added support for baseUri usage; refined README.md

create the Parser instance using:

> new Parser(new DataFactory(), $baseUri);

to tell it to use $baseUri instead of a random string

Author: k00ni

README.md

@@ -71,7 +71,6 @@ foreach ($quadsIterator as $quad ) {
 
 When using this class keep the following in mind:
 
-* Even though output buffering is used, `exec` keeps leaking output in the terminal (maybe in the browser too?). It is shown at least in PHPUnit tests.
 * The `Parser` class is basically a wrapper around the `rapper` command, which means input must be prepared for further processing (may impact performance). A readable local file as source is needed as well as a local file for generated N-Quads output, which is used for the internal NQuads parser later on.
 
 ## License

src/Parser.php

@@ -30,6 +30,8 @@
  */
 class Parser implements ParserInterface
 {
+    private string|null $baseUri = null;
+
     private DataFactoryInterface $dataFactory;
 
     /**
@@ -51,8 +53,9 @@ class Parser implements ParserInterface
      * @throws \Error
      * @throws \Exception
      */
-    public function __construct(DataFactoryInterface $dataFactory)
+    public function __construct(DataFactoryInterface $dataFactory, string|null $baseUri = null)
     {
+        $this->baseUri = $baseUri;
         $this->dataFactory = $dataFactory;
 
         $tempDir = sys_get_temp_dir();
@@ -78,6 +81,8 @@ public function __destruct()
     }
 
     /**
+     * Tells the parser to not guess the format, but to use the given one.
+     *
      * @throws \ValueError
      */
     public function setFormat(string|null $format): void
@@ -192,7 +197,8 @@ public function parse($input): QuadIteratorInterface
         RapperCommand::parseSourceFileAndPutGeneratedRdfIntoTargetFile(
             $sourceFilePath,
             $targetFilepath,
-            $this->format
+            $this->format,
+            $this->baseUri
         );
 
         // create NQuads parser to parse generated target file

src/RapperCommand.php

@@ -130,12 +130,24 @@ public static function rapperCommandIsAvailable(): bool
     public static function parseSourceFileAndPutGeneratedRdfIntoTargetFile(
         string $sourceFilepath,
         string $targetFilepath,
-        string|null $sourceFileFormat = null
+        string|null $sourceFileFormat = null,
+        string|null $baseUri = null
     ): void {
         $normalizedFormat = self::getNormalizedFormat($sourceFileFormat);
 
         if (file_exists($sourceFilepath) && file_exists($targetFilepath)) {
-            $command = 'rapper --quiet '.$normalizedFormat.' -o ntriples '.$sourceFilepath.' > '.$targetFilepath;
+            // build command string
+            $command = 'rapper --quiet --ignore-errors ';
+
+            if (is_string($baseUri) && 0 < strlen($baseUri)) {
+                $command .= ' --input-uri '.$baseUri.' ';
+            }
+
+            $command .= $normalizedFormat.' -o ntriples '.$sourceFilepath.' > '.$targetFilepath;
+
+            // note: using escapeshellcmd here would escape the > in the command which breaks the whole thing
+
+            // run the command
             exec($command);
         } else {
             throw new RdfIoException('Either source or target filepath points to a non existing file');

tests/ParserTest.php

@@ -32,9 +32,9 @@ public function setUp(): void
         }
     }
 
-    private function getSubjectUnderTest(): Parser
+    private function getSubjectUnderTest(string|null $baseUri): Parser
     {
-        $subjectUnderTest = new Parser(new DataFactory());
+        $subjectUnderTest = new Parser(new DataFactory(), $baseUri);
         $subjectUnderTest->setDirPathForTemporaryFiles(__DIR__.'/../.cache');
         return $subjectUnderTest;
     }
@@ -55,22 +55,41 @@ private function generateTripleStringArray(QuadIteratorInterface $iterator): arr
 
     public function testParseString(): void
     {
-        $iterator = $this->getSubjectUnderTest()->parse($this->testRdfString);
+        $iterator = $this->getSubjectUnderTest(null)->parse($this->testRdfString);
 
         $this->assertEquals(
             ['http://bar http://baz 1', 'http://bar http://baz 2'],
             $this->generateTripleStringArray($iterator)
         );
     }
 
+    public function testParseStringWithBaseUri(): void
+    {
+        $str = '@prefix : <http://example.org/prefix/> .
+        @prefix rdf: <http://example.org/rdf/> .
+
+        <name> rdf:type rdf:Property .
+        :phone rdf:type rdf:Property .';
+
+        $iterator = $this->getSubjectUnderTest('http://test/base/')->parse($str);
+
+        $this->assertEquals(
+            [
+                'http://test/base/name http://example.org/rdf/type http://example.org/rdf/Property',
+                'http://example.org/prefix/phone http://example.org/rdf/type http://example.org/rdf/Property',
+            ],
+            $this->generateTripleStringArray($iterator)
+        );
+    }
+
     public function testParseResource(): void
     {
         // put test RDF into a temp. file
         $filepath = tempnam(sys_get_temp_dir(), 'phpunit_parsertest_');
         file_put_contents($filepath, $this->testRdfString);
         $resource = fopen($filepath, 'r');
 
-        $iterator = $this->getSubjectUnderTest()->parse($resource);
+        $iterator = $this->getSubjectUnderTest(null)->parse($resource);
 
         $this->assertEquals(
             ['http://bar http://baz 1', 'http://bar http://baz 2'],
@@ -87,7 +106,7 @@ public function testParseResponseInterface(): void
         $response = $this->createMock(ResponseInterface::class);
         $response->method('getBody')->willReturn($stream);
 
-        $iterator = $this->getSubjectUnderTest()->parse($response);
+        $iterator = $this->getSubjectUnderTest(null)->parse($response);
 
         $this->assertEquals(
             ['http://bar http://baz 1', 'http://bar http://baz 2'],
@@ -100,7 +119,7 @@ public function testParseStreamInterface(): void
         $stream = $this->createMock(StreamInterface::class);
         $stream->method('__toString')->willReturn($this->testRdfString);
 
-        $iterator = $this->getSubjectUnderTest()->parse($stream);
+        $iterator = $this->getSubjectUnderTest(null)->parse($stream);
 
         $this->assertEquals(
             ['http://bar http://baz 1', 'http://bar http://baz 2'],
@@ -110,7 +129,7 @@ public function testParseStreamInterface(): void
 
     public function testParseWithCustomFormat(): void
     {
-        $subjectUnderTest = $this->getSubjectUnderTest();
+        $subjectUnderTest = $this->getSubjectUnderTest(null);
         $subjectUnderTest->setFormat('ntriples');
         $iterator = $subjectUnderTest->parse($this->testRdfString);
 
@@ -127,7 +146,7 @@ public function testParseWithInvalidFormat(): void
         $msg .= 'ntriples, n-triples, rdfa, rdfxml, rdfxml-abbrev, rdfxml-xmp, rss-1.0, trig, turtle, text/turtle, ttl, xml';
         $this->expectExceptionMessage($msg);
 
-        $subjectUnderTest = $this->getSubjectUnderTest();
+        $subjectUnderTest = $this->getSubjectUnderTest(null);
         $subjectUnderTest->setFormat('invalid');
         $subjectUnderTest->parse($this->testRdfString);
     }
@@ -139,7 +158,7 @@ public function testParseStreamResource(): void
         file_put_contents($filepath, $this->testRdfString);
         $resource = fopen($filepath, 'r');
 
-        $iterator = $this->getSubjectUnderTest()->parseStream($resource);
+        $iterator = $this->getSubjectUnderTest(null)->parseStream($resource);
 
         $this->assertEquals(
             ['http://bar http://baz 1', 'http://bar http://baz 2'],
@@ -152,7 +171,7 @@ public function testParseStreamStreamInterface(): void
         $stream = $this->createMock(StreamInterface::class);
         $stream->method('__toString')->willReturn($this->testRdfString);
 
-        $iterator = $this->getSubjectUnderTest()->parseStream($stream);
+        $iterator = $this->getSubjectUnderTest(null)->parseStream($stream);
 
         $this->assertEquals(
             ['http://bar http://baz 1', 'http://bar http://baz 2'],