本文整理汇总了Java中org.apache.tika.sax.TeeContentHandler类的典型用法代码示例。如果您正苦于以下问题：Java TeeContentHandler类的具体用法？Java TeeContentHandler怎么用？Java TeeContentHandler使用的例子？那么, 这里精选的类代码示例或许可以为您提供帮助。
TeeContentHandler类属于org.apache.tika.sax包，在下文中一共展示了TeeContentHandler类的11个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Java代码示例。
示例1: getContentHandler
import org.apache.tika.sax.TeeContentHandler; //导入依赖的package包/类
protected ContentHandler getContentHandler(
ContentHandler handler, Metadata metadata, ParseContext context) {
return new TeeContentHandler(
super.getContentHandler(handler, metadata, context),
getDublinCoreHandler(metadata, TikaCoreProperties.TITLE, "title"),
getDublinCoreHandler(metadata, TikaCoreProperties.KEYWORDS, "subject"),
getDublinCoreHandler(metadata, TikaCoreProperties.CREATOR, "creator"),
getDublinCoreHandler(metadata, TikaCoreProperties.DESCRIPTION, "description"),
getDublinCoreHandler(metadata, TikaCoreProperties.PUBLISHER, "publisher"),
getDublinCoreHandler(metadata, TikaCoreProperties.CONTRIBUTOR, "contributor"),
getDublinCoreHandler(metadata, TikaCoreProperties.CREATED, "date"),
getDublinCoreHandler(metadata, TikaCoreProperties.TYPE, "type"),
getDublinCoreHandler(metadata, TikaCoreProperties.FORMAT, "format"),
getDublinCoreHandler(metadata, TikaCoreProperties.IDENTIFIER, "identifier"),
getDublinCoreHandler(metadata, TikaCoreProperties.LANGUAGE, "language"),
getDublinCoreHandler(metadata, TikaCoreProperties.RIGHTS, "rights"));
}
示例2: getImgInfo
import org.apache.tika.sax.TeeContentHandler; //导入依赖的package包/类
public Metadata getImgInfo(String urlStr) throws Exception {
if (StringUtils.isBlank(urlStr)) return null;
URL url = new URL(urlStr);
Metadata md = new Metadata();
StringWriter htmlBuffer = new StringWriter();
Parser parser = new AutoDetectParser();
imageParser= new ImageSavingParser(parser);
TikaInputStream stream = TikaInputStream.get(url, md);
try {
ContentHandler handler = new TeeContentHandler(getHtmlHandler(htmlBuffer));
parser.parse(stream, handler, md, new ParseContext());
} finally {
stream.close();
}
return md;
}
示例3: htmlParserShouldReturnMeta
import org.apache.tika.sax.TeeContentHandler; //导入依赖的package包/类
@Test
public void htmlParserShouldReturnMeta() throws Exception {
try {
new HtmlParser().parse(
stream, new TeeContentHandler(body, link),
metadata, new ParseContext());
} finally {
stream.close();
}
assertEquals("Tika Developers", metadata.get("Author"));
assertEquals("5", metadata.get("refresh"));
assertEquals("51.2312", metadata.get(Geographic.LATITUDE));
assertEquals("-5.1987", metadata.get(Geographic.LONGITUDE));
}
示例4: getMeta
import org.apache.tika.sax.TeeContentHandler; //导入依赖的package包/类
private static ContentHandler getMeta(
ContentHandler ch, Metadata md, Property property, String element) {
Matcher matcher = new CompositeMatcher(
META_XPATH.parse("//meta:" + element),
META_XPATH.parse("//meta:" + element + "//text()"));
ContentHandler branch =
new MatchingContentHandler(new MetadataHandler(md, property), matcher);
return new TeeContentHandler(ch, branch);
}
示例5: getUserDefined
import org.apache.tika.sax.TeeContentHandler; //导入依赖的package包/类
private static ContentHandler getUserDefined(
ContentHandler ch, Metadata md) {
Matcher matcher = new CompositeMatcher(
META_XPATH.parse("//meta:user-defined/@meta:name"),
META_XPATH.parse("//meta:user-defined//text()"));
// eg <meta:user-defined meta:name="Info1">Text1</meta:user-defined> becomes custom:Info1=Text1
ContentHandler branch = new MatchingContentHandler(
new AttributeDependantMetadataHandler(md, "meta:name", Metadata.USER_DEFINED_METADATA_NAME_PREFIX),
matcher);
return new TeeContentHandler(ch, branch);
}
示例6: getStatistic
import org.apache.tika.sax.TeeContentHandler; //导入依赖的package包/类
@Deprecated private static ContentHandler getStatistic(
ContentHandler ch, Metadata md, String name, String attribute) {
Matcher matcher =
META_XPATH.parse("//meta:document-statistic/@meta:"+attribute);
ContentHandler branch = new MatchingContentHandler(
new AttributeMetadataHandler(META_NS, attribute, md, name), matcher);
return new TeeContentHandler(ch, branch);
}
示例7: getMetaInfo
import org.apache.tika.sax.TeeContentHandler; //导入依赖的package包/类
public Metadata getMetaInfo(String urlStr) throws Exception {
if (StringUtils.isBlank(urlStr)) return null;
URL url = new URL(urlStr);
Metadata md = new Metadata();
TikaInputStream stream = TikaInputStream.get(url, md);
try {
ContentHandler handler = new TeeContentHandler();
Parser parser = new AutoDetectParser();
parser.parse(stream, handler, md, new ParseContext());
} finally {
stream.close();
}
return md;
}
示例8: htmlParserShouldReturnTitle
import org.apache.tika.sax.TeeContentHandler; //导入依赖的package包/类
@Test
public void htmlParserShouldReturnTitle() throws Exception {
try {
new HtmlParser().parse(
stream, new TeeContentHandler(body, link),
metadata, new ParseContext());
} finally {
stream.close();
}
assertEquals("Title : Test Indexation Html", metadata.get(TikaCoreProperties.TITLE));
}
示例9: htmlParserShouldReturnAnchor
import org.apache.tika.sax.TeeContentHandler; //导入依赖的package包/类
@Test
public void htmlParserShouldReturnAnchor() throws Exception {
try {
new HtmlParser().parse(
stream, new TeeContentHandler(body, link),
metadata, new ParseContext());
} finally {
stream.close();
}
assertEquals("http://www.apache.org/", href.toString());
assertEquals("test-anchor", name.toString());
}
示例10: htmlParserShouldReturnBody
import org.apache.tika.sax.TeeContentHandler; //导入依赖的package包/类
@Test
public void htmlParserShouldReturnBody() throws Exception {
try {
new HtmlParser().parse(
stream, new TeeContentHandler(body, link),
metadata, new ParseContext());
} finally {
stream.close();
}
String content = body.toString();
assertTrue(content.contains("Test Indexation Html"));
assertTrue(content.contains("Indexation du fichier"));
}
示例11: parseToCache
import org.apache.tika.sax.TeeContentHandler; //导入依赖的package包/类
private void parseToCache(final TikaInputStream tis, final ContentHandler handler, final Metadata metadata,
final ParseContext context, final TesseractOCRConfig config, final boolean inline,
final Writer writer) throws SAXException, IOException, TikaException {
final ContentHandler tee = new TeeContentHandler(handler, new WriteOutContentHandler(writer));
if (inline) {
super.parseInline(tis, new XHTMLContentHandler(tee, metadata), context, config);
} else {
super.parse(tis, tee, metadata, context);
}
}