Can read very small HTML files

Fixes #194
PHPOffice · Dec 11, 2017 · 962367c · 962367c
1 parent dfcab0c
commit 962367c
Show file tree

Hide file tree

Showing 3 changed files with 39 additions and 2 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -13,6 +13,8 @@ and this project adheres to [Semantic Versioning](http://semver.org/).
 
 ### Fixed
 
+- Can read very small HTML files - [#194](https://github.com/PHPOffice/PhpSpreadsheet/issues/194)
+
 ## [1.0.0-beta2] - 2017-11-26
 
 ### Added

diff --git a/src/PhpSpreadsheet/Reader/Html.php b/src/PhpSpreadsheet/Reader/Html.php
@@ -112,8 +112,6 @@ public function __construct()
      *
      * @param string $pFilename
      *
-     * @throws Exception
-     *
      * @return bool
      */
     public function canRead($pFilename)
@@ -148,7 +146,14 @@ private function readEnding()
         $filename = $meta['uri'];
 
         $size = filesize($filename);
+        if ($size === 0) {
+            return '';
+        }
+
         $blockSize = self::TEST_SAMPLE_SIZE;
+        if ($size < $blockSize) {
+            $blockSize = $size;
+        }
 
         fseek($this->fileHandle, $size - $blockSize);
 

diff --git a/tests/PhpSpreadsheetTests/Reader/HtmlTest.php b/tests/PhpSpreadsheetTests/Reader/HtmlTest.php
@@ -13,4 +13,34 @@ public function testCsvWithAngleBracket()
         $reader = new Html();
         self::assertFalse($reader->canRead($filename));
     }
+
+    public function providerCanReadVerySmallFile()
+    {
+        $padding = str_repeat('a', 2048);
+
+        return [
+            [true, ' <html> ' . $padding . ' </html> '],
+            [true, ' <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd"> <html>' . $padding . '</html>'],
+            [true, '<html></html>'],
+            [false, ''],
+        ];
+    }
+
+    /**
+     * @dataProvider providerCanReadVerySmallFile
+     *
+     * @param bool $expected
+     * @param string $content
+     */
+    public function testCanReadVerySmallFile($expected, $content)
+    {
+        $filename = tempnam(sys_get_temp_dir(), 'html');
+        file_put_contents($filename, $content);
+
+        $reader = new Html();
+        $actual = $reader->canRead($filename);
+        unlink($filename);
+
+        self::assertSame($expected, $actual);
+    }
 }