feat(rag): add document parsing structures

src/test/java/com/bruce/common/document/parse/DocumentParserFactoryTests.java

@@ -0,0 +1,50 @@
+package com.bruce.common.document.parse;
+
+import com.bruce.common.document.parse.impl.ExcelDocumentParser;
+import com.bruce.common.document.parse.impl.PdfDocumentParser;
+import com.bruce.common.document.parse.impl.TxtDocumentParser;
+import com.bruce.common.document.parse.impl.WordDocumentParser;
+import org.junit.jupiter.api.Test;
+
+import java.nio.file.Path;
+import java.util.List;
+
+import static org.junit.jupiter.api.Assertions.assertEquals;
+import static org.junit.jupiter.api.Assertions.assertThrows;
+
+class DocumentParserFactoryTests {
+
+    @Test
+    void resolveShouldChooseParserByFileSuffix() {
+        DocumentParserFactory factory = new DocumentParserFactory(List.of(
+                new TxtDocumentParser(),
+                new WordDocumentParser(),
+                new PdfDocumentParser(),
+                new ExcelDocumentParser()
+        ));
+
+        assertEquals(TxtDocumentParser.class, factory.resolve(context("txt")).getClass());
+        assertEquals(WordDocumentParser.class, factory.resolve(context("docx")).getClass());
+        assertEquals(PdfDocumentParser.class, factory.resolve(context("pdf")).getClass());
+        assertEquals(ExcelDocumentParser.class, factory.resolve(context("xlsx")).getClass());
+    }
+
+    @Test
+    void resolveShouldRejectUnsupportedSuffix() {
+        DocumentParserFactory factory = new DocumentParserFactory(List.of(new TxtDocumentParser()));
+
+        DocumentParseException exception = assertThrows(
+                DocumentParseException.class,
+                () -> factory.resolve(context("zip"))
+        );
+
+        assertEquals("不支持的文档类型: zip", exception.getMessage());
+    }
+
+    private DocumentParseContext context(String suffix) {
+        DocumentParseContext context = new DocumentParseContext();
+        context.setSuffix(suffix);
+        context.setFilePath(Path.of("sample." + suffix));
+        return context;
+    }
+}

src/test/java/com/bruce/common/document/parse/TxtDocumentParserTests.java

@@ -0,0 +1,47 @@
+package com.bruce.common.document.parse;
+
+import com.bruce.common.document.parse.impl.TxtDocumentParser;
+import org.junit.jupiter.api.Test;
+import org.junit.jupiter.api.io.TempDir;
+
+import java.nio.charset.StandardCharsets;
+import java.nio.file.Files;
+import java.nio.file.Path;
+
+import static org.junit.jupiter.api.Assertions.assertEquals;
+import static org.junit.jupiter.api.Assertions.assertTrue;
+
+class TxtDocumentParserTests {
+
+    @TempDir
+    private Path tempDir;
+
+    @Test
+    void parseShouldReadPlainTextContent() throws Exception {
+        Path file = tempDir.resolve("people.txt");
+        Files.writeString(file, "张三 是 产品经理\n李四 是 后端工程师", StandardCharsets.UTF_8);
+        DocumentParseContext context = new DocumentParseContext();
+        context.setOriginalName("people.txt");
+        context.setSuffix("txt");
+        context.setContentType("text/plain");
+        context.setFilePath(file);
+
+        DocumentParseResult result = new TxtDocumentParser().parse(context);
+
+        assertEquals("张三 是 产品经理\n李四 是 后端工程师", result.getText());
+        assertEquals(result.getText().length(), result.getTextLength());
+        assertTrue(result.getMetadata().get("contentType").toString().startsWith("text/plain"));
+    }
+
+    @Test
+    void supportsShouldAcceptTextSuffixAndContentType() {
+        TxtDocumentParser parser = new TxtDocumentParser();
+        DocumentParseContext suffixContext = new DocumentParseContext();
+        suffixContext.setSuffix("TXT");
+        DocumentParseContext contentTypeContext = new DocumentParseContext();
+        contentTypeContext.setContentType("text/plain");
+
+        assertTrue(parser.supports(suffixContext));
+        assertTrue(parser.supports(contentTypeContext));
+    }
+}