gpt4 book ai didi

org.apache.tika.parser.pkg.ZipContainerDetector类的使用及代码示例

转载 作者:知者 更新时间:2024-03-13 12:59:21 30 4
gpt4 key购买 nike

本文整理了Java中org.apache.tika.parser.pkg.ZipContainerDetector类的一些代码示例,展示了ZipContainerDetector类的具体用法。这些代码示例主要来源于Github/Stackoverflow/Maven等平台,是从一些精选项目中提取出来的代码,具有较强的参考意义,能在一定程度帮忙到你。ZipContainerDetector类的具体详情如下:
包路径:org.apache.tika.parser.pkg.ZipContainerDetector
类名称:ZipContainerDetector

ZipContainerDetector介绍

[英]A detector that works on Zip documents and other archive and compression formats to figure out exactly what the file is.
[中]一种检测器,可以对Zip文档和其他存档和压缩格式进行检测,以准确确定文件是什么。

代码示例

代码示例来源:origin: apache/tika

public MediaType detect(InputStream input, Metadata metadata)
    throws IOException {
  // Check if we have access to the document
  if (input == null) {
    return MediaType.OCTET_STREAM;
  }
  TemporaryResources tmp = new TemporaryResources();
  try {
    TikaInputStream tis = TikaInputStream.get(input, tmp);
    byte[] prefix = new byte[1024]; // enough for all known formats
    int length = tis.peek(prefix);
    MediaType type = detectArchiveFormat(prefix, length);
    if (type == TIFF) {
      return TIFF;
    } else if (PackageParser.isZipArchive(type)
          && TikaInputStream.isTikaInputStream(input)) {
      return detectZipFormat(tis);
    } else if (!type.equals(MediaType.OCTET_STREAM)) {
      return type;
    } else {
      return detectCompressorFormat(prefix, length);
    }
  } finally {
    try {
      tmp.dispose();
    } catch (TikaException e) {
      // ignore
    }
  }
}

代码示例来源:origin: apache/tika

zipEntrySource = new ZipFileZipEntrySource(new ZipFile(stream.getFile()));
} catch (IOException e) {
  return tryStreamingDetection(stream);
  pkg = OPCPackage.open(zipEntrySource);
} catch (SecurityException e) {
  closeQuietly(zipEntrySource);
  closeQuietly(zipEntrySource);
  return null;
  type = detectOfficeOpenXML(pkg);
  if (type == null) {
    type = detectXPSOPC(pkg);
    type = detectAutoCADOPC(pkg);
  closeQuietly(zipEntrySource);
  closeQuietly(zipEntrySource);
  return null;

代码示例来源:origin: apache/tika

MediaType type = detectOPCBased(tis);
if (type != null) {
  return type;
  type = detectOpenDocument(zip);
    type = detectIWork13(zip);
    type = detectIWork(zip);
    type = detectJar(zip);
    type = detectKmz(zip);
    type = detectIpa(zip);

代码示例来源:origin: apache/tika

ZipContainerDetector detector = new ZipContainerDetector();
MediaType type = null;
try {
  type = detector.detect(stream, new Metadata());
} catch (Exception e) {
  EmbeddedDocumentUtil.recordEmbeddedStreamException(e, parentMetadata);

代码示例来源:origin: com.github.lafa.tikaNoExternal/tika-parsers

MediaType type = detectOfficeOpenXML(pkg);
if (type != null) return type;
type = detectXPSOPC(pkg);
if (type != null) return type;
type = detectAutoCADOPC(pkg);
if (type != null) return type;

代码示例来源:origin: stackoverflow.com

Detector detector;
List<Detector> detectors = new ArrayList<Detector>();
detectors.add(new ZipContainerDetector());
detectors.add(new POIFSContainerDetector());

detectors.add(new MultipartSignedDetector());

detectors.add(MimeTypes.getDefaultMimeTypes());
detector = new CompositeDetector(detectors);
String mimetype = detector.detect(TikaInputStream.get(new File(args[0])), new Metadata()).toString();

代码示例来源:origin: org.apache.tika/tika-parsers

ZipContainerDetector detector = new ZipContainerDetector();
MediaType type = null;
try {
  type = detector.detect(stream, new Metadata());
} catch (Exception e) {
  EmbeddedDocumentUtil.recordEmbeddedStreamException(e, parentMetadata);

代码示例来源:origin: stackoverflow.com

detectors.add(new ZipContainerDetector());

代码示例来源:origin: org.apache.tika/tika-parsers

MediaType type = detectOPCBased(tis);
if (type != null) {
  return type;
  type = detectOpenDocument(zip);
    type = detectIWork13(zip);
    type = detectIWork(zip);
    type = detectJar(zip);
    type = detectKmz(zip);
    type = detectIpa(zip);

代码示例来源:origin: org.apache.tika/tika-parsers

pkg = OPCPackage.open(zipEntrySource);
} catch (SecurityException e) {
  closeQuietly(zipEntrySource);
  closeQuietly(zipEntrySource);
  return null;
  type = detectOfficeOpenXML(pkg);
  if (type == null) {
    type = detectXPSOPC(pkg);
    type = detectAutoCADOPC(pkg);
  closeQuietly(zipEntrySource);
  closeQuietly(zipEntrySource);
  return null;

代码示例来源:origin: org.apache.tika/tika-parsers

public MediaType detect(InputStream input, Metadata metadata)
    throws IOException {
  // Check if we have access to the document
  if (input == null) {
    return MediaType.OCTET_STREAM;
  }
  TemporaryResources tmp = new TemporaryResources();
  try {
    TikaInputStream tis = TikaInputStream.get(input, tmp);
    byte[] prefix = new byte[1024]; // enough for all known formats
    int length = tis.peek(prefix);
    MediaType type = detectArchiveFormat(prefix, length);
    if (type == TIFF) {
      return TIFF;
    } else if (PackageParser.isZipArchive(type)
          && TikaInputStream.isTikaInputStream(input)) {
      return detectZipFormat(tis);
    } else if (!type.equals(MediaType.OCTET_STREAM)) {
      return type;
    } else {
      return detectCompressorFormat(prefix, length);
    }
  } finally {
    try {
      tmp.dispose();
    } catch (TikaException e) {
      // ignore
    }
  }
}

代码示例来源:origin: com.github.lafa.tikaNoExternal/tika-parsers

ZipContainerDetector detector = new ZipContainerDetector();
MediaType type = null;
try {
  type = detector.detect(stream, new Metadata());
} catch (Exception e) {
  EmbeddedDocumentUtil.recordEmbeddedStreamException(e, parentMetadata);

代码示例来源:origin: com.github.lafa.tikaNoExternal/tika-parsers

ZipFile zip = new ZipFile(tis.getFile()); // TODO: hasFile()?
try {
  MediaType type = detectOpenDocument(zip);
  if (type == null) {
    type = detectOPCBased(zip, tis);
    type = detectIWork13(zip);
    type = detectIWork(zip);
    type = detectJar(zip);
    type = detectKmz(zip);
    type = detectIpa(zip);

代码示例来源:origin: com.github.lafa.tikaNoExternal/tika-parsers

public MediaType detect(InputStream input, Metadata metadata)
    throws IOException {
  // Check if we have access to the document
  if (input == null) {
    return MediaType.OCTET_STREAM;
  }
  TemporaryResources tmp = new TemporaryResources();
  try {
    TikaInputStream tis = TikaInputStream.get(input, tmp);
    byte[] prefix = new byte[1024]; // enough for all known formats
    int length = tis.peek(prefix);
    MediaType type = detectArchiveFormat(prefix, length);
    if (PackageParser.isZipArchive(type)
        && TikaInputStream.isTikaInputStream(input)) {
      return detectZipFormat(tis);
    } else if (!type.equals(MediaType.OCTET_STREAM)) {
      return type;
    } else {
      return detectCompressorFormat(prefix, length);
    }
  } finally {
    try {
      tmp.dispose();
    } catch (TikaException e) {
      // ignore
    }
  }
}

30 4 0
Copyright 2021 - 2024 cfsdn All Rights Reserved 蜀ICP备2022000587号
广告合作:1813099741@qq.com 6ren.com