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 08:32:31 UTC
(tika) branch branch_2x updated: TIKA-4290: replace deprecated
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 37adc5b4f TIKA-4290: replace deprecated
37adc5b4f is described below
commit 37adc5b4f61d3de94ae6a08ddf7a4541168a5988
Author: Tilman Hausherr <ti...@apache.org>
AuthorDate: Mon Aug 12 15:42:24 2024 +0200
TIKA-4290: replace deprecated
---
.../java/org/apache/tika/parser/isatab/ISArchiveParser.java | 10 ++++++----
.../html/charsetdetector/StandardHtmlEncodingDetector.java | 2 +-
2 files changed, 7 insertions(+), 5 deletions(-)
diff --git a/tika-parsers/tika-parsers-extended/tika-parser-scientific-module/src/main/java/org/apache/tika/parser/isatab/ISArchiveParser.java b/tika-parsers/tika-parsers-extended/tika-parser-scientific-module/src/main/java/org/apache/tika/parser/isatab/ISArchiveParser.java
index 7fd6f39c0..6c7975f82 100644
--- a/tika-parsers/tika-parsers-extended/tika-parser-scientific-module/src/main/java/org/apache/tika/parser/isatab/ISArchiveParser.java
+++ b/tika-parsers/tika-parsers-extended/tika-parser-scientific-module/src/main/java/org/apache/tika/parser/isatab/ISArchiveParser.java
@@ -116,7 +116,7 @@ public class ISArchiveParser implements Parser {
}
String investigation = investigationList[0]; // TODO add to metadata?
- try (InputStream stream = TikaInputStream.get(new File(this.location + investigation))) {
+ try (InputStream stream = TikaInputStream.get(new File(this.location + investigation).toPath())) {
ISATabUtils.parseInvestigation(stream, xhtml, metadata, context, this.studyFileName);
}
xhtml.element("h1", "INVESTIGATION " + metadata.get("Investigation Identifier"));
@@ -134,9 +134,11 @@ public class ISArchiveParser implements Parser {
for (String assayFileName : metadata.getValues(studyAssayFileNameField)) {
xhtml.startElement("div");
xhtml.element("h3", "ASSAY " + assayFileName);
- InputStream stream = TikaInputStream.get(new File(this.location + assayFileName));
- ISATabUtils.parseAssay(stream, xhtml, metadata, context);
- stream.close();
+ // location starts with "/C:" on windows, can't use Paths.get()
+ try (InputStream stream = TikaInputStream.get(new File(this.location + assayFileName).toPath()))
+ {
+ ISATabUtils.parseAssay(stream, xhtml, metadata, context);
+ }
xhtml.endElement("div");
}
}
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-html-module/src/main/java/org/apache/tika/parser/html/charsetdetector/StandardHtmlEncodingDetector.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-html-module/src/main/java/org/apache/tika/parser/html/charsetdetector/StandardHtmlEncodingDetector.java
index 53c89f1f2..90af81e18 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-html-module/src/main/java/org/apache/tika/parser/html/charsetdetector/StandardHtmlEncodingDetector.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-html-module/src/main/java/org/apache/tika/parser/html/charsetdetector/StandardHtmlEncodingDetector.java
@@ -78,7 +78,7 @@ public final class StandardHtmlEncodingDetector implements EncodingDetector {
int limit = getMarkLimit();
input.mark(limit);
// Never read more than the first META_TAG_BUFFER_SIZE bytes
- InputStream limitedStream = new BoundedInputStream(input, limit);
+ InputStream limitedStream = BoundedInputStream.builder().setInputStream(input).setMaxCount(limit).get();
PreScanner preScanner = new PreScanner(limitedStream);
// The order of priority for detection is: