From 7b070007da3b4a4b666084c8afb99eac41286281 Mon Sep 17 00:00:00 2001
From: Luca Foppiano <luca@foppiano.org>
Date: Mon, 12 Aug 2024 10:38:41 +0200
Subject: [PATCH] avoid null pointer exceptions during training data generation
 with certain nasty documents

---
 .../grobid/core/engines/FullTextParser.java   | 22 ++++++++++---------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/grobid-core/src/main/java/org/grobid/core/engines/FullTextParser.java b/grobid-core/src/main/java/org/grobid/core/engines/FullTextParser.java
index 953d92f8b1..d2b1bf8661 100755
--- a/grobid-core/src/main/java/org/grobid/core/engines/FullTextParser.java
+++ b/grobid-core/src/main/java/org/grobid/core/engines/FullTextParser.java
@@ -1234,17 +1234,19 @@ public Document createTraining(File inputFile,
                                      "\t\t\t\t<biblStruct>\n\t\t\t\t\t<analytic>\n\n");
 
                     for (LabeledReferenceResult ref : references) {
-                        if ( (ref.getReferenceText() != null) && (ref.getReferenceText().trim().length() > 0) ) {
+                        if ( StringUtils.isNotBlank(ref.getReferenceText()) ) {
                             BiblioItem bib = parsers.getCitationParser().processingString(ref.getReferenceText(), 0);
-                            String authorSequence = bib.getAuthors();
-                            if ((authorSequence != null) && (authorSequence.trim().length() > 0) ) {
-                                /*List<String> inputs = new ArrayList<String>();
-                                inputs.add(authorSequence);*/
-                                StringBuilder bufferName = parsers.getAuthorParser().trainingExtraction(authorSequence, false);
-                                if ( (bufferName != null) && (bufferName.length()>0) ) {
-                                    writerName.write("\n\t\t\t\t\t\t<author>");
-                                    writerName.write(bufferName.toString());
-                                    writerName.write("</author>\n");
+                            if (bib != null) {
+                                String authorSequence = bib.getAuthors();
+                                if (StringUtils.isNotBlank(authorSequence)) {
+                                    /*List<String> inputs = new ArrayList<String>();
+                                    inputs.add(authorSequence);*/
+                                    StringBuilder bufferName = parsers.getAuthorParser().trainingExtraction(authorSequence, false);
+                                    if ((bufferName != null) && (bufferName.length() > 0)) {
+                                        writerName.write("\n\t\t\t\t\t\t<author>");
+                                        writerName.write(bufferName.toString());
+                                        writerName.write("</author>\n");
+                                    }
                                 }
                             }
                         }