Example usage for org.apache.poi.xssf.extractor XSSFExcelExtractor setIncludeHeadersFooters

Introduction

In this page you can find the example usage for org.apache.poi.xssf.extractor XSSFExcelExtractor setIncludeHeadersFooters.

Prototype

public void setIncludeHeadersFooters(boolean includeHeadersFooters) 

Source Link

Document

Should headers and footers be included?

Usage

From source file:com.jaeksoft.searchlib.parser.XlsxParser.java

License:Open Source License

@Override
protected void parseContent(StreamLimiter streamLimiter, LanguageEnum lang) throws IOException {

    XSSFWorkbook workbook = new XSSFWorkbook(streamLimiter.getNewInputStream());
    XSSFExcelExtractor excelExtractor = null;
    try {/*from   w ww.  java  2 s.  c  om*/
        excelExtractor = new XSSFExcelExtractor(workbook);
        ParserResultItem result = getNewParserResultItem();

        CoreProperties info = excelExtractor.getCoreProperties();
        if (info != null) {
            result.addField(ParserFieldEnum.title, info.getTitle());
            result.addField(ParserFieldEnum.creator, info.getCreator());
            result.addField(ParserFieldEnum.subject, info.getSubject());
            result.addField(ParserFieldEnum.description, info.getDescription());
            result.addField(ParserFieldEnum.keywords, info.getKeywords());
        }

        excelExtractor.setIncludeCellComments(true);
        excelExtractor.setIncludeHeadersFooters(true);
        excelExtractor.setIncludeSheetNames(true);
        String content = excelExtractor.getText();
        result.addField(ParserFieldEnum.content, StringUtils.replaceConsecutiveSpaces(content, " "));

        result.langDetection(10000, ParserFieldEnum.content);
    } finally {
        IOUtils.close(excelExtractor);
    }

}

---

From source file:com.opensearchserver.extractor.parser.Xlsx.java

License:Apache License

@Override
protected void parseContent(InputStream inputStream, String extension, String mimeType) throws Exception {

    XSSFWorkbook workbook = null;//from  w  ww.j av  a2  s.co  m
    XSSFExcelExtractor excelExtractor = null;
    try {
        workbook = new XSSFWorkbook(inputStream);
        excelExtractor = new XSSFExcelExtractor(workbook);

        CoreProperties info = excelExtractor.getCoreProperties();
        if (info != null) {
            metas.add(TITLE, info.getTitle());
            metas.add(CREATOR, info.getCreator());
            metas.add(CREATION_DATE, info.getCreated());
            metas.add(MODIFICATION_DATE, info.getModified());
            metas.add(SUBJECT, info.getSubject());
            metas.add(DESCRIPTION, info.getDescription());
            metas.add(KEYWORDS, info.getKeywords());
        }

        ParserDocument result = getNewParserDocument();
        excelExtractor.setIncludeCellComments(true);
        excelExtractor.setIncludeHeadersFooters(true);
        excelExtractor.setIncludeSheetNames(true);
        result.add(CONTENT, excelExtractor.getText());
        result.add(LANG_DETECTION, languageDetection(CONTENT, 10000));

    } finally {
        if (excelExtractor != null)
            IOUtils.closeQuietly(excelExtractor);
        if (workbook != null)
            IOUtils.closeQuietly(workbook);
    }

}

---

From source file:com.opensearchserver.textextractor.parser.Xlsx.java

License:Apache License

private void parseContent(XSSFWorkbook workbook) throws Exception {

    XSSFExcelExtractor excelExtractor = null;
    try {/*  w  w  w .  ja  v a  2s. co  m*/
        excelExtractor = new XSSFExcelExtractor(workbook);

        CoreProperties info = excelExtractor.getCoreProperties();
        if (info != null) {
            metas.add(TITLE, info.getTitle());
            metas.add(CREATOR, info.getCreator());
            metas.add(CREATION_DATE, info.getCreated());
            metas.add(MODIFICATION_DATE, info.getModified());
            metas.add(SUBJECT, info.getSubject());
            metas.add(DESCRIPTION, info.getDescription());
            metas.add(KEYWORDS, info.getKeywords());
        }

        ParserDocument result = getNewParserDocument();
        excelExtractor.setIncludeCellComments(true);
        excelExtractor.setIncludeHeadersFooters(true);
        excelExtractor.setIncludeSheetNames(true);
        result.add(CONTENT, excelExtractor.getText());
        result.add(LANG_DETECTION, languageDetection(CONTENT, 10000));

    } finally {
        if (excelExtractor != null)
            IOUtils.closeQuietly(excelExtractor);
    }

}

---