From 3a41b3a19802b835b54162185752f65f5694a7a2 Mon Sep 17 00:00:00 2001
From: 0007 <0007@qq.com>
Date: Wed, 27 Aug 2025 19:59:16 +0800
Subject: [PATCH] Add File

---
 .../document/parser/PdfBoxDocumentParser.java | 73 +++++++++++++++++++
 1 file changed, 73 insertions(+)
 create mode 100644 agents-flex-document-parser/agents-flex-document-parser-pdfbox/src/main/java/com/agentsflex/document/parser/PdfBoxDocumentParser.java

diff --git a/agents-flex-document-parser/agents-flex-document-parser-pdfbox/src/main/java/com/agentsflex/document/parser/PdfBoxDocumentParser.java b/agents-flex-document-parser/agents-flex-document-parser-pdfbox/src/main/java/com/agentsflex/document/parser/PdfBoxDocumentParser.java
new file mode 100644
index 0000000..ab008d4
--- /dev/null
+++ b/agents-flex-document-parser/agents-flex-document-parser-pdfbox/src/main/java/com/agentsflex/document/parser/PdfBoxDocumentParser.java
@@ -0,0 +1,73 @@
+/*
+ *  Copyright (c) 2023-2025, Agents-Flex (fuhai999@gmail.com).
+ *  <p>
+ *  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
+ *  <p>
+ *  http://www.apache.org/licenses/LICENSE-2.0
+ *  <p>
+ *  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.document.parser;
+
+import com.agentsflex.core.document.Document;
+import com.agentsflex.core.document.DocumentParser;
+import org.apache.pdfbox.pdmodel.PDDocument;
+import org.apache.pdfbox.text.PDFTextStripper;
+
+import java.io.IOException;
+import java.io.InputStream;
+import java.util.ArrayList;
+import java.util.List;
+
+public class PdfBoxDocumentParser implements DocumentParser {
+
+    /**
+     * 返回整个文档的内容
+     */
+    @Override
+    public Document parse(InputStream stream) {
+        try (PDDocument pdfDocument = PDDocument.load(stream)) {
+            PDFTextStripper stripper = new PDFTextStripper();
+            String text = stripper.getText(pdfDocument);
+            return new Document(text);
+        } catch (IOException e) {
+            throw new RuntimeException(e);
+        }
+    }
+
+    /**
+     * 返回每页文档的内容
+     */
+    public List<Document> parseWithPage(InputStream inputStream) {
+        try (PDDocument pdfDocument = PDDocument.load(inputStream)) {
+            return getDocuments(pdfDocument);
+        } catch (IOException e) {
+            throw new RuntimeException(e);
+        }
+    }
+
+    private List<Document> getDocuments(PDDocument pdDocument) throws IOException {
+        List<Document> documents = new ArrayList<>();
+        int pageCount = pdDocument.getNumberOfPages();
+        for (int pageNumber = 1; pageNumber <= pageCount; pageNumber++) {
+            PDFTextStripper stripper = new PDFTextStripper();
+            stripper.setStartPage(pageNumber);
+            stripper.setEndPage(pageNumber);
+            String content = stripper.getText(pdDocument);
+
+            Document document = new Document();
+            document.setContent(content);
+
+            document.addMetadata("pageNumber", pageNumber);
+            documents.add(document);
+        }
+        return documents;
+    }
+
+}