Distributed Peer-to-Peer Web Search Engine and Intranet Search Appliance
Java decentralizedintranet-searchintranet-search-enginep2pp2p-networkprivacyprivacy-protectionsearch-enginesearchenginewebweb-search-enginewebsearchwebseearch-engine
as requested, disable/remove old swf parser http://forum.yacy-websuche.de/viewtopic.php?f=8&t=5861#p33098
regera4465c97d6b2
diff --git a/.classpath b/.classpathindex ebace4e59..5351922df 100644--- a/.classpath+++ b/.classpath@@ -16,7 +16,6 @@<classpathentry kind="con" path="org.eclipse.jdt.launching.JRE_CONTAINER"/><classpathentry kind="lib" path="lib/commons-logging-1.2.jar"/><classpathentry kind="lib" path="lib/J7Zip-modified.jar"/>- <classpathentry kind="lib" path="lib/webcat-swf-0.1.jar"/><classpathentry kind="lib" path="lib/commons-jxpath-1.3.jar"/><classpathentry kind="lib" path="lib/jsch-0.1.53.jar"/><classpathentry kind="lib" path="lib/jakarta-oro-2.0.8.jar"/>diff --git a/build.xml b/build.xmlindex 14acd7b66..acd74bf6d 100644--- a/build.xml+++ b/build.xml@@ -238,7 +238,6 @@<pathelement location="${lib}/solr-solrj-5.5.2.jar" /><pathelement location="${lib}/spatial4j-0.5.jar" /><pathelement location="${lib}/stax2-api_3.1.4.jar" />- <pathelement location="${lib}/webcat-swf-0.1.jar" /><pathelement location="${lib}/weupnp-0.1.4.jar" /><pathelement location="${lib}/woodstox-core-asl-4.4.1.jar" /><pathelement location="${lib}/xercesImpl.jar" />diff --git a/lib/webcat-swf-0.1.jar b/lib/webcat-swf-0.1.jardeleted file mode 100644index 79ab7eebb..000000000Binary files a/lib/webcat-swf-0.1.jar and /dev/null differdiff --git a/lib/webcat-swf.License b/lib/webcat-swf.Licensedeleted file mode 100644index 24e6084bc..000000000--- a/lib/webcat-swf.License+++ /dev/null@@ -1,7 +0,0 @@-This package is part of WebCAT (http://webcat.sourceforge.net/)--WebCAT was developed at the XLDB group of the Department of Informatics of the Faculty of Sciences of the University of Lisbon in Portugal.--WebCAT was written by Bruno Martins.--WebCAT is released under the BSD License. (http://www.opensource.org/licenses/bsd-license.php)diff --git a/pom.xml b/pom.xmlindex 191ced648..c355bdb03 100644--- a/pom.xml+++ b/pom.xml@@ -591,12 +591,7 @@<artifactId>slf4j-jdk14</artifactId><version>1.7.21</version><type>jar</type>- </dependency>- <dependency>- <groupId>pt.tumba</groupId>- <artifactId>webcat-swf</artifactId>- <version>0.1</version>- </dependency>+ </dependency><dependency><groupId>org.bitlet</groupId><artifactId>weupnp</artifactId>diff --git a/source/net/yacy/document/TextParser.java b/source/net/yacy/document/TextParser.javaindex f483a0f2c..8657071a5 100644--- a/source/net/yacy/document/TextParser.java+++ b/source/net/yacy/document/TextParser.java@@ -56,7 +56,6 @@ import net.yacy.document.parser.rssParser;import net.yacy.document.parser.rtfParser;import net.yacy.document.parser.sevenzipParser;import net.yacy.document.parser.sidAudioParser;-import net.yacy.document.parser.swfParser;import net.yacy.document.parser.tarParser;import net.yacy.document.parser.torrentParser;import net.yacy.document.parser.vcfParser;@@ -106,7 +105,6 @@ public final class TextParser {initParser(new sevenzipParser());initParser(new sidAudioParser());initParser(new svgParser());- initParser(new swfParser());initParser(new tarParser());initParser(new torrentParser());initParser(new vcfParser());diff --git a/source/net/yacy/document/parser/swfParser.java b/source/net/yacy/document/parser/swfParser.javadeleted file mode 100644index f0c7a163f..000000000--- a/source/net/yacy/document/parser/swfParser.java+++ /dev/null@@ -1,113 +0,0 @@-//swfParser.java-//-------------------------//part of YaCy-//(C) by Michael Peter Christen; [email protected]-//first published on http://www.anomic.de-//Frankfurt, Germany, 2005-//-//this file is contributed by Marc Nause-//-// $LastChangedDate$-// $LastChangedRevision$-// $LastChangedBy$-//-//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.IOException;-import java.io.InputStream;-import java.nio.charset.StandardCharsets;--import net.yacy.cora.document.id.DigestURL;-import net.yacy.document.AbstractParser;-import net.yacy.document.Document;-import net.yacy.document.Parser;-import net.yacy.document.VocabularyScraper;-import net.yacy.document.parser.html.ContentScraper;-import pt.tumba.parser.swf.SWF2HTML;--public class swfParser extends AbstractParser implements Parser {-- public swfParser() {- super("Adobe Flash Parser");- this.SUPPORTED_EXTENSIONS.add("swf");- this.SUPPORTED_MIME_TYPES.add("application/x-shockwave-flash");- this.SUPPORTED_MIME_TYPES.add("application/x-shockwave-flash2-preview");- this.SUPPORTED_MIME_TYPES.add("application/futuresplash");- this.SUPPORTED_MIME_TYPES.add("image/vnd.rn-realflash");- }-- /*- * parses the source documents and returns a plasmaParserDocument containing- * all extracted information about the parsed document- */- @Override- public Document[] parse(- final DigestURL location,- final String mimeType,- final String charset,- final VocabularyScraper scraper,- final int timezoneOffset,- final InputStream source)- throws Parser.Failure, InterruptedException- {-- try {- final SWF2HTML swf2html = new SWF2HTML();- String contents = "";- try {- contents = swf2html.convertSWFToHTML(source);- scraperObject = htmlParser.parseToScraper(location, charset, scraper, timezoneOffset, contents, 100);- } catch (final NegativeArraySizeException e) {- throw new Parser.Failure(e.getMessage(), location);- } catch (final IOException e) {- throw new Parser.Failure(e.getMessage(), location);- } catch (final Exception e) {- throw new Parser.Failure(e.getMessage(), location);- }-- // As the result of parsing this function must return a plasmaParserDocument object- ContentScraper htmlscraper = (ContentScraper) this.scraperObject; // shortcut to access ContentScraper methodes- return new Document[]{new Document(- location, // url of the source document- mimeType, // the documents mime type- StandardCharsets.UTF_8.name(), // charset of the document text- this,- htmlscraper.getContentLanguages(),- htmlscraper.getKeywords(),- htmlscraper.getTitles(),- htmlscraper.getAuthor(),- htmlscraper.getPublisher(),- null, // sections- htmlscraper.getDescriptions(),- htmlscraper.getLon(), htmlscraper.getLat(),- htmlscraper.getText(),- htmlscraper.getAnchors(),- htmlscraper.getRSS(),- null, // images- false,- htmlscraper.getDate())};- } catch (final Exception e) {- if (e instanceof InterruptedException) throw (InterruptedException) e;-- // if an unexpected error occures just log the error and raise a new Parser.Failure- final String errorMsg = "Unable to parse the swf document '" + location + "':" + e.getMessage();- //AbstractParser.log.logSevere(errorMsg);- throw new Parser.Failure(errorMsg, location);- }- }--}\ No newline at end of file