feature #18294 [Yaml] dump non UTF-8 encoded strings as binary data (xabbuh)

fabpot · fabpot · commit 06eb52cb7576 · 2016-03-30T16:44:34.000+02:00
This PR was merged into the 3.1-dev branch. Discussion ---------- [Yaml] dump non UTF-8 encoded strings as binary data | Q | A | ------------- | --- | Branch? | master | Bug fix? | yes | New feature? | no | BC breaks? | no | Deprecations? | yes | Tests pass? | yes | Fixed tickets | #18241 | License | MIT | Doc PR | Commits ------- 86e4a6f dump non UTF-8 encoded strings as binary data
diff --git a/src/Symfony/Component/Yaml/CHANGELOG.md b/src/Symfony/Component/Yaml/CHANGELOG.md
@@ -4,14 +4,14 @@ CHANGELOG
 3.1.0
 -----
 
+ * Strings that are not UTF-8 encoded will be dumped as base64 encoded binary
+   data.
+
  * Added support for dumping multi line strings as literal blocks.
 
  * Added support for parsing base64 encoded binary data when they are tagged
    with the `!!binary` tag.
 
- * Added support for dumping binary data as base64 encoded strings by passing
-   the `Yaml::DUMP_BASE64_BINARY_DATA` flag.
-
  * Added support for parsing timestamps as `\DateTime` objects:
 
    ```php
diff --git a/src/Symfony/Component/Yaml/Inline.php b/src/Symfony/Component/Yaml/Inline.php
@@ -201,7 +201,7 @@ public static function dump($value, $flags = 0)
                 return $repr;
             case '' == $value:
                 return "''";
-            case Yaml::DUMP_BASE64_BINARY_DATA & $flags && self::isBinaryString($value):
+            case self::isBinaryString($value):
                 return '!!binary '.base64_encode($value);
             case Escaper::requiresDoubleQuoting($value):
                 return Escaper::escapeWithDoubleQuotes($value);
@@ -627,7 +627,7 @@ public static function evaluateBinaryScalar($scalar)
 
     private static function isBinaryString($value)
     {
-        return preg_match('/[^\x09-\x0d\x20-\xff]/', $value);
+        return !preg_match('//u', $value) || preg_match('/[^\x09-\x0d\x20-\xff]/', $value);
     }
 
     /**
diff --git a/src/Symfony/Component/Yaml/Tests/DumperTest.php b/src/Symfony/Component/Yaml/Tests/DumperTest.php
@@ -277,20 +277,18 @@ public function getEscapeSequences()
         );
     }
 
-    public function testBinaryDataIsDumpedAsIsWithoutFlag()
+    public function testBinaryDataIsDumpedBase64Encoded()
     {
         $binaryData = file_get_contents(__DIR__.'/Fixtures/arrow.gif');
-        $expected = "{ data: '".str_replace("'", "''", $binaryData)."' }";
+        $expected = '{ data: !!binary '.base64_encode($binaryData).' }';
 
         $this->assertSame($expected, $this->dumper->dump(array('data' => $binaryData)));
     }
 
-    public function testBinaryDataIsDumpedBase64EncodedWithFlag()
+    public function testNonUtf8DataIsDumpedBase64Encoded()
     {
-        $binaryData = file_get_contents(__DIR__.'/Fixtures/arrow.gif');
-        $expected = '{ data: !!binary '.base64_encode($binaryData).' }';
-
-        $this->assertSame($expected, $this->dumper->dump(array('data' => $binaryData), 0, 0, Yaml::DUMP_BASE64_BINARY_DATA));
+        // "für" (ISO-8859-1 encoded)
+        $this->assertSame('!!binary ZsM/cg==', $this->dumper->dump("f\xc3\x3fr"));
     }
 
     /**
diff --git a/src/Symfony/Component/Yaml/Yaml.php b/src/Symfony/Component/Yaml/Yaml.php
@@ -26,9 +26,8 @@ class Yaml
     const PARSE_OBJECT_FOR_MAP = 8;
     const DUMP_EXCEPTION_ON_INVALID_TYPE = 16;
     const PARSE_DATETIME = 32;
-    const DUMP_BASE64_BINARY_DATA = 64;
-    const DUMP_OBJECT_AS_MAP = 128;
-    const DUMP_MULTI_LINE_LITERAL_BLOCK = 256;
+    const DUMP_OBJECT_AS_MAP = 64;
+    const DUMP_MULTI_LINE_LITERAL_BLOCK = 128;
 
     /**
      * Parses YAML into a PHP value.

Original file line number	Diff line number	Diff line change
`@@ -277,20 +277,18 @@ public function getEscapeSequences()`
`277`	`277`	`);`
`278`	`278`	`}`
`279`	`279`
`280`		`- public function testBinaryDataIsDumpedAsIsWithoutFlag()`
	`280`	`+ public function testBinaryDataIsDumpedBase64Encoded()`
`281`	`281`	`{`
`282`	`282`	`$binaryData = file_get_contents(__DIR__.'/Fixtures/arrow.gif');`
`283`		`- $expected = "{ data: '".str_replace("'", "''", $binaryData)."' }";`
	`283`	`+ $expected = '{ data: !!binary '.base64_encode($binaryData).' }';`
`284`	`284`
`285`	`285`	`$this->assertSame($expected, $this->dumper->dump(array('data' => $binaryData)));`
`286`	`286`	`}`
`287`	`287`
`288`		`- public function testBinaryDataIsDumpedBase64EncodedWithFlag()`
	`288`	`+ public function testNonUtf8DataIsDumpedBase64Encoded()`
`289`	`289`	`{`
`290`		`- $binaryData = file_get_contents(__DIR__.'/Fixtures/arrow.gif');`
`291`		`- $expected = '{ data: !!binary '.base64_encode($binaryData).' }';`
`292`		`-`
`293`		`- $this->assertSame($expected, $this->dumper->dump(array('data' => $binaryData), 0, 0, Yaml::DUMP_BASE64_BINARY_DATA));`
	`290`	`+ // "für" (ISO-8859-1 encoded)`
	`291`	`+ $this->assertSame('!!binary ZsM/cg==', $this->dumper->dump("f\xc3\x3fr"));`
`294`	`292`	`}`
`295`	`293`
`296`	`294`	`/**`