SpringBoot集成Solr全文检索，示例工程源码，ik分词插件

package com.example.solr.util; import cn.hutool.core.util.StrUtil; import lombok.extern.slf4j.Slf4j; import org.apache.pdfbox.pdmodel.PDDocument; import org.apache.pdfbox.text.PDFTextStripper; import org.apache.poi.hwpf.HWPFDocument; import org.apache.poi.hwpf.extractor.WordExtractor; import org.apache.poi.xwpf.usermodel.XWPFDocument; import org.apache.poi.xwpf.usermodel.XWPFParagraph; import org.apache.poi.xwpf.usermodel.XWPFRun; import org.springframework.web.multipart.MultipartFile; import java.io.IOException; import java.io.InputStream; @Slf4j public class FileUtil { /** * 读取文档内容 * 目前仅支持 txt, doc, docx, pdf 格式 * * @param file 文件对象 * @return 文档内容 */ public static String readFileContent(MultipartFile file) { String filename = file.getOriginalFilename(); assert filename != null; String fileType = filename.substring(filename.lastIndexOf(".") + 1).toUpperCase(); switch (fileType) { case "TXT": return readTxtContent(file); case "DOC": case "DOCX": return readWordContent(file); case "PDF": return readPDFContent(file); default: return ""; } } /** * 读取 txt 文档内容 */ private static String readTxtContent(MultipartFile file) { try { return StrUtil.utf8Str(file.getBytes()); } catch (IOException e) { e.printStackTrace(); log.error("读取 txt 文件内容时发生 IO 异常"); return ""; } } /** * 读取 doc 和 docx 文档内容 */ private static String readWordContent(MultipartFile file) { String filename = file.getOriginalFilename(); assert filename != null; String fileType = filename.substring(filename.lastIndexOf(".") + 1); return "doc".equals(fileType) ? readDocContent(file) : readDocxContent(file); } /** * 读取 .doc 格式的 word 文档 * * @param file 文件对象 * @return 文本内容 */ private static String readDocContent(MultipartFile file) { StringBuilder content = new StringBuilder(); try (InputStream inputStream = file.getInputStream(); HWPFDocument document = new HWPFDocument(inputStream)) { WordExtractor extractor = new WordExtractor(document); String[] paragraphs = extractor.getParagraphText(); for (String paragraph : paragraphs) { content.append(paragraph); } } catch (IOException e) { e.printStackTrace(); log.error("读取文件内容时发生 IO 异常"); } return content.toString(); } /** * 读取 .docx 格式的 word 文档 * * @param file 文件对象 * @return 文本内容 */ private static String readDocxContent(MultipartFile file) { StringBuilder content = new StringBuilder(); try (InputStream inputStream = file.getInputStream(); XWPFDocument document = new XWPFDocument(inputStream)) { for (XWPFParagraph paragraph : document.getParagraphs()) { for (XWPFRun run : paragraph.getRuns()) { String runText = run.getText(0); if (runText != null) { content.append(runText); } } } } catch (IOException e) { e.printStackTrace(); log.error("读取文件内容时发生 IO 异常"); } return content.toString(); } /** * 读取 pdf 文档内容 */ private static String readPDFContent(MultipartFile file) { StringBuilder content = new StringBuilder(); try (InputStream inputStream = file.getInputStream(); PDDocument document = PDDocument.load(inputStream)) { // 检查是否是由文档转换出的 pdf 文件 if (!document.isEncrypted() && document.getNumberOfPages() > 0) { PDFTextStripper textStripper = new PDFTextStripper(); content.append(textStripper.getText(document)); } else { log.warn("PDF 已加密或不是由文档转换的 PDF 格式，无法读取内容！"); } } catch (IOException e) { e.printStackTrace(); log.error("读取文件内容时发生 IO 异常"); } return content.toString(); } }