You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by gr...@apache.org on 2017/03/23 23:39:03 UTC
[tika] 04/08: Cosmetics: extra spaces and diamond operator
This is an automated email from the ASF dual-hosted git repository.
grossws pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/tika.git
commit 6ff825c684236a6e1c8a4f77cbcd2d7fb953870e
Author: Konstantin Gribov <gr...@gmail.com>
AuthorDate: Tue Mar 21 20:32:55 2017 +0300
Cosmetics: extra spaces and diamond operator
---
tika-batch/pom.xml | 1 +
.../java/org/apache/tika/batch/BatchProcess.java | 9 ++---
.../apache/tika/batch/BatchProcessDriverCLI.java | 7 ++--
.../apache/tika/batch/FileResourceConsumer.java | 2 --
.../apache/tika/batch/fs/FSBatchProcessCLI.java | 3 +-
.../batch/fs/RecursiveParserWrapperFSConsumer.java | 2 +-
.../batch/fs/strawman/StrawManTikaAppDriver.java | 6 ++--
tika-bundle/pom.xml | 5 +--
.../test/java/org/apache/tika/bundle/BundleIT.java | 41 +++++++++------------
tika-bundle/test-bundles.xml | 2 +-
.../main/java/org/apache/tika/fork/ForkClient.java | 13 +++----
.../main/java/org/apache/tika/fork/ForkParser.java | 5 ++-
tika-eval/pom.xml | 30 +++++++---------
.../org/apache/tika/parser/html/HtmlParser.java | 2 +-
.../org/apache/tika/parser/image/ImageParser.java | 3 +-
.../apache/tika/parser/ocr/TesseractOCRParser.java | 19 +++-------
.../tika/parser/pot/PooledTimeSeriesParser.java | 2 +-
.../tika/parser/wordperfect/QPWTextExtractor.java | 42 +++++++++++-----------
.../tika/parser/ner/nltk/NLTKNERecogniserTest.java | 6 ++--
tika-serialization/pom.xml | 3 +-
tika-server/pom.xml | 1 +
.../java/org/apache/tika/server/TikaServerCli.java | 9 +++--
.../server/resource/RecursiveMetadataResource.java | 4 +--
.../apache/tika/server/resource/TikaResource.java | 2 +-
.../tika/server/resource/TranslateResource.java | 1 -
.../tika/server/resource/UnpackerResource.java | 4 +--
26 files changed, 91 insertions(+), 133 deletions(-)
diff --git a/tika-batch/pom.xml b/tika-batch/pom.xml
index 354a2f9..db689f8 100644
--- a/tika-batch/pom.xml
+++ b/tika-batch/pom.xml
@@ -65,6 +65,7 @@
<artifactId>commons-io</artifactId>
<version>${commons.io.version}</version>
</dependency>
+
<dependency>
<groupId>org.apache.tika</groupId>
<artifactId>tika-core</artifactId>
diff --git a/tika-batch/src/main/java/org/apache/tika/batch/BatchProcess.java b/tika-batch/src/main/java/org/apache/tika/batch/BatchProcess.java
index 2afad39..7a8fcd4 100644
--- a/tika-batch/src/main/java/org/apache/tika/batch/BatchProcess.java
+++ b/tika-batch/src/main/java/org/apache/tika/batch/BatchProcess.java
@@ -51,7 +51,6 @@ import org.slf4j.LoggerFactory;
* communicate without interference with the parent process on stderr.
*/
public class BatchProcess implements Callable<ParallelFileProcessingResult> {
-
public enum BATCH_CONSTANTS {
BATCH_PROCESS_EXCEEDED_MAX_ALIVE_TIME,
BATCH_PROCESS_FATAL_MUST_RESTART
@@ -110,7 +109,7 @@ public class BatchProcess implements Callable<ParallelFileProcessingResult> {
this.consumersManager = consumersManager;
this.reporter = reporter;
this.interrupter = interrupter;
- timedOuts = new ArrayBlockingQueue<FileStarted>(consumersManager.getConsumers().size());
+ timedOuts = new ArrayBlockingQueue<>(consumersManager.getConsumers().size());
this.consumersManagerMaxMillis = consumersManager.getConsumersManagerMaxMillis();
}
@@ -146,8 +145,7 @@ public class BatchProcess implements Callable<ParallelFileProcessingResult> {
ExecutorService ex = Executors.newFixedThreadPool(numConsumers
+ numNonConsumers);
CompletionService<IFileProcessorFutureResult> completionService =
- new ExecutorCompletionService<IFileProcessorFutureResult>(
- ex);
+ new ExecutorCompletionService<>(ex);
TimeoutChecker timeoutChecker = new TimeoutChecker();
try {
@@ -175,14 +173,12 @@ public class BatchProcess implements Callable<ParallelFileProcessingResult> {
State state = new State();
LOG.info("BatchProcess starting up");
-
state.start = new Date().getTime();
completionService.submit(interrupter);
completionService.submit(fileResourceCrawler);
completionService.submit(reporter);
completionService.submit(timeoutChecker);
-
for (FileResourceConsumer consumer : consumersManager.getConsumers()) {
completionService.submit(consumer);
}
@@ -543,7 +539,6 @@ public class BatchProcess implements Callable<ParallelFileProcessingResult> {
}
private class TimeoutChecker implements Callable<IFileProcessorFutureResult> {
-
@Override
public TimeoutFutureResult call() throws Exception {
while (timedOuts.size() == 0) {
diff --git a/tika-batch/src/main/java/org/apache/tika/batch/BatchProcessDriverCLI.java b/tika-batch/src/main/java/org/apache/tika/batch/BatchProcessDriverCLI.java
index 937422d..aa8ebf8 100644
--- a/tika-batch/src/main/java/org/apache/tika/batch/BatchProcessDriverCLI.java
+++ b/tika-batch/src/main/java/org/apache/tika/batch/BatchProcessDriverCLI.java
@@ -36,7 +36,6 @@ import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
public class BatchProcessDriverCLI {
-
/**
* This relies on an special exit values of 254 (do not restart),
* 0 ended correctly, 253 ended with exception (do restart)
@@ -56,10 +55,8 @@ public class BatchProcessDriverCLI {
//how many times to wait pulseMillis milliseconds if a restart
//message has been received through stdout, but the
//child process has not yet exited
- private int waitNumLoopsAfterRestartmessage = 60;
- int loopsAfterRestartMessageReceived = 0;
-
-
+ private int waitNumLoopsAfterRestartMessage = 60;
+ private int loopsAfterRestartMessageReceived = 0;
private volatile boolean userInterrupted = false;
private boolean receivedRestartMsg = false;
diff --git a/tika-batch/src/main/java/org/apache/tika/batch/FileResourceConsumer.java b/tika-batch/src/main/java/org/apache/tika/batch/FileResourceConsumer.java
index 3f2ed7a..6e9d314 100644
--- a/tika-batch/src/main/java/org/apache/tika/batch/FileResourceConsumer.java
+++ b/tika-batch/src/main/java/org/apache/tika/batch/FileResourceConsumer.java
@@ -128,7 +128,6 @@ public abstract class FileResourceConsumer implements Callable<IFileProcessorFut
return new FileConsumerFutureResult(currentFile, numResourcesConsumed);
}
-
/**
* Main piece of code that needs to be implemented. Clients
* are responsible for closing streams and handling the exceptions
@@ -419,5 +418,4 @@ public abstract class FileResourceConsumer implements Callable<IFileProcessorFut
close(is);
}
}
-
}
diff --git a/tika-batch/src/main/java/org/apache/tika/batch/fs/FSBatchProcessCLI.java b/tika-batch/src/main/java/org/apache/tika/batch/fs/FSBatchProcessCLI.java
index 6a8cf96..7347164 100644
--- a/tika-batch/src/main/java/org/apache/tika/batch/fs/FSBatchProcessCLI.java
+++ b/tika-batch/src/main/java/org/apache/tika/batch/fs/FSBatchProcessCLI.java
@@ -145,8 +145,7 @@ public class FSBatchProcessCLI {
}
public static void main(String[] args) throws Exception {
-
- try{
+ try {
FSBatchProcessCLI cli = new FSBatchProcessCLI(args);
cli.execute(args);
} catch (Throwable t) {
diff --git a/tika-batch/src/main/java/org/apache/tika/batch/fs/RecursiveParserWrapperFSConsumer.java b/tika-batch/src/main/java/org/apache/tika/batch/fs/RecursiveParserWrapperFSConsumer.java
index 5a334b1..f95bcbb 100644
--- a/tika-batch/src/main/java/org/apache/tika/batch/fs/RecursiveParserWrapperFSConsumer.java
+++ b/tika-batch/src/main/java/org/apache/tika/batch/fs/RecursiveParserWrapperFSConsumer.java
@@ -108,7 +108,7 @@ public class RecursiveParserWrapperFSConsumer extends AbstractFSConsumer {
thrown = t;
metadataList = parser.getMetadata();
if (metadataList == null) {
- metadataList = new LinkedList<Metadata>();
+ metadataList = new LinkedList<>();
}
Metadata m = null;
if (metadataList.size() == 0) {
diff --git a/tika-batch/src/main/java/org/apache/tika/batch/fs/strawman/StrawManTikaAppDriver.java b/tika-batch/src/main/java/org/apache/tika/batch/fs/strawman/StrawManTikaAppDriver.java
index c23b269..8523d5c 100644
--- a/tika-batch/src/main/java/org/apache/tika/batch/fs/strawman/StrawManTikaAppDriver.java
+++ b/tika-batch/src/main/java/org/apache/tika/batch/fs/strawman/StrawManTikaAppDriver.java
@@ -125,7 +125,7 @@ public class StrawManTikaAppDriver implements Callable<Integer> {
long pulse = 100;
for (int i = 0; i < totalTime; i += pulse) {
try {
- Thread.currentThread().sleep(pulse);
+ Thread.sleep(pulse);
} catch (InterruptedException e) {
//swallow
}
@@ -221,12 +221,12 @@ public class StrawManTikaAppDriver implements Callable<Integer> {
Path outputDir = Paths.get(args[1]);
int totalThreads = Integer.parseInt(args[2]);
- List<String> commandLine = new ArrayList<String>();
+ List<String> commandLine = new ArrayList<>();
commandLine.addAll(Arrays.asList(args).subList(3, args.length));
totalThreads = (totalThreads < 1) ? 1 : totalThreads;
ExecutorService ex = Executors.newFixedThreadPool(totalThreads);
ExecutorCompletionService<Integer> completionService =
- new ExecutorCompletionService<Integer>(ex);
+ new ExecutorCompletionService<>(ex);
for (int i = 0; i < totalThreads; i++) {
StrawManTikaAppDriver driver =
diff --git a/tika-bundle/pom.xml b/tika-bundle/pom.xml
index 28ddc1a..b9cfc88 100644
--- a/tika-bundle/pom.xml
+++ b/tika-bundle/pom.xml
@@ -266,7 +266,8 @@
org.xml.sax.helpers;resolution:=optional,
org.xmlpull.v1;resolution:=optional,
com.microsoft.schemas.office.powerpoint;resolution:=optional,
- com.microsoft.schemas.office.word;resolution:=optional, sun.misc;resolution:=optional,
+ com.microsoft.schemas.office.word;resolution:=optional,
+ sun.misc;resolution:=optional,
ucar.units;resolution:=optional,
ucar.httpservices;resolution:=optional,
ucar.nc2.util;resolution:=optional,
@@ -443,4 +444,4 @@
<system>Jenkins</system>
<url>https://builds.apache.org/job/Tika-trunk/</url>
</ciManagement>
-</project>
\ No newline at end of file
+</project>
diff --git a/tika-bundle/src/test/java/org/apache/tika/bundle/BundleIT.java b/tika-bundle/src/test/java/org/apache/tika/bundle/BundleIT.java
index c610e9a..77e60c3 100644
--- a/tika-bundle/src/test/java/org/apache/tika/bundle/BundleIT.java
+++ b/tika-bundle/src/test/java/org/apache/tika/bundle/BundleIT.java
@@ -72,8 +72,10 @@ public class BundleIT {
@Inject
private Parser defaultParser;
+
@Inject
private Detector contentTypeDetector;
+
@Inject
private BundleContext bc;
@@ -86,7 +88,6 @@ public class BundleIT {
bundle(new File(base, "tika-bundle.jar").toURI().toURL().toString()));
}
-
@Test
public void testBundleLoaded() throws Exception {
boolean hasCore = false, hasBundle = false;
@@ -104,7 +105,6 @@ public class BundleIT {
assertTrue("Bundle bundle not found", hasBundle);
}
-
@Test
public void testManifestNoJUnit() throws Exception {
File TARGET = new File("target");
@@ -123,12 +123,11 @@ public class BundleIT {
assertFalse("The bundle should not import junit", containsJunit);
}
-
@Test
public void testBundleDetection() throws Exception {
Metadata metadataTXT = new Metadata();
metadataTXT.set(Metadata.RESOURCE_NAME_KEY, "test.txt");
-
+
Metadata metadataPDF = new Metadata();
metadataPDF.set(Metadata.RESOURCE_NAME_KEY, "test.pdf");
@@ -137,7 +136,6 @@ public class BundleIT {
assertEquals(MediaType.application("pdf"), contentTypeDetector.detect(null, metadataPDF));
}
-
@Test
public void testForkParser() throws Exception {
ForkParser parser = new ForkParser(Activator.class.getClassLoader(), defaultParser);
@@ -157,7 +155,6 @@ public class BundleIT {
assertEquals("test content", content.trim());
}
-
@Test
public void testBundleSimpleText() throws Exception {
Tika tika = new Tika();
@@ -167,7 +164,6 @@ public class BundleIT {
assertTrue(xml.contains("tika-bundle"));
}
-
@Test
public void testBundleDetectors() throws Exception {
//For some reason, the detector created by OSGi has a flat
@@ -178,9 +174,9 @@ public class BundleIT {
// Get the classes found within OSGi
ServiceReference<Detector> detectorRef = bc.getServiceReference(Detector.class);
- DefaultDetector detectorService = (DefaultDetector)bc.getService(detectorRef);
-
- Set<String> osgiDetectors = new HashSet<String>();
+ DefaultDetector detectorService = (DefaultDetector) bc.getService(detectorRef);
+
+ Set<String> osgiDetectors = new HashSet<>();
for (Detector d : detectorService.getDetectors()) {
osgiDetectors.add(d.getClass().getName());
}
@@ -194,7 +190,7 @@ public class BundleIT {
Set<String> rawDetectors = new HashSet<String>();
for (Detector d : detector.getDetectors()) {
if (d instanceof DefaultDetector) {
- for (Detector dChild : ((DefaultDetector)d).getDetectors()) {
+ for (Detector dChild : ((DefaultDetector) d).getDetectors()) {
rawDetectors.add(dChild.getClass().getName());
}
} else {
@@ -204,14 +200,13 @@ public class BundleIT {
assertEquals(osgiDetectors, rawDetectors);
}
-
@Test
public void testBundleParsers() throws Exception {
// Get the classes found within OSGi
ServiceReference<Parser> parserRef = bc.getServiceReference(Parser.class);
- DefaultParser parserService = (DefaultParser)bc.getService(parserRef);
-
- Set<String> osgiParsers = new HashSet<String>();
+ DefaultParser parserService = (DefaultParser) bc.getService(parserRef);
+
+ Set<String> osgiParsers = new HashSet<>();
for (Parser p : parserService.getAllComponentParsers()) {
osgiParsers.add(p.getClass().getName());
}
@@ -221,11 +216,11 @@ public class BundleIT {
osgiParsers.size() > 15);
// Get the raw parsers list from the traditional service loading mechanism
- CompositeParser parser = (CompositeParser)defaultParser;
- Set<String> rawParsers = new HashSet<String>();
+ CompositeParser parser = (CompositeParser) defaultParser;
+ Set<String> rawParsers = new HashSet<>();
for (Parser p : parser.getAllComponentParsers()) {
if (p instanceof DefaultParser) {
- for (Parser pChild : ((DefaultParser)p).getAllComponentParsers()) {
+ for (Parser pChild : ((DefaultParser) p).getAllComponentParsers()) {
rawParsers.add(pChild.getClass().getName());
}
} else {
@@ -234,19 +229,17 @@ public class BundleIT {
}
assertEquals(rawParsers, osgiParsers);
}
-
+
@Test
public void testTesseractParser() throws Exception {
ContentHandler handler = new BodyContentHandler();
ParseContext context = new ParseContext();
Parser tesseractParser = new TesseractOCRParser();
- try(InputStream stream = new FileInputStream("src/test/resources/testOCR.jpg"))
- {
+ try (InputStream stream = new FileInputStream("src/test/resources/testOCR.jpg")) {
tesseractParser.parse(stream, handler, new Metadata(), context);
}
-
- }
+ }
@Test
public void testTikaBundle() throws Exception {
@@ -260,7 +253,7 @@ public class BundleIT {
context.set(Parser.class, parser);
try (InputStream stream =
- new FileInputStream("src/test/resources/test-documents.zip")) {
+ new FileInputStream("src/test/resources/test-documents.zip")) {
parser.parse(stream, handler, new Metadata(), context);
}
diff --git a/tika-bundle/test-bundles.xml b/tika-bundle/test-bundles.xml
index 8c010e3..0e60103 100644
--- a/tika-bundle/test-bundles.xml
+++ b/tika-bundle/test-bundles.xml
@@ -32,4 +32,4 @@
</includes>
</dependencySet>
</dependencySets>
-</assembly>
\ No newline at end of file
+</assembly>
diff --git a/tika-core/src/main/java/org/apache/tika/fork/ForkClient.java b/tika-core/src/main/java/org/apache/tika/fork/ForkClient.java
index f59b56e..dd1d033 100644
--- a/tika-core/src/main/java/org/apache/tika/fork/ForkClient.java
+++ b/tika-core/src/main/java/org/apache/tika/fork/ForkClient.java
@@ -37,7 +37,7 @@ import org.xml.sax.ContentHandler;
class ForkClient {
- private final List<ForkResource> resources = new ArrayList<ForkResource>();
+ private final List<ForkResource> resources = new ArrayList<>();
private final ClassLoader loader;
@@ -59,7 +59,7 @@ class ForkClient {
this.jar = createBootstrapJar();
ProcessBuilder builder = new ProcessBuilder();
- List<String> command = new ArrayList<String>();
+ List<String> command = new ArrayList<>();
command.addAll(java);
command.add("-jar");
command.add(jar.getPath());
@@ -117,7 +117,7 @@ class ForkClient {
public synchronized Throwable call(String method, Object... args)
throws IOException, TikaException {
- List<ForkResource> r = new ArrayList<ForkResource>(resources);
+ List<ForkResource> r = new ArrayList<>(resources);
output.writeByte(ForkServer.CALL);
output.writeUTF(method);
for (int i = 0; i < args.length; i++) {
@@ -265,10 +265,8 @@ class ForkClient {
* @throws IOException if the bootstrap archive could not be created
*/
private static void fillBootstrapJar(File file) throws IOException {
- try (JarOutputStream jar =
- new JarOutputStream(new FileOutputStream(file))) {
- String manifest =
- "Main-Class: " + ForkServer.class.getName() + "\n";
+ try (JarOutputStream jar = new JarOutputStream(new FileOutputStream(file))) {
+ String manifest = "Main-Class: " + ForkServer.class.getName() + "\n";
jar.putNextEntry(new ZipEntry("META-INF/MANIFEST.MF"));
jar.write(manifest.getBytes(UTF_8));
@@ -290,5 +288,4 @@ class ForkClient {
}
}
}
-
}
diff --git a/tika-core/src/main/java/org/apache/tika/fork/ForkParser.java b/tika-core/src/main/java/org/apache/tika/fork/ForkParser.java
index c4fcd39..c69b11c 100644
--- a/tika-core/src/main/java/org/apache/tika/fork/ForkParser.java
+++ b/tika-core/src/main/java/org/apache/tika/fork/ForkParser.java
@@ -54,8 +54,7 @@ public class ForkParser extends AbstractParser {
private int currentlyInUse = 0;
- private final Queue<ForkClient> pool =
- new LinkedList<ForkClient>();
+ private final Queue<ForkClient> pool = new LinkedList<>();
private long serverPulseMillis = 5000;
@@ -134,7 +133,7 @@ public class ForkParser extends AbstractParser {
* @param java java command line
*/
public void setJavaCommand(List<String> java) {
- this.java = new ArrayList<String>(java);
+ this.java = new ArrayList<>(java);
}
/**
diff --git a/tika-eval/pom.xml b/tika-eval/pom.xml
index 8bc7680..d4b1726 100644
--- a/tika-eval/pom.xml
+++ b/tika-eval/pom.xml
@@ -19,18 +19,8 @@
under the License.
-->
-<project xmlns="http://maven.apache.org/POM/4.0.0"
- xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
- xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
-
+<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
- <properties>
- <cli.version>1.3.1</cli.version> <!--sync version with tika-server or move to parent? -->
- <!-- upgrade to 6.x or something more modern once Tika requires Java 1.8 -->
- <lucene.version>5.5.3</lucene.version>
- <poi.version>3.16-beta2</poi.version>
-
- </properties>
<parent>
<groupId>org.apache.tika</groupId>
@@ -43,6 +33,13 @@
<name>Apache Tika eval</name>
<url>http://tika.apache.org/</url>
+ <properties>
+ <cli.version>1.3.1</cli.version> <!--sync version with tika-server or move to parent? -->
+ <!-- upgrade to 6.x or something more modern once Tika requires Java 1.8 -->
+ <lucene.version>5.5.3</lucene.version>
+ <poi.version>3.16-beta2</poi.version>
+ </properties>
+
<dependencies>
<dependency>
<groupId>${project.groupId}</groupId>
@@ -59,6 +56,7 @@
<artifactId>tika-serialization</artifactId>
<version>${project.version}</version>
</dependency>
+
<dependency>
<groupId>org.apache.commons</groupId>
<artifactId>commons-math3</artifactId>
@@ -136,6 +134,7 @@
<artifactId>poi-scratchpad</artifactId>
<version>${poi.version}</version>
</dependency>
+
<dependency>
<groupId>org.apache.tika</groupId>
<artifactId>tika-batch</artifactId>
@@ -150,14 +149,14 @@
<type>test-jar</type>
<scope>test</scope>
</dependency>
+
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<scope>test</scope>
</dependency>
-
-
</dependencies>
+
<build>
<plugins>
<plugin>
@@ -255,11 +254,8 @@
</executions>
</plugin>
</plugins>
-
</build>
-
-
<organization>
<name>The Apache Software Foundation</name>
<url>http://www.apache.org</url>
@@ -277,6 +273,4 @@
<system>Jenkins</system>
<url>https://builds.apache.org/job/Tika-trunk/</url>
</ciManagement>
-
-
</project>
diff --git a/tika-parsers/src/main/java/org/apache/tika/parser/html/HtmlParser.java b/tika-parsers/src/main/java/org/apache/tika/parser/html/HtmlParser.java
index c115956..e1284c6 100644
--- a/tika-parsers/src/main/java/org/apache/tika/parser/html/HtmlParser.java
+++ b/tika-parsers/src/main/java/org/apache/tika/parser/html/HtmlParser.java
@@ -58,7 +58,7 @@ public class HtmlParser extends AbstractEncodingDetectorParser {
private static final MediaType X_ASP = MediaType.application("x-asp");
private static final Set<MediaType> SUPPORTED_TYPES =
- Collections.unmodifiableSet(new HashSet<MediaType>(Arrays.asList(
+ Collections.unmodifiableSet(new HashSet<>(Arrays.asList(
MediaType.text("html"),
XHTML,
WAP_XHTML,
diff --git a/tika-parsers/src/main/java/org/apache/tika/parser/image/ImageParser.java b/tika-parsers/src/main/java/org/apache/tika/parser/image/ImageParser.java
index 97fdc33..ddb4f92 100644
--- a/tika-parsers/src/main/java/org/apache/tika/parser/image/ImageParser.java
+++ b/tika-parsers/src/main/java/org/apache/tika/parser/image/ImageParser.java
@@ -59,7 +59,7 @@ public class ImageParser extends AbstractParser {
private static final Set<MediaType> TMP_SUPPORTED;
static {
- TMP_SUPPORTED = new HashSet<MediaType>(Arrays.asList(
+ TMP_SUPPORTED = new HashSet<>(Arrays.asList(
MAIN_BMP_TYPE,
OLD_BMP_TYPE,
MediaType.image("gif"),
@@ -217,5 +217,4 @@ public class ImageParser extends AbstractParser {
xhtml.startDocument();
xhtml.endDocument();
}
-
}
diff --git a/tika-parsers/src/main/java/org/apache/tika/parser/ocr/TesseractOCRParser.java b/tika-parsers/src/main/java/org/apache/tika/parser/ocr/TesseractOCRParser.java
index 5f9134f..9728b38 100644
--- a/tika-parsers/src/main/java/org/apache/tika/parser/ocr/TesseractOCRParser.java
+++ b/tika-parsers/src/main/java/org/apache/tika/parser/ocr/TesseractOCRParser.java
@@ -95,12 +95,12 @@ public class TesseractOCRParser extends AbstractParser {
private static final long serialVersionUID = -8167538283213097265L;
private static final TesseractOCRConfig DEFAULT_CONFIG = new TesseractOCRConfig();
private static final Set<MediaType> SUPPORTED_TYPES = Collections.unmodifiableSet(
- new HashSet<MediaType>(Arrays.asList(new MediaType[] {
+ new HashSet<>(Arrays.asList(new MediaType[]{
MediaType.image("png"), MediaType.image("jpeg"), MediaType.image("tiff"),
MediaType.image("bmp"), MediaType.image("gif"), MediaType.image("jp2"),
MediaType.image("jpx"), MediaType.image("x-portable-pixmap")
})));
- private static Map<String,Boolean> TESSERACT_PRESENT = new HashMap<String, Boolean>();
+ private static Map<String,Boolean> TESSERACT_PRESENT = new HashMap<>();
@@ -182,7 +182,6 @@ public class TesseractOCRParser extends AbstractParser {
public void parse(Image image, ContentHandler handler, Metadata metadata, ParseContext context) throws IOException,
SAXException, TikaException {
-
TemporaryResources tmp = new TemporaryResources();
FileOutputStream fos = null;
TikaInputStream tis = null;
@@ -195,7 +194,6 @@ public class TesseractOCRParser extends AbstractParser {
ImageIO.write(bImage, "png", fos);
tis = TikaInputStream.get(file);
parse(tis, handler, metadata, context);
-
} finally {
tmp.dispose();
if (tis != null)
@@ -203,13 +201,11 @@ public class TesseractOCRParser extends AbstractParser {
if (fos != null)
fos.close();
}
-
}
@Override
public void parse(InputStream stream, ContentHandler handler, Metadata metadata, ParseContext parseContext)
throws IOException, SAXException, TikaException {
-
TesseractOCRConfig config = parseContext.get(TesseractOCRConfig.class, DEFAULT_CONFIG);
// If Tesseract is not on the path with the current config, do not try to run OCR
// getSupportedTypes shouldn't have listed us as handling it, so this should only
@@ -290,7 +286,6 @@ public class TesseractOCRParser extends AbstractParser {
} finally {
tmp.dispose();
}
-
}
/**
@@ -420,7 +415,6 @@ public class TesseractOCRParser extends AbstractParser {
* if an input error occurred
*/
private void doOCR(File input, File output, TesseractOCRConfig config) throws IOException, TikaException {
-
String[] cmd = { config.getTesseractPath() + getTesseractProg(), input.getPath(), output.getPath(), "-l",
config.getLanguage(), "-psm", config.getPageSegMode(),
config.getOutputType().name().toLowerCase(Locale.US),
@@ -437,7 +431,7 @@ public class TesseractOCRParser extends AbstractParser {
logStream("OCR MSG", out, input);
logStream("OCR ERROR", err, input);
- FutureTask<Integer> waitTask = new FutureTask<Integer>(new Callable<Integer>() {
+ FutureTask<Integer> waitTask = new FutureTask<>(new Callable<Integer>() {
public Integer call() throws Exception {
return process.waitFor();
}
@@ -448,22 +442,18 @@ public class TesseractOCRParser extends AbstractParser {
try {
waitTask.get(config.getTimeout(), TimeUnit.SECONDS);
-
} catch (InterruptedException e) {
waitThread.interrupt();
process.destroy();
Thread.currentThread().interrupt();
throw new TikaException("TesseractOCRParser interrupted", e);
-
} catch (ExecutionException e) {
// should not be thrown
-
} catch (TimeoutException e) {
waitThread.interrupt();
process.destroy();
throw new TikaException("TesseractOCRParser timeout", e);
}
-
}
/**
@@ -480,7 +470,6 @@ public class TesseractOCRParser extends AbstractParser {
* if an input error occurred
*/
private void extractOutput(InputStream stream, XHTMLContentHandler xhtml) throws SAXException, IOException {
-
xhtml.startElement("div", "class", "ocr");
try (Reader reader = new InputStreamReader(stream, UTF_8)) {
char[] buffer = new char[1024];
@@ -581,7 +570,7 @@ public class TesseractOCRParser extends AbstractParser {
private static Set<String> unmodifiableSet(String... elements) {
return Collections.unmodifiableSet(
- new HashSet<String>(Arrays.asList(elements)));
+ new HashSet<>(Arrays.asList(elements)));
}
}
}
diff --git a/tika-parsers/src/main/java/org/apache/tika/parser/pot/PooledTimeSeriesParser.java b/tika-parsers/src/main/java/org/apache/tika/parser/pot/PooledTimeSeriesParser.java
index 29be16b..2eb996b 100644
--- a/tika-parsers/src/main/java/org/apache/tika/parser/pot/PooledTimeSeriesParser.java
+++ b/tika-parsers/src/main/java/org/apache/tika/parser/pot/PooledTimeSeriesParser.java
@@ -74,7 +74,7 @@ public class PooledTimeSeriesParser extends AbstractParser {
isAvailable ? Collections.unmodifiableSet(
new HashSet<>(Arrays.asList(new MediaType[]{
MediaType.video("avi"), MediaType.video("mp4")
- }))) : Collections.EMPTY_SET;
+ }))) : Collections.<MediaType>emptySet();
;
// TODO: Add all supported video types
diff --git a/tika-parsers/src/main/java/org/apache/tika/parser/wordperfect/QPWTextExtractor.java b/tika-parsers/src/main/java/org/apache/tika/parser/wordperfect/QPWTextExtractor.java
index aaf16fc..e890a34 100644
--- a/tika-parsers/src/main/java/org/apache/tika/parser/wordperfect/QPWTextExtractor.java
+++ b/tika-parsers/src/main/java/org/apache/tika/parser/wordperfect/QPWTextExtractor.java
@@ -45,7 +45,7 @@ class QPWTextExtractor {
private static final String OLE_DOCUMENT_NAME = "NativeContent_MAIN";
- private enum Extractor{
+ private enum Extractor {
IGNORE { @Override public void extract(Context ctx) throws IOException {
ctx.in.skipWPByte(ctx.bodyLength);
}},
@@ -62,7 +62,7 @@ class QPWTextExtractor {
ctx.metadata.set(TikaCoreProperties.CREATOR, getQstrLabel(ctx.in));
ctx.metadata.set(TikaCoreProperties.MODIFIER, getQstrLabel(ctx.in));
}},
- EXT_LINK { @Override public void extract(Context ctx)
+ EXT_LINK { @Override public void extract(Context ctx)
throws IOException, SAXException {
ctx.in.readWPShort(); // index
ctx.in.readWPShort(); // page first
@@ -70,7 +70,7 @@ class QPWTextExtractor {
ctx.xhtml.characters(getQstrLabel(ctx.in));
ctx.xhtml.characters(System.lineSeparator());
}},
- STRING_TABLE { @Override public void extract(Context ctx)
+ STRING_TABLE { @Override public void extract(Context ctx)
throws IOException, SAXException {
long entries = ctx.in.readWPLong();
ctx.in.readWPLong(); // Total used
@@ -92,26 +92,26 @@ class QPWTextExtractor {
ctx.xhtml.characters(getQstrLabel(ctx.in));
ctx.xhtml.characters(System.lineSeparator());
}},
- SHEET_HEADFOOT { @Override public void extract(Context ctx)
+ SHEET_HEADFOOT { @Override public void extract(Context ctx)
throws IOException, SAXException {
ctx.in.readWPShort(); // flag
ctx.xhtml.characters(getQstrLabel(ctx.in));
ctx.xhtml.characters(System.lineSeparator());
}},
- FORMULA_STRING_VALUE { @Override public void extract(Context ctx)
+ FORMULA_STRING_VALUE { @Override public void extract(Context ctx)
throws IOException, SAXException {
ctx.in.readWPShort(); // column
ctx.in.readWPLong(); // row
ctx.xhtml.characters(getQstrLabel(ctx.in));
}},
- CGENERICLABEL { @Override public void extract(Context ctx)
+ CGENERICLABEL { @Override public void extract(Context ctx)
throws IOException, SAXException {
ctx.in.readWPShort(); // column
ctx.in.readWPLong(); // row
ctx.in.readWPShort(); // format index
ctx.xhtml.characters(getQstrLabel(ctx.in));
}},
- CCOMMENT { @Override public void extract(Context ctx)
+ CCOMMENT { @Override public void extract(Context ctx)
throws IOException, SAXException {
ctx.in.readWPShort(); // column
ctx.in.readWPLong(); // row
@@ -123,13 +123,13 @@ class QPWTextExtractor {
DEBUG { @Override public void extract(Context ctx) throws IOException {
LOG.error("REC ({}/{}):{}", Integer.toHexString(ctx.type), ctx.bodyLength, ctx.in.readWPString(ctx.bodyLength));
}};
- public abstract void extract(Context ctx)
+ public abstract void extract(Context ctx)
throws IOException, SAXException;
}
-
+
// Holds extractors for each record types we are interested in.
// All record types not defined here will be skipped.
- private static final Map<Integer, Extractor> EXTRACTORS =
+ private static final Map<Integer, Extractor> EXTRACTORS =
new HashMap<>();
static {
//--- Global Records ---
@@ -146,18 +146,18 @@ class QPWTextExtractor {
EXTRACTORS.put(0x0606, Extractor.SHEET_HEADFOOT); // Sheet footer
//--- Cells ---
- EXTRACTORS.put(0x0c02, Extractor.FORMULA_STRING_VALUE);
- EXTRACTORS.put(0x0c72, Extractor.CGENERICLABEL);
- EXTRACTORS.put(0x0c80, Extractor.CCOMMENT);
+ EXTRACTORS.put(0x0c02, Extractor.FORMULA_STRING_VALUE);
+ EXTRACTORS.put(0x0c72, Extractor.CGENERICLABEL);
+ EXTRACTORS.put(0x0c80, Extractor.CCOMMENT);
}
-
+
class Context {
private final WPInputStream in;
private final XHTMLContentHandler xhtml;
private final Metadata metadata;
private int type;
private int bodyLength;
- public Context(WPInputStream in, XHTMLContentHandler xhtml,
+ public Context(WPInputStream in, XHTMLContentHandler xhtml,
Metadata metadata) {
super();
this.in = in;
@@ -165,20 +165,20 @@ class QPWTextExtractor {
this.metadata = metadata;
}
}
-
+
@SuppressWarnings("resource")
public void extract(
InputStream input, XHTMLContentHandler xhtml, Metadata metadata)
throws IOException, SAXException, TikaException {
-
+
POIFSFileSystem pfs = new POIFSFileSystem(input);
DirectoryNode rootNode = pfs.getRoot();
if (rootNode == null || !rootNode.hasEntry(OLE_DOCUMENT_NAME)) {
throw new UnsupportedFormatException("Unsupported QuattroPro file format. "
+ "Looking for OLE entry \"" + OLE_DOCUMENT_NAME
- + "\". Found: "+ rootNode.getEntryNames());
+ + "\". Found: " + (rootNode == null ? "null" : rootNode.getEntryNames()));
}
-
+
//TODO shall we validate and throw warning/error if the file does not
//start with a BOF and ends with a EOF?
xhtml.startElement("p");
@@ -200,7 +200,7 @@ class QPWTextExtractor {
}
xhtml.endElement("p");
}
-
+
private boolean hasNext(InputStream in) throws IOException {
try {
in.mark(1);
@@ -209,7 +209,7 @@ class QPWTextExtractor {
in.reset();
}
}
-
+
private static String getQstrLabel(WPInputStream in) throws IOException {
// QSTR
int count = in.readWPShort();
diff --git a/tika-parsers/src/test/java/org/apache/tika/parser/ner/nltk/NLTKNERecogniserTest.java b/tika-parsers/src/test/java/org/apache/tika/parser/ner/nltk/NLTKNERecogniserTest.java
index 1dc4711..4b0101e 100644
--- a/tika-parsers/src/test/java/org/apache/tika/parser/ner/nltk/NLTKNERecogniserTest.java
+++ b/tika-parsers/src/test/java/org/apache/tika/parser/ner/nltk/NLTKNERecogniserTest.java
@@ -35,15 +35,13 @@ public class NLTKNERecogniserTest {
public void testGetEntityTypes() throws Exception {
String text = "America is a big country.";
System.setProperty(NamedEntityParser.SYS_PROP_NER_IMPL, NLTKNERecogniser.class.getName());
+
Tika tika = new Tika(new TikaConfig(NamedEntityParser.class.getResourceAsStream("tika-config.xml")));
Metadata md = new Metadata();
tika.parse(new ByteArrayInputStream(text.getBytes(StandardCharsets.UTF_8)), md);
Set<String> names = new HashSet<>(Arrays.asList(md.getValues("NER_NAMES")));
- if(names.size() == 0) {
- return;
- }
- else {
+ if(names.size() != 0) {
assertTrue(names.contains("America"));
assertTrue(names.size() == 1);
}
diff --git a/tika-serialization/pom.xml b/tika-serialization/pom.xml
index e07cf5d..b602215 100644
--- a/tika-serialization/pom.xml
+++ b/tika-serialization/pom.xml
@@ -21,6 +21,7 @@
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
+
<parent>
<groupId>org.apache.tika</groupId>
<artifactId>tika-parent</artifactId>
@@ -78,7 +79,6 @@
</plugins>
</build>
-
<organization>
<name>The Apache Software Foundation</name>
<url>http://www.apache.org</url>
@@ -91,5 +91,4 @@
<system>Jenkins</system>
<url>https://builds.apache.org/job/Tika-trunk/</url>
</ciManagement>
-
</project>
diff --git a/tika-server/pom.xml b/tika-server/pom.xml
index f230bfd..21563df 100644
--- a/tika-server/pom.xml
+++ b/tika-server/pom.xml
@@ -146,6 +146,7 @@
<type>test-jar</type>
<scope>test</scope>
</dependency>
+
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
diff --git a/tika-server/src/main/java/org/apache/tika/server/TikaServerCli.java b/tika-server/src/main/java/org/apache/tika/server/TikaServerCli.java
index 5397d04..b5d94d9 100644
--- a/tika-server/src/main/java/org/apache/tika/server/TikaServerCli.java
+++ b/tika-server/src/main/java/org/apache/tika/server/TikaServerCli.java
@@ -190,7 +190,7 @@ public class TikaServerCli {
TikaResource.init(tika, digester, inputStreamFactory);
JAXRSServerFactoryBean sf = new JAXRSServerFactoryBean();
- List<ResourceProvider> rCoreProviders = new ArrayList<ResourceProvider>();
+ List<ResourceProvider> rCoreProviders = new ArrayList<>();
rCoreProviders.add(new SingletonResourceProvider(new MetadataResource()));
rCoreProviders.add(new SingletonResourceProvider(new RecursiveMetadataResource()));
rCoreProviders.add(new SingletonResourceProvider(new DetectorResource()));
@@ -202,11 +202,11 @@ public class TikaServerCli {
rCoreProviders.add(new SingletonResourceProvider(new TikaDetectors()));
rCoreProviders.add(new SingletonResourceProvider(new TikaParsers()));
rCoreProviders.add(new SingletonResourceProvider(new TikaVersion()));
- List<ResourceProvider> rAllProviders = new ArrayList<ResourceProvider>(rCoreProviders);
+ List<ResourceProvider> rAllProviders = new ArrayList<>(rCoreProviders);
rAllProviders.add(new SingletonResourceProvider(new TikaWelcome(rCoreProviders)));
sf.setResourceProviders(rAllProviders);
- List<Object> providers = new ArrayList<Object>();
+ List<Object> providers = new ArrayList<>();
providers.add(new TarWriter());
providers.add(new ZipWriter());
providers.add(new CSVMessageBodyWriter());
@@ -229,8 +229,7 @@ public class TikaServerCli {
BindingFactoryManager manager = sf.getBus().getExtension(BindingFactoryManager.class);
JAXRSBindingFactory factory = new JAXRSBindingFactory();
factory.setBus(sf.getBus());
- manager.registerBindingFactory(JAXRSBindingFactory.JAXRS_BINDING_ID,
- factory);
+ manager.registerBindingFactory(JAXRSBindingFactory.JAXRS_BINDING_ID, factory);
sf.create();
LOG.info("Started Apache Tika server at {}", url);
} catch (Exception ex) {
diff --git a/tika-server/src/main/java/org/apache/tika/server/resource/RecursiveMetadataResource.java b/tika-server/src/main/java/org/apache/tika/server/resource/RecursiveMetadataResource.java
index 24e3f91..739794c 100644
--- a/tika-server/src/main/java/org/apache/tika/server/resource/RecursiveMetadataResource.java
+++ b/tika-server/src/main/java/org/apache/tika/server/resource/RecursiveMetadataResource.java
@@ -76,7 +76,7 @@ public class RecursiveMetadataResource {
@POST
@Consumes("multipart/form-data")
@Produces({"application/json"})
- @Path("form{"+HANDLER_TYPE_PARAM+" : (\\w+)?}")
+ @Path("form{" + HANDLER_TYPE_PARAM + " : (\\w+)?}")
public Response getMetadataFromMultipart(Attachment att, @Context UriInfo info,
@PathParam(HANDLER_TYPE_PARAM) String handlerTypeName)
throws Exception {
@@ -110,7 +110,7 @@ public class RecursiveMetadataResource {
@PUT
@Produces("application/json")
- @Path("{"+HANDLER_TYPE_PARAM+" : (\\w+)?}")
+ @Path("{" + HANDLER_TYPE_PARAM + " : (\\w+)?}")
public Response getMetadata(InputStream is,
@Context HttpHeaders httpHeaders,
@Context UriInfo info,
diff --git a/tika-server/src/main/java/org/apache/tika/server/resource/TikaResource.java b/tika-server/src/main/java/org/apache/tika/server/resource/TikaResource.java
index 98287a1..288d11d 100644
--- a/tika-server/src/main/java/org/apache/tika/server/resource/TikaResource.java
+++ b/tika-server/src/main/java/org/apache/tika/server/resource/TikaResource.java
@@ -82,7 +82,7 @@ import org.xml.sax.SAXException;
@Path("/tika")
public class TikaResource {
- public static final String GREETING = "This is Tika Server ("+new Tika().toString()+"). Please PUT\n";
+ public static final String GREETING = "This is Tika Server (" + new Tika().toString() + "). Please PUT\n";
public static final String X_TIKA_OCR_HEADER_PREFIX = "X-Tika-OCR";
public static final String X_TIKA_PDF_HEADER_PREFIX = "X-Tika-PDF";
diff --git a/tika-server/src/main/java/org/apache/tika/server/resource/TranslateResource.java b/tika-server/src/main/java/org/apache/tika/server/resource/TranslateResource.java
index 8dad762..0aba6f9 100644
--- a/tika-server/src/main/java/org/apache/tika/server/resource/TranslateResource.java
+++ b/tika-server/src/main/java/org/apache/tika/server/resource/TranslateResource.java
@@ -108,5 +108,4 @@ public class TranslateResource {
}
return null;
}
-
}
diff --git a/tika-server/src/main/java/org/apache/tika/server/resource/UnpackerResource.java b/tika-server/src/main/java/org/apache/tika/server/resource/UnpackerResource.java
index 2292bef..716d171 100644
--- a/tika-server/src/main/java/org/apache/tika/server/resource/UnpackerResource.java
+++ b/tika-server/src/main/java/org/apache/tika/server/resource/UnpackerResource.java
@@ -77,7 +77,7 @@ public class UnpackerResource {
for (String name : metadata.names()) {
String[] values = metadata.getValues(name);
- ArrayList<String> list = new ArrayList<String>(values.length + 1);
+ ArrayList<String> list = new ArrayList<>(values.length + 1);
list.add(name);
list.addAll(Arrays.asList(values));
writer.writeNext(list.toArray(values));
@@ -135,7 +135,7 @@ public class UnpackerResource {
ch = new DefaultHandler();
}
- Map<String, byte[]> files = new HashMap<String, byte[]>();
+ Map<String, byte[]> files = new HashMap<>();
MutableInt count = new MutableInt();
pc.set(EmbeddedDocumentExtractor.class, new MyEmbeddedDocumentExtractor(count, files));
--
To stop receiving notification emails like this one, please contact
"commits@tika.apache.org" <co...@tika.apache.org>.