Xlsx Reader Optionally Ignore Rows With No Cells

Fix #3982. A number of issues submitted about Xlsx read performance have a common theme, namely that row 1,048,576 and a few rows before it are defined in the worksheet Xml with no cells attached to them. These might be the work of a third party product. While these extraneous rows do not cause any problems for the cells that are actually used on the worksheet, they can lead to excessive memory use. This PR provides an option for the application to ignore rows with no cells when loading.

Recent changes to the load logic had already made a significant difference to memory consumption and load time. For the spreadsheet attached to issue 3982, which had caused out-of-memory errors on the user's system, peak memory usage was already reduced to 40-odd MB. With the new option, this is drastically reduced again, to just over 9MB. Specifying the new option is very easy:
```php
$reader->setIgnoreRowsWithNoCells(true);
```
Note that there are cases where you might not want this (non-default) behavior. For example, if you set a row height on a row with no cells, the height would be lost with this option. Unfortunately, the extraneous row definitions in the problematic spreadsheets claim to have a custom height, so I can't just use "no custom row styles" as an additional filter.

Author: oleibman

src/PhpSpreadsheet/Reader/BaseReader.php

@@ -39,6 +39,13 @@ abstract class BaseReader implements IReader
      */
     protected ?array $loadSheetsOnly = null;
 
+    /**
+     * Ignore rows with no cells?
+     * Identifies whether the Reader should ignore rows with no cells.
+     *        Currently implemented only for Xlsx.
+     */
+    protected bool $ignoreRowsWithNoCells = false;
+
     /**
      * IReadFilter instance.
      */
@@ -78,6 +85,18 @@ public function setReadEmptyCells(bool $readEmptyCells): self
         return $this;
     }
 
+    public function getIgnoreRowsWithNoCells(): bool
+    {
+        return $this->ignoreRowsWithNoCells;
+    }
+
+    public function setIgnoreRowsWithNoCells(bool $ignoreRowsWithNoCells): self
+    {
+        $this->ignoreRowsWithNoCells = $ignoreRowsWithNoCells;
+
+        return $this;
+    }
+
     public function getIncludeCharts(): bool
     {
         return $this->includeCharts;
@@ -150,6 +169,9 @@ protected function processFlags(int $flags): void
         if (((bool) ($flags & self::SKIP_EMPTY_CELLS) || (bool) ($flags & self::IGNORE_EMPTY_CELLS)) === true) {
             $this->setReadEmptyCells(false);
         }
+        if (((bool) ($flags & self::IGNORE_ROWS_WITH_NO_CELLS)) === true) {
+            $this->setIgnoreRowsWithNoCells(true);
+        }
     }
 
     protected function loadSpreadsheetFromFile(string $filename): Spreadsheet

src/PhpSpreadsheet/Reader/IReader.php

@@ -13,6 +13,8 @@ interface IReader
     public const SKIP_EMPTY_CELLS = 4;
     public const IGNORE_EMPTY_CELLS = 4;
 
+    public const IGNORE_ROWS_WITH_NO_CELLS = 8;
+
     public function __construct();
 
     /**

src/PhpSpreadsheet/Reader/Xlsx.php

@@ -796,10 +796,10 @@ protected function loadSpreadsheetFromFile(string $filename): Spreadsheet
                                 }
 
                                 $sheetViewOptions = new SheetViewOptions($docSheet, $xmlSheetNS);
-                                $sheetViewOptions->load($this->getReadDataOnly(), $this->styleReader);
+                                $sheetViewOptions->load($this->readDataOnly, $this->styleReader);
 
                                 (new ColumnAndRowAttributes($docSheet, $xmlSheetNS))
-                                    ->load($this->getReadFilter(), $this->getReadDataOnly());
+                                    ->load($this->getReadFilter(), $this->readDataOnly, $this->ignoreRowsWithNoCells);
                             }
 
                             $holdSelectedCells = $docSheet->getSelectedCells();

src/PhpSpreadsheet/Reader/Xlsx/ColumnAndRowAttributes.php

@@ -72,7 +72,7 @@ private function setRowAttributes(int $rowNumber, array $rowAttributes): void
         }
     }
 
-    public function load(?IReadFilter $readFilter = null, bool $readDataOnly = false): void
+    public function load(?IReadFilter $readFilter = null, bool $readDataOnly = false, bool $ignoreRowsWithNoCells = false): void
     {
         if ($this->worksheetXml === null) {
             return;
@@ -85,7 +85,7 @@ public function load(?IReadFilter $readFilter = null, bool $readDataOnly = false
         }
 
         if ($this->worksheetXml->sheetData && $this->worksheetXml->sheetData->row) {
-            $rowsAttributes = $this->readRowAttributes($this->worksheetXml->sheetData->row, $readDataOnly);
+            $rowsAttributes = $this->readRowAttributes($this->worksheetXml->sheetData->row, $readDataOnly, $ignoreRowsWithNoCells);
         }
 
         if ($readFilter !== null && $readFilter::class === DefaultReadFilter::class) {
@@ -189,13 +189,13 @@ private function isFilteredRow(IReadFilter $readFilter, int $rowCoordinate, arra
         return false;
     }
 
-    private function readRowAttributes(SimpleXMLElement $worksheetRow, bool $readDataOnly): array
+    private function readRowAttributes(SimpleXMLElement $worksheetRow, bool $readDataOnly, bool $ignoreRowsWithNoCells): array
     {
         $rowAttributes = [];
 
         foreach ($worksheetRow as $rowx) {
             $row = $rowx->attributes();
-            if ($row !== null) {
+            if ($row !== null && (!$ignoreRowsWithNoCells || isset($rowx->c))) {
                 if (isset($row['ht']) && !$readDataOnly) {
                     $rowAttributes[(int) $row['r']]['rowHeight'] = (float) $row['ht'];
                 }

tests/PhpSpreadsheetTests/Reader/Xlsx/Issue3982Test.php

@@ -0,0 +1,41 @@
+<?php
+
+declare(strict_types=1);
+
+namespace PhpOffice\PhpSpreadsheetTests\Reader\Xlsx;
+
+use PhpOffice\PhpSpreadsheet\IOFactory;
+use PhpOffice\PhpSpreadsheet\Reader\IReader;
+use PhpOffice\PhpSpreadsheet\Reader\Xlsx as XlsxReader;
+
+class Issue3982Test extends \PHPUnit\Framework\TestCase
+{
+    private static string $testbook = 'tests/data/Reader/XLSX/issue.3982.xlsx';
+
+    public function testLoadAllRows(): void
+    {
+        $spreadsheet = IOFactory::load(self::$testbook);
+        $sheet = $spreadsheet->getActiveSheet();
+        $data = $sheet->toArray(null, true, false, true);
+        self::assertCount(1048576, $data);
+        $spreadsheet->disconnectWorksheets();
+    }
+
+    public function testIgnoreCellsWithNoRows(): void
+    {
+        $spreadsheet = IOFactory::load(self::$testbook, IReader::IGNORE_ROWS_WITH_NO_CELLS);
+        $sheet = $spreadsheet->getActiveSheet();
+        $data = $sheet->toArray(null, true, false, true);
+        self::assertSame([1, 2, 3, 4, 5, 6], array_keys($data));
+        $spreadsheet->disconnectWorksheets();
+    }
+
+    public function testDefaultSetting(): void
+    {
+        $reader = new XlsxReader();
+        self::assertFalse($reader->getIgnoreRowsWithNoCells());
+        self::assertFalse($reader->getReadDataOnly());
+        self::assertFalse($reader->getIncludeCharts());
+        self::assertTrue($reader->getReadEmptyCells());
+    }
+}