[drill] branch master updated: DRILL-8392: Empty Tables Causes Index Out of Bounds Exception on PDF Reader (#2744)

[cgivre]

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

cgivre pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/drill.git


The following commit(s) were added to refs/heads/master by this push:
     new 807138d085 DRILL-8392: Empty Tables Causes Index Out of Bounds 
Exception on PDF Reader (#2744)
807138d085 is described below

commit 807138d085106ba0b97489a55fe9a4c57854f032
Author: Charles S. Givre <cgi...@apache.org>
AuthorDate: Wed Jan 25 08:54:29 2023 -0500

    DRILL-8392: Empty Tables Causes Index Out of Bounds Exception on PDF Reader 
(#2744)
---
 .../java/org/apache/drill/exec/store/pdf/PdfBatchReader.java   | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git 
a/contrib/format-pdf/src/main/java/org/apache/drill/exec/store/pdf/PdfBatchReader.java
 
b/contrib/format-pdf/src/main/java/org/apache/drill/exec/store/pdf/PdfBatchReader.java
index 26d3a94c9f..05dd3b4a52 100644
--- 
a/contrib/format-pdf/src/main/java/org/apache/drill/exec/store/pdf/PdfBatchReader.java
+++ 
b/contrib/format-pdf/src/main/java/org/apache/drill/exec/store/pdf/PdfBatchReader.java
@@ -218,8 +218,16 @@ public class PdfBatchReader implements ManagedReader {
 
       if (!Strings.isNullOrEmpty(value)) {
         writers.get(rowPosition).load(row.get(rowPosition));
+
+        // If there is not a provided schema, advance the row position index 
only when values are found
+        if (negotiator.providedSchema() == null) {
+          rowPosition++;
+        }
+      }
+      // Advance the row position index when there is a provided schema.
+      if (negotiator.providedSchema() != null) {
+        rowPosition++;
       }
-      rowPosition++;
     }
 
     metadataReader.writeMetadata();