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 2019/12/03 01:52:08 UTC
[tika] branch branch_1x updated (5920689 -> a8d20dd)
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 5920689 improve logging and error handling in TikaServerIntegrationTest
new 3c3214d update changes for 1.23-rc2
new 4eb73d0 TIKA-2630 -- add defensive null check and fix "if (...width)" to "if (...height)"
new a8d20dd roll back in preparation for 1.23-rc2
The 3 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:
CHANGES.txt | 6 +++++-
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-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/parser/image/ImageMetadataExtractor.java | 17 ++++++++++++-----
tika-serialization/pom.xml | 2 +-
tika-server/pom.xml | 2 +-
tika-translate/pom.xml | 2 +-
tika-xmp/pom.xml | 2 +-
19 files changed, 34 insertions(+), 23 deletions(-)
[tika] 02/03: TIKA-2630 -- add defensive null check and fix "if
(...width)" to "if (...height)"
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 4eb73d02888fa36d00305f47d3c70f8d9f3d9b48
Author: tallison <ta...@apache.org>
AuthorDate: Mon Dec 2 20:34:51 2019 -0500
TIKA-2630 -- add defensive null check and fix "if (...width)" to "if (...height)"
---
.../tika/parser/image/ImageMetadataExtractor.java | 17 ++++++++++++-----
1 file changed, 12 insertions(+), 5 deletions(-)
diff --git a/tika-parsers/src/main/java/org/apache/tika/parser/image/ImageMetadataExtractor.java b/tika-parsers/src/main/java/org/apache/tika/parser/image/ImageMetadataExtractor.java
index 9fec322..912c0f1 100644
--- a/tika-parsers/src/main/java/org/apache/tika/parser/image/ImageMetadataExtractor.java
+++ b/tika-parsers/src/main/java/org/apache/tika/parser/image/ImageMetadataExtractor.java
@@ -504,12 +504,19 @@ public class ImageMetadataExtractor {
// For Compressed Images read from ExifSubIFDDirectory
if (directory.containsTag(ExifSubIFDDirectory.TAG_EXIF_IMAGE_WIDTH)) {
- metadata.set(Metadata.IMAGE_WIDTH,
- trimPixels(directory.getDescription(ExifSubIFDDirectory.TAG_EXIF_IMAGE_WIDTH)));
+ String width = directory.getDescription(ExifSubIFDDirectory.TAG_EXIF_IMAGE_WIDTH);
+ //check for null because this could overwrite earlier set width if the value is null
+ if (width != null) {
+ metadata.set(Metadata.IMAGE_WIDTH,
+ trimPixels(width));
+ }
}
- if (directory.containsTag(ExifSubIFDDirectory.TAG_EXIF_IMAGE_WIDTH)) {
- metadata.set(Metadata.IMAGE_LENGTH,
- trimPixels(directory.getDescription(ExifSubIFDDirectory.TAG_EXIF_IMAGE_HEIGHT)));
+
+ if (directory.containsTag(ExifSubIFDDirectory.TAG_EXIF_IMAGE_HEIGHT)) {
+ String height = directory.getDescription(ExifSubIFDDirectory.TAG_EXIF_IMAGE_HEIGHT);
+ if (height != null) {
+ metadata.set(Metadata.IMAGE_LENGTH, trimPixels(height));
+ }
}
}
[tika] 03/03: roll back in preparation for 1.23-rc2
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 a8d20dd33ead3eb37447f20dc27b5a4810db6010
Author: tallison <ta...@apache.org>
AuthorDate: Mon Dec 2 20:51:38 2019 -0500
roll back in preparation for 1.23-rc2
---
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-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 +-
17 files changed, 17 insertions(+), 17 deletions(-)
diff --git a/pom.xml b/pom.xml
index 837c704..249b2d5 100644
--- a/pom.xml
+++ b/pom.xml
@@ -25,7 +25,7 @@
<parent>
<groupId>org.apache.tika</groupId>
<artifactId>tika-parent</artifactId>
- <version>1.24-SNAPSHOT</version>
+ <version>1.23-SNAPSHOT</version>
<relativePath>tika-parent/pom.xml</relativePath>
</parent>
diff --git a/tika-app/pom.xml b/tika-app/pom.xml
index 8faaab8..930b739 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>1.24-SNAPSHOT</version>
+ <version>1.23-SNAPSHOT</version>
<relativePath>../tika-parent/pom.xml</relativePath>
</parent>
diff --git a/tika-batch/pom.xml b/tika-batch/pom.xml
index 8595a51..c7365a2 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>1.24-SNAPSHOT</version>
+ <version>1.23-SNAPSHOT</version>
<relativePath>../tika-parent/pom.xml</relativePath>
</parent>
diff --git a/tika-bundle/pom.xml b/tika-bundle/pom.xml
index 9550fd7..6d889dc 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>1.24-SNAPSHOT</version>
+ <version>1.23-SNAPSHOT</version>
<relativePath>../tika-parent/pom.xml</relativePath>
</parent>
diff --git a/tika-core/pom.xml b/tika-core/pom.xml
index 32ae3ed..15eecaa 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>1.24-SNAPSHOT</version>
+ <version>1.23-SNAPSHOT</version>
<relativePath>../tika-parent/pom.xml</relativePath>
</parent>
diff --git a/tika-dl/pom.xml b/tika-dl/pom.xml
index dcf1d9b..b13eadb 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>1.24-SNAPSHOT</version>
+ <version>1.23-SNAPSHOT</version>
<relativePath>../tika-parent/pom.xml</relativePath>
</parent>
diff --git a/tika-eval/pom.xml b/tika-eval/pom.xml
index 3b3f4f7..402dd5e 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>1.24-SNAPSHOT</version>
+ <version>1.23-SNAPSHOT</version>
<relativePath>../tika-parent/pom.xml</relativePath>
</parent>
diff --git a/tika-example/pom.xml b/tika-example/pom.xml
index dd813a9..29e09cd 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>1.24-SNAPSHOT</version>
+ <version>1.23-SNAPSHOT</version>
<relativePath>../tika-parent/pom.xml</relativePath>
</parent>
diff --git a/tika-java7/pom.xml b/tika-java7/pom.xml
index cf7b029..e3bad91 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>1.24-SNAPSHOT</version>
+ <version>1.23-SNAPSHOT</version>
<relativePath>../tika-parent/pom.xml</relativePath>
</parent>
diff --git a/tika-langdetect/pom.xml b/tika-langdetect/pom.xml
index 4c5a0b2..e267a1e 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>1.24-SNAPSHOT</version>
+ <version>1.23-SNAPSHOT</version>
<relativePath>../tika-parent/pom.xml</relativePath>
</parent>
diff --git a/tika-nlp/pom.xml b/tika-nlp/pom.xml
index eeedd78..055dcd3 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>1.24-SNAPSHOT</version>
+ <version>1.23-SNAPSHOT</version>
<relativePath>../tika-parent/pom.xml</relativePath>
</parent>
diff --git a/tika-parent/pom.xml b/tika-parent/pom.xml
index 60d4334..15f7db3 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>1.24-SNAPSHOT</version>
+ <version>1.23-SNAPSHOT</version>
<packaging>pom</packaging>
<name>Apache Tika parent</name>
diff --git a/tika-parsers/pom.xml b/tika-parsers/pom.xml
index 0424efc..221cd50 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>1.24-SNAPSHOT</version>
+ <version>1.23-SNAPSHOT</version>
<relativePath>../tika-parent/pom.xml</relativePath>
</parent>
diff --git a/tika-serialization/pom.xml b/tika-serialization/pom.xml
index 053f9f9..fc8963e 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>1.24-SNAPSHOT</version>
+ <version>1.23-SNAPSHOT</version>
<relativePath>../tika-parent/pom.xml</relativePath>
</parent>
diff --git a/tika-server/pom.xml b/tika-server/pom.xml
index 5781d21..cd4a4d6 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>1.24-SNAPSHOT</version>
+ <version>1.23-SNAPSHOT</version>
<relativePath>../tika-parent/pom.xml</relativePath>
</parent>
diff --git a/tika-translate/pom.xml b/tika-translate/pom.xml
index b65c75f..f181f1f 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>1.24-SNAPSHOT</version>
+ <version>1.23-SNAPSHOT</version>
<relativePath>../tika-parent/pom.xml</relativePath>
</parent>
diff --git a/tika-xmp/pom.xml b/tika-xmp/pom.xml
index 020d182..60d89fe 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>1.24-SNAPSHOT</version>
+ <version>1.23-SNAPSHOT</version>
<relativePath>../tika-parent/pom.xml</relativePath>
</parent>
[tika] 01/03: update changes for 1.23-rc2
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 3c3214d05fcb190c169c2d5424c6f9f1d9b1266c
Author: tallison <ta...@apache.org>
AuthorDate: Mon Dec 2 20:33:41 2019 -0500
update changes for 1.23-rc2
# Conflicts:
# CHANGES.txt
---
CHANGES.txt | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/CHANGES.txt b/CHANGES.txt
index a4fc87e..67dda93 100644
--- a/CHANGES.txt
+++ b/CHANGES.txt
@@ -1,4 +1,4 @@
-Release 1.23 - 11/26/2019
+Release 1.23 - 12/02/2019
* NOTE: The PDFParser now relies on OCRDPI to render page images when
users configure OCR on rendered page images. This will have the effect
@@ -7,6 +7,10 @@ Release 1.23 - 11/26/2019
* NOTE: tika-server no longer returns 415 for file types for which there
is no parser.
+ * Fix bug in AUTO OCR strategy in the PDFParser (TIKA-3002).
+
+ * Fix incorrect height and width metadata extraction from JPEG images (TIKA-2630).
+
* Upgrade to POI 4.1.1 (TIKA-2851).
* Upgrade to PDFBox 2.0.17 (TIKA-2951).