Skip to content

Commit 0c75e48

Browse files
justperson94bundolee
authored andcommitted
fix: add safeGetTextColor guard for prevNode/nextNode in processHeadings
1 parent b6d1860 commit 0c75e48

1 file changed

Lines changed: 6 additions & 0 deletions

File tree

java/opendataloader-pdf-core/src/main/java/org/opendataloader/pdf/processors/HeadingProcessor.java

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -90,6 +90,12 @@ public static void processHeadings(List<IObject> contents, boolean isTableCell)
9090
}
9191
SemanticTextNode prevNode = index != 0 ? textNodes.get(index - 1) : null;
9292
SemanticTextNode nextNode = index + 1 < textNodesCount ? textNodes.get(index + 1) : null;
93+
if (prevNode != null && safeGetTextColor(prevNode) == null) {
94+
prevNode = null;
95+
}
96+
if (nextNode != null && safeGetTextColor(nextNode) == null) {
97+
nextNode = null;
98+
}
9399
double probability = NodeUtils.headingProbability(textNode, prevNode, nextNode, textNode);
94100

95101
probability += textNodeStatistics.fontSizeRarityBoost(textNode);

0 commit comments

Comments
 (0)