yacy_search_server/source/net/yacy/document/AbstractParser.java

103 lines
3.2 KiB
Java
Raw Normal View History

/**
* Parser
* Copyright 2010 by Michael Peter Christen, mc@yacy.net, Frankfurt am Main, Germany
* First released 29.6.2010 at http://yacy.net
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public License
* along with this program in the file lgpl21.txt
* If not, see <http://www.gnu.org/licenses/>.
*/
// this is a new implementation of the parser interface using multiple documents as result set
// and a much simpler method structure with only one single parser method to implement
package net.yacy.document;
import java.util.ArrayList;
import java.util.HashSet;
import java.util.LinkedHashSet;
import java.util.List;
import java.util.Set;
import net.yacy.cora.util.ConcurrentLog;
public abstract class AbstractParser implements Parser {
public final static ConcurrentLog log = new ConcurrentLog("PARSER");
// use LinkedHashSet to maintain order, as in TextParser.initParser() supported_Extensions are mapped to 1. mime-type
// means also, add the most common mime first, which is mapped to all extension
protected final Set<String> SUPPORTED_MIME_TYPES = new LinkedHashSet<String>();
protected final Set<String> SUPPORTED_EXTENSIONS = new HashSet<String>();
private final String name;
/**
* initialize a parser with a name
* @param name
*/
public AbstractParser(final String name) {
this.name = name;
}
*) plasmaHTCache: - method loadResourceContent defined as deprecated. Please do not use this function to avoid OutOfMemory Exceptions when loading large files - new function getResourceContentStream to get an inputstream of a cache file - new function getResourceContentLength to get the size of a cached file *) httpc.java: - Bugfix: resource content was loaded into memory even if this was not requested *) Crawler: - new option to hold loaded resource content in memory - adding option to use the worker class without the worker pool (needed by the snippet fetcher) *) plasmaSnippetCache - snippet loader does not use a crawl-worker from pool but uses a newly created instance to avoid blocking by normal crawling activity. - now operates on streams instead of byte arrays to avoid OutOfMemory Exceptions when operating on large files - snippet loader now forces the crawl-worker to keep the loaded resource in memory to avoid IO *) plasmaCondenser: adding new function getWords that can directly operate on input streams *) Parsers - keep resource in memory whenever possible (to avoid IO) - when parsing from stream the content length must be passed to the parser function now. this length value is needed by the parsers to decide if the parsed resource content is to large to hold it in memory and must be stored to file - AbstractParser.java: new function to pass the contentLength of a resource to the parsers git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@2701 6c8d7289-2bf4-0310-a012-ef5d649a1542
2006-10-03 13:05:48 +02:00
/**
* return the name of the parser
*) plasmaHTCache: - method loadResourceContent defined as deprecated. Please do not use this function to avoid OutOfMemory Exceptions when loading large files - new function getResourceContentStream to get an inputstream of a cache file - new function getResourceContentLength to get the size of a cached file *) httpc.java: - Bugfix: resource content was loaded into memory even if this was not requested *) Crawler: - new option to hold loaded resource content in memory - adding option to use the worker class without the worker pool (needed by the snippet fetcher) *) plasmaSnippetCache - snippet loader does not use a crawl-worker from pool but uses a newly created instance to avoid blocking by normal crawling activity. - now operates on streams instead of byte arrays to avoid OutOfMemory Exceptions when operating on large files - snippet loader now forces the crawl-worker to keep the loaded resource in memory to avoid IO *) plasmaCondenser: adding new function getWords that can directly operate on input streams *) Parsers - keep resource in memory whenever possible (to avoid IO) - when parsing from stream the content length must be passed to the parser function now. this length value is needed by the parsers to decide if the parsed resource content is to large to hold it in memory and must be stored to file - AbstractParser.java: new function to pass the contentLength of a resource to the parsers git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@2701 6c8d7289-2bf4-0310-a012-ef5d649a1542
2006-10-03 13:05:48 +02:00
*/
@Override
public String getName() {
return this.name;
*) plasmaHTCache: - method loadResourceContent defined as deprecated. Please do not use this function to avoid OutOfMemory Exceptions when loading large files - new function getResourceContentStream to get an inputstream of a cache file - new function getResourceContentLength to get the size of a cached file *) httpc.java: - Bugfix: resource content was loaded into memory even if this was not requested *) Crawler: - new option to hold loaded resource content in memory - adding option to use the worker class without the worker pool (needed by the snippet fetcher) *) plasmaSnippetCache - snippet loader does not use a crawl-worker from pool but uses a newly created instance to avoid blocking by normal crawling activity. - now operates on streams instead of byte arrays to avoid OutOfMemory Exceptions when operating on large files - snippet loader now forces the crawl-worker to keep the loaded resource in memory to avoid IO *) plasmaCondenser: adding new function getWords that can directly operate on input streams *) Parsers - keep resource in memory whenever possible (to avoid IO) - when parsing from stream the content length must be passed to the parser function now. this length value is needed by the parsers to decide if the parsed resource content is to large to hold it in memory and must be stored to file - AbstractParser.java: new function to pass the contentLength of a resource to the parsers git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@2701 6c8d7289-2bf4-0310-a012-ef5d649a1542
2006-10-03 13:05:48 +02:00
}
/**
* each parser must define a set of supported mime types
* @return a set of mime type strings that are supported
*/
@Override
public Set<String> supportedMimeTypes() {
return this.SUPPORTED_MIME_TYPES;
}
/**
* each parser must define a set of supported file extensions
* @return a set of file name extensions that are supported
*/
@Override
public Set<String> supportedExtensions() {
return this.SUPPORTED_EXTENSIONS;
}
/**
* check equivalence of parsers; this simply tests equality of parser names
* @param o
* @return
*/
@Override
public boolean equals(final Object o) {
return getName().equals(((Parser) o).getName());
}
/**
* the hash code of a parser
* @return the hash code of the parser name string
*/
@Override
public int hashCode() {
return getName().hashCode();
}
public static List<String> singleList(String t) {
List<String> c = new ArrayList<String>(1);
if (t != null) c.add(t);
return c;
}
}