This is an automated email from the ASF dual-hosted git repository.
tallison 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 c0331e3 fix for TIKA-3398 contributed by kamaci (#439)
c0331e3 is described below
commit c0331e3f74635cda68a345402b2855792a0bc140
Author: Furkan KAMACI <[email protected]>
AuthorDate: Wed May 12 19:24:54 2021 +0300
fix for TIKA-3398 contributed by kamaci (#439)
Thank you @kamaci !
---
.../src/main/java/org/apache/tika/cli/TikaCLI.java | 2 -
.../src/main/java/org/apache/tika/gui/TikaGUI.java | 2 +-
.../java/org/apache/tika/pipes/PipesClient.java | 4 +-
.../org/apache/tika/sax/DIFContentHandler.java | 8 +-
.../java/org/apache/tika/utils/ParserUtils.java | 2 +-
.../java/org/apache/tika/fork/ForkParserTest.java | 2 +-
.../apache/tika/utils/ServiceLoaderUtilsTest.java | 3 +-
.../org/apache/tika/eval/app/AbstractProfiler.java | 4 +-
.../org/apache/tika/eval/app/ExtractProfiler.java | 2 +-
.../java/org/apache/tika/eval/app/TikaEvalCLI.java | 6 +-
.../java/org/apache/tika/eval/app/db/JDBCUtil.java | 3 +-
.../eval/app/tools/CommonTokenOverlapCounter.java | 2 +-
.../tika/eval/app/tools/TopCommonTokenCounter.java | 2 +-
.../apache/tika/eval/app/ProfilerBatchTest.java | 2 +-
.../tika/eval/app/db/AbstractBufferTest.java | 2 +-
.../tika/eval/core/tokens/TokenContraster.java | 2 +-
.../apache/tika/eval/core/langid/LangIdTest.java | 2 +-
.../tika/example/InterruptableParsingExample.java | 2 +-
.../org/apache/tika/example/RollbackSoftware.java | 3 +-
.../org/apache/tika/fuzzing/pdf/EvilCOSWriter.java | 2 +-
.../langdetect/tika/LanguageIdentifierTest.java | 14 +--
.../apache/tika/parser/journal/TEIDOMParser.java | 4 +-
.../tika/parser/ner/mitie/MITIENERecogniser.java | 9 +-
.../org/apache/tika/parser/mp3/ID3v1Handler.java | 4 +-
.../apache/tika/parser/code/SourceCodeParser.java | 2 +-
.../org/apache/tika/parser/crypto/TSDParser.java | 2 +-
.../org/apache/tika/parser/image/ICNSParser.java | 31 ++++--
.../org/apache/tika/parser/image/PSDParser.java | 3 +-
.../tika/parser/microsoft/AbstractListManager.java | 2 +-
.../tika/parser/microsoft/HSLFExtractor.java | 2 +-
.../apache/tika/parser/microsoft/ListManager.java | 2 +-
.../tika/parser/microsoft/WordExtractor.java | 12 +--
.../tika/parser/microsoft/chm/ChmBlockInfo.java | 10 +-
.../microsoft/chm/ChmDirectoryListingSet.java | 8 +-
.../tika/parser/microsoft/chm/ChmItsfHeader.java | 26 ++---
.../tika/parser/microsoft/chm/ChmItspHeader.java | 84 ++++++++++------
.../tika/parser/microsoft/chm/ChmLzxState.java | 83 +++++++++------
.../parser/microsoft/chm/ChmLzxcControlData.java | 31 ++++--
.../parser/microsoft/chm/ChmLzxcResetTable.java | 17 ++--
.../tika/parser/microsoft/chm/ChmPmgiHeader.java | 4 +-
.../tika/parser/microsoft/chm/ChmPmglHeader.java | 10 +-
.../microsoft/chm/DirectoryListingEntry.java | 10 +-
.../tika/parser/microsoft/onenote/IndentUtil.java | 6 +-
.../parser/microsoft/onenote/OneNoteParser.java | 3 +-
.../tika/parser/microsoft/onenote/OneNotePtr.java | 6 +-
.../ooxml/XSLFPowerPointExtractorDecorator.java | 2 +-
.../microsoft/ooxml/xps/XPSPageContentHandler.java | 2 +-
.../apache/tika/parser/dif/DIFContentHandler.java | 8 +-
.../apache/tika/parser/iptc/IptcAnpaParser.java | 112 ++++++++++-----------
.../tika/parser/ocr/TesseractOCRParserTest.java | 4 +-
.../tika/parser/pdf/ImageGraphicsEngine.java | 5 +-
.../org/apache/tika/parser/pdf/PDFParserTest.java | 1 +
.../tika/parser/strings/Latin1StringsParser.java | 5 +-
.../tika/parser/xmp/JempboxExtractorTest.java | 3 +-
.../pipesiterator/jdbc/JDBCPipesIterator.java | 2 +-
.../apache/tika/server/core/TikaServerConfig.java | 7 +-
.../tika/server/core/TikaServerWatchDog.java | 4 +-
.../org/apache/tika/xmp/convert/RTFConverter.java | 2 +-
58 files changed, 324 insertions(+), 275 deletions(-)
diff --git a/tika-app/src/main/java/org/apache/tika/cli/TikaCLI.java
b/tika-app/src/main/java/org/apache/tika/cli/TikaCLI.java
index c110a6d..5026a3e 100644
--- a/tika-app/src/main/java/org/apache/tika/cli/TikaCLI.java
+++ b/tika-app/src/main/java/org/apache/tika/cli/TikaCLI.java
@@ -67,7 +67,6 @@ import org.apache.tika.config.TikaConfig;
import org.apache.tika.config.TikaConfigSerializer;
import org.apache.tika.detect.CompositeDetector;
import org.apache.tika.detect.Detector;
-import org.apache.tika.exception.TikaConfigException;
import org.apache.tika.exception.TikaException;
import org.apache.tika.extractor.DefaultEmbeddedStreamTranslator;
import org.apache.tika.extractor.EmbeddedDocumentExtractor;
@@ -99,7 +98,6 @@ import org.apache.tika.parser.pdf.PDFParserConfig;
import org.apache.tika.pipes.FetchEmitTuple;
import org.apache.tika.pipes.PipesException;
import org.apache.tika.pipes.async.AsyncProcessor;
-import org.apache.tika.pipes.fetcher.Fetcher;
import org.apache.tika.pipes.pipesiterator.PipesIterator;
import org.apache.tika.sax.BasicContentHandlerFactory;
import org.apache.tika.sax.BodyContentHandler;
diff --git a/tika-app/src/main/java/org/apache/tika/gui/TikaGUI.java
b/tika-app/src/main/java/org/apache/tika/gui/TikaGUI.java
index 49e11f3..386d0d4 100644
--- a/tika-app/src/main/java/org/apache/tika/gui/TikaGUI.java
+++ b/tika-app/src/main/java/org/apache/tika/gui/TikaGUI.java
@@ -409,7 +409,7 @@ public class TikaGUI extends JFrame
private void handleError(String name, Throwable t) {
StringWriter writer = new StringWriter();
writer.append("Apache Tika was unable to parse the document\n");
- writer.append("at " + name + ".\n\n");
+ writer.append("at ").append(name).append(".\n\n");
writer.append("The full exception stack trace is included below:\n\n");
t.printStackTrace(new PrintWriter(writer));
diff --git a/tika-core/src/main/java/org/apache/tika/pipes/PipesClient.java
b/tika-core/src/main/java/org/apache/tika/pipes/PipesClient.java
index 09826b0..52d921c 100644
--- a/tika-core/src/main/java/org/apache/tika/pipes/PipesClient.java
+++ b/tika-core/src/main/java/org/apache/tika/pipes/PipesClient.java
@@ -234,9 +234,7 @@ public class PipesClient implements Closeable {
if (! hasExitOnOOM) {
//warn
}
- for (String arg : configArgs) {
- commandLine.add(arg);
- }
+ commandLine.addAll(configArgs);
commandLine.add("org.apache.tika.pipes.PipesServer");
commandLine.add(
ProcessUtils.escapeCommandLine(pipesConfig.getTikaConfig().toAbsolutePath().toString()));
diff --git a/tika-core/src/main/java/org/apache/tika/sax/DIFContentHandler.java
b/tika-core/src/main/java/org/apache/tika/sax/DIFContentHandler.java
index 9764437..b76c4d7 100644
--- a/tika-core/src/main/java/org/apache/tika/sax/DIFContentHandler.java
+++ b/tika-core/src/main/java/org/apache/tika/sax/DIFContentHandler.java
@@ -116,16 +116,16 @@ public class DIFContentHandler extends DefaultHandler {
}
if (this.isLeaf) {
Stack<String> tempStack = (Stack<String>) this.treeStack.clone();
- String key = "";
+ StringBuilder key = new StringBuilder();
while (!tempStack.isEmpty()) {
if (key.length() == 0) {
- key = tempStack.pop();
+ key = new StringBuilder(tempStack.pop());
} else {
- key = tempStack.pop() + "-" + key;
+ key.insert(0, tempStack.pop() + "-");
}
}
String value = this.dataStack.peek();
- this.metadata.add(key, value);
+ this.metadata.add(key.toString(), value);
this.isLeaf = false;
}
this.treeStack.pop();
diff --git a/tika-core/src/main/java/org/apache/tika/utils/ParserUtils.java
b/tika-core/src/main/java/org/apache/tika/utils/ParserUtils.java
index 10e9243..c1400fd 100644
--- a/tika-core/src/main/java/org/apache/tika/utils/ParserUtils.java
+++ b/tika-core/src/main/java/org/apache/tika/utils/ParserUtils.java
@@ -80,7 +80,7 @@ public class ParserUtils {
String[] parsedBys =
metadata.getValues(TikaCoreProperties.TIKA_PARSED_BY);
if (parsedBys == null || parsedBys.length == 0) {
metadata.add(TikaCoreProperties.TIKA_PARSED_BY, className);
- } else if (! Arrays.stream(parsedBys).anyMatch(className::equals)) {
+ } else if (Arrays.stream(parsedBys).noneMatch(className::equals)) {
//only add parser once
metadata.add(TikaCoreProperties.TIKA_PARSED_BY, className);
}
diff --git a/tika-core/src/test/java/org/apache/tika/fork/ForkParserTest.java
b/tika-core/src/test/java/org/apache/tika/fork/ForkParserTest.java
index bd992b4..6cfeb23 100644
--- a/tika-core/src/test/java/org/apache/tika/fork/ForkParserTest.java
+++ b/tika-core/src/test/java/org/apache/tika/fork/ForkParserTest.java
@@ -491,7 +491,7 @@ public class ForkParserTest extends TikaTest {
}
if (!contentHandler.getClass().equals(DefaultHandler.class)) {
sb.append("\n");
- sb.append("CONTENT: " + contentHandler.toString());
+ sb.append("CONTENT: ").append(contentHandler);
sb.append("\n\n");
}
return sb.toString().getBytes(StandardCharsets.UTF_8);
diff --git
a/tika-core/src/test/java/org/apache/tika/utils/ServiceLoaderUtilsTest.java
b/tika-core/src/test/java/org/apache/tika/utils/ServiceLoaderUtilsTest.java
index bb79311..269e77c 100644
--- a/tika-core/src/test/java/org/apache/tika/utils/ServiceLoaderUtilsTest.java
+++ b/tika-core/src/test/java/org/apache/tika/utils/ServiceLoaderUtilsTest.java
@@ -44,8 +44,7 @@ public class ServiceLoaderUtilsTest {
Detector[] detectors = new Detector[]{new MyCustomDetector(), new
EmptyDetector(),
new FileCommandDetector(), new OverrideDetector(), new
ZeroSizeFileDetector()};
List<Detector> expected = Arrays.asList(detectors);
- List<Detector> shuffled = new ArrayList<>();
- shuffled.addAll(expected);
+ List<Detector> shuffled = new ArrayList<>(expected);
Random random = new Random(42);
for (int i = 0; i < 10; i++) {
Collections.shuffle(shuffled, random);
diff --git
a/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/AbstractProfiler.java
b/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/AbstractProfiler.java
index 7202204..5e5756e 100644
---
a/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/AbstractProfiler.java
+++
b/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/AbstractProfiler.java
@@ -609,7 +609,7 @@ public abstract class AbstractProfiler extends
FileResourceConsumer {
if (i > 0) {
sb.append(" | ");
}
- sb.append(pairs.get(i).getKey() + ": " + pairs.get(i).getValue());
+ sb.append(pairs.get(i).getKey()).append(":
").append(pairs.get(i).getValue());
}
data.put(Cols.UNICODE_CHAR_BLOCKS, sb.toString());
}
@@ -648,7 +648,7 @@ public abstract class AbstractProfiler extends
FileResourceConsumer {
if (i++ > 0) {
sb.append(" | ");
}
- sb.append(t.getToken() + ": " + t.getValue());
+ sb.append(t.getToken()).append(": ").append(t.getValue());
}
data.put(Cols.TOP_N_TOKENS, sb.toString());
diff --git
a/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/ExtractProfiler.java
b/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/ExtractProfiler.java
index edaa2e4..5c041c6 100644
---
a/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/ExtractProfiler.java
+++
b/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/ExtractProfiler.java
@@ -193,7 +193,7 @@ public class ExtractProfiler extends AbstractProfiler {
}
Map<Cols, String> contOutput = new HashMap<>();
- Long srcFileLen = getSourceFileLength(fps, metadataList);
+ long srcFileLen = getSourceFileLength(fps, metadataList);
contOutput.put(Cols.LENGTH,
srcFileLen > NON_EXISTENT_FILE_LENGTH ?
Long.toString(srcFileLen) : "");
contOutput.put(Cols.CONTAINER_ID, containerIdString);
diff --git
a/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/TikaEvalCLI.java
b/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/TikaEvalCLI.java
index 5a71544..20e9db6 100644
---
a/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/TikaEvalCLI.java
+++
b/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/TikaEvalCLI.java
@@ -40,7 +40,7 @@ public class TikaEvalCLI {
StringBuilder sb = new StringBuilder();
sb.append("Must specify one of the following tools in the first
parameter:\n");
for (String s : tools) {
- sb.append(s + "\n");
+ sb.append(s).append("\n");
}
return sb.toString();
@@ -82,7 +82,7 @@ public class TikaEvalCLI {
}
private void handleProfileFiles(String[] subsetArgs) throws Exception {
- List<String> argList = new ArrayList(Arrays.asList(subsetArgs));
+ List<String> argList = Arrays.asList(subsetArgs);
boolean containsBC = false;
String inputDir = null;
@@ -106,7 +106,7 @@ public class TikaEvalCLI {
argList.add(tmpBCConfig.toAbsolutePath().toString());
}
- String[] updatedArgs = argList.toArray(new String[argList.size()]);
+ String[] updatedArgs = argList.toArray(new String[0]);
DefaultParser defaultCLIParser = new DefaultParser();
try {
CommandLine commandLine =
defaultCLIParser.parse(FileProfiler.OPTIONS, updatedArgs);
diff --git
a/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/db/JDBCUtil.java
b/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/db/JDBCUtil.java
index 0f30540..4988642 100644
---
a/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/db/JDBCUtil.java
+++
b/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/db/JDBCUtil.java
@@ -278,7 +278,7 @@ public class JDBCUtil {
//does not close the connection
private void createTable(Connection conn, TableInfo tableInfo) throws
SQLException {
StringBuilder createSql = new StringBuilder();
- createSql.append("CREATE TABLE " + tableInfo.getName());
+ createSql.append("CREATE TABLE ").append(tableInfo.getName());
createSql.append("(");
int last = 0;
@@ -299,7 +299,6 @@ public class JDBCUtil {
createSql.append(")");
try (Statement st = conn.createStatement()) {
st.execute(createSql.toString());
- st.close();
}
conn.commit();
}
diff --git
a/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/tools/CommonTokenOverlapCounter.java
b/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/tools/CommonTokenOverlapCounter.java
index 79d3136..d78a64a 100644
---
a/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/tools/CommonTokenOverlapCounter.java
+++
b/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/tools/CommonTokenOverlapCounter.java
@@ -61,7 +61,7 @@ public class CommonTokenOverlapCounter {
denom = setA.size() + setB.size();
double percent = (double) overlap / (double) denom;
if (percent > 0.01) {
- System.out.println(String.format(Locale.US, "%s %s %.2f", langA,
langB, percent));
+ System.out.printf(Locale.US, "%s %s %.2f%n", langA, langB,
percent);
}
}
diff --git
a/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/tools/TopCommonTokenCounter.java
b/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/tools/TopCommonTokenCounter.java
index 484729b..c15eb1b 100644
---
a/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/tools/TopCommonTokenCounter.java
+++
b/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/tools/TopCommonTokenCounter.java
@@ -258,7 +258,7 @@ public class TopCommonTokenCounter {
return new BufferedReader(new InputStreamReader(is,
StandardCharsets.UTF_8));
}
- private abstract class AbstractTokenTFDFPriorityQueue extends
PriorityQueue<TokenDFTF> {
+ private abstract static class AbstractTokenTFDFPriorityQueue extends
PriorityQueue<TokenDFTF> {
AbstractTokenTFDFPriorityQueue(int maxSize) {
super(maxSize);
diff --git
a/tika-eval/tika-eval-app/src/test/java/org/apache/tika/eval/app/ProfilerBatchTest.java
b/tika-eval/tika-eval-app/src/test/java/org/apache/tika/eval/app/ProfilerBatchTest.java
index 701ee81..a39ff01 100644
---
a/tika-eval/tika-eval-app/src/test/java/org/apache/tika/eval/app/ProfilerBatchTest.java
+++
b/tika-eval/tika-eval-app/src/test/java/org/apache/tika/eval/app/ProfilerBatchTest.java
@@ -59,7 +59,7 @@ public class ProfilerBatchTest {
public static void setUp() throws Exception {
Path inputRoot = Paths.get(
- new
ComparerBatchTest().getClass().getResource("/test-dirs/extractsA").toURI());
+
ComparerBatchTest.class.getResource("/test-dirs/extractsA").toURI());
dbDir = Files.createTempDirectory(inputRoot, "tika-test-db-dir-");
Map<String, String> args = new HashMap<>();
Path db = dbDir.resolve("profiler_test");
diff --git
a/tika-eval/tika-eval-app/src/test/java/org/apache/tika/eval/app/db/AbstractBufferTest.java
b/tika-eval/tika-eval-app/src/test/java/org/apache/tika/eval/app/db/AbstractBufferTest.java
index 4e14256..2df0cec 100644
---
a/tika-eval/tika-eval-app/src/test/java/org/apache/tika/eval/app/db/AbstractBufferTest.java
+++
b/tika-eval/tika-eval-app/src/test/java/org/apache/tika/eval/app/db/AbstractBufferTest.java
@@ -77,7 +77,7 @@ public class AbstractBufferTest {
assertEquals(keys.size(), b.getNumWrites());
}
- private class Tester implements Callable<MyTestResult> {
+ private static class Tester implements Callable<MyTestResult> {
private final AbstractDBBuffer dbBuffer;
private final int numGets;
diff --git
a/tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/tokens/TokenContraster.java
b/tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/tokens/TokenContraster.java
index 84ddb18..b618625 100644
---
a/tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/tokens/TokenContraster.java
+++
b/tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/tokens/TokenContraster.java
@@ -137,7 +137,7 @@ public class TokenContraster {
}
- class TokenCountDiffQueue extends PriorityQueue<TokenCountDiff> {
+ static class TokenCountDiffQueue extends PriorityQueue<TokenCountDiff> {
TokenCountDiffQueue(int maxSize) {
super(maxSize);
diff --git
a/tika-eval/tika-eval-core/src/test/java/org/apache/tika/eval/core/langid/LangIdTest.java
b/tika-eval/tika-eval-core/src/test/java/org/apache/tika/eval/core/langid/LangIdTest.java
index f5e8bb7..bff574c 100644
---
a/tika-eval/tika-eval-core/src/test/java/org/apache/tika/eval/core/langid/LangIdTest.java
+++
b/tika-eval/tika-eval-core/src/test/java/org/apache/tika/eval/core/langid/LangIdTest.java
@@ -49,7 +49,7 @@ public class LangIdTest {
for (String lang : langs) {
Set<String> tokens = commonTokens.getTokens(lang);
if (tokens.size() == 0) {
- System.out.println(String.format(Locale.US, "missing common
tokens for: %s", lang));
+ System.out.printf(Locale.US, "missing common tokens for:
%s%n", lang);
} else if (tokens.size() < 250) { //ssw has 255
fail(String.format(Locale.US, "common tokens too small (%s)
for: %s", tokens.size(),
lang));
diff --git
a/tika-example/src/main/java/org/apache/tika/example/InterruptableParsingExample.java
b/tika-example/src/main/java/org/apache/tika/example/InterruptableParsingExample.java
index 9ef1085..652ddc8 100644
---
a/tika-example/src/main/java/org/apache/tika/example/InterruptableParsingExample.java
+++
b/tika-example/src/main/java/org/apache/tika/example/InterruptableParsingExample.java
@@ -71,7 +71,7 @@ public class InterruptableParsingExample {
* <p>
* Throws {@link QueryMatchedException} when query string is found.
*/
- class InterruptingContentHandler extends DefaultHandler {
+ static class InterruptingContentHandler extends DefaultHandler {
private String query;
private StringBuilder sb = new StringBuilder();
diff --git
a/tika-example/src/main/java/org/apache/tika/example/RollbackSoftware.java
b/tika-example/src/main/java/org/apache/tika/example/RollbackSoftware.java
index 6a57450..83377cf 100755
--- a/tika-example/src/main/java/org/apache/tika/example/RollbackSoftware.java
+++ b/tika-example/src/main/java/org/apache/tika/example/RollbackSoftware.java
@@ -22,7 +22,6 @@ import static java.nio.charset.StandardCharsets.UTF_8;
import java.io.File;
import java.io.IOException;
import java.io.InputStream;
-import java.util.Arrays;
import java.util.Collections;
import java.util.Comparator;
import java.util.HashSet;
@@ -84,7 +83,7 @@ public class RollbackSoftware {
*/
public Set<MediaType> getSupportedTypes(ParseContext context) {
return Collections
- .unmodifiableSet(new
HashSet<>(Arrays.asList(MediaType.TEXT_PLAIN)));
+ .unmodifiableSet(new
HashSet<>(Collections.singletonList(MediaType.TEXT_PLAIN)));
}
/*
diff --git
a/tika-fuzzing/src/main/java/org/apache/tika/fuzzing/pdf/EvilCOSWriter.java
b/tika-fuzzing/src/main/java/org/apache/tika/fuzzing/pdf/EvilCOSWriter.java
index dcfd40a..58292a0 100644
--- a/tika-fuzzing/src/main/java/org/apache/tika/fuzzing/pdf/EvilCOSWriter.java
+++ b/tika-fuzzing/src/main/java/org/apache/tika/fuzzing/pdf/EvilCOSWriter.java
@@ -1317,7 +1317,7 @@ public class EvilCOSWriter implements ICOSVisitor,
Closeable {
* policy.
*/
public void write(PDDocument doc, SignatureInterface signInterface) throws
IOException {
- Long idTime = doc.getDocumentId() == null ? System.currentTimeMillis()
:
+ long idTime = doc.getDocumentId() == null ? System.currentTimeMillis()
:
doc.getDocumentId();
pdDocument = doc;
diff --git
a/tika-langdetect/tika-langdetect-tika/src/test/java/org/apache/tika/langdetect/tika/LanguageIdentifierTest.java
b/tika-langdetect/tika-langdetect-tika/src/test/java/org/apache/tika/langdetect/tika/LanguageIdentifierTest.java
index e58b971..0e47293 100644
---
a/tika-langdetect/tika-langdetect-tika/src/test/java/org/apache/tika/langdetect/tika/LanguageIdentifierTest.java
+++
b/tika-langdetect/tika-langdetect-tika/src/test/java/org/apache/tika/langdetect/tika/LanguageIdentifierTest.java
@@ -114,7 +114,7 @@ public class LanguageIdentifierTest {
for (int m = 0; m < MRUNS; m++) {
LanguageProfile.useInterleaved =
(m & 1) == 1; // Alternate between standard and interleaved
- String currentResult = "";
+ StringBuilder currentResult = new StringBuilder();
final long start = System.nanoTime();
for (int i = 0; i < IRUNS; i++) {
for (String language : languages) {
@@ -122,21 +122,21 @@ public class LanguageIdentifierTest {
writeTo(language, writer);
LanguageIdentifier identifier = new
LanguageIdentifier(writer.getProfile());
if (identifier.isReasonablyCertain()) {
- currentResult += identifier.getLanguage();
+ currentResult.append(identifier.getLanguage());
detected++;
}
}
}
- System.out.println(String.format(Locale.ROOT,
- "Performed %d detections at %2d ms/test with
interleaved=%b",
+ System.out.printf(Locale.ROOT,
+ "Performed %d detections at %2d ms/test with
interleaved=%b%n",
languages.length * IRUNS,
(System.nanoTime() - start) / 1000000 / (languages.length
* IRUNS),
- LanguageProfile.useInterleaved));
+ LanguageProfile.useInterleaved);
if (lastResult !=
null) { // Might as well test that they behave the same
while we're at it
- assertEquals("This result should be equal to the last",
lastResult, currentResult);
+ assertEquals("This result should be equal to the last",
lastResult, currentResult.toString());
}
- lastResult = currentResult;
+ lastResult = currentResult.toString();
}
if (detected == -1) {
System.out.println(
diff --git
a/tika-parsers/tika-parsers-advanced/tika-parser-nlp-module/src/main/java/org/apache/tika/parser/journal/TEIDOMParser.java
b/tika-parsers/tika-parsers-advanced/tika-parser-nlp-module/src/main/java/org/apache/tika/parser/journal/TEIDOMParser.java
index 52fecc9..f43cbd0 100644
---
a/tika-parsers/tika-parsers-advanced/tika-parser-nlp-module/src/main/java/org/apache/tika/parser/journal/TEIDOMParser.java
+++
b/tika-parsers/tika-parsers-advanced/tika-parser-nlp-module/src/main/java/org/apache/tika/parser/journal/TEIDOMParser.java
@@ -586,7 +586,7 @@ public class TEIDOMParser {
}
- class OrgName {
+ static class OrgName {
private List<OrgTypeName> typeNames;
public OrgName() {
@@ -710,7 +710,7 @@ public class TEIDOMParser {
}
}
- private class Address {
+ private static class Address {
private String region;
private String postCode;
diff --git
a/tika-parsers/tika-parsers-advanced/tika-parser-nlp-module/src/main/java/org/apache/tika/parser/ner/mitie/MITIENERecogniser.java
b/tika-parsers/tika-parsers-advanced/tika-parser-nlp-module/src/main/java/org/apache/tika/parser/ner/mitie/MITIENERecogniser.java
index b83b5ee..8686476 100644
---
a/tika-parsers/tika-parsers-advanced/tika-parser-nlp-module/src/main/java/org/apache/tika/parser/ner/mitie/MITIENERecogniser.java
+++
b/tika-parsers/tika-parsers-advanced/tika-parser-nlp-module/src/main/java/org/apache/tika/parser/ner/mitie/MITIENERecogniser.java
@@ -155,11 +155,12 @@ public class MITIENERecogniser implements NERecogniser {
.invoke(entityMentionObject);
int end = (Integer) entityMentionClass.getMethod("getEnd")
.invoke(entityMentionObject);
- String match = "";
- for (; start < end; start++) {
- match += stringVector.get(start) + " ";
+ StringBuilder match = new StringBuilder();
+ while (start < end) {
+ match.append(stringVector.get(start)).append(" ");
+ start++;
}
- x.add(match.trim());
+ x.add(match.toString().trim());
}
} catch (Exception e) {
diff --git
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-audiovideo-module/src/main/java/org/apache/tika/parser/mp3/ID3v1Handler.java
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-audiovideo-module/src/main/java/org/apache/tika/parser/mp3/ID3v1Handler.java
index ca4803f..7029d41 100644
---
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-audiovideo-module/src/main/java/org/apache/tika/parser/mp3/ID3v1Handler.java
+++
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-audiovideo-module/src/main/java/org/apache/tika/parser/mp3/ID3v1Handler.java
@@ -20,7 +20,7 @@ import static java.nio.charset.StandardCharsets.ISO_8859_1;
import java.io.IOException;
import java.io.InputStream;
-import java.util.Arrays;
+import java.util.Collections;
import java.util.List;
import org.xml.sax.ContentHandler;
@@ -135,7 +135,7 @@ public class ID3v1Handler implements ID3Tags {
}
public List<ID3Comment> getComments() {
- return Arrays.asList(comment);
+ return Collections.singletonList(comment);
}
public String getGenre() {
diff --git
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-code-module/src/main/java/org/apache/tika/parser/code/SourceCodeParser.java
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-code-module/src/main/java/org/apache/tika/parser/code/SourceCodeParser.java
index 00b39c2..1b675b0 100644
---
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-code-module/src/main/java/org/apache/tika/parser/code/SourceCodeParser.java
+++
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-code-module/src/main/java/org/apache/tika/parser/code/SourceCodeParser.java
@@ -105,7 +105,7 @@ public class SourceCodeParser extends
AbstractEncodingDetectorParser {
String line;
int nbLines = 0;
while ((line = reader.readLine()) != null) {
- out.append(line + System.getProperty("line.separator"));
+
out.append(line).append(System.getProperty("line.separator"));
String author = parserAuthor(line);
if (author != null) {
metadata.add(TikaCoreProperties.CREATOR, author);
diff --git
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-crypto-module/src/main/java/org/apache/tika/parser/crypto/TSDParser.java
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-crypto-module/src/main/java/org/apache/tika/parser/crypto/TSDParser.java
index 397d581..5d0b05e 100644
---
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-crypto-module/src/main/java/org/apache/tika/parser/crypto/TSDParser.java
+++
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-crypto-module/src/main/java/org/apache/tika/parser/crypto/TSDParser.java
@@ -140,7 +140,7 @@ public class TSDParser extends AbstractParser {
}
private void buildMetas(List<TSDMetas> tsdMetasList, Metadata metadata) {
- Integer count = 1;
+ int count = 1;
for (TSDMetas tsdm : tsdMetasList) {
metadata.set(TSD_LOOP_LABEL + count + " - " +
Metadata.CONTENT_TYPE, TSD_MIME_TYPE);
diff --git
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-image-module/src/main/java/org/apache/tika/parser/image/ICNSParser.java
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-image-module/src/main/java/org/apache/tika/parser/image/ICNSParser.java
index 095cd05..9b32b42 100644
---
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-image-module/src/main/java/org/apache/tika/parser/image/ICNSParser.java
+++
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-image-module/src/main/java/org/apache/tika/parser/image/ICNSParser.java
@@ -101,30 +101,39 @@ public class ICNSParser extends AbstractParser {
}
offset = offset + icon_length;
}
- String icon_details = "", iconmask_details = "", bitsPerPixel,
dimensions;
+ StringBuilder icon_details = new StringBuilder();
+ StringBuilder iconmask_details = new StringBuilder();
+ String bitsPerPixel;
+ String dimensions;
for (ICNSType icon : icons) {
bitsPerPixel = (icon.getBitsPerPixel() != 0) ?
icon.getBitsPerPixel() + " bpp" :
"JPEG 2000 or PNG format";
dimensions = (!icon.hasRetinaDisplay()) ? (icon.getHeight() + "x"
+ icon.getWidth()) :
(icon.getHeight() + "x" + icon.getWidth() + "@2X");
- icon_details = icon_details + ", " + dimensions + " (" +
bitsPerPixel + ")";
+ icon_details.append(", ").append(dimensions).append("
(").append(bitsPerPixel).append(")");
}
for (ICNSType icon : icon_masks) {
- iconmask_details =
- iconmask_details + ", " + icon.getHeight() + "x" +
icon.getWidth() + " (" +
- icon.getBitsPerPixel() + " bpp" + ")";
+ iconmask_details
+ .append(", ")
+ .append(icon.getHeight())
+ .append("x")
+ .append(icon.getWidth())
+ .append(" (")
+ .append(icon.getBitsPerPixel())
+ .append(" bpp")
+ .append(")");
}
metadata.set(Metadata.CONTENT_TYPE, ICNS_MIME_TYPE);
- if (!icon_details.equals("")) {
+ if (!icon_details.toString().equals("")) {
metadata.set("Icon count", String.valueOf(icons.size()));
- icon_details = icon_details.substring(2);
- metadata.set("Icon details", icon_details);
+ icon_details = new StringBuilder(icon_details.substring(2));
+ metadata.set("Icon details", icon_details.toString());
}
- if (!iconmask_details.equals("")) {
+ if (!iconmask_details.toString().equals("")) {
metadata.set("Masked icon count",
String.valueOf(icon_masks.size()));
- iconmask_details = iconmask_details.substring(2);
- metadata.set("Masked icon details", iconmask_details);
+ iconmask_details = new
StringBuilder(iconmask_details.substring(2));
+ metadata.set("Masked icon details", iconmask_details.toString());
}
XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
xhtml.startDocument();
diff --git
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-image-module/src/main/java/org/apache/tika/parser/image/PSDParser.java
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-image-module/src/main/java/org/apache/tika/parser/image/PSDParser.java
index 752891b..997b6e3 100644
---
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-image-module/src/main/java/org/apache/tika/parser/image/PSDParser.java
+++
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-image-module/src/main/java/org/apache/tika/parser/image/PSDParser.java
@@ -22,7 +22,6 @@ import java.io.ByteArrayInputStream;
import java.io.EOFException;
import java.io.IOException;
import java.io.InputStream;
-import java.util.Arrays;
import java.util.Collections;
import java.util.HashSet;
import java.util.Set;
@@ -61,7 +60,7 @@ public class PSDParser extends AbstractParser {
private static final long serialVersionUID = 883387734607994914L;
private static final Set<MediaType> SUPPORTED_TYPES =
Collections.unmodifiableSet(
- new
HashSet<>(Arrays.asList(MediaType.image("vnd.adobe.photoshop"))));
+ new
HashSet<>(Collections.singletonList(MediaType.image("vnd.adobe.photoshop"))));
private static final int MAX_DATA_LENGTH_BYTES = 10_000_000;
private static final int MAX_BLOCKS = 10000;
diff --git
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/AbstractListManager.java
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/AbstractListManager.java
index 7857509..2e5f8f2 100644
---
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/AbstractListManager.java
+++
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/AbstractListManager.java
@@ -33,7 +33,7 @@ public abstract class AbstractListManager {
protected Map<Integer, LevelTuple[]> overrideTupleMap = new HashMap<>();
//helper class that is docx/doc format agnostic
- protected class ParagraphLevelCounter {
+ protected static class ParagraphLevelCounter {
//counts can == 0 if the format is decimal, make sure
//that flag values are < 0
diff --git
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/HSLFExtractor.java
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/HSLFExtractor.java
index aa89ee0..2b20089 100644
---
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/HSLFExtractor.java
+++
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/HSLFExtractor.java
@@ -179,7 +179,7 @@ public class HSLFExtractor extends AbstractPOIFSExtractor {
if (authorStringBuilder.length() > 0) {
authorStringBuilder.append(" ");
}
- authorStringBuilder.append("(" + comment.getAuthorInitials() +
")");
+
authorStringBuilder.append("(").append(comment.getAuthorInitials()).append(")");
}
if (authorStringBuilder.length() > 0) {
if (comment.getText() != null) {
diff --git
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ListManager.java
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ListManager.java
index fa7a4f2..404d98a 100644
---
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ListManager.java
+++
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ListManager.java
@@ -164,7 +164,7 @@ public class ListManager extends AbstractListManager {
//adds one. In .doc, this was the array index;
//but in .docx, this is the level number
int lvlNum = (int) numberText.charAt(offset - 1) + 1;
- sb.append("%" + lvlNum);
+ sb.append("%").append(lvlNum);
last = offset;
}
if (last < numberText.length()) {
diff --git
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/WordExtractor.java
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/WordExtractor.java
index 0e44076..f8ff5e1 100644
---
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/WordExtractor.java
+++
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/WordExtractor.java
@@ -456,15 +456,15 @@ public class WordExtractor extends AbstractPOIFSExtractor
{
// Do we need to do something special with this?
if (controls.size() > 0) {
- String text = controls.get(0).text();
+ StringBuilder text = new StringBuilder(controls.get(0).text());
for (int j = 1; j < controls.size(); j++) {
- text += controls.get(j).text();
+ text.append(controls.get(j).text());
}
- if ((text.startsWith("HYPERLINK") || text.startsWith("
HYPERLINK")) &&
- text.indexOf('"') > -1) {
- int start = text.indexOf('"') + 1;
- int end = findHyperlinkEnd(text, start);
+ if ((text.toString().startsWith("HYPERLINK") ||
text.toString().startsWith(" HYPERLINK"))
+ && text.toString().indexOf('"') > -1) {
+ int start = text.toString().indexOf('"') + 1;
+ int end = findHyperlinkEnd(text.toString(), start);
String url = "";
if (start >= 0 && start < end && end <= text.length()) {
url = text.substring(start, end);
diff --git
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmBlockInfo.java
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmBlockInfo.java
index 3162eea..817ac78 100644
---
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmBlockInfo.java
+++
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmBlockInfo.java
@@ -93,11 +93,11 @@ public class ChmBlockInfo {
*/
public String toString() {
StringBuilder sb = new StringBuilder();
- sb.append("iniBlock:=" + getIniBlock() + ", ");
- sb.append("startBlock:=" + getStartBlock() + ", ");
- sb.append("endBlock:=" + getEndBlock() + ", ");
- sb.append("startOffset:=" + getStartOffset() + ", ");
- sb.append("endOffset:=" + getEndOffset() +
System.getProperty("line.separator"));
+ sb.append("iniBlock:=").append(getIniBlock()).append(", ");
+ sb.append("startBlock:=").append(getStartBlock()).append(", ");
+ sb.append("endBlock:=").append(getEndBlock()).append(", ");
+ sb.append("startOffset:=").append(getStartOffset()).append(", ");
+
sb.append("endOffset:=").append(getEndOffset()).append(System.getProperty("line.separator"));
return sb.toString();
}
diff --git
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmDirectoryListingSet.java
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmDirectoryListingSet.java
index b2153d5..87538c4 100644
---
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmDirectoryListingSet.java
+++
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmDirectoryListingSet.java
@@ -75,9 +75,11 @@ public class ChmDirectoryListingSet {
public String toString() {
StringBuilder sb = new StringBuilder();
- sb.append("list:=" + getDirectoryListingEntryList().toString() +
- System.getProperty("line.separator"));
- sb.append("number of list items:=" +
getDirectoryListingEntryList().size());
+ sb.append("list:=")
+ .append(getDirectoryListingEntryList().toString())
+ .append(System.getProperty("line.separator"));
+ sb.append("number of list items:=")
+ .append(getDirectoryListingEntryList().size());
return sb.toString();
}
diff --git
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmItsfHeader.java
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmItsfHeader.java
index 990b06a..5fcb3c7 100644
---
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmItsfHeader.java
+++
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmItsfHeader.java
@@ -66,19 +66,19 @@ public class ChmItsfHeader implements
ChmAccessor<ChmItsfHeader> {
*/
public String toString() {
StringBuilder sb = new StringBuilder();
- sb.append(new String(getSignature(), UTF_8) + " ");
- sb.append(getVersion() + " ");
- sb.append(getHeaderLen() + " ");
- sb.append(getUnknown_000c() + " ");
- sb.append(getLastModified() + " ");
- sb.append(getLangId() + " ");
- sb.append(getDir_uuid() + " ");
- sb.append(getStream_uuid() + " ");
- sb.append(getUnknownOffset() + " ");
- sb.append(getUnknownLen() + " ");
- sb.append(getDirOffset() + " ");
- sb.append(getDirLen() + " ");
- sb.append(getDataOffset() + " ");
+ sb.append(new String(getSignature(), UTF_8)).append(" ");
+ sb.append(getVersion()).append(" ");
+ sb.append(getHeaderLen()).append(" ");
+ sb.append(getUnknown_000c()).append(" ");
+ sb.append(getLastModified()).append(" ");
+ sb.append(getLangId()).append(" ");
+ sb.append(getDir_uuid()).append(" ");
+ sb.append(getStream_uuid()).append(" ");
+ sb.append(getUnknownOffset()).append(" ");
+ sb.append(getUnknownLen()).append(" ");
+ sb.append(getDirOffset()).append(" ");
+ sb.append(getDirLen()).append(" ");
+ sb.append(getDataOffset()).append(" ");
return sb.toString();
}
diff --git
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmItspHeader.java
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmItspHeader.java
index 3015733..d9176d9 100644
---
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmItspHeader.java
+++
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmItspHeader.java
@@ -68,35 +68,61 @@ public class ChmItspHeader implements
ChmAccessor<ChmItspHeader> {
public String toString() {
StringBuilder sb = new StringBuilder();
- sb.append("[ signature:=" + new String(getSignature(), UTF_8) +
- System.getProperty("line.separator"));
- sb.append("version:=\t" + getVersion() +
System.getProperty("line.separator"));
- sb.append("header_len:=\t" + getHeader_len() +
System.getProperty("line.separator"));
- sb.append("unknown_00c:=\t" + getUnknown_000c() +
System.getProperty("line.separator"));
- sb.append("block_len:=\t" + getBlock_len() + " [directory chunk size]"
+
- System.getProperty("line.separator"));
- sb.append("blockidx_intvl:=" + getBlockidx_intvl() +
- ", density of quickref section, usually 2" +
System.getProperty("line.separator"));
- sb.append("index_depth:=\t" + getIndex_depth() +
- ", depth of the index tree - 1 there is no index, 2 if there
is one level of PMGI" +
- " chunk" + System.getProperty("line.separator"));
- sb.append("index_root:=\t" + getIndex_root() +
- ", chunk number of root index chunk, -1 if there is none" +
- System.getProperty("line.separator"));
- sb.append("index_head:=\t" + getIndex_head() +
- ", chunk number of first PMGL (listing) chunk" +
- System.getProperty("line.separator"));
- sb.append("unknown_0024:=\t" + getUnknown_0024() +
- ", chunk number of last PMGL (listing) chunk" +
- System.getProperty("line.separator"));
- sb.append("num_blocks:=\t" + getNum_blocks() + ", -1 (unknown)" +
- System.getProperty("line.separator"));
- sb.append("unknown_002c:=\t" + getUnknown_002c() + ", number of
directory chunks (total)" +
- System.getProperty("line.separator"));
- sb.append("lang_id:=\t" + getLang_id() + " - " +
ChmCommons.getLanguage(getLang_id()) +
- System.getProperty("line.separator"));
- sb.append("system_uuid:=" + getSystem_uuid() +
System.getProperty("line.separator"));
- sb.append("unknown_0044:=" + getUnknown_0044() + " ]");
+ sb.append("[ signature:=")
+ .append(new String(getSignature(), UTF_8))
+ .append(System.getProperty("line.separator"));
+ sb.append("version:=\t")
+ .append(getVersion())
+ .append(System.getProperty("line.separator"));
+ sb.append("header_len:=\t")
+ .append(getHeader_len())
+ .append(System.getProperty("line.separator"));
+ sb.append("unknown_00c:=\t")
+ .append(getUnknown_000c())
+ .append(System.getProperty("line.separator"));
+ sb.append("block_len:=\t")
+ .append(getBlock_len())
+ .append(" [directory chunk size]")
+ .append(System.getProperty("line.separator"));
+ sb.append("blockidx_intvl:=")
+ .append(getBlockidx_intvl())
+ .append(", density of quickref section, usually 2")
+ .append(System.getProperty("line.separator"));
+ sb.append("index_depth:=\t")
+ .append(getIndex_depth())
+ .append(", depth of the index tree - 1 there is no index, 2 if
there is one level of PMGI")
+ .append(" chunk")
+ .append(System.getProperty("line.separator"));
+ sb.append("index_root:=\t")
+ .append(getIndex_root())
+ .append(", chunk number of root index chunk, -1 if there is
none")
+ .append(System.getProperty("line.separator"));
+ sb.append("index_head:=\t")
+ .append(getIndex_head())
+ .append(", chunk number of first PMGL (listing) chunk")
+ .append(System.getProperty("line.separator"));
+ sb.append("unknown_0024:=\t")
+ .append(getUnknown_0024())
+ .append(", chunk number of last PMGL (listing) chunk")
+ .append(System.getProperty("line.separator"));
+ sb.append("num_blocks:=\t")
+ .append(getNum_blocks())
+ .append(", -1 (unknown)")
+ .append(System.getProperty("line.separator"));
+ sb.append("unknown_002c:=\t")
+ .append(getUnknown_002c()).append(", number of directory
chunks (total)")
+ .append(System.getProperty("line.separator"));
+ sb.append("lang_id:=\t")
+ .append(getLang_id())
+ .append(" - ")
+ .append(ChmCommons.getLanguage(getLang_id()))
+ .append(System.getProperty("line.separator"));
+ sb.append("system_uuid:=")
+ .append(getSystem_uuid())
+ .append(System.getProperty("line.separator"));
+ sb.append("unknown_0044:=")
+ .append(getUnknown_0044())
+ .append(" ]");
return sb.toString();
}
diff --git
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmLzxState.java
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmLzxState.java
index 1fb445d..a41ee80 100644
---
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmLzxState.java
+++
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmLzxState.java
@@ -145,38 +145,57 @@ public class ChmLzxState implements Cloneable {
*/
public String toString() {
StringBuilder sb = new StringBuilder();
- sb.append("actual decoding window:=" + getWindow() +
System.getProperty("line.separator"));
- sb.append("window size (32Kb through 2Mb):=" + getWindowSize() +
- System.getProperty("line.separator"));
- sb.append("current offset within the window:=" + getWindowPosition() +
- System.getProperty("line.separator"));
- sb.append("number of main tree elements:=" + getMainTreeElements() +
- System.getProperty("line.separator"));
- sb.append("have we started decoding at all yet?:=" + getHadStarted() +
- System.getProperty("line.separator"));
- sb.append("type of this block:=" + getBlockType() +
System.getProperty("line.separator"));
- sb.append("uncompressed length of this block:=" + getBlockLength() +
- System.getProperty("line.separator"));
- sb.append("uncompressed bytes still left to decode:=" +
getBlockRemaining() +
- System.getProperty("line.separator"));
- sb.append("the number of CFDATA blocks processed:=" + getFramesRead() +
- System.getProperty("line.separator"));
- sb.append("magic header value used for transform:=" +
getIntelFileSize() +
- System.getProperty("line.separator"));
- sb.append("current offset in transform space:=" +
getIntelCurrentPossition() +
- System.getProperty("line.separator"));
- sb.append("have we seen any translatable data yet?:=" +
getIntelState() +
- System.getProperty("line.separator"));
- sb.append(
- "R0 for the LRU offset system:=" + getR0() +
System.getProperty("line.separator"));
- sb.append(
- "R1 for the LRU offset system:=" + getR1() +
System.getProperty("line.separator"));
- sb.append(
- "R2 for the LRU offset system:=" + getR2() +
System.getProperty("line.separator"));
- sb.append("main tree length:=" + getMainTreeLengtsTable().length +
- System.getProperty("line.separator"));
- sb.append("secondary tree length:=" +
getLengthTreeLengtsTable().length +
- System.getProperty("line.separator"));
+ sb.append("actual decoding window:=")
+ .append(getWindow())
+ .append(System.getProperty("line.separator"));
+ sb.append("window size (32Kb through 2Mb):=")
+ .append(getWindowSize())
+ .append(System.getProperty("line.separator"));
+ sb.append("current offset within the window:=")
+ .append(getWindowPosition())
+ .append(System.getProperty("line.separator"));
+ sb.append("number of main tree elements:=")
+ .append(getMainTreeElements())
+ .append(System.getProperty("line.separator"));
+ sb.append("have we started decoding at all yet?:=")
+ .append(getHadStarted())
+ .append(System.getProperty("line.separator"));
+ sb.append("type of this block:=")
+ .append(getBlockType())
+ .append(System.getProperty("line.separator"));
+ sb.append("uncompressed length of this block:=")
+ .append(getBlockLength())
+ .append(System.getProperty("line.separator"));
+ sb.append("uncompressed bytes still left to decode:=")
+ .append(getBlockRemaining())
+ .append(System.getProperty("line.separator"));
+ sb.append("the number of CFDATA blocks processed:=")
+ .append(getFramesRead())
+ .append(System.getProperty("line.separator"));
+ sb.append("magic header value used for transform:=")
+ .append(getIntelFileSize())
+ .append(System.getProperty("line.separator"));
+ sb.append("current offset in transform space:=")
+ .append(getIntelCurrentPossition())
+ .append(System.getProperty("line.separator"));
+ sb.append("have we seen any translatable data yet?:=")
+ .append(getIntelState())
+ .append(System.getProperty("line.separator"));
+ sb.append("R0 for the LRU offset system:=")
+ .append(getR0())
+ .append(System.getProperty("line.separator"));
+ sb.append("R1 for the LRU offset system:=")
+ .append(getR1())
+ .append(System.getProperty("line.separator"));
+ sb.append("R2 for the LRU offset system:=")
+ .append(getR2())
+ .append(System.getProperty("line.separator"));
+ sb.append("main tree length:=")
+ .append(getMainTreeLengtsTable().length)
+ .append(System.getProperty("line.separator"));
+ sb.append("secondary tree length:=")
+ .append(getLengthTreeLengtsTable().length)
+ .append(System.getProperty("line.separator"));
return sb.toString();
}
diff --git
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmLzxcControlData.java
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmLzxcControlData.java
index 0a7a61e..32b2ea6 100644
---
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmLzxcControlData.java
+++
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmLzxcControlData.java
@@ -248,16 +248,27 @@ public class ChmLzxcControlData implements
ChmAccessor<ChmLzxcControlData> {
*/
public String toString() {
StringBuilder sb = new StringBuilder();
- sb.append("size(unknown):=" + this.getSize() + ", ");
- sb.append("signature(Compression type identifier):=" +
- new String(this.getSignature(), UTF_8) + ", ");
- sb.append("version(Possibly numeric code for LZX):=" +
this.getVersion() +
- System.getProperty("line.separator"));
- sb.append("resetInterval(The Huffman reset interval):=" +
this.getResetInterval() + ", ");
- sb.append("windowSize:=" + this.getWindowSize() + ", ");
- sb.append("windowsPerReset(unknown (sometimes 2, sometimes 1,
sometimes 0):=" +
- this.getWindowsPerReset() + ", ");
- sb.append("unknown_18:=" + this.getUnknown_18() +
System.getProperty("line.separator"));
+ sb.append("size(unknown):=")
+ .append(this.getSize())
+ .append(", ");
+ sb.append("signature(Compression type identifier):=")
+ .append(new String(this.getSignature(), UTF_8))
+ .append(", ");
+ sb.append("version(Possibly numeric code for LZX):=")
+ .append(this.getVersion())
+ .append(System.getProperty("line.separator"));
+ sb.append("resetInterval(The Huffman reset interval):=")
+ .append(this.getResetInterval())
+ .append(", ");
+ sb.append("windowSize:=")
+ .append(this.getWindowSize())
+ .append(", ");
+ sb.append("windowsPerReset(unknown (sometimes 2, sometimes 1,
sometimes 0):=")
+ .append(this.getWindowsPerReset())
+ .append(", ");
+ sb.append("unknown_18:=")
+ .append(this.getUnknown_18())
+ .append(System.getProperty("line.separator"));
return sb.toString();
}
diff --git
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmLzxcResetTable.java
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmLzxcResetTable.java
index 485c53d..91543aa 100644
---
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmLzxcResetTable.java
+++
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmLzxcResetTable.java
@@ -81,15 +81,14 @@ public class ChmLzxcResetTable implements
ChmAccessor<ChmLzxcResetTable> {
@Override
public String toString() {
StringBuilder sb = new StringBuilder();
- sb.append("version:=" + getVersion() +
System.getProperty("line.separator"));
- sb.append("block_count:=" + getBlockCount() +
System.getProperty("line.separator"));
- sb.append("unknown:=" + getUnknown() +
System.getProperty("line.separator"));
- sb.append("table_offset:=" + getTableOffset() +
System.getProperty("line.separator"));
- sb.append(
- "uncompressed_len:=" + getUncompressedLen() +
System.getProperty("line.separator"));
- sb.append("compressed_len:=" + getCompressedLen() +
System.getProperty("line.separator"));
- sb.append("block_len:=" + getBlockLen() +
System.getProperty("line.separator"));
- sb.append("block_addresses:=" + Arrays.toString(getBlockAddress()));
+
sb.append("version:=").append(getVersion()).append(System.getProperty("line.separator"));
+
sb.append("block_count:=").append(getBlockCount()).append(System.getProperty("line.separator"));
+
sb.append("unknown:=").append(getUnknown()).append(System.getProperty("line.separator"));
+
sb.append("table_offset:=").append(getTableOffset()).append(System.getProperty("line.separator"));
+
sb.append("uncompressed_len:=").append(getUncompressedLen()).append(System.getProperty("line.separator"));
+
sb.append("compressed_len:=").append(getCompressedLen()).append(System.getProperty("line.separator"));
+
sb.append("block_len:=").append(getBlockLen()).append(System.getProperty("line.separator"));
+
sb.append("block_addresses:=").append(Arrays.toString(getBlockAddress()));
return sb.toString();
}
diff --git
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmPmgiHeader.java
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmPmgiHeader.java
index 0c93301..ccd59bb 100644
---
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmPmgiHeader.java
+++
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmPmgiHeader.java
@@ -142,8 +142,8 @@ public class ChmPmgiHeader implements
ChmAccessor<ChmPmgiHeader> {
*/
public String toString() {
StringBuilder sb = new StringBuilder();
- sb.append("signature:=" + new String(getSignature(), UTF_8) + ", ");
- sb.append("free space:=" + getFreeSpace() +
System.getProperty("line.separator"));
+ sb.append("signature:=").append(new String(getSignature(),
UTF_8)).append(", ");
+ sb.append("free
space:=").append(getFreeSpace()).append(System.getProperty("line.separator"));
return sb.toString();
}
diff --git
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmPmglHeader.java
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmPmglHeader.java
index 7a41938..e1e74fe 100644
---
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmPmglHeader.java
+++
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmPmglHeader.java
@@ -94,11 +94,11 @@ public class ChmPmglHeader implements
ChmAccessor<ChmPmglHeader> {
public String toString() {
StringBuilder sb = new StringBuilder();
- sb.append("signatute:=" + new String(getSignature(), UTF_8) + ", ");
- sb.append("free space:=" + getFreeSpace() + ", ");
- sb.append("unknown0008:=" + getUnknown0008() + ", ");
- sb.append("prev block:=" + getBlockPrev() + ", ");
- sb.append("next block:=" + getBlockNext() +
System.getProperty("line.separator"));
+ sb.append("signatute:=").append(new String(getSignature(),
UTF_8)).append(", ");
+ sb.append("free space:=").append(getFreeSpace()).append(", ");
+ sb.append("unknown0008:=").append(getUnknown0008()).append(", ");
+ sb.append("prev block:=").append(getBlockPrev()).append(", ");
+ sb.append("next
block:=").append(getBlockNext()).append(System.getProperty("line.separator"));
return sb.toString();
}
diff --git
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/DirectoryListingEntry.java
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/DirectoryListingEntry.java
index df5eb25..8a4b7f9 100644
---
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/DirectoryListingEntry.java
+++
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/DirectoryListingEntry.java
@@ -66,11 +66,11 @@ public class DirectoryListingEntry {
public String toString() {
StringBuilder sb = new StringBuilder();
- sb.append("name_length:=" + getNameLength() +
System.getProperty("line.separator"));
- sb.append("name:=" + getName() + System.getProperty("line.separator"));
- sb.append("entryType:=" + getEntryType() +
System.getProperty("line.separator"));
- sb.append("offset:=" + getOffset() +
System.getProperty("line.separator"));
- sb.append("length:=" + getLength());
+
sb.append("name_length:=").append(getNameLength()).append(System.getProperty("line.separator"));
+
sb.append("name:=").append(getName()).append(System.getProperty("line.separator"));
+
sb.append("entryType:=").append(getEntryType()).append(System.getProperty("line.separator"));
+
sb.append("offset:=").append(getOffset()).append(System.getProperty("line.separator"));
+ sb.append("length:=").append(getLength());
return sb.toString();
}
diff --git
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/onenote/IndentUtil.java
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/onenote/IndentUtil.java
index 50c381f..4ccef77 100644
---
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/onenote/IndentUtil.java
+++
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/onenote/IndentUtil.java
@@ -18,10 +18,10 @@ package org.apache.tika.parser.microsoft.onenote;
class IndentUtil {
public static String getIndent(int indentLevel) {
- String retval = "";
+ StringBuilder retval = new StringBuilder();
for (int i = 0; i < indentLevel; ++i) {
- retval += " ";
+ retval.append(" ");
}
- return retval;
+ return retval.toString();
}
}
diff --git
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/onenote/OneNoteParser.java
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/onenote/OneNoteParser.java
index 058a31c..41d342c 100644
---
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/onenote/OneNoteParser.java
+++
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/onenote/OneNoteParser.java
@@ -19,7 +19,6 @@ package org.apache.tika.parser.microsoft.onenote;
import java.io.IOException;
import java.io.InputStream;
import java.time.Instant;
-import java.util.Arrays;
import java.util.Collections;
import java.util.HashMap;
import java.util.List;
@@ -57,7 +56,7 @@ public class OneNoteParser extends AbstractParser {
static {
// All types should be 4 bytes long, space padded as needed
- typesMap.put(MediaType.application("onenote; format=one"),
Arrays.asList("ONE "));
+ typesMap.put(MediaType.application("onenote; format=one"),
Collections.singletonList("ONE "));
// TODO - add onetoc and other onenote mime types
}
diff --git
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/onenote/OneNotePtr.java
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/onenote/OneNotePtr.java
index 46ba76c..03fb58e 100644
---
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/onenote/OneNotePtr.java
+++
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/onenote/OneNotePtr.java
@@ -224,11 +224,11 @@ class OneNotePtr {
}
private String getIndent() {
- String retval = "";
+ StringBuilder retval = new StringBuilder();
for (int i = 0; i < indentLevel; ++i) {
- retval += " ";
+ retval.append(" ");
}
- return retval;
+ return retval.toString();
}
public void reposition(FileChunkReference loc) throws IOException {
diff --git
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSLFPowerPointExtractorDecorator.java
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSLFPowerPointExtractorDecorator.java
index eaf40e9..7994046 100644
---
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSLFPowerPointExtractorDecorator.java
+++
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSLFPowerPointExtractorDecorator.java
@@ -156,7 +156,7 @@ public class XSLFPowerPointExtractorDecorator extends
AbstractOOXMLExtractor {
if (authorStringBuilder.length() > 0) {
authorStringBuilder.append(" ");
}
- authorStringBuilder.append("(" +
comment.getAuthorInitials() + ")");
+
authorStringBuilder.append("(").append(comment.getAuthorInitials()).append(")");
}
if (comment.getText() != null &&
authorStringBuilder.length() > 0) {
authorStringBuilder.append(" - ");
diff --git
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/xps/XPSPageContentHandler.java
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/xps/XPSPageContentHandler.java
index 3a5148f..bce65b9 100644
---
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/xps/XPSPageContentHandler.java
+++
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/xps/XPSPageContentHandler.java
@@ -139,7 +139,7 @@ class XPSPageContentHandler extends DefaultHandler {
Float originX = null;
Float originY = null;
String unicodeString = null;
- Integer bidilevel = 1;
+ int bidilevel = 1;
String indicesString = null;
for (int i = 0; i < atts.getLength(); i++) {
diff --git
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/dif/DIFContentHandler.java
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/dif/DIFContentHandler.java
index 6028216..5a021e0 100644
---
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/dif/DIFContentHandler.java
+++
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/dif/DIFContentHandler.java
@@ -115,16 +115,16 @@ public class DIFContentHandler extends DefaultHandler {
}
if (this.isLeaf) {
Stack<String> tempStack = (Stack<String>) this.treeStack.clone();
- String key = "";
+ StringBuilder key = new StringBuilder();
while (!tempStack.isEmpty()) {
if (key.length() == 0) {
- key = tempStack.pop();
+ key = new StringBuilder(tempStack.pop());
} else {
- key = tempStack.pop() + "-" + key;
+ key.insert(0, tempStack.pop() + "-");
}
}
String value = this.dataStack.peek();
- this.metadata.add(key, value);
+ this.metadata.add(key.toString(), value);
this.isLeaf = false;
}
this.treeStack.pop();
diff --git
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-news-module/src/main/java/org/apache/tika/parser/iptc/IptcAnpaParser.java
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-news-module/src/main/java/org/apache/tika/parser/iptc/IptcAnpaParser.java
index 40ec405..ad52ca7 100644
---
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-news-module/src/main/java/org/apache/tika/parser/iptc/IptcAnpaParser.java
+++
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-news-module/src/main/java/org/apache/tika/parser/iptc/IptcAnpaParser.java
@@ -365,9 +365,9 @@ public class IptcAnpaParser implements Parser {
String env_category = "";
String env_urgency = "";
String hdr_edcode = "";
- String hdr_subject = "";
- String hdr_date = "";
- String hdr_time = "";
+ StringBuilder hdr_subject = new StringBuilder();
+ StringBuilder hdr_date = new StringBuilder();
+ StringBuilder hdr_time = new StringBuilder();
int read = 0;
@@ -405,7 +405,7 @@ public class IptcAnpaParser implements Parser {
byte val_next = value[read++];
while ((subject) && (val_next != SP) &&
(val_next != 0x00)) { // ignore the envelope subject
- hdr_subject += (char) (val_next & 0xff); // convert the
byte to an unsigned int
+ hdr_subject.append((char) (val_next & 0xff)); // convert
the byte to an unsigned int
val_next = (read < value.length) ? value[read++] : 0x00;
while (val_next == SP) { // consume all the spaces
subject = false;
@@ -427,8 +427,7 @@ public class IptcAnpaParser implements Parser {
while (((val_next >= (byte) 0x30) && (val_next <= (byte)
0x39))
// consume all numerics and hyphens
|| (val_next == HY)) {
- hdr_date +=
- (char) (val_next & 0xff); // convert the byte
to an unsigned int
+ hdr_date.append((char) (val_next & 0xff)); // convert
the byte to an unsigned int
val_next = (read < value.length) ? value[read++] :
0x00;
}
} else if (val_next == SP) {
@@ -440,8 +439,7 @@ public class IptcAnpaParser implements Parser {
while (((val_next >= (byte) 0x30) && (val_next <= (byte)
0x39))
// consume all numerics and hyphens
|| (val_next == HY)) {
- hdr_time +=
- (char) (val_next & 0xff); // convert the byte
to an unsigned int
+ hdr_time.append((char) (val_next & 0xff)); // convert
the byte to an unsigned int
val_next = (read < value.length) ? value[read++] :
0x00;
}
}
@@ -459,11 +457,11 @@ public class IptcAnpaParser implements Parser {
private boolean parseBody(byte[] value, HashMap<String, String>
properties) {
boolean added = false;
- String bdy_heading = "";
- String bdy_title = "";
- String bdy_source = "";
- String bdy_author = "";
- String bdy_body = "";
+ StringBuilder bdy_heading = new StringBuilder();
+ StringBuilder bdy_title = new StringBuilder();
+ StringBuilder bdy_source = new StringBuilder();
+ StringBuilder bdy_author = new StringBuilder();
+ StringBuilder bdy_body = new StringBuilder();
int read = 0;
boolean done = false;
@@ -478,8 +476,7 @@ public class IptcAnpaParser implements Parser {
// AP, NYT, and Bloomberg end with < , Reuters with EOL
while ((val_next != LT) && (val_next != CR) &&
(val_next != LF)) { // less than delimiter
(\x3c) and not EOL
- bdy_heading +=
- (char) (val_next & 0xff); // convert the byte
to an unsigned int
+ bdy_heading.append((char) (val_next & 0xff)); //
convert the byte to an unsigned int
val_next = (read < value.length) ? value[read++] :
0x00;
if (read >= value.length) {
break;
@@ -531,8 +528,7 @@ public class IptcAnpaParser implements Parser {
// AP, NYT, and Bloomberg end with < , Reuters with EOL
while ((val_next != LT) && (val_next != CT) && (val_next
!= CR) && (val_next !=
LF)) { // less than delimiter (\x3c), or carat
(\x5e) and not EOL
- bdy_title +=
- (char) (val_next & 0xff); // convert the byte
to an unsigned int
+ bdy_title.append((char) (val_next & 0xff)); //
convert the byte to an unsigned int
val_next = (read < value.length) ? value[read++] :
0x00;
if (read >= value.length) {
break;
@@ -593,7 +589,7 @@ public class IptcAnpaParser implements Parser {
// pull apart the body, getting the title (^....\x0d\x0a)
boolean metastarted = false;
String longline = "";
- String longkey = "";
+ String longkey;
while (read < value.length) {
byte val_next = value[read++];
@@ -605,12 +601,11 @@ public class IptcAnpaParser implements Parser {
if (val_next ==
CT) { // start of a new section , could be
authors, sources, etc
val_next = (read < value.length) ? value[read++] : 0x00;
- String tmp_line = "";
+ StringBuilder tmp_line = new StringBuilder();
while ((val_next != LT) && (val_next != CT) && (val_next
!= CR) &&
(val_next != LF) && (val_next != 0)) {
// less than delimiter (\x3c), maybe also badly formed
with just new line
- tmp_line +=
- (char) (val_next & 0xff); // convert the byte
to an unsigned int
+ tmp_line.append((char) (val_next & 0xff)); // convert
the byte to an unsigned int
val_next = (read < value.length) ? value[read++] :
0x00;
if (read >= value.length) {
break;
@@ -634,49 +629,49 @@ public class IptcAnpaParser implements Parser {
--read;
}
}
- if (tmp_line.toLowerCase(Locale.ROOT).startsWith("by") ||
+ if
(tmp_line.toString().toLowerCase(Locale.ROOT).startsWith("by") ||
longline.equals("bdy_author")) {
longkey = "bdy_author";
// prepend a space to subsequent line, so it gets
parsed consistent with
// the lead line
- tmp_line = (longline.equals(longkey) ? " " : "") +
tmp_line;
+ tmp_line.insert(0, (longline.equals(longkey) ? " " :
""));
// we have an author candidate
int term = tmp_line.length();
term = Math.min(term,
- (tmp_line.contains("<") ?
tmp_line.indexOf("<") : term));
+ (tmp_line.toString().contains("<") ?
tmp_line.indexOf("<") : term));
term = Math.min(term,
- (tmp_line.contains("=") ?
tmp_line.indexOf("=") : term));
+ (tmp_line.toString().contains("=") ?
tmp_line.indexOf("=") : term));
term = Math.min(term,
- (tmp_line.contains("\n") ?
tmp_line.indexOf("\n") : term));
+ (tmp_line.toString().contains("\n") ?
tmp_line.indexOf("\n") : term));
term = (term > 0) ? term : tmp_line.length();
- bdy_author += tmp_line.substring(tmp_line.indexOf("
"), term);
+
bdy_author.append(tmp_line.substring(tmp_line.indexOf(" "), term));
metastarted = true;
longline =
- ((tmp_line.contains("=")) &&
(!longline.equals(longkey)) ? longkey :
+ ((tmp_line.toString().contains("=")) &&
(!longline.equals(longkey)) ? longkey :
"");
} else if (FORMAT == this.FMT_IPTC_BLM) {
String byline = " by ";
- if
(tmp_line.toLowerCase(Locale.ROOT).contains(byline)) {
+ if
(tmp_line.toString().toLowerCase(Locale.ROOT).contains(byline)) {
longkey = "bdy_author";
int term = tmp_line.length();
term = Math.min(term,
- (tmp_line.contains("<") ?
tmp_line.indexOf("<") : term));
+ (tmp_line.toString().contains("<") ?
tmp_line.indexOf("<") : term));
term = Math.min(term,
- (tmp_line.contains("=") ?
tmp_line.indexOf("=") : term));
+ (tmp_line.toString().contains("=") ?
tmp_line.indexOf("=") : term));
term = Math.min(term,
- (tmp_line.contains("\n") ?
tmp_line.indexOf("\n") : term));
+ (tmp_line.toString().contains("\n") ?
tmp_line.indexOf("\n") : term));
term = (term > 0) ? term : tmp_line.length();
// for bloomberg, the author line sits below their
copyright statement
- bdy_author += tmp_line.substring(
-
tmp_line.toLowerCase(Locale.ROOT).indexOf(byline) +
- byline.length(), term) + " ";
+ bdy_author.append(tmp_line.substring(
+
tmp_line.toString().toLowerCase(Locale.ROOT).indexOf(byline) +
+ byline.length(), term)).append(" ");
metastarted = true;
- longline = ((tmp_line.contains("=")) &&
(!longline.equals(longkey)) ?
+ longline = ((tmp_line.toString().contains("=")) &&
(!longline.equals(longkey)) ?
longkey : "");
- } else if
(tmp_line.toLowerCase(Locale.ROOT).startsWith("c.")) {
+ } else if
(tmp_line.toString().toLowerCase(Locale.ROOT).startsWith("c.")) {
// the author line for bloomberg is a multiline
starting with c.2011
// Bloomberg News
// then containing the author info on the next line
@@ -684,8 +679,8 @@ public class IptcAnpaParser implements Parser {
value[--read] = CT;
continue;
}
- } else if
(tmp_line.toLowerCase(Locale.ROOT).trim().startsWith("(") &&
-
tmp_line.toLowerCase(Locale.ROOT).trim().endsWith(")")) {
+ } else if
(tmp_line.toString().toLowerCase(Locale.ROOT).trim().startsWith("(") &&
+
tmp_line.toString().toLowerCase(Locale.ROOT).trim().endsWith(")")) {
// the author line may have one or more comment
lines between the
// copyright
// statement, and the By AUTHORNAME line
@@ -694,44 +689,43 @@ public class IptcAnpaParser implements Parser {
continue;
}
}
- } else if
(tmp_line.toLowerCase(Locale.ROOT).startsWith("eds") ||
- longline.equals("bdy_source")) {
+ } else if
(tmp_line.toString().toLowerCase(Locale.ROOT).startsWith("eds") ||
+ longline.equals("bdy_source")) {
longkey = "bdy_source";
// prepend a space to subsequent line, so it gets
parsed consistent with
// the lead line
- tmp_line = (longline.equals(longkey) ? " " : "") +
tmp_line;
+ tmp_line.insert(0, (longline.equals(longkey) ? " " :
""));
// we have a source candidate
int term = tmp_line.length();
term = Math.min(term,
- (tmp_line.contains("<") ?
tmp_line.indexOf("<") : term));
+ (tmp_line.toString().contains("<") ?
tmp_line.indexOf("<") : term));
term = Math.min(term,
- (tmp_line.contains("=") ?
tmp_line.indexOf("=") : term));
+ (tmp_line.toString().contains("=") ?
tmp_line.indexOf("=") : term));
// term = Math.min(term, (tmp_line.indexOf("\n") > -1 ?
tmp_line.indexOf("\n") :
// term));
term = (term > 0) ? term : tmp_line.length();
- bdy_source += tmp_line.substring(tmp_line.indexOf(" ")
+ 1, term) + " ";
+
bdy_source.append(tmp_line.substring(tmp_line.indexOf(" ") + 1, term)).append("
");
metastarted = true;
longline = (!longline.equals(longkey) ? longkey : "");
} else {
// this has fallen all the way through. trap it as
part of the subject,
// rather than just losing it
if (!metastarted) {
- bdy_title += " , " +
- tmp_line; // not sure where else to
put this but in the
+ bdy_title.append(" , ").append(tmp_line); //
not sure where else to put this but in the
// title
} else {
// what to do with stuff that is metadata, which
falls after metadata
// lines started?
- bdy_body += " " + tmp_line +
- " , "; // not sure where else to put
this but in the title
+ bdy_body.append(" ")
+ .append(tmp_line)
+ .append(" , "); // not sure where
else to put this but in the title
}
}
} else { // we're on to the main body
while ((read < value.length) && (val_next != 0)) {
// read until the train runs out of tracks
- bdy_body +=
- (char) (val_next & 0xff); // convert the byte
to an unsigned int
+ bdy_body.append((char) (val_next & 0xff)); // convert
the byte to an unsigned int
val_next = (read < value.length) ? value[read++] :
0x00;
if (read >= value.length) {
break;
@@ -743,11 +737,11 @@ public class IptcAnpaParser implements Parser {
}
done = true; // don't let this run back through and start
thrashing metadata
}
- properties.put("body", bdy_body);
- properties.put("title", bdy_title);
- properties.put("subject", bdy_heading);
- properties.put("author", bdy_author);
- properties.put("source", bdy_source);
+ properties.put("body", bdy_body.toString());
+ properties.put("title", bdy_title.toString());
+ properties.put("subject", bdy_heading.toString());
+ properties.put("author", bdy_author.toString());
+ properties.put("source", bdy_source.toString());
added = (bdy_body.length() + bdy_title.length() + bdy_heading.length()
+
bdy_author.length() + bdy_source.length()) > 0;
@@ -758,7 +752,7 @@ public class IptcAnpaParser implements Parser {
private boolean parseFooter(byte[] value, HashMap<String, String>
properties) {
boolean added = false;
- String ftr_source = "";
+ StringBuilder ftr_source = new StringBuilder();
String ftr_datetime = "";
int read = 0;
@@ -772,7 +766,7 @@ public class IptcAnpaParser implements Parser {
while (((val_next < (byte) 0x30) || (val_next > (byte) 0x39)) &&
(val_next != 0)) { // consume all non-numerics first
- ftr_source += (char) (val_next & 0xff); // convert the byte
to an unsigned int
+ ftr_source.append((char) (val_next & 0xff)); // convert the
byte to an unsigned int
val_next = (read < value.length) ? value[read] :
0x00; // attempt to read until end of stream
read++;
@@ -826,7 +820,7 @@ public class IptcAnpaParser implements Parser {
done = true; // don't let this run back through and start
thrashing metadata
}
- properties.put("publisher", ftr_source);
+ properties.put("publisher", ftr_source.toString());
properties.put("created", ftr_datetime);
properties.put("modified", ftr_datetime);
diff --git
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-ocr-module/src/test/java/org/apache/tika/parser/ocr/TesseractOCRParserTest.java
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-ocr-module/src/test/java/org/apache/tika/parser/ocr/TesseractOCRParserTest.java
index 26cc1c4..a67fc17 100644
---
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-ocr-module/src/test/java/org/apache/tika/parser/ocr/TesseractOCRParserTest.java
+++
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-ocr-module/src/test/java/org/apache/tika/parser/ocr/TesseractOCRParserTest.java
@@ -235,9 +235,7 @@ public class TesseractOCRParserTest extends TikaTest {
for (Parser p : new Parser[]{new BPGParser(), new HeifParser(), new
ICNSParser(),
new ImageParser(), new JpegParser(), new PSDParser(), new
TiffParser(),
new WebPParser(),}) {
- for (MediaType mt : p.getSupportedTypes(new ParseContext())) {
- imageParserMimes.add(mt);
- }
+ imageParserMimes.addAll(p.getSupportedTypes(new ParseContext()));
}
//mime types that Tesseract will cover if there is no existing parser
//that in turn will call tesseract .. e.g. the mime subtype doesn't
start
diff --git
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/ImageGraphicsEngine.java
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/ImageGraphicsEngine.java
index d0c2bc8..63c3825 100644
---
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/ImageGraphicsEngine.java
+++
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/ImageGraphicsEngine.java
@@ -24,6 +24,7 @@ import java.io.InputStream;
import java.io.OutputStream;
import java.util.ArrayList;
import java.util.Arrays;
+import java.util.Collections;
import java.util.List;
import java.util.Map;
import java.util.concurrent.atomic.AtomicInteger;
@@ -80,9 +81,9 @@ class ImageGraphicsEngine extends PDFGraphicsStreamEngine {
Arrays.asList(COSName.DCT_DECODE.getName(),
COSName.DCT_DECODE_ABBREVIATION.getName());
- private static final List<String> JP2 =
Arrays.asList(COSName.JPX_DECODE.getName());
+ private static final List<String> JP2 =
Collections.singletonList(COSName.JPX_DECODE.getName());
- private static final List<String> JB2 =
Arrays.asList(COSName.JBIG2_DECODE.getName());
+ private static final List<String> JB2 =
Collections.singletonList(COSName.JBIG2_DECODE.getName());
final List<IOException> exceptions = new ArrayList<>();
private final EmbeddedDocumentExtractor embeddedDocumentExtractor;
private final PDFParserConfig pdfParserConfig;
diff --git
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
index 0c83ab4..4ec104a 100644
---
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
+++
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
@@ -639,6 +639,7 @@ public class PDFParserTest extends TikaTest {
for (String v : vals) {
if (v.equals(e.getValue())) {
foundDC = true;
+ break;
}
}
assertTrue("dc:format ::" + e.getValue(), foundDC);
diff --git
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/strings/Latin1StringsParser.java
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/strings/Latin1StringsParser.java
index ce45e41..47eee7c 100644
---
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/strings/Latin1StringsParser.java
+++
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/strings/Latin1StringsParser.java
@@ -175,8 +175,9 @@ public class Latin1StringsParser extends AbstractParser {
xhtml.characters(new String(output, 0, outPos, "windows-1252"));
- for (int k = 0; k < tmpPos - outPos; k++)
- output[k] = output[outPos + k];
+ if (tmpPos - outPos >= 0) {
+ System.arraycopy(output, outPos, output, 0, tmpPos - outPos);
+ }
tmpPos = tmpPos - outPos;
outPos = 0;
}
diff --git
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-xmp-commons/src/test/java/org/apache/tika/parser/xmp/JempboxExtractorTest.java
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-xmp-commons/src/test/java/org/apache/tika/parser/xmp/JempboxExtractorTest.java
index a204491..76364cb 100644
---
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-xmp-commons/src/test/java/org/apache/tika/parser/xmp/JempboxExtractorTest.java
+++
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-xmp-commons/src/test/java/org/apache/tika/parser/xmp/JempboxExtractorTest.java
@@ -23,6 +23,7 @@ import java.io.IOException;
import java.io.InputStream;
import java.util.Arrays;
import java.util.Collection;
+import java.util.Collections;
import org.junit.Test;
@@ -103,7 +104,7 @@ public class JempboxExtractorTest extends TikaTest {
@Test
public void testJoinCreators() {
- assertEquals("Mr B", new
JempboxExtractor(null).joinCreators(Arrays.asList("Mr B")));
+ assertEquals("Mr B", new
JempboxExtractor(null).joinCreators(Collections.singletonList("Mr B")));
// TODO use multi-value property instead?
assertEquals("Mr B, Mr A",
new JempboxExtractor(null).joinCreators(Arrays.asList("Mr B",
"Mr A")));
diff --git
a/tika-pipes/tika-pipes-iterators/tika-pipes-iterator-jdbc/src/main/java/org/apache/tika/pipes/pipesiterator/jdbc/JDBCPipesIterator.java
b/tika-pipes/tika-pipes-iterators/tika-pipes-iterator-jdbc/src/main/java/org/apache/tika/pipes/pipesiterator/jdbc/JDBCPipesIterator.java
index 024b99b..3fb45a1 100644
---
a/tika-pipes/tika-pipes-iterators/tika-pipes-iterator-jdbc/src/main/java/org/apache/tika/pipes/pipesiterator/jdbc/JDBCPipesIterator.java
+++
b/tika-pipes/tika-pipes-iterators/tika-pipes-iterator-jdbc/src/main/java/org/apache/tika/pipes/pipesiterator/jdbc/JDBCPipesIterator.java
@@ -211,7 +211,7 @@ public class JDBCPipesIterator extends PipesIterator
implements Initializable {
String val = rs.getString(i);
val = (val == null) ? "" : val;
val = (val.length() > 100) ? val.substring(0, 100) : val;
- sb.append(rs.getMetaData().getColumnLabel(i) + ":" + val + "\n");
+
sb.append(rs.getMetaData().getColumnLabel(i)).append(":").append(val).append("\n");
}
return sb.toString();
}
diff --git
a/tika-server/tika-server-core/src/main/java/org/apache/tika/server/core/TikaServerConfig.java
b/tika-server/tika-server-core/src/main/java/org/apache/tika/server/core/TikaServerConfig.java
index d73307a..b8c9473 100644
---
a/tika-server/tika-server-core/src/main/java/org/apache/tika/server/core/TikaServerConfig.java
+++
b/tika-server/tika-server-core/src/main/java/org/apache/tika/server/core/TikaServerConfig.java
@@ -332,12 +332,7 @@ public class TikaServerConfig extends ConfigBase {
}
}
//add headless if not already configured
- boolean foundHeadlessOption = false;
- for (String arg : forkedJvmArgs) {
- if (arg.contains("java.awt.headless")) {
- foundHeadlessOption = true;
- }
- }
+ boolean foundHeadlessOption = forkedJvmArgs.stream().anyMatch(arg ->
arg.contains("java.awt.headless"));
//if user has already specified headless...don't modify
if (!foundHeadlessOption) {
forkedJvmArgs.add("-Djava.awt.headless=true");
diff --git
a/tika-server/tika-server-core/src/main/java/org/apache/tika/server/core/TikaServerWatchDog.java
b/tika-server/tika-server-core/src/main/java/org/apache/tika/server/core/TikaServerWatchDog.java
index 186d84a..d00141f 100644
---
a/tika-server/tika-server-core/src/main/java/org/apache/tika/server/core/TikaServerWatchDog.java
+++
b/tika-server/tika-server-core/src/main/java/org/apache/tika/server/core/TikaServerWatchDog.java
@@ -138,7 +138,7 @@ public class TikaServerWatchDog implements
Callable<WatchDogResult> {
forkedProcess.close();
mustRestart = true;
} else {
- Long elapsed =
Duration.between(Instant.ofEpochMilli(status.timestamp),
+ long elapsed =
Duration.between(Instant.ofEpochMilli(status.timestamp),
Instant.now()).toMillis();
if (elapsed >
tikaServerConfig.getTaskTimeoutMillis()) {
LOG.info(
@@ -255,7 +255,7 @@ public class TikaServerWatchDog implements
Callable<WatchDogResult> {
private ForkedStatus readStatus() throws Exception {
Instant started = Instant.now();
- Long elapsed = Duration.between(started, Instant.now()).toMillis();
+ long elapsed = Duration.between(started, Instant.now()).toMillis();
//only reading, but need to include write to allow for locking
try (FileChannel fc = FileChannel.open(forkedStatusFile, READ,
WRITE)) {
diff --git
a/tika-xmp/src/main/java/org/apache/tika/xmp/convert/RTFConverter.java
b/tika-xmp/src/main/java/org/apache/tika/xmp/convert/RTFConverter.java
index 8118686..4f83543 100644
--- a/tika-xmp/src/main/java/org/apache/tika/xmp/convert/RTFConverter.java
+++ b/tika-xmp/src/main/java/org/apache/tika/xmp/convert/RTFConverter.java
@@ -38,7 +38,7 @@ import com.adobe.xmp.options.PropertyOptions;
*/
public class RTFConverter extends AbstractConverter {
protected static final Set<Namespace> ADDITIONAL_NAMESPACES = Collections
- .unmodifiableSet(new HashSet<>(Arrays.asList(new Namespace(
+ .unmodifiableSet(new HashSet<>(Collections.singletonList(new
Namespace(
OfficeOpenXMLExtended.NAMESPACE_URI,
OfficeOpenXMLExtended.PREFIX))) );
public RTFConverter() throws TikaException {
