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
The following commit(s) were added to refs/heads/branch_2x by this push:
new 671977514 TIKA-4278: more code cleanup, replace deprecated
671977514 is described below
commit 67197751444a8ed6212c766da9d22482465436d9
Author: Tilman Hausherr <[email protected]>
AuthorDate: Mon Jul 15 09:28:28 2024 +0200
TIKA-4278: more code cleanup, replace deprecated
---
.../src/main/java/org/apache/tika/parser/csv/CSVSniffer.java | 2 +-
.../main/java/org/apache/tika/parser/csv/TextAndCSVParser.java | 10 +++++-----
.../src/main/java/org/apache/tika/parser/txt/TXTParser.java | 7 ++++---
3 files changed, 10 insertions(+), 9 deletions(-)
diff --git
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/csv/CSVSniffer.java
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/csv/CSVSniffer.java
index 53c9e4cb5..24123a56b 100644
---
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/csv/CSVSniffer.java
+++
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/csv/CSVSniffer.java
@@ -86,7 +86,7 @@ class CSVSniffer {
//TODO: take into consideration the filename. Perhaps require
//a higher confidence if detection contradicts filename?
List<CSVResult> results = sniff(reader);
- if (results == null || results.size() == 0) {
+ if (results == null || results.isEmpty()) {
return CSVResult.TEXT;
}
CSVResult bestResult = results.get(0);
diff --git
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/csv/TextAndCSVParser.java
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/csv/TextAndCSVParser.java
index 304d9f928..e9b35da67 100644
---
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/csv/TextAndCSVParser.java
+++
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/csv/TextAndCSVParser.java
@@ -192,9 +192,9 @@ public class TextAndCSVParser extends
AbstractEncodingDetectorParser {
return;
}
- CSVFormat csvFormat =
CSVFormat.EXCEL.withDelimiter(params.getDelimiter());
+ CSVFormat csvFormat =
CSVFormat.EXCEL.builder().setDelimiter(params.getDelimiter()).build();
metadata.set(DELIMITER_PROPERTY,
- CHAR_TO_STRING_DELIMITER_MAP.get(csvFormat.getDelimiter()));
+
CHAR_TO_STRING_DELIMITER_MAP.get(csvFormat.getDelimiterString().charAt(0)));
XHTMLContentHandler xhtmlContentHandler = new
XHTMLContentHandler(handler, metadata);
int totalRows = 0;
@@ -282,13 +282,13 @@ public class TextAndCSVParser extends
AbstractEncodingDetectorParser {
MediaType mediaType = MediaType.parse(mediaString);
if (!SUPPORTED_TYPES.contains(mediaType.getBaseType())) {
params.setMediaType(mediaType);
- return new AutoDetectReader(new
CloseShieldInputStream(stream), metadata,
+ return new
AutoDetectReader(CloseShieldInputStream.wrap(stream), metadata,
getEncodingDetector(context));
}
}
Reader reader;
if (params.getCharset() == null) {
- reader = new AutoDetectReader(new CloseShieldInputStream(stream),
metadata,
+ reader = new AutoDetectReader(CloseShieldInputStream.wrap(stream),
metadata,
getEncodingDetector(context));
params.setCharset(((AutoDetectReader) reader).getCharset());
if (params.isComplete()) {
@@ -296,7 +296,7 @@ public class TextAndCSVParser extends
AbstractEncodingDetectorParser {
}
} else {
reader = new BufferedReader(
- new InputStreamReader(new CloseShieldInputStream(stream),
params.getCharset()));
+ new InputStreamReader(CloseShieldInputStream.wrap(stream),
params.getCharset()));
}
if (params.getDelimiter() == null &&
diff --git
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/txt/TXTParser.java
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/txt/TXTParser.java
index c6e743091..f39a2fe01 100644
---
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/txt/TXTParser.java
+++
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/txt/TXTParser.java
@@ -41,7 +41,7 @@ import org.apache.tika.sax.XHTMLContentHandler;
* beginning of the stream and the given document metadata, most
* notably the <code>charset</code> parameter of a
* {@link org.apache.tika.metadata.HttpHeaders#CONTENT_TYPE} value.
- * <p/>
+ * <p>
* This parser sets the following output metadata entries:
* <dl>
* <dt>{@link org.apache.tika.metadata.HttpHeaders#CONTENT_TYPE}</dt>
@@ -59,22 +59,23 @@ public class TXTParser extends
AbstractEncodingDetectorParser {
Collections.singleton(MediaType.TEXT_PLAIN);
public TXTParser() {
- super();
}
public TXTParser(EncodingDetector encodingDetector) {
super(encodingDetector);
}
+ @Override
public Set<MediaType> getSupportedTypes(ParseContext context) {
return SUPPORTED_TYPES;
}
+ @Override
public void parse(InputStream stream, ContentHandler handler, Metadata
metadata,
ParseContext context) throws IOException, SAXException,
TikaException {
// Automatically detect the character encoding
- try (AutoDetectReader reader = new AutoDetectReader(new
CloseShieldInputStream(stream),
+ try (AutoDetectReader reader = new
AutoDetectReader(CloseShieldInputStream.wrap(stream),
metadata, getEncodingDetector(context))) {
//try to get detected content type; could be a subclass of
text/plain
//such as vcal, etc.
