From d4822e1b2c6cf98844cca0b1963ad86151d3be05 Mon Sep 17 00:00:00 2001 From: lopez Date: Sun, 18 Feb 2024 17:15:14 +0100 Subject: [PATCH] fix error case with empty affiliation when creating pre-annotated training --- .../java/org/grobid/core/engines/FullTextParser.java | 11 +++++++---- 1 file changed, 7 insertions(+), 4 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 fec619919f..28eda7e693 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 @@ -1370,11 +1370,14 @@ public Document createTraining(File inputFile, List> tokenizationsAffiliation = resHeader.getAffiliationAddresslabeledTokens(); //List tokenizationsAffiliation = resHeader.getLayoutTokens(TaggingLabels.HEADER_AFFILIATION); List tokenizationAffiliation = new ArrayList<>(); - for (List tokenization : tokenizationsAffiliation) { - tokenizationAffiliation.addAll(tokenization); + StringBuilder bufferAffiliation = null; + if (tokenizationsAffiliation != null && tokenizationsAffiliation.size()>0) { + for (List tokenization : tokenizationsAffiliation) { + tokenizationAffiliation.addAll(tokenization); + } + bufferAffiliation = + parsers.getAffiliationAddressParser().trainingExtraction(tokenizationAffiliation); } - StringBuilder bufferAffiliation = - parsers.getAffiliationAddressParser().trainingExtraction(tokenizationAffiliation); // buffer for the date block StringBuilder bufferDate = null;