在reactjs中解析Pdf中的文本

import React, { useState, useRef } from "react";
import * as pdfjs from "pdfjs-dist";
import { WorkerMessageHandler } from "pdfjs-dist/build/pdf.worker.min.mjs";

function PDFParser() {
  const [extractedText, setExtractedText] = useState("");
  const [pdfSrc, setPdfSrc] = useState(null);
  const [selectedFileName, setSelectedFileName] = useState("");
  const fileInputRef = useRef(null);

  const handleFileChange = async (event) => {
    const selectedFile = event.target.files[0];
  
    if (!selectedFile) {
      return;
    }
  
    const fileReader = new FileReader();
    fileReader.onload = async () => {
      const arrayBuffer = fileReader.result;
  
      try {
        pdfjs.GlobalWorkerOptions.workerSrc = "pdf.worker.min.mjs";
        const pdf = await pdfjs.getDocument({ data: arrayBuffer }).promise;
  
        const numPages = pdf.numPages;
        let extractedText = "";
  
        for (let i = 1; i <= numPages; i++) {
          const page = await pdf.getPage(i);
          const pageText = await page.getTextContent();
          
          // Map over text items and join them with a newline character
          const pageLines = pageText.items.map((item) => item.str).join("\n");
  
          // Append the lines from this page to the extracted text
          if (extractedText !== "") {
            extractedText += "\n";
          }
          extractedText += pageLines;
        }

        // Segment the extracted text into sections
        const sections = segmentText(extractedText);

        // Update state with segmented text
        setExtractedText(sections);
        setPdfSrc(URL.createObjectURL(selectedFile));
        setSelectedFileName(selectedFile.name);
      } catch (error) {
        console.error("Error parsing PDF:", error);
      }
    };
  
    setExtractedText("");
    fileReader.readAsArrayBuffer(selectedFile);
  };

  // Function to segment text into sections
  const segmentText = (text) => {
    // Split text into lines
    const lines = text.split("\n");

    // Define section keywords
    const sectionKeywords = ["education", "experience", "skills", "summary"];

    // Initialize sections object
    const sections = {};

    // Initialize current section
    let currentSection = "";

    // Iterate over lines to identify section boundaries
    lines.forEach((line) => {
      const lowerCaseLine = line.toLowerCase();

      // Check if line contains a section keyword
      const matchedKeyword = sectionKeywords.find(keyword => lowerCaseLine.includes(keyword));
      if (matchedKeyword) {
        currentSection = matchedKeyword;
        if (!sections[currentSection]) {
          sections[currentSection] = [];
        }
      } else {
        // Add line to current section
        if (currentSection !== "") {
          sections[currentSection].push(line);
        }
      }
    });

    return sections;
  };

  const openFileDialog = () => {
    if (fileInputRef.current) {
      fileInputRef.current.click();
    }
  };

  return (
    <div>
      <input
        type="file"
        onChange={handleFileChange}
        accept=".pdf"
        ref={fileInputRef}
        style={{ display: "none" }}
      />
      <button className="UploadButton" onClick={openFileDialog}>
        Upload PDF
      </button>
      <div className="ScrollableContainer">
        {Object.keys(extractedText).map((section, index) => (
          <div key={index}>
            <h2>{section.toUpperCase()}</h2>
            <ul>
              {extractedText[section].map((item, idx) => (
                <li key={idx}>{item}</li>
              ))}
            </ul>
          </div>
        ))}
      </div>
    </div>
  );
}

export default PDFParser;