You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ta...@apache.org on 2022/02/08 16:18:18 UTC

[tika] branch branch_1x updated (ab950dc -> 4099401)

This is an automated email from the ASF dual-hosted git repository.

tallison pushed a change to branch branch_1x
in repository https://gitbox.apache.org/repos/asf/tika.git.


    from ab950dc  TIKA-3671 -- general upgrades with some security upgrades.
     new 54dc778  construct autodetectparser from existing resources
     new d1b6a43  add tab after chart value
     new 0b2b0b5  TIKA-3671 -- general upgrades for 1.28.1
     new 4099401  revert version for rc1 of 1.28.1

The 4 revisions listed above as "new" are entirely new to this
repository and will be described in separate emails.  The revisions
listed as "add" were already present in the repository and have only
been added to this reference.


Summary of changes:
 pom.xml                                                        |  2 +-
 tika-app/pom.xml                                               |  2 +-
 tika-batch/pom.xml                                             |  2 +-
 tika-bundle/pom.xml                                            |  2 +-
 tika-bundle/src/test/java/org/apache/tika/bundle/BundleIT.java |  3 ++-
 tika-core/pom.xml                                              |  2 +-
 tika-dl/pom.xml                                                |  6 +++---
 tika-eval/pom.xml                                              |  4 ++--
 tika-example/pom.xml                                           |  2 +-
 tika-fuzzing/pom.xml                                           |  2 +-
 tika-java7/pom.xml                                             |  2 +-
 tika-langdetect/pom.xml                                        |  2 +-
 tika-nlp/pom.xml                                               |  2 +-
 tika-parent/pom.xml                                            | 10 +++++-----
 tika-parsers/pom.xml                                           |  4 ++--
 .../microsoft/ooxml/OOXMLWordAndPowerPointTextHandler.java     |  3 +--
 tika-serialization/pom.xml                                     |  2 +-
 tika-server/pom.xml                                            |  2 +-
 tika-translate/pom.xml                                         |  2 +-
 tika-xmp/pom.xml                                               |  2 +-
 20 files changed, 29 insertions(+), 29 deletions(-)

[tika] 02/04: add tab after chart value

Posted by ta...@apache.org.
This is an automated email from the ASF dual-hosted git repository.

tallison pushed a commit to branch branch_1x
in repository https://gitbox.apache.org/repos/asf/tika.git

commit d1b6a43114acfbdfa0b6fefe215ff16a24570a99
Author: tallison <ta...@apache.org>
AuthorDate: Tue Feb 8 11:15:28 2022 -0500

    add tab after chart value
---
 tika-eval/pom.xml                                                      | 2 +-
 .../tika/parser/microsoft/ooxml/OOXMLWordAndPowerPointTextHandler.java | 3 +--
 2 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/tika-eval/pom.xml b/tika-eval/pom.xml
index 856f812..48844e3 100644
--- a/tika-eval/pom.xml
+++ b/tika-eval/pom.xml
@@ -65,7 +65,7 @@
         <dependency>
             <groupId>com.h2database</groupId>
             <artifactId>h2</artifactId>
-            <version>2.0.202</version>
+            <version>2.1.210</version>
         </dependency>
         <dependency>
             <groupId>commons-cli</groupId>
diff --git a/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLWordAndPowerPointTextHandler.java b/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLWordAndPowerPointTextHandler.java
index b16befd..2cd4e31 100644
--- a/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLWordAndPowerPointTextHandler.java
+++ b/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLWordAndPowerPointTextHandler.java
@@ -447,6 +447,7 @@ public class OOXMLWordAndPowerPointTextHandler extends DefaultHandler {
             handlePict();
         } else if (V.equals(localName) && C_NS.equals(uri)) { // in value in a chart
             inV = false;
+            appendToBuffer(TAB_CHAR, 0, 1);
             handleEndOfRun();
         } else if (RT.equals(localName)) {
             inRt = false;
@@ -491,7 +492,6 @@ public class OOXMLWordAndPowerPointTextHandler extends DefaultHandler {
 
     @Override
     public void characters(char[] ch, int start, int length) throws SAXException {
-
         if (inACChoiceDepth > 0) {
             return;
         } else if (! includeTextBox && inTextBox) {
@@ -508,7 +508,6 @@ public class OOXMLWordAndPowerPointTextHandler extends DefaultHandler {
             appendToBuffer(ch, start, length);
         } else if (inV) {
             appendToBuffer(ch, start, length);
-            appendToBuffer(TAB_CHAR, 0, 1);
         }
     }
 

[tika] 01/04: construct autodetectparser from existing resources

Posted by ta...@apache.org.
This is an automated email from the ASF dual-hosted git repository.

tallison pushed a commit to branch branch_1x
in repository https://gitbox.apache.org/repos/asf/tika.git

commit 54dc77816234ad021c5fc0841fe9dbe547f551cf
Author: tallison <ta...@apache.org>
AuthorDate: Tue Feb 8 11:14:34 2022 -0500

    construct autodetectparser from existing resources
---
 tika-bundle/src/test/java/org/apache/tika/bundle/BundleIT.java | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tika-bundle/src/test/java/org/apache/tika/bundle/BundleIT.java b/tika-bundle/src/test/java/org/apache/tika/bundle/BundleIT.java
index 6fd1b09..1537f07 100644
--- a/tika-bundle/src/test/java/org/apache/tika/bundle/BundleIT.java
+++ b/tika-bundle/src/test/java/org/apache/tika/bundle/BundleIT.java
@@ -52,6 +52,7 @@ import org.apache.tika.fork.ForkParser;
 import org.apache.tika.io.TikaInputStream;
 import org.apache.tika.metadata.Metadata;
 import org.apache.tika.mime.MediaType;
+import org.apache.tika.parser.AutoDetectParser;
 import org.apache.tika.parser.CompositeParser;
 import org.apache.tika.parser.DefaultParser;
 import org.apache.tika.parser.ParseContext;
@@ -298,7 +299,7 @@ public class BundleIT {
         // Package extraction
         ContentHandler handler = new BodyContentHandler();
 
-        Parser parser = tika.getParser();
+        Parser parser = new AutoDetectParser(contentTypeDetector, defaultParser);
         ParseContext context = new ParseContext();
         context.set(Parser.class, parser);
 

[tika] 04/04: revert version for rc1 of 1.28.1

Posted by ta...@apache.org.
This is an automated email from the ASF dual-hosted git repository.

tallison pushed a commit to branch branch_1x
in repository https://gitbox.apache.org/repos/asf/tika.git

commit 4099401a54da9ac269f7634341e9573cf3c8712d
Author: tallison <ta...@apache.org>
AuthorDate: Tue Feb 8 11:18:02 2022 -0500

    revert version for rc1 of 1.28.1
---
 pom.xml                    | 2 +-
 tika-app/pom.xml           | 2 +-
 tika-batch/pom.xml         | 2 +-
 tika-bundle/pom.xml        | 2 +-
 tika-core/pom.xml          | 2 +-
 tika-dl/pom.xml            | 2 +-
 tika-eval/pom.xml          | 2 +-
 tika-example/pom.xml       | 2 +-
 tika-fuzzing/pom.xml       | 2 +-
 tika-java7/pom.xml         | 2 +-
 tika-langdetect/pom.xml    | 2 +-
 tika-nlp/pom.xml           | 2 +-
 tika-parent/pom.xml        | 2 +-
 tika-parsers/pom.xml       | 2 +-
 tika-serialization/pom.xml | 2 +-
 tika-server/pom.xml        | 2 +-
 tika-translate/pom.xml     | 2 +-
 tika-xmp/pom.xml           | 2 +-
 18 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/pom.xml b/pom.xml
index 327a43b..1dfcc13 100644
--- a/pom.xml
+++ b/pom.xml
@@ -25,7 +25,7 @@
   <parent>
     <groupId>org.apache.tika</groupId>
     <artifactId>tika-parent</artifactId>
-    <version>1.29-SNAPSHOT</version>
+    <version>1.28.1-SNAPSHOT</version>
     <relativePath>tika-parent/pom.xml</relativePath>
   </parent>
 
diff --git a/tika-app/pom.xml b/tika-app/pom.xml
index bdf102a..537f552 100644
--- a/tika-app/pom.xml
+++ b/tika-app/pom.xml
@@ -25,7 +25,7 @@
   <parent>
     <groupId>org.apache.tika</groupId>
     <artifactId>tika-parent</artifactId>
-    <version>1.29-SNAPSHOT</version>
+    <version>1.28.1-SNAPSHOT</version>
     <relativePath>../tika-parent/pom.xml</relativePath>
   </parent>
 
diff --git a/tika-batch/pom.xml b/tika-batch/pom.xml
index 2a4676c..23dfe85 100644
--- a/tika-batch/pom.xml
+++ b/tika-batch/pom.xml
@@ -25,7 +25,7 @@
   <parent>
     <groupId>org.apache.tika</groupId>
     <artifactId>tika-parent</artifactId>
-    <version>1.29-SNAPSHOT</version>
+    <version>1.28.1-SNAPSHOT</version>
     <relativePath>../tika-parent/pom.xml</relativePath>
   </parent>
 
diff --git a/tika-bundle/pom.xml b/tika-bundle/pom.xml
index 531894d..829e823 100644
--- a/tika-bundle/pom.xml
+++ b/tika-bundle/pom.xml
@@ -25,7 +25,7 @@
   <parent>
     <groupId>org.apache.tika</groupId>
     <artifactId>tika-parent</artifactId>
-    <version>1.29-SNAPSHOT</version>
+    <version>1.28.1-SNAPSHOT</version>
     <relativePath>../tika-parent/pom.xml</relativePath>
   </parent>
 
diff --git a/tika-core/pom.xml b/tika-core/pom.xml
index 5f458a9..3995e37 100644
--- a/tika-core/pom.xml
+++ b/tika-core/pom.xml
@@ -25,7 +25,7 @@
   <parent>
     <groupId>org.apache.tika</groupId>
     <artifactId>tika-parent</artifactId>
-    <version>1.29-SNAPSHOT</version>
+    <version>1.28.1-SNAPSHOT</version>
     <relativePath>../tika-parent/pom.xml</relativePath>
   </parent>
 
diff --git a/tika-dl/pom.xml b/tika-dl/pom.xml
index bda77a4..9c0fdcd 100644
--- a/tika-dl/pom.xml
+++ b/tika-dl/pom.xml
@@ -24,7 +24,7 @@
   <parent>
     <groupId>org.apache.tika</groupId>
     <artifactId>tika-parent</artifactId>
-    <version>1.29-SNAPSHOT</version>
+    <version>1.28.1-SNAPSHOT</version>
     <relativePath>../tika-parent/pom.xml</relativePath>
   </parent>
 
diff --git a/tika-eval/pom.xml b/tika-eval/pom.xml
index 48844e3..ee3bc18 100644
--- a/tika-eval/pom.xml
+++ b/tika-eval/pom.xml
@@ -25,7 +25,7 @@
     <parent>
         <groupId>org.apache.tika</groupId>
         <artifactId>tika-parent</artifactId>
-        <version>1.29-SNAPSHOT</version>
+        <version>1.28.1-SNAPSHOT</version>
         <relativePath>../tika-parent/pom.xml</relativePath>
     </parent>
 
diff --git a/tika-example/pom.xml b/tika-example/pom.xml
index 585959f..f07fa16 100644
--- a/tika-example/pom.xml
+++ b/tika-example/pom.xml
@@ -25,7 +25,7 @@
   <parent>
     <groupId>org.apache.tika</groupId>
     <artifactId>tika-parent</artifactId>
-    <version>1.29-SNAPSHOT</version>
+    <version>1.28.1-SNAPSHOT</version>
     <relativePath>../tika-parent/pom.xml</relativePath>
   </parent>
 
diff --git a/tika-fuzzing/pom.xml b/tika-fuzzing/pom.xml
index 8b88095..93b8d52 100644
--- a/tika-fuzzing/pom.xml
+++ b/tika-fuzzing/pom.xml
@@ -21,7 +21,7 @@
     <parent>
         <groupId>org.apache.tika</groupId>
         <artifactId>tika-parent</artifactId>
-        <version>1.29-SNAPSHOT</version>
+        <version>1.28.1-SNAPSHOT</version>
         <relativePath>../tika-parent/pom.xml</relativePath>
     </parent>
 
diff --git a/tika-java7/pom.xml b/tika-java7/pom.xml
index 4fc42f9..76fcb51 100644
--- a/tika-java7/pom.xml
+++ b/tika-java7/pom.xml
@@ -25,7 +25,7 @@
   <parent>
     <groupId>org.apache.tika</groupId>
     <artifactId>tika-parent</artifactId>
-    <version>1.29-SNAPSHOT</version>
+    <version>1.28.1-SNAPSHOT</version>
     <relativePath>../tika-parent/pom.xml</relativePath>
   </parent>
 
diff --git a/tika-langdetect/pom.xml b/tika-langdetect/pom.xml
index c97884c..62ba4ca 100644
--- a/tika-langdetect/pom.xml
+++ b/tika-langdetect/pom.xml
@@ -25,7 +25,7 @@
   <parent>
     <groupId>org.apache.tika</groupId>
     <artifactId>tika-parent</artifactId>
-    <version>1.29-SNAPSHOT</version>
+    <version>1.28.1-SNAPSHOT</version>
     <relativePath>../tika-parent/pom.xml</relativePath>
   </parent>
 
diff --git a/tika-nlp/pom.xml b/tika-nlp/pom.xml
index d058fed..2b7a2d8 100644
--- a/tika-nlp/pom.xml
+++ b/tika-nlp/pom.xml
@@ -24,7 +24,7 @@
   <parent>
     <groupId>org.apache.tika</groupId>
     <artifactId>tika-parent</artifactId>
-    <version>1.29-SNAPSHOT</version>
+    <version>1.28.1-SNAPSHOT</version>
     <relativePath>../tika-parent/pom.xml</relativePath>
   </parent>
 
diff --git a/tika-parent/pom.xml b/tika-parent/pom.xml
index b58f6d3..221e1dc 100644
--- a/tika-parent/pom.xml
+++ b/tika-parent/pom.xml
@@ -31,7 +31,7 @@
 
   <groupId>org.apache.tika</groupId>
   <artifactId>tika-parent</artifactId>
-  <version>1.29-SNAPSHOT</version>
+  <version>1.28.1-SNAPSHOT</version>
   <packaging>pom</packaging>
 
   <name>Apache Tika parent</name>
diff --git a/tika-parsers/pom.xml b/tika-parsers/pom.xml
index 651b5cb..867e564 100644
--- a/tika-parsers/pom.xml
+++ b/tika-parsers/pom.xml
@@ -25,7 +25,7 @@
   <parent>
     <groupId>org.apache.tika</groupId>
     <artifactId>tika-parent</artifactId>
-    <version>1.29-SNAPSHOT</version>
+    <version>1.28.1-SNAPSHOT</version>
     <relativePath>../tika-parent/pom.xml</relativePath>
   </parent>
 
diff --git a/tika-serialization/pom.xml b/tika-serialization/pom.xml
index e62f8cd..cc1e480 100644
--- a/tika-serialization/pom.xml
+++ b/tika-serialization/pom.xml
@@ -25,7 +25,7 @@
   <parent>
     <groupId>org.apache.tika</groupId>
     <artifactId>tika-parent</artifactId>
-    <version>1.29-SNAPSHOT</version>
+    <version>1.28.1-SNAPSHOT</version>
     <relativePath>../tika-parent/pom.xml</relativePath>
   </parent>
 
diff --git a/tika-server/pom.xml b/tika-server/pom.xml
index 667dbdb..64c69f8 100644
--- a/tika-server/pom.xml
+++ b/tika-server/pom.xml
@@ -20,7 +20,7 @@
   <parent>
     <groupId>org.apache.tika</groupId>
     <artifactId>tika-parent</artifactId>
-    <version>1.29-SNAPSHOT</version>
+    <version>1.28.1-SNAPSHOT</version>
     <relativePath>../tika-parent/pom.xml</relativePath>
   </parent>
 
diff --git a/tika-translate/pom.xml b/tika-translate/pom.xml
index 1627a2d..dd3e94d 100644
--- a/tika-translate/pom.xml
+++ b/tika-translate/pom.xml
@@ -25,7 +25,7 @@
   <parent>
     <groupId>org.apache.tika</groupId>
     <artifactId>tika-parent</artifactId>
-    <version>1.29-SNAPSHOT</version>
+    <version>1.28.1-SNAPSHOT</version>
     <relativePath>../tika-parent/pom.xml</relativePath>
   </parent>
 
diff --git a/tika-xmp/pom.xml b/tika-xmp/pom.xml
index 237c999..3e1410d 100644
--- a/tika-xmp/pom.xml
+++ b/tika-xmp/pom.xml
@@ -25,7 +25,7 @@
   <parent>
     <groupId>org.apache.tika</groupId>
     <artifactId>tika-parent</artifactId>
-    <version>1.29-SNAPSHOT</version>
+    <version>1.28.1-SNAPSHOT</version>
     <relativePath>../tika-parent/pom.xml</relativePath>
   </parent>
 

[tika] 03/04: TIKA-3671 -- general upgrades for 1.28.1

Posted by ta...@apache.org.
This is an automated email from the ASF dual-hosted git repository.

tallison pushed a commit to branch branch_1x
in repository https://gitbox.apache.org/repos/asf/tika.git

commit 0b2b0b5b4e2b9ac8e0b1e78c6ad3abeeff131051
Author: tallison <ta...@apache.org>
AuthorDate: Tue Feb 8 11:16:36 2022 -0500

    TIKA-3671 -- general upgrades for 1.28.1
---
 tika-dl/pom.xml      | 4 ++--
 tika-parent/pom.xml  | 8 ++++----
 tika-parsers/pom.xml | 2 +-
 3 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/tika-dl/pom.xml b/tika-dl/pom.xml
index 2d829b2..bda77a4 100644
--- a/tika-dl/pom.xml
+++ b/tika-dl/pom.xml
@@ -37,7 +37,7 @@
   <properties>
     <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
     <dl4j.version>1.0.0-beta6</dl4j.version>
-    <twelvemonkeys.version>3.8.0</twelvemonkeys.version>
+    <twelvemonkeys.version>3.8.1</twelvemonkeys.version>
   </properties>
 
   <dependencies>
@@ -375,7 +375,7 @@
     <dependency>
       <groupId>joda-time</groupId>
       <artifactId>joda-time</artifactId>
-      <version>2.10.10</version>
+      <version>2.10.13</version>
     </dependency>
     <dependency>
       <groupId>commons-io</groupId>
diff --git a/tika-parent/pom.xml b/tika-parent/pom.xml
index f590fc8..b58f6d3 100644
--- a/tika-parent/pom.xml
+++ b/tika-parent/pom.xml
@@ -281,7 +281,7 @@
     <osgi.core.version>6.0.0</osgi.core.version>
 
     <cxf.version>3.5.0</cxf.version>
-    <slf4j.version>1.7.32</slf4j.version>
+    <slf4j.version>1.7.35</slf4j.version>
     <log4j2.version>2.17.1</log4j2.version>
     <jackson.version>2.13.1</jackson.version>
     <!-- when this is next upgraded, see if we can get rid of
@@ -292,7 +292,7 @@
     <cli.version>1.5.0</cli.version>
     <lucene.version>8.11.1</lucene.version>
     <mockito.version>3.11.2</mockito.version>
-    <lombok.version>1.18.20</lombok.version>
+    <lombok.version>1.18.22</lombok.version>
     <opennlp.version>1.9.4</opennlp.version>
     <xerces.version>2.12.2</xerces.version>
   </properties>
@@ -504,12 +504,12 @@
           <dependency>
             <groupId>org.apache.maven.scm</groupId>
             <artifactId>maven-scm-provider-gitexe</artifactId>
-            <version>1.11.2</version>
+            <version>1.12.2</version>
           </dependency>
           <dependency>
             <groupId>org.apache.maven.scm</groupId>
             <artifactId>maven-scm-api</artifactId>
-            <version>1.11.2</version>
+            <version>1.12.2</version>
           </dependency>
         </dependencies>
       </plugin>
diff --git a/tika-parsers/pom.xml b/tika-parsers/pom.xml
index 604e821..651b5cb 100644
--- a/tika-parsers/pom.xml
+++ b/tika-parsers/pom.xml
@@ -170,7 +170,7 @@
     <dependency>
       <groupId>com.github.luben</groupId>
       <artifactId>zstd-jni</artifactId>
-      <version>1.5.0-5</version>
+      <version>1.5.2-1</version>
       <scope>provided</scope>
     </dependency>