/** * If true, the parser should try to remove duplicated * text over the same region. This is needed for some * PDFs that achieve bolding by re-writing the same * text in the same area. Note that this can * slow down extraction substantially (PDFBOX-956) and * sometimes remove characters that were not in fact * duplicated (PDFBOX-1155). By default this is disabled. * * @deprecated use {@link #setPDFParserConfig(PDFParserConfig)} */ public void setSuppressDuplicateOverlappingText(boolean v) { defaultConfig.setSuppressDuplicateOverlappingText(v); }
setSuppressDuplicateOverlappingText( getBooleanProp(props.getProperty("suppressDuplicateOverlappingText"), getSuppressDuplicateOverlappingText()));
/** * If true, the parser should try to remove duplicated * text over the same region. This is needed for some * PDFs that achieve bolding by re-writing the same * text in the same area. Note that this can * slow down extraction substantially (PDFBOX-956) and * sometimes remove characters that were not in fact * duplicated (PDFBOX-1155). By default this is disabled. * * @deprecated use {@link #setPDFParserConfig(PDFParserConfig)} */ public void setSuppressDuplicateOverlappingText(boolean v) { defaultConfig.setSuppressDuplicateOverlappingText(v); }
/** * If true, the parser should try to remove duplicated * text over the same region. This is needed for some * PDFs that achieve bolding by re-writing the same * text in the same area. Note that this can * slow down extraction substantially (PDFBOX-956) and * sometimes remove characters that were not in fact * duplicated (PDFBOX-1155). By default this is disabled. * * @deprecated use {@link #setPDFParserConfig(PDFParserConfig)} */ public void setSuppressDuplicateOverlappingText(boolean v) { defaultConfig.setSuppressDuplicateOverlappingText(v); }
pdfParserConfig.setSuppressDuplicateOverlappingText((Boolean) suppressDuplicateOverlappingText);
setSuppressDuplicateOverlappingText( getBooleanProp(props.getProperty("suppressDuplicateOverlappingText"), getSuppressDuplicateOverlappingText()));
setSuppressDuplicateOverlappingText( getBooleanProp(props.getProperty("suppressDuplicateOverlappingText"), getSuppressDuplicateOverlappingText()));
pdfConfig.setOcrStrategy(PDFParserConfig.OCR_STRATEGY.NO_OCR); pdfConfig.setSuppressDuplicateOverlappingText(true); context.set(PDFParserConfig.class, pdfConfig); modifyParseContext(context);