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 2014/07/24 15:37:36 UTC
svn commit: r1613122 - in
/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf:
PDF2XHTML.java PDFParser.java PDFParserConfig.java
Author: tallison
Date: Thu Jul 24 13:37:35 2014
New Revision: 1613122
URL: http://svn.apache.org/r1613122
Log:
Fix potential NPE and fix javadoc refs for PDFParser
Modified:
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDF2XHTML.java
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParser.java
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParserConfig.java
Modified: tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDF2XHTML.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDF2XHTML.java?rev=1613122&r1=1613121&r2=1613122&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDF2XHTML.java (original)
+++ tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDF2XHTML.java Thu Jul 24 13:37:35 2014
@@ -293,7 +293,12 @@ class PDF2XHTML extends PDFTextStripper
return;
}
- for (Map.Entry<String, PDXObject> entry : resources.getXObjects().entrySet()) {
+ Map<String, PDXObject> xObjects = resources.getXObjects();
+ if (xObjects == null) {
+ return;
+ }
+
+ for (Map.Entry<String, PDXObject> entry : xObjects.entrySet()) {
PDXObject object = entry.getValue();
if (object instanceof PDXObjectForm) {
Modified: tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParser.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParser.java?rev=1613122&r1=1613121&r2=1613122&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParser.java (original)
+++ tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParser.java Thu Jul 24 13:37:35 2014
@@ -472,7 +472,7 @@ public class PDFParser extends AbstractP
}
/**
- * @see #setEnableAutoSpace.
+ * @see #setEnableAutoSpace(boolean)
* @deprecated use {@link #getPDFParserConfig()}
*/
public boolean getEnableAutoSpace() {
@@ -513,7 +513,7 @@ public class PDFParser extends AbstractP
}
/**
- * @see #setSuppressDuplicateOverlappingText.
+ * @see #setSuppressDuplicateOverlappingText(boolean)
*
* @deprecated use {@link #getPDFParserConfig()}
*/
@@ -536,7 +536,7 @@ public class PDFParser extends AbstractP
}
/**
- * @see #setSortByPosition.
+ * @see #setSortByPosition(boolean)
*
* @deprecated use {@link #getPDFParserConfig()}
*/
Modified: tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParserConfig.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParserConfig.java?rev=1613122&r1=1613121&r2=1613122&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParserConfig.java (original)
+++ tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParserConfig.java Thu Jul 24 13:37:35 2014
@@ -165,7 +165,7 @@ public class PDFParserConfig implements
* If true (the default), extract content from AcroForms
* at the end of the document.
*
- * @param b
+ * @param extractAcroFormContent
*/
public void setExtractAcroFormContent(boolean extractAcroFormContent) {
this.extractAcroFormContent = extractAcroFormContent;
@@ -227,7 +227,7 @@ public class PDFParserConfig implements
}
- /** @see #setEnableAutoSpace. */
+ /** @see #setEnableAutoSpace(boolean) */
public boolean getEnableAutoSpace() {
return enableAutoSpace;
}