You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ti...@apache.org on 2023/08/12 18:44:20 UTC
[tika] branch main updated (7c3831715 -> f5fbf1490)
This is an automated email from the ASF dual-hosted git repository.
tilman pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tika.git
from 7c3831715 TIKA-4114: avoid methods that no longer exists in PDFBox 3.0
new 05de5ce81 TIKA-4064: avoid deprecated method
new b2710285e TIKA-4114: add comment
new f5fbf1490 TIKA-4114: fix checkstyle
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:
.../main/java/org/apache/tika/parser/pdf/PDFEncodedStringDecoder.java | 3 ++-
.../src/main/java/org/apache/tika/parser/xmp/XMPMetadataExtractor.java | 2 +-
2 files changed, 3 insertions(+), 2 deletions(-)
[tika] 02/03: TIKA-4114: add comment
Posted by ti...@apache.org.
This is an automated email from the ASF dual-hosted git repository.
tilman pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tika.git
commit b2710285e95e784bcbc7904f9de61caa52dc328e
Author: Tilman Hausherr <ti...@apache.org>
AuthorDate: Sat Aug 12 20:17:19 2023 +0200
TIKA-4114: add comment
---
.../main/java/org/apache/tika/parser/pdf/PDFEncodedStringDecoder.java | 1 +
1 file changed, 1 insertion(+)
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFEncodedStringDecoder.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFEncodedStringDecoder.java
index 1d240bf9c..41cd2d573 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFEncodedStringDecoder.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFEncodedStringDecoder.java
@@ -83,6 +83,7 @@ class PDFEncodedStringDecoder {
try {
byte[] bytes = new String("(" + value + ")").getBytes(ISO_8859_1);
InputStream is = UnsynchronizedByteArrayInputStream.builder().setByteArray(bytes).get();
+ //TODO PDFBOX30 replace RandomAccessBuffer with RandomAccessReadBuffer
COSStringParser p = new COSStringParser(new RandomAccessBuffer(is));
String parsed = p.myParseCOSString();
if (parsed != null) {
[tika] 03/03: TIKA-4114: fix checkstyle
Posted by ti...@apache.org.
This is an automated email from the ASF dual-hosted git repository.
tilman pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tika.git
commit f5fbf1490842f7ea4f098ec546f1540f5be9f856
Author: Tilman Hausherr <ti...@apache.org>
AuthorDate: Sat Aug 12 20:44:10 2023 +0200
TIKA-4114: fix checkstyle
---
.../src/main/java/org/apache/tika/parser/xmp/XMPMetadataExtractor.java | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-xmp-commons/src/main/java/org/apache/tika/parser/xmp/XMPMetadataExtractor.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-xmp-commons/src/main/java/org/apache/tika/parser/xmp/XMPMetadataExtractor.java
index 157aedb90..e5e710688 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-xmp-commons/src/main/java/org/apache/tika/parser/xmp/XMPMetadataExtractor.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-xmp-commons/src/main/java/org/apache/tika/parser/xmp/XMPMetadataExtractor.java
@@ -25,6 +25,7 @@ import org.apache.commons.io.input.CloseShieldInputStream;
import org.apache.xmpbox.XMPMetadata;
import org.apache.xmpbox.schema.DublinCoreSchema;
import org.apache.xmpbox.schema.XMPBasicSchema;
+import org.apache.xmpbox.type.BadFieldValueException;
import org.apache.xmpbox.xml.DomXmpParser;
import org.apache.tika.exception.TikaException;
@@ -32,7 +33,6 @@ import org.apache.tika.metadata.DublinCore;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.Property;
import org.apache.tika.metadata.XMP;
-import org.apache.xmpbox.type.BadFieldValueException;
/**
* XMP Metadata Extractor based on Apache XmpBox.
[tika] 01/03: TIKA-4064: avoid deprecated method
Posted by ti...@apache.org.
This is an automated email from the ASF dual-hosted git repository.
tilman pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tika.git
commit 05de5ce811df1c3ce4f8089646500a03dff34215
Author: Tilman Hausherr <ti...@apache.org>
AuthorDate: Sat Aug 12 20:15:25 2023 +0200
TIKA-4064: avoid deprecated method
---
.../main/java/org/apache/tika/parser/pdf/PDFEncodedStringDecoder.java | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFEncodedStringDecoder.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFEncodedStringDecoder.java
index 255465ebb..1d240bf9c 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFEncodedStringDecoder.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFEncodedStringDecoder.java
@@ -82,7 +82,7 @@ class PDFEncodedStringDecoder {
String decode(String value) {
try {
byte[] bytes = new String("(" + value + ")").getBytes(ISO_8859_1);
- InputStream is = new UnsynchronizedByteArrayInputStream(bytes);
+ InputStream is = UnsynchronizedByteArrayInputStream.builder().setByteArray(bytes).get();
COSStringParser p = new COSStringParser(new RandomAccessBuffer(is));
String parsed = p.myParseCOSString();
if (parsed != null) {