You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
yacy_search_server/source/de/anomic/plasma/plasmaParserDocument.java

192 lines
7.0 KiB

/*
* Check4Update is a stand-alone server application that can be used to
* monitor various types of online resources for updates and changes and
* notifies the user if a modification was detected.
*
* Copyright (C) 2005 Martin Thelian
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or (at
* your option) any later version.
*
* This program 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
* General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software Foundation,
* Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* For more information, please email thelian@users.sourceforge.net
*
*/
/* =======================================================================
* Revision Control Information
* $Source: $
* $Author: $
* $Date: $
* $Revision: $
* ======================================================================= */
package de.anomic.plasma;
import java.net.URL;
import java.util.HashMap;
import java.util.Iterator;
import java.util.Map;
public class plasmaParserDocument {
URL location; // the source url
String mimeType; // mimeType as taken from http header
String keywords; // most resources provide a keyword field
String shortTitle; // a shortTitle mostly appears in the window header (border)
String longTitle; // the real title of the document, commonly h1-tags
String[] sections; // if present: more titles/headlines appearing in the document
String abstrct; // an abstract, if present: short content description
byte[] text; // the clear text, all that is visible
Map anchors; // all links embedded as clickeable entities (anchor tags)
Map images; // all visible pictures in document
// the anchors and images - Maps are URL-to-EntityDescription mappings.
// The EntityDescription appear either as visible text in anchors or as alternative
// text in image tags.
Map hyperlinks;
Map medialinks;
Map emaillinks;
public plasmaParserDocument(URL location, String mimeType,
String keywords, String shortTitle, String longTitle,
String[] sections, String abstrct,
byte[] text, Map anchors, Map images) {
this.location = location;
this.mimeType = mimeType;
this.keywords = keywords;
this.shortTitle = shortTitle;
this.longTitle = longTitle;
this.sections = sections;
this.abstrct = abstrct;
this.text = text;
this.anchors = (anchors==null)?new HashMap():anchors;
this.images = (images==null)?new HashMap():images;
this.hyperlinks = null;
this.medialinks = null;
this.emaillinks = null;
}
private String absolutePath(String relativePath) {
try {
return plasmaParser.urlNormalform(new URL(location, relativePath));
} catch (Exception e) {
return "";
}
}
public String getMainShortTitle() {
if (shortTitle != null) return shortTitle; else return longTitle;
}
public String getMainLongTitle() {
if (longTitle != null) return longTitle; else return shortTitle;
}
public String[] getSectionTitles() {
if (sections != null) return sections; else return new String[]{getMainLongTitle()};
}
public String getAbstract() {
if (abstrct != null) return abstrct; else return getMainLongTitle();
}
public byte[] getText() {
// returns only the clear (visible) text (not the source data)
return text;
}
public Map getAnchors() {
// returns all links embedded as anchors (clickeable entities)
return anchors;
}
public Map getImages() {
// returns all links enbedded as pictures (visible iin document)
return images;
}
// the next three methods provide a calculated view on the getAnchors/getImages:
public Map getHyperlinks() {
// this is a subset of the getAnchor-set: only links to other hyperrefs
if (hyperlinks == null) resortLinks();
return hyperlinks;
}
public Map getMedialinks() {
// this is partly subset of getAnchor and getImage: all non-hyperrefs
if (medialinks == null) resortLinks();
return medialinks;
}
public Map getEmaillinks() {
// this is part of the getAnchor-set: only links to email addresses
if (emaillinks == null) resortLinks();
return emaillinks;
}
private synchronized void resortLinks() {
Iterator i;
String url;
int extpos;
String ext;
i = anchors.entrySet().iterator();
hyperlinks = new HashMap();
medialinks = new HashMap();
emaillinks = new HashMap();
Map.Entry entry;
while (i.hasNext()) {
entry = (Map.Entry) i.next();
url = (String) entry.getKey();
if ((url != null) && (url.startsWith("mailto:"))) {
emaillinks.put(url.substring(7), entry.getValue());
} else {
extpos = url.lastIndexOf(".");
String normal;
if (extpos > 0) {
ext = url.substring(extpos).toLowerCase();
normal = plasmaParser.urlNormalform(url);
if (normal != null) {
if (plasmaParser.mediaExt.indexOf(ext.substring(1)) >= 0) {
// this is not an normal anchor, its a media link
medialinks.put(normal, entry.getValue());
} else {
hyperlinks.put(normal, entry.getValue());
}
}
}
}
}
// finally add the images to the medialinks
i = images.entrySet().iterator();
String normal;
while (i.hasNext()) {
entry = (Map.Entry) i.next();
url = (String) entry.getKey();
normal = plasmaParser.urlNormalform(url);
if (normal != null) medialinks.put(normal, entry.getValue()); // avoid NullPointerException
}
expandHyperlinks();
}
public synchronized void expandHyperlinks() {
// we add artificial hyperlinks to the hyperlink set that can be calculated from
// given hyperlinks and imagelinks
hyperlinks.putAll(plasmaParser.allReflinks(hyperlinks));
hyperlinks.putAll(plasmaParser.allReflinks(medialinks));
hyperlinks.putAll(plasmaParser.allSubpaths(hyperlinks));
hyperlinks.putAll(plasmaParser.allSubpaths(medialinks));
}
}