From 207d9dec975a5d53c39920d27eb3748d5d1fe1fc Mon Sep 17 00:00:00 2001 From: yhampe Date: Thu, 16 Nov 2023 12:40:49 +0100 Subject: [PATCH] * added back in if statement * removed not needed commentar --- .../layoutparser/processor/LayoutParsingPipeline.java | 4 ++-- .../processor/services/parsing/PDFLinesTextStripper.java | 5 ----- 2 files changed, 2 insertions(+), 7 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 d628681..a02f627 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 @@ -244,9 +244,9 @@ public class LayoutParsingPipeline { private void increaseDocumentStatistics(ClassificationPage classificationPage, ClassificationDocument document) { - // if (!classificationPage.isLandscape()) { + if (!classificationPage.isLandscape()) { document.getFontSizeCounter().addAll(classificationPage.getFontSizeCounter().getCountPerValue()); -// } + } document.getFontCounter().addAll(classificationPage.getFontCounter().getCountPerValue()); document.getTextHeightCounter().addAll(classificationPage.getTextHeightCounter().getCountPerValue()); document.getFontStyleCounter().addAll(classificationPage.getFontStyleCounter().getCountPerValue()); diff --git a/layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/services/parsing/PDFLinesTextStripper.java b/layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/services/parsing/PDFLinesTextStripper.java index f7b523f..09a8eb2 100644 --- a/layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/services/parsing/PDFLinesTextStripper.java +++ b/layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/services/parsing/PDFLinesTextStripper.java @@ -329,11 +329,6 @@ public class PDFLinesTextStripper extends PDFTextStripper { .getXDirAdj() - (previous.getXDirAdj() + previous.getWidthDirAdj()) < maximumGapSize; } - // !(sublist.isEmpty() || sublist.size() == 1 && (sublist.get(0).getUnicode().equals(" ") || sublist.get(0).getUnicode().equals("\u00A0") || sublist.get(0) - // .getUnicode() - // .equals("\t"))) - - @Override public String getText(PDDocument doc) throws IOException {