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 fe6f33e TIKA-3488 -- revert to include jdom2
fe6f33e is described below
commit fe6f33ee0b61c09d30c46229ea020ad20328d29f
Author: tallison <[email protected]>
AuthorDate: Mon Aug 30 11:31:31 2021 -0400
TIKA-3488 -- revert to include jdom2
---
tika-bundles/tika-bundle-standard/pom.xml | 1 +
.../tika-parsers-standard-modules/tika-parser-news-module/pom.xml | 6 ------
.../src/main/java/org/apache/tika/parser/feed/FeedParser.java | 6 ++++--
3 files changed, 5 insertions(+), 8 deletions(-)
diff --git a/tika-bundles/tika-bundle-standard/pom.xml
b/tika-bundles/tika-bundle-standard/pom.xml
index 0ec97bf..e4d55d7 100644
--- a/tika-bundles/tika-bundle-standard/pom.xml
+++ b/tika-bundles/tika-bundle-standard/pom.xml
@@ -180,6 +180,7 @@
boilerpipe|
rome|
rome-utils|
+ jdom2|
sentiment-analysis-parser|
opennlp-tools|
geoapi|
diff --git
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-news-module/pom.xml
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-news-module/pom.xml
index 2676e6b..9fbdd2f 100644
---
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-news-module/pom.xml
+++
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-news-module/pom.xml
@@ -34,12 +34,6 @@
<groupId>com.rometools</groupId>
<artifactId>rome</artifactId>
<version>${rome.version}</version>
- <exclusions>
- <exclusion>
- <groupId>org.jdom</groupId>
- <artifactId>jdom2</artifactId>
- </exclusion>
- </exclusions>
</dependency>
<dependency>
<groupId>org.slf4j</groupId>
diff --git
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-news-module/src/main/java/org/apache/tika/parser/feed/FeedParser.java
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-news-module/src/main/java/org/apache/tika/parser/feed/FeedParser.java
index b572791..f4d99dd 100644
---
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-news-module/src/main/java/org/apache/tika/parser/feed/FeedParser.java
+++
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-news-module/src/main/java/org/apache/tika/parser/feed/FeedParser.java
@@ -30,6 +30,7 @@ import com.rometools.rome.io.FeedException;
import com.rometools.rome.io.SyndFeedInput;
import org.apache.commons.io.input.CloseShieldInputStream;
import org.xml.sax.ContentHandler;
+import org.xml.sax.InputSource;
import org.xml.sax.SAXException;
import org.apache.tika.exception.TikaException;
@@ -39,7 +40,6 @@ import org.apache.tika.mime.MediaType;
import org.apache.tika.parser.AbstractParser;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.sax.XHTMLContentHandler;
-import org.apache.tika.utils.XMLReaderUtils;
/**
* Feed parser.
@@ -85,8 +85,10 @@ public class FeedParser extends AbstractParser {
ParseContext context) throws IOException, SAXException,
TikaException {
// set the encoding?
try {
+ SyndFeedInput input = new SyndFeedInput();
+ input.setAllowDoctypes(false);
SyndFeed feed =
- new SyndFeedInput().build(XMLReaderUtils.buildDOM(new
CloseShieldInputStream(stream)));
+ input.build(new InputSource(new
CloseShieldInputStream(stream)));
String title = stripTags(feed.getTitleEx());
String description = stripTags(feed.getDescriptionEx());