feature #48022 [Yaml] Fix Yaml Parser with quote end in a new line (maxbeckers)

fabpot · fabpot · commit 40a2cfbbebfa · 2024-02-03T18:57:49.000+01:00
This PR was submitted for the 5.4 branch but it was merged into the 7.1 branch instead. Discussion ---------- [Yaml] Fix Yaml Parser with quote end in a new line | Q | A | ------------- | --- | Branch? | 5.4 | Bug fix? | yes | New feature? | no | Deprecations? | no | Tickets | Fix #33082 | License | MIT | Doc PR | N/A This is a fix for issue #33082. The bug described in the ticket breaks on a ending quote in a new line: ``` foo: bar: 'baz ' baz: 'Lorem' ``` Before the fix: `Symfony\Component\Yaml\Exception\ParseException: Malformed inline YAML string: 'baz at line 4.` There was already a PR #33119, which was closed because of problems. Commits ------- 21cec3f [Yaml] Fix Yaml Parser with quote end in a new line
diff --git a/src/Symfony/Component/Yaml/Parser.php b/src/Symfony/Component/Yaml/Parser.php
@@ -597,8 +597,12 @@ private function getNextEmbedBlock(?int $indentation = null, bool $inSequence =
         }
 
         $data = [];
+        $isInMultiLineQuote = false;
 
         if ($this->getCurrentLineIndentation() >= $newIndent) {
+            if ($this->isCurrentLineMultiLineQuoteStart()) {
+                $isInMultiLineQuote = true;
+            }
             $data[] = substr($this->currentLine, $newIndent ?? 0);
         } elseif ($this->isCurrentLineEmpty() || $this->isCurrentLineComment()) {
             $data[] = $this->currentLine;
@@ -635,6 +639,16 @@ private function getNextEmbedBlock(?int $indentation = null, bool $inSequence =
             if ($this->isCurrentLineBlank()) {
                 $data[] = substr($this->currentLine, $newIndent);
                 continue;
+            } elseif (!$isInMultiLineQuote && $this->isCurrentLineMultiLineQuoteStart()) {
+                $isInMultiLineQuote = true;
+                $data[] = substr($this->currentLine, $newIndent);
+                continue;
+            } elseif ($isInMultiLineQuote) {
+                $data[] = $this->currentLine;
+                if ("'" === (rtrim($this->currentLine)[-1] ?? '')) {
+                    $isInMultiLineQuote = false;
+                }
+                continue;
             }
 
             if ($indent >= $newIndent) {
@@ -965,6 +979,49 @@ private function isCurrentLineLastLineInDocument(): bool
         return ($this->offset + $this->currentLineNb) >= ($this->totalNumberOfLines - 1);
     }
 
+    /**
+     * Returns true if the current line is the beginning of a multiline quoted block.
+     */
+    private function isCurrentLineMultiLineQuoteStart(): bool
+    {
+        $trimmedLine = trim($this->currentLine);
+        $trimmedLineLength = \strlen($trimmedLine);
+        $quoteCount = 0;
+        $value = '';
+        // check if the key is quoted
+        for ($i = 0; $i < $trimmedLineLength; ++$i) {
+            $char = $trimmedLine[$i];
+            if ("'" === $char) {
+                ++$quoteCount;
+            } elseif (':' === $char && 0 === $quoteCount % 2 && ($i === $trimmedLineLength - 1 || ' ' === $trimmedLine[$i + 1])) {
+                // key and value are separated by the first colon after the (quoted) key followed by a space or linebreak
+                $value = trim(substr($trimmedLine, ++$i), ' ');
+                break;
+            }
+        }
+
+        if (0 !== strpos($value, "'")) {
+            return false;
+        }
+
+        $lineEndQuoteCount = 0;
+        for ($i = \strlen($value) - 1; $i > 0; --$i) {
+            $char = $value[$i];
+            if ("'" === $char) {
+                ++$lineEndQuoteCount;
+            } else {
+                break;
+            }
+        }
+
+        return 0 === $lineEndQuoteCount % 2;
+    }
+
+    /**
+     * Cleanups a YAML string to be parsed.
+     *
+     * @param string $value The input YAML string
+     */
     private function cleanup(string $value): string
     {
         $value = str_replace(["\r\n", "\r"], "\n", $value);
diff --git a/src/Symfony/Component/Yaml/Tests/YamlTest.php b/src/Symfony/Component/Yaml/Tests/YamlTest.php
@@ -12,6 +12,7 @@
 namespace Symfony\Component\Yaml\Tests;
 
 use PHPUnit\Framework\TestCase;
+use Symfony\Component\Yaml\Exception\ParseException;
 use Symfony\Component\Yaml\Yaml;
 
 class YamlTest extends TestCase
@@ -24,6 +25,56 @@ public function testParseAndDump()
         $this->assertEquals($data, $parsed);
     }
 
+    public function testParseWithMultilineQuotes()
+    {
+        $yaml = <<<YAML
+foo:
+  bar: 'baz
+biz
+
+'
+  baz: 'Lorem
+
+       ipsum'
+  error: Une erreur s'est produite.
+  trialMode: 'période d''essai'
+  double_line: 'Les utilisateurs sélectionnés
+n''ont pas d''email.
+
+'
+  a: 'b''
+c'
+  empty: ''
+  foo:bar: 'foobar'
+YAML;
+
+        $this->assertSame(['foo' => [
+            'bar' => "baz biz\n",
+            'baz' => "Lorem\nipsum",
+            'error' => "Une erreur s'est produite.",
+            'trialMode' => "période d'essai",
+            'double_line' => "Les utilisateurs sélectionnés n'ont pas d'email.\n",
+            'a' => "b' c",
+            'empty' => '',
+            'foo:bar' => 'foobar',
+        ]], Yaml::parse($yaml));
+    }
+
+    public function testParseWithMultilineQuotesExpectException()
+    {
+        $yaml = <<<YAML
+foo:
+  bar: 'baz
+
+'
+'
+YAML;
+
+        $this->expectException(ParseException::class);
+        $this->expectExceptionMessage('Unable to parse at line 5 (near "\'").');
+        Yaml::parse($yaml);
+    }
+
     public function testZeroIndentationThrowsException()
     {
         $this->expectException(\InvalidArgumentException::class);
