From 318917bcc65b386dd7d49a249a8e38ad892d958f Mon Sep 17 00:00:00 2001 From: "eugene.livis" Date: Wed, 7 Jun 2023 15:37:30 -0400 Subject: [PATCH] Renamed interface and classes to more appropriate name --- .../autopsy/keywordsearch/AccountsText.java | 4 +- .../keywordsearch/Bundle.properties-MERGED | 18 +- .../keywordsearch/ExtractedContentPanel.form | 6 +- .../keywordsearch/ExtractedContentPanel.java | 30 +- .../autopsy/keywordsearch/ExtractedText.java | 306 +++++++----------- .../keywordsearch/ExtractedTextViewer.java | 32 +- .../FileReaderExtractedText.java | 234 ++++++++++++++ .../keywordsearch/HighlightedText.java | 6 +- .../autopsy/keywordsearch/IndexedText.java | 148 --------- .../keywordsearch/SolrIndexedText.java | 16 +- 10 files changed, 402 insertions(+), 398 deletions(-) mode change 100755 => 100644 KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/ExtractedText.java create mode 100755 KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/FileReaderExtractedText.java delete mode 100644 KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/IndexedText.java diff --git a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/AccountsText.java b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/AccountsText.java index 00d5670151..73a824a942 100644 --- a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/AccountsText.java +++ b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/AccountsText.java @@ -50,7 +50,7 @@ import org.sleuthkit.datamodel.TskCoreException; * and HighlightedText are very similar and could probably use some refactoring * to reduce code duplication. */ -class AccountsText implements IndexedText { +class AccountsText implements ExtractedText { private static final Logger logger = Logger.getLogger(AccountsText.class.getName()); private static final boolean DEBUG = (Version.getBuildType() == Version.Type.DEVELOPMENT); @@ -312,7 +312,7 @@ class AccountsText implements IndexedText { return "
" + highlightedText + "
"; //NON-NLS } catch (Exception ex) { logger.log(Level.SEVERE, "Error getting highlighted text for Solr doc id " + this.solrObjectId + ", chunkID " + this.currentPage, ex); //NON-NLS - return Bundle.IndexedText_errorMessage_errorGettingText(); + return Bundle.ExtractedText_errorMessage_errorGettingText(); } } diff --git a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/Bundle.properties-MERGED b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/Bundle.properties-MERGED index c05fd15c02..2ff50a4048 100755 --- a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/Bundle.properties-MERGED +++ b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/Bundle.properties-MERGED @@ -15,6 +15,7 @@ ExtractAllTermsReport.error.noOpenCase=No currently open case. ExtractAllTermsReport.export.error=Error During Unique Word Extraction ExtractAllTermsReport.exportComplete=Unique Word Extraction Complete ExtractAllTermsReport.getName.text=Extract Unique Words +# {0} - Number of extracted terms ExtractAllTermsReport.numberExtractedTerms=Extracted {0} terms... ExtractAllTermsReport.search.ingestInProgressBody=Keyword Search Ingest is currently running.
Not all files have been indexed and unique word extraction might yield incomplete results.
Do you want to proceed with unique word extraction anyway? ExtractAllTermsReport.search.noFilesInIdxMsg=No files are in index yet. If Solr keyword search indexing and Solr indexing were enabled, wait for ingest to complete. @@ -22,13 +23,15 @@ ExtractAllTermsReport.search.noFilesInIdxMsg2=No files are in index yet. Re-inge ExtractAllTermsReport.search.searchIngestInProgressTitle=Keyword Search Ingest in Progress ExtractAllTermsReport.startExport=Starting Unique Word Extraction ExtractedContentPanel.setMarkup.panelTxt=Loading text... Please wait +# {0} - Content name ExtractedContentPanel.SetMarkup.progress.loading=Loading text for {0} +ExtractedText.errorMessage.errorGettingText=Error retrieving text. +ExtractedText.FileText=File Text +ExtractedText.warningMessage.knownFile=This file is a known file (based on MD5 hash) and does not have indexed text. +ExtractedText.warningMessage.noTextAvailable=No text available for this file. GlobalEditListPanel.editKeyword.title=Edit Keyword GlobalEditListPanel.warning.text=Boundary characters ^ and $ do not match word boundaries. Consider\nreplacing with an explicit list of boundary characters, such as [ \\.,] GlobalEditListPanel.warning.title=Warning -IndexedText.errorMessage.errorGettingText=Error retrieving indexed text. -IndexedText.warningMessage.knownFile=This file is a known file (based on MD5 hash) and does not have indexed text. -IndexedText.warningMessage.noTextAvailable=No indexed text for this file. KeywordSearchGlobalSearchSettingsPanel.customizeComponents.windowsLimitedOCR=Only process images which are over 100KB in size or extracted from a document. (Beta) (Requires Windows 64-bit) KeywordSearchGlobalSearchSettingsPanel.customizeComponents.windowsOCR=Enable Optical Character Recognition (OCR) (Requires Windows 64-bit) KeywordSearchGlobalSettingsPanel.Title=Global Keyword Search Settings @@ -49,7 +52,7 @@ KeywordSearchResultFactory.createNodeForKey.noResultsFound.text=No results found KeywordSearchResultFactory.query.exception.msg=Could not perform the query OpenIDE-Module-Display-Category=Ingest Module -OpenIDE-Module-Long-Description=Keyword Search ingest module.\n\nThe module indexes files found in the disk image at ingest time.\nIt then periodically runs the search on the indexed files using one or more keyword lists (containing pure words and/or regular expressions) and posts results.\n\nThe module also contains additional tools integrated in the main GUI, such as keyword list configuration, keyword search bar in the top-right corner, extracted text viewer and search results viewer showing highlighted keywords found. +OpenIDE-Module-Long-Description=Keyword Search ingest module.\n\nThe module indexes files found in the disk image at ingest time.\nIt then periodically runs the search on the indexed files using one or more keyword lists (containing pure words and/or regular expressions) and posts results.\n\n\The module also contains additional tools integrated in the main GUI, such as keyword list configuration, keyword search bar in the top-right corner, extracted text viewer and search results viewer showing highlighted keywords found. OpenIDE-Module-Name=KeywordSearch OptionsCategory_Name_KeywordSearchOptions=Keyword Search OptionsCategory_Keywords_KeywordSearchOptions=Keyword Search @@ -91,7 +94,7 @@ AbstractKeywordSearchPerformer.search.emptyKeywordErrorBody=Keyword list is empt AbstractKeywordSearchPerformer.search.noFilesInIdxMsg=No files are in index yet.
If Solr keyword search indexing was enabled, wait for ingest to complete AbstractKeywordSearchPerformer.search.noFilesIdxdMsg=No files were indexed.
Re-ingest the image with the Keyword Search Module and Solr indexing enabled. ExtractedContentViewer.toolTip=Displays extracted text from files and keyword-search results. Requires Keyword Search ingest to be run on a file to activate this viewer. -ExtractedContentViewer.getTitle=Indexed Text +ExtractedContentViewer.getTitle=Extracted Text HighlightedMatchesSource.toString=Search Results Installer.reportPortError=Indexing server port {0} is not available. Check if your security software does not block {1} and consider changing {2} in {3} property file in the application user folder. Then try rebooting your system if another process was causing the conflict. Installer.reportStopPortError=Indexing server stop port {0} is not available. Consider changing {1} in {2} property file in the application user folder. @@ -137,8 +140,6 @@ KeywordSearchIngestModule.init.onlyIdxKwSkipMsg=Only indexing will be done and k KeywordSearchIngestModule.doInBackGround.displayName=Periodic Keyword Search KeywordSearchIngestModule.doInBackGround.finalizeMsg=Finalizing KeywordSearchIngestModule.doInBackGround.pendingMsg=(Pending) -RawText.FileText=File Text -RawText.ResultText=Result Text SearchRunner.doInBackGround.cancelMsg=(Cancelling...) KeywordSearchIngestModule.postIndexSummary.knowFileHeaderLbl=Files with known types KeywordSearchIngestModule.postIndexSummary.fileGenStringsHead=Files with general strings extracted @@ -224,6 +225,7 @@ KeywordSearchSettings.properties_options.text={0}_Options KeywordSearchSettings.propertiesNSRL.text={0}_NSRL KeywordSearchSettings.propertiesScripts.text={0}_Scripts NoOpenCoreException.err.noOpenSorlCore.msg=No currently open Solr core. +# {0} - colelction name Server.deleteCore.exception.msg=Failed to delete Solr colelction {0} Server.exceptionMessage.unableToBackupCollection=Unable to backup Solr collection Server.exceptionMessage.unableToCreateCollection=Unable to create Solr collection @@ -336,6 +338,8 @@ GlobalListsManagementPanel.copyListButton.text=Copy List GlobalListsManagementPanel.renameListButton.text=Edit List Name GlobalEditListPanel.editWordButton.text=Edit Keyword SolrConnectionCheck.Port=Invalid port number. +SolrIndexedText.FileText=File Text +SolrIndexedText.ResultText=Result Text SolrSearch.checkingForLatestIndex.msg=Looking for text index with latest Solr and schema version SolrSearch.complete.msg=Text index successfully opened SolrSearch.creatingNewIndex.msg=Creating new text index diff --git a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/ExtractedContentPanel.form b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/ExtractedContentPanel.form index 13e535f4ed..c2079a204f 100644 --- a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/ExtractedContentPanel.form +++ b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/ExtractedContentPanel.form @@ -565,7 +565,7 @@ - + @@ -579,7 +579,7 @@ - + @@ -622,4 +622,4 @@ - + \ No newline at end of file diff --git a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/ExtractedContentPanel.java b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/ExtractedContentPanel.java index 41d384d559..0a441ab3b1 100644 --- a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/ExtractedContentPanel.java +++ b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/ExtractedContentPanel.java @@ -396,7 +396,7 @@ class ExtractedContentPanel extends javax.swing.JPanel implements ResizableTextP textSourcePanel.add(jLabel1); textSourcePanel.add(fillerSmall12); - sourceComboBox.setModel(new javax.swing.DefaultComboBoxModel()); + sourceComboBox.setModel(new javax.swing.DefaultComboBoxModel()); sourceComboBox.setMaximumSize(new java.awt.Dimension(150, 32767)); sourceComboBox.setMinimumSize(new java.awt.Dimension(150, 25)); sourceComboBox.setPreferredSize(new java.awt.Dimension(150, 25)); @@ -443,7 +443,7 @@ class ExtractedContentPanel extends javax.swing.JPanel implements ResizableTextP private javax.swing.JLabel pagesLabel; private javax.swing.JPopupMenu rightClickMenu; private javax.swing.JMenuItem selectAllMenuItem; - private javax.swing.JComboBox sourceComboBox; + private javax.swing.JComboBox sourceComboBox; private javax.swing.JPanel textSourcePanel; private javax.swing.JPanel zoomPanel; // End of variables declaration//GEN-END:variables @@ -457,10 +457,10 @@ class ExtractedContentPanel extends javax.swing.JPanel implements ResizableTextP * default) * * @param contentName The name of the content to be displayed - * @param sources A list of IndexedText that have different 'views' of - * the content. + * @param sources A list of ExtractedText that have different 'views' of + the content. */ - final void setSources(String contentName, List sources) { + final void setSources(String contentName, List sources) { this.lastKnownAnchor = null; this.contentName = contentName; setPanelText(null, false); @@ -480,8 +480,8 @@ class ExtractedContentPanel extends javax.swing.JPanel implements ResizableTextP * * @return currently selected Source */ - public IndexedText getSelectedSource() { - return (IndexedText) sourceComboBox.getSelectedItem(); + public ExtractedText getSelectedSource() { + return (ExtractedText) sourceComboBox.getSelectedItem(); } private void setPanelText(String text, boolean detectDirection) { @@ -636,7 +636,7 @@ class ExtractedContentPanel extends javax.swing.JPanel implements ResizableTextP * * @param source the selected source */ - void updateControls(IndexedText source) { + void updateControls(ExtractedText source) { updatePageControls(source); updateSearchControls(source); } @@ -646,7 +646,7 @@ class ExtractedContentPanel extends javax.swing.JPanel implements ResizableTextP * * @param source selected source */ - void updatePageControls(IndexedText source) { + void updatePageControls(ExtractedText source) { if (source == null) { enableNextPageControl(false); enablePrevPageControl(false); @@ -668,7 +668,7 @@ class ExtractedContentPanel extends javax.swing.JPanel implements ResizableTextP * * @param source selected source */ - void updateSearchControls(IndexedText source) { + void updateSearchControls(ExtractedText source) { //setup search controls if (source != null && source.isSearchable()) { updateCurrentMatchDisplay(source.currentItem()); @@ -688,7 +688,7 @@ class ExtractedContentPanel extends javax.swing.JPanel implements ResizableTextP * * @param source */ - private void scrollToCurrentHit(final IndexedText source) { + private void scrollToCurrentHit(final ExtractedText source) { if (source == null || !source.isSearchable()) { return; } @@ -704,7 +704,7 @@ class ExtractedContentPanel extends javax.swing.JPanel implements ResizableTextP * be invoked from GUI thread only. */ @NbBundle.Messages("ExtractedContentPanel.setMarkup.panelTxt=Loading text... Please wait") - private void setMarkup(IndexedText source) { + private void setMarkup(ExtractedText source) { setPanelText(Bundle.ExtractedContentPanel_setMarkup_panelTxt(), false); new SetMarkupWorker(contentName, source).execute(); } @@ -718,11 +718,11 @@ class ExtractedContentPanel extends javax.swing.JPanel implements ResizableTextP private final String contentName; - private final IndexedText source; + private final ExtractedText source; private ProgressHandle progress; - SetMarkupWorker(String contentName, IndexedText source) { + SetMarkupWorker(String contentName, ExtractedText source) { this.contentName = contentName; this.source = source; } @@ -753,7 +753,7 @@ class ExtractedContentPanel extends javax.swing.JPanel implements ResizableTextP } } catch (InterruptedException | CancellationException | ExecutionException ex) { logger.log(Level.SEVERE, "Error getting marked up text", ex); //NON-NLS - setPanelText(Bundle.IndexedText_errorMessage_errorGettingText(), true); + setPanelText(Bundle.ExtractedText_errorMessage_errorGettingText(), true); } updateControls(source); diff --git a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/ExtractedText.java b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/ExtractedText.java old mode 100755 new mode 100644 index c0e4e5f6c4..cf1a12e19c --- a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/ExtractedText.java +++ b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/ExtractedText.java @@ -1,7 +1,7 @@ /* * Autopsy Forensic Browser * - * Copyright 2023 Basis Technology Corp. + * Copyright 2011-2023 Basis Technology Corp. * Contact: carrier sleuthkit org * * Licensed under the Apache License, Version 2.0 (the "License"); @@ -18,217 +18,131 @@ */ package org.sleuthkit.autopsy.keywordsearch; -import com.google.common.io.CharSource; -import java.io.BufferedReader; -import java.io.IOException; -import java.io.Reader; -import java.util.HashMap; -import java.util.Map; -import java.util.logging.Level; import org.openide.util.NbBundle; -import org.sleuthkit.autopsy.coreutils.EscapeUtil; -import org.sleuthkit.autopsy.coreutils.Logger; -import org.sleuthkit.autopsy.textextractors.TextExtractor; -import org.sleuthkit.autopsy.textextractors.TextExtractorFactory; -import org.sleuthkit.datamodel.AbstractFile; /** - * A "source" for abstractFile viewer that displays "raw" extracted text for a - * file. Only supports file types for which there are text extractors. Uses - * chunking algorithm used by KeywordSearchIngestModule. The readers used in - * chunking don't have ability to go backwards or to fast forward to a specific - * offset. Therefore there is no way to scroll pages back, or to determine how - * many total pages there are. + * Interface to provide HTML text to display in ExtractedContentViewer. There is + * a SOLR implementation of this that interfaces with SOLR to highlight the + * keyword hits and a version that does not do markup so that you can simply + * view the stored text. There is also an implementation that extracts text from + * a file using one os TextExtractors. */ -class ExtractedText implements IndexedText { - - private int numPages = 0; - private int currentPage = 0; - private final AbstractFile abstractFile; - private Chunker chunker = null; - private static final Logger logger = Logger.getLogger(ExtractedText.class.getName()); +@NbBundle.Messages({ + "ExtractedText.errorMessage.errorGettingText=Error retrieving text.", + "ExtractedText.warningMessage.knownFile=This file is a known file (based on MD5 hash) and does not have indexed text.", + "ExtractedText.warningMessage.noTextAvailable=No text available for this file." +}) +interface ExtractedText { /** - * Construct a new ExtractedText object for the given abstract file. + * @return text optionally marked up with the subset of HTML that Swing + * components can handle in their setText() method. * - * @param file Abstract file. */ - ExtractedText(AbstractFile file) throws TextExtractorFactory.NoTextExtractorFound, TextExtractor.InitReaderException { - this.abstractFile = file; - this.numPages = -1; // We don't know how many pages there are until we reach end of the document - - TextExtractor extractor = TextExtractorFactory.getExtractor(abstractFile, null); - - Map extractedMetadata = new HashMap<>(); - Reader sourceReader = getTikaOrTextExtractor(extractor, abstractFile, extractedMetadata); - - //Get a reader for the content of the given source - BufferedReader reader = new BufferedReader(sourceReader); - this.chunker = new Chunker(reader); - } - - @Override - public int getCurrentPage() { - return this.currentPage; - } - - @Override - public boolean hasNextPage() { - if (chunker.hasNext()) { - return true; - } - return false; - } - - @Override - public boolean hasPreviousPage() { - return false; - } - - @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 { - return getContentText(currentPage); - } catch (Exception ex) { - logger.log(Level.SEVERE, "Couldn't get extracted text", ex); //NON-NLS - } - return Bundle.IndexedText_errorMessage_errorGettingText(); - } - - @NbBundle.Messages({ - "ExtractedText.FileText=File Text"}) - @Override - public String toString() { - return Bundle.ExtractedText_FileText(); - } - - @Override - public boolean isSearchable() { - return false; - } - - @Override - public String getAnchorPrefix() { - return ""; - } - - @Override - public int getNumberHits() { - return 0; - } - - @Override - public int getNumberPages() { - return numPages; - } + String getText(); /** - * Extract text from abstractFile * - * @param currentPage currently used page - * - * @return the extracted text + * @return true if text is marked to be searchable */ - private String getContentText(int currentPage) throws TextExtractor.InitReaderException, IOException, Exception { - String indexedText; - if (chunker.hasNext()) { - Chunker.Chunk chunk = chunker.next(); - chunk.setChunkId(currentPage); + boolean isSearchable(); - if (chunker.hasException()) { - logger.log(Level.WARNING, "Error chunking content from " + abstractFile.getId() + ": " + abstractFile.getName(), chunker.getException()); - throw chunker.getException(); - } + /** + * If searchable text, returns prefix of anchor, otherwise return empty + * string + * + * @return + */ + String getAnchorPrefix(); - indexedText = chunk.toString(); - } else { - return Bundle.IndexedText_errorMessage_errorGettingText(); - } + /** + * if searchable text, returns number of hits found and encoded in the text + * + * @return + */ + int getNumberHits(); - indexedText = EscapeUtil.escapeHtml(indexedText).trim(); - StringBuilder sb = new StringBuilder(indexedText.length() + 20); - sb.append("
").append(indexedText).append("
"); //NON-NLS - return sb.toString(); - } + /** + * @return title of text source + */ + @Override + String toString(); - private Reader getTikaOrTextExtractor(TextExtractor extractor, AbstractFile aFile, - Map extractedMetadata) throws TextExtractor.InitReaderException { + /** + * get number pages/chunks + * + * @return number pages + */ + int getNumberPages(); - Reader fileText = extractor.getReader(); - Reader finalReader; - try { - Map metadata = extractor.getMetadata(); - if (!metadata.isEmpty()) { - // save the metadata map to use after this method is complete. - extractedMetadata.putAll(metadata); - } - CharSource formattedMetadata = KeywordSearchIngestModule.getMetaDataCharSource(metadata); - //Append the metadata to end of the file text - finalReader = CharSource.concat(new CharSource() { - //Wrap fileText reader for concatenation - @Override - public Reader openStream() throws IOException { - return fileText; - } - }, formattedMetadata).openStream(); - } catch (IOException ex) { - logger.log(Level.WARNING, String.format("Could not format extracted metadata for file %s [id=%d]", - aFile.getName(), aFile.getId()), ex); - //Just send file text. - finalReader = fileText; - } - //divide into chunks - return finalReader; - } + /** + * get the current page number + * + * @return current page number + */ + int getCurrentPage(); + + /** + * Check if has next page + * + * @return true, if next page exists in the source + */ + boolean hasNextPage(); + + /** + * Move to next page + * + * @return the new page number + */ + int nextPage(); + + /** + * Check if has previous page + * + * @return true, if previous page exists in the source + */ + boolean hasPreviousPage(); + + /** + * Move to previous page + * + * @return the new page number + */ + int previousPage(); + + /** + * Check if has next searchable item + * + * @return true, if next item exists in the source + */ + boolean hasNextItem(); + + /** + * Move to next item + * + * @return the new item number + */ + int nextItem(); + + /** + * Check if has previous item + * + * @return true, if previous item exists in the source + */ + boolean hasPreviousItem(); + + /** + * Move to previous item + * + * @return the new item number + */ + int previousItem(); + + /** + * Get the current item number, do not change anything + * + * @return the current item number + */ + int currentItem(); } diff --git a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/ExtractedTextViewer.java b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/ExtractedTextViewer.java index 3471e4d055..67f260485d 100644 --- a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/ExtractedTextViewer.java +++ b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/ExtractedTextViewer.java @@ -67,7 +67,7 @@ public class ExtractedTextViewer implements TextViewer { private ExtractedContentPanel panel; private volatile Node currentNode = null; - private IndexedText currentSource = null; + private ExtractedText currentSource = null; private FileTypeDetector fileTypeDetector = null; // cache of last 10 solrHasFullyIndexedContent() requests sent to Solr. @@ -118,7 +118,7 @@ public class ExtractedTextViewer implements TextViewer { * Assemble a collection of all of the indexed text "sources" for the * node. */ - List sources = new ArrayList<>(); + List sources = new ArrayList<>(); Lookup nodeLookup = node.getLookup(); /** @@ -134,7 +134,7 @@ public class ExtractedTextViewer implements TextViewer { * First, get text with highlighted hits if this node is for a search * result. */ - IndexedText highlightedHitText = null; + ExtractedText highlightedHitText = null; if (adHocQueryResult != null) { /* * The node is an ad hoc search result node. @@ -172,7 +172,7 @@ public class ExtractedTextViewer implements TextViewer { * Next, add the "raw" (not highlighted) text, if any, for any file * associated with the node. */ - IndexedText rawContentText = null; + ExtractedText rawContentText = null; if (file != null) { // see if Solr has fully indexed this file @@ -184,7 +184,7 @@ public class ExtractedTextViewer implements TextViewer { // see if it's a file type for which we can extract text if (ableToExtractTextFromFile(file)) { try { - rawContentText = new ExtractedText(file); + rawContentText = new FileReaderExtractedText(file); sources.add(rawContentText); } catch (TextExtractorFactory.NoTextExtractorFound | TextExtractor.InitReaderException ex) { // do nothing @@ -209,7 +209,7 @@ public class ExtractedTextViewer implements TextViewer { * Finally, add the "raw" (not highlighted) text, if any, for any * artifact associated with the node. */ - IndexedText rawArtifactText = null; + ExtractedText rawArtifactText = null; try { rawArtifactText = getRawArtifactText(artifact); if (rawArtifactText != null) { @@ -229,7 +229,7 @@ public class ExtractedTextViewer implements TextViewer { } // Push the text sources into the panel. - for (IndexedText source : sources) { + for (ExtractedText source : sources) { int currentPage = source.getCurrentPage(); if (currentPage == 0 && source.hasNextPage()) { source.nextPage(); @@ -245,8 +245,8 @@ public class ExtractedTextViewer implements TextViewer { } - private IndexedText getRawArtifactText(BlackboardArtifact artifact) throws TskCoreException, NoCurrentCaseException { - IndexedText rawArtifactText = null; + private ExtractedText getRawArtifactText(BlackboardArtifact artifact) throws TskCoreException, NoCurrentCaseException { + ExtractedText rawArtifactText = null; if (null != artifact) { /* * For keyword hit artifacts, add the text of the artifact that hit, @@ -273,7 +273,7 @@ public class ExtractedTextViewer implements TextViewer { return rawArtifactText; } - static private IndexedText getAccountsText(Content content, Lookup nodeLookup) throws TskCoreException { + static private ExtractedText getAccountsText(Content content, Lookup nodeLookup) throws TskCoreException { /* * get all the credit card artifacts */ @@ -287,7 +287,7 @@ public class ExtractedTextViewer implements TextViewer { } private void scrollToCurrentHit() { - final IndexedText source = panel.getSelectedSource(); + final ExtractedText source = panel.getSelectedSource(); if (source == null || !source.isSearchable()) { return; } @@ -431,10 +431,10 @@ public class ExtractedTextViewer implements TextViewer { * panel hasn't been created yet) * * @param contentName The name of the content to be displayed - * @param sources A list of IndexedText that have different 'views' of - * the content. + * @param sources A list of ExtractedText that have different 'views' of + the content. */ - private void setPanel(String contentName, List sources) { + private void setPanel(String contentName, List sources) { if (panel != null) { panel.setSources(contentName, sources); } @@ -525,7 +525,7 @@ public class ExtractedTextViewer implements TextViewer { @Override public void actionPerformed(ActionEvent e) { - IndexedText source = panel.getSelectedSource(); + ExtractedText source = panel.getSelectedSource(); if (source == null) { // reset panel.updateControls(null); @@ -568,7 +568,7 @@ public class ExtractedTextViewer implements TextViewer { @Override public void actionPerformed(ActionEvent e) { - IndexedText source = panel.getSelectedSource(); + ExtractedText source = panel.getSelectedSource(); final boolean hasPreviousItem = source.hasPreviousItem(); final boolean hasPreviousPage = source.hasPreviousPage(); int indexVal; diff --git a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/FileReaderExtractedText.java b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/FileReaderExtractedText.java new file mode 100755 index 0000000000..0025be94d8 --- /dev/null +++ b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/FileReaderExtractedText.java @@ -0,0 +1,234 @@ +/* + * Autopsy Forensic Browser + * + * Copyright 2023 Basis Technology Corp. + * Contact: carrier sleuthkit 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 com.google.common.io.CharSource; +import java.io.BufferedReader; +import java.io.IOException; +import java.io.Reader; +import java.util.HashMap; +import java.util.Map; +import java.util.logging.Level; +import org.openide.util.NbBundle; +import org.sleuthkit.autopsy.coreutils.EscapeUtil; +import org.sleuthkit.autopsy.coreutils.Logger; +import org.sleuthkit.autopsy.textextractors.TextExtractor; +import org.sleuthkit.autopsy.textextractors.TextExtractorFactory; +import org.sleuthkit.datamodel.AbstractFile; + +/** + * A "source" for abstractFile viewer that displays "raw" extracted text for a + * file. Only supports file types for which there are text extractors. Uses + * chunking algorithm used by KeywordSearchIngestModule. The readers used in + * chunking don't have ability to go backwards or to fast forward to a specific + * offset. Therefore there is no way to scroll pages back, or to determine how + * many total pages there are. + */ +class FileReaderExtractedText implements ExtractedText { + + private int numPages = 0; + private int currentPage = 0; + private final AbstractFile abstractFile; + private Chunker chunker = null; + private static final Logger logger = Logger.getLogger(FileReaderExtractedText.class.getName()); + + /** + * Construct a new ExtractedText object for the given abstract file. + * + * @param file Abstract file. + */ + FileReaderExtractedText(AbstractFile file) throws TextExtractorFactory.NoTextExtractorFound, TextExtractor.InitReaderException { + this.abstractFile = file; + this.numPages = -1; // We don't know how many pages there are until we reach end of the document + + TextExtractor extractor = TextExtractorFactory.getExtractor(abstractFile, null); + + Map extractedMetadata = new HashMap<>(); + Reader sourceReader = getTikaOrTextExtractor(extractor, abstractFile, extractedMetadata); + + //Get a reader for the content of the given source + BufferedReader reader = new BufferedReader(sourceReader); + this.chunker = new Chunker(reader); + } + + @Override + public int getCurrentPage() { + return this.currentPage; + } + + @Override + public boolean hasNextPage() { + if (chunker.hasNext()) { + return true; + } + return false; + } + + @Override + public boolean hasPreviousPage() { + return false; + } + + @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 { + return getContentText(currentPage); + } catch (Exception ex) { + logger.log(Level.SEVERE, "Couldn't get extracted text", ex); //NON-NLS + } + return Bundle.ExtractedText_errorMessage_errorGettingText(); + } + + @NbBundle.Messages({ + "ExtractedText.FileText=File Text"}) + @Override + public String toString() { + return Bundle.ExtractedText_FileText(); + } + + @Override + public boolean isSearchable() { + return false; + } + + @Override + public String getAnchorPrefix() { + return ""; + } + + @Override + public int getNumberHits() { + return 0; + } + + @Override + public int getNumberPages() { + return numPages; + } + + /** + * Extract text from abstractFile + * + * @param currentPage currently used page + * + * @return the extracted text + */ + private String getContentText(int currentPage) throws TextExtractor.InitReaderException, IOException, Exception { + String indexedText; + if (chunker.hasNext()) { + Chunker.Chunk chunk = chunker.next(); + chunk.setChunkId(currentPage); + + if (chunker.hasException()) { + logger.log(Level.WARNING, "Error chunking content from " + abstractFile.getId() + ": " + abstractFile.getName(), chunker.getException()); + throw chunker.getException(); + } + + indexedText = chunk.toString(); + } else { + return Bundle.ExtractedText_errorMessage_errorGettingText(); + } + + indexedText = EscapeUtil.escapeHtml(indexedText).trim(); + StringBuilder sb = new StringBuilder(indexedText.length() + 20); + sb.append("
").append(indexedText).append("
"); //NON-NLS + return sb.toString(); + } + + private Reader getTikaOrTextExtractor(TextExtractor extractor, AbstractFile aFile, + Map extractedMetadata) throws TextExtractor.InitReaderException { + + Reader fileText = extractor.getReader(); + Reader finalReader; + try { + Map metadata = extractor.getMetadata(); + if (!metadata.isEmpty()) { + // save the metadata map to use after this method is complete. + extractedMetadata.putAll(metadata); + } + CharSource formattedMetadata = KeywordSearchIngestModule.getMetaDataCharSource(metadata); + //Append the metadata to end of the file text + finalReader = CharSource.concat(new CharSource() { + //Wrap fileText reader for concatenation + @Override + public Reader openStream() throws IOException { + return fileText; + } + }, formattedMetadata).openStream(); + } catch (IOException ex) { + logger.log(Level.WARNING, String.format("Could not format extracted metadata for file %s [id=%d]", + aFile.getName(), aFile.getId()), ex); + //Just send file text. + finalReader = fileText; + } + //divide into chunks + return finalReader; + } + +} diff --git a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/HighlightedText.java b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/HighlightedText.java index dedc81e35e..43d6b5417c 100644 --- a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/HighlightedText.java +++ b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/HighlightedText.java @@ -52,7 +52,7 @@ import org.sleuthkit.datamodel.TskCoreException; * Highlights hits for a given document. Knows about pages and such for the * content viewer. */ -class HighlightedText implements IndexedText { +class HighlightedText implements ExtractedText { private static final Logger logger = Logger.getLogger(HighlightedText.class.getName()); @@ -475,7 +475,7 @@ class HighlightedText implements IndexedText { return "
" + highlightedContent + "
"; //NON-NLS } catch (TskCoreException | KeywordSearchModuleException | NoOpenCoreException ex) { logger.log(Level.SEVERE, "Error getting highlighted text for Solr doc id " + solrObjectId + ", chunkID " + chunkID + ", highlight query: " + highlightField, ex); //NON-NLS - return Bundle.IndexedText_errorMessage_errorGettingText(); + return Bundle.ExtractedText_errorMessage_errorGettingText(); } } @@ -519,7 +519,7 @@ class HighlightedText implements IndexedText { */ static String attemptManualHighlighting(SolrDocumentList solrDocumentList, String highlightField, Collection keywords) { if (solrDocumentList.isEmpty()) { - return Bundle.IndexedText_errorMessage_errorGettingText(); + return Bundle.ExtractedText_errorMessage_errorGettingText(); } // It doesn't make sense for there to be more than a single document in diff --git a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/IndexedText.java b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/IndexedText.java deleted file mode 100644 index 880d4c8a0c..0000000000 --- a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/IndexedText.java +++ /dev/null @@ -1,148 +0,0 @@ -/* - * Autopsy Forensic Browser - * - * Copyright 2011-2023 Basis Technology Corp. - * Contact: carrier sleuthkit 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 org.openide.util.NbBundle; - -/** - * Interface to provide HTML text to display in ExtractedContentViewer. There is - * a SOLR implementation of this that interfaces with SOLR to highlight the - * keyword hits and a version that does not do markup so that you can simply - * view the stored text. There is also an implementation that extracts text from - * a file using one os TextExtractors. - */ -@NbBundle.Messages({ - "IndexedText.errorMessage.errorGettingText=Error retrieving text.", - "IndexedText.warningMessage.knownFile=This file is a known file (based on MD5 hash) and does not have indexed text.", - "IndexedText.warningMessage.noTextAvailable=No text available for this file." -}) -interface IndexedText { - - /** - * @return text optionally marked up with the subset of HTML that Swing - * components can handle in their setText() method. - * - */ - String getText(); - - /** - * - * @return true if text is marked to be searchable - */ - boolean isSearchable(); - - /** - * If searchable text, returns prefix of anchor, otherwise return empty - * string - * - * @return - */ - String getAnchorPrefix(); - - /** - * if searchable text, returns number of hits found and encoded in the text - * - * @return - */ - int getNumberHits(); - - /** - * @return title of text source - */ - @Override - String toString(); - - /** - * get number pages/chunks - * - * @return number pages - */ - int getNumberPages(); - - /** - * get the current page number - * - * @return current page number - */ - int getCurrentPage(); - - /** - * Check if has next page - * - * @return true, if next page exists in the source - */ - boolean hasNextPage(); - - /** - * Move to next page - * - * @return the new page number - */ - int nextPage(); - - /** - * Check if has previous page - * - * @return true, if previous page exists in the source - */ - boolean hasPreviousPage(); - - /** - * Move to previous page - * - * @return the new page number - */ - int previousPage(); - - /** - * Check if has next searchable item - * - * @return true, if next item exists in the source - */ - boolean hasNextItem(); - - /** - * Move to next item - * - * @return the new item number - */ - int nextItem(); - - /** - * Check if has previous item - * - * @return true, if previous item exists in the source - */ - boolean hasPreviousItem(); - - /** - * Move to previous item - * - * @return the new item number - */ - int previousItem(); - - /** - * Get the current item number, do not change anything - * - * @return the current item number - */ - int currentItem(); - -} diff --git a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/SolrIndexedText.java b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/SolrIndexedText.java index a500c5ef48..32d6fe8fc9 100644 --- a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/SolrIndexedText.java +++ b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/SolrIndexedText.java @@ -32,7 +32,7 @@ import org.sleuthkit.datamodel.TskData; * A "source" for the extracted content viewer that displays "raw" (not * highlighted) Solr indexed text for a file or an artifact. */ -class SolrIndexedText implements IndexedText { +class SolrIndexedText implements ExtractedText { private int numPages = 0; private int currentPage = 0; @@ -152,7 +152,7 @@ class SolrIndexedText implements IndexedText { } catch (SolrServerException | NoOpenCoreException ex) { logger.log(Level.SEVERE, "Couldn't get extracted text", ex); //NON-NLS } - return Bundle.IndexedText_errorMessage_errorGettingText(); + return Bundle.ExtractedText_errorMessage_errorGettingText(); } @NbBundle.Messages({ @@ -236,11 +236,11 @@ class SolrIndexedText implements IndexedText { //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.IndexedText_warningMessage_knownFile(); + msg = Bundle.ExtractedText_warningMessage_knownFile(); } } if (msg == null) { - msg = Bundle.IndexedText_warningMessage_noTextAvailable(); + msg = Bundle.ExtractedText_warningMessage_noTextAvailable(); } return msg; } @@ -250,12 +250,12 @@ class SolrIndexedText implements IndexedText { String indexedText = solrServer.getSolrContent(this.objectId, chunkId); if (indexedText == null) { if (content instanceof AbstractFile) { - return Bundle.IndexedText_errorMessage_errorGettingText(); + return Bundle.ExtractedText_errorMessage_errorGettingText(); } else { - return Bundle.IndexedText_warningMessage_noTextAvailable(); + return Bundle.ExtractedText_warningMessage_noTextAvailable(); } } else if (indexedText.isEmpty()) { - return Bundle.IndexedText_warningMessage_noTextAvailable(); + return Bundle.ExtractedText_warningMessage_noTextAvailable(); } indexedText = EscapeUtil.escapeHtml(indexedText).trim(); @@ -276,7 +276,7 @@ class SolrIndexedText implements IndexedText { private String getArtifactText() throws NoOpenCoreException, SolrServerException { String indexedText = KeywordSearch.getServer().getSolrContent(this.objectId, 1); if (indexedText == null || indexedText.isEmpty()) { - return Bundle.IndexedText_errorMessage_errorGettingText(); + return Bundle.ExtractedText_errorMessage_errorGettingText(); } indexedText = EscapeUtil.escapeHtml(indexedText).trim();