Merge pull request #4689 from oleibman/listdimensions

oleibman · web-flow · commit 0cab37fa7c61 · 2025-10-24T01:05:40.000Z
Xls Reader ListWorksheetInfo and New ListWorksheetDimensions
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -11,6 +11,7 @@ and this project adheres to [Semantic Versioning](https://semver.org). Thia is a
 
 - Option to display numbers with less precision. [Issue #4626](https://github.com/PHPOffice/PhpSpreadsheet/issues/4626) [PR #4640](https://github.com/PHPOffice/PhpSpreadsheet/pull/4640)
 - Offer Tcpdf Interface which throws exception rather than die. [PR #4666](https://github.com/PHPOffice/PhpSpreadsheet/pull/4666)
+- Xls Reader ListWorksheetDimensions method. [PR #4689](https://github.com/PHPOffice/PhpSpreadsheet/pull/4689)
 
 ### Removed
 
@@ -45,6 +46,8 @@ and this project adheres to [Semantic Versioning](https://semver.org). Thia is a
 - Better support for Style Alignment Read Order. [Issue #850](https://github.com/PHPOffice/PhpSpreadsheet/issues/850) [PR #4655](https://github.com/PHPOffice/PhpSpreadsheet/pull/4655)
 - More sophisticated workbook password algorithms (Xlsx only). [Issue #4673](https://github.com/PHPOffice/PhpSpreadsheet/issues/4673) [PR #4675](https://github.com/PHPOffice/PhpSpreadsheet/pull/4675)
 - Xls Writer fix DIMENSIONS record. [Issue #4682](https://github.com/PHPOffice/PhpSpreadsheet/issues/4682) [PR #4687](https://github.com/PHPOffice/PhpSpreadsheet/pull/4687)
+- Xls Reader listWorksheetInfo process MULRK records. [PR #4689](https://github.com/PHPOffice/PhpSpreadsheet/pull/4689)
+- Make Reader Xls Escher generic. [PR #4690](https://github.com/PHPOffice/PhpSpreadsheet/pull/4690)
 
 ## 2025-09-03 - 5.1.0
 
diff --git a/src/PhpSpreadsheet/Reader/Xls.php b/src/PhpSpreadsheet/Reader/Xls.php
@@ -294,6 +294,16 @@ public function listWorksheetInfo(string $filename): array
         return (new Xls\ListFunctions())->listWorksheetInfo2($filename, $this);
     }
 
+    /**
+     * Return worksheet info (Name, Last Column Letter, Last Column Index, Total Rows, Total Columns).
+     *
+     * @return array<int, array{worksheetName: string, dimensionsMinR: int, dimensionsMinC: int, dimensionsMaxR: int, dimensionsMaxC: int, lastColumnLetter: string}>
+     */
+    public function listWorksheetDimensions(string $filename): array
+    {
+        return (new Xls\ListFunctions())->listWorksheetDimensions2($filename, $this);
+    }
+
     /**
      * Loads PhpSpreadsheet from file.
      */
diff --git a/src/PhpSpreadsheet/Reader/Xls/ListFunctions.php b/src/PhpSpreadsheet/Reader/Xls/ListFunctions.php
@@ -124,14 +124,19 @@ protected function listWorksheetInfo2(string $filename, Xls $xls): array
                     case self::XLS_TYPE_FORMULA:
                     case self::XLS_TYPE_BOOLERR:
                     case self::XLS_TYPE_LABEL:
+                    case self::XLS_TYPE_MULRK:
                         $length = self::getUInt2d($xls->data, $xls->pos + 2);
                         $recordData = $xls->readRecordData($xls->data, $xls->pos + 4, $length);
 
                         // move stream pointer to next record
                         $xls->pos += 4 + $length;
 
                         $rowIndex = self::getUInt2d($recordData, 0) + 1;
-                        $columnIndex = self::getUInt2d($recordData, 2);
+                        if ($code === self::XLS_TYPE_MULRK) {
+                            $columnIndex = self::getUInt2d($recordData, $length - 2);
+                        } else {
+                            $columnIndex = self::getUInt2d($recordData, 2);
+                        }
 
                         $tmpInfo['totalRows'] = max($tmpInfo['totalRows'], $rowIndex);
                         $tmpInfo['lastColumnIndex'] = max($tmpInfo['lastColumnIndex'], $columnIndex);
@@ -160,4 +165,103 @@ protected function listWorksheetInfo2(string $filename, Xls $xls): array
 
         return $worksheetInfo;
     }
+
+    /**
+     * Return worksheet info (Name, Last Column Letter, Last Column Index, Total Rows, Total Columns).
+     *
+     * @return array<int, array{worksheetName: string, dimensionsMinR: int, dimensionsMinC: int, dimensionsMaxR: int, dimensionsMaxC: int, lastColumnLetter: string}>
+     */
+    protected function listWorksheetDimensions2(string $filename, Xls $xls): array
+    {
+        File::assertFile($filename);
+
+        $worksheetInfo = [];
+
+        // Read the OLE file
+        $xls->loadOLE($filename);
+
+        // total byte size of Excel data (workbook global substream + sheet substreams)
+        $xls->dataSize = strlen($xls->data);
+
+        // initialize
+        $xls->pos = 0;
+        $xls->sheets = [];
+
+        // Parse Workbook Global Substream
+        while ($xls->pos < $xls->dataSize) {
+            $code = self::getUInt2d($xls->data, $xls->pos);
+
+            match ($code) {
+                self::XLS_TYPE_BOF => $xls->readBof(),
+                self::XLS_TYPE_SHEET => $xls->readSheet(),
+                self::XLS_TYPE_EOF => $xls->readDefault(),
+                self::XLS_TYPE_CODEPAGE => $xls->readCodepage(),
+                default => $xls->readDefault(),
+            };
+
+            if ($code === self::XLS_TYPE_EOF) {
+                break;
+            }
+        }
+
+        // Parse the individual sheets
+        foreach ($xls->sheets as $sheet) {
+            if ($sheet['sheetType'] !== 0x00) {
+                // 0x00: Worksheet
+                // 0x02: Chart
+                // 0x06: Visual Basic module
+                continue;
+            }
+
+            $tmpInfo = [];
+            $tmpInfo['worksheetName'] = StringHelper::convertToString($sheet['name']);
+            $tmpInfo['dimensionsMinR'] = -1;
+            $tmpInfo['dimensionsMaxR'] = -1;
+            $tmpInfo['dimensionsMinC'] = -1;
+            $tmpInfo['dimensionsMaxC'] = -1;
+            $tmpInfo['lastColumnLetter'] = '';
+
+            $xls->pos = $sheet['offset'];
+
+            while ($xls->pos <= $xls->dataSize - 4) {
+                $code = self::getUInt2d($xls->data, $xls->pos);
+
+                switch ($code) {
+                    case self::XLS_TYPE_BOF:
+                        $xls->readBof();
+
+                        break;
+                    case self::XLS_TYPE_EOF:
+                        $xls->readDefault();
+
+                        break 2;
+                    case self::XLS_TYPE_DIMENSION:
+                        $length = self::getUInt2d($xls->data, $xls->pos + 2);
+                        if ($length === 14) {
+                            $dimensionsData = substr($xls->data, $xls->pos + 4, $length);
+                            $data = unpack('VrwMic/VrwMac/vcolMic/vcolMac/vreserved', $dimensionsData);
+                            if (is_array($data)) {
+                                /** @var int[] $data */
+                                $tmpInfo['dimensionsMinR'] = $data['rwMic'];
+                                $tmpInfo['dimensionsMaxR'] = $data['rwMac'];
+                                $tmpInfo['dimensionsMinC'] = $data['colMic'];
+                                $tmpInfo['dimensionsMaxC'] = $data['colMac'];
+                                $tmpInfo['lastColumnLetter'] = Coordinate::stringFromColumnIndex($tmpInfo['dimensionsMaxC']);
+                            }
+                        }
+                        $xls->readDefault();
+
+                        break;
+                    default:
+                        $xls->readDefault();
+
+                        break;
+                }
+            }
+
+            $worksheetInfo[] = $tmpInfo;
+        }
+
+        return $worksheetInfo;
+    }
 }
diff --git a/src/PhpSpreadsheet/Reader/XlsBase.php b/src/PhpSpreadsheet/Reader/XlsBase.php
@@ -25,8 +25,6 @@ class XlsBase extends BaseReader
     final const XLS_TYPE_FORMULA = 0x0006;
     final const XLS_TYPE_EOF = 0x000A;
     final const XLS_TYPE_PROTECT = 0x0012;
-    final const XLS_TYPE_OBJECTPROTECT = 0x0063;
-    final const XLS_TYPE_SCENPROTECT = 0x00DD;
     final const XLS_TYPE_PASSWORD = 0x0013;
     final const XLS_TYPE_HEADER = 0x0014;
     final const XLS_TYPE_FOOTER = 0x0015;
@@ -50,6 +48,7 @@ class XlsBase extends BaseReader
     final const XLS_TYPE_CODEPAGE = 0x0042;
     final const XLS_TYPE_DEFCOLWIDTH = 0x0055;
     final const XLS_TYPE_OBJ = 0x005D;
+    final const XLS_TYPE_OBJECTPROTECT = 0x0063;
     final const XLS_TYPE_COLINFO = 0x007D;
     final const XLS_TYPE_IMDATA = 0x007F;
     final const XLS_TYPE_SHEETPR = 0x0081;
@@ -62,6 +61,7 @@ class XlsBase extends BaseReader
     final const XLS_TYPE_MULRK = 0x00BD;
     final const XLS_TYPE_MULBLANK = 0x00BE;
     final const XLS_TYPE_DBCELL = 0x00D7;
+    final const XLS_TYPE_SCENPROTECT = 0x00DD;
     final const XLS_TYPE_XF = 0x00E0;
     final const XLS_TYPE_MERGEDCELLS = 0x00E5;
     final const XLS_TYPE_MSODRAWINGGROUP = 0x00EB;
@@ -70,6 +70,8 @@ class XlsBase extends BaseReader
     final const XLS_TYPE_LABELSST = 0x00FD;
     final const XLS_TYPE_EXTSST = 0x00FF;
     final const XLS_TYPE_EXTERNALBOOK = 0x01AE;
+    final const XLS_TYPE_CFHEADER = 0x01B0;
+    final const XLS_TYPE_CFRULE = 0x01B1;
     final const XLS_TYPE_DATAVALIDATIONS = 0x01B2;
     final const XLS_TYPE_TXO = 0x01B6;
     final const XLS_TYPE_HYPERLINK = 0x01B8;
@@ -90,13 +92,11 @@ class XlsBase extends BaseReader
     final const XLS_TYPE_FORMAT = 0x041E;
     final const XLS_TYPE_SHAREDFMLA = 0x04BC;
     final const XLS_TYPE_BOF = 0x0809;
+    final const XLS_TYPE_SHEETLAYOUT = 0x0862;
     final const XLS_TYPE_SHEETPROTECTION = 0x0867;
     final const XLS_TYPE_RANGEPROTECTION = 0x0868;
-    final const XLS_TYPE_SHEETLAYOUT = 0x0862;
     final const XLS_TYPE_XFEXT = 0x087D;
     final const XLS_TYPE_PAGELAYOUTVIEW = 0x088B;
-    final const XLS_TYPE_CFHEADER = 0x01B0;
-    final const XLS_TYPE_CFRULE = 0x01B1;
     final const XLS_TYPE_UNKNOWN = 0xFFFF;
 
     // Encryption type
diff --git a/tests/PhpSpreadsheetTests/Reader/Xls/InfoNamesTest.php b/tests/PhpSpreadsheetTests/Reader/Xls/InfoNamesTest.php
@@ -165,4 +165,80 @@ public function testLoadMacCentralEuropeBiff8(): void
         self::assertSame('Użytkownik Microsoft Office', $properties->getLastModifiedBy());
         $spreadsheet->disconnectWorksheets();
     }
+
+    public function testDimensions(): void
+    {
+        $filename = 'tests/data/Reader/XLS/pr.4687.excel.xls';
+        $reader = new Xls();
+        $info = $reader->listWorksheetInfo($filename);
+        $expected = [
+            [
+                'worksheetName' => 'Sheet1',
+                'lastColumnLetter' => 'D',
+                'lastColumnIndex' => 3,
+                'totalRows' => 2,
+                'totalColumns' => 4,
+                'sheetState' => 'visible',
+            ],
+            [
+                'worksheetName' => 'Sheet2',
+                'lastColumnLetter' => 'B',
+                'lastColumnIndex' => 1,
+                'totalRows' => 4,
+                'totalColumns' => 2,
+                'sheetState' => 'visible',
+            ],
+        ];
+        self::assertSame($expected, $info);
+        $info = $reader->listWorksheetDimensions($filename);
+        $expected = [
+            [
+                'worksheetName' => 'Sheet1',
+                'dimensionsMinR' => 0,
+                'dimensionsMaxR' => 2,
+                'dimensionsMinC' => 0,
+                'dimensionsMaxC' => 4,
+                'lastColumnLetter' => 'D',
+            ],
+            [
+                'worksheetName' => 'Sheet2',
+                'dimensionsMinR' => 0,
+                'dimensionsMaxR' => 4,
+                'dimensionsMinC' => 0,
+                'dimensionsMaxC' => 2,
+                'lastColumnLetter' => 'B',
+            ],
+        ];
+        self::assertSame($expected, $info);
+    }
+
+    public function testChartSheetIgnored(): void
+    {
+        $filename = 'tests/data/Reader/XLS/chartsheet.xls';
+        $reader = new Xls();
+        $info = $reader->listWorksheetInfo($filename);
+        $expected = [
+            [
+                'worksheetName' => 'Data',
+                'lastColumnLetter' => 'M',
+                'lastColumnIndex' => 12,
+                'totalRows' => 7,
+                'totalColumns' => 13,
+                'sheetState' => 'visible',
+            ],
+        ];
+        self::assertSame($expected, $info);
+        $info = $reader->listWorksheetDimensions($filename);
+        $expected = [
+            [
+                'worksheetName' => 'Data',
+                'dimensionsMinR' => 0,
+                'dimensionsMaxR' => 7,
+                'dimensionsMinC' => 0,
+                'dimensionsMaxC' => 13,
+                'lastColumnLetter' => 'M',
+            ],
+        ];
+        self::assertSame($expected, $info);
+    }
 }
diff --git a/tests/PhpSpreadsheetTests/Shared/OLETest.php b/tests/PhpSpreadsheetTests/Shared/OLETest.php
@@ -75,4 +75,40 @@ public function testChainedBadPath(): void
             }
         }
     }
+
+    public function testOleFunctions(): void
+    {
+        $ole = new OLE();
+        $infile = 'tests/data/Reader/XLS/pr.4687.excel.xls';
+        $ole->read($infile);
+        self::assertSame(4, $ole->ppsTotal());
+        self::assertFalse($ole->isFile(0), 'root entry');
+        self::assertTrue($ole->isFile(1), 'workbook');
+        self::assertTrue($ole->isFile(2), 'summary information');
+        self::assertTrue($ole->isFile(3), 'document summary information');
+        self::assertFalse($ole->isFile(4), 'no such index');
+        self::assertTrue($ole->isRoot(0), 'root entry');
+        self::assertFalse($ole->isRoot(1), 'workbook');
+        self::assertFalse($ole->isRoot(2), 'summary information');
+        self::assertFalse($ole->isRoot(3), 'document summary information');
+        self::assertFalse($ole->isRoot(4), 'no such index');
+        self::assertSame(0, $ole->getDataLength(0), 'root entry');
+        self::assertSame(15712, $ole->getDataLength(1), 'workbook');
+        self::assertSame(4096, $ole->getDataLength(2), 'summary information');
+        self::assertSame(4096, $ole->getDataLength(3), 'document summary information');
+        self::assertSame(0, $ole->getDataLength(4), 'no such index');
+        self::assertSame('', $ole->getData(2, -1, 4), 'negative position');
+        self::assertSame('', $ole->getData(2, 5000, 4), 'position > length');
+        self::assertSame('feff0000', bin2hex($ole->getData(2, 0, 4)));
+        self::assertSame('', $ole->getData(4, 0, 4), 'no such index');
+    }
+
+    public function testBadEndian(): void
+    {
+        $this->expectException(ReaderException::class);
+        $this->expectExceptionMessage('Only Little-Endian encoding is supported');
+        $ole = new OLE();
+        $infile = 'tests/data/Reader/XLS/pr.4687.excel.badendian.xls';
+        $ole->read($infile);
+    }
 }
diff --git a/tests/PhpSpreadsheetTests/Shared/XlsTest.php b/tests/PhpSpreadsheetTests/Shared/XlsTest.php
@@ -0,0 +1,26 @@
+<?php
+
+declare(strict_types=1);
+
+namespace PhpOffice\PhpSpreadsheetTests\Shared;
+
+use PhpOffice\PhpSpreadsheet\Shared\Xls as SharedXls;
+use PhpOffice\PhpSpreadsheet\Spreadsheet;
+use PHPUnit\Framework\TestCase;
+
+class XlsTest extends TestCase
+{
+    public function testSizes(): void
+    {
+        $spreadsheet = new Spreadsheet();
+        $sheet = $spreadsheet->getActiveSheet();
+        $sheet->fromArray([[1, 2], [3, 4]]);
+        $sheet->getColumnDimension('B')->setVisible(false);
+        $sheet->getRowDimension(2)->setVisible(false);
+        self::assertSame(64, SharedXls::sizeCol($sheet, 'A'));
+        self::assertSame(0, SharedXls::sizeCol($sheet, 'B'));
+        self::assertSame(20, SharedXls::sizeRow($sheet, 1));
+        self::assertSame(0, SharedXls::sizeRow($sheet, 2));
+        $spreadsheet->disconnectWorksheets();
+    }
+}
diff --git a/tests/data/Reader/XLS/chartsheet.xls b/tests/data/Reader/XLS/chartsheet.xls
diff --git a/tests/data/Reader/XLS/pr.4687.excel.badendian.xls b/tests/data/Reader/XLS/pr.4687.excel.badendian.xls
diff --git a/tests/data/Reader/XLS/pr.4687.excel.xls b/tests/data/Reader/XLS/pr.4687.excel.xls
