From 7b6a12da862373a36c31d27d1470472828853521 Mon Sep 17 00:00:00 2001 From: "Clarissa.Dietrich" Date: Wed, 21 Apr 2021 13:46:54 +0200 Subject: [PATCH] fix: add paragraph to first page --- .../v1/server/segmentation/SectionsBuilderService.java | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/segmentation/SectionsBuilderService.java b/redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/segmentation/SectionsBuilderService.java index 7ee5a4c8..f6b92cda 100644 --- a/redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/segmentation/SectionsBuilderService.java +++ b/redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/segmentation/SectionsBuilderService.java @@ -121,6 +121,14 @@ public class SectionsBuilderService { paragraphMap.computeIfAbsent(1, x -> new TreeSet<>()).add(paragraph); } + // first page is always a paragraph, else we can't process pages 1..N, + // where N is the first found page with a paragraph + if (paragraphMap.get(1) == null) { + Paragraph paragraph = new Paragraph(); + document.getParagraphs().add(paragraph); + paragraphMap.computeIfAbsent(1, x -> new TreeSet<>()).add(paragraph); + } + for (Page page : document.getPages()) { for (PdfImage image : page.getImages()) { SortedSet paragraphsOnPage = paragraphMap.get(page.getPageNumber());