From 4f45921567ea7b5065804d3ed779d6d2162197d1 Mon Sep 17 00:00:00 2001
From: 0007 <0007@qq.com>
Date: Wed, 27 Aug 2025 19:58:42 +0800
Subject: [PATCH] Add File
---
.../splitter/RegexDocumentSplitter.java | 56 +++++++++++++++++++
1 file changed, 56 insertions(+)
create mode 100644 agents-flex-core/src/main/java/com/agentsflex/core/document/splitter/RegexDocumentSplitter.java
diff --git a/agents-flex-core/src/main/java/com/agentsflex/core/document/splitter/RegexDocumentSplitter.java b/agents-flex-core/src/main/java/com/agentsflex/core/document/splitter/RegexDocumentSplitter.java
new file mode 100644
index 0000000..eddca2b
--- /dev/null
+++ b/agents-flex-core/src/main/java/com/agentsflex/core/document/splitter/RegexDocumentSplitter.java
@@ -0,0 +1,56 @@
+/*
+ * Copyright (c) 2023-2025, Agents-Flex (fuhai999@gmail.com).
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package com.agentsflex.core.document.splitter;
+
+import com.agentsflex.core.document.DocumentSplitter;
+import com.agentsflex.core.document.Document;
+import com.agentsflex.core.document.id.DocumentIdGenerator;
+import com.agentsflex.core.util.StringUtil;
+
+import java.util.ArrayList;
+import java.util.Collections;
+import java.util.List;
+
+public class RegexDocumentSplitter implements DocumentSplitter {
+
+ private final String regex;
+
+ public RegexDocumentSplitter(String regex) {
+ this.regex = regex;
+ }
+
+ @Override
+ public List split(Document document, DocumentIdGenerator idGenerator) {
+ if (document == null || StringUtil.noText(document.getContent())) {
+ return Collections.emptyList();
+ }
+ String[] textArray = document.getContent().split(regex);
+ List chunks = new ArrayList<>(textArray.length);
+ for (String textString : textArray) {
+ if (StringUtil.noText(textString)) {
+ continue;
+ }
+ Document newDocument = new Document();
+ newDocument.addMetadata(document.getMetadataMap());
+ newDocument.setContent(textString);
+
+ //we should invoke setId after setContent
+ newDocument.setId(idGenerator == null ? null : idGenerator.generateId(newDocument));
+ chunks.add(newDocument);
+ }
+ return chunks;
+ }
+}