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

x33g5p2x  于2022-01-26 转载在 其他  
字(11.4k)|赞(0)|评价(0)|浏览(396)

本文整理了Java中org.apache.tika.parser.Parser类的一些代码示例，展示了Parser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。Parser类的具体详情如下：
包路径：org.apache.tika.parser.Parser
类名称：Parser

Parser介绍

[英]Tika parser interface.
[中]Tika解析器接口。

代码示例

代码示例来源：origin: apache/tika

  1. public static void useAutoDetectParser() throws Exception {
  2.   InputStream stream = new ByteArrayInputStream(new byte[0]);
  3.   ContentHandler handler = new DefaultHandler();
  4.   Metadata metadata = new Metadata();
  5.   ParseContext context = new ParseContext();
  6.   Parser parser = new AutoDetectParser();
  7.   parser.parse(stream, handler, metadata, context);
  8. }

代码示例来源：origin: apache/tika

  1. public boolean isSupported(TikaInputStream input) throws IOException {
  2.   MediaType type = detector.detect(input, new Metadata());
  3.   return parser.getSupportedTypes(new ParseContext()).contains(type);
  4. }

代码示例来源：origin: javasoze/meaningfulweb

  1. private static void parseMeta(Parser parser,InputStream in,Metadata meta,Map<String,String> ogmeta) throws IOException, SAXException, TikaException{
  2.  parser.parse(in, new DefaultHandler(), meta, new ParseContext());
  3.  String[] propnames = meta.names();
  4.  for (String propname : propnames){
  5.   String val = meta.get(propname);
  6.   ogmeta.put(propname, val);
  7.  }
  8. }

代码示例来源：origin: jpotts/alfresco-api-java-examples

  1. InputStream stream = new FileInputStream(file);
  2. try {
  3.   Metadata metadata = new Metadata();
  4.   ContentHandler handler = new DefaultHandler();
  5.   Parser parser = new JpegParser();
  6.   ParseContext context = new ParseContext();
  7.   metadata.set(Metadata.CONTENT_TYPE, mimeType);
  8.   parser.parse(stream, handler, metadata, context);
  9.   String lat = metadata.get("geo:lat");
  10.   String lon = metadata.get("geo:long");
  11.   stream.close();

代码示例来源：origin: apache/cxf

  1. return null;
  2. final Metadata metadata = new Metadata();
  3.     metadata.set(HttpHeaders.CONTENT_TYPE, mediaType.toString());
  4.   } else {
  5.     for (Parser p : parsers) {
  6.       if (mediaType != null && !p.getSupportedTypes(context).contains(mediaType)) {
  7.         continue;
  8.     context = new ParseContext();
  9.   if (context.get(Parser.class) == null) {
  10.     context.set(Parser.class,
  11.           parser instanceof AutoDetectParser ? parser : new AutoDetectParser());
  12.     parser.parse(in, handler, metadata, context);
  13.   } catch (Exception ex) {
  14.       parser.parse(in, handler, metadata, context);
  15.     } else {
  16.       throw ex;

代码示例来源：origin: apache/tika

  1. ParseContext context = new ParseContext();
  2. BodyContentHandler handler;
  3. Metadata metadata;
  4. metadata = new Metadata();
  5. handler = new BodyContentHandler();
  6. p.parse(new ByteArrayInputStream(new byte[] {0,1,2,3,4}), handler, metadata, context);
  7. assertEquals("Fell back!", handler.toString());
  8. usedParsers = metadata.getValues("X-Parsed-By");
  9. assertEquals(1, usedParsers.length);
  10. assertEquals(DummyParser.class.getName(), usedParsers[0]);
  11. metadata = new Metadata();
  12. handler = new BodyContentHandler();
  13. p.parse(new ByteArrayInputStream(new byte[] {0,1,2,3,4}), handler, metadata, context);
  14. assertEquals("Fell back!", handler.toString());
  15. metadata = new Metadata();
  16. handler = new BodyContentHandler();
  17. p.parse(new ByteArrayInputStream(new byte[] {0,1,2,3,4}), handler, metadata, context);
  18. assertEquals("Fell back!", handler.toString());

代码示例来源：origin: apache/tika

  1. metadata.set(Metadata.CONTENT_TYPE, type);
  2. } else if (entry.getName().equals(META_NAME)) {
  3.   meta.parse(zip, new DefaultHandler(), metadata, context);
  4. } else if (entry.getName().endsWith("content.xml")) {
  5.   if (content instanceof OpenDocumentContentParser) {
  6.   } else {
  7.     content.parse(zip, handler, metadata, context);
  8.   } else {
  9.     content.parse(zip, handler, metadata, context);
  10.     EmbeddedDocumentExtractor embeddedDocumentExtractor =
  11.         EmbeddedDocumentUtil.getEmbeddedDocumentExtractor(context);
  12.     Metadata embeddedMetadata = new Metadata();
  13.     embeddedMetadata.set(TikaCoreProperties.ORIGINAL_RESOURCE_NAME, entry.getName());

代码示例来源：origin: apache/tika

  1. xhtml.startDocument();
  2. ContentHandler childHandler = new EmbeddedContentHandler(
  3.    new BodyContentHandler(xhtml));
  4.       type = type.trim();
  5.     metadata.set(Metadata.CONTENT_TYPE, type);
  6.   } else if (entry.getName().equals("metadata.xml")) {
  7.     meta.parse(zip, new DefaultHandler(), metadata, context);
  8.   } else if (entry.getName().endsWith(".opf")) {
  9.     meta.parse(zip, new DefaultHandler(), metadata, context);
  10.   } else if (entry.getName().endsWith(".htm") || 
  11.           entry.getName().endsWith(".html") || 
  12.         entry.getName().endsWith(".xhtml")) {
  13.     content.parse(zip, childHandler, metadata, context);

代码示例来源：origin: gentics/mesh

  1. @Override
  2. public Single<Map<String, String>> getMetadata(InputStream ins) {
  3.   return Single.create(sub -> {
  4.     Parser parser = new AutoDetectParser();
  5.     BodyContentHandler handler = new BodyContentHandler();
  6.     Metadata metadata = new Metadata();
  7.     ParseContext context = new ParseContext();
  8.     try {
  9.       parser.parse(ins, handler, metadata, context);
  10.       Map<String, String> map = new HashMap<>();
  11.       String[] metadataNames = metadata.names();
  12.       for (String name : metadataNames) {
  13.         map.put(name, metadata.get(name));
  14.       }
  15.       sub.onSuccess(map);
  16.     } catch (Exception e) {
  17.       sub.onError(e);
  18.     }
  19.     // ins.close();
  20.   });
  21. }

代码示例来源：origin: org.apache.beam/beam-sdks-java-io-tika

  1. @ProcessElement
  2.  public void processElement(ProcessContext c) throws Exception {
  3.   ReadableFile file = c.element();
  4.   InputStream stream = Channels.newInputStream(file.open());
  5.   try (InputStream tikaStream = TikaInputStream.get(stream)) {
  6.    Parser parser =
  7.      tikaConfig == null ? new AutoDetectParser() : new AutoDetectParser(tikaConfig);
  8.    ParseContext context = new ParseContext();
  9.    context.set(Parser.class, parser);
  10.    Metadata tikaMetadata =
  11.      spec.getInputMetadata() != null ? spec.getInputMetadata() : new Metadata();
  12.    if (spec.getContentTypeHint() != null) {
  13.     tikaMetadata.set(Metadata.CONTENT_TYPE, spec.getContentTypeHint());
  14.    }
  15.    String location = file.getMetadata().resourceId().toString();
  16.    ParseResult res;
  17.    ContentHandler tikaHandler = new ToTextContentHandler();
  18.    try {
  19.     parser.parse(tikaStream, tikaHandler, tikaMetadata, context);
  20.     res = ParseResult.success(location, tikaHandler.toString(), tikaMetadata);
  21.    } catch (Exception e) {
  22.     res = ParseResult.failure(location, tikaHandler.toString(), tikaMetadata, e);
  23.    }
  24.    c.output(res);
  25.   }
  26.  }
  27. }

代码示例来源：origin: apache/tika

  1. MediaType.OCTET_STREAM, MediaType.TEXT_PLAIN));
  2. ParseContext context = new ParseContext();
  3. BodyContentHandler handler;
  4. Metadata metadata;
  5. Set<MediaType> types = p.getSupportedTypes(context);
  6. assertEquals(2, types.size());
  7. assertEquals(types.toString(), true, types.contains(MediaType.TEXT_PLAIN));
  8. metadata = new Metadata();
  9. handler = new BodyContentHandler();
  10. p.parse(new ByteArrayInputStream(new byte[] {0,1,2,3,4}), handler, metadata, context);
  11. assertEquals("Fell back!", handler.toString());
  12. metadata = new Metadata();
  13. handler = new BodyContentHandler();
  14. p.parse(new ByteArrayInputStream(new byte[] {0,1,2,3,4}), handler, metadata, context);
  15. assertEquals("", handler.toString());

代码示例来源：origin: apache/tika

  1. private void parsePage(byte[] byteObject, Parser htmlParser,
  2.             ContentHandler xhtml, ParseContext context) throws TikaException {// throws IOException
  3.   InputStream stream = null;
  4.   Metadata metadata = new Metadata();
  5.   ContentHandler handler = new EmbeddedContentHandler(new BodyContentHandler(xhtml));// -1
  6.   try {
  7.     stream = new ByteArrayInputStream(byteObject);
  8.     htmlParser.parse(stream, handler, metadata, context);
  9.   } catch (SAXException e) {
  10.     throw new RuntimeException(e);
  11.   } catch (IOException e) {
  12.     // Pushback overflow from tagsoup
  13.   }
  14. }

代码示例来源：origin: apache/tika

  1. @Override
  2. public void parse(InputStream stream, ContentHandler handler, Metadata metadata, ParseContext parseContext)
  3.     throws IOException, SAXException, TikaException {
  4.   TesseractOCRConfig config = parseContext.get(TesseractOCRConfig.class, defaultConfig);
  5.     _TMP_IMAGE_METADATA_PARSER.parse(tikaStream, new DefaultHandler(), metadata, parseContext);

代码示例来源：origin: NGDATA/lilyproject

  1. BodyContentHandler ch = new BodyContentHandler(woh);
  2.   Metadata metadata = new Metadata();
  3.   metadata.add(Metadata.CONTENT_TYPE, blob.getMediaType());
  4.   if (blob.getName() != null) {
  5.     metadata.add(Metadata.RESOURCE_NAME_KEY, blob.getName());
  6.   ParseContext parseContext = new ParseContext();
  7.   tikaParser.parse(is, ch, metadata, parseContext);
  8. } catch (Throwable t) {
  9.   if (woh.isWriteLimitReached(t)) {
  10. String text = ch.toString();
  11. if (text.length() > 0) {
  12.   result.add(text);

代码示例来源：origin: apache/tika

  1. String v = toString(obj, c.getType());
  2. if (isRichText(c)) {
  3.   BodyContentHandler h = new BodyContentHandler();
  4.   Metadata m = new Metadata();
  5.   m.set(Metadata.CONTENT_TYPE, "text/html; charset=UTF-8");
  6.   try {
  7.     htmlParser.parse(new ByteArrayInputStream(v.getBytes(UTF_8)),
  8.         h,
  9.         m, parseContext);
  10.     handler.characters(h.toString());
  11.   } catch (SAXException e) {

代码示例来源：origin: apache/tika

  1. public static void main(String[] args) throws Exception {
  2.     ApplicationContext context = new ClassPathXmlApplicationContext(
  3.         new String[]{"org/apache/tika/example/spring.xml"});
  4.     Parser parser = context.getBean("tika", Parser.class);
  5.     parser.parse(new ByteArrayInputStream("Hello, World!".getBytes(UTF_8)),
  6.         new WriteOutContentHandler(System.out), new Metadata(),
  7.         new ParseContext());
  8.   }
  9. }

代码示例来源：origin: apache/tika

  1. metadata.set(TikaCoreProperties.RESOURCE_NAME_KEY, filename);
  2. System.out.println("The MIME type (based on filename) is: ["
  3.     + mimeRegistry.detect(null, metadata) + "]");
  4. metadata.set(Metadata.CONTENT_TYPE, type.toString());
  5. ContentHandler handler = new BodyContentHandler();
  6. parser.parse(stream, handler, metadata, new ParseContext());

代码示例来源：origin: ViDA-NYU/ache

  1. public ParsedData parse(InputStream stream, String fileName, String contentType) {
  2.   BodyContentHandler handler = new BodyContentHandler(MAX_CHARACTERS);
  3.   BoilerpipeContentHandler textHandler = new BoilerpipeContentHandler(handler, KeepEverythingExtractor.INSTANCE);
  4.   Metadata metadata = createMetadata(fileName, contentType);
  5.   ParseContext context = new ParseContext();
  6.   try {
  7.     parser.parse(stream, textHandler, metadata, context);
  8.     
  9.     Map<String, String> metadataMap = new HashMap<String, String>();
  10.     for (String propertyName : metadata.names()) {
  11.       metadataMap.put(propertyName, metadata.get(propertyName));
  12.     }
  13.     
  14.     return new ParsedData(handler.toString(), metadataMap);
  15.     
  16.   } catch (IOException | SAXException | TikaException e) {
  17.     logger.error("Failed to extract metadata using Tika.", e);
  18.     return null;
  19.   }
  20. }

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

  1. private void handleZipEntry(ZipEntry entry, InputStream zip, Metadata metadata,
  2.                 ParseContext context, EndDocumentShieldingContentHandler handler)
  3.       throws IOException, SAXException, TikaException {
  4.     if (entry == null) return;
  6.     if (entry.getName().equals("mimetype")) {
  7.       String type = IOUtils.toString(zip, UTF_8);
  8.       metadata.set(Metadata.CONTENT_TYPE, type);
  9.     } else if (entry.getName().equals(META_NAME)) {
  10.       meta.parse(zip, new DefaultHandler(), metadata, context);
  11.     } else if (entry.getName().endsWith("content.xml")) {
  12.       if (content instanceof OpenDocumentContentParser) {
  13.         ((OpenDocumentContentParser) content).parseInternal(zip, handler, metadata, context);
  14.       } else {
  15.         // Foreign content parser was set:
  16.         content.parse(zip, handler, metadata, context);
  17.       }
  18.     } else if (entry.getName().endsWith("styles.xml")) {
  19.       if (content instanceof OpenDocumentContentParser) {
  20.         ((OpenDocumentContentParser) content).parseInternal(zip, handler, metadata, context);
  21.       } else {
  22.         // Foreign content parser was set:
  23.         content.parse(zip, handler, metadata, context);
  24.       }
  25.     }
  26.   }
  27. }

代码示例来源：origin: apache/tika

  1. context.set(Parser.class, decorator);
  2. ContentHandler localHandler = parserState.recursiveParserWrapperHandler.getNewContentHandler();
  3. long started = System.currentTimeMillis();
  4. parserState.recursiveParserWrapperHandler.startDocument();
  5. try {
  6.   getWrappedParser().parse(stream, localHandler, metadata, context);
  7. } catch (SAXException e) {
  8.   boolean wlr = isWriteLimitReached(e);
  9.     throw e;
  10.   metadata.set(RecursiveParserWrapperHandler.WRITE_LIMIT_REACHED, "true");
  11. } catch (Throwable e) {
  12.   metadata.add(TikaCoreProperties.TIKA_META_EXCEPTION_PREFIX+"runtime", stackTrace);
  13.   throw e;
  14. } finally {
  15.   long elapsedMillis = System.currentTimeMillis() - started;
  16.   metadata.set(RecursiveParserWrapperHandler.PARSE_TIME_MILLIS, Long.toString(elapsedMillis));
  17.   parserState.recursiveParserWrapperHandler.endDocument(localHandler, metadata);
  18.   parserState.recursiveParserWrapperHandler.endDocument();

内容来源于网络，如有侵权，请联系作者删除！

Parser

相关文章

    查看更多

    热门标签

    更多
    JavaquerypythonNode开发语言requestUtil数据库Table后端算法LoggerMessageElementParser

    最新文章

    更多
    • 蜀ICP备13028337号-1 大数据知识库 https://www.saoniuhuo.com © All rights reserved
    • 本站内容来源互联网,如果侵犯您的权益请联系我们删除, 联系方式：448109455@qq.com