Java PDFParserConfig.setExtractInlineImages方法代码示例

import org.apache.tika.parser.pdf.PDFParserConfig; //导入方法依赖的package包/类
public PDFExtract(){
    parser = new AutoDetectParser();
    TesseractOCRConfig config = new TesseractOCRConfig();
    PDFParserConfig pdfConfig = new PDFParserConfig();
    pdfConfig.setExtractInlineImages(true);

    parseContext = new ParseContext();
    parseContext.set(TesseractOCRConfig.class, config);
    parseContext.set(PDFParserConfig.class, pdfConfig);
    //need to add this to make sure recursive parsing happens!
    parseContext.set(Parser.class, parser);
}
 

import org.apache.tika.parser.pdf.PDFParserConfig; //导入方法依赖的package包/类
public Indexer(String indexDir, boolean create, boolean fork, boolean ocr) throws IOException {
logger.entry();

this.fork = fork;

numErrors = 0;
numFiles = 0;

Directory dir = FSDirectory.open(Paths.get(indexDir));
Analyzer analyzer = new StandardAnalyzer();
IndexWriterConfig iwc = new IndexWriterConfig(analyzer);

if (create) {
    iwc.setOpenMode(OpenMode.CREATE);
    logger.info("Configuration specified to create a new index or overwrites an existing one.");
} else {
    iwc.setOpenMode(OpenMode.CREATE_OR_APPEND);
    logger.info("Configuration specified to create a new index if one does not exist, otherwise the index will be opened and documents will be appended.");
}

writer = new IndexWriter(dir, iwc);

Parser autoDetectParser = new AutoDetectParser();
context = new ParseContext();

if (ocr) {
    TesseractOCRConfig ocrConfig = new TesseractOCRConfig();
    PDFParserConfig pdfConfig = new PDFParserConfig();
    pdfConfig.setExtractInlineImages(true);
    pdfConfig.setExtractUniqueInlineImagesOnly(false);
    context.set(Parser.class, autoDetectParser);
    context.set(TesseractOCRConfig.class, ocrConfig);
    context.set(PDFParserConfig.class, pdfConfig);
}

if (fork) {
    parser = new ForkParser(ForkParser.class.getClassLoader(), autoDetectParser);
} else {
    parser = autoDetectParser;
}

logger.exit();
   }
 

import org.apache.tika.parser.pdf.PDFParserConfig; //导入方法依赖的package包/类
private static void fillPdfOptions(PDFParserConfig pdfParserConfig, Map<String, Object> options) {
	final Object averageCharTolerance = options.get("pdfAverageCharTolerance");
	final Object enableAutoSpace = options.get("pdfEnableAutoSpace");
	final Object extractAcroFormContent = options.get("pdfExtractAcroFormContent");
	final Object extractAnnotationText = options.get("pdfExtractAnnotationText");
	final Object extractInlineImages = options.get("pdfExtractInlineImages");
	final Object extractUniqueInlineImagesOnly = options.get("pdfExtractUniqueInlineImagesOnly");
	final Object sortByPosition = options.get("pdfSortByPosition");
	final Object spacingTolerance = options.get("pdfSpacingTolerance");
	final Object suppressDuplicateOverlappingText = options.get("pdfSuppressDuplicateOverlappingText");

	if (averageCharTolerance != null) {
		pdfParserConfig.setAverageCharTolerance(Float.parseFloat(averageCharTolerance.toString()));
	}

	if (enableAutoSpace != null) {
		pdfParserConfig.setEnableAutoSpace((Boolean) enableAutoSpace);
	}

	if (extractAcroFormContent != null) {
		pdfParserConfig.setExtractAcroFormContent((Boolean) extractAcroFormContent);
	}

	if (extractAnnotationText != null) {
		pdfParserConfig.setExtractAnnotationText((Boolean) extractAnnotationText);
	}

	if (extractInlineImages != null) {
		pdfParserConfig.setExtractInlineImages((Boolean) extractInlineImages);
	} else {
		pdfParserConfig.setExtractInlineImages(true);
	}

	if (extractUniqueInlineImagesOnly != null) {
		pdfParserConfig.setExtractUniqueInlineImagesOnly((Boolean) extractUniqueInlineImagesOnly);
	}

	if (sortByPosition != null) {
		pdfParserConfig.setSortByPosition((Boolean) sortByPosition);
	}

	if (spacingTolerance != null) {
		pdfParserConfig.setSpacingTolerance(Float.parseFloat(spacingTolerance.toString()));
	}

	if (suppressDuplicateOverlappingText != null) {
		pdfParserConfig.setSuppressDuplicateOverlappingText((Boolean) suppressDuplicateOverlappingText);
	}
}