PlainAnalyzer.java revision 20bc00e4946cb455e11b148ae09f8a3c8376318d
/*
* CDDL HEADER START
*
* The contents of this file are subject to the terms of the
* Common Development and Distribution License (the "License").
* You may not use this file except in compliance with the License.
*
* See LICENSE.txt included in this distribution for the specific
* language governing permissions and limitations under the License.
*
* When distributing Covered Code, include this CDDL HEADER in each
* file and include the License file at LICENSE.txt.
* If applicable, add the following below this CDDL HEADER, with the
* fields enclosed by brackets "[]" replaced with your own identifying
* information: Portions Copyright [yyyy] [name of copyright owner]
*
* CDDL HEADER END
*/
/*
* Copyright (c) 2005, 2013, Oracle and/or its affiliates. All rights reserved.
*/
package org.opensolaris.opengrok.analysis.plain;
import java.io.CharArrayReader;
import java.io.IOException;
import java.io.Reader;
import java.io.Writer;
import java.util.Arrays;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.StoredField;
import org.apache.lucene.document.TextField;
import org.opensolaris.opengrok.analysis.Definitions;
import org.opensolaris.opengrok.analysis.ExpandTabsReader;
import org.opensolaris.opengrok.analysis.FileAnalyzerFactory;
import org.opensolaris.opengrok.analysis.Hash2Tokenizer;
import org.opensolaris.opengrok.analysis.TextAnalyzer;
import org.opensolaris.opengrok.configuration.Project;
import org.opensolaris.opengrok.history.Annotation;
/**
* Analyzer for plain text files Created on September 21, 2005
*
* @author Chandan
*/
public class PlainAnalyzer extends TextAnalyzer {
private char[] content;
private int len;
protected PlainXref xref = new PlainXref((Reader) null);
protected Definitions defs;
/**
* Creates a new instance of PlainAnalyzer
*/
protected PlainAnalyzer(FileAnalyzerFactory factory) {
super(factory);
content = new char[64 * 1024];
len = 0;
}
@Override
public void analyze(Document doc, Reader in) throws IOException {
Reader inReader =
ExpandTabsReader.wrap(in, project);
len = 0;
do {
int rbytes = inReader.read(content, len, content.length - len);
if (rbytes >= 0) {
if (rbytes == (content.length - len)) {
content = Arrays.copyOf(content, content.length * 2);
}
len += rbytes;
} else {
break;
}
} while (true);
doc.add(new TextField("full", getContentReader()));
String fullpath = doc.get("fullpath");
if (fullpath != null && ctags != null) {
defs = ctags.doCtags(fullpath + "\n");
if (defs != null && defs.numberOfSymbols() > 0) {
doc.add(new TextField("defs", new Hash2Tokenizer(defs.getSymbols())));
doc.add(new TextField("refs", getContentReader()));
byte[] tags = defs.serialize();
doc.add(new StoredField("tags", tags));
}
}
}
@Override
public TokenStreamComponents createComponents(String fieldName, Reader reader) {
if ("refs".equals(fieldName)) {
return new TokenStreamComponents(new PlainSymbolTokenizer(reader));
}
return super.createComponents(fieldName, reader);
}
/**
* Get a reader that reads from the {@link #content} array.
*/
protected Reader getContentReader() {
return new CharArrayReader(content, 0, len);
}
/**
* Write a cross referenced HTML file.
*
* @param out Writer to write HTML cross-reference
*/
@Override
public void writeXref(Writer out) throws IOException {
xref.reInit(getContentReader());
xref.project = project;
xref.write(out);
}
/**
* Write a cross referenced HTML file reads the source from in
*
* @param in Input source
* @param out Output xref writer
* @param defs definitions for the file (could be null)
* @param annotation annotation for the file (could be null)
*/
static void writeXref(Reader in, Writer out, Definitions defs, Annotation annotation, Project project) throws IOException {
PlainXref xref = new PlainXref(in);
xref.annotation = annotation;
xref.project = project;
xref.setDefs(defs);
xref.write(out);
}
}