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 2024/08/14 11:47:20 UTC
(tika) 01/02: TIKA-4290: fix checkstyle issues, add override
This is an automated email from the ASF dual-hosted git repository.
tilman pushed a commit to branch branch_2x
in repository https://gitbox.apache.org/repos/asf/tika.git
commit 86c0ae60e129799a278fa4c92669d0cd5a269ee5
Author: Tilman Hausherr <ti...@apache.org>
AuthorDate: Wed Aug 14 13:23:15 2024 +0200
TIKA-4290: fix checkstyle issues, add override
---
tika-core/src/main/java/org/apache/tika/mime/MagicMatch.java | 6 +++++-
.../src/main/java/org/apache/tika/parser/html/HtmlHandler.java | 3 ++-
.../src/main/java/org/apache/tika/parser/jdbc/JDBCTableReader.java | 3 ++-
.../main/java/org/apache/tika/parser/microsoft/OfficeParser.java | 6 ++++--
.../src/main/java/org/apache/tika/parser/txt/CharsetMatch.java | 3 ++-
.../src/main/java/org/apache/tika/parser/xml/FictionBookParser.java | 3 ++-
6 files changed, 17 insertions(+), 7 deletions(-)
diff --git a/tika-core/src/main/java/org/apache/tika/mime/MagicMatch.java b/tika-core/src/main/java/org/apache/tika/mime/MagicMatch.java
index 4917ea542..bb0b9e7fb 100644
--- a/tika-core/src/main/java/org/apache/tika/mime/MagicMatch.java
+++ b/tika-core/src/main/java/org/apache/tika/mime/MagicMatch.java
@@ -55,9 +55,11 @@ class MagicMatch implements Clause {
return detector;
}
+ @Override
public boolean eval(byte[] data) {
try {
- return getDetector().detect(UnsynchronizedByteArrayInputStream.builder().setByteArray(data).get(), new Metadata()) !=
+ return getDetector().detect(
+ UnsynchronizedByteArrayInputStream.builder().setByteArray(data).get(), new Metadata()) !=
MediaType.OCTET_STREAM;
} catch (IOException e) {
// Should never happen with a ByteArrayInputStream
@@ -65,10 +67,12 @@ class MagicMatch implements Clause {
}
}
+ @Override
public int size() {
return getDetector().getLength();
}
+ @Override
public String toString() {
return mediaType.toString() + " " + type + " " + offset + " " + value + " " + mask;
}
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-html-module/src/main/java/org/apache/tika/parser/html/HtmlHandler.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-html-module/src/main/java/org/apache/tika/parser/html/HtmlHandler.java
index 17912125d..cb25f63a1 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-html-module/src/main/java/org/apache/tika/parser/html/HtmlHandler.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-html-module/src/main/java/org/apache/tika/parser/html/HtmlHandler.java
@@ -354,7 +354,8 @@ class HtmlHandler extends TextContentHandler {
EmbeddedDocumentExtractor embeddedDocumentExtractor =
EmbeddedDocumentUtil.getEmbeddedDocumentExtractor(context);
if (embeddedDocumentExtractor.shouldParseEmbedded(m)) {
- try (InputStream stream = UnsynchronizedByteArrayInputStream.builder().setByteArray(string.getBytes(StandardCharsets.UTF_8)).get()) {
+ try (InputStream stream = UnsynchronizedByteArrayInputStream.builder().
+ setByteArray(string.getBytes(StandardCharsets.UTF_8)).get()) {
embeddedDocumentExtractor.parseEmbedded(stream, xhtml, m, true);
} catch (IOException e) {
EmbeddedDocumentUtil.recordEmbeddedStreamException(e, metadata);
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-jdbc-commons/src/main/java/org/apache/tika/parser/jdbc/JDBCTableReader.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-jdbc-commons/src/main/java/org/apache/tika/parser/jdbc/JDBCTableReader.java
index 9df4d197d..66c6634f6 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-jdbc-commons/src/main/java/org/apache/tika/parser/jdbc/JDBCTableReader.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-jdbc-commons/src/main/java/org/apache/tika/parser/jdbc/JDBCTableReader.java
@@ -201,7 +201,8 @@ public class JDBCTableReader {
String s = clob.getSubString(0, readSize);
if (embeddedDocumentUtil.shouldParseEmbedded(m)) {
embeddedDocumentUtil
- .parseEmbedded(UnsynchronizedByteArrayInputStream.builder().setByteArray(s.getBytes(UTF_8)).get(), handler, m, true);
+ .parseEmbedded(UnsynchronizedByteArrayInputStream.builder().setByteArray(
+ s.getBytes(UTF_8)).get(), handler, m, true);
}
}
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OfficeParser.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OfficeParser.java
index c59e57072..9f491f80b 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OfficeParser.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OfficeParser.java
@@ -118,7 +118,8 @@ public class OfficeParser extends AbstractOfficeParser {
if (embeddedDocumentExtractor.shouldParseEmbedded(m)) {
embeddedDocumentExtractor.parseEmbedded(
//pass in space character so that we don't trigger a zero-byte exception
- UnsynchronizedByteArrayInputStream.builder().setByteArray(new byte[]{'\u0020'}).get(), xhtml, m, true);
+ UnsynchronizedByteArrayInputStream.builder().
+ setByteArray(new byte[]{'\u0020'}).get(), xhtml, m, true);
}
return;
}
@@ -132,7 +133,8 @@ public class OfficeParser extends AbstractOfficeParser {
}
if (embeddedDocumentExtractor.shouldParseEmbedded(m)) {
embeddedDocumentExtractor.parseEmbedded(
- UnsynchronizedByteArrayInputStream.builder().setByteArray(e.getValue().getBytes(StandardCharsets.UTF_8)).get(),
+ UnsynchronizedByteArrayInputStream.builder().
+ setByteArray(e.getValue().getBytes(StandardCharsets.UTF_8)).get(),
xhtml, m, true);
}
}
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/txt/CharsetMatch.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/txt/CharsetMatch.java
index beb56f394..cdbe934c3 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/txt/CharsetMatch.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/txt/CharsetMatch.java
@@ -100,7 +100,8 @@ public class CharsetMatch implements Comparable<CharsetMatch> {
if (inputStream == null) {
try {
- inputStream = UnsynchronizedByteArrayInputStream.builder().setByteArray(fRawInput).setLength(fRawLength).get();
+ inputStream = UnsynchronizedByteArrayInputStream.builder().
+ setByteArray(fRawInput).setLength(fRawLength).get();
}
catch (IOException ex) {
return null;
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-xml-module/src/main/java/org/apache/tika/parser/xml/FictionBookParser.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-xml-module/src/main/java/org/apache/tika/parser/xml/FictionBookParser.java
index 4e7f0dad7..c83af0fd1 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-xml-module/src/main/java/org/apache/tika/parser/xml/FictionBookParser.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-xml-module/src/main/java/org/apache/tika/parser/xml/FictionBookParser.java
@@ -87,7 +87,8 @@ public class FictionBookParser extends XMLParser {
public void endElement(String uri, String localName, String qName) throws SAXException {
if (binaryMode) {
try (InputStream stream =
- UnsynchronizedByteArrayInputStream.builder().setByteArray(Base64.decodeBase64(binaryData.toString())).get()) {
+ UnsynchronizedByteArrayInputStream.builder().
+ setByteArray(Base64.decodeBase64(binaryData.toString())).get()) {
partExtractor.parseEmbedded(
stream, handler, metadata, true);
} catch (IOException e) {