SolrIndexedText.java

Go to the documentation of this file.

/*
 * Autopsy Forensic Browser
 *
 * Copyright 2011-2023 Basis Technology Corp.
 * Contact: carrier <at> sleuthkit <dot> org
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */
package org.sleuthkit.autopsy.keywordsearch;

import java.util.logging.Level;
import org.apache.solr.client.solrj.SolrServerException;
import org.openide.util.NbBundle;
import org.sleuthkit.autopsy.coreutils.EscapeUtil;
import org.sleuthkit.autopsy.coreutils.Logger;
import org.sleuthkit.datamodel.AbstractFile;
import org.sleuthkit.datamodel.BlackboardArtifact;
import org.sleuthkit.datamodel.Content;
import org.sleuthkit.datamodel.TskData;

class SolrIndexedText implements ExtractedText {

    private int numPages = 0;
    private int currentPage = 0;
    private boolean hasChunks = false;
    private final Content content;
    private final BlackboardArtifact blackboardArtifact;
    private final long objectId;
    private static final Logger logger = Logger.getLogger(SolrIndexedText.class.getName());

    SolrIndexedText(Content content, long objectId) {
        this.content = content;
        this.blackboardArtifact = null;
        this.objectId = objectId;
        initialize();
    }

    SolrIndexedText(BlackboardArtifact bba, long objectId) {
        this.content = null;
        this.blackboardArtifact = bba;
        this.objectId = objectId;
        initialize();
    }

    public long getObjectId() {
        return this.objectId;
    }

    @Override
    public int getCurrentPage() {
        return this.currentPage;
    }

    @Override
    public boolean hasNextPage() {
        return currentPage < numPages;
    }

    @Override
    public boolean hasPreviousPage() {
        return currentPage > 1;
    }

    @Override
    public int nextPage() {
        if (!hasNextPage()) {
            throw new IllegalStateException(
                    NbBundle.getMessage(this.getClass(), "ExtractedContentViewer.nextPage.exception.msg"));
        }
        ++currentPage;
        return currentPage;
    }

    @Override
    public int previousPage() {
        if (!hasPreviousPage()) {
            throw new IllegalStateException(
                    NbBundle.getMessage(this.getClass(), "ExtractedContentViewer.previousPage.exception.msg"));
        }
        --currentPage;
        return currentPage;
    }

    @Override
    public boolean hasNextItem() {
        throw new UnsupportedOperationException(
                NbBundle.getMessage(this.getClass(), "ExtractedContentViewer.hasNextItem.exception.msg"));
    }

    @Override
    public boolean hasPreviousItem() {
        throw new UnsupportedOperationException(
                NbBundle.getMessage(this.getClass(), "ExtractedContentViewer.hasPreviousItem.exception.msg"));
    }

    @Override
    public int nextItem() {
        throw new UnsupportedOperationException(
                NbBundle.getMessage(this.getClass(), "ExtractedContentViewer.nextItem.exception.msg"));
    }

    @Override
    public int previousItem() {
        throw new UnsupportedOperationException(
                NbBundle.getMessage(this.getClass(), "ExtractedContentViewer.previousItem.exception.msg"));
    }

    @Override
    public int currentItem() {
        throw new UnsupportedOperationException(
                NbBundle.getMessage(this.getClass(), "ExtractedContentViewer.currentItem.exception.msg"));
    }

    @Override
    public String getText() {
        try {
            if (this.content != null) {
                return getContentText(currentPage, hasChunks);
            } else if (this.blackboardArtifact != null) {
                return getArtifactText();
            }
        } catch (SolrServerException | NoOpenCoreException ex) {
            logger.log(Level.SEVERE, "Couldn't get extracted text", ex); //NON-NLS
        }
        return Bundle.ExtractedText_errorMessage_errorGettingText();
    }

    @NbBundle.Messages({
        "SolrIndexedText.FileText=File Text",
        "SolrIndexedText.ResultText=Result Text"})
    @Override
    public String toString() {
        if (null != content) {
            return Bundle.SolrIndexedText_FileText();
        } else {
            return Bundle.SolrIndexedText_ResultText();
        }
    }

    @Override
    public boolean isSearchable() {
        return false;
    }

    @Override
    public String getAnchorPrefix() {
        return "";
    }

    @Override
    public int getNumberHits() {
        return 0;
    }

    @Override
    public int getNumberPages() {
        return numPages;
    }

    private void initialize() {
        final Server solrServer = KeywordSearch.getServer();

        try {
            //add to page tracking if not there yet             
            numPages = solrServer.queryNumFileChunks(this.objectId);
            if (numPages == 0) {
                numPages = 1;
                hasChunks = false;
            } else {
                hasChunks = true;
            }
        } catch (KeywordSearchModuleException | NoOpenCoreException ex) {
            logger.log(Level.SEVERE, "Could not get number of chunks: ", ex); //NON-NLS         
        }
    }

    private String getContentText(int currentPage, boolean hasChunks) throws NoOpenCoreException, SolrServerException {
        final Server solrServer = KeywordSearch.getServer();

        if (hasChunks == false) {
            //if no chunks, it is safe to assume there is no text content
            //because we are storing extracted text in chunks only
            //and the non-chunk stores meta-data only
            String msg = null;

            if (content instanceof AbstractFile) {
                //we know it's AbstractFile, but do quick check to make sure if we index other objects in future
                boolean isKnown = TskData.FileKnown.KNOWN.equals(((AbstractFile) content).getKnown());
                if (isKnown && KeywordSearchSettings.getSkipKnown()) {
                    msg = Bundle.ExtractedText_warningMessage_knownFile();
                }
            }
            if (msg == null) {
                msg = Bundle.ExtractedText_warningMessage_noTextAvailable();
            }
            return msg;
        }

        int chunkId = currentPage;
        //not cached
        String indexedText = solrServer.getSolrContent(this.objectId, chunkId);
        if (indexedText == null) {
            if (content instanceof AbstractFile) {
                return Bundle.ExtractedText_errorMessage_errorGettingText();
            } else {
                return Bundle.ExtractedText_warningMessage_noTextAvailable();
            }
        } else if (indexedText.isEmpty()) {
            return Bundle.ExtractedText_warningMessage_noTextAvailable();
        }

        indexedText = EscapeUtil.escapeHtml(indexedText).trim();
        StringBuilder sb = new StringBuilder(indexedText.length() + 20);
        sb.append("<pre>").append(indexedText).append("</pre>"); //NON-NLS
        return sb.toString();
    }

    private String getArtifactText() throws NoOpenCoreException, SolrServerException {
        String indexedText = KeywordSearch.getServer().getSolrContent(this.objectId, 1);
        if (indexedText == null || indexedText.isEmpty()) {
            return Bundle.ExtractedText_errorMessage_errorGettingText();
        }

        indexedText = EscapeUtil.escapeHtml(indexedText).trim();
        StringBuilder sb = new StringBuilder(indexedText.length() + 20);
        sb.append("<pre>").append(indexedText).append("</pre>"); //NON-NLS

        return sb.toString();
    }

}