Format::guessFormat is a bit more precise from now on (for rdf/xml + …

…turtle)
sweetrdf · Apr 3, 2024 · ac378cc · ac378cc
1 parent a5c3c97
commit ac378cc
Show file tree

Hide file tree

Showing 2 changed files with 25 additions and 1 deletion.
diff --git a/lib/Format.php b/lib/Format.php
@@ -269,6 +269,8 @@ public static function guessFormat($data, $filename = null)
             return self::getFormat('json');
         } elseif (preg_match('/<rdf:/i', $short)) {
             return self::getFormat('rdfxml');
+        } elseif (str_contains($short, '<Ontology xmlns=')) {
+            return self::getFormat('rdfxml');
         } elseif (preg_match('|http://www.w3.org/2005/sparql-results|', $short)) {
             return self::getFormat('sparql-xml');
         } elseif (preg_match('/\WRDFa\W/i', $short)) {
@@ -278,7 +280,11 @@ public static function guessFormat($data, $filename = null)
             return self::getFormat('rdfa');
         } elseif (preg_match('/@prefix\s|@base\s/', $short)) {
             return self::getFormat('turtle');
-        } elseif (preg_match('/prefix\s|base\s/i', $short)) {
+        } elseif (
+            preg_match('/prefix\s|base\s/i', $short)
+            // see FormatTest::testGuessFormatTurtleByPrefix for an example
+            && false === str_contains($short, '<?xml')
+        ) {
             return self::getFormat('turtle');
         } elseif (preg_match('/^\s*<.+> <.+>/m', $short)) {
             return self::getFormat('ntriples');

diff --git a/tests/EasyRdf/FormatTest.php b/tests/EasyRdf/FormatTest.php
@@ -665,6 +665,24 @@ public function testGuessFormatXml()
         $this->assertStringEquals('', $format);
     }
 
+    /**
+     * Case with regex
+     *
+     *      /prefix\s|base\s/i
+     *
+     * was not precise enough and lead to (avoidable) wrong guesses.
+     */
+    public function testGuessFormatTurtleByPrefix()
+    {
+        $data = '<?xml version="1.0"?>
+        <Ontology xmlns="http://www.w3.org/2002/07/owl#"
+             xml:base="http://www.semanticweb.org/hsiehjulien/ontologies/2016/3/untitled-ontology-4"
+             ontologyIRI="http://www.semanticweb.org/hsiehjulien/ontologies/2016/3/untitled-ontology-4">
+            <Prefix name="" IRI="http://www.semanticweb.org/hsiehjulien/ontologies/2016/3/untitled-ontology-4#"/>
+            <Prefix name="owl" IRI="http://www.w3.org/2002/07/owl#"/>';
+        $this->assertStringEquals('rdfxml', Format::guessFormat($data));
+    }
+
     public function testGuessFormatByFilenameTtl()
     {
         $format = Format::guessFormat(