From 80e701a0fd86b43f6c9eb1ed026b73af6475a565 Mon Sep 17 00:00:00 2001 From: Kilian Schuettler Date: Wed, 26 Jun 2024 12:28:53 +0200 Subject: [PATCH] clari-section-chunk: change structure object from paragraph/headline to sections * filter headers/footers --- .../processor/services/mapper/TaasDocumentDataMapper.java | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/services/mapper/TaasDocumentDataMapper.java b/layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/services/mapper/TaasDocumentDataMapper.java index 1978503..a610d4e 100644 --- a/layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/services/mapper/TaasDocumentDataMapper.java +++ b/layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/services/mapper/TaasDocumentDataMapper.java @@ -28,7 +28,11 @@ public class TaasDocumentDataMapper { AtomicInteger structureObjectNumber = new AtomicInteger(); List structureObjects = document.streamAllSubNodes() .filter(node -> !node.getType().equals(NodeType.TABLE_CELL)) - .filter(node -> !node.getType().equals(NodeType.SECTION)) + .filter(node -> !node.getType().equals(NodeType.SUPER_SECTION)) + .filter(node -> !node.getType().equals(NodeType.HEADER)) + .filter(node -> !node.getType().equals(NodeType.FOOTER)) + .filter(node -> !node.getType().equals(NodeType.HEADLINE)) + .filter(node -> !node.getType().equals(NodeType.PARAGRAPH)) .map(node -> { if (node.getType().equals(NodeType.TABLE)) { return TaasDocumentDataMapper.fromTableWithTableData((Table) node, structureObjectNumber.getAndIncrement());