Clientbase
/
PhpSpreadsheet
mirror of https://github.com/basemaster/PhpSpreadsheet.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Xls Reader Handle MACCENTRALEUROPE With or Without Hyphen (#2213) 

* Xls Reader Handle MACCENTRALEUROPE With or Without Hyphen

Fixes issue #549 and https://github.com/Maatwebsite/Laravel-Excel/issues/989 (which is the source of the new test file). Some systems accept MACCENTRALEUROPE as the name for the appropriate encoding, and some accept MAC-CENTRALEUROPE. I fortunately have access to at least one of each type, and have run the tests on each.

CodePage.php has an array of translations from codepage number to string. I now allow the value to itself be an array; if so, the code will test each in turn to see if it can be used in iconv. I did not go fishing for other similar problems. If such show up, they can be dealt with in the same manner as this one. I don't really expect others, since this is a problem not merely for Xls, but, even then, it applies only to BIFF5 and earlier.

I also moved XlsTest from Reader to Reader/Xls.

* Cache Successful Result For Future Use

Per suggestion from @MarkBaker
This commit is contained in:
oleibman 2021-07-11 18:02:47 -07:00 committed by GitHub
parent 075cecd268
commit 8729a68338
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
6 changed files with 76 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
phpstan-baseline.neon
View File

@ -3490,11 +3490,6 @@ parameters:
count: 1
path: src/PhpSpreadsheet/Settings.php
-
message: "#^Property PhpOffice\\\\PhpSpreadsheet\\\\Shared\\\\CodePage\\:\\:\\$pageArray has no typehint specified\\.$#"
count: 1
path: src/PhpSpreadsheet/Shared/CodePage.php
-
message: "#^Parameter \\#1 \\$dateValue of static method PhpOffice\\\\PhpSpreadsheet\\\\Shared\\\\Date\\:\\:timestampToExcel\\(\\) expects int, float\\|int\\|string given\\.$#"
count: 1
@ -6525,16 +6520,6 @@ parameters:
count: 1
path: tests/PhpSpreadsheetTests/Reader/Security/XmlScannerTest.php
-
message: "#^Cannot call method getFormattedValue\\(\\) on PhpOffice\\\\PhpSpreadsheet\\\\Cell\\\\Cell\\|null\\.$#"
count: 1
path: tests/PhpSpreadsheetTests/Reader/XlsTest.php
-
message: "#^Cannot call method getCoordinate\\(\\) on PhpOffice\\\\PhpSpreadsheet\\\\Cell\\\\Cell\\|null\\.$#"
count: 1
path: tests/PhpSpreadsheetTests/Reader/XlsTest.php
-
message: "#^Method PhpOffice\\\\PhpSpreadsheetTests\\\\Reader\\\\Xlsx\\\\AutoFilterTest\\:\\:getWorksheetInstance\\(\\) has no return typehint specified\\.$#"
count: 1

19
src/PhpSpreadsheet/Shared/CodePage.php
View File

@ -8,6 +8,7 @@ class CodePage
{
public const DEFAULT_CODE_PAGE = 'CP1252';
/** @var array */
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
@ -56,7 +57,7 @@ class CodePage
10010 => 'MACROMANIA', // Macintosh Romania
10017 => 'MACUKRAINE', // Macintosh Ukraine
10021 => 'MACTHAI', // Macintosh Thai
10029 => 'MACCENTRALEUROPE', // Macintosh Central Europe
10029 => ['MACCENTRALEUROPE', 'MAC-CENTRALEUROPE'], // Macintosh Central Europe
10079 => 'MACICELAND', // Macintosh Icelandic
10081 => 'MACTURKISH', // Macintosh Turkish
10082 => 'MACCROATIAN', // Macintosh Croatian
@ -65,6 +66,7 @@ class CodePage
//32769 => 'unsupported', // ANSI Latin I (BIFF2-BIFF3)
65000 => 'UTF-7', // Unicode (UTF-7)
65001 => 'UTF-8', // Unicode (UTF-8)
99999 => ['unsupported'], // Unicode (UTF-8)
];
public static function validate(string $codePage): bool
@ -83,7 +85,20 @@ class CodePage
public static function numberToName(int $codePage): string
{
if (array_key_exists($codePage, self::$pageArray)) {
return self::$pageArray[$codePage];
$value = self::$pageArray[$codePage];
if (is_array($value)) {
foreach ($value as $encoding) {
if (@iconv('UTF-8', $encoding, ' ') !== false) {
self::$pageArray[$codePage] = $encoding;
return $encoding;
}
}
throw new PhpSpreadsheetException("Code page $codePage not implemented on this system.");
} else {
return $value;
}
}
if ($codePage == 720 || $codePage == 32769) {
throw new PhpSpreadsheetException("Code page $codePage not supported."); // OEM Arabic

47
tests/PhpSpreadsheetTests/Reader/XlsTest.php → tests/PhpSpreadsheetTests/Reader/Xls/XlsTest.php
View File

@ -1,8 +1,10 @@
<?php
namespace PhpOffice\PhpSpreadsheetTests\Reader;
namespace PhpOffice\PhpSpreadsheetTests\Reader\Xls;
use PhpOffice\PhpSpreadsheet\Cell\Cell;
use PhpOffice\PhpSpreadsheet\Reader\Xls;
use PhpOffice\PhpSpreadsheet\Shared\CodePage;
use PhpOffice\PhpSpreadsheetTests\Functional\AbstractFunctional;
class XlsTest extends AbstractFunctional
@ -16,6 +18,7 @@ class XlsTest extends AbstractFunctional
$reader = new Xls();
$spreadsheet = $reader->load($filename);
self::assertEquals('Title', $spreadsheet->getSheet(0)->getCell('A1')->getValue());
$spreadsheet->disconnectWorksheets();
}
/**
@ -42,6 +45,8 @@ class XlsTest extends AbstractFunctional
self::assertEquals($row, $newrow);
self::assertEquals($sheet->getCell('A1')->getFormattedValue(), $newsheet->getCell('A1')->getFormattedValue());
self::assertEquals($sheet->getCell("$col$row")->getFormattedValue(), $newsheet->getCell("$col$row")->getFormattedValue());
$spreadsheet->disconnectWorksheets();
$newspreadsheet->disconnectWorksheets();
}
/**
@ -71,11 +76,49 @@ class XlsTest extends AbstractFunctional
$rowIterator = $sheet->getRowIterator();
foreach ($rowIterator as $row) {
foreach ($row->getCellIterator() as $cell) {
foreach ($row->getCellIterator() as $cellx) {
/** @var Cell */
$cell = $cellx;
$valOld = $cell->getFormattedValue();
$valNew = $newsheet->getCell($cell->getCoordinate())->getFormattedValue();
self::assertEquals($valOld, $valNew);
}
}
$spreadsheet->disconnectWorksheets();
$newspreadsheet->disconnectWorksheets();
}
/**
* Test load Xls file with MACCENTRALEUROPE encoding, which is implemented
* as MAC-CENTRALEUROPE on some systems. Issue #549.
*/
public function testLoadMacCentralEurope(): void
{
$codePages = CodePage::getEncodings();
self::assertIsArray($codePages[10029]);
$filename = 'tests/data/Reader/XLS/maccentraleurope.xls';
$reader = new Xls();
// When no fix applied, spreadsheet fails to load on some systems
$spreadsheet = $reader->load($filename);
$sheet = $spreadsheet->getActiveSheet();
self::assertSame('Ładowność', $sheet->getCell('I1')->getValue());
$spreadsheet->disconnectWorksheets();
}
/**
* First test changes array entry in CodePage.
* This test confirms new that new entry is okay.
*/
public function testLoadMacCentralEurope2(): void
{
$codePages = CodePage::getEncodings();
self::assertIsString($codePages[10029]);
$filename = 'tests/data/Reader/XLS/maccentraleurope.xls';
$reader = new Xls();
// When no fix applied, spreadsheet fails to load on some systems
$spreadsheet = $reader->load($filename);
$sheet = $spreadsheet->getActiveSheet();
self::assertSame('Ładowność', $sheet->getCell('I1')->getValue());
$spreadsheet->disconnectWorksheets();
}
}

9
tests/PhpSpreadsheetTests/Shared/CodePageTest.php
View File

@ -16,8 +16,15 @@ class CodePageTest extends TestCase
*/
public function testCodePageNumberToName($expectedResult, $codePageIndex): void
{
if ($expectedResult === 'exception') {
$this->expectException(Exception::class);
}
$result = CodePage::numberToName($codePageIndex);
self::assertEquals($expectedResult, $result);
if (is_array($expectedResult)) {
self::assertContains($result, $expectedResult);
} else {
self::assertEquals($expectedResult, $result);
}
}
public function providerCodePage(): array

BIN
tests/data/Reader/XLS/maccentraleurope.xls Normal file
View File

Binary file not shown.

7
tests/data/Shared/CodePage.php
View File

@ -233,7 +233,7 @@ return [
],
// Macintosh Central Europe
[
'MACCENTRALEUROPE',
['MACCENTRALEUROPE', 'MAC-CENTRALEUROPE'],
10029,
],
// Macintosh Icelandic
@ -271,4 +271,9 @@ return [
'UTF-8',
65001,
],
// invalid
[
'exception',
99999,
],
];