From 3b82c83414f97c835c318ac328783ae07c3c42e9 Mon Sep 17 00:00:00 2001
From: lopez <patrice.lopez@science-miner.com>
Date: Sun, 13 Nov 2022 22:13:19 +0100
Subject: [PATCH]  fix possible missing start token position in block

---
 .../src/main/java/org/grobid/core/sax/PDFALTOSaxHandler.java    | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/grobid-core/src/main/java/org/grobid/core/sax/PDFALTOSaxHandler.java b/grobid-core/src/main/java/org/grobid/core/sax/PDFALTOSaxHandler.java
index f5be3a8e7f..11f4201146 100755
--- a/grobid-core/src/main/java/org/grobid/core/sax/PDFALTOSaxHandler.java
+++ b/grobid-core/src/main/java/org/grobid/core/sax/PDFALTOSaxHandler.java
@@ -260,6 +260,7 @@ else if (qName.equals("TextBlock")) {
 				//page.addBlock(block);
 			}
 			block = new Block();
+			block.setStartToken(tokenizations.size());
 			//block.setPage(currentPage);
 			blabla = new StringBuffer();
 			int imagePos = images.size()-1;
@@ -393,6 +394,7 @@ public void startElement(String namespaceURI, String localName,
 			block = new Block();
 			blabla = new StringBuffer();
 			nbTokens = 0;
+			block.setStartToken(tokenizations.size());
 			//block.setPage(currentPage);
 			// blabla.append("\n@block\n");
 		} else if (qName.equals("Illustration")) {