java - 解析二进制文件时出错

Question

将 PDFBOX 版本升级到 1.6.0 后，我尝试使用 Apache Tika 解析 pdf 文件...并且我开始在少数 pdf 文件中收到此错误。有什么建议吗？

java.io.IOException: expected='endstream' actual='' org.apache.pdfbox.io.PushBackInputStream@3a72d4e5
        at org.apache.pdfbox.pdfparser.BaseParser.parseCOSStream(BaseParser.java:439)
        at org.apache.pdfbox.pdfparser.PDFParser.parseObject(PDFParser.java:552)
        at org.apache.pdfbox.pdfparser.PDFParser.parse(PDFParser.java:184)
        at org.apache.pdfbox.pdmodel.PDDocument.load(PDDocument.java:1088)
        at org.apache.pdfbox.pdmodel.PDDocument.load(PDDocument.java:1053)
        at org.apache.tika.parser.pdf.PDFParser.parse(PDFParser.java:74)
        at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:197)
        at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:197)
        at org.apache.tika.parser.AutoDetectParser.parse(AutoDetectParser.java:135)
        at org.apache.tika.Tika.parseToString(Tika.java:357)
        at edu.uci.ics.crawler4j.crawler.BinaryParser.parse(BinaryParser.java:37)
        at edu.uci.ics.crawler4j.crawler.WebCrawler.handleBinary(WebCrawler.java:223)
        at edu.uci.ics.crawler4j.crawler.WebCrawler.processPage(WebCrawler.java:461)
        at edu.uci.ics.crawler4j.crawler.WebCrawler.run(WebCrawler.java:129)
        at java.lang.Thread.run(Thread.java:662)
     WARN [Crawler 2] Did not found XRef object at specified startxref position 0

<小时/>

这是我的代码。

        if (page.isBinary()) {
                        handleBinary(page, curURL);
                    }
        -------------------------------------------------------------------------------

            public int handleBinary(Page page, WebURL curURL) {
                    try {
                        binaryParser.parse(page.getBinaryData());
                        page.setText(binaryParser.getText());
                        handleMetaData(page, binaryParser.getMetaData());



                        //System.out.println(" pdf url " +page.getWebURL().getURL());
                        //System.out.println("Text" +page.getText());
                    } catch (Exception e) {
                        // TODO: handle exception
                    }
                    return PROCESS_OK;
                }

<小时/>

        public class BinaryParser {

            private String text;
            private Map<String, String> metaData;

            private Tika tika;

            public BinaryParser() {
                tika = new Tika();
            }

            public void parse(byte[] data) {
                InputStream is = null;
                try {
                    is = new ByteArrayInputStream(data);
                    text = null;
                    Metadata md = new Metadata();
                    metaData = new HashMap<String, String>();
                    text = tika.parseToString(is, md).trim();
                    processMetaData(md);
                } catch (Exception e) {
                    e.printStackTrace();
                } finally {
                    IOUtils.closeQuietly(is);
                }
            }

            public String getText() {
                return text;
            }

            public void setText(String text) {
                this.text = text;
            }


            private void processMetaData(Metadata md){
                if ((getMetaData() == null) || (!getMetaData().isEmpty())) {
                    setMetaData(new HashMap<String, String>());
                }
                for (String name : md.names()){
                    getMetaData().put(name.toLowerCase(), md.get(name));
                }
            }

            public Map<String, String> getMetaData() {
                return metaData;
            }

            public void setMetaData(Map<String, String> metaData) {
                this.metaData = metaData;
            }

        }

<小时/>

    public class Page {

        private WebURL url;

        private String html;

        // Data for textual content
        private String text;

        private String title;

        private String keywords;
        private String authors;
        private String description;
        private String contentType;
        private String contentEncoding;

        // binary data (e.g, image content)
        // It's null for html pages
        private byte[] binaryData;

        private List<WebURL> urls;

        private ByteBuffer bBuf;

        private final static String defaultEncoding = Configurations
                .getStringProperty("crawler.default_encoding", "UTF-8");

        public boolean load(final InputStream in, final int totalsize,
                final boolean isBinary) {
            if (totalsize > 0) {
                this.bBuf = ByteBuffer.allocate(totalsize + 1024);
            } else {
                this.bBuf = ByteBuffer.allocate(PageFetcher.MAX_DOWNLOAD_SIZE);
            }
            final byte[] b = new byte[1024];
            int len;
            double finished = 0;
            try {
                while ((len = in.read(b)) != -1) {
                    if (finished + b.length > this.bBuf.capacity()) {
                        break;
                    }
                    this.bBuf.put(b, 0, len);
                    finished += len;
                }
            } catch (final BufferOverflowException boe) {
                System.out.println("Page size exceeds maximum allowed.");
                return false;
            } catch (final Exception e) {
                System.err.println(e.getMessage());
                return false;
            }

            this.bBuf.flip();
            if (isBinary) {
                binaryData = new byte[bBuf.limit()];
                bBuf.get(binaryData);
            } else {
                this.html = "";
                this.html += Charset.forName(defaultEncoding).decode(this.bBuf);
                this.bBuf.clear();
                if (this.html.length() == 0) {
                    return false;
                }
            }
            return true;
        }
    public boolean isBinary() {
        return binaryData != null;
    }

    public byte[] getBinaryData() {
        return binaryData;
    }

Answer 1

当您将 PDF 文档加载到 Page 类的二进制缓冲区中时，您确定不会意外截断 PDF 文档吗？

您的 Page.load() 方法中存在多个潜在问题。首先，自 read() 以来，finished + b.length > this.bBuf.capacity() 应该是 finished + len > this.bBuf.capacity()方法返回的字节数可能少于 b.length。另外，你确定你给出的totalsize参数是准确的吗？最后，给定文档可能大于 MAX_DOWNLOAD_SIZE 限制。