Merge pull request #667 from GoogleCloudPlatform/language-encoding-test

Adds test for encoded characters.

Author: gguuss

language/analysis/src/main/java/com/google/cloud/language/samples/Analyze.java

@@ -138,7 +138,7 @@ public static void printSyntax(PrintStream out, List<Token> tokens) {
  out.printf("\tBeginOffset: %d\n", token.getText().getBeginOffset());
  out.printf("Lemma: %s\n", token.getLemma());
  out.printf("PartOfSpeechTag: %s\n", token.getPartOfSpeech().getTag());
- out.printf("\tAspect: %s\n",token.getPartOfSpeech().getAspect());
+ out.printf("\tAspect: %s\n", token.getPartOfSpeech().getAspect());
  out.printf("\tCase: %s\n", token.getPartOfSpeech().getCase());
  out.printf("\tForm: %s\n", token.getPartOfSpeech().getForm());
  out.printf("\tGender: %s\n",token.getPartOfSpeech().getGender());

language/analysis/src/test/java/com/google/cloud/language/samples/AnalyzeBetaIT.java

@@ -20,6 +20,7 @@
 
 import com.google.cloud.language.spi.v1beta2.LanguageServiceClient;
 import com.google.cloud.language.v1beta2.Entity;
+import com.google.cloud.language.v1beta2.EntityMention;
 import com.google.cloud.language.v1beta2.Sentiment;
 
 import org.junit.Before;
@@ -66,6 +67,15 @@ public class AnalyzeBetaIT {
  assertThat(got).named("entity names").contains("Seattle");
  }
 
+ @Test public void analyzeSyntax_entitySentimentTextEncoded() throws Exception {
+ List<Entity> entities = analyzeApp.entitySentimentText("foo→bar");
+
+ List<EntityMention> mentions = entities.listIterator().next().getMentionsList();
+
+ // Assert
+ assertThat(mentions.get(0).getText().getBeginOffset() == 4);
+ }
+
  @Test public void analyzeSyntax_entitySentimentFile() throws Exception {
  List<Entity> entities =
  analyzeApp.entitySentimentFile("gs://" + BUCKET + "/natural-language/gettysburg.txt");