You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ti...@apache.org on 2020/12/14 05:35:27 UTC
[tika] branch main updated: Revert "Merge origin/main into main"
This is an automated email from the ASF dual-hosted git repository.
tilman pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tika.git
The following commit(s) were added to refs/heads/main by this push:
new 326b7d7 Revert "Merge origin/main into main"
326b7d7 is described below
commit 326b7d7abda238ccc181fc2acaf2271e08fe9c1b
Author: THausherr <ti...@snafu.de>
AuthorDate: Mon Dec 14 06:34:03 2020 +0100
Revert "Merge origin/main into main"
This reverts commit dd85c73094dc87f6f6e208278325be810761f490, reversing
changes made to 081070065ec2a989ecfccb9d1186610bbce52f5e.
---
.../tika/batch/fs/strawman/StrawManTikaAppDriver.java | 4 +++-
tika-core/src/main/java/org/apache/tika/Tika.java | 17 ++++++++++++++++-
.../org/apache/tika/config/TikaConfigSerializer.java | 3 ++-
.../src/main/java/org/apache/tika/fork/ForkClient.java | 6 ++++--
.../main/java/org/apache/tika/utils/SystemUtils.java | 2 +-
.../java/org/apache/tika/parser/mock/MockParser.java | 2 +-
.../apache/tika/eval/core/tokens/TokenStatistics.java | 2 +-
.../apache/tika/fuzzing/pdf/PDFTransformerConfig.java | 3 ++-
.../apache/tika/parser/ner/NamedEntityParserTest.java | 3 ++-
.../org/apache/tika/parser/html/HtmlParserTest.java | 6 ++++--
.../apache/tika/parser/microsoft/chm/ChmCommons.java | 5 +++--
.../org/apache/tika/parser/pkg/CompressorParser.java | 6 ++++--
.../main/java/org/apache/tika/server/ServerStatus.java | 4 +++-
13 files changed, 46 insertions(+), 17 deletions(-)
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 7b0bd1e..dd3cd48 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
@@ -226,8 +226,10 @@ public class StrawManTikaAppDriver implements Callable<Integer> {
}
}
+ List<String> commandLine = new ArrayList<>();
+
int initialParams = (fileList == null) ? 3 : 4;
- List<String> commandLine = new ArrayList<>(Arrays.asList(args).subList(initialParams, args.length));
+ commandLine.addAll(Arrays.asList(args).subList(initialParams, args.length));
totalThreads = (totalThreads < 1) ? 1 : totalThreads;
ExecutorService ex = Executors.newFixedThreadPool(totalThreads);
ExecutorCompletionService<Integer> completionService =
diff --git a/tika-core/src/main/java/org/apache/tika/Tika.java b/tika-core/src/main/java/org/apache/tika/Tika.java
index afb8630..a14dced 100644
--- a/tika-core/src/main/java/org/apache/tika/Tika.java
+++ b/tika-core/src/main/java/org/apache/tika/Tika.java
@@ -488,7 +488,22 @@ public class Tika {
*/
public String parseToString(InputStream stream, Metadata metadata)
throws IOException, TikaException {
- return parseToString(stream, metadata, maxStringLength);
+ WriteOutContentHandler handler =
+ new WriteOutContentHandler(maxStringLength);
+ try {
+ ParseContext context = new ParseContext();
+ context.set(Parser.class, parser);
+ parser.parse(
+ stream, new BodyContentHandler(handler), metadata, context);
+ } catch (SAXException e) {
+ if (!handler.isWriteLimitReached(e)) {
+ // This should never happen with BodyContentHandler...
+ throw new TikaException("Unexpected SAX processing failure", e);
+ }
+ } finally {
+ stream.close();
+ }
+ return handler.toString();
}
/**
diff --git a/tika-core/src/main/java/org/apache/tika/config/TikaConfigSerializer.java b/tika-core/src/main/java/org/apache/tika/config/TikaConfigSerializer.java
index dbe63e3..2e16567 100644
--- a/tika-core/src/main/java/org/apache/tika/config/TikaConfigSerializer.java
+++ b/tika-core/src/main/java/org/apache/tika/config/TikaConfigSerializer.java
@@ -273,7 +273,8 @@ public class TikaConfigSerializer {
Set<MediaType> addedTypes = new TreeSet<>();
Set<MediaType> excludedTypes = new TreeSet<>();
if (decorator != null) {
- Set<MediaType> types = new TreeSet<>(decorator.getSupportedTypes(context));
+ Set<MediaType> types = new TreeSet<>();
+ types.addAll(decorator.getSupportedTypes(context));
addedTypes.addAll(types);
for (MediaType type : parser.getSupportedTypes(context)) {
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 15c31fd..94c9262 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
@@ -79,7 +79,8 @@ class ForkClient {
loader = null;
boolean ok = false;
ProcessBuilder builder = new ProcessBuilder();
- List<String> command = new ArrayList<>(java);
+ List<String> command = new ArrayList<>();
+ command.addAll(java);
command.add("-cp");
String dirString = tikaDir.toAbsolutePath().toString();
if (!dirString.endsWith("/")) {
@@ -133,7 +134,8 @@ class ForkClient {
this.jar = createBootstrapJar();
ProcessBuilder builder = new ProcessBuilder();
- List<String> command = new ArrayList<>(java);
+ List<String> command = new ArrayList<>();
+ command.addAll(java);
command.add("-jar");
command.add(jar.getPath());
command.add(Long.toString(timeoutLimits.getPulseMS()));
diff --git a/tika-core/src/main/java/org/apache/tika/utils/SystemUtils.java b/tika-core/src/main/java/org/apache/tika/utils/SystemUtils.java
index 6ccdc5e..889f62c 100644
--- a/tika-core/src/main/java/org/apache/tika/utils/SystemUtils.java
+++ b/tika-core/src/main/java/org/apache/tika/utils/SystemUtils.java
@@ -50,7 +50,7 @@ public class SystemUtils {
}
static boolean isOSNameMatch(String osName, String osNamePrefix) {
- return osName != null && osName.startsWith(osNamePrefix);
+ return osName == null ? false : osName.startsWith(osNamePrefix);
}
static {
diff --git a/tika-core/src/test/java/org/apache/tika/parser/mock/MockParser.java b/tika-core/src/test/java/org/apache/tika/parser/mock/MockParser.java
index 8d29f3c..a039e76 100644
--- a/tika-core/src/test/java/org/apache/tika/parser/mock/MockParser.java
+++ b/tika-core/src/test/java/org/apache/tika/parser/mock/MockParser.java
@@ -195,7 +195,7 @@ public class MockParser extends AbstractParser {
private void print(Node action, String name) throws IOException {
String content = action.getTextContent();
- boolean isStatic = (action.getAttributes().getNamedItem("static") != null);
+ boolean isStatic = (action.getAttributes().getNamedItem("static") == null) ? false : true;
Node rand = action.getAttributes().getNamedItem("random");
int randLength = -1;
if (rand != null) {
diff --git a/tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/tokens/TokenStatistics.java b/tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/tokens/TokenStatistics.java
index f24606c..a1a9759 100644
--- a/tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/tokens/TokenStatistics.java
+++ b/tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/tokens/TokenStatistics.java
@@ -120,7 +120,7 @@ public class TokenStatistics {
}
private static boolean doubleEquals(double a, double b, double epsilon) {
- return a == b || Math.abs(a - b) < epsilon;
+ return a == b ? true : Math.abs(a - b) < epsilon;
}
diff --git a/tika-fuzzing/src/main/java/org/apache/tika/fuzzing/pdf/PDFTransformerConfig.java b/tika-fuzzing/src/main/java/org/apache/tika/fuzzing/pdf/PDFTransformerConfig.java
index 41f0daf..aa7729c 100644
--- a/tika-fuzzing/src/main/java/org/apache/tika/fuzzing/pdf/PDFTransformerConfig.java
+++ b/tika-fuzzing/src/main/java/org/apache/tika/fuzzing/pdf/PDFTransformerConfig.java
@@ -156,7 +156,8 @@ public class PDFTransformerConfig {
numFilters = minFilters + random.nextInt(maxFilters - minFilters);
}
- List<COSName> allowable = new ArrayList<>(allowableFilters);
+ List<COSName> allowable = new ArrayList<>();
+ allowable.addAll(allowableFilters);
List<COSName> filters = new ArrayList<>();
for (int i = 0; i < numFilters; i++) {
diff --git a/tika-parsers/tika-parsers-advanced/tika-parser-nlp-module/src/test/java/org/apache/tika/parser/ner/NamedEntityParserTest.java b/tika-parsers/tika-parsers-advanced/tika-parser-nlp-module/src/test/java/org/apache/tika/parser/ner/NamedEntityParserTest.java
index 97279f9..a7aef2f 100644
--- a/tika-parsers/tika-parsers-advanced/tika-parser-nlp-module/src/test/java/org/apache/tika/parser/ner/NamedEntityParserTest.java
+++ b/tika-parsers/tika-parsers-advanced/tika-parser-nlp-module/src/test/java/org/apache/tika/parser/ner/NamedEntityParserTest.java
@@ -52,7 +52,8 @@ public class NamedEntityParserTest extends TikaTest {
Metadata md = new Metadata();
tika.parse(new ByteArrayInputStream(text.getBytes(Charset.defaultCharset())), md);
- HashSet<String> set = new HashSet<String>(Arrays.asList(md.getValues("X-Parsed-By")));
+ HashSet<String> set = new HashSet<String>();
+ set.addAll(Arrays.asList(md.getValues("X-Parsed-By")));
assumeTrue(set.contains(NamedEntityParser.class.getName()));
set.clear();
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-html-module/src/test/java/org/apache/tika/parser/html/HtmlParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-html-module/src/test/java/org/apache/tika/parser/html/HtmlParserTest.java
index 3b26443..ba13d00 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-html-module/src/test/java/org/apache/tika/parser/html/HtmlParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-html-module/src/test/java/org/apache/tika/parser/html/HtmlParserTest.java
@@ -1312,8 +1312,10 @@ public class HtmlParserTest extends TikaTest {
@Test
public void testMultiThreadingEncodingDetection() throws Exception {
- ServiceLoader loader = new ServiceLoader(AutoDetectReader.class.getClassLoader());
- List<EncodingDetector> detectors = new ArrayList<>(loader.loadServiceProviders(EncodingDetector.class));
+ List<EncodingDetector> detectors = new ArrayList<>();
+ ServiceLoader loader =
+ new ServiceLoader(AutoDetectReader.class.getClassLoader());
+ detectors.addAll(loader.loadServiceProviders(EncodingDetector.class));
for (EncodingDetector detector : detectors) {
testDetector(detector);
}
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/ChmCommons.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmCommons.java
index 1dc3593..8c061f0 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmCommons.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmCommons.java
@@ -192,8 +192,9 @@ public class ChmCommons {
* @return boolean
*/
public static boolean hasSkip(DirectoryListingEntry directoryListingEntry) {
- String name = directoryListingEntry.getName();
- return name.startsWith("/$") || name.startsWith("/#") || name.startsWith("::");
+ return (directoryListingEntry.getName().startsWith("/$")
+ || directoryListingEntry.getName().startsWith("/#") || directoryListingEntry
+ .getName().startsWith("::")) ? true : false;
}
/**
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pkg-module/src/main/java/org/apache/tika/parser/pkg/CompressorParser.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pkg-module/src/main/java/org/apache/tika/parser/pkg/CompressorParser.java
index 9e1087c..e428b73 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pkg-module/src/main/java/org/apache/tika/parser/pkg/CompressorParser.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pkg-module/src/main/java/org/apache/tika/parser/pkg/CompressorParser.java
@@ -83,8 +83,10 @@ public class CompressorParser extends AbstractParser {
private static Map<String, String> MIMES_TO_NAME;
static {
- Set<MediaType> TMP_SET = new HashSet<>(MediaType.set(
- BZIP, BZIP2, DEFLATE64, GZIP, GZIP_ALT, LZ4_FRAMED, COMPRESS, XZ, PACK, SNAPPY_FRAMED, ZLIB, LZMA));
+ Set<MediaType> TMP_SET = new HashSet<>();
+ TMP_SET.addAll(
+ MediaType.set(BZIP, BZIP2, DEFLATE64, GZIP, GZIP_ALT, LZ4_FRAMED, COMPRESS,
+ XZ, PACK, SNAPPY_FRAMED, ZLIB, LZMA));
try {
Class.forName("org.brotli.dec.BrotliInputStream");
TMP_SET.add(BROTLI);
diff --git a/tika-server/src/main/java/org/apache/tika/server/ServerStatus.java b/tika-server/src/main/java/org/apache/tika/server/ServerStatus.java
index b49ecbc..bc9ad0a 100644
--- a/tika-server/src/main/java/org/apache/tika/server/ServerStatus.java
+++ b/tika-server/src/main/java/org/apache/tika/server/ServerStatus.java
@@ -125,7 +125,9 @@ public class ServerStatus {
}
public synchronized Map<Long, TaskStatus> getTasks() {
- return new HashMap<>(tasks);
+ Map<Long, TaskStatus> ret = new HashMap<>();
+ ret.putAll(tasks);
+ return ret;
}
public synchronized long getFilesProcessed() {