Mirrors
/
yacy_search_server
mirror of https://github.com/yacy/yacy_search_server.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

removed 7Zip parser because the old library could not be replaced by a maven repository

pull/583/head
Michael Peter Christen 2023-07-27 23:11:27 +02:00
parent 5afcba162b
commit 92dad3ed49
4 changed files with 10 additions and 290 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
.gitignore vendored
View File

@ -28,4 +28,5 @@ yacy.log
/.settings/
/.classpath
/.project
/ivy
/ivy
/lib

BIN
lib/J7Zip-modified-1.0.2.jar
View File

Binary file not shown.

18
source/net/yacy/document/TextParser.java
View File

@ -51,7 +51,6 @@ import net.yacy.document.parser.docParser;
import net.yacy.document.parser.genericParser;
import net.yacy.document.parser.gzipParser;
import net.yacy.document.parser.gzipParser.GZIPOpeningStreamException;
import net.yacy.document.parser.html.TagValency;
import net.yacy.document.parser.htmlParser;
import net.yacy.document.parser.linkScraperParser;
import net.yacy.document.parser.mmParser;
@ -62,7 +61,6 @@ import net.yacy.document.parser.pptParser;
import net.yacy.document.parser.psParser;
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.tarParser;
import net.yacy.document.parser.torrentParser;
@ -70,6 +68,7 @@ import net.yacy.document.parser.vcfParser;
import net.yacy.document.parser.vsdParser;
import net.yacy.document.parser.xlsParser;
import net.yacy.document.parser.zipParser;
import net.yacy.document.parser.html.TagValency;
import net.yacy.document.parser.images.genericImageParser;
import net.yacy.document.parser.images.metadataImageParser;
import net.yacy.document.parser.images.svgParser;
@ -115,7 +114,6 @@ public final class TextParser {
initParser(new psParser());
initParser(new rssParser());
initParser(new rtfParser());
initParser(new sevenzipParser());
initParser(new sidAudioParser());
initParser(new svgParser());
initParser(new tarParser());
@ -404,7 +402,7 @@ public final class TextParser {
public static Document[] parseSource(
final DigestURL location,
String mimeType,
final String mimeType,
final String charset,
final TagValency defaultValency,
final Set<String> valencySwitchTagNames,
@ -438,7 +436,7 @@ public final class TextParser {
*/
public static Document[] parseWithLimits(
final DigestURL location,
String mimeType,
final String mimeType,
final String charset,
final TagValency defaultValency,
final Set<String> valencySwitchTagNames,
@ -446,8 +444,8 @@ public final class TextParser {
final int depth,
final long contentLength,
final InputStream sourceStream,
int maxLinks,
long maxBytes) throws Parser.Failure{
final int maxLinks,
final long maxBytes) throws Parser.Failure{
return parseSource(location, mimeType, charset, defaultValency, valencySwitchTagNames, new VocabularyScraper(), timezoneOffset, depth, contentLength,
sourceStream, maxLinks, maxBytes);
}
@ -471,9 +469,9 @@ public final class TextParser {
* @throws Parser.Failure when the parser processing failed
*/
public static Document[] parseWithLimits(
final DigestURL location, String mimeType, final String charset,
final int timezoneOffset, final int depth, final long contentLength, final InputStream sourceStream, int maxLinks,
long maxBytes) throws Parser.Failure{
final DigestURL location, final String mimeType, final String charset,
final int timezoneOffset, final int depth, final long contentLength, final InputStream sourceStream, final int maxLinks,
final long maxBytes) throws Parser.Failure{
return parseSource(location, mimeType, charset, TagValency.EVAL, new HashSet<String>(), new VocabularyScraper(), timezoneOffset, depth, contentLength,
sourceStream, maxLinks, maxBytes);
}

279
source/net/yacy/document/parser/sevenzipParser.java
View File

@ -1,279 +0,0 @@
// sevenzipParser.java
// -------------------------------------
// part of YACY
// (C) by Michael Peter Christen; mc@yacy.net
// first published on http://www.anomic.de
// Frankfurt, Germany, 2004
//
// This file ist contributed by Franz Brausze
//
// $LastChangedDate$
// $LastChangedRevision$
// $LastChangedBy$
//
// 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.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.util.Date;
import java.util.Set;
import net.yacy.cora.document.id.AnchorURL;
import net.yacy.cora.document.id.DigestURL;
import net.yacy.cora.document.id.MultiProtocolURL;
import net.yacy.cora.util.ConcurrentLog;
import net.yacy.document.AbstractParser;
import net.yacy.document.Document;
import net.yacy.document.Parser;
import net.yacy.document.TextParser;
import net.yacy.document.VocabularyScraper;
import net.yacy.document.parser.html.TagValency;
import net.yacy.kelondro.util.FileUtils;
import SevenZip.ArchiveExtractCallback;
import SevenZip.IInStream;
import SevenZip.Archive.IInArchive;
import SevenZip.Archive.SevenZipEntry;
import SevenZip.Archive.SevenZip.Handler;
public class sevenzipParser extends AbstractParser implements Parser {
public sevenzipParser() {
super("7zip Archive Parser");
this.SUPPORTED_EXTENSIONS.add("7z");
this.SUPPORTED_MIME_TYPES.add("application/x-7z-compressed");
}
public Document parse(
final DigestURL location,
final String mimeType,
final String charset,
final TagValency defaultValency,
final Set<String> valencySwitchTagNames,
final int timezoneOffset,
final IInStream source) throws Parser.Failure, InterruptedException {
final String filename = location.getFileName();
final Document doc = new Document(
location,
mimeType,
charset,
this,
null,
null,
AbstractParser.singleList(filename.isEmpty() ? location.toTokens() : MultiProtocolURL.unescape(filename)), // title,
null,
null,
null,
null,
0.0d, 0.0d,
(Object)null,
null,
null,
null,
false,
new Date());
Handler archive;
AbstractParser.log.fine("opening 7zip archive...");
try {
archive = new Handler(source);
} catch (final IOException e) {
throw new Parser.Failure("error opening 7zip archive: " + e.getMessage(), location);
}
final SZParserExtractCallback aec = new SZParserExtractCallback(AbstractParser.log, archive, doc, location.getFile(), defaultValency, valencySwitchTagNames, timezoneOffset);
AbstractParser.log.fine("processing archive contents...");
try {
archive.Extract(null, -1, 0, aec);
return doc;
} catch (final IOException e) {
if (e.getCause() instanceof InterruptedException)
throw (InterruptedException)e.getCause();
if (e.getCause() instanceof Parser.Failure)
throw (Parser.Failure)e.getCause();
throw new Parser.Failure(
"error processing 7zip archive at internal file " + aec.getCurrentFilePath() + ": " + e.getMessage(),
location);
} finally {
try { archive.close(); } catch (final IOException e) { }
}
}
public Document parse(
final DigestURL location,
final String mimeType,
final String charset,
final TagValency defaultValency,
final Set<String> valencySwitchTagNames,
final int timezoneOffset,
final byte[] source) throws Parser.Failure, InterruptedException {
return parse(location, mimeType, charset, defaultValency, valencySwitchTagNames, timezoneOffset, new ByteArrayIInStream(source));
}
@Override
public Document[] parse(
final DigestURL location,
final String mimeType,
final String charset,
final TagValency defaultValency,
final Set<String> valencySwitchTagNames,
final VocabularyScraper scraper,
final int timezoneOffset,
final InputStream source) throws Parser.Failure, InterruptedException {
try {
final ByteArrayOutputStream cfos = new ByteArrayOutputStream();
FileUtils.copy(source, cfos);
return new Document[]{parse(location, mimeType, charset, defaultValency, valencySwitchTagNames, timezoneOffset, cfos.toByteArray())};
} catch (final IOException e) {
throw new Parser.Failure("error processing 7zip archive: " + e.getMessage(), location);
}
}
// wrapper class to redirect output of standard ArchiveExtractCallback to serverLog
// and parse the extracted content
private static class SZParserExtractCallback extends ArchiveExtractCallback {
private final ConcurrentLog log;
private ByteArrayOutputStream cfos = null;
private final Document doc;
private final String prefix;
private final TagValency defaultValency;
private Set<String> valencySwitchTagNames;
private final int timezoneOffset;
public SZParserExtractCallback(
final ConcurrentLog logger,
final IInArchive handler,
final Document doc,
final String prefix,
final TagValency defaultValency,
final Set<String> valencySwitchTagNames,
final int timezoneOffset) {
super.Init(handler);
this.log = logger;
this.doc = doc;
this.prefix = prefix;
this.defaultValency = defaultValency;
this.valencySwitchTagNames = valencySwitchTagNames;
this.timezoneOffset = timezoneOffset;
}
@Override
public void PrepareOperation(final int arg0) {
this.extractMode = (arg0 == IInArchive.NExtract_NAskMode_kExtract);
switch (arg0) {
case IInArchive.NExtract_NAskMode_kExtract:
this.log.fine("Extracting " + this.filePath);
break;
case IInArchive.NExtract_NAskMode_kTest:
this.log.fine("Testing " + this.filePath);
break;
case IInArchive.NExtract_NAskMode_kSkip:
this.log.fine("Skipping " + this.filePath);
break;
}
}
@Override
public void SetOperationResult(final int arg0) throws IOException {
if (arg0 != IInArchive.NExtract_NOperationResult_kOK) {
this.NumErrors++;
switch(arg0) {
case IInArchive.NExtract_NOperationResult_kUnSupportedMethod:
throw new IOException("Unsupported Method");
case IInArchive.NExtract_NOperationResult_kCRCError:
throw new IOException("CRC Failed");
case IInArchive.NExtract_NOperationResult_kDataError:
throw new IOException("Data Error");
default:
// throw new IOException("Unknown Error");
}
} else try {
if (this.cfos != null) {
// parse the file
Document[] theDocs;
// workaround for relative links in file, normally '#' shall be used behind the location, see
// below for reversion of the effects
final AnchorURL url = AnchorURL.newAnchor(this.doc.dc_source(), this.prefix + "/" + super.filePath);
final String mime = TextParser.mimeOf(super.filePath.substring(super.filePath.lastIndexOf('.') + 1));
theDocs = TextParser.parseSource(url, mime, null,this.defaultValency, this.valencySwitchTagNames, new VocabularyScraper(), timezoneOffset, this.doc.getDepth() + 1, this.cfos.toByteArray());
this.doc.addSubDocuments(theDocs);
}
} catch (final Exception e) {
final IOException ex = new IOException("error parsing extracted content of " + super.filePath + ": " + e.getMessage());
ex.initCause(e);
throw ex;
}
}
@Override
public OutputStream GetStream(final int index, final int askExtractMode) throws IOException {
final SevenZipEntry item = super.archiveHandler.getEntry(index);
super.filePath = item.getName();
this.cfos = (item.isDirectory()) ? null : new ByteArrayOutputStream();
return this.cfos;
}
public String getCurrentFilePath() {
return super.filePath;
}
}
private static class SeekableByteArrayInputStream extends ByteArrayInputStream {
public SeekableByteArrayInputStream(final byte[] buf) { super(buf); }
public SeekableByteArrayInputStream(final byte[] buf, final int off, final int len) { super(buf, off, len); }
public int getPosition() { return super.pos; }
public void seekRelative(final int offset) { seekAbsolute(super.pos + offset); }
public void seekAbsolute(final int offset) {
if (offset > super.count)
throw new IndexOutOfBoundsException(Integer.toString(offset));
super.pos = offset;
}
}
private static class ByteArrayIInStream extends IInStream {
private final SeekableByteArrayInputStream sbais;
public ByteArrayIInStream(final byte[] buffer) {
this.sbais = new SeekableByteArrayInputStream(buffer);
}
@Override
public long Seek(final long offset, final int origin) {
switch (origin) {
case STREAM_SEEK_SET: this.sbais.seekAbsolute((int)offset); break;
case STREAM_SEEK_CUR: this.sbais.seekRelative((int)offset); break;
}
return this.sbais.getPosition();
}
@Override
public int read() throws IOException {
return this.sbais.read();
}
@Override
public int read(final byte[] b, final int off, final int len) throws IOException {
return this.sbais.read(b, off, len);
}
}
}