add ability to set codepage explicitly for BIFF5

CHANGELOG.md

@@ -12,6 +12,7 @@ and this project adheres to [Semantic Versioning](https://semver.org).
 - Add support for IFS() logical function [#1442](https://github.com/PHPOffice/PhpSpreadsheet/pull/1442)
 - Add Cell Address Helper to provide conversions between the R1C1 and A1 address formats [#1558](https://github.com/PHPOffice/PhpSpreadsheet/pull/1558)
 - Add ability to edit Html/Pdf before saving [#1499](https://github.com/PHPOffice/PhpSpreadsheet/pull/1499)
+- Add ability to set codepage explicitly for BIFF5 [#1018](https://github.com/PHPOffice/PhpSpreadsheet/issues/1018)
 
 ### Fixed
 

src/PhpSpreadsheet/Reader/Xls.php

@@ -439,6 +439,15 @@ public function canRead($pFilename)
         }
     }
 
+    public function setCodepage(string $codepage): void
+    {
+        if (!CodePage::validate($codepage)) {
+            throw new PhpSpreadsheetException('Unknown codepage: ' . $codepage);
+        }
+
+        $this->codepage = $codepage;
+    }
+
     /**
      * Reads names of the worksheets from a file, without parsing the whole file to a PhpSpreadsheet object.
      *
@@ -640,7 +649,7 @@ public function load($pFilename)
 
         // initialize
         $this->pos = 0;
-        $this->codepage = 'CP1252';
+        $this->codepage = $this->codepage ?: CodePage::DEFAULT_CODE_PAGE;
         $this->formats = [];
         $this->objFonts = [];
         $this->palette = [];

src/PhpSpreadsheet/Shared/CodePage.php

@@ -6,6 +6,8 @@
 
 class CodePage
 {
+    public const DEFAULT_CODE_PAGE = 'CP1252';
+
     private static $pageArray = [
         0 => 'CP1252', //    CodePage is not always correctly set when the xls file was saved by Apple's Numbers program
         367 => 'ASCII', //    ASCII
@@ -65,6 +67,11 @@ class CodePage
         65001 => 'UTF-8', //    Unicode (UTF-8)
     ];
 
+    public static function validate(string $codePage): bool
+    {
+        return in_array($codePage, self::$pageArray, true);
+    }
+
     /**
      * Convert Microsoft Code Page Identifier to Code Page Name which iconv
      * and mbstring understands.