" ss:Height="47.5">
+                <Cell ss:StyleID="s63"><ss:Data ss:Type="String"
+                  xmlns="http://www.w3.org/TR/REC-html40"><I>italic</I><B>bold&#10;</B><Font
+                   html:Color="#FF0000">second</Font><Font> line</Font></ss:Data></Cell>
+               </Row>
+              </Table>
+              <WorksheetOptions xmlns="urn:schemas-microsoft-com:office:excel">
+               <Unsynced/>
+               <Selected/>
+               <ProtectObjects>False</ProtectObjects>
+               <ProtectScenarios>False</ProtectScenarios>
+              </WorksheetOptions>
+             </Worksheet>
+            </Workbook>
+            EOT;
+        $reader = new Xml();
+        $spreadsheet = $reader->loadSpreadsheetFromString($xmldata);
+        self::assertEquals(1, $spreadsheet->getSheetCount());
+
+        $sheet = $spreadsheet->getActiveSheet();
+        self::assertEquals('Test', $sheet->getTitle());
+        $richText = $sheet->getCell('A1')->getValue();
+        self::assertInstanceOf(RichText::class, $richText);
+        $elements = $richText->getRichTextElements();
+        self::assertCount(4, $elements);
+        $run = $elements[0];
+        self::assertInstanceOf(Run::class, $run);
+        self::assertSame('italic', $run->getText());
+        self::assertNotNull($run->getFont());
+        self::assertTrue($run->getFont()->getItalic());
+        self::assertFalse($run->getFont()->getBold());
+
+        $run = $elements[1];
+        self::assertInstanceOf(Run::class, $run);
+        self::assertSame("bold\n", $run->getText());
+        self::assertNotNull($run->getFont());
+        self::assertFalse($run->getFont()->getItalic());
+        self::assertTrue($run->getFont()->getBold());
+
+        $run = $elements[2];
+        self::assertInstanceOf(Run::class, $run);
+        self::assertSame('second', $run->getText());
+        self::assertSame('FF0000', $run->getFont()?->getColor()->getRgb());
+
+        $run = $elements[3];
+        self::assertInstanceOf(Run::class, $run);
+        self::assertSame(' line', $run->getText());
+
+        $spreadsheet->disconnectWorksheets();
+    }
+}