Java ExtractorFactory类代码示例

import org.apache.poi.extractor.ExtractorFactory; //导入依赖的package包/类
@Override
protected String readContent(final VFSLeaf leaf) throws IOException, DocumentException {
    BufferedInputStream bis = null;
    final StringBuilder buffy = new StringBuilder();
    try {
        bis = new BufferedInputStream(leaf.getInputStream());
        final POIXMLTextExtractor extractor = (POIXMLTextExtractor) ExtractorFactory.createExtractor(bis);
        final POIXMLDocument document = extractor.getDocument();

        if (document instanceof XWPFDocument) {
            final XWPFDocument xDocument = (XWPFDocument) document;
            final XWPFHeaderFooterPolicy hfPolicy = xDocument.getHeaderFooterPolicy();
            extractHeaders(buffy, hfPolicy);
            extractContent(buffy, xDocument);
            extractFooters(buffy, hfPolicy);
        }

        return buffy.toString();
    } catch (final Exception e) {
        throw new DocumentException(e.getMessage());
    } finally {
        if (bis != null) {
            bis.close();
        }
    }
}
 

import org.apache.poi.extractor.ExtractorFactory; //导入依赖的package包/类
@Override
protected String readContent(final VFSLeaf leaf) throws IOException, DocumentException {
    BufferedInputStream bis = null;
    final StringBuilder buffy = new StringBuilder();
    try {
        bis = new BufferedInputStream(leaf.getInputStream());
        final POIXMLTextExtractor extractor = (POIXMLTextExtractor) ExtractorFactory.createExtractor(bis);
        final POIXMLDocument document = extractor.getDocument();

        if (document instanceof XSSFWorkbook) {
            final XSSFWorkbook xDocument = (XSSFWorkbook) document;
            extractContent(buffy, xDocument);
        }

        return buffy.toString();
    } catch (final Exception e) {
        throw new DocumentException(e.getMessage());
    } finally {
        if (bis != null) {
            bis.close();
        }
    }
}
 

import org.apache.poi.extractor.ExtractorFactory; //导入依赖的package包/类
@Override
public String readContent(final VFSLeaf leaf) throws IOException, DocumentException {
    BufferedInputStream bis = null;
    final StringBuilder buffy = new StringBuilder();
    try {
        bis = new BufferedInputStream(leaf.getInputStream());
        final POIXMLTextExtractor extractor = (POIXMLTextExtractor) ExtractorFactory.createExtractor(bis);
        final POIXMLDocument document = extractor.getDocument();

        if (document instanceof XSLFSlideShow) {
            final XSLFSlideShow slideShow = (XSLFSlideShow) document;
            final XMLSlideShow xmlSlideShow = new XMLSlideShow(slideShow);
            extractContent(buffy, xmlSlideShow);
        }

        return buffy.toString();
    } catch (final Exception e) {
        throw new DocumentException(e.getMessage());
    } finally {
        if (bis != null) {
            bis.close();
        }
    }
}
 

import org.apache.poi.extractor.ExtractorFactory; //导入依赖的package包/类
FileDocumentFactory(final SearchModule searchModule, MimeTypeProvider mimeTypeProvider) {
    fileBlackList = searchModule.getFileBlackList();
    pptFileEnabled = searchModule.isPptFileEnabled();
    if (!pptFileEnabled) {
        log.info("PPT files are disabled in indexer.");
    }
    excelFileEnabled = searchModule.isExcelFileEnabled();
    if (!excelFileEnabled) {
        log.info("Excel files are disabled in indexer.");
    }
    checkFileSizeSuffixes = searchModule.getFileSizeSuffixes();
    maxFileSize = searchModule.getMaxFileSize();

    FileDocumentFactory.mimeTypeProvider = mimeTypeProvider;
    // there are two ways of how text extraction for MS Open XML documents (Office >= 2003) is handled technically:
    // model based or event based (similar to DOM/SAX parsing of XML)
    // for complex Excel files model based text extraction leads to intolerably long processing times!
    // therefore we switched to event based text extraction (despite extraction for headers/footers
    // is not implemented for this extraction method).
    ExtractorFactory.setAllThreadsPreferEventExtractors(true);
}
 

import org.apache.poi.extractor.ExtractorFactory; //导入依赖的package包/类
@Override
protected String readContent(final VFSLeaf leaf) throws IOException, DocumentException {
    BufferedInputStream bis = null;
    try {
        bis = new BufferedInputStream(leaf.getInputStream());
        // event based text extraction in POI 3.9 doesn't consider header/footer
        // (see org.apache.poi.xssf.extractor.XSSFEventBasedExcelExtractor
        // and comments in constructor of FileDocumentFactory)
        // Previous versions of this class had implemented support for header/footer extraction
        // based on the complete memory model which caused performance problems for large files.
        return ExtractorFactory.createExtractor(bis).getText();
    } catch (final Exception e) {
        throw new DocumentException(e.getMessage());
    } finally {
        if (bis != null) {
            bis.close();
        }
    }
}
 

import org.apache.poi.extractor.ExtractorFactory; //导入依赖的package包/类
@Override
public String readContent(final VFSLeaf leaf) throws IOException, DocumentException {
    BufferedInputStream bis = null;
    try {
        bis = new BufferedInputStream(leaf.getInputStream());
        final POITextExtractor extractor = ExtractorFactory.createExtractor(bis);
        if (extractor instanceof XSLFPowerPointExtractor) {
            // retrieve slide content and notes
            return ((XSLFPowerPointExtractor) extractor).getText(true, true);
        }
        throw new AssertException("Expected XSLFPowerPointExtractor as text extractor.");
    } catch (final Exception e) {
        throw new DocumentException(e.getMessage());
    } finally {
        if (bis != null) {
            bis.close();
        }
    }
}
 

import org.apache.poi.extractor.ExtractorFactory; //导入依赖的package包/类
/**
 * Detects the type of an OfficeOpenXML (OOXML) file from
 *  opened Package 
 */
public static MediaType detectOfficeOpenXML(OPCPackage pkg) {
    PackageRelationshipCollection core = 
       pkg.getRelationshipsByType(ExtractorFactory.CORE_DOCUMENT_REL);
    if (core.size() != 1) {
        // Invalid OOXML Package received
        return null;
    }

    // Get the type of the core document part
    PackagePart corePart = pkg.getPart(core.getRelationship(0));
    String coreType = corePart.getContentType();

    // Turn that into the type of the overall document
    String docType = coreType.substring(0, coreType.lastIndexOf('.'));

    // The Macro Enabled formats are a little special
    if(docType.toLowerCase().endsWith("macroenabled")) {
        docType = docType.toLowerCase() + ".12";
    }

    if(docType.toLowerCase().endsWith("macroenabledtemplate")) {
        docType = MACRO_TEMPLATE_PATTERN.matcher(docType).replaceAll("macroenabled.12");
    }

    // Build the MediaType object and return
    return MediaType.parse(docType);
}