Java 类com.itextpdf.text.pdf.parser.TextExtractionStrategy 实例源码

private String getPdfContent(String pdfFile) {
    try {
        PdfReader reader = new PdfReader(pdfFile);
        StringBuffer sb = new StringBuffer();
        PdfReaderContentParser parser = new PdfReaderContentParser(reader);
        TextExtractionStrategy strategy;
        for (int i = 1; i <= reader.getNumberOfPages(); i++) {
            strategy = parser.processContent(i, new SimpleTextExtractionStrategy());
            sb.append(strategy.getResultantText());
        }
        reader.close();
        return sb.toString();
    } catch (IOException e) {
        throw new IllegalArgumentException("Not able to read file " + pdfFile, e);
    }
}

<E extends TextExtractionStrategy> String extractAndStore(PdfReader reader, String format, Class<E> strategyClass, RenderFilter... filters) throws Exception
{
    StringBuilder builder = new StringBuilder();

    for (int page = 1; page <= reader.getNumberOfPages(); page++)
    {
        TextExtractionStrategy strategy = strategyClass.getConstructor().newInstance();
        if (filters != null && filters.length > 0)
        {
            strategy = new FilteredTextRenderListener(strategy, filters);
        }
        String pageText = extract(reader, page, strategy);
        Files.write(Paths.get(String.format(format, page)), pageText.getBytes("UTF8"));

        if (page > 1)
            builder.append("\n\n");
        builder.append(pageText);
    }

    return builder.toString();
}

public static String[] extractsPdfLines(String PdfFile) throws IOException {
    try {
        StringBuffer buff = new StringBuffer();
        String ExtractedText = null;
        PdfReader reader = new PdfReader(PdfFile);
        PdfReaderContentParser parser = new PdfReaderContentParser(reader);
        TextExtractionStrategy strategy;

        for (int i = 1; i <= reader.getNumberOfPages(); i++) {
            strategy = parser.processContent(i, new SimpleTextExtractionStrategy());
            ExtractedText = strategy.getResultantText().toString();
            buff.append(ExtractedText + "\n");
        }

        String[] LinesArray;
        LinesArray = buff.toString().split("\n");
        reader.close();
        return LinesArray;
    } catch (Exception e) {
        return null;
    }
}

private static List<LocationTextExtractionStrategy.TextChunk> getTextChunks() throws IOException {
    PdfReader reader = new PdfReader(RESOURCES_DIR + "KLEE.pdf");
    PdfReaderContentParser parser = new PdfReaderContentParser(reader);
    PrintWriter out = new PrintWriter(new FileOutputStream(RESOURCES_DIR + "extracted text"));
    TextExtractionStrategy strategy;
    for (int i = 1; i <= reader.getNumberOfPages(); i++) {
        strategy
                = parser.processContent(i, new LocationTextExtractionStrategy());
        out.println(strategy.getResultantText());
    }
    out.flush();
    out.close();
    return null;
}

@Override
public BookReadingResult open(@NonNull File file, @NonNull PercentSender percentSender, @NonNull Runnable readingEndSender) {

    try {
        PdfReader pdfReader = new PdfReader(file.getAbsolutePath());
        PdfReaderContentParser parser = new PdfReaderContentParser(pdfReader);
        int numberOfPages = pdfReader.getNumberOfPages();
        int oldPercent = 0, newPercent;

        StringBuffer stringBuffer = new StringBuffer();
        for (int i = 1; i <= pdfReader.getNumberOfPages(); i++) {
            TextExtractionStrategy strategy = parser.processContent(i, new SimpleTextExtractionStrategy());
            String pageText = strategy.getResultantText();

            stringBuffer.append(pageText);

            if (pageText.endsWith("\\.") ||
                    pageText.endsWith("!") ||
                    pageText.endsWith("?") ||
                    pageText.endsWith(":")) {
                stringBuffer.append(" ");
            } else {
                stringBuffer.append(". ");
            }

            newPercent = 100 * i / numberOfPages;
            if (newPercent != oldPercent) {
                percentSender.refreshPercents(oldPercent, newPercent);
                oldPercent = newPercent;
            }
        }

        pdfReader.close();

        String resultText = new String(stringBuffer);
        resultText = resultText.trim();                         // delete first and last space (if exist)
        resultText = resultText.replaceAll("\\s+", " ");        // delete all duplicate white spaces
        resultText = resultText.replaceAll("(\\.)+", "\\.");        // delete all duplicate dots

        if (resultText.length() < 1) {
            return null;
        }

        readingEndSender.run();
        return new BookReadingResult(resultText, InternalStorageFileHelper.fileNameWithoutExtension(file), "");

    } catch (IOException e) {
        e.printStackTrace();

        return null;
    }

}

public RemappingExtractionFilter(TextExtractionStrategy strategy) throws NoSuchFieldException, SecurityException
{
    this.strategy = strategy;
    this.stringField = TextRenderInfo.class.getDeclaredField("text");
    this.stringField.setAccessible(true);
}

String extract(PdfReader reader, int pageNo, TextExtractionStrategy strategy) throws IOException
{
    return PdfTextExtractor.getTextFromPage(reader, pageNo, strategy);
}

String extractRemapped(PdfReader reader, int pageNo) throws IOException, NoSuchFieldException, SecurityException
{
    TextExtractionStrategy strategy = new RemappingExtractionFilter(new LocationTextExtractionStrategy());
    return PdfTextExtractor.getTextFromPage(reader, pageNo, strategy);
}

public static void searchforStringinPdfFiles(File file) throws IOException {

        outputfile.println("<Dateiname>" + (file.getName()) + "</Dateiname>");

        int trefferinDatei;

        if (filetools.pdf.PdfAnalysis.testPdfOk(file)) {
            try {
                PdfReader reader = new PdfReader(file.toString());
                int pagesPdf = reader.getNumberOfPages();
                StringBuffer buff = new StringBuffer();
                String ExtractedText = null;
                PdfReaderContentParser parser = new PdfReaderContentParser(reader);
                TextExtractionStrategy strategy;

                trefferinDatei = 0;
                for (int i = 1; i <= pagesPdf; i++) {
                    strategy = parser.processContent(i, new SimpleTextExtractionStrategy());
                    ExtractedText = strategy.getResultantText().toString();
                    buff.append(ExtractedText + "\n");
                    String[] LinesArray = buff.toString().split("\n");
                    int linesPdf = LinesArray.length;

                    for (int j = 0; (j < linesPdf && (stringfound < MAXIMAL_HITS)); j++) {
                        String paragraph = LinesArray[j].toLowerCase();
                        String searchStringlowerCase = searchedString.toLowerCase();
                        if (paragraph.contains(searchStringlowerCase)) {
                            trefferinDatei++;
                            stringfound++;
                            outputfile.println("<Seitenzahl>" + i + "</Seitenzahl>");
                            outputfile.println("<GanzeZeile>" + (LinesArray[j]) + "</GanzeZeile>");
                        }
                    }

                }
                outputfile.println("<TextinDatei>" + trefferinDatei + "</TextinDatei>");
                outputfile.println("<Suchergebnis>" + trefferinDatei + " x " + "</Suchergebnis>");

                reader.close();

            } catch (Exception e) {
                outputfile.println("<Fehlermeldung>" + e + "</Fehlermeldung>");
            }
        }

    }