fix(core): add blank-text validation in TextDocumentParser (alibaba#2237)

Co-authored-by: shown <yuluo08290126@gmail.com>

Author: 2 people

spring-ai-alibaba-core/src/main/java/com/alibaba/cloud/ai/document/TextDocumentParser.java

@@ -18,6 +18,7 @@
 import org.springframework.ai.document.Document;
 import org.springframework.util.Assert;
 
+import java.io.IOException;
 import java.io.InputStream;
 import java.nio.charset.Charset;
 import java.nio.charset.StandardCharsets;
@@ -44,13 +45,17 @@ public TextDocumentParser(Charset charset) {
 	@Override
 	public List<Document> parse(InputStream inputStream) {
 		try {
-			String text = new String(inputStream.readAllBytes(), charset);
+			// Read all text from the input stream and decode it using the specified
+			// character set.
+			String text = new String(inputStream.readAllBytes(), this.charset);
+			// If the text is completely empty, report an illegal argument exception.
 			if (text.isBlank()) {
-				throw new Exception();
+				throw new IllegalArgumentException("text must not be blank");
 			}
 			return Collections.singletonList(new Document(text));
 		}
-		catch (Exception e) {
+		catch (IOException e) {
+			// Convert any IO exception into a RuntimeException for propagation.
 			throw new RuntimeException(e);
 		}
 	}

spring-ai-alibaba-core/src/test/java/com/alibaba/cloud/ai/document/TextDocumentParserTests.java

@@ -62,24 +62,21 @@ void testParseWithCustomCharset() {
 
 	@Test
 	void testParseEmptyText() {
-		// Test parsing empty text should throw exception
+		// An empty string should trigger an IllegalArgumentException.
 		String text = "";
 		TextDocumentParser parser = new TextDocumentParser();
 
-		RuntimeException exception = assertThrows(RuntimeException.class, () -> parser.parse(toInputStream(text)));
-
-		assertThat(exception).hasRootCauseInstanceOf(Exception.class);
+		assertThrows(IllegalArgumentException.class, () -> parser.parse(toInputStream(text)));
 	}
 
 	@Test
 	void testParseBlankText() {
-		// Test parsing blank text (only whitespace) should throw exception
+		// A blank string containing spaces or inserted characters should also throw an
+		// IllegalArgumentException.
 		String text = "   \n\t   ";
 		TextDocumentParser parser = new TextDocumentParser();
 
-		RuntimeException exception = assertThrows(RuntimeException.class, () -> parser.parse(toInputStream(text)));
-
-		assertThat(exception).hasRootCauseInstanceOf(Exception.class);
+		assertThrows(IllegalArgumentException.class, () -> parser.parse(toInputStream(text)));
 	}
 
 	@Test