Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

SAK-49497 Update Tika Parsers and dependencies #12126

Merged
merged 3 commits into from
Nov 28, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 9 additions & 1 deletion kernel/kernel-impl/pom.xml
Original file line number Diff line number Diff line change
Expand Up @@ -88,7 +88,15 @@
</dependency>
<dependency>
<groupId>org.apache.tika</groupId>
<artifactId>tika-parsers</artifactId>
<artifactId>tika-parsers-standard-package</artifactId>
</dependency>
<dependency>
<groupId>org.apache.tika</groupId>
<artifactId>tika-parser-scientific-package</artifactId>
</dependency>
<dependency>
<groupId>org.apache.tika</groupId>
<artifactId>tika-parser-sqlite3-package</artifactId>
</dependency>
<dependency>
<groupId>org.zwobble.mammoth</groupId>
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -78,6 +78,7 @@
import org.apache.tika.detect.Detector;
import org.apache.tika.io.TikaInputStream;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.mime.MimeTypes;
import org.apache.tika.parser.txt.CharsetDetector;
import org.apache.tika.parser.txt.CharsetMatch;
Expand Down Expand Up @@ -5964,7 +5965,7 @@ public void commitResource(ContentResourceEdit edit, int priority) throws OverQu

final Metadata metadata = new Metadata();
//This might not want to be set as it would advise the detector
metadata.set(Metadata.RESOURCE_NAME_KEY, edit.getId());
metadata.set(TikaCoreProperties.RESOURCE_NAME_KEY, edit.getId());
metadata.set(Metadata.CONTENT_TYPE, currentContentType);
String newmatch = "";
//If we are ignoring the content for this extension, don't give it any data
Expand Down
46 changes: 21 additions & 25 deletions master/pom.xml
Original file line number Diff line number Diff line change
Expand Up @@ -72,12 +72,12 @@
<sakai.spring.security.version>5.5.7</sakai.spring.security.version>
<sakai.spring.hateoas.version>1.5.5</sakai.spring.hateoas.version>
<sakai.spring.plugin.version>2.0.0.RELEASE</sakai.spring.plugin.version>
<sakai.tika.version>1.28.5</sakai.tika.version>
<sakai.tika.version>2.9.1</sakai.tika.version>
<sakai.tomcat.version>9.0.83</sakai.tomcat.version>
<sakai.thymeleaf.version>3.0.15.RELEASE</sakai.thymeleaf.version>
<sakai.velocity.version>1.6.4</sakai.velocity.version>
<sakai.log4j.version>2.20.0</sakai.log4j.version>
<sakai.slf4j.version>1.7.36</sakai.slf4j.version>
<sakai.slf4j.version>2.0.9</sakai.slf4j.version>
<sakai.poi.version>5.2.4</sakai.poi.version>
<sakai.mockito.version>3.11.2</sakai.mockito.version>
<sakai.powermock.version>2.0.9</sakai.powermock.version>
Expand Down Expand Up @@ -1165,30 +1165,26 @@
<scope>test</scope>
</dependency>

<!-- Tika includes asm-debug-all which it really shouldn't
since it is used in multiple places it is declared here so its done right -->
<dependency>
<groupId>org.apache.tika</groupId>
<artifactId>tika-parsers</artifactId>
<version>${sakai.tika.version}</version>
<exclusions>
<exclusion>
<groupId>de.l3s.boilerpipe</groupId>
<artifactId>boilerpipe</artifactId>
</exclusion>
<exclusion>
<groupId>org.ow2.asm</groupId>
<artifactId>asm-debug-all</artifactId>
</exclusion>
<exclusion>
<groupId>commons-logging</groupId>
<artifactId>commons-logging</artifactId>
</exclusion>
<exclusion>
<groupId>commons-logging</groupId>
<artifactId>commons-logging-api</artifactId>
</exclusion>
</exclusions>
<groupId>org.apache.tika</groupId>
<artifactId>tika-parsers-standard-package</artifactId>
<version>${sakai.tika.version}</version>
<exclusions>
<exclusion>
<groupId>commons-logging</groupId>
<artifactId>commons-logging</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.apache.tika</groupId>
<artifactId>tika-parser-scientific-package</artifactId>
<version>${sakai.tika.version}</version>
</dependency>
<dependency>
<groupId>org.apache.tika</groupId>
<artifactId>tika-parser-sqlite3-package</artifactId>
<version>${sakai.tika.version}</version>
</dependency>
<dependency>
<groupId>org.apache.tika</groupId>
Expand Down
14 changes: 11 additions & 3 deletions search/search-impl/impl/pom.xml
Original file line number Diff line number Diff line change
Expand Up @@ -120,7 +120,7 @@
<dependency>
<groupId>org.apache.pdfbox</groupId>
<artifactId>pdfbox</artifactId>
<version>2.0.26</version>
<version>2.0.29</version>
<exclusions>
<exclusion>
<groupId>commons-logging</groupId>
Expand All @@ -144,8 +144,16 @@
<artifactId>tika-core</artifactId>
</dependency>
<dependency>
<groupId>org.apache.tika</groupId>
<artifactId>tika-parsers</artifactId>
<groupId>org.apache.tika</groupId>
<artifactId>tika-parsers-standard-package</artifactId>
</dependency>
<dependency>
<groupId>org.apache.tika</groupId>
<artifactId>tika-parser-scientific-package</artifactId>
</dependency>
<dependency>
<groupId>org.apache.tika</groupId>
<artifactId>tika-parser-sqlite3-package</artifactId>
</dependency>
<dependency>
<groupId>commons-codec</groupId>
Expand Down
Loading