Java WordExtractor.getParagraphText方法代码示例

import org.apache.poi.hwpf.extractor.WordExtractor; //导入方法依赖的package包/类
private String readDoc(String path) {
    String content = "";
    try {
        File file = new File(path);
        FileInputStream fis = new FileInputStream(file.getAbsolutePath());

        HWPFDocument doc = new HWPFDocument(fis);

        WordExtractor we = new WordExtractor(doc);
        String[] paragraphs = we.getParagraphText();
        for (String para : paragraphs) {
            content += para.toString();
        }
        fis.close();
        return content;
    } catch (Exception e) {
        e.printStackTrace();
    }
    return content;
}
 

import org.apache.poi.hwpf.extractor.WordExtractor; //导入方法依赖的package包/类
/** {@inheritDoc} */
@Override
public String getUnfilteredTextContent() throws ConQATException {
	InputStream in = new ByteArrayInputStream(getContent());
	String[] paragraphs;
	try {
		WordExtractor extractor = new WordExtractor(in);
		paragraphs = extractor.getParagraphText();
	} catch (IOException e) {
		throw new ConQATException(
				"Had an error while reading word document: "
						+ e.getMessage(), e);
	} finally {
		FileSystemUtils.close(in);
	}

	String text = StringUtils.concat(paragraphs, StringUtils.CR);

	if (wrapAtDot) {
		text = text.replaceAll("[.]", "." + StringUtils.CR);
	}

	if (wrapAtWhitespace) {
		text = text.replaceAll("\\s+", StringUtils.CR);
	}

	// normalize linebreaks according to method's contract
	return StringUtils.replaceLineBreaks(text, "\n");
}
 

import org.apache.poi.hwpf.extractor.WordExtractor; //导入方法依赖的package包/类
public static void writePDFFromDoc(
  final String docFilePath,
  final String pdfFilePath) throws SSErr{
  
  try{
    final Document        document = new Document();
    final POIFSFileSystem fs       = new POIFSFileSystem(openFileForRead(docFilePath));
    final HWPFDocument    word     = new HWPFDocument  (fs);
    final WordExtractor   we       = new WordExtractor (word);
    final OutputStream    out      = openOrCreateFileWithPathForWrite(pdfFilePath);
    final PdfWriter       writer   = PdfWriter.getInstance(document, out);
    final Range           range    = word.getRange();
    
    document.open();
    writer.setPageEmpty(true);
    document.newPage();
    writer.setPageEmpty(true);
    
    String[] paragraphs = we.getParagraphText();
    
    for (int i = 0; i < paragraphs.length; i++) {
      
      org.apache.poi.hwpf.usermodel.Paragraph pr = range.getParagraph(i);
      // CharacterRun run = pr.getCharacterRun(i);
      // run.setBold(true);
      // run.setCapitalized(true);
      // run.setItalic(true);
      paragraphs[i] = paragraphs[i].replaceAll("\\cM?\r?\n", "");
      System.out.println("Length:" + paragraphs[i].length());
      System.out.println("Paragraph" + i + ": " + paragraphs[i].toString());
      
      // add the paragraph to the document
      document.add(new Paragraph(paragraphs[i]));
    }
    
    document.close();
  }catch(Exception error){
    SSServErrReg.regErrThrow(error);
  }
}
 

import org.apache.poi.hwpf.extractor.WordExtractor; //导入方法依赖的package包/类
static int[] wordCountNew(String doc, boolean isDebug) throws Exception {
        long time = System.currentTimeMillis();
        InputStream is = new FileInputStream(new File(doc));
        WordExtractor ex = new WordExtractor(is);
        int cnt = 0;
        StringBuilder builder = new StringBuilder();
        for (String text : ex.getParagraphText()) {
//            text = text.replaceAll("\u0007", "").replaceAll("\f", "")
//                    .replaceAll("\r", "").replaceAll("\n", "")
//                    .replaceAll("\u0015", "");
            if (isDebug) {
                text = trimAllChars(text, new char[] { '\u0007', '\f', '\b', '\u0015' });
            } else {
                text = trimAllChars(text, new char[] { '\u0007', '\f', '\b', '\u0015', '\r', '\n' });
            }

            String prefix = " TOC \\o \\u \u0014";
            if (text.startsWith(prefix))
                text = text.substring(prefix.length());
//            flag = "\u0013 EMBED Visio.Drawing.11 \u0014\u0001";
//            flag = "\u0013 EMBED Word.Document.12 \\s \u0014\u0001";
            int start = text.indexOf("\u0013");
            int end = text.indexOf("\u0014\u0001");
            if (start >= 0 && end > start) {
                text = text.replaceAll("\u0013[^\u0014\u0001]+\u0014\u0001", "");
            }
            text = text.replaceAll("\u0013[^\u0014\u0013]+\u0014", "");

            String flag = "\u0013 HYPERLINK";
            int pos = text.indexOf(flag);
            if (pos >= 0) {
                String[] arr = text.split(" \u0014");
                text = text.substring(0, pos) + arr[1];
            }

            if (text.length() >= 767) {
                // word doc格式时, 如果连续字符数数大于767个(大于等于768), 则该段落的字数不计入
//                if (text.replaceAll(" ", "").length() < text.length() - 767) { //
                text = text.replaceAll(" {767,}", "");
//                }
            }

            if (isDebug)
                builder.append(text);
            cnt += text.length();
        }

        int t = Long.valueOf(System.currentTimeMillis() - time).intValue();

        if (isDebug) {
            System.out.println(builder.toString()); // .replaceAll("\r", "").replaceAll("\n", "")
            System.out.println(cnt);
            System.out.println(t + " ms");
        }
        return new int[] { cnt, t };
    }