Skip to content

Fix escaping issue in filterExpression for RedisVectorStore file name #3202

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.

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

Open
wants to merge 4 commits into
base: main
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
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
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,7 @@
package org.springframework.ai.vectorstore;

import java.util.Objects;
import java.util.Map;

import org.springframework.ai.document.Document;
import org.springframework.ai.vectorstore.filter.Filter;
Expand Down Expand Up @@ -59,6 +60,8 @@ public class SearchRequest {
@Nullable
private Filter.Expression filterExpression;

private static final Map<Character, String> ESCAPE_TEXT = Map.of('\\', "\\\\", '.', "\\.");

/**
* Copy an existing {@link SearchRequest.Builder} instance.
* @param originalSearchRequest {@link SearchRequest} instance to copy.
Expand Down Expand Up @@ -191,7 +194,6 @@ public Builder similarityThresholdAll() {
/**
* Retrieves documents by query embedding similarity and matching the filters.
* Value of 'null' means that no metadata filters will be applied to the search.
*
* For example if the {@link Document#getMetadata()} schema is:
*
* <pre>{@code
Expand Down Expand Up @@ -283,10 +285,32 @@ public Builder filterExpression(@Nullable Filter.Expression expression) {
*/
public Builder filterExpression(@Nullable String textExpression) {
this.searchRequest.filterExpression = (textExpression != null)
? new FilterExpressionTextParser().parse(textExpression) : null;
? new FilterExpressionTextParser().parse(escapeTextExpression(textExpression)) : null;
return this;
}

private String escapeTextExpression(String expression) {
StringBuilder sb = new StringBuilder(expression.length() + 8);
boolean inQuote = false;

for (int i = 0; i < expression.length(); i++) {
char ch = expression.charAt(i);

if (ch == '\'') {
inQuote = !inQuote;
sb.append(ch);
}
else if (inQuote) {
sb.append(ESCAPE_TEXT.getOrDefault(ch, String.valueOf(ch)));
}
else {
sb.append(ch);
}
}

return sb.toString();
}

public SearchRequest build() {
return this.searchRequest;
}
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -138,6 +138,61 @@ public void filterExpression() {

}

@Test
public void filterExpressionWithDotAndBackslashIsEscaped() {
var request = SearchRequest.builder()
.query("Test")
.filterExpression("file_name == 'clean.code.pdf' && path == 'C:\\docs\\files'")
.build();

var expression = request.getFilterExpression();

assertThat(expression.toString()).contains("clean\\.code\\.pdf");
assertThat(expression.toString()).contains("C:\\\\docs\\\\files");
}

@Test
public void filterExpressionWithMultipleLiteralsIsEscapedIndependently() {
var request = SearchRequest.builder()
.query("Test")
.filterExpression("file_name == 'a.b.c' && author == 'me.you'")
.build();

var expression = request.getFilterExpression();

assertThat(expression.toString()).contains("a\\.b\\.c");
assertThat(expression.toString()).contains("me\\.you");
}

@Test
public void filterExpressionWithVariousFileExtensionsIsEscaped() {
var request = SearchRequest.builder()
.query("Test")
.filterExpression(
"file_name == 'summary.epub' || file_name == 'lecture_notes.md' || file_name == 'slides.pptx'")
.build();

String expression = request.getFilterExpression().toString();

assertThat(expression).contains("summary\\.epub");
assertThat(expression).contains("lecture_notes\\.md");
assertThat(expression).contains("slides\\.pptx");
}

@Test
public void filterExpressionWithInListIsEscaped() {
var request = SearchRequest.builder()
.query("Test")
.filterExpression("file_name IN ['a.pdf', 'b.txt', 'final.report.docx']")
.build();

String expression = request.getFilterExpression().toString();

assertThat(expression).contains("a\\.pdf");
assertThat(expression).contains("b\\.txt");
assertThat(expression).contains("final\\.report\\.docx");
}

private void checkDefaults(SearchRequest request) {
assertThat(request.getFilterExpression()).isNull();
assertThat(request.getSimilarityThreshold()).isEqualTo(SearchRequest.SIMILARITY_THRESHOLD_ACCEPT_ALL);
Expand Down