Apache Tika源码研究（七）

frcd

　　tika怎样加载Parser实现类的，怎样根据文档的mime类型调用相应的Parser实现类,本文接着分析
　　先熟悉一下tika的解析类的相关接口和类的UML模型：

　　
　　Parser接口的源码如下：



/**
* Tika parser interface.
*/
public interface Parser extends Serializable {
/**
* Returns the set of media types supported by this parser when used
* with the given parse context.
*
* @since Apache Tika 0.7
* @param context parse context
* @return immutable set of media types
*/
Set getSupportedTypes(ParseContext context);
/**
* Parses a document stream into a sequence of XHTML SAX events.
* Fills in related document metadata in the given metadata object.
*
* The given document stream is consumed but not closed by this method.
* The responsibility to close the stream remains on the caller.
*
* Information about the parsing context can be passed in the context
* parameter. See the parser implementations for the kinds of context
* information they expect.
*
* @since Apache Tika 0.5
* @param stream the document stream (input)
* @param handler handler for the XHTML SAX events (output)
* @param metadata document metadata (input and output)
* @param context parse context
* @throws IOException if the document stream could not be read
* @throws SAXException if the SAX events could not be processed
* @throws TikaException if the document could not be parsed
*/
void parse(
InputStream stream, ContentHandler handler,
Metadata metadata, ParseContext context)
throws IOException, SAXException, TikaException;
}
　　该接口只提供void parse(InputStream stream, ContentHandler handler,Metadata metadata, ParseContext context)方法供其他类调用
　　抽象类AbstractParser实现了Parser接口，其源码如下：



/**
* Abstract base class for new parsers. This method implements the old
* deprecated parse method so subclasses won't have to.
*
* @since Apache Tika 0.10
*/
public abstract class AbstractParser implements Parser {
/**
* Serial version UID.
*/
private static final long serialVersionUID = 7186985395903074255L;
/**
* Calls the
* {@link Parser#parse(InputStream, ContentHandler, Metadata, ParseContext)}
* method with an empty {@link ParseContext}. This method exists as a
* leftover from Tika 0.x when the three-argument parse() method still
* existed in the {@link Parser} interface. No new code should call this
* method anymore, it's only here for backwards compatibility.
*
* @deprecated use the {@link Parser#parse(InputStream, ContentHandler, Metadata, ParseContext)} method instead
*/
public void parse(
InputStream stream, ContentHandler handler, Metadata metadata)
throws IOException, SAXException, TikaException {
parse(stream, handler, metadata, new ParseContext());
}
}
　　
　　新增void parse(InputStream stream, ContentHandler handler, Metadata metadata)方法，提供模板方法功能
　　下面接着贴出CompositeParser的源码，它继承自抽象类AbstractParser



/**
* Composite parser that delegates parsing tasks to a component parser
* based on the declared content type of the incoming document. A fallback
* parser is defined for cases where a parser for the given content type is
* not available.
*/
public class CompositeParser extends AbstractParser {
/** Serial version UID */
private static final long serialVersionUID = 2192845797749627824L;
/**
* Media type registry.
*/
private MediaTypeRegistry registry;
/**
* List of component parsers.
*/
private List parsers;
/**
* The fallback parser, used when no better parser is available.
*/
private Parser fallback = new EmptyParser();
public CompositeParser(MediaTypeRegistry registry, List parsers) {
this.parsers = parsers;
this.registry = registry;
}
public CompositeParser(MediaTypeRegistry registry, Parser... parsers) {
this(registry, Arrays.asList(parsers));
}
public CompositeParser() {
this(new MediaTypeRegistry());
}
public Map getParsers(ParseContext context) {
Map map = new HashMap();
for (Parser parser : parsers) {
for (MediaType type : parser.getSupportedTypes(context)) {
map.put(registry.normalize(type), parser);
}
}
return map;
}
/**
* Utility method that goes through all the component parsers and finds
* all media types for which more than one parser declares support. This
* is useful in tracking down conflicting parser definitions.
*
* @since Apache Tika 0.10
* @see TIKA-660
* @param context parsing context
* @return media types that are supported by at least two component parsers
*/
public Map findDuplicateParsers(
ParseContext context) {
Map types = new HashMap();
Map duplicates =
new HashMap();
for (Parser parser : parsers) {
for (MediaType type : parser.getSupportedTypes(context)) {
MediaType canonicalType = registry.normalize(type);
if (types.containsKey(canonicalType)) {
List list = duplicates.get(canonicalType);
if (list == null) {
list = new ArrayList();
list.add(types.get(canonicalType));
duplicates.put(canonicalType, list);
}
list.add(parser);
} else {
types.put(canonicalType, parser);
}
}
}
return duplicates;
}
/**
* Returns the media type registry used to infer type relationships.
*
* @since Apache Tika 0.8
* @return media type registry
*/
public MediaTypeRegistry getMediaTypeRegistry() {
return registry;
}
/**
* Sets the media type registry used to infer type relationships.
*
* @since Apache Tika 0.8
* @param registry media type registry
*/
public void setMediaTypeRegistry(MediaTypeRegistry registry) {
this.registry = registry;
}
/**
* Returns the component parsers.
*
* @return component parsers, keyed by media type
*/
public Map getParsers() {
return getParsers(new ParseContext());
}
/**
* Sets the component parsers.
*
* @param parsers component parsers, keyed by media type
*/
public void setParsers(Map parsers) {
this.parsers = new ArrayList(parsers.size());
for (Map.Entry entry : parsers.entrySet()) {
this.parsers.add(ParserDecorator.withTypes(
entry.getValue(), Collections.singleton(entry.getKey())));
}
}
/**
* Returns the fallback parser.
*
* @return fallback parser
*/
public Parser getFallback() {
return fallback;
}
/**
* Sets the fallback parser.
*
* @param fallback fallback parser
*/
public void setFallback(Parser fallback) {
this.fallback = fallback;
}
/**
* Returns the parser that best matches the given metadata. By default
* looks for a parser that matches the content type metadata property,
* and uses the fallback parser if a better match is not found. The
* type hierarchy information included in the configured media type
* registry is used when looking for a matching parser instance.
*
* Subclasses can override this method to provide more accurate
* parser resolution.
*
* @param metadata document metadata
* @return matching parser
*/
protected Parser getParser(Metadata metadata) {
return getParser(metadata, new ParseContext());
}
protected Parser getParser(Metadata metadata, ParseContext context) {
Map map = getParsers(context);
MediaType type = MediaType.parse(metadata.get(Metadata.CONTENT_TYPE));
if (type != null) {
// We always work on the normalised, canonical form
type = registry.normalize(type);
}
while (type != null) {
// Try finding a parser for the type
Parser parser = map.get(type);
if (parser != null) {
return parser;
}
// Failing that, try for the parent of the type
type = registry.getSupertype(type);
}
return fallback;
}
public Set getSupportedTypes(ParseContext context) {
return getParsers(context).keySet();
}
/**
* Delegates the call to the matching component parser.
*
* Potential {@link RuntimeException}s, {@link IOException}s and
* {@link SAXException}s unrelated to the given input stream and content
* handler are automatically wrapped into {@link TikaException}s to better
* honor the {@link Parser} contract.
*/
public void parse(
InputStream stream, ContentHandler handler,
Metadata metadata, ParseContext context)
throws IOException, SAXException, TikaException {
Parser parser = getParser(metadata);
TemporaryResources tmp = new TemporaryResources();
try {
TikaInputStream taggedStream = TikaInputStream.get(stream, tmp);
TaggedContentHandler taggedHandler = new TaggedContentHandler(handler);
try {
parser.parse(taggedStream, taggedHandler, metadata, context);
} catch (RuntimeException e) {
throw new TikaException(
"Unexpected RuntimeException from " + parser, e);
} catch (IOException e) {
taggedStream.throwIfCauseOf(e);
throw new TikaException(
"TIKA-198: Illegal IOException from " + parser, e);
} catch (SAXException e) {
taggedHandler.throwIfCauseOf(e);
throw new TikaException(
"TIKA-237: Illegal SAXException from " + parser, e);
}
} finally {
tmp.dispose();
}
}
}
　　该类的注释很清楚，相当于将解析任务委托给了其他的解析组件，而自身提供的parser方法供其他类调用
　　且分析CompositeParser类是怎样将解析任务委托给其他解析组件的，关键是parser方法的这行代码 Parser parser = getParser(metadata);
　　它调用了下面的方法：



    protected Parser getParser(Metadata metadata) {
return getParser(metadata, new ParseContext());
}
protected Parser getParser(Metadata metadata, ParseContext context) {
Map map = getParsers(context);
MediaType type = MediaType.parse(metadata.get(Metadata.CONTENT_TYPE));
if (type != null) {
// We always work on the normalised, canonical form
type = registry.normalize(type);
}
while (type != null) {
// Try finding a parser for the type
Parser parser = map.get(type);
if (parser != null) {
return parser;
}
// Failing that, try for the parent of the type
type = registry.getSupertype(type);
}
return fallback;
}
　　
　　执行流程是首先获取mime类型跟相应的Parser实现类的映射Map ，然后根据Metadata的Metadata.CONTENT_TYPE属性得到MediaType类型，最后从Map获取相应的Parser实现类
　　上面的代码Map map = getParsers(context)是获取Map映射



public Map getParsers(ParseContext context) {
Map map = new HashMap();
for (Parser parser : parsers) {
for (MediaType type : parser.getSupportedTypes(context)) {
map.put(registry.normalize(type), parser);
}
}
return map;
}
　　
　　即根据构造方法初始化的List parsers组件集合，这里注意的是如果该组件类集合中的成员之一为CompositeParser本身的类型，则该成员提供的可以支持的mime类型同时又来自于该成员的解析组件集合（这里也许是CompositeParser命名的原因，这里用到了Composite模式），我们可以看到它Set getSupportedTypes(ParseContext context)方法：



    public Set getSupportedTypes(ParseContext context) {
return getParsers(context).keySet();
}
　　Composite模式的简要UML模型图如下：

　　我们接下来分析DefaultParser的源码，该类继承自CompositeParser类，用于初始化CompositeParser类的相关成员变量



/**
* A composite parser based on all the {@link Parser} implementations
* available through the
* {@link javax.imageio.spi.ServiceRegistry service provider mechanism}.
*
* @since Apache Tika 0.8
*/
public class DefaultParser extends CompositeParser {
/** Serial version UID */
private static final long serialVersionUID = 3612324825403757520L;
/**
* Finds all statically loadable parsers and sort the list by name,
* rather than discovery order. CompositeParser takes the last
* parser for any given media type, so put the Tika parsers first
* so that non-Tika (user supplied) parsers can take precedence.
*
* @param loader service loader
* @return ordered list of statically loadable parsers
*/
private static List getDefaultParsers(ServiceLoader loader) {
List parsers =
loader.loadStaticServiceProviders(Parser.class);
Collections.sort(parsers, new Comparator() {
public int compare(Parser p1, Parser p2) {
String n1 = p1.getClass().getName();
String n2 = p2.getClass().getName();
boolean t1 = n1.startsWith("org.apache.tika.");
boolean t2 = n2.startsWith("org.apache.tika.");
if (t1 == t2) {
return n1.compareTo(n2);
} else if (t1) {
return -1;
} else {
return 1;
}
}
});
return parsers;
}
private transient final ServiceLoader loader;
public DefaultParser(MediaTypeRegistry registry, ServiceLoader loader) {
super(registry, getDefaultParsers(loader));
this.loader = loader;
}
public DefaultParser(MediaTypeRegistry registry, ClassLoader loader) {
this(registry, new ServiceLoader(loader));
}
public DefaultParser(ClassLoader loader) {
this(MediaTypeRegistry.getDefaultRegistry(), new ServiceLoader(loader));
}
public DefaultParser(MediaTypeRegistry registry) {
this(registry, new ServiceLoader());
}
public DefaultParser() {
this(MediaTypeRegistry.getDefaultRegistry());
}
@Override
public Map getParsers(ParseContext context) {
Map map = super.getParsers(context);
if (loader != null) {
// Add dynamic parser service (they always override static ones)
MediaTypeRegistry registry = getMediaTypeRegistry();
for (Parser parser
: loader.loadDynamicServiceProviders(Parser.class)) {
for (MediaType type : parser.getSupportedTypes(context)) {
map.put(registry.normalize(type), parser);
}
}
}
return map;
}
}
　　
　　该类主要是为基类初始化MediaTypeRegistry registry成员与List parsers成员，它本身并没有覆盖void parse(InputStream stream, ContentHandler handler,Metadata metadata, ParseContext context)方法，为的是执行基类的方法（根据mime类型执行具体parser类的parse方法）
　　最后来分析AutoDetectParser类的源码，它也继承自CompositeParser类：



public class AutoDetectParser extends CompositeParser {
/** Serial version UID */
private static final long serialVersionUID = 6110455808615143122L;
/**
* The type detector used by this parser to auto-detect the type
* of a document.
*/
private Detector detector; // always set in the constructor
/**
* Creates an auto-detecting parser instance using the default Tika
* configuration.
*/
public AutoDetectParser() {
this(TikaConfig.getDefaultConfig());
}
public AutoDetectParser(Detector detector) {
this(TikaConfig.getDefaultConfig());
setDetector(detector);
}
/**
* Creates an auto-detecting parser instance using the specified set of parser.
* This allows one to create a Tika configuration where only a subset of the
* available parsers have their 3rd party jars included, as otherwise the
* use of the default TikaConfig will throw various "ClassNotFound" exceptions.
*
* @param detector Detector to use
* @param parsers
*/
public AutoDetectParser(Parser...parsers) {
this(new DefaultDetector(), parsers);
}
public AutoDetectParser(Detector detector, Parser...parsers) {
super(MediaTypeRegistry.getDefaultRegistry(), parsers);
setDetector(detector);
}
public AutoDetectParser(TikaConfig config) {
super(config.getMediaTypeRegistry(), config.getParser());
setDetector(config.getDetector());
}
/**
* Returns the type detector used by this parser to auto-detect the type
* of a document.
*
* @return type detector
* @since Apache Tika 0.4
*/
public Detector getDetector() {
return detector;
}
/**
* Sets the type detector used by this parser to auto-detect the type
* of a document.
*
* @param detector type detector
* @since Apache Tika 0.4
*/
public void setDetector(Detector detector) {
this.detector = detector;
}
public void parse(
InputStream stream, ContentHandler handler,
Metadata metadata, ParseContext context)
throws IOException, SAXException, TikaException {
TemporaryResources tmp = new TemporaryResources();
try {
TikaInputStream tis = TikaInputStream.get(stream, tmp);
// Automatically detect the MIME type of the document
MediaType type = detector.detect(tis, metadata);
metadata.set(Metadata.CONTENT_TYPE, type.toString());
// TIKA-216: Zip bomb prevention
SecureContentHandler sch = new SecureContentHandler(handler, tis);
try {
// Parse the document
super.parse(tis, sch, metadata, context);
} catch (SAXException e) {
// Convert zip bomb exceptions to TikaExceptions
                sch.throwIfCauseOf(e);
throw e;
}
} finally {
tmp.dispose();
}
}
public void parse(
InputStream stream, ContentHandler handler, Metadata metadata)
throws IOException, SAXException, TikaException {
ParseContext context = new ParseContext();
context.set(Parser.class, this);
parse(stream, handler, metadata, context);
}
}
　　
　　该类也初始化基类的MediaTypeRegistry registry成员与List parsers成员，不过这里的List parsers成员有TikaConfig类提供，后者默认提供的Parser实现类为DefaultParser
　　它的void parse(InputStream stream, ContentHandler handler,Metadata metadata, ParseContext context)方法首先检测文档的mime类型，然后将解析处理委托给CompositeParser基类执行，自身对外提供接口
　　所以整个解析的流程是
　　一、AutoDetectParser的parse方法：首先检测文件的mime类型，然后将解析任务交给基类CompositeParser的parse方法
　　二、AutoDetectParser的基类CompositeParser的parse方法：根据参数里面的mime类型获取解析类DefaultParser（支持所有已经注册的mime类型，由List parsers成员提供）
　　三、调用DefaultParser的parse方法（DefaultParser默认执行父类的parse方法），即基类CompositeParser的parse方法，根据参数里面的mime类型获取具体解析类
　　四、最后执行具体解析类的parse方法
　　
　　这里第一次AutoDetectParser初始化基类CompositeParser的parser组件集合是DefaultParser，基类CompositeParser的parse方法委托给DefaultParser
　　第二次DefaultParser初始化基类的CompositeParser的parser组件集合是具体的parser实现类集合，基类CompositeParser的parse方法委托给具体的parser实现类
　　这里体现的是Composite模式的运用。