[Core] Delegate encoding and BOM handling to gherkin

CHANGELOG.md

@@ -11,6 +11,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+### Changed
+- [Core] Update dependency io.cucumber:gherkin to v24.1
+- [Core] Delegate encoding and BOM handling to gherkin ([2624](https://github.com/cucumber/cucumber-jvm/issues/2624) M.P. Korstanje)
+
 ## [7.8.1] - 2022-10-03
 ### Fixed
 - [Core] Remove Jackson services from `META-INF/services` ([#2621](https://github.com/cucumber/cucumber-jvm/issues/2621) M.P. Korstanje)

cucumber-core/src/main/java/io/cucumber/core/feature/FeatureParser.java

@@ -1,8 +1,11 @@
 package io.cucumber.core.feature;
 
 import io.cucumber.core.gherkin.Feature;
+import io.cucumber.core.gherkin.FeatureParserException;
 import io.cucumber.core.resource.Resource;
 
+import java.io.IOException;
+import java.io.InputStream;
 import java.net.URI;
 import java.util.ArrayList;
 import java.util.Collections;
@@ -19,8 +22,6 @@
 
 public final class FeatureParser {
 
-    private final EncodingParser encodingParser = new EncodingParser();
-
     private final Supplier<UUID> idGenerator;
 
     public FeatureParser(Supplier<UUID> idGenerator) {
@@ -31,8 +32,6 @@ public Optional<Feature> parseResource(Resource resource) {
         requireNonNull(resource);
         URI uri = resource.getUri();
 
-        String source = encodingParser.parse(resource);
-
         ServiceLoader<io.cucumber.core.gherkin.FeatureParser> services = ServiceLoader
                 .load(io.cucumber.core.gherkin.FeatureParser.class);
         Iterator<io.cucumber.core.gherkin.FeatureParser> iterator = services.iterator();
@@ -42,7 +41,13 @@ public Optional<Feature> parseResource(Resource resource) {
         }
         Comparator<io.cucumber.core.gherkin.FeatureParser> version = comparing(
             io.cucumber.core.gherkin.FeatureParser::version);
-        return Collections.max(parser, version).parse(uri, source, idGenerator);
+
+        try (InputStream source = resource.getInputStream()) {
+            return Collections.max(parser, version).parse(uri, source, idGenerator);
+
+        } catch (IOException e) {
+            throw new FeatureParserException("Failed to parse resource at: " + uri, e);
+        }
     }
 
 }

cucumber-gherkin-messages/pom.xml

@@ -49,7 +49,6 @@
         <dependency>
             <groupId>org.junit.jupiter</groupId>
             <artifactId>junit-jupiter</artifactId>
-            <version>${junit-jupiter.version}</version>
             <scope>test</scope>
         </dependency>
 

cucumber-gherkin-messages/src/main/java/io/cucumber/core/gherkin/messages/GherkinMessagesFeatureParser.java

@@ -12,23 +12,36 @@
 import io.cucumber.messages.types.ParseError;
 import io.cucumber.messages.types.Source;
 
+import java.io.ByteArrayInputStream;
+import java.io.IOException;
+import java.io.InputStream;
 import java.net.URI;
 import java.util.List;
 import java.util.Optional;
 import java.util.UUID;
 import java.util.function.Supplier;
 
-import static io.cucumber.messages.types.SourceMediaType.TEXT_X_CUCUMBER_GHERKIN_PLAIN;
+import static java.nio.charset.StandardCharsets.UTF_8;
 import static java.util.stream.Collectors.toList;
 
 public final class GherkinMessagesFeatureParser implements FeatureParser {
 
+    @Deprecated
     @Override
     public Optional<Feature> parse(URI path, String source, Supplier<UUID> idGenerator) {
+        try (InputStream is = new ByteArrayInputStream(source.getBytes(UTF_8))) {
+            return parse(path, is, idGenerator);
+        } catch (IOException e) {
+            throw new FeatureParserException("Failed to parse resource at: " + path, e);
+        }
+    }
+
+    @Override
+    public Optional<Feature> parse(URI path, InputStream source, Supplier<UUID> idGenerator) throws IOException {
         List<Envelope> envelopes = GherkinParser.builder()
                 .idGenerator(() -> idGenerator.get().toString())
                 .build()
-                .parse(Envelope.of(new Source(path.toString(), source, TEXT_X_CUCUMBER_GHERKIN_PLAIN)))
+                .parse(path.toString(), source)
                 .collect(toList());
 
         List<String> errors = envelopes.stream()
@@ -70,10 +83,17 @@ public Optional<Feature> parse(URI path, String source, Supplier<UUID> idGenerat
                             .map(pickle -> new GherkinMessagesPickle(pickle, path, dialect, cucumberQuery))
                             .collect(toList());
 
+                    Source sourceMessage = envelopes.stream()
+                            .map(Envelope::getSource)
+                            .filter(Optional::isPresent)
+                            .map(Optional::get)
+                            .findFirst()
+                            .orElseThrow(() -> new IllegalStateException("source message was not emitted by parser"));
+
                     return new GherkinMessagesFeature(
                         feature,
                         path,
-                        source,
+                        sourceMessage.getData(),
                         pickles,
                         envelopes);
                 });