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 2020/08/19 07:36:08 UTC
[tika] 02/02: TIKA-3172 -- setEnableAutoSpace and a few others
should have @Field annotation
This is an automated email from the ASF dual-hosted git repository.
tallison pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tika.git
commit 7f0394247c8f5a731b258adbd6683449bc5c757b
Author: tallison <ta...@apache.org>
AuthorDate: Wed Aug 19 03:35:39 2020 -0400
TIKA-3172 -- setEnableAutoSpace and a few others should have @Field annotation
---
tika-parsers/pom.xml | 21 +--------------------
.../java/org/apache/tika/parser/pdf/PDFParser.java | 11 ++---------
.../org/apache/tika/parser/pdf/PDFParserConfig.java | 1 -
3 files changed, 3 insertions(+), 30 deletions(-)
diff --git a/tika-parsers/pom.xml b/tika-parsers/pom.xml
index f479774..ffc4ab2 100644
--- a/tika-parsers/pom.xml
+++ b/tika-parsers/pom.xml
@@ -87,26 +87,7 @@
<scope>test</scope>
</dependency>
- <!-- for java 10
- See TIKA-2778 for why we need to do this now.
- May the gods of API design fix this in the future.
- -->
- <dependency>
- <groupId>org.glassfish.jaxb</groupId>
- <artifactId>jaxb-runtime</artifactId>
- <version>${jaxb.version}</version>
- <exclusions>
- <exclusion>
- <groupId>jakarta.activation</groupId>
- <artifactId>jakarta.activation-api</artifactId>
- </exclusion>
- </exclusions>
- </dependency>
- <dependency>
- <groupId>com.sun.activation</groupId>
- <artifactId>jakarta.activation</artifactId>
- <version>1.2.1</version>
- </dependency>
+
<dependency>
<groupId>xerces</groupId>
<artifactId>xercesImpl</artifactId>
diff --git a/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParser.java b/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParser.java
index c09ca81..f045123 100644
--- a/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParser.java
+++ b/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParser.java
@@ -385,7 +385,6 @@ public class PDFParser extends AbstractParser implements Initializable {
/**
* @see #setEnableAutoSpace(boolean)
- * @deprecated use {@link #getPDFParserConfig()}
*/
public boolean getEnableAutoSpace() {
return defaultConfig.getEnableAutoSpace();
@@ -396,9 +395,8 @@ public class PDFParser extends AbstractParser implements Initializable {
* where spaces should be inserted between words. For
* many PDFs this is necessary as they do not include
* explicit whitespace characters.
- *
- * @deprecated use {@link #setPDFParserConfig(PDFParserConfig)}
*/
+ @Field
public void setEnableAutoSpace(boolean v) {
defaultConfig.setEnableAutoSpace(v);
}
@@ -415,8 +413,6 @@ public class PDFParser extends AbstractParser implements Initializable {
/**
* If true (the default), text in annotations will be
* extracted.
- *
- * @deprecated use {@link #setPDFParserConfig(PDFParserConfig)}
*/
public void setExtractAnnotationText(boolean v) {
defaultConfig.setExtractAnnotationText(v);
@@ -438,9 +434,8 @@ public class PDFParser extends AbstractParser implements Initializable {
* slow down extraction substantially (PDFBOX-956) and
* sometimes remove characters that were not in fact
* duplicated (PDFBOX-1155). By default this is disabled.
- *
- * @deprecated use {@link #setPDFParserConfig(PDFParserConfig)}
*/
+ @Field
public void setSuppressDuplicateOverlappingText(boolean v) {
defaultConfig.setSuppressDuplicateOverlappingText(v);
}
@@ -460,8 +455,6 @@ public class PDFParser extends AbstractParser implements Initializable {
* order"), while for other PDFs it can produce the
* wrong result (for example if there are 2 columns,
* the text will be interleaved). Default is false.
- *
- * @deprecated use {@link #setPDFParserConfig(PDFParserConfig)}
*/
@Field
public void setSortByPosition(boolean v) {
diff --git a/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParserConfig.java b/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParserConfig.java
index bb588df..ce4290e 100644
--- a/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParserConfig.java
+++ b/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParserConfig.java
@@ -93,7 +93,6 @@ public class PDFParserConfig implements Serializable {
// True if we should sort text tokens by position
// (necessary for some PDFs, but messes up other PDFs):
- @Field
private boolean sortByPosition = false;
//True if acroform content should be extracted