mirror of
https://github.com/yacy/yacy_search_server.git
synced 2024-09-21 00:00:13 +02:00
f5ca5cea44
the actual data which is fetched from solr. - used the new field options to reduce generic options like getting the load date or the count of search results. should increase overall speed - used the new field options to reduce overhead in the host browser during aquisition of links. - used the field options to make checking of links in crawler faster - if the crawler is paused, the crawl queue is not cleaned
90 lines
3.1 KiB
Java
90 lines
3.1 KiB
Java
package net.yacy.document.parser.augment;
|
|
|
|
import java.io.IOException;
|
|
import java.io.InputStream;
|
|
import java.util.HashSet;
|
|
import java.util.Iterator;
|
|
import java.util.Set;
|
|
|
|
import net.yacy.data.ymark.YMarkUtil;
|
|
import net.yacy.document.AbstractParser;
|
|
import net.yacy.document.Document;
|
|
import net.yacy.document.Parser;
|
|
import net.yacy.document.parser.rdfa.impl.RDFaParser;
|
|
import net.yacy.kelondro.data.meta.DigestURI;
|
|
import net.yacy.kelondro.logging.Log;
|
|
import net.yacy.search.Switchboard;
|
|
|
|
|
|
public class AugmentParser extends AbstractParser implements Parser {
|
|
|
|
RDFaParser rdfaParser;
|
|
|
|
public AugmentParser() {
|
|
super("AugmentParser");
|
|
this.rdfaParser = new RDFaParser();
|
|
|
|
Log.logInfo("AugmentedParser", "augmented parser was initialized");
|
|
|
|
this.SUPPORTED_EXTENSIONS.add("html");
|
|
this.SUPPORTED_EXTENSIONS.add("php");
|
|
this.SUPPORTED_MIME_TYPES.add("text/html");
|
|
this.SUPPORTED_MIME_TYPES.add("text/xhtml+xml");
|
|
this.SUPPORTED_EXTENSIONS.add("html");
|
|
this.SUPPORTED_EXTENSIONS.add("htm");
|
|
}
|
|
|
|
@Override
|
|
public Document[] parse(DigestURI url, String mimeType, String charset, InputStream source) throws Parser.Failure, InterruptedException {
|
|
|
|
Document[] htmlDocs = this.rdfaParser.parse(url, mimeType, charset, source);
|
|
try {
|
|
source.reset();
|
|
} catch (IOException e) {
|
|
Log.logException(e);
|
|
}
|
|
|
|
for (final Document doc : htmlDocs) {
|
|
/* analyze(doc, url, mimeType, charset); // enrich document text */
|
|
parseAndAugment(doc, url, mimeType, charset); // enrich document with additional tags
|
|
}
|
|
return htmlDocs;
|
|
}
|
|
|
|
/* TODO: not implemented yet
|
|
*
|
|
private void analyze(Document origDoc, DigestURI url,
|
|
String mimeType, String charset) {
|
|
// if the magic word appears in the document, perform extra actions.
|
|
if (origDoc.getKeywords().contains("magicword")) {
|
|
String all = "";
|
|
all = "yacylatest";
|
|
// TODO: append content of string all to origDoc.text, maybe use Document.mergeDocuments() to do so
|
|
}
|
|
}
|
|
*/
|
|
private void parseAndAugment(Document origDoc, DigestURI url, @SuppressWarnings("unused") String mimeType, @SuppressWarnings("unused") String charset) {
|
|
|
|
Iterator<net.yacy.kelondro.blob.Tables.Row> it;
|
|
try {
|
|
it = Switchboard.getSwitchboard().tables.iterator("aggregatedtags");
|
|
it = Switchboard.getSwitchboard().tables.orderBy(it, -1, "timestamp_creation").iterator();
|
|
while (it.hasNext()) {
|
|
net.yacy.kelondro.blob.Tables.Row r = it.next();
|
|
if (r.get("url", "").equals(url.toNormalform(false))) {
|
|
Set<String> tags = new HashSet<String>();
|
|
for (String s : YMarkUtil.keysStringToSet(r.get("scitag", ""))) {
|
|
tags.add(s);
|
|
}
|
|
origDoc.addTags(tags);
|
|
}
|
|
}
|
|
|
|
} catch (IOException e) {
|
|
Log.logException(e);
|
|
}
|
|
}
|
|
|
|
|
|
}
|