From ca2f3512d206e118f7832d7887bb519a59a275bb Mon Sep 17 00:00:00 2001 From: Kilian Schuettler Date: Mon, 4 Nov 2024 12:16:44 +0100 Subject: [PATCH] RED-10249: regex found incorrectly due to wrong text sorting --- .../processor/LayoutParsingPipeline.java | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) diff --git a/layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/LayoutParsingPipeline.java b/layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/LayoutParsingPipeline.java index 5b1b71b..eb93d8e 100644 --- a/layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/LayoutParsingPipeline.java +++ b/layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/LayoutParsingPipeline.java @@ -243,10 +243,7 @@ public class LayoutParsingPipeline { List classificationPages = new ArrayList<>(); - // parsing the structure elements could be useful as well - if (layoutParsingType != LayoutParsingType.REDACT_MANAGER_OLD) { - classificationDocument.setOutlineObjectTree(outlineExtractorService.getOutlineObjectTree(originDocument)); - } + classificationDocument.setOutlineObjectTree(outlineExtractorService.getOutlineObjectTree(originDocument)); long pageCount = originDocument.getNumberOfPages(); @@ -363,11 +360,11 @@ public class LayoutParsingPipeline { private static void updateClassificationPage(PDPage pdPage, - PDRectangle pdr, - ClassificationPage classificationPage, - CleanRulings cleanRulings, - int pageNumber, - PageInformation pageInformation) { + PDRectangle pdr, + ClassificationPage classificationPage, + CleanRulings cleanRulings, + int pageNumber, + PageInformation pageInformation) { int rotation = pdPage.getRotation(); boolean isLandscape = pdr.getWidth() > pdr.getHeight() && (rotation == 0 || rotation == 180) || pdr.getHeight() > pdr.getWidth() && (rotation == 90 || rotation == 270);