feat: add JSoup HTML document reader

This commit introduces the `JsoupDocumentReader` and `JsoupDocumentReaderConfig` classes, which provide functionality to read and parse HTML documents using the JSoup library. The reader supports: - Extracting text from specific HTML elements using CSS selectors. - Extracting all text from the body of the document. - Grouping text by element. - Extracting metadata, including the document title, meta tags, and link URLs. - Reading from various resource types (files, URLs, byte arrays). - Configurable character encoding, selector, separator, and metadata extraction. This new reader enhances Spring AI's ability to process web content and other HTML-based data sources.
spring-projects · Feb 14, 2025 · 2879e6c · 2879e6c
1 parent c623264
commit 2879e6c
Show file tree

Hide file tree

Showing 11 changed files with 759 additions and 0 deletions.
diff --git a/document-readers/jsoup-reader/ README.md b/document-readers/jsoup-reader/ README.md
@@ -0,0 +1,30 @@
+# Spring AI JSoup Document Reader
+
+This module provides an HTML document reader for the Spring AI project. It leverages the [JSoup](https://jsoup.org/) library to parse HTML content and extract text and metadata, making it suitable for use in AI applications.
+
+## Features
+
+*   **Flexible Text Extraction:**
+    *   Extract all text from the `<body>` of an HTML document.
+    *   Extract text from specific elements using CSS selectors.
+    *   Group text by element, creating a separate document for each selected element.
+    *   Combine text from multiple selected elements using a configurable separator.
+*   **Metadata Extraction:**
+    *   Extract the document title.
+    *   Extract content from `<meta>` tags (e.g., description, keywords).  You can specify which meta tags to extract.
+    *   Extract a list of all absolute URLs of links (`<a href="...">`) within the document.
+*   **Configurable:**
+    *   Specify the character encoding (defaults to UTF-8).
+    *   Customize the CSS selector for element selection.
+    *   Configure the separator string for joining text from multiple elements.
+    *   Choose whether to extract all text or use element-based extraction.
+    *   Enable/disable link URL extraction.
+    * Add additional metadata using configuration.
+*   **Resource-Based:** Works with Spring's `Resource` abstraction, allowing you to read HTML from files, classpath resources, URLs, and even in-memory byte arrays.
+
+---
+
+#### How to Build:
+```bash
+./mvnw -pl document-readers/jsoup-reader clean install 
+```
diff --git a/document-readers/jsoup-reader/pom.xml b/document-readers/jsoup-reader/pom.xml
@@ -0,0 +1,63 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!--
+  ~ Copyright 2025-2025 the original author or authors.
+  ~
+  ~ 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
+  ~
+  ~      https://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.
+  -->
+
+<project xmlns="http://maven.apache.org/POM/4.0.0"
+		 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+		 xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
+	<modelVersion>4.0.0</modelVersion>
+	<parent>
+		<groupId>org.springframework.ai</groupId>
+		<artifactId>spring-ai</artifactId>
+		<version>1.0.0-SNAPSHOT</version>
+		<relativePath>../../pom.xml</relativePath>
+	</parent>
+
+	<artifactId>spring-ai-jsoup-document-reader</artifactId>
+	<packaging>jar</packaging>
+	<name>Spring AI Document Reader - HTML</name>
+	<description>Spring AI HTML document reader</description>
+	<url>https://github.com/spring-projects/spring-ai</url>
+
+	<scm>
+		<url>https://github.com/spring-projects/spring-ai</url>
+		<connection>git://github.com/spring-projects/spring-ai.git</connection>
+		<developerConnection>[email protected]:spring-projects/spring-ai.git</developerConnection>
+	</scm>
+
+	<dependencies>
+		<dependency>
+			<groupId>org.springframework.ai</groupId>
+			<artifactId>spring-ai-core</artifactId>
+			<version>${project.parent.version}</version>
+		</dependency>
+
+		<dependency>
+			<groupId>org.jsoup</groupId>
+			<artifactId>jsoup</artifactId>
+			<version>1.18.3</version>
+		</dependency>
+
+		<!-- TESTING -->
+		<dependency>
+			<groupId>org.springframework.boot</groupId>
+			<artifactId>spring-boot-starter-test</artifactId>
+			<scope>test</scope>
+		</dependency>
+
+	</dependencies>
+
+</project>
diff --git a/...s/jsoup-reader/src/main/java/org/springframework/ai/reader/jsoup/JsoupDocumentReader.java b/...s/jsoup-reader/src/main/java/org/springframework/ai/reader/jsoup/JsoupDocumentReader.java
@@ -0,0 +1,135 @@
+/*
+ * Copyright 2025-2025 the original author or authors.
+ *
+ * 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
+ *
+ *      https://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 org.springframework.ai.reader.jsoup;
+
+import java.io.IOException;
+import java.io.InputStream;
+import java.util.ArrayList;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
+import java.util.stream.Collectors;
+
+import org.jsoup.Jsoup;
+import org.jsoup.nodes.Element;
+import org.jsoup.select.Elements;
+
+import org.springframework.ai.document.Document;
+import org.springframework.ai.document.DocumentReader;
+import org.springframework.ai.reader.jsoup.config.JsoupDocumentReaderConfig;
+import org.springframework.core.io.DefaultResourceLoader;
+import org.springframework.core.io.Resource;
+
+/**
+ * Reads HTML documents and extracts text content using JSoup.
+ *
+ * This reader provides options for selecting specific HTML elements to extract, handling
+ * links, and extracting metadata. It leverages the JSoup library for parsing HTML.
+ *
+ * @see <a href="https://jsoup.org/">JSoup Website</a>
+ * @author Alexandros Pappas
+ */
+public class JsoupDocumentReader implements DocumentReader {
+
+	private final Resource htmlResource;
+
+	private final JsoupDocumentReaderConfig config;
+
+	public JsoupDocumentReader(String htmlResource) {
+		this(new DefaultResourceLoader().getResource(htmlResource));
+	}
+
+	public JsoupDocumentReader(Resource htmlResource) {
+		this(htmlResource, JsoupDocumentReaderConfig.defaultConfig());
+	}
+
+	public JsoupDocumentReader(String htmlResource, JsoupDocumentReaderConfig config) {
+		this(new DefaultResourceLoader().getResource(htmlResource), config);
+	}
+
+	public JsoupDocumentReader(Resource htmlResource, JsoupDocumentReaderConfig config) {
+		this.htmlResource = htmlResource;
+		this.config = config;
+	}
+
+	@Override
+	public List<Document> get() {
+		try (InputStream inputStream = htmlResource.getInputStream()) {
+			org.jsoup.nodes.Document doc = Jsoup.parse(inputStream, this.config.charset, "");
+
+			List<Document> documents = new ArrayList<>();
+
+			if (this.config.allElements) {
+				// Extract text from all elements and create a single document
+				String allText = doc.body().text(); // .body to exclude head
+				Document document = new Document(allText);
+				addMetadata(doc, document);
+				documents.add(document);
+			}
+			else if (this.config.groupByElement) {
+				// Extract text on a per-element base using the defined selector.
+				Elements selectedElements = doc.select(this.config.selector);
+				for (Element element : selectedElements) {
+					String elementText = element.text();
+					Document document = new Document(elementText);
+					addMetadata(doc, document);
+					// Do not add metadata from element to avoid duplication.
+					documents.add(document);
+				}
+			}
+			else {
+				// Extract text from specific elements based on the selector
+				Elements elements = doc.select(this.config.selector);
+				String text = elements.stream().map(Element::text).collect(Collectors.joining(this.config.separator));
+				Document document = new Document(text);
+				addMetadata(doc, document);
+				documents.add(document);
+			}
+
+			return documents;
+
+		}
+		catch (IOException e) {
+			throw new RuntimeException("Failed to read HTML resource: " + htmlResource, e);
+		}
+	}
+
+	private void addMetadata(org.jsoup.nodes.Document jsoupDoc, Document springDoc) {
+		Map<String, Object> metadata = new HashMap<>();
+		metadata.put("title", jsoupDoc.title());
+
+		for (String metaTag : this.config.metadataTags) {
+			String value = jsoupDoc.select("meta[name=" + metaTag + "]").attr("content");
+			if (!value.isEmpty()) {
+				metadata.put(metaTag, value);
+			}
+		}
+
+		if (this.config.includeLinkUrls) {
+			Elements links = jsoupDoc.select("a[href]");
+			List<String> linkUrls = links.stream().map(link -> link.attr("abs:href")).toList();
+			metadata.put("linkUrls", linkUrls);
+		}
+
+		// Use putAll to add all entries from additionalMetadata
+		metadata.putAll(this.config.additionalMetadata);
+
+		// Add all collected metadata to the Spring Document
+		springDoc.getMetadata().putAll(metadata);
+	}
+
+}