Skip to content

fix: fixed NPE while splitting document chunks #1572

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 2 commits into from
Closed

fix: fixed NPE while splitting document chunks #1572

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6fcafb3
fix: fixed possible NPE while splitting document chunks
Oct 20, 2024
3d30403
fix: fixed possible NPE while splitting document chunks
Oct 22, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 6 additions & 2 deletions spring-ai-core/src/main/java/org/springframework/ai/transformer/splitter/TextSplitter.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -87,8 +87,12 @@ private List<Document> createDocuments(List<String> texts, List<ContentFormatter
for (String chunk : chunks) {
// only primitive values are in here -
Map<String, Object> metadataCopy = metadata.entrySet()
.stream()
.collect(Collectors.toMap(e -> e.getKey(), e -> e.getValue()));
.stream()
.filter(e -> e.getKey() != null && e.getValue() != null)
.collect(Collectors.toMap(
Map.Entry::getKey,
Map.Entry::getValue
));
Document newDoc = new Document(chunk, metadataCopy);

if (this.copyContentFormatter) {
Expand Down
33 changes: 32 additions & 1 deletion ...-ai-core/src/test/java/org/springframework/ai/transformer/splitter/TextSplitterTests.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,7 @@ protected List<String> splitText(String text) {
List<String> chunks = new ArrayList<>();

chunks.add(text.substring(0, chuckSize));
chunks.add(text.substring(chuckSize, text.length()));
chunks.add(text.substring(chuckSize));

return chunks;
}
Expand Down Expand Up @@ -213,4 +213,35 @@ public void pageWithChunkSplit() {
() -> assertThat(splitedDocument.get(3).getMetadata().get("page_number")).isEqualTo(3));
}

@Test
public void testSplitTextWithNullMetadata() {

var contentFormatter = DefaultContentFormatter.defaultConfig();

var doc = new Document("In the end, writing arises when man realizes that memory is not enough.");

doc.getMetadata().put("key1", "value1");
doc.getMetadata().put("key2", null);

doc.setContentFormatter(contentFormatter);

List<Document> chunks = testTextSplitter.apply(List.of(doc));

assertThat(testTextSplitter.isCopyContentFormatter()).isTrue();

assertThat(chunks).hasSize(2);

// Doc chunks:
assertThat(chunks.get(0).getContent()).isEqualTo("In the end, writing arises when man");
assertThat(chunks.get(1).getContent()).isEqualTo(" realizes that memory is not enough.");

// Verify that the same, merged metadata is copied to all chunks.
assertThat(chunks.get(0).getMetadata()).isEqualTo(chunks.get(1).getMetadata());
assertThat(chunks.get(1).getMetadata()).containsKeys("key1");

// Verify that the content formatters are copied from the parents to the chunks.
assertThat(chunks.get(0).getContentFormatter()).isSameAs(contentFormatter);
assertThat(chunks.get(1).getContentFormatter()).isSameAs(contentFormatter);
}

}
Loading