This is an automated email from the ASF dual-hosted git repository.
tilman pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tika.git
The following commit(s) were added to refs/heads/main by this push:
new 091fbfcce TIKA-4435: add amazon bom, add aws v2 dependencies, migrate
to aws v2
091fbfcce is described below
commit 091fbfcce6118bcd4fe101991aeb873b41e2768b
Author: Tilman Hausherr <[email protected]>
AuthorDate: Sun Jun 8 17:00:23 2025 +0200
TIKA-4435: add amazon bom, add aws v2 dependencies, migrate to aws v2
---
tika-parent/pom.xml | 15 ++
.../tika-parsers-ml/tika-transcribe-aws/pom.xml | 43 ++---
.../parser/transcribe/aws/AmazonTranscribe.java | 176 ++++++++++++---------
.../transcribe/aws/AmazonTranscribeTest.java | 22 +--
4 files changed, 147 insertions(+), 109 deletions(-)
diff --git a/tika-parent/pom.xml b/tika-parent/pom.xml
index aa849fa09..03e539e1d 100644
--- a/tika-parent/pom.xml
+++ b/tika-parent/pom.xml
@@ -312,6 +312,7 @@
<!-- change threetenbp exclusion version -->
<google.cloud.version>2.53.0</google.cloud.version>
<aws.version>1.12.783</aws.version> <!-- convergence problems with 785,
wait -->
+ <aws2.version>2.31.56</aws2.version>
<!-- WARNING: when you upgrade asm make sure that you update the
OpCode in the initializer in
org.apache.tika.parser.asm.XHTMLClassVisitor
See TIKA-2992.
@@ -587,6 +588,20 @@
<artifactId>aws-java-sdk-s3</artifactId>
<version>${aws.version}</version>
</dependency>
+ <dependency>
+ <groupId>com.amazonaws</groupId>
+ <artifactId>aws-java-sdk-bom</artifactId>
+ <version>${aws.version}</version>
+ <type>pom</type>
+ <scope>import</scope>
+ </dependency>
+ <dependency>
+ <groupId>software.amazon.awssdk</groupId>
+ <artifactId>bom</artifactId>
+ <version>${aws2.version}</version>
+ <type>pom</type>
+ <scope>import</scope>
+ </dependency>
<dependency>
<groupId>com.azure</groupId>
<artifactId>azure-storage-blob</artifactId>
diff --git a/tika-parsers/tika-parsers-ml/tika-transcribe-aws/pom.xml
b/tika-parsers/tika-parsers-ml/tika-transcribe-aws/pom.xml
index ea7a73569..cefa6b4bf 100644
--- a/tika-parsers/tika-parsers-ml/tika-transcribe-aws/pom.xml
+++ b/tika-parsers/tika-parsers-ml/tika-transcribe-aws/pom.xml
@@ -33,26 +33,27 @@
<name>Apache Tika transcribe aws</name>
<url>http://tika.apache.org/</url>
- <dependencyManagement>
- <dependencies>
- <dependency>
- <groupId>com.amazonaws</groupId>
- <artifactId>aws-java-sdk-swf-libraries</artifactId>
- <version>2.0.0</version>
- </dependency>
- </dependencies>
- </dependencyManagement>
-
<!--TODO use latest aws version or the one defined in the tika-parent-->
<dependencies>
<dependency>
- <groupId>com.amazonaws</groupId>
- <artifactId>aws-java-sdk-transcribe</artifactId>
- <version>${aws.version}</version>
+ <groupId>software.amazon.awssdk</groupId>
+ <artifactId>transcribe</artifactId>
+ <version>${aws2.version}</version>
+ </dependency>
+ <dependency>
+ <groupId>software.amazon.awssdk</groupId>
+ <artifactId>s3</artifactId>
+ <version>${aws2.version}</version>
+ </dependency>
+ <dependency>
+ <groupId>software.amazon.awssdk</groupId>
+ <artifactId>sts</artifactId>
+ <version>${aws2.version}</version>
</dependency>
<dependency>
- <groupId>com.amazonaws</groupId>
- <artifactId>aws-java-sdk-s3</artifactId>
+ <groupId>software.amazon.awssdk</groupId>
+ <artifactId>swf</artifactId>
+ <version>${aws2.version}</version>
</dependency>
<dependency>
<groupId>com.googlecode.json-simple</groupId>
@@ -63,16 +64,6 @@
<artifactId>slf4j-simple</artifactId>
<scope>test</scope>
</dependency>
- <dependency>
- <groupId>com.amazonaws</groupId>
- <artifactId>aws-java-sdk</artifactId>
- <version>${aws.version}</version>
- </dependency>
- <dependency>
- <groupId>com.amazonaws</groupId>
- <artifactId>aws-java-sdk-simpleworkflow</artifactId>
- <version>${aws.version}</version>
- </dependency>
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-databind</artifactId>
@@ -168,4 +159,4 @@
<scm>
<tag>3.0.0-rc1</tag>
</scm>
-</project>
\ No newline at end of file
+</project>
diff --git
a/tika-parsers/tika-parsers-ml/tika-transcribe-aws/src/main/java/org/apache/tika/parser/transcribe/aws/AmazonTranscribe.java
b/tika-parsers/tika-parsers-ml/tika-transcribe-aws/src/main/java/org/apache/tika/parser/transcribe/aws/AmazonTranscribe.java
index db5600232..2d5215cd6 100644
---
a/tika-parsers/tika-parsers-ml/tika-transcribe-aws/src/main/java/org/apache/tika/parser/transcribe/aws/AmazonTranscribe.java
+++
b/tika-parsers/tika-parsers-ml/tika-transcribe-aws/src/main/java/org/apache/tika/parser/transcribe/aws/AmazonTranscribe.java
@@ -25,38 +25,43 @@ import java.util.HashSet;
import java.util.Map;
import java.util.Set;
import java.util.UUID;
+import java.util.concurrent.CompletableFuture;
-import com.amazonaws.AmazonServiceException;
-import com.amazonaws.SdkClientException;
-import com.amazonaws.auth.AWSStaticCredentialsProvider;
-import com.amazonaws.auth.BasicAWSCredentials;
-import com.amazonaws.services.s3.AmazonS3;
-import com.amazonaws.services.s3.AmazonS3ClientBuilder;
-import com.amazonaws.services.s3.model.AmazonS3Exception;
-import com.amazonaws.services.s3.model.GetObjectRequest;
-import com.amazonaws.services.s3.model.PutObjectRequest;
-import com.amazonaws.services.s3.model.PutObjectResult;
-import com.amazonaws.services.s3.model.S3Object;
-import com.amazonaws.services.s3.model.S3ObjectInputStream;
-import com.amazonaws.services.securitytoken.AWSSecurityTokenService;
-import
com.amazonaws.services.securitytoken.AWSSecurityTokenServiceClientBuilder;
-import com.amazonaws.services.securitytoken.model.GetCallerIdentityRequest;
-import com.amazonaws.services.securitytoken.model.GetCallerIdentityResult;
-import com.amazonaws.services.transcribe.AmazonTranscribeAsync;
-import com.amazonaws.services.transcribe.AmazonTranscribeAsyncClientBuilder;
-import com.amazonaws.services.transcribe.model.GetTranscriptionJobRequest;
-import com.amazonaws.services.transcribe.model.GetTranscriptionJobResult;
-import com.amazonaws.services.transcribe.model.LanguageCode;
-import com.amazonaws.services.transcribe.model.Media;
-import com.amazonaws.services.transcribe.model.StartTranscriptionJobRequest;
-import com.amazonaws.services.transcribe.model.TranscriptionJob;
-import com.amazonaws.services.transcribe.model.TranscriptionJobStatus;
import com.fasterxml.jackson.databind.JsonNode;
import com.fasterxml.jackson.databind.ObjectMapper;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
+import software.amazon.awssdk.auth.credentials.AwsBasicCredentials;
+import software.amazon.awssdk.auth.credentials.StaticCredentialsProvider;
+import software.amazon.awssdk.awscore.exception.AwsServiceException;
+import software.amazon.awssdk.core.ResponseInputStream;
+import software.amazon.awssdk.core.exception.SdkClientException;
+import software.amazon.awssdk.core.sync.RequestBody;
+import software.amazon.awssdk.regions.Region;
+import software.amazon.awssdk.services.s3.S3Client;
+import software.amazon.awssdk.services.s3.model.CreateBucketRequest;
+import software.amazon.awssdk.services.s3.model.DeleteObjectRequest;
+import software.amazon.awssdk.services.s3.model.GetObjectRequest;
+import software.amazon.awssdk.services.s3.model.GetObjectResponse;
+import software.amazon.awssdk.services.s3.model.GetUrlRequest;
+import software.amazon.awssdk.services.s3.model.HeadBucketRequest;
+import software.amazon.awssdk.services.s3.model.NoSuchBucketException;
+import software.amazon.awssdk.services.s3.model.PutObjectRequest;
+import software.amazon.awssdk.services.s3.model.PutObjectResponse;
+import software.amazon.awssdk.services.s3.model.S3Exception;
+import software.amazon.awssdk.services.sts.StsClient;
+import software.amazon.awssdk.services.sts.model.GetCallerIdentityRequest;
+import software.amazon.awssdk.services.sts.model.GetCallerIdentityResponse;
+import software.amazon.awssdk.services.transcribe.TranscribeAsyncClient;
+import
software.amazon.awssdk.services.transcribe.model.GetTranscriptionJobRequest;
+import
software.amazon.awssdk.services.transcribe.model.GetTranscriptionJobResponse;
+import software.amazon.awssdk.services.transcribe.model.LanguageCode;
+import software.amazon.awssdk.services.transcribe.model.Media;
+import
software.amazon.awssdk.services.transcribe.model.StartTranscriptionJobRequest;
+import software.amazon.awssdk.services.transcribe.model.TranscriptionJob;
+import software.amazon.awssdk.services.transcribe.model.TranscriptionJobStatus;
import org.apache.tika.config.Field;
import org.apache.tika.config.Initializable;
@@ -85,14 +90,14 @@ import org.apache.tika.sax.XHTMLContentHandler;
public class AmazonTranscribe implements Parser, Initializable {
private static final Logger LOG =
LoggerFactory.getLogger(AmazonTranscribe.class);
- private AmazonTranscribeAsync amazonTranscribeAsync;
- private AmazonS3 amazonS3;
+ private TranscribeAsyncClient amazonTranscribeAsync;
+ private S3Client amazonS3;
private String bucketName;
private String region;
private boolean isAvailable; // Flag for whether or not transcription is
available.
private String clientId; // Access key
private String clientSecret; // Keys used for the API calls.
- private AWSStaticCredentialsProvider credsProvider;
+ private StaticCredentialsProvider credsProvider;
//https://docs.aws.amazon.com/transcribe/latest/dg/input.html
protected static final Set<MediaType> SUPPORTED_TYPES =
Collections.unmodifiableSet(
@@ -138,16 +143,16 @@ public class AmazonTranscribe implements Parser,
Initializable {
LanguageCode languageCode = context.get(LanguageCode.class);
uploadFileToBucket(stream, jobName);
StartTranscriptionJobRequest startTranscriptionJobRequest =
- new StartTranscriptionJobRequest();
- Media media = new Media();
- media.setMediaFileUri(amazonS3.getUrl(bucketName, jobName).toString());
-
startTranscriptionJobRequest.withMedia(media).withOutputBucketName(this.bucketName)
-
.withTranscriptionJobName(jobName).setRequestCredentialsProvider(credsProvider);
+ StartTranscriptionJobRequest.builder()
+ .build();
+ Media media =
Media.builder().mediaFileUri(amazonS3.utilities().getUrl(GetUrlRequest.builder().bucket(bucketName).key(jobName).build()).toString()).build();
+ startTranscriptionJobRequest =
startTranscriptionJobRequest.toBuilder().media(media).outputBucketName(bucketName)
+ .transcriptionJobName(jobName).build();
if (languageCode != null) {
- startTranscriptionJobRequest.withLanguageCode(languageCode);
+ startTranscriptionJobRequest =
startTranscriptionJobRequest.toBuilder().languageCode(languageCode).build();
} else {
- startTranscriptionJobRequest.withIdentifyLanguage(true);
+ startTranscriptionJobRequest =
startTranscriptionJobRequest.toBuilder().identifyLanguage(true).build();
}
amazonTranscribeAsync.startTranscriptionJob(startTranscriptionJobRequest);
XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
@@ -238,19 +243,21 @@ public class AmazonTranscribe implements Parser,
Initializable {
* @param jobName The unique job name for each job(UUID).
*/
private void uploadFileToBucket(InputStream inputStream, String jobName)
throws TikaException {
- PutObjectRequest request =
- new PutObjectRequest(this.bucketName, jobName, inputStream,
null);
+ PutObjectRequest request =
PutObjectRequest.builder().bucket(bucketName).key(jobName).build();
try {
- @SuppressWarnings("unused") PutObjectResult response =
amazonS3.putObject(request);
- } catch (SdkClientException e) {
+ @SuppressWarnings("unused")
+ PutObjectResponse response = amazonS3.putObject(request,
RequestBody.fromInputStream(inputStream, inputStream.available()));
+ } catch (SdkClientException | IOException e) {
throw new TikaException("File upload to AWS failed: " +
e.getMessage(), e);
}
}
private void deleteFilesFromBucket(String jobName) throws TikaException {
try {
- amazonS3.deleteObject(bucketName, jobName);
- amazonS3.deleteObject(bucketName, jobName + ".json");
+
amazonS3.deleteObject(DeleteObjectRequest.builder().bucket(bucketName).key(jobName)
+ .build());
+
amazonS3.deleteObject(DeleteObjectRequest.builder().bucket(bucketName).key(jobName
+ ".json")
+ .build());
} catch (SdkClientException e) {
LOG.error("Failed to delete {} and/or {} from {}", jobName,
jobName + ".json", bucketName, e);
}
@@ -266,19 +273,20 @@ public class AmazonTranscribe implements Parser,
Initializable {
* whilst processing JSON from the AWS S3
SelectObjectContentResult operation.
* @throws SdkClientException a AWS-specific exception related to
SelectObjectContentResult
* operation.
- * @throws AmazonServiceException possibly thrown if there is an issue
selecting object content
+ * @throws AwsServiceException possibly thrown if there is an issue
selecting object content
* from AWS S3 objects.
*/
private String getTranscriptText(String fileNameS3)
- throws AmazonServiceException, SdkClientException, IOException {
+ throws AwsServiceException, SdkClientException, IOException {
TranscriptionJob transcriptionJob =
retrieveObjectWhenJobCompleted(fileNameS3);
String text = "";
- if (transcriptionJob != null && !TranscriptionJobStatus.FAILED.name()
- .equals(transcriptionJob.getTranscriptionJobStatus())) {
- S3Object s3Object = amazonS3.getObject(new
GetObjectRequest(bucketName, fileNameS3 + ".json"));
- try (S3ObjectInputStream objectContent =
s3Object.getObjectContent()) {
+ if (transcriptionJob != null && !TranscriptionJobStatus.FAILED
+ .equals(transcriptionJob.transcriptionJobStatus())) {
+ ResponseInputStream<GetObjectResponse> s3Object =
amazonS3.getObject(GetObjectRequest.builder().bucket(bucketName).key(fileNameS3
+ ".json")
+ .build());
+ try (s3Object) {
ObjectMapper mapper = new ObjectMapper();
- JsonNode root = mapper.readTree(objectContent);
+ JsonNode root = mapper.readTree(s3Object);
text = root
.path("results")
.path("transcripts")
@@ -299,16 +307,22 @@ public class AmazonTranscribe implements Parser,
Initializable {
* @return TranscriptionJob object
*/
private TranscriptionJob retrieveObjectWhenJobCompleted(String jobName) {
- GetTranscriptionJobRequest getTranscriptionJobRequest = new
GetTranscriptionJobRequest();
-
getTranscriptionJobRequest.withRequestCredentialsProvider(credsProvider);
- getTranscriptionJobRequest.setTranscriptionJobName(jobName);
+ GetTranscriptionJobRequest transcriptionJobRequest =
GetTranscriptionJobRequest.builder().transcriptionJobName(jobName).build();
while (true) {
- GetTranscriptionJobResult innerResult =
-
amazonTranscribeAsync.getTranscriptionJob(getTranscriptionJobRequest);
- String status =
innerResult.getTranscriptionJob().getTranscriptionJobStatus();
- if (TranscriptionJobStatus.COMPLETED.name().equals(status) ||
- TranscriptionJobStatus.FAILED.name().equals(status)) {
- return innerResult.getTranscriptionJob();
+ CompletableFuture<GetTranscriptionJobResponse> transcriptionJob =
amazonTranscribeAsync.getTranscriptionJob(transcriptionJobRequest);
+ GetTranscriptionJobResponse transcriptionJobResponse =
transcriptionJob.join();
+ TranscriptionJobStatus status =
transcriptionJobResponse.transcriptionJob().transcriptionJobStatus();
+ if (TranscriptionJobStatus.COMPLETED.equals(status) ||
+ TranscriptionJobStatus.FAILED.equals(status)) {
+ return transcriptionJobResponse.transcriptionJob();
+ }
+ try
+ {
+ Thread.sleep(1000);
+ }
+ catch (InterruptedException ex)
+ {
+ LOG.warn("interrupted");
}
}
}
@@ -320,34 +334,36 @@ public class AmazonTranscribe implements Parser,
Initializable {
}
try {
- BasicAWSCredentials creds = new BasicAWSCredentials(this.clientId,
this.clientSecret);
- this.credsProvider = new AWSStaticCredentialsProvider(creds);
+ AwsBasicCredentials creds =
AwsBasicCredentials.create(this.clientId, this.clientSecret);
+ this.credsProvider = StaticCredentialsProvider.create(creds);
if (region != null) {
- this.amazonS3 =
AmazonS3ClientBuilder.standard().withCredentials(credsProvider)
- .withRegion(this.region).build();
+ this.amazonS3 =
S3Client.builder().credentialsProvider(credsProvider)
+ .region(Region.of(this.region)).build();
} else {
this.amazonS3 =
-
AmazonS3ClientBuilder.standard().withCredentials(credsProvider).build();
- this.region = amazonS3.getRegionName(); // not sure if this
works at all
+
S3Client.builder().credentialsProvider(credsProvider).build();
+ this.region =
amazonS3.serviceClientConfiguration().region().id(); // not sure if this works
at all
}
// for debugging
- AWSSecurityTokenService stsClient =
AWSSecurityTokenServiceClientBuilder.standard()
- .withCredentials(credsProvider).withRegion(region)
+ StsClient stsClient = StsClient.builder()
+
.credentialsProvider(credsProvider).region(Region.of(region))
.build();
- GetCallerIdentityResult identity = stsClient.getCallerIdentity(new
GetCallerIdentityRequest());
- LOG.debug("Authenticated as: {}", identity.getArn());
+ GetCallerIdentityResponse identity =
stsClient.getCallerIdentity(GetCallerIdentityRequest.builder()
+ .build());
+ LOG.debug("Authenticated as: {}", identity.arn());
- if (!this.amazonS3.doesBucketExistV2(this.bucketName)) { //
returns true if no access
+ if (!doesBucketExistV2(amazonS3, bucketName)) { // returns true if
no access
try {
- amazonS3.createBucket(this.bucketName);
- } catch (AmazonS3Exception e) {
+
amazonS3.createBucket(CreateBucketRequest.builder().bucket(this.bucketName)
+ .build());
+ } catch (S3Exception e) {
throw new TikaConfigException("couldn't create bucket", e);
}
}
this.amazonTranscribeAsync =
-
AmazonTranscribeAsyncClientBuilder.standard().withCredentials(credsProvider)
- .withRegion(this.region).build();
+
TranscribeAsyncClient.builder().credentialsProvider(credsProvider)
+ .region(Region.of(this.region)).build();
} catch (Exception e) {
LOG.warn("Exception reading config file", e);
isAvailable = false;
@@ -361,4 +377,20 @@ public class AmazonTranscribe implements Parser,
Initializable {
//TODO alert user if they've gotten 1 or 2 out of three?
this.isAvailable = checkAvailable();
}
+
+ // Thanks, ChatGPT
+ private boolean doesBucketExistV2(S3Client s3, String bucketName) {
+ try {
+
s3.headBucket(HeadBucketRequest.builder().bucket(bucketName).build());
+ return true; // Bucket exists
+ } catch (NoSuchBucketException e) {
+ return false; // Bucket doesn't exist
+ } catch (S3Exception e) {
+ // Could be 403 Forbidden (bucket exists but no access), or other
error
+ if (e.statusCode() == 403) {
+ return true; // Bucket exists but you don't have access
+ }
+ throw e; // Re-throw unexpected exception
+ }
+ }
}
diff --git
a/tika-parsers/tika-parsers-ml/tika-transcribe-aws/src/test/java/org/apache/tika/parser/transcribe/aws/AmazonTranscribeTest.java
b/tika-parsers/tika-parsers-ml/tika-transcribe-aws/src/test/java/org/apache/tika/parser/transcribe/aws/AmazonTranscribeTest.java
index 4ff112c2b..18224b306 100644
---
a/tika-parsers/tika-parsers-ml/tika-transcribe-aws/src/test/java/org/apache/tika/parser/transcribe/aws/AmazonTranscribeTest.java
+++
b/tika-parsers/tika-parsers-ml/tika-transcribe-aws/src/test/java/org/apache/tika/parser/transcribe/aws/AmazonTranscribeTest.java
@@ -18,10 +18,10 @@ package org.apache.tika.parser.transcribe.aws;
import java.io.InputStream;
-import com.amazonaws.services.transcribe.model.LanguageCode;
import org.junit.jupiter.api.BeforeAll;
import org.junit.jupiter.api.Disabled;
import org.junit.jupiter.api.Test;
+import software.amazon.awssdk.services.transcribe.model.LanguageCode;
import org.apache.tika.TikaTest;
import org.apache.tika.config.TikaConfig;
@@ -64,7 +64,7 @@ public class AmazonTranscribeTest extends TikaTest {
@Test
public void testAmazonTranscribeAudio_enUS() throws Exception {
ParseContext context = new ParseContext();
- context.set(LanguageCode.class, LanguageCode.EnUS);
+ context.set(LanguageCode.class, LanguageCode.EN_US);
String xml = getXML("en-US_(A_Little_Bottle_Of_Water).mp3", PARSER,
context).xml;
String expected = "A little bottle of water";
assertContains(expected, xml);
@@ -89,7 +89,7 @@ public class AmazonTranscribeTest extends TikaTest {
public void testAmazonTranscribeVideo_enUS() throws Exception {
String expected = "Hi";
ParseContext context = new ParseContext();
- context.set(LanguageCode.class, LanguageCode.EnUS);
+ context.set(LanguageCode.class, LanguageCode.EN_US);
String xml = getXML("en-US_(Hi).mp4", PARSER, context).xml;
assertContains(expected, xml);
}
@@ -114,7 +114,7 @@ public class AmazonTranscribeTest extends TikaTest {
String file = "en-GB_(A_Little_Bottle_Of_Water).mp3";
String expected = "A little bottle of water";
ParseContext context = new ParseContext();
- context.set(LanguageCode.class, LanguageCode.EnGB);
+ context.set(LanguageCode.class, LanguageCode.EN_GB);
String xml = getXML(file, PARSER, context).xml;
assertContains(expected, xml);
}
@@ -140,7 +140,7 @@ public class AmazonTranscribeTest extends TikaTest {
String file = "en-AU_(A_Little_Bottle_Of_Water).mp3";
String expected = "A little bottle of water";
ParseContext context = new ParseContext();
- context.set(LanguageCode.class, LanguageCode.EnAU);
+ context.set(LanguageCode.class, LanguageCode.EN_AU);
String xml = getXML(file, PARSER, context).xml;
assertContains(expected, xml);
}
@@ -166,7 +166,7 @@ public class AmazonTranscribeTest extends TikaTest {
String file = "de-DE_(We_Are_At_School_x2).mp3";
String expected = "Wir sind in der Schule. Wir sind in der Schule.";
ParseContext context = new ParseContext();
- context.set(LanguageCode.class, LanguageCode.DeDE);
+ context.set(LanguageCode.class, LanguageCode.DE_DE);
String xml = getXML(file, PARSER, context).xml;
assertContains(expected, xml);
}
@@ -192,7 +192,7 @@ public class AmazonTranscribeTest extends TikaTest {
String file = "it-IT_(We_Are_Having_Class_x2).mp3";
String expected = "stiamo facendo lezione. stiamo facendo lezione.";
ParseContext context = new ParseContext();
- context.set(LanguageCode.class, LanguageCode.ItIT);
+ context.set(LanguageCode.class, LanguageCode.IT_IT);
String xml = getXML(file, PARSER, context).xml;
assertContains(expected, xml);
}
@@ -218,7 +218,7 @@ public class AmazonTranscribeTest extends TikaTest {
String file = "ja-JP_(We_Are_At_School).mp3";
String expected = "私達は学校にいます"; //TODO or Watashitachi wa gakkō ni imasu
ParseContext context = new ParseContext();
- context.set(LanguageCode.class, LanguageCode.JaJP);
+ context.set(LanguageCode.class, LanguageCode.JA_JP);
String xml = getXML(file, PARSER, context).xml;
assertContains(expected, xml);
@@ -245,7 +245,7 @@ public class AmazonTranscribeTest extends TikaTest {
String file = "ko-KR_(We_Are_Having_Class_x2).mp3";
String expected = "우리는 수업을하고있다"; //TODO or ulineun sueob-eulhagoissda
ParseContext context = new ParseContext();
- context.set(LanguageCode.class, LanguageCode.KoKR);
+ context.set(LanguageCode.class, LanguageCode.KO_KR);
String xml = getXML(file, PARSER, context).xml;
assertContains(expected, xml);
}
@@ -272,7 +272,7 @@ public class AmazonTranscribeTest extends TikaTest {
//TODO: Check whether output is Annyeonghaseyo or 안녕하세요
String expected = "Annyeonghaseyo";
ParseContext context = new ParseContext();
- context.set(LanguageCode.class, LanguageCode.KoKR);
+ context.set(LanguageCode.class, LanguageCode.KO_KR);
String xml = getXML(file, PARSER, context).xml;
assertContains(expected, xml);
}
@@ -299,7 +299,7 @@ public class AmazonTranscribeTest extends TikaTest {
String file = "pt-BR_(We_Are_At_School).mp3";
String expected = "nós estamos na escola.";
ParseContext context = new ParseContext();
- context.set(LanguageCode.class, LanguageCode.PtBR);
+ context.set(LanguageCode.class, LanguageCode.PT_BR);
String xml = getXML(file, PARSER, context).xml;
assertContains(expected, xml);
}
