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.
483 lines
19 KiB
483 lines
19 KiB
//plasmaParserDocument.java
|
|
//------------------------
|
|
//part of YaCy
|
|
//(C) by Michael Peter Christen; mc@anomic.de
|
|
//first published on http://www.anomic.de
|
|
//Frankfurt, Germany, 2005
|
|
//
|
|
//last major change: 24.04.2005
|
|
//
|
|
//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
|
|
//
|
|
//Using this software in any meaning (reading, learning, copying, compiling,
|
|
//running) means that you agree that the Author(s) is (are) not responsible
|
|
//for cost, loss of data or any harm that may be caused directly or indirectly
|
|
//by usage of this softare or this documentation. The usage of this software
|
|
//is on your own risk. The installation and usage (starting/running) of this
|
|
//software may allow other people or application to access your computer and
|
|
//any attached devices and is highly dependent on the configuration of the
|
|
//software which must be done by the user of the software; the author(s) is
|
|
//(are) also not responsible for proper configuration and usage of the
|
|
//software, even if provoked by documentation provided together with
|
|
//the software.
|
|
//
|
|
//Any changes to this file according to the GPL as documented in the file
|
|
//gpl.txt aside this file in the shipment you received can be done to the
|
|
//lines that follows this copyright notice here, but changes must not be
|
|
//done inside the copyright notive above. A re-distribution must contain
|
|
//the intact and unchanged copyright notice.
|
|
//Contributions and changes to the program code must be marked as such.
|
|
|
|
package de.anomic.plasma;
|
|
|
|
import java.io.BufferedInputStream;
|
|
import java.io.ByteArrayInputStream;
|
|
import java.io.File;
|
|
import java.io.FileInputStream;
|
|
import java.io.IOException;
|
|
import java.io.InputStream;
|
|
|
|
import de.anomic.server.serverCachedFileOutputStream;
|
|
import de.anomic.server.serverFileUtils;
|
|
import de.anomic.yacy.yacyURL;
|
|
|
|
import java.util.Arrays;
|
|
import java.util.Date;
|
|
import java.util.HashMap;
|
|
import java.util.Iterator;
|
|
import java.util.LinkedList;
|
|
import java.util.List;
|
|
import java.util.Map;
|
|
import java.util.TreeSet;
|
|
|
|
import de.anomic.htmlFilter.htmlFilterContentScraper;
|
|
import de.anomic.htmlFilter.htmlFilterImageEntry;
|
|
import de.anomic.plasma.parser.Parser;
|
|
|
|
public class plasmaParserDocument {
|
|
|
|
private yacyURL source; // the source url
|
|
private String mimeType; // mimeType as taken from http header
|
|
private String charset; // the charset of the document
|
|
private List<String> keywords; // most resources provide a keyword field
|
|
private StringBuffer title; // a document title, taken from title or h1 tag; shall appear as headline of search result
|
|
private StringBuffer creator; // author or copyright
|
|
private List<String> sections; // if present: more titles/headlines appearing in the document
|
|
private StringBuffer description; // an abstract, if present: short content description
|
|
private Object text; // the clear text, all that is visible
|
|
private Map<yacyURL, String> anchors; // all links embedded as clickeable entities (anchor tags)
|
|
private HashMap<String, htmlFilterImageEntry> 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.
|
|
private Map<yacyURL, String> hyperlinks, audiolinks, videolinks, applinks;
|
|
private Map<String, String> emaillinks;
|
|
private yacyURL favicon;
|
|
private boolean resorted;
|
|
private InputStream textStream;
|
|
private int inboundLinks, outboundLinks; // counters for inbound and outbound links, are counted after calling notifyWebStructure
|
|
|
|
protected plasmaParserDocument(yacyURL location, String mimeType, String charset,
|
|
String[] keywords, String title, String author,
|
|
String[] sections, String abstrct,
|
|
Object text, Map<yacyURL, String> anchors, HashMap<String, htmlFilterImageEntry> images) {
|
|
this.source = location;
|
|
this.mimeType = (mimeType == null) ? "application/octet-stream" : mimeType;
|
|
this.charset = charset;
|
|
this.keywords = (keywords == null) ? new LinkedList<String>() : Arrays.asList(keywords);
|
|
this.title = (title == null) ? new StringBuffer() : new StringBuffer(title);
|
|
this.creator = (author == null) ? new StringBuffer() : new StringBuffer(author);
|
|
this.sections = (sections == null) ? new LinkedList<String>() : Arrays.asList(sections);
|
|
this.description = (abstrct == null) ? new StringBuffer() : new StringBuffer(abstrct);
|
|
this.anchors = (anchors == null) ? new HashMap<yacyURL, String>(0) : anchors;
|
|
this.images = (images == null) ? new HashMap<String, htmlFilterImageEntry>() : images;
|
|
this.hyperlinks = null;
|
|
this.audiolinks = null;
|
|
this.videolinks = null;
|
|
this.applinks = null;
|
|
this.emaillinks = null;
|
|
this.resorted = false;
|
|
this.inboundLinks = -1;
|
|
this.outboundLinks = -1;
|
|
|
|
if (text == null) try {
|
|
this.text = new serverCachedFileOutputStream(Parser.MAX_KEEP_IN_MEMORY_SIZE);
|
|
} catch (IOException e) {
|
|
e.printStackTrace();
|
|
this.text = new StringBuffer();
|
|
} else {
|
|
this.text = text;
|
|
}
|
|
}
|
|
|
|
public plasmaParserDocument(yacyURL location, String mimeType, String charset) {
|
|
this(location, mimeType, charset, null, null, null, null, null, (Object)null, null, null);
|
|
}
|
|
|
|
public plasmaParserDocument(yacyURL location, String mimeType, String charset,
|
|
String[] keywords, String title, String author,
|
|
String[] sections, String abstrct,
|
|
byte[] text, Map<yacyURL, String> anchors, HashMap<String, htmlFilterImageEntry> images) {
|
|
this(location, mimeType, charset, keywords, title, author, sections, abstrct, (Object)text, anchors, images);
|
|
}
|
|
|
|
public plasmaParserDocument(yacyURL location, String mimeType, String charset,
|
|
String[] keywords, String title, String author,
|
|
String[] sections, String abstrct,
|
|
File text, Map<yacyURL, String> anchors, HashMap<String, htmlFilterImageEntry> images) {
|
|
this(location, mimeType, charset, keywords, title, author, sections, abstrct, (Object)text, anchors, images);
|
|
}
|
|
|
|
public plasmaParserDocument(yacyURL location, String mimeType, String charset,
|
|
String[] keywords, String title, String author,
|
|
String[] sections, String abstrct,
|
|
serverCachedFileOutputStream text, Map<yacyURL, String> anchors, HashMap<String, htmlFilterImageEntry> images) {
|
|
this(location, mimeType, charset, keywords, title, author, sections, abstrct, (Object)text, anchors, images);
|
|
}
|
|
|
|
/*
|
|
DC according to rfc 5013
|
|
|
|
* dc_title
|
|
* dc_creator
|
|
* dc_subject
|
|
* dc_description
|
|
* dc_publisher
|
|
dc_contributor
|
|
dc_date
|
|
dc_type
|
|
* dc_format
|
|
* dc_identifier
|
|
* dc_source
|
|
dc_language
|
|
dc_relation
|
|
dc_coverage
|
|
dc_rights
|
|
*/
|
|
|
|
public String dc_title() {
|
|
return title.toString();
|
|
}
|
|
|
|
public String dc_creator() {
|
|
if (creator != null) return creator.toString(); else return new String();
|
|
}
|
|
|
|
public String dc_subject(char separator) {
|
|
// sort out doubles and empty words
|
|
TreeSet<String> hs = new TreeSet<String>();
|
|
String s;
|
|
for (int i = 0; i < this.keywords.size(); i++) {
|
|
if (this.keywords.get(i) == null) continue;
|
|
s = ((String)this.keywords.get(i)).trim();
|
|
if (s.length() > 0) hs.add(s.toLowerCase());
|
|
}
|
|
if (hs.size() == 0) return "";
|
|
// generate a new list
|
|
StringBuffer sb = new StringBuffer(this.keywords.size() * 6);
|
|
Iterator<String> i = hs.iterator();
|
|
while (i.hasNext()) sb.append(i.next()).append(separator);
|
|
return sb.substring(0, sb.length() - 1);
|
|
}
|
|
|
|
public String dc_description() {
|
|
if (description != null) return description.toString(); else return dc_title();
|
|
}
|
|
|
|
public String dc_publisher() {
|
|
// if we don't have a publisher, simply return the host/domain name
|
|
return this.source.getHost();
|
|
}
|
|
|
|
public String dc_format() {
|
|
return this.mimeType;
|
|
}
|
|
|
|
public String dc_identifier() {
|
|
return "yacy.net:" + this.source.hash();
|
|
}
|
|
|
|
public yacyURL dc_source() {
|
|
return this.source;
|
|
}
|
|
|
|
/**
|
|
* @return the supposed charset of this document or <code>null</code> if unknown
|
|
*/
|
|
public String getCharset() {
|
|
return this.charset;
|
|
}
|
|
|
|
public String[] getSectionTitles() {
|
|
if (sections != null) {
|
|
return (String[])sections.toArray(new String[this.sections.size()]);
|
|
} else {
|
|
return new String[] { dc_title() };
|
|
}
|
|
}
|
|
|
|
public InputStream getText() {
|
|
try {
|
|
if (this.text == null) return null;
|
|
|
|
if (this.text instanceof File) {
|
|
this.textStream = new BufferedInputStream(new FileInputStream((File)this.text));
|
|
} else if (this.text instanceof byte[]) {
|
|
this.textStream = new ByteArrayInputStream((byte[])this.text);
|
|
} else if (this.text instanceof serverCachedFileOutputStream) {
|
|
return ((serverCachedFileOutputStream)this.text).getContent();
|
|
}
|
|
return this.textStream;
|
|
} catch (Exception e) {
|
|
e.printStackTrace();
|
|
}
|
|
return null;
|
|
}
|
|
|
|
public byte[] getTextBytes() {
|
|
try {
|
|
if (this.text == null) return new byte[0];
|
|
|
|
if (this.text instanceof File) {
|
|
return serverFileUtils.read((File)this.text);
|
|
} else if (this.text instanceof byte[]) {
|
|
return (byte[])this.text;
|
|
} else if (this.text instanceof serverCachedFileOutputStream) {
|
|
serverCachedFileOutputStream ffbaos = (serverCachedFileOutputStream)this.text;
|
|
if (ffbaos.isFallback()) {
|
|
return serverFileUtils.read(ffbaos.getContent());
|
|
} else {
|
|
return ffbaos.getContentBAOS();
|
|
}
|
|
}
|
|
} catch (Exception e) {
|
|
e.printStackTrace();
|
|
}
|
|
return new byte[0];
|
|
}
|
|
|
|
public long getTextLength() {
|
|
if (this.text == null) return 0;
|
|
if (this.text instanceof File) return ((File)this.text).length();
|
|
else if (this.text instanceof byte[]) return ((byte[])this.text).length;
|
|
else if (this.text instanceof serverCachedFileOutputStream) {
|
|
return ((serverCachedFileOutputStream)this.text).getLength();
|
|
}
|
|
|
|
return -1;
|
|
}
|
|
|
|
public Iterator<StringBuffer> getSentences(boolean pre) {
|
|
if (this.text == null) return null;
|
|
plasmaCondenser.sentencesFromInputStreamEnum e = plasmaCondenser.sentencesFromInputStream(getText(), this.charset);
|
|
e.pre(pre);
|
|
return e;
|
|
}
|
|
|
|
public List<String> getKeywords() {
|
|
return this.keywords;
|
|
}
|
|
|
|
public Map<yacyURL, String> getAnchors() {
|
|
// returns all links embedded as anchors (clickeable entities)
|
|
// this is a url(String)/text(String) map
|
|
return anchors;
|
|
}
|
|
|
|
|
|
// the next three methods provide a calculated view on the getAnchors/getImages:
|
|
|
|
public Map<yacyURL, String> getHyperlinks() {
|
|
// this is a subset of the getAnchor-set: only links to other hyperrefs
|
|
if (!resorted) resortLinks();
|
|
return hyperlinks;
|
|
}
|
|
|
|
public Map<yacyURL, String> getAudiolinks() {
|
|
if (!resorted) resortLinks();
|
|
return this.audiolinks;
|
|
}
|
|
|
|
public Map<yacyURL, String> getVideolinks() {
|
|
if (!resorted) resortLinks();
|
|
return this.videolinks;
|
|
}
|
|
|
|
public HashMap<String, htmlFilterImageEntry> getImages() {
|
|
// returns all links enbedded as pictures (visible in document)
|
|
// this resturns a htmlFilterImageEntry collection
|
|
if (!resorted) resortLinks();
|
|
return images;
|
|
}
|
|
|
|
public Map<yacyURL, String> getApplinks() {
|
|
if (!resorted) resortLinks();
|
|
return this.applinks;
|
|
}
|
|
|
|
public Map<String, String> getEmaillinks() {
|
|
// this is part of the getAnchor-set: only links to email addresses
|
|
if (!resorted) resortLinks();
|
|
return emaillinks;
|
|
}
|
|
|
|
private synchronized void resortLinks() {
|
|
|
|
// extract hyperlinks, medialinks and emaillinks from anchorlinks
|
|
yacyURL url;
|
|
String u;
|
|
int extpos, qpos;
|
|
String ext = null;
|
|
Iterator<Map.Entry<yacyURL, String>> i = anchors.entrySet().iterator();
|
|
hyperlinks = new HashMap<yacyURL, String>();
|
|
videolinks = new HashMap<yacyURL, String>();
|
|
audiolinks = new HashMap<yacyURL, String>();
|
|
applinks = new HashMap<yacyURL, String>();
|
|
emaillinks = new HashMap<String, String>();
|
|
HashMap<String, htmlFilterImageEntry> collectedImages = new HashMap<String, htmlFilterImageEntry>(); // this is a set that is collected now and joined later to the imagelinks
|
|
Map.Entry<yacyURL, String> entry;
|
|
while (i.hasNext()) {
|
|
entry = i.next();
|
|
url = entry.getKey();
|
|
if (url == null) continue;
|
|
u = url.toNormalform(true, false);
|
|
if ((u != null) && (u.startsWith("mailto:"))) {
|
|
emaillinks.put(u.substring(7), entry.getValue());
|
|
} else {
|
|
extpos = u.lastIndexOf(".");
|
|
if (extpos > 0) {
|
|
if (((qpos = u.indexOf("?")) >= 0) && (qpos > extpos)) {
|
|
ext = u.substring(extpos + 1, qpos).toLowerCase();
|
|
} else {
|
|
ext = u.substring(extpos + 1).toLowerCase();
|
|
}
|
|
if (plasmaParser.mediaExtContains(ext)) {
|
|
// this is not a normal anchor, its a media link
|
|
if (plasmaParser.imageExtContains(ext)) {
|
|
htmlFilterContentScraper.addImage(collectedImages, new htmlFilterImageEntry(url, (String) entry.getValue(), -1, -1));
|
|
}
|
|
else if (plasmaParser.audioExtContains(ext)) audiolinks.put(url, (String)entry.getValue());
|
|
else if (plasmaParser.videoExtContains(ext)) videolinks.put(url, (String)entry.getValue());
|
|
else if (plasmaParser.appsExtContains(ext)) applinks.put(url, (String)entry.getValue());
|
|
} else {
|
|
hyperlinks.put(url, (String) entry.getValue());
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
// add image links that we collected from the anchors to the image map
|
|
htmlFilterContentScraper.addAllImages(images, collectedImages);
|
|
|
|
// expand the hyperlinks:
|
|
// we add artificial hyperlinks to the hyperlink set
|
|
// that can be calculated from given hyperlinks and imagelinks
|
|
|
|
hyperlinks.putAll(plasmaParser.allReflinks(images.values()));
|
|
hyperlinks.putAll(plasmaParser.allReflinks(audiolinks.keySet()));
|
|
hyperlinks.putAll(plasmaParser.allReflinks(videolinks.keySet()));
|
|
hyperlinks.putAll(plasmaParser.allReflinks(applinks.keySet()));
|
|
hyperlinks.putAll(plasmaParser.allSubpaths(hyperlinks.keySet()));
|
|
hyperlinks.putAll(plasmaParser.allSubpaths(images.values()));
|
|
hyperlinks.putAll(plasmaParser.allSubpaths(audiolinks.keySet()));
|
|
hyperlinks.putAll(plasmaParser.allSubpaths(videolinks.keySet()));
|
|
hyperlinks.putAll(plasmaParser.allSubpaths(applinks.keySet()));
|
|
|
|
// don't do this again
|
|
this.resorted = true;
|
|
}
|
|
|
|
public void addSubDocument(plasmaParserDocument doc) throws IOException {
|
|
this.sections.addAll(Arrays.asList(doc.getSectionTitles()));
|
|
|
|
if (this.title.length() > 0) this.title.append('\n');
|
|
this.title.append(doc.dc_title());
|
|
|
|
this.keywords.addAll(doc.getKeywords());
|
|
|
|
if (this.description.length() > 0) this.description.append('\n');
|
|
this.description.append(doc.dc_description());
|
|
|
|
if (!(this.text instanceof serverCachedFileOutputStream)) {
|
|
this.text = new serverCachedFileOutputStream(Parser.MAX_KEEP_IN_MEMORY_SIZE);
|
|
serverFileUtils.copy(getText(), (serverCachedFileOutputStream)this.text);
|
|
}
|
|
serverFileUtils.copy(doc.getText(), (serverCachedFileOutputStream)this.text);
|
|
|
|
anchors.putAll(doc.getAnchors());
|
|
htmlFilterContentScraper.addAllImages(images, doc.getImages());
|
|
}
|
|
|
|
/**
|
|
* @return the {@link URL} to the favicon that belongs to the document
|
|
*/
|
|
public yacyURL getFavicon() {
|
|
return this.favicon;
|
|
}
|
|
|
|
/**
|
|
* @param faviconURL the {@link URL} to the favicon that belongs to the document
|
|
*/
|
|
public void setFavicon(yacyURL faviconURL) {
|
|
this.favicon = faviconURL;
|
|
}
|
|
|
|
public void notifyWebStructure(plasmaWebStructure webStructure, plasmaCondenser condenser, Date docDate) {
|
|
Integer[] ioLinks = webStructure.generateCitationReference(this, condenser, docDate); // [outlinksSame, outlinksOther]
|
|
this.inboundLinks = ioLinks[0].intValue();
|
|
this.outboundLinks = ioLinks[1].intValue();
|
|
}
|
|
|
|
public int inboundLinks() {
|
|
assert this.inboundLinks >= 0;
|
|
return (this.inboundLinks < 0) ? 0 : this.inboundLinks;
|
|
}
|
|
|
|
public int outboundLinks() {
|
|
assert this.outboundLinks >= 0;
|
|
return (this.outboundLinks < 0) ? 0 : this.outboundLinks;
|
|
}
|
|
|
|
public void close() {
|
|
// try close the output stream
|
|
if (this.textStream != null) {
|
|
try {
|
|
this.textStream.close();
|
|
} catch (Exception e) {
|
|
/* ignore this */
|
|
} finally {
|
|
this.textStream = null;
|
|
}
|
|
}
|
|
|
|
// delete the temp file
|
|
if ((this.text != null) && (this.text instanceof File)) {
|
|
try {
|
|
((File)this.text).delete();
|
|
} catch (Exception e) {
|
|
/* ignore this */
|
|
} finally {
|
|
this.text = null;
|
|
}
|
|
}
|
|
}
|
|
|
|
protected void finalize() throws Throwable {
|
|
this.close();
|
|
super.finalize();
|
|
}
|
|
|
|
}
|