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/net/yacy/document/parser/vcfParser.java

279 lines
13 KiB

//vcfParser.java
//------------------------
//part of YaCy
//(C) by Michael Peter Christen; mc@yacy.net
//first published on http://www.anomic.de
//Frankfurt, Germany, 2005
//
//this file is contributed by Martin Thelian
//
// $LastChangedDate$
// $LastChangedRevision$
// $LastChangedBy$
//
//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
package net.yacy.document.parser;
import java.io.BufferedReader;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.MalformedURLException;
import java.util.HashMap;
import java.util.HashSet;
import java.util.Iterator;
import java.util.LinkedList;
import java.util.Set;
import net.yacy.cora.document.MultiProtocolURI;
import net.yacy.document.AbstractParser;
import net.yacy.document.Document;
import net.yacy.document.Idiom;
import net.yacy.document.ParserException;
import net.yacy.kelondro.order.Base64Order;
/**
* Vcard specification: http://www.imc.org/pdi/vcard-21.txt
* @author theli
*
*/
public class vcfParser extends AbstractParser implements Idiom {
/**
* a list of mime types that are supported by this parser class
* @see #getSupportedMimeTypes()
*
* TODO: support of x-mozilla-cpt and x-mozilla-html tags
*/
public static final Set<String> SUPPORTED_MIME_TYPES = new HashSet<String>();
public static final Set<String> SUPPORTED_EXTENSIONS = new HashSet<String>();
static {
SUPPORTED_EXTENSIONS.add("vcf");
SUPPORTED_MIME_TYPES.add("text/x-vcard");
SUPPORTED_MIME_TYPES.add("application/vcard");
SUPPORTED_MIME_TYPES.add("application/x-versit");
SUPPORTED_MIME_TYPES.add("text/x-versit");
SUPPORTED_MIME_TYPES.add("text/x-vcalendar");
}
public vcfParser() {
super("vCard Parser");
}
public Set<String> supportedMimeTypes() {
return SUPPORTED_MIME_TYPES;
}
public Set<String> supportedExtensions() {
return SUPPORTED_EXTENSIONS;
}
public Document parse(final MultiProtocolURI url, final String mimeType, final String charset, final InputStream source) throws ParserException, InterruptedException {
try {
final StringBuilder parsedTitle = new StringBuilder();
final StringBuilder parsedDataText = new StringBuilder();
final HashMap<String, String> parsedData = new HashMap<String, String>();
final HashMap<MultiProtocolURI, String> anchors = new HashMap<MultiProtocolURI, String>();
final LinkedList<String> parsedNames = new LinkedList<String>();
boolean useLastLine = false;
int lineNr = 0;
String line = null;
final BufferedReader inputReader = (charset!=null)
? new BufferedReader(new InputStreamReader(source,charset))
: new BufferedReader(new InputStreamReader(source));
while (true) {
// check for interruption
checkInterruption();
// getting the next line
if (!useLastLine) {
line = inputReader.readLine();
} else {
useLastLine = false;
}
if (line == null) break;
else if (line.length() == 0) continue;
lineNr++;
final int pos = line.indexOf(":");
if (pos != -1) {
final String key = line.substring(0,pos).trim().toUpperCase();
String value = line.substring(pos+1).trim();
String encoding = null;
final String[] keyParts = key.split(";");
if (keyParts.length > 1) {
for (int i=0; i < keyParts.length; i++) {
if (keyParts[i].toUpperCase().startsWith("ENCODING")) {
encoding = keyParts[i].substring("ENCODING".length()+1);
} else if (keyParts[i].toUpperCase().startsWith("QUOTED-PRINTABLE")) {
encoding = "QUOTED-PRINTABLE";
} else if (keyParts[i].toUpperCase().startsWith("BASE64")) {
encoding = "BASE64";
}
}
if (encoding != null) {
try {
if (encoding.equalsIgnoreCase("QUOTED-PRINTABLE")) {
// if the value has multiple lines ...
if (line.endsWith("=")) {
do {
value = value.substring(0,value.length()-1);
line = inputReader.readLine();
if (line == null) break;
value += line;
} while (line.endsWith("="));
}
value = decodeQuotedPrintable(value);
} else if (encoding.equalsIgnoreCase("base64")) {
do {
line = inputReader.readLine();
if (line == null) break;
if (line.indexOf(":")!= -1) {
// we have detected an illegal block end of the base64 data
useLastLine = true;
}
if (!useLastLine) value += line.trim();
else break;
} while (line.length()!=0);
value = Base64Order.standardCoder.decodeString(value);
}
} catch (final Exception ey) {
// Encoding error: This could occure e.g. if the base64 doesn't
// end with an empty newline
//
// We can simply ignore it.
}
}
}
if (key.equalsIgnoreCase("END")) {
String name = null, title = null;
// using the name of the current version as section headline
if (parsedData.containsKey("FN")) {
parsedNames.add(name = parsedData.get("FN"));
} else if (parsedData.containsKey("N")) {
parsedNames.add(name = parsedData.get("N"));
} else {
parsedNames.add(name = "unknown name");
}
// getting the vcard title
if (parsedData.containsKey("TITLE")) {
parsedNames.add(title = parsedData.get("TITLE"));
}
if (parsedTitle.length() > 0) parsedTitle.append(", ");
parsedTitle.append((title==null)?name:name + " - " + title);
// looping through the properties and add there values to
// the text representation of the vCard
final Iterator<String> iter = parsedData.values().iterator();
while (iter.hasNext()) {
value = iter.next();
parsedDataText.append(value).append("\r\n");
}
parsedDataText.append("\r\n");
parsedData.clear();
} else if (key.toUpperCase().startsWith("URL")) {
try {
final MultiProtocolURI newURL = new MultiProtocolURI(value);
anchors.put(newURL, newURL.toString());
//parsedData.put(key,value);
} catch (final MalformedURLException ex) {/* ignore this */}
} else if (
!key.equalsIgnoreCase("BEGIN") &&
!key.equalsIgnoreCase("END") &&
!key.equalsIgnoreCase("VERSION") &&
!key.toUpperCase().startsWith("LOGO") &&
!key.toUpperCase().startsWith("PHOTO") &&
!key.toUpperCase().startsWith("SOUND") &&
!key.toUpperCase().startsWith("KEY") &&
!key.toUpperCase().startsWith("X-")
) {
// value = value.replaceAll(";","\t");
if ((value.length() > 0)) parsedData.put(key, value);
}
} else {
if (theLogger.isFinest()) this.theLogger.logFinest("Invalid data in vcf file" +
"\n\tURL: " + url +
"\n\tLine: " + line +
"\n\tLine-Nr: " + lineNr);
}
}
final String[] sections = parsedNames.toArray(new String[parsedNames.size()]);
final byte[] text = parsedDataText.toString().getBytes();
final Document theDoc = new Document(
url, // url of the source document
mimeType, // the documents mime type
null, // charset
null, // set of languages
null, // a list of extracted keywords
parsedTitle.toString(), // a long document title
"", // TODO: AUTHOR
"", // the publisher
sections, // an array of section headlines
"vCard", // an abstract
text, // the parsed document text
anchors, // a map of extracted anchors
null, // a treeset of image URLs
false);
return theDoc;
} catch (final Exception e) {
if (e instanceof InterruptedException) throw (InterruptedException) e;
if (e instanceof ParserException) throw (ParserException) e;
throw new ParserException("Unexpected error while parsing vcf resource. " + e.getMessage(),url);
}
}
@Override
public void reset() {
*) 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
18 years ago
// Nothing todo here at the moment
super.reset();
}
public static final String decodeQuotedPrintable(final String s) {
if (s == null) return null;
final byte[] b = s.getBytes();
final StringBuilder sb = new StringBuilder();
for (int i = 0; i < b.length; i++) {
final int c = b[i];
if (c == '=') {
try {
final int u = Character.digit((char) b[++i], 16);
final int l = Character.digit((char) b[++i], 16);
if (u == -1 || l == -1) throw new RuntimeException("bad quoted-printable encoding");
sb.append((char) ((u << 4) + l));
} catch (final ArrayIndexOutOfBoundsException e) {
throw new RuntimeException("bad quoted-printable encoding");
}
} else {
sb.append((char) c);
}
}
return sb.toString();
}
}