Skip to content

Commit 315704a

Browse files
committed
2 parents 0fefbe6 + 446bc14 commit 315704a

16 files changed

Lines changed: 43 additions & 47 deletions

File tree

CHANGES.txt

Lines changed: 11 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -1,8 +1,8 @@
1-
Release 4.0.0-BETA1 - ???
1+
Release 4.0.0-alpha-1 - 5/4/2026
22

33
BREAKING CHANGES
44

5-
* Moved towards default json based configuration (TIKA-4544 and many others).
5+
* Move from xml to json based configuration (TIKA-4544 and many others).
66

77
* tika-pipes implementation modules have been reorganized by
88
resource (tika-pipes-solr) vs task (tika-pipes-fetcher-solr)
@@ -39,9 +39,14 @@ Release 4.0.0-BETA1 - ???
3939

4040
* Fix concurrency bug in TikaToXMP (TIKA-4393)
4141

42-
Release 3.3.0 - ???
42+
Release 3.3.0 - 3/18/2026
4343

44-
* Various fixes based on regression testing (TIKA-4563).
44+
* Switch to poi-ooxml-full (TIKA-4563).
45+
46+
* Users need to add "allowAbsolutePaths=true" for the FileSystemFetcher to fetch
47+
an absolute path (TIKA-4649).
48+
49+
* Add a markdown option for content handlers (TIKA-4563).
4550

4651
* Improve zip parsing (TIKA-4650).
4752

@@ -57,14 +62,15 @@ Release 3.3.0 - ???
5762

5863
* Improve extraction of Javascript from PDFs (TIKA-4465).
5964

60-
Release 3.2.3 - ???
65+
Release 3.2.3 - 9/11/2025
6166

6267
* Allow backwards compatibility with versions of commons-compress before 1.28.0 (TIKA-4469).
6368

6469
* Fix XFA parsing within PDFs when woodstox is on the classpath as in tika-server (TIKA-4482).
6570

6671
* Dependency updates.
6772

73+
6874
Release 3.2.2 - 8/6/2025
6975

7076
* Fix for CVE-2025-54988.

tika-bom/pom.xml

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -51,6 +51,7 @@
5151
<connection>scm:git:https://github.com/apache/tika.git</connection>
5252
<developerConnection>scm:git:https://github.com/apache/tika.git</developerConnection>
5353
<url>https://github.com/apache/tika</url>
54+
<tag>HEAD</tag>
5455
</scm>
5556

5657
<distributionManagement>

tika-core/src/test/java/org/apache/tika/TikaIT.java

Lines changed: 4 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -27,8 +27,10 @@ public class TikaIT {
2727
public void testToString() {
2828
String version = new Tika().toString();
2929
assertNotNull(version);
30-
assertTrue(
31-
version.matches("Apache Tika \\d+\\.\\d+\\.\\d+(-(?:ALPHA|BETA)\\d*)?(?:-SNAPSHOT)?"));
30+
assertTrue(version.matches(
31+
"Apache Tika \\d+\\.\\d+\\.\\d+"
32+
+ "(?:-(?:ALPHA|BETA)\\d*|-(?:alpha|beta|milestone|rc)-\\d+)?"
33+
+ "(?:-SNAPSHOT)?"));
3234
}
3335

3436
}

tika-ml/tika-ml-chardetect/pom.xml

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -134,9 +134,9 @@
134134
<transformer implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
135135
<mainClass>org.apache.tika.ml.chardetect.tools.TrainNaiveBayesBigram</mainClass>
136136
</transformer>
137-
<transformer implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer"/>
138-
<transformer implementation="org.apache.maven.plugins.shade.resource.ApacheLicenseResourceTransformer"/>
139-
<transformer implementation="org.apache.maven.plugins.shade.resource.ApacheNoticeResourceTransformer"/>
137+
<transformer implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer" />
138+
<transformer implementation="org.apache.maven.plugins.shade.resource.ApacheLicenseResourceTransformer" />
139+
<transformer implementation="org.apache.maven.plugins.shade.resource.ApacheNoticeResourceTransformer" />
140140
</transformers>
141141
<filters>
142142
<filter>

tika-ml/tika-ml-junkdetect/pom.xml

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -135,9 +135,9 @@
135135
<transformer implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
136136
<mainClass>org.apache.tika.ml.junkdetect.tools.TrainJunkModel</mainClass>
137137
</transformer>
138-
<transformer implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer"/>
139-
<transformer implementation="org.apache.maven.plugins.shade.resource.ApacheLicenseResourceTransformer"/>
140-
<transformer implementation="org.apache.maven.plugins.shade.resource.ApacheNoticeResourceTransformer"/>
138+
<transformer implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer" />
139+
<transformer implementation="org.apache.maven.plugins.shade.resource.ApacheLicenseResourceTransformer" />
140+
<transformer implementation="org.apache.maven.plugins.shade.resource.ApacheNoticeResourceTransformer" />
141141
</transformers>
142142
<filters>
143143
<filter>

tika-parent/pom.xml

Lines changed: 10 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -19,15 +19,14 @@
1919
under the License.
2020
-->
2121

22-
<project xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://maven.apache.org/POM/4.0.0"
23-
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 https://maven.apache.org/xsd/maven-4.0.0.xsd">
22+
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 https://maven.apache.org/xsd/maven-4.0.0.xsd">
2423
<modelVersion>4.0.0</modelVersion>
2524

2625
<parent>
2726
<groupId>org.apache</groupId>
2827
<artifactId>apache</artifactId>
2928
<version>37</version>
30-
<relativePath/>
29+
<relativePath />
3130
</parent>
3231

3332
<groupId>org.apache.tika</groupId>
@@ -140,7 +139,7 @@
140139
<organization>NASA Jet Propulsion Laboratory</organization>
141140
<organizationUrl>http://www.jpl.nasa.gov</organizationUrl>
142141
<timezone>-8</timezone>
143-
<properties/>
142+
<properties />
144143
<roles>
145144
<role>committer</role>
146145
</roles>
@@ -150,7 +149,7 @@
150149
<id>mikemccand</id>
151150
<email>mikemccand@apache.org</email>
152151
<organization>IBM</organization>
153-
<properties/>
152+
<properties />
154153
<roles>
155154
<role>committer</role>
156155
</roles>
@@ -289,7 +288,7 @@
289288
<maven.compiler.release>17</maven.compiler.release>
290289
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
291290
<project.reporting.outputEncoding>${project.build.sourceEncoding}</project.reporting.outputEncoding>
292-
<project.build.outputTimestamp>2026-02-01T00:00:00Z</project.build.outputTimestamp>
291+
<project.build.outputTimestamp>2026-05-04T23:37:57Z</project.build.outputTimestamp>
293292
<!-- plugin versions -->
294293
<!-- updates may not be detected by the maven versions plugin:
295294
https://github.com/mojohaus/versions/issues/1070 -->
@@ -467,12 +466,12 @@
467466
<maven.exec.version>3.6.3</maven.exec.version>
468467

469468
<!-- needs to exist even if empty due to problems with jacoco-maven-plugin -->
470-
<addmod/>
469+
<addmod />
471470
<!-- This is a default value to avoid problems when running single tests
472471
see also https://stackoverflow.com/a/28695766/535646
473472
https://maven.apache.org/surefire/maven-surefire-plugin/faq.html#late-property-evaluation
474473
-->
475-
<surefireArgLine/>
474+
<surefireArgLine />
476475
</properties>
477476

478477
<dependencyManagement>
@@ -1523,7 +1522,7 @@
15231522
<id>enforce-maven</id>
15241523
<configuration>
15251524
<rules>
1526-
<dependencyConvergence/>
1525+
<dependencyConvergence />
15271526
<requireMavenVersion>
15281527
<version>3.5</version>
15291528
</requireMavenVersion>
@@ -1607,7 +1606,7 @@
16071606
<spaces>true</spaces>
16081607
<spacesPerTab>4</spacesPerTab>
16091608
</indent>
1610-
<removeUnusedImports/>
1609+
<removeUnusedImports />
16111610
<importOrder>
16121611
<order>\#,java|javax,,org.apache.tika</order>
16131612
</importOrder>
@@ -1772,7 +1771,7 @@
17721771
</profile>
17731772

17741773
</profiles>
1775-
<scm>
1774+
<scm child.scm.connection.inherit.append.path="false" child.scm.developerConnection.inherit.append.path="false" child.scm.url.inherit.append.path="false">
17761775
<tag>3.0.0-rc1</tag>
17771776
<connection>scm:git:https://github.com/apache/tika.git</connection>
17781777
<developerConnection>scm:git:https://github.com/apache/tika.git</developerConnection>

tika-parsers/tika-http-jdk/pom.xml

Lines changed: 1 addition & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -17,9 +17,7 @@
1717
specific language governing permissions and limitations
1818
under the License.
1919
-->
20-
<project xmlns="http://maven.apache.org/POM/4.0.0"
21-
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
22-
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 https://maven.apache.org/xsd/maven-4.0.0.xsd">
20+
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 https://maven.apache.org/xsd/maven-4.0.0.xsd">
2321
<modelVersion>4.0.0</modelVersion>
2422

2523
<parent>

tika-parsers/tika-parsers-ml/tika-inference/pom.xml

Lines changed: 1 addition & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -17,9 +17,7 @@
1717
specific language governing permissions and limitations
1818
under the License.
1919
-->
20-
<project xmlns="http://maven.apache.org/POM/4.0.0"
21-
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
22-
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 https://maven.apache.org/xsd/maven-4.0.0.xsd">
20+
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 https://maven.apache.org/xsd/maven-4.0.0.xsd">
2321
<modelVersion>4.0.0</modelVersion>
2422

2523
<parent>

tika-parsers/tika-parsers-ml/tika-parser-tess4j-module/pom.xml

Lines changed: 1 addition & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -17,9 +17,7 @@
1717
specific language governing permissions and limitations
1818
under the License.
1919
-->
20-
<project xmlns="http://maven.apache.org/POM/4.0.0"
21-
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
22-
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 https://maven.apache.org/xsd/maven-4.0.0.xsd">
20+
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 https://maven.apache.org/xsd/maven-4.0.0.xsd">
2321
<modelVersion>4.0.0</modelVersion>
2422

2523
<parent>

tika-parsers/tika-parsers-ml/tika-vlm/pom.xml

Lines changed: 1 addition & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -17,9 +17,7 @@
1717
specific language governing permissions and limitations
1818
under the License.
1919
-->
20-
<project xmlns="http://maven.apache.org/POM/4.0.0"
21-
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
22-
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 https://maven.apache.org/xsd/maven-4.0.0.xsd">
20+
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 https://maven.apache.org/xsd/maven-4.0.0.xsd">
2321
<modelVersion>4.0.0</modelVersion>
2422

2523
<parent>

0 commit comments

Comments
 (0)